Search

This study is threefold objective. First, a nonlinear one-dimensional steady-state simulation model for hydrogen production from proton exchange membrane water electrolyzer (PEMWE) is established. The model comprehensively addresses activation, diffusion overpotentials and ohmic potential drop, and particularly incorporating Nafion membrane properties in the presence of liquid water. The model is enhanced by analyzing the hydrogen crossover, introducing corresponding diffusion equations to evaluate Faraday efficiency. The model accurately quantifies voltage efficiency, hydrogen production rate and specific energy consumption, and it is validated with published experimental data found in the scientific literature. Second, a variance-based global sensitivity analysis (GSA) on the model, is employed as a metric to assess the impact of operating conditions and material characteristics on three objective functions: the hydrogen production rate; the voltage efficiency and the specific energy consumption. Third, to support the GSA analysis, genetic algorithm (GA) technique is performed to maximize hydrogen production rate while minimizing specific energy consumption. In the course of this novel investigation, it was discerned that the number of cells, the cross-sectional area of the electrolyzer, the current density and temperature all exerted a significant impact on the three objective functions. This combined approach GSA-GA provides a thorough exploration of parameter influences and an efficient optimization strategy for enhancing the model's performance. These findings provide valuable insights that can guide analysis of the performance and the optimization of the PEMWE system. • Detailed modeling of PEM water electrolyzer operations. • PEM water electrolyzer performance defined as H 2 rate, voltage efficiency and energy consumption. • Employed Kendall, Spearman, and Pearson correlation coefficients for the assessment of factors' influence. • Global sensitivity analysis of the performance of PEM water electrolyzer. [ABSTRACT FROM AUTHOR]

This article presents a comprehensive optimization approach for a fuzzy logic-based energy management system (EMS) designed for a fuel cell hybrid electric vehicle (FCHEV) powered by a fuel cell and a battery. The aim is to enhance EMS performance and overall system efficiency by optimizing fuzzy logic parameters using a genetic algorithm (GA). The effectiveness of the proposed strategy is demonstrated through simulations using ADVISOR software and the MATLAB/SIMULINK environment. The optimization process consists of four phases: tuning the membership function types, fuzzy variable ranges, membership function parameters, and rule weights. The proposed method has resulted in a significant improvement in the fitness function, highlighting the high sensitivity of the fuzzy logic system to optimization parameters. The optimized EMS is compared with the original one and a thermostat-based strategy built into ADVISOR. Results show a 28.5% improvement in fuel utilization and a 13% reduction in the low-efficiency operation of the fuel cell system. [Display omitted] • A comprehensive optimization approach for energy management system in FCHEVs. • Simulation environment development with real-time FCHEVs interactive monitoring. • FCHEVs Performances improvement in terms of energy efficiency and management. • FCHEVs Energy losses minimization with robust and efficient decision-making. • Innovative solutions provided to overcome the operating constraints of FCHEVs. [ABSTRACT FROM AUTHOR]

Multimodal perception represents a vital approach for observing non-cooperative targets in space. The accurate determination of the extrinsic parameters for monocular camera and LiDAR systems serves as the cornerstone for achieving effective space multimodal perception. However, due to factors like launch and operation, these extrinsic parameters can experience drift, thereby compromising the overall performance of the multimodal perception system. To tackle this challenge, this study introduces a novel approach: an edge feature-based external calibration method for monocular camera and LiDAR using in-orbit data. The proposed methodology involves several steps. Firstly, edges are extracted from the image, followed by distance transformation based on the edge image. The subsequent integration of the edge image and distance image yields the search scene image. Then, edge feature is extracted from the point cloud data. Finally, after constructing the objective function, genetic algorithms are used to determine precise external parameters. Simulation results underscore the effectiveness of the proposed algorithm, affirming its ability to achieve high-precision calibration results for external parameters even within intricate spatial environments. [ABSTRACT FROM AUTHOR]

High-precision tidal forecasting plays a crucial role in providing reliable tidal information to coastal communities, ship operators, fishermen, and government agencies. Existing tidal prediction models, such as backpropagation neural networks (BPNN) and genetic algorithm-optimized BPNN (GA-BPNN), frequently difficulty in in achieving high precision because they rely solely on past tidal variations for real-time predictions. Signal-to-Noise Ratio (SNR) data have emerged as a valuable indicator closely related to real-time sea level changes due to the widespread adoption of Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) technology. In this paper, we propose a nowcasting tide level prediction method by adding SNR data to BPNN, i.e., Improved BPNN and Improved GA-BPNN, which predicts the next momentary tide level value by using the previous 15 tidal values and real-time SNR as input factors to BPNN. The results of 100-day, 200-day and 1-year tide prediction based on Astoria and Friday Harbor tide gauge stations show that the improved model prediction accuracies are better than the traditional model. Meanwhile, among the two improved models, Improved GA-BPNN has the higher prediction accuracy and can adapt to different time lengths of tide level prediction. [ABSTRACT FROM AUTHOR]

Ion exchange typically involves replacing smaller ions with larger ions below the glass transition temperature. This study introduces an innovative computational approach for the inverse design of ion-exchangeable glasses. It aims to simultaneously achieve high depth of layer (DOL) and surface compressive stress (CS), a task complicated by the inherent trade-offs between these properties. Traditional ion exchange experimental methods are not only time-consuming and expensive, but they also involve complex practical difficulties. Addressing these challenges, this paper introduces a novel computational approach that synergistically combines a multi-objective genetic algorithm with machine learning models. The approach involves training models on a diverse set of glass compositions to predict DOL and CS, which then guide an evolutionary algorithm to optimize these properties concurrently. Physics-informed parameters further refine the search, enabling a flexible design framework in glass manufacturing. Comprehensive experimentation and subsequent analysis affirm the proposed method's capacity to efficiently and effectively traverse the intricate design landscape of glass materials. The findings elucidated the influence of distinct compositional and process parameters on DOL and CS, facilitating the manual design process. Additionally, the study identified sixteen glass composition candidates within the SiO 2 –B 2 O 3 –Al 2 O 3 –MgO–Na 2 O system, exhibiting remarkable properties. Specifically, some compositions achieved a DOL of up to 95 μm with a corresponding CS of 890 MPa, while others attained a CS of up to 1654 MPa with a DOL of 14.72 μm. [ABSTRACT FROM AUTHOR]

• This algorithm attains attitude inversion with less data, confirming accuracy and noise resilience. The attitude of space debris holds significant implications for active debris removal and collision warnings. This study constructs a comprehensive photometry dataset for the target, utilizing angle transformation relationships and drawing upon the CZ-4C photometric data tested in the laboratory. The photometry in the dataset with noise and translation simulates the telescope observed one. We use the genetic algorithm to search for attitude parameters of the photometry that matches the simulated photometry in the dataset under the constraint of attitude angle rules. The derived and preset values of attitude parameters exhibit a strong alignment, applicable to light curves with an amplitude of about 2.5 magnitudes and noise levels up to 1.0 magnitudes. This suggests that the algorithm's accuracy is validated against the preset values, demonstrating its robust resistance to noise. Furthermore, the algorithm proposed in this study for deriving attitude from photometry requires a small amount of photometry data. This study provides a promising algorithm for future attitude analyses from telescope-observed photometry. [ABSTRACT FROM AUTHOR]

The arrangement of charging infrastructure has become an urgent issue as electric logistics vehicles (ELVs) transition from urban areas to intercity operations. In this study, we established a multi-stage layout model for intercity charging and swapping infrastructure (CSI) based on the travel characteristics of electric logistics vehicles, to minimize the investment cost of operators and the time cost of vehicle users in Hubei Province, China. Furthermore, the effect of "random", "conservative", and "radical" layout strategies for the infrastructure deployment was analyzed based on an improved genetic algorithm. It is found that the random layout strategy leads to a balance between infrastructure operators and users with the lowest total cost, which is 81.2% and 88.8% of the costs based on the radical strategy and the conservative strategy, respectively. The conservative strategy could reduce investment risks for operators with the lowest investment cost, while the radical strategy prioritizes the convenience of electric logistics vehicles, with the lowest user time cost. The case study suggests that choosing conservative strategies can bring benefits when the budget is limited, while radical strategies have more advantages when the budget is abundant. Random strategies bring the best overall social benefits. The configuration of CSI and travel characteristics of ELVs play important roles in determining layout strategies. • Travel characteristics of electric logistics vehicles is explored. • Multi-stage layout model for intercity charging and swapping infrastructure. • To minimize the investment cost of operators and the time cost of vehicle users. • The effect of random, conservative, and radical strategies is analyzed. • Results show that each strategy has its specific application scenarios. [ABSTRACT FROM AUTHOR]

• Interstellar exploration is defined as bi-objective multi-vehicle problem with profits. • Mission return increases approximately linearly with mission duration. • Lower probe numbers enable more efficient routing through shorter transfers. In the past decade, the discovery of exoplanets has sparked new interests in the idea of interstellar travel and exploration. Despite various proposals for probe concepts and relevant technologies, there is a lack of extensive literature on viable exploration strategies for journeys beyond a single star system. Such exploration strategies might not only have implications on technology development strategies for achieving interstellar exploration but could also enrich existing models for galactic exploration feeding into solutions of the Fermi Paradox. This article presents optimal strategies for the exploration of a large number of near-by stars, using a dedicated, novel methodology, which sets it apart from existing literature: For the first time, the mission design problem of interstellar exploration is redefined as a bi-objective multi-vehicle open routing problem with profits. It is tackled by an adapted hybrid multi-objective genetic algorithm, which is further improved and modified according to the problem characteristics (e. g. large search space). The overall mission model assumes probes traveling on straight trajectories, utilizing flybys, and maintaining an average velocity of 10% of the speed of light. Surpassing prior research that typically relies on statistical models or restricted star data, the star models are founded on the second Gaia data release (Gaia DR2), which represents the most extensive star catalogue to the date of this study and is employed for the first time in the context of interstellar exploration. The resulting star model contains a maximum of 10,000 stars within a spherical region around Sol, covering a distance of 110 light years. It is found, that the number of explored stars J 1 scales with mission duration J 2 and probe number m according to J 1 ∼ J 2 m 0.66 , which provides an initial guidance for future interstellar mission design. Furthermore, the routes and selection of stars vary depending on the number of probes used: When conducting missions with a large number of probes, stars in close proximity to the Solar System are given more focus. On the other hand, missions with a small number of probes include more distant stars to facilitate shorter transfers along the route. Based on these findings, the following recommendations for interstellar exploration strategies can be drawn: When energy resources such as fuel reserves are scarce and the exploration mission is not limited to nearby stars, low probe numbers are more efficient. In contrast, high probe numbers enable faster exploration of nearby stars but involve less resource-efficient transfers, making them a suitable option for small, remotely propelled probe concepts. To address crowding effects in high probe number missions, swarm-based probe concepts are recommended based on the scaling law characteristics derived. [ABSTRACT FROM AUTHOR]

This work presents the study of effect of morphology of carbonyl iron, carbonyl iron-based, and e-waste-based mixtures on microwave absorption properties. Firstly, the flake shaped carbonyl iron particles and its mixture are prepared using conventional and efficient ball milling and blending method, respectively. It provides the absorption in lower frequency region. Further, the covered frequency range starts to shifts slowly towards higher frequency ranges due to the morphological changes. On the other hand, effect of complex morphology of e-waste-based mixtures are also studied. These heterogeneous mixtures are developed using the cutting mill and blending methods that can provide the absorption in higher frequency with very narrow bandwidth. In this manner, effect of morphology on single layer microwave absorption performance of developed heterogenous material is proposed. It is also explored that the developed samples cover a wider bandwidth by utilizing the multilayering technique. A three-layer absorber is designed using genetic algorithm and the results are also validated. The structural and morphological study of the developed heterogeneous materials has been done using X-ray diffraction (XRD) and Field Emission Scanning Electron Microscope (FESEM) analysis. Also, rigorous study has been done on magnetic properties and Cole-Cole plots to understand the magnetic and dielectric losses respectively occurring inside the materials. The results showed wide bandwidth absorption of 11.62 GHz (≤−10 dB bandwidth) in the lower frequency region ranges from 0.5 to 12.12 GHz (i.e., L, C, and X-band). The total thickness achieved is 1.85 mm which is very compact (<2 mm). Thus, a thin and wideband microwave absorber at lower frequency range using heterogeneous morphology of developed materials is also presented. The proposed microwave absorbing materials can be potentially utilized for the shielding applications. [Display omitted] • Study explores the impact of morphology on microwave absorption in heterogeneous mixtures. • Milled Carbonyl iron and its mixture exhibit absorption in lower frequency regions. • E-waste-based mixtures with complex morphology exhibit absorption in higher frequency regions. • Multilayering techniques extend bandwidth, with a three-layer absorber designed using genetic algorithms. • Wideband absorption (11.62 GHz) achieved in the lower frequency range (0.5–12.12 GHz) at a compact (<2 mm) thickness. [ABSTRACT FROM AUTHOR]

Conventional metasurfaces rely heavily on manual design and optimization, which is tedious and inefficient and cannot be adapted to the engineering applications of modern wireless communication networks. The use of intelligent algorithms to design smart metasurfaces with high accuracy and efficiency is becoming a growing trend. In this paper, a uniform scattering smart metasurface based on a 2-bit cell structure is implemented by optimizing the coding sequence of the metasurface using genetic algorithm. By increasing the number of scattering beams, the incident wave is reflected to as many directions as possible with uniform energy. It has an important application prospect in the fields of future 6G mobile communication and radar stealth technology. [ABSTRACT FROM AUTHOR]

With the improvement of productivity and the development of internet and information technology, many e-commerce systems and supply chain logistics systems have emerged, allowing for online purchases of food such as vegetables and fruits, as well as clothing and shoes. Nowadays, online shopping platforms such as Duoduo Maicai, Taobao, JD, and Meituan Youxuan have been integrated into people's lives, and various supermarkets and shopping malls are also everywhere. Therefore, the safety, efficiency, and real-time location of goods delivery need to be taken into account. Traditional supply chain logistics has problems such as requiring a large amount of manpower, inaccurate system positioning, inaccurate designed delivery routes, low efficiency, and inability to understand the status of drivers and vehicles. GIS (Geographic Information System) can assist systems in designing delivery routes, obtaining real-time locations of drivers or goods, and navigating. Therefore, in order to save manpower and ensure the safety and efficiency of goods delivery, this article used genetic algorithms to optimize and design a supply chain logistics intelligent management information system for GIS. This system had three modules, namely the client, driver, and terminal. The client mainly had functions such as publishing orders, checking the estimated arrival time of goods, and learning the real-time location of goods. The driver end mainly had functions such as real-time positioning, navigation, communication, viewing delivered orders, and monitoring cameras. The terminal mainly had functions such as viewing driver monitoring cameras and managing background information. Experiments showed that optimizing GIS could more accurately locate drivers and goods, assist drivers in navigation, assist systems in arranging delivery routes, and calculate the estimated arrival time of goods, resulting in an efficiency improvement of nearly 12%. [ABSTRACT FROM AUTHOR]

Hydraulic turbine control system is a complex system with strong nonlinearity and multiple variables. Therefore, in order to better control the turbine system, it is necessary to obtain the parameters of key components. Aiming at the limitation of the traditional particle swarm optimization algorithm in global search ability, mutation operator and dynamic inertia weight coefficient are introduced to enhance the search ability of the algorithm. In addition, in order to further improve the global search performance of the algorithm, this paper combines the optimized particle swarm optimization algorithm with genetic algorithm to form a hybrid parameter identification algorithm. The hybrid algorithm not only uses the fast convergence of particle swarm optimization (PSO), but also uses the global search advantage of genetic algorithm (GA) to realize efficient and accurate identification of turbine torque and load parameters. Through MATLAB2021a/Simulink simulation experiments, the application effect of the algorithm in the identification of turbine torque and generator load parameters is verified. The simulation results show that the optimized particle swarm optimization algorithm has significant advantages in the accuracy and robustness of parameter identification, and the identified parameters have a high degree of fitting with the actual measured torque and speed. This study not only provides a new optimization strategy for the parameter identification of turbine regulation system, but also provides an effective intelligent algorithm solution for the parameter identification of nonlinear system. [ABSTRACT FROM AUTHOR]

Catalytic methane decomposition (CMD) stands out as a promising alternative for hydrogen production, distinguished by its ability to generate hydrogen with minimal byproducts. While some studies have explored the use of biochar as an alternative catalyst in the CMD process, the role of biochar surface functional groups and inherent properties have not been well understood. This study aimed to explore the influence of various woody biochar types, acidic sites, physicochemical properties, and operating temperatures on their catalytic activity in catalytic methane decomposition (CMD) process. Biochar derived from three biomass sources (pine, poplar, and bark) were examined at 600, 800, and 1000 °C reaction temperature. The findings revealed that heat-treated (HT) poplar biochar exhibited the lowest specific surface area (215.1 m2g⁻1) and the highest concentration of acidic sites. All samples exhibited improved performance at 1000 °C compared to other temperatures. The CH 4 conversion order was observed as HT poplar > HT red pine > HT bark, with the initial conversion of approximately 50%, 35%, and 25%, respectively. Additionally, employing genetic algorithms, kinetics models for the CMD reaction were developed. The study concluded a consistent second order reaction and an activation energy in the range of 300–330 kJ/mol for all three biochar samples. [Display omitted] • The role of acidic functional groups on biochar activity during CMD was revealed. • Poplar demonstrated the highest acidity and best catalytic performance at 1000 °C. • The O:C and H:C ratios suggested potential for carbon sequestration potential. • Biocarbon-catalyzed CMD exhibited an activation energy between 300 and 330 kJ/mol. [ABSTRACT FROM AUTHOR]

The recent emergence of modular space-based solar power concepts has brought the topic to the forefront of alternatives for power generation. Additionally, advancements in wireless power transmission, space robotics, and reusable launch vehicles have improved the viability of space-based solar power concepts. Modular concepts have led to several benefits compared to classical space-based solar power designs in terms of improved manufacturability and assembly, but they also have introduced new challenges with respect to orbital and attitude design. In particular, the coupling of sunlight collection and power beaming on opposing sides of modular configurations, such as for flat-plane sandwich configurations, requires a compromise between power collection and beaming within the orbital and attitude kinematics. This study develops a simultaneous power-beaming geometric efficiency optimization approach that integrates orbital dynamics and attitude kinematics of space-based solar power satellite arrays. The efficacy of the developed approach is demonstrated through three case studies, each reflecting typical constraints on the relative geometry of the satellite array with respect to the Sun and the ground; thereby, enabling a comprehensive exploration of various orbits. Near-optimal solutions of orbits and attitudes that maximize the efficiency of power beaming to the ground are generated, broadening the spectrum of orbits previously investigated in the literature. The approach and findings presented lay the groundwork for evaluating power-beaming systems and conducting analyses that take into account different types of perturbations. • Concurrent orbit and attitude optimization for space-based solar power arrays. • Optimizations assess power beaming for general, Molniya, and Sun-synchronous orbits. • Evaluates multiple configurations of modular sandwich configurations with mirrors. • Analyzes effects of ground locations and time of year on power-beaming efficiency. • Investigates power-beaming efficiency from inclined highly elliptical orbits. [ABSTRACT FROM AUTHOR]

• A new constellation lifecycle cost optimization problem was introduced. • Useful insights to the satellite burn-in problem can guide satellite manufacturers. • Long testing durations are undesirable; testing can be traded off with number of satellites produced. • Combining burn-in, warranty and availability analysis opens new paths for constellation research. Constellation lifecycle costs are an important metric for constellation designers. Recurring costs of mega constellations in particular are large relative to the non-recurring costs, yet little attention has been given to the reduction of recurring costs. Moreover, few studies exist on the impacts of pre-launch activities such as satellite testing on subsequent operational reliability. We thus study the lifecycle cost impacts of environmental stress screening during acceptance testing to minimize constellation lifecycle costs. Parallels are drawn with the field of electronics testing, and costs arising from burn-in, replacement and availability are considered in our formulation. A single-objective cost minimization problem and a multi-objective cost and unavailability minimization problem are presented to capture different mission applications that require different objectives. The effects of system homogeneity and the use of sparing strategies are investigated. We propose genetic algorithms to solve the optimization problems and give some insight into how burn-in should be carried out for minimizing total costs. The optimization is also applied to a case study of a proposed mission scenario and the constellation lifecycle costs of an optimized burn-in plan are compared to those of a typical "reliability target" burn-in plan. The optimization resulted in lifecycle cost savings of around 19% while significantly reducing the burn-in duration, showing much promise in the burn-in cost optimization approach. [ABSTRACT FROM AUTHOR]

To improve the cell productivity of Corynebacterium glutamicum , its initial specific growth rate was improved by medium improvement using deep neural network (DNN)-assisted design with Bayesian optimization (BO) and a genetic algorithm (GA). To obtain training data for the DNN, experimental design with an orthogonal array was set up using a chemically defined basal medium (GC XII). Based on the cultivation results for the training data, specific growth rates were observed between 0.04 and 0.3/h. The resulting DNN model estimated the test data with high accuracy (R2 test ≥ 0.98). According to the validation cultivation, specific growth rates in the optimal media components estimated by DNN-BO and DNN-GA increased from 0.242 to 0.355/h. Using the optimal media (UCB_3), the specific growth rate, along with other parameters, was evaluated in batch culture. The specific growth rate reached 0.371/h from 3 to 12 h, and the dry cell weight was 28.0 g/L at 22.5 h. From the cultivation, the cell yields against glucose, ammonium ion, phosphate ion, sulfate ion, potassium ion, and magnesium ion were calculated. The cell yield calculation was used to estimate the required amounts of each component, and magnesium was found to limit the cell growth. However, in the follow-up fed-batch cultivation, glucose and magnesium addition was required to achieve the high initial specific growth rate, while appropriate feeding of glucose and magnesium during cultivation resulted in maintaining the high specific growth rate, and obtaining a cell yield of 80 g/L ini. • A novel growth medium for Corynebacterium glutamicum was developed using deep neural networks and optimization algorithms. • During the validation cultivation, high specific growth rates were observed in the proposed media. • The limiting factors for high biomass yield were identified in the proposed medium. • To optimize productivity and yield, a fed-batch culture was designed using the proposed medium. [ABSTRACT FROM AUTHOR]

This research stems from the urgent need to address the complex challenges faced in multimodal transportation within the cargo sector, particularly concerning the reduction of transportation costs and CO 2 emissions. Existing transportation systems often struggle to efficiently balance economic and environmental concerns, necessitating innovative solutions. In this paper, we have introduced a novel mathematical model that integrates Singular Value Decomposition (SVD), Genetic Algorithms (GA), and the Adaptive Neural Fuzzy Inference System (ANFIS). The synergy of GA and the ANFIS forms a dynamic learning system that continually refines solutions by adapting to historical decisions and aligning with supply-demand dynamics. This integrated approach aims to optimize cost allocation and resource utilization while simultaneously minimizing CO 2 emissions. Deploying the ANFIS+GA+SVD model in multimodal scenarios yields impressive results, with a minimal average percentage error (MAPE) of 0.28% for transportation costs and a remarkable coefficient of determination R2 of 0.992 for the Truck + Ship scenario. Similarly, a MAPE of 0.11% for CO 2 emissions, supported by an impressive R2 of 0.989, underscores the model's accuracy. Observations of people's transportation choices in response to emission price changes reveal a significant decrease in truck usage, plummeting from 84% to below 50%. Alternative transportation methods, especially in the 3S-3 M-3 C scenario, show a substantial surge, with railways leading at a remarkable 30% increase in utilization. The combined quantity and cost comparison, utilizing the ANFIS+GA+SVD model, emphasizes the suitability of the Truck + Ship scenario for Iraq's transportation network, reinforcing the case for sustainable and efficient multimodal transportation systems. [ABSTRACT FROM AUTHOR]

This paper proposes a pricing model to ensure the budget balance of a company responsible for collecting and treating solid household waste in a city. The model used is of the Principal-Agent type which considers two actors at play, namely the leader (the service provider company) and the follower (the households and establishments that are the beneficiaries of the waste collection service). The model is a constrained bi-level optimization program. The model was applied in the case of Benin to the Grand Nokoué waste management and healthiness Company (SGDS-GN) whose intervention area, in the beginning, covers five communes in the southern part of the country. The solving of the optimization program was made with three (03) scenarios: the company spends two (02) times a week for waste collection (scenario 1), the company spends three (03) times a week for waste collection (scenario 2) and the company spends four (04) times a week for waste collection (scenario 3). The simulation results show that scenario 2 with three (03) passages per week appears more optimal for both the company (the operating result is higher) and the beneficiaries of waste collection services (the rate to be paid is lower). [ABSTRACT FROM AUTHOR]

In this article, we investigate the interaction of multiple steps in hybrid rocket fuel grains. Previous studies have shown the potential of single steps to increase the regression rate. In this study, we evaluate if the single step results can be translated to a multi-step approach. Of special interest are the interactions between the different step configurations. Four grain profiles are assembled by using fuel grain segments with different inner diameters, therefore forming a multi-step approximation of the profiles that can easily be manufactured and scaled up. The multi-step grains enhance the regression rate because of increased mixing and convective heat transfer induced by the recirculation zones of the steps. The experimentally obtained regression rate profiles are similar to the single step experimental data. This signifies that they are reproducible and therefore predictable. Most importantly, multiple steps do not interfere negatively with each other, which proves that steps can be used to approximate different fuel grain profiles. We show experimentally that the regression rate can be increased up to 81% by accumulating the regression rate enhancing potential of single steps. Moreover, we developed a genetic algorithm to estimate the spatially resolved Marxman parameters with only one single burn. • Results from single steps translate to multiple steps. • Regression rate profiles reproducible for multi-steps. • Multi-step grains increase regression rate by up to 81%. • Spatial resolution of Marxman law possible with genetic algorithm. • Complex fuel profiles can be approximated with steps. [ABSTRACT FROM AUTHOR]

Customized bus systems can improve service quality and efficiency by taking advantage of the speed regulation and capacity variation of autonomous bus systems. To address the challenges of customized bus systems design, this study proposes a collaborative optimization model of vehicle scheduling and speed regulation for the autonomous customized bus system. This model minimizes enterprise operation and passenger travel costs by considering mileage constraints, the time window of passenger travel constraints, and demand pairs coverage constraints. Based on the theoretical properties discovered in the joint design model, the problem is decomposed into a set partitioning master problem and route-selection subproblem. An algorithm combining column generation approach and genetic algorithm is proposed to solve the joint design model. To accelerate the calculation in searching for the shortest route for subproblems, hierarchical filtering strategy is used to reduce the cost of finding feasible routes and improve computational efficiency. The case study reveals that the proposed algorithm exhibits better convergence and stability according to the Wilcoxon test. In a numerical experiment with 100 demand pairs, the joint model can be solved by the algorithm proposed in the study optimally with 19% of the computation time required by the exact algorithms. The departure frequency was reduced by 22%, and the operating cost was reduced by 42% compared with those of customized bus lines serviced separately by human-driven buses. Sensitivity analyses were performed on various operating parameters, such as modular bus capacity and speed boundary, across three different scale cases. The results demonstrate that reasonable parameter settings are beneficial for reducing operating costs and vacant seats. • A collaborative optimization model of bus scheduling and speed regulation is proposed. • An algorithm combining column generation and genetic algorithm is proposed. • Hierarchical filtering strategy is used in the subproblem of the proposed algorithm. • An autonomous customized bus system can reduce corporate costs compared to human-driven buses. [ABSTRACT FROM AUTHOR]

To optimize rapidly the medium for green fluorescent protein expression by Escherichia coli with an introduced plasmid, pRSET/emGFP, a single-cycle optimization pipeline was applied. The pipeline included a deep neural network (DNN) and mathematical optimization algorithms with simultaneous optimization of 18 medium components. To evaluate the DNN data sampling method, two methods, orthogonal array (OA) and Latin hypercube sampling (LHS), were used to design 64 initial media for each sampling method. The OA- and LHS-based data sampling resulted in green fluorescent protein fluorescence intensities of 0.088 × 103−1.85 × 104 and 3.30 × 103−1.50 × 104, respectively. Fifty DNN models were built using the OA and LHS datasets. Hold-out validation was performed using 15 % test of OA and LHS data. Mean square errors of the DNN models were 0.015–0.64, indicating the estimation accuracies were sufficient. However, the sensitivities of components in the DNN models varied and were grouped into six major classes by the index of k -means clustering. A representative model was selected for each class. Mathematical optimization algorithms using Bayesian optimization and genetic algorithm were applied to the representative models, and representative optimized medium (OM) compositions were selected by k -means clustering from the proposed OMs. A total of 54 OMs were obtained from the OA and LHS datasets. In the validating cultivation, the best OMs of OA and LHS were 2.12-fold and 2.13-fold higher, respectively, than those of the learning data. • Semi-synthetic medium for Escherichia coli was improved using the high-throughput pipeline. • The new pipeline proposed numerous improved media candidates quickly. • The pipeline-proposed media compositions were different using an orthogonal array or using Latin hypercube sampling. • The best proposed media increased protein expression by 2.13-fold compared with the best initial dataset. [ABSTRACT FROM AUTHOR]

Predicting cyclone intensity is an important aspect of weather forecasting since it influences disaster preparation and response. This framework addresses the pressing need for precise cyclone intensity prediction by presenting a unique predictive model based on a hybrid CNN and Bi-LSTM architecture optimized using a Genetic Algorithm (GA) enhanced Fruit Fly Optimizer (FFO). Existing methods have primarily relied on traditional machine learning models and meteorological data, demonstrating limitations in capturing the complex spatial-temporal patterns inherent in cyclone evolution. These drawbacks include insufficient feature extraction abilities, underutilization of convolutional neural networks (CNN), and poor model tuning. This unique method incorporates a hybrid CNN and Bi-LSTM architecture that is tuned by a Genetic Algorithm (GA) enhanced Fruit Fly Optimizer (FFO), resulting in higher cyclone intensity prediction accuracy. The experimental results are implemented in Python software, and they reveal that this method outperforms current models by an average of 21% when compared to existing methods such as VGG-16 achieved an accuracy of 78% and Ty 5-CNN (95.23%). The suggested CNN-Bi-LSTM model predicts cyclone strength with an excellent accuracy of 99.4%. This unique approach offers a possible avenue for increasing cyclone intensity prediction, hence improving disaster preparedness and risk mitigation efforts in sensitive locations. [ABSTRACT FROM AUTHOR]

Circular Economy initiatives have introduced a solution demand for the treatment of End of Life (EoL) products, switching from shredding and material recycling to the recovery of modules/components that remain functional. The process needs product recovery and diagnostic, disassembly, and requalification. These tasks are today carried out by human labour due to their complexity and uncertainties concerning the working conditions of the received product. But it implies time and costs that hardly balance the economical balance in developed countries context. Human – Cobot collaborative disassembly are promising solution to overcome the uncertainties without compromising the flexibility and the rate of disassembly operation. The Smart Disassembly Cell for Circularity (SDC2) project aims to provide a semi–automated disassembly solution for EoL electronic products. This paper portrays the requirements for the implementation of a Human-Cobot collaborative cell for electronic products. The goal of this project is to implement a shared workplace where the robot and the worker can work in parallel or share a common task with safe interaction. A literature study on available solutions was made. From there, the study and implementation of the decision system, database and service platform started. This document describes the function of the database and decision system as well as the service platform to establish global communication. MySQL and Python with the FLASK package were used to frame the database and service platform, Genetic algorithm was implemented for providing the robotic disassembly planning solution. A case study using a personal computer and a Power inverter was conducted to verify the development in each stage. The systems are under development with an aim to provide a global disassembly cell which will be able to disassemble various products rather than focusing on a specific product. [ABSTRACT FROM AUTHOR]

• For the first time 100% accuracy for epileptic seizure detection using electroencephalogram signals is demonstrated. • Both balanced and unbalanced datasets are studied. • Wavelet extraction from the original EEG signal enhances the feature extraction and selection steps. • Automatic segmentation with algorithmic intelligence is used. • As opposed to Genetic algorithms fast GA is used to achieve fast analysis. The precise electroencephalogram (EEG) signal classification with the highest possible accuracy is a key goal in the brain-computer interface (BCI). Considering the complexity and nonstationary nature of the EEG signals, there is an urgent need for effective feature extraction and data mining techniques. Here, we introduce a novel pipeline based on Bat and genetic algorithms for feature construction and dimension reduction of EEG signals. After wavelet extraction and segmentation, the Bat algorithm identifies the most relevant features. We use these features and a genetic algorithm combined with a neural network method to automatically classify the segments of the epilepsy EEG signals. We also use available classification methods based on k-Nearest Neighbors or naïve Bayes for comparison purposes. The code distinguishes individual signals within various combinations of data obtained from healthy volunteers with open or closed eyes and patients suffering from epilepsy disorders during seizure-free periods or seizure activities. Compared to the previously introduced methods, our proposed framework demonstrates a superior balance of high accuracy and short runtime. The minimum achieved accuracies for balanced and unbalanced classes are 100% and 75.9%, respectively. This approach has the potential for direct applications in clinics, enabling accurate and rapid analysis of the epilepsy EEG signals obtained from patients. [ABSTRACT FROM AUTHOR]

The last-mile delivery challenges and complexity are increasing simultaneously with the e-commerce growth, the e-commerce growth constitutes a threat to urban transport, especially for big cities and developing countries. This paper examines the economic impact of crowd-shipping based on public transport collaborated with the automated parcel locker and the impact of traditional delivery, as two different methods of last-mile delivery under the same circumstances. This paper aims to assess crowd-shipping as an alternative solution for last-mile delivery compared to traditional delivery. Data has been simulated based on Cairo reality, one of the largest cities in the world. The mathematical models were formulated for the problem, where the first model objective function minimizes the costs of vehicle possession and vehicle kilometers traveled, while the second model objective function minimizes the costs of establishing lockers, vehicle possession, and vehicle kilometers traveled. A genetic algorithm has been used due to the complexity of the problem. The results show that the economic impact of the crowd-shipping delivery system is better than the traditional delivery system under the conditions of large-sized and medium-sized demand, while the economic impact of traditional delivery is better than the crowd-shipping delivery system under the conditions of small-sized demand. [ABSTRACT FROM AUTHOR]

Rainstorm is one of the most severe and frequent meteorological disasters. The rainstorm event brings considerable risks to the natural ecosystem and human life. There is a limited body of research on applying the grey prediction model for predicting rainstorm-related data. Based on the extreme precipitation index defined by the Expert Team on Climate Change Detection and Indices, this paper uses the data of rainstorm days from 493 weather stations in the middle and lower reaches of the Yangtze River to establish a prediction model. Improving the accuracy of rainstorm days prediction can bring valuable results to decision-makers in a specific region. The annual rainstorm days series exhibits randomness, irregular nonlinearity, fluctuations, etc.; however, the traditional grey prediction model can only identify the trend of a series but not its fluctuations, making its prediction extremely challenging. Therefore, this paper introduces a new dynamic grey action quantity based on the traditional grey model, and the parameters are solved by the hybrid technique of the genetic algorithm and the constrained fmincon function. The prediction results of the new model are compared with those of the traditional grey model, the seasonal grey model, the neural network, and the seasonal autoregressive integrated moving average. In terms of prediction accuracy and similarity of fluctuations, the results demonstrate that the new model outperforms these models. • A fluctuation data grey model is proposed to predict the rainstorm days. • A novel dynamic grey action quantity is introduced into the traditional grey model. • The nonlinear parameters are determined based on hybrid optimization algorithm. • The new model has better simulation and prediction accuracy than the traditional models. [ABSTRACT FROM AUTHOR]

The research on particle size classification in lunar microgravity has gradually attracted the attention of scholars. Based on the discrete element method (DEM), this work proposes a double-layer auxiliary screening vibrating screen in the form of intermediate feeding, and takes the screening efficiency and screening time as the evaluation indicators. Firstly, the Helmholtz-Maxwell coil is used to simulate the force of particles under lunar microgravity, which verifies the reliability of the numerical simulation of particles under lunar microgravity based on the discrete element method. Then, the influence of the parameters of each screen on the comprehensive performance of screening was analyzed by a single-factor experiment. Finally, based on the BP (Back Propagation) neural network optimized by genetic algorithm, the evaluation model of screen parameters and screen performance is established, and the multi-objective genetic algorithm is used to optimize the screen parameters combination scheme with excellent performance. An efficient comprehensive model of screening is provided to improve the screening performance and the design of the screen machine under lunar microgravity. [ABSTRACT FROM AUTHOR]

The increased internet usage after the pandemic led the UN Forum to improve cybersecurity measures, with zero-knowledge proofs (ZKP) being a viable solution for securing confidential information. ZKP protocols can be demonstrated through the binary puzzle, an NP-complete logic puzzle with four specific constraints. The key contribution of this paper is its successful implementation of the genetic algorithm as a new method to solve the binary puzzle. The optimized fitness function determined the solution at an average of 1.33-2.33 generations for populations ranging from 100 to 500. Its quadratic property calculated the solution faster than the ordinary linear fitness function. [ABSTRACT FROM AUTHOR]

In the literature, the reliability analysis of one-shot devices is found under accelerated life testing in the presence of various stress factors. The application of one-shot devices can be extended to the bio-medical field, where we often evidence that inflicted with a certain disease, survival time would be under different stress factors like environmental stress, co-morbidity, the severity of disease etc. This work is concerned with a one-shot device data analysis and applies it to SEER gallbladder cancer data. The two-parameter logistic-exponential distribution is applied as a lifetime distribution. For robust parameter estimation, weighted minimum density power divergence estimators (WMDPDE) is obtained along with the conventional maximum likelihood estimators (MLE). The asymptotic behaviour of the WMDPDE and the robust test statistic based on the density power divergence measure are also studied. The performances of estimators are evaluated through extensive simulation experiments. Later those developments are applied to SEER gallbladder cancer data. Citing the importance of knowing exactly when to inspect the one-shot devices put to the test, a search for optimum inspection times is performed. This optimization is designed to minimize a defined cost function which strikes a trade-off between the precision of the estimation and experimental cost. The search is accomplished through the population-based heuristic optimization method genetic algorithm. • A robust inference based on weighted density power divergence. • Elaborated study of the asymptotic property. • Testing of hypothesis based on a robust statistic. • Search for optimum inspection times using genetic algorithm. • Application to SEER gallbladder cancer data. [ABSTRACT FROM AUTHOR]

The satellites are assigned to perform scanning tasks by maneuvering sensors in roll and pitch directions within resource constraints. However, these task regions may be larger than the scanned region by the satellites in a single attempt, so multiple attempts are needed to complete the task. Previous literature has proposed strip-based segregation for larger task regions with parallel strips. However, satellite trajectories may not be parallel to each other, and multiple visits from multiple satellites may be required to complete a scanning task. This results in higher usage of resources due to overlapping strips in strip-based segregation. Therefore, a novel three-stage scheduling methodology is proposed for better performance in terms of the size of the scanned region and resource utilization. The initial stage assigns satellites to the tasks irrespective of task segmentation for each scan. The second stage optimizes the roll and pitch angles of assigned satellites to maximize the scanned region with parallel computation since the tasks are independent. The third stage handles uncertainty associated with task failures. An elitist mixed-coded evolutionary solution technique with a constrained non-linear optimization and Markov decision process is proposed. The efficiency of the proposed methodology in small and large-scale scenarios is illustrated with simulations that show up to 20% improvement in the reward collection and 16% improvement in resource utilization compared to the traditional strip-based method. [ABSTRACT FROM AUTHOR]

The present study focuses on modeling the solid oxide fuel cell power plant combined with an absorption-ejection refrigeration cycle. First, a comparison is made between the absorption chiller refrigeration cycle and the absorption-ejection chiller to connect the superior cycle to the solid oxide fuel cell as an auxiliary cycle. Then, the solid oxide fuel cell cycle, the combustion of the output product, the heat recovery unit combined with the refrigeration cycle, and freshwater production are modeled. Next, the sensitivity analysis is presented in order to study the effect of the design parameters on objective functions, which simplifies the justification of the optimization results based on the genetic algorithm. In order to perform optimization, machine learning methods have been employed to reduce computational time and cost. The optimization of this cycle shows that the exergy efficiency is enhanced up to 68%, whereas the overall cost rate is in within 9.7–10.4 dollars per hour. • An integrated gSOFC cycle power plant is proposed, modeled, and designed. • A parametric study is conducted to study the effect of design variables. • Using ejector absorption chiller to increase the efficiency. • Optimal design is performed through a multi-objective optimization method. [ABSTRACT FROM AUTHOR]

Hydrogen purification from steam methane reforming (SMR) by pressure swing adsorption (PSA) technology is a common method to obtain high-purity hydrogen. The breakthrough time can well reflect the adsorption dynamics and help PSA cycle design. In order to avoid time-consuming and labor-intensive breakthrough curve experiments, it is very necessary to develop a fast and accurate surrogate model. In this study, a genetic algorithm (GA) and artificial neural network (ANN) are combined to predict and optimize breakthrough times of adsorbates in activated carbon/zeolite layered beds. Using the Latin hypercube sampling strategy, training data sets of GA-optimized ANN (GA-ANN) obtains from the physical model of adsorption, heat and mass transfer model. The genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. The ANN topology has 4 input variables (superficial velocity, activated carbon height, adsorption pressure and feed temperature) and 3 output variables (breakthrough times of CH 4 , CO and CO 2). The number of neurons in the hidden layer for the GA-ANN model was optimized as 7 to predict and optimize the maximum breakthrough time of SMR with a four-component (H 2 /CH 4 /CO/CO 2) system. The sensitivity analysis displays that relative importance to the breakthrough time is in the order of superficial velocity (40.88%) > adsorption pressure (24.55%) > activated carbon height (21.04%) > feed temperature (13.53%). To obtain high-purity hydrogen, the GA-ANN model combined with multi-objective GA optimization is used to maximize the breakthrough times of CH 4 and CO. The GA-ANN surrogate model proposed in this paper can not only accurately and quickly achieve the purpose of predicting the system breakthrough time with a high correlation coefficient (R = 0.9937) but also obtains the optimal operating conditions of PSA hydrogen purification. • A rigorous heat and mass transfer model of multi-component adsorption is established. • Artificial neural network (ANN) is well-trained by Latin hypercube sampling method. • Genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. • Superficial velocity has the highest relative importance value on breakthrough time. • GA-optimized ANN model and GA combined for maximal breakthrough time of impurities. [ABSTRACT FROM AUTHOR]

Accurate isotherm models contribute to predicting the amount of adsorbate adsorbed in the adsorbent within a certain range of pressure and temperature. Experimental adsorption isotherms of five components (CO 2 , CO, N 2 , CH 4 and H 2) on pelletized zeolite 13X from publication data were correlated with common-used fundamental isotherm models, including Langmuir, Sips, dual-site Langmuir (DSL), and temperature-dependent (TD) isotherm models, including TD Langmuir, TD Sips and TD DSL. Overall, the average relative errors (AREs) of TD models are higher than those of common-used fundamental isotherm models, but TD models have better applicability. In addition, three surrogate artificial neural networks (ANNs) optimized by genetic algorithm (GA) of single- and multi-component gas adsorption isotherm models are proposed. Three GA-ANN models set the adsorption amount as the output and take one, two or three potential inputs, such as adsorption pressure, temperature and adsorbate components. Three GA-ANN models generally have lower AREs and better applicability than fundamental isotherm models and TD isotherm models. The proposed GA-ANN3 model, which has three inputs, makes a new attempt at adsorption isotherms and can fit the multi-component gas adsorption at different temperatures with the change of adsorption pressure. The adsorber dynamics for multi-component adsorption (CO 2 : CO: N 2 : H 2 = 19.9: 0.1: 44.6: 35.4 mol%) in zeolite 13X bed are compared by the extended TD Langmuir model and extended TD DSL model. Since the AREs of the TD DSL model are smaller than that of the TD Langmuir, the breakthrough curves of multi-component gas simulated by the TD DSL model are better than that of TD Langmuir. These results can contribute to relevant researchers choosing suitable adsorption isotherm models for numerical simulations of adsorption processes. • Fitted dual-site Langmuir model performs better in breakthrough curve simulation. • Artificial neural network (ANN) enables construction of adsorption isotherm models. • Genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. • Three GA-ANN models have lower average relative errors and better applicability. • GA-ANN3 attempts to express adsorption isotherms for multi-component mixtures. [ABSTRACT FROM AUTHOR]

Climatic changes, exhaustion of resources, air and water pollution are the detrimental consequences of mismanaging the use of fossil fuels. Likewise, the low performance of the traditional energy-conversion plants encourages scientists to replace these plants with hybrid systems. Accordingly, this study suggests a biomass-based combined system encompassing a gasifier, a gas turbine, a S–CO 2 unit, along with a hot water heater. This system will be analyzed from exergy, and economic point of view also using the genetic algorithm optimization tool multi-objective optimization is carried out. The parametric analysis to evaluate the influences of various variables on the plant operation. It was found that the changing r p of the compressor have a small impact on the efficiencies while it increases the total exergy efficiency and cost. The largest exergy destruction rate of the plant was for the compressor unit with 7391 kW. After that the combustion chamber with 2124 kW represents the worst performance from exergy destruction rate point of view. The optimization is done according to five decision parameters of moisture content, compressor pressure ratio, T 9 , T 14 , and P 36. The objective functions were energy efficiency, exergy destruction rate, and total product cost rate. According to the results of multi-aspect optimization in the optimum point the energy efficiency, exergy destruction and cost of electricity are 33.44%, 12448.1 kw and 130.57 $/h, respectively. • Introduce a multi-generation plant integrated with biomass-feed gasifier. • Gasifier among all components has the highest exergy destruction with 7391 kW. • ANN optimization of system suggests different optimize states for introduced plant. • The optimized system efficiency and cost rate determined as 33.44% and 130.57 $/h. [ABSTRACT FROM AUTHOR]

We propose a new method, called a deep-genetic algorithm (deep-GA), to accelerate the performance of the so-called deep-BSDE method, which is a deep learning algorithm to solve high dimensional partial differential equations through their corresponding backward stochastic differential equations (BSDEs). Recognizing the sensitivity of the solver to the initial guess selection, we embed a genetic algorithm (GA) into the solver to optimize the selection. We aim to achieve faster convergence for the nonlinear PDEs on a broader interval than deep-BSDE. Our proposed method is applied to two nonlinear parabolic PDEs, i.e., the Black-Scholes (BS) equation with default risk and the Hamilton-Jacobi-Bellman (HJB) equation. We compare the results of our method with those of the deep-BSDE and show that our method provides comparable accuracy with significantly improved computational efficiency. • We introduce a deep-GA method. • The method provides a better accuracy and efficiency than the deep-BSDE solver. • Efficiency and accuracy is obtained by embedding a genetic algorithm (GA). • We solve the Black-Scholes with default risk and Hamilton-Jacobi-Bellman equations. [ABSTRACT FROM AUTHOR]

The flow field dominates the process of mass transport and distribution inside the proton exchange membrane water electrolysis cell (PEMEC). Initially, a three-dimensional and non-isothermal PEMEC channel model was estimated to investigate the impact of channel height and width. Based on these results, a complete PEMEC model with a parallel flow-field pattern was developed, and the channel heights and widths of the model were optimized using a genetic algorithm (GA). Compared to the original model, the optimized model decreased the pressure drop by 34.97% at a lower voltage. In addition, because of the optimized flow-field pattern, the optimized model improves the current density on the proton exchange membrane as well as the gas holdup situation in a partial position in the cathode gas diffusion layer. • PEMEC channel height influences the gas fraction, voltage, and pressure drop. • The channel width has a stronger influence on voltage. • GA was used to optimize PEMEC channel structure with two objectives. • The optimized model was characterized by a decrease in pressure drop of 34.97%. [ABSTRACT FROM AUTHOR]

Cryogenic supercritical hydrogen storage technology is a high-density physical hydrogen storage method, which is a highly promising hydrogen storage approach. However, existing research has mainly focused on the development of storage devices for cryogenic supercritical hydrogen, with limited research on the cooling process of supercritical hydrogen. Therefore, a novel cooling process for cryogenic supercritical hydrogen production based on helium expansion cycle with liquid nitrogen (LN 2) pre-cooling is proposed in this paper. In this process, after being compressed and cooled in multiple stages, the feed hydrogen is pre-cooled by LN 2. Then, cryogenic supercritical hydrogen (10 MPa, −235.15 °C, 63.36 g/L) is obtained by helium multi-stage expansion refrigeration. The process is simulated by Aspen HYSYS and optimized by genetic algorithm (GA) to obtain lower specific energy consumption (SEC). Thermodynamic analyses are conducted to evaluate the process. And compared with the conventional hydrogen liquefaction process, the results show that the proposed process is reasonable and superior. The SEC 0 , figure of merit (FOM), and the total exergy loss of the system are 5.432 kWh/kg H2 , 43.88%, and 289.69 kW respectively. This study indicates that the proposed process has significant implications for the hydrogen industry and provides valuable information for cryogenic supercritical hydrogen storage systems. • A novel high-density cryogenic supercritical hydrogen storage system is proposed. • Twelve key variables in the process are optimized to reduce the energy consumption. • The process has higher exergy efficiency than conventional LH 2 plants. • The volume storage density of hydrogen can reach 63.36 kg/m3 in the system. [ABSTRACT FROM AUTHOR]

Sustainable management of water distribution networks (WDNs) is essential to ensure the continuous supply of water. However, the water pipes in WDNs often experience unprecedented failure, which causes disruption in services, flooding, increased maintenance costs, and reduced water quality. Although researchers have developed models to predict the failure of water pipes, the literature lacks fully optimized and robust models. Therefore, this study proposes a new methodology to develop optimized models for predicting the failure probability of water pipes by fusing logistic regression with genetic algorithms. The methodology was applied to the data of the Hong Kong WDN, and experiments were conducted to optimize the hyperparameters and features of logistic regression models. The performance of the proposed methodology is evaluated using five key metrics: accuracy, precision, recall, F1 score, and Area Under the Curve (AUC). The results show significant improvement over conventional approaches, with the best model achieving an F1 score of 0.868 and an AUC of 0.944. These results show that the model can effectively predict the failure probability of water pipes. The relative contribution of each feature to the model's outcome was investigated using the SHapley Additive exPlanations. Additionally, a web application based on the proposed methodology in this study was developed for Hong Kong that other water utility management can benefit from, which can facilitate reliable decision-making for the management of WDNs. [ABSTRACT FROM AUTHOR]

Bundle AI is a marketing tool project motivated to provide solutions for manual product bundling, a popular marketing strategy that boosts sales of low-selling products and encourages mass purchases with promising customer satisfaction. It is a cost-effective solution as it does not depend on large volumes of transactional data, which is suitable for small businesses. The bundling of products was defined as a Multiple Constraints Knapsack Problem where the best solution is determined using Genetic Algorithm. Bundle AI delivers the fit product bundle with the incorporation of the value and reward system. [ABSTRACT FROM AUTHOR]

In this work, a higher-order Proton Exchange Membrane (PEM) Fuel Cell system is controlled using a cascaded control approach. The primary and secondary controllers, NPID/PI, are non-linear proportional-integral-derivative and proportional-integral, respectively. The suggested cascade approach controls the stack voltage by adjusting the air compressor voltage to maintain the oxygen excess ratio value within limits. Two additional cascade control structures, PID/PI and FOPID/FOPI (fractional order PID and fractional order PI), are also created for a fair comparison. A genetic algorithm is used to determine the controller's optimal parameters by minimising the time integral absolute error of the primary controller. Results show that NPID/PI control structure achieves the minimum value of settling time and overshot (0.9514 s, 0.021%) compared to FOPID/PI (1.8980 s, 0.036%) and PID/PI (3.2308 s, 0.092%), respectively. Finally, it can be concluded from the result of setpoint tracking, disturbance rejection, and noise suppression that the proposed controller is efficient and robust compared to other designed controllers. [Display omitted] • A novel NPID/PI cascaded control is proposed for stack voltage control of FC. • FOPID/FOPI, and PID/PI are also designed for comparative analysis. • GA is utilised to estimate the design parameters of the all the controllers. • Detailed performance analysis for NPID/PI is investigated for different scenarios. [ABSTRACT FROM AUTHOR]

Due to the rapid development of confidential digital communication over international networks, security is the most significant factor. Steganography is the science of concealed communication and is used to conceal the presence of secret information among the various methods of hiding data in communications. Steganography techniques are usually implemented either in spatial or frequency domains. Some spatial domain methods fundamentally utilize the absolute difference value between neighbor pixels to encode the secret message, categorized as Pixel-Value Differencing Steganography methods (PVDS). In PVDS, the hiding capacity of the adjacent pixels depends on their difference value. Consequently, the secret data will be embedded with a high visual quality of the stego-image. Indicator-based PVDS (IPVDS) technique is derived from the PVDS method. It depends on an Indicator pixel (IP) to extract the secret data correctly. The Genetic Algorithm (GA) approach to optimization depends on the concept of survival of the fittest. This paper introduces two proposals, GA-based steganography schemes (GA-IPVD) and (GA-IPVDM). These new techniques encoded secret data using the IPVDS method. Before embedding data in the cover image, the order of the pixels corresponding to the secret data is modified and rearranged. GA controls the operation of rearranging and modifying the order of pixels and all parameters. The current paper addresses steganography as an optimization problem and seeks to determine the optimal order of the pixels that enhance the matching between the cover image and stego-image to reduce distortion despite high embedded capacity. In the first proposed technique GA-IPVD, GA concentrates on the imperceptibility of embedded data and maximizes the quality of the stego-image according to the given secret data. In contrast, the GA maximizes the capacity of embedded data while maintaining an acceptable amount of stego-image quality in the second proposed technique GA-IPVDM. The proposed systems have embedding key that increase the security of proposed schemes. The experimental results demonstrate that the proposed methods can embed a large quantity of secret data while maintaining an acceptable visual quality of the stego-images. The proposed technique has also demonstrated excellent resistance to a variety of stego-attacks, including the pixel difference histogram (PDH) as well as regular and singular (RS) analyses. Additionally, the out-of-boundary pixel issue (BI), which endures in the majority of modern data hiding algorithms, has been successfully resolved. [ABSTRACT FROM AUTHOR]

• A Cascade 2-stage condensation ORC is integrated with LNG vaporizing at 6 bar. • Simultaneous optimization in 3 levels is implemented using Genetic algorithm. • Novel variable definition method accelerates accurate result achievements. • Structure, working fluids, and variables optimized considering vital constraints. • A structure is proposed based on the exergy analysis result. One of the most efficient methods of exergy recovery during the regasification process is integrating the LNG stream with an Organic Rankine Cycle (ORC) to generate electricity. This study employs a cascade structure of ORC consisting of two double-stage condensations operating at 6 bar regasification pressure. To obtain an optimal ORC system integrated with an LNG, three optimization levels for a specific heat source are addressed, including process variables, working fluids, and structure. Ten process variables and two working fluid variables for the top and bottom cycle among 13 candidates of refrigerants were optimized to provide the maximum power output. The results determined that refrigerants of R41 and R1150 have the best performance in the optimized process conditions for the top and bottom cycles, respectively. For the regasification of 36 tonnes per hour of an LNG stream, the produced net power and the exergy efficiency are achieved by 2116.76 kW and 0.29, respectively. The exergy analysis revealed that employing the double-stage condenser ORC is not a good choice. Accordingly, a cascade-parallel structure is proposed for further studies. [ABSTRACT FROM AUTHOR]

Recovering ammonia from anaerobic digestion (AD) effluent offers the opportunity to produce a renewable fertilizer and reduce environmental impact. A novel process developed for such an application was evaluated during this study. The feature of the process is integrating biogas stripping and gypsum (CaSO 4 ·2H 2 O) absorption. The result revealed that the lower CO 2 content and the absorption temperature contributed the higher efficiency of ammonia recovery. The gypsum solution recovered around 95% of the stripped ammonia when the stripping gas contained 10% CO 2 and it rose to 100% when the gas contained more than 30% CO 2. Furthermore, a statistical model and genetic algorithm were applied to estimate the total ammonia recovery and optimize the operating parameters. The experimental and modeling results indicated that integrating biogas stripping with gypsum absorption can effectively harvest ammonia nitrogen and reduce CO 2 emissions while producing (NH 4) 2 SO 4 fertilizer from AD effluent. [Display omitted] [ABSTRACT FROM AUTHOR]

The existence of space debris will pose a serious threat to the safety of spacecraft in orbit and cause serious impact damage to spacecraft. Therefore, the timely and accurate determination of the impact location of space debris is very important to improve the safety and reliability of the orbiting spacecraft in the long run. This paper proposes an intelligent back-propagation artificial neural network-based algorithm for locating the impact source of space debris. The method of building and training the algorithm is described, based on the moment of arrival of the stress waves detected by the PVDF (Polyvinylidene Fluoride) sensor array and the sensor coordinates. Based on the ABAQUS finite element simulation data, the neural network is trained. The result shows that compared with the traditional TOA (Time of Arrival) localization algorithm, the localization accuracy of the BP (Back Propagation) neural network localization algorithm is improved by 34.7%. The optimal objective is to minimize the error between the space debris impact point and the localization point. The parameters of the PVDF sensor array (diameter d of the circular PVDF thin film sensor, radius R of the PVDF sensor array) were optimized by genetic algorithm, and the optimal sensor array parameters were obtained based on the optimization algorithm. [ABSTRACT FROM AUTHOR]

[Display omitted] • An end-to-end inverse framework achieves fast identification of 3D microstructures from tailored strength, stiffness, and fatigue property. • A deep learning and genetic algorithm framework that is capable of both forward and inverse predictions. • We demonstrated the performance of this framework in the context of Ti-6Al-4V in both forward/inverse directions and achieved tailored mechanical properties with large variance. • The framework is highly transferrable to other materials and scientific fields. Materials-by-design has been historically challenging due to complex process-microstructure-property relations. Conventional analytical or simulation-based approaches suffer from low accuracy or long computational time and poor transferability, limiting their applications in solving the inverse material design problem. Here, we establish a deep learning and genetic algorithm framework that integrates forward prediction and inverse exploration. This framework provides an end-to-end solution to achieve application-specific mechanical properties by microstructure optimization. In this study, we select the widely used Ti-6Al-4V alloy to demonstrate the effectiveness and efficiency of this framework. We realize this by tailoring its 3D microstructures to achieve various yield strengths and elastic moduli across a large design space, while minimizing stress concentration factors. Compared with conventional methods, our framework is efficient, versatile, and readily transferrable to a wide range of materials and properties. Paired with emerging additive manufacturing techniques in controlling local microstructural features, our method offers far-reaching potentials for the accelerated development of application-specific, high-performing materials. [ABSTRACT FROM AUTHOR]