Search

Introduction: Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components. Method: A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy. Results: The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31–60 min in 34%, 61–90 min in 11%, 91–120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%). Conclusion: The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance. [ABSTRACT FROM AUTHOR]

Deformable linear objects (DLOs), such as rods, cables, and ropes, play important roles in daily life. However, manipulation of DLOs is challenging as large geometrically nonlinear deformations may occur during the manipulation process. This problem is made even more difficult as the different deformation modes (e.g., stretching, bending, and twisting) may result in elastic instabilities during manipulation. In this paper, we formulate a physics-guided data-driven method to solve a challenging manipulation task—accurately deploying a DLO (an elastic rod) onto a rigid substrate along various prescribed patterns. Our framework combines machine learning, scaling analysis, and physical simulations to develop a physics-based neural controller for deployment. We explore the complex interplay between the gravitational and elastic energies of the manipulated DLO and obtain a control method for DLO deployment that is robust against friction and material properties. Out of the numerous geometrical and material properties of the rod and substrate, we show that only three non-dimensional parameters are needed to describe the deployment process with physical analysis. Therefore, the essence of the controlling law for the manipulation task can be constructed with a low-dimensional model, drastically increasing the computation speed. The effectiveness of our optimal control scheme is shown through a comprehensive robotic case study comparing against a heuristic control method for deploying rods for a wide variety of patterns. In addition to this, we also showcase the practicality of our control scheme by having a robot accomplish challenging high-level tasks such as mimicking human handwriting, cable placement, and tying knots. [ABSTRACT FROM AUTHOR]

Batteries have been considered a key element in several applications, ranging from grid-scale storage systems through electric vehicles to daily-use small-scale electronic devices. However, excessive charging and discharging will impair their capabilities and could cause their applications to fail catastrophically. Among several diagnostic indices, state-of-charge estimation is essential for evaluating a battery's capabilities. Various approaches have been introduced to reach this target, including white, gray, and black box or data-driven battery models. The main objective of this work is to provide an extensive comparison of currently highly utilized machine learning-based estimation techniques. The paper thoroughly investigates these models' architectures, computational burdens, advantages, drawbacks, and robustness validation. The evaluation's main criteria were based on measurements recorded under various operating conditions at the Energy Systems Research Laboratory (ESRL) at FIU for the eFlex 52.8 V/5.4 kWh lithium iron phosphate battery pack. The primary outcome of this research is that, while the random forest regression (RFR) model emerges as the most effective tool for SoC estimation in lithium-ion batteries, there is potential to enhance the performance of simpler models through strategic adjustments and optimizations. Additionally, the choice of model ultimately depends on the specific requirements of the task at hand, balancing the need for accuracy with the complexity and computational resources available and how it can be merged with other SoC estimation approaches to achieve high precision. [ABSTRACT FROM AUTHOR]

Accurate and reliable monthly streamflow prediction plays a crucial role in the scientific allocation and efficient utilization of water resources. In this paper, we proposed a prediction framework that integrates the input variable selection method and Long Short-Term Memory (LSTM). The input selection methods, including autocorrelation function (ACF), partial autocorrelation function (PACF), and time lag cross-correlation (TLCC), were used to analyze the lagged time between variables. Then, the performance of the LSTM model was compared with three other traditional methods. The framework was used to predict monthly streamflow at the Jimai, Maqu, and Tangnaihai stations in the source area of the Yellow River. The results indicated that grid search and cross-validation can improve the efficiency of determining model parameters. The models incorporating ACF, PACF, and TLCC with lagged time are evidently superior to the models using the current variable as the model inputs. Furthermore, the LSTM model, which considers the lagged time, demonstrated better performance in predicting monthly streamflow. The coefficient of determination (R2) improved by an average of 17.46%, 33.94%, and 15.29% for each station, respectively. The integrated framework shows promise in enhancing the accuracy of monthly streamflow prediction, thereby aiding in strategic decision-making for water resources management. [ABSTRACT FROM AUTHOR]

Waste-to-energy processes remain essential to ensure the safe and irreversible removal of materials and substances that are (or have become) unsuitable for reuse or recycling, and hence, to keep intended cycles of materials in the circular economy clean. In this paper, the behavior of inorganic compounds in waste-to-energy combustion processes are discussed from a multi-disciplinary perspective, against a background of ever tightening emission limits and targets of increasing energy efficiency and materials recovery. This leads to the observation that, due to the typical complexity of thermally treated waste, the intelligence of combustion control systems used in state-of-the-art waste-to-energy plants needs to be expanded to better control the behavior of inorganic compounds that typically end up in waste furnaces. This paper further explains how this goal can be achieved by developing (experimentally validated) predictive numerical models that are engineering-based and/or data-driven. Additionally, the significant economic potential of advanced thermochemical intelligence towards inorganic compounds in waste-to-energy combustion control systems is estimated on the basis of typical operational figures. [ABSTRACT FROM AUTHOR]

The re-evaluation of oil-bearing wells enables finding potential oil-bearing areas and estimating the results of well logging. The re-evaluation of oil bearing is one of the key procedures for guiding the development of lower production wells with long-term production histories. However, there are many limitations to traditional oil-bearing assessment due to low resolution and excessive reliance on geological expert experience, which may lead to inaccurate and uncertain predictions. Based on information gain, three data-driven models were established in this paper to re-evaluate the oil bearing of long-term production wells. The results indicated that the RF model performed best with an accuracy of 95.07%, while the prediction capability of the neural network model was the worst, with only 79.8% accuracy. Moreover, an integrated model was explored to improve model accuracy. Compared with the neural network, support vector machine, and random forest models, the accuracy of the fusion model was improved by 20.9%, 8.5%, and 1.4%, which indicated that the integrated model assisted in enhancing the accuracy of oil-bearing prediction. Combined with the long-term production characteristics of oil wells in the actual oil field, the potential target sweet spot was found, providing theoretical guidance for the effective development of lower production wells in the late period of oilfield development. [ABSTRACT FROM AUTHOR]

The paper presents two effective methods for discovering process models in the form of partial differential equations based on an evolutionary algorithm and an algorithm for the best subset selection. The methods are designed to work with sparse and noisy data and implement various numerical differentiation techniques, including piecewise local approximation using multidimensional polynomial functions, neural network approximation, and an additional algorithm for selecting differentiation steps. To verify the algorithms, the experiment is carried out on pulsed heating of a viscous liquid (glycerol) by a submerged horizontal cylindrical heat source. Temperature measurements are taken only at six points, which makes the data very sparse. The noise level ranges from 0.2 to 1% of the observed maximum temperature. The algorithms can successfully restore the structure of the heat transfer equation in cylindrical coordinates and determine the thermal diffusivity coefficient with an error of 2.5–20%, depending on the algorithm type and heating mode. Additional synthetic setups are employed to analyze the dependence of accuracy on the noise level. Results also demonstrate the algorithms' ability to identify underlying processes such as convective motion. [ABSTRACT FROM AUTHOR]

Due to the dynamic and complexity of leachate percolation within municipal solid waste (MSW), planning and operation of solid waste management systems are challenging for decision-makers. In this regard, data-driven methods can be considered robust approaches to modeling this problem. In this paper, three black-box data-driven models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and support vector regression (SVR), and also three white-box data-driven models, including the M5 model tree (M5MT), classification and regression trees (CART), and group method of data handling (GMDH), were developed for modeling and predicting landfill leachate permeability (k ). Based on a previous study conducted by Ghasemi et al. (2021), k can be formulated as a function of impermeable sheets ( IS ) and copper pipes ( CP ). Hence, in the present study, IS and CP were adopted as input variables for the prediction of k and evaluated for the performance of the suggested black-box and white-box data-driven models. Scatter plots and statistical indices such as coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were used for qualitative and quantitative evaluations of the effectiveness of the suggested methods. The outcomes indicated all of the provided models successfully predicted k . However, ANN and GMDH had higher accuracy between the proposed black-box and white-box data-driven models. ANN with R2 = 0.939, RMSE = 0.056, and MAE = 0.017 was marginally better than GMDH with R2 = 0.857, RMSE = 0.064, and MAE = 0.026 in the testing stage. Nevertheless, an explicit mathematical expression provided by GMDH to predict k was easier and more understandable than ANN. [ABSTRACT FROM AUTHOR]

Multilateral well drilling technology has recently assisted the drilling industry in improving borehole contact area and reducing operation time, while maintaining a competitive cost. The most advanced multilateral well drilling method is Fishbone drilling (FbD). This method has been utilized in several hydrocarbon fields worldwide, resulting in high recovery enhancement and reduced carbon emissions from drilling. FbD involves drilling several branches from laterals and can be considered as an alternative method to hydraulic fracturing to increase the stimulated reservoir volume. However, the expected productivity of applying a Fishbone well from one field to another can vary due to various challenges such as Fishbone well design, reservoir lithology, and accessibility. Another challenge is the lack of existing analytical models and the effect of each Fishbone parameter on the cumulative production, as well as the interaction between them. In this paper, analytical and empirical productivity models were modified for FbD in a dry gas reservoir. The modified analytical model showed a higher accuracy with respect to the existing model. It was also compared with the modified empirical model, which proved its higher accuracy. Finally, machine learning algorithms were developed to predict FbD productivity, which showed close results with both analytical and empirical models. [ABSTRACT FROM AUTHOR]

Batteries are complex systems involving spatially distributed microscopic mechanisms on different time scales whose adequate interplay is essential to ensure a desired functioning. Describing these phenomena yields nonlinearly coupled partial differential equations whose numerical solution requires considerable effort and computation time, making it an infeasible solution for real-time applications. Anyway, having information about the internal electrochemical states of the battery can pave the way for many different advanced monitoring and control strategies with a big potential for improving efficiency and longevity. For such purposes, in the present paper, a combination of a low-order representation of the essential dynamics associated to the internal electrochemical mechanisms based on Dynamic Mode Decomposition for control (DMDc) is proposed to obtain an improved equivalent circuit model (ECM) representation with continuously updated parameters and combined with an extended Kalman Filter (EKF). The model-order reduction step extensively exploits the model structure, yielding a well structured low-order representation without artificial numerical correlations. The performance of the proposed method is illustrated with numerical simulations based on a well-established reference model, showing its potential usefulness in real-time applications requiring knowledge of the internal electrochemical states besides the state-of-charge. [ABSTRACT FROM AUTHOR]

Liquid loading is the most common operational problem influencing gas well productivity for the petroleum operator. Liquid loading is defined as an operational constraint that is associated with gas wells where the major driving mechanism for hydrocarbon production is by the associated gas-driven mechanisms. Liquid loading occurs when liquid accumulated in the tubing or casing results in the gas velocity lower than the critical value (the minimum velocity required for gas to push the liquid out of the gas well), which overtime leads to a hydrostatic back pressure greater than the formation pressure of the well, thereby limiting the flow of gas into the well. The continuous build-up of pressure from liquid loading eventually minimizes well productivity and expensive work over operations. However, current mathematical models to predict liquid loading are flawed with varying inaccuracies and depending on the models deployed will ultimately lead to loss of production time and well productivity. In our work we present prediction of liquid loading using a software-based model incorporating the particle swarm optimization algorithm, genetic algorithm, and artificial neural network and Bayesian neural network algorithms applications. The results of our research findings show that artificial neural network software-based model with a simulated accuracy of 93% and 92% for test and trained data, respectively, outperformed the particle swarm optimization data-driven model with a simulated sensitivity accuracy of 92% and 83%, and genetic algorithm data-driven models with a simulated accuracy of 89% and 83%. The Bayesian neural network was postulated as a robust model because of its simplicity shown to have simulated accuracy of 77% and 73% for train and test data, respectively. Thus software-based code environment and data-driven model developed and presented in this paper may resolve many of current deficiencies and gaps in the current technical literature to predict liquid loading with high precision offering saving in millions of dollars to the operators. [ABSTRACT FROM AUTHOR]

The present study aims to thoroughly review GWL depletion monitoring studies completed between 2000 and 2023 based on data-driven models and GIS approaches from a global perspective. The review summarizes the details of the reviewed papers, including location, period, time scale, key objective, input parameter, applied model, performance metrics, research gaps, limitations, and depletion rate. The mean rate of GWL depletion varied worldwide from 2.9 ± 1.56 to 1100 ± 33.76 mm/yr using data-driven models and from 7.6 ± 2.98 to 2046 ± 45.27 mm/yr using GIS-based approaches. This study assesses the strength of relationships between various keywords and analyzed co-author networks using the Vos-viewer. It proposes a groundwater development strategy based on the evaluated papers to provide a long-term solution to the water scarcity problem. Overall, this review highlights the existing research gaps and suggests potential future research paths to boost the associated new knowledge and increase the accuracy of the GWL depletion monitoring approaches.

Disasters in developing countries tremendously affect the economy and long-term development. Recent years have seen an increase in epidemic outbreaks in countries like Haiti and in West Africa. However, there seems to be a lack of decision support to address epidemic outbreak challenges in developing countries compared to their developed counterparts. The lack of data to implement such models is a potential reason. This paper presents a data set that will permit to develop data-driven allocation models and policies for an epidemic outbreak in a developing country. The data set is for the cholera epidemic that occurred in the aftermath of the 2010 earthquake in Haiti. The detailed time-series patient data is intended to facilitate the development and evaluation of multi-period supply chain models that support emergency health response, allocate medical resources and staff, and design coordination mechanisms among humanitarian stakeholders. We also provide a simple model to illustrate how the data can be utilized to develop a basic epidemic outbreak response model. The data set will be made available online for researchers interested in developing models in this field. [ABSTRACT FROM AUTHOR]

Anaerobic Digestion (AD) is one of the oldest processes for producing biofuels from organic waste. Approximately 180 years have passed since the construction of the first modern plant, however, large prospects for improvement are still feasible, especially in regards to the quality and uniformity of the biogas produced. This work focalizes on the main quality issues and the available post-production treatment processes for biogas; subsequently, a mini-review on data-driven models and control strategies for biogas and bio-methane production plants is presented. Attention is focused on High Solids Anaerobic Digesters (HSADs), since these reactors present many interesting advantages, including a high number of operating variables which enable process optimization, high methane concentration in exit, reduced reactor volume and low water requirements. HSADs are the reactors with which Europe is aiming to rapidly increase the production of biogas and bio-methane, in order to carry out de-carbonization and reduce dependence on external methane imports. Crucial points for achieving these objectives include qualitative leaps in process operation and management, which, contrary to current practice in existing plants, require a significant increase in process automation, with control of product quality and reduction of stops due to death of bacteria at changing process parameters (such as temperature and pH). The most significant papers related to biogas quality, data-driven models and control strategies are briefly analyzed. [ABSTRACT FROM AUTHOR]

In this paper, a methodology based on data-driven models is developed to predict the NOx emissions of an internal combustion engine using, as inputs, a set of ECU channels representing the main engine actuations. Several regressors derived from the machine learning and deep learning algorithms are tested and compared in terms of prediction accuracy and computational efficiency to assess the most suitable for the aim of this work. Six Real Driving Emission (RDE) cycles performed at the roll bench were used for the model training, while another two RDE cycles and a steady-state map of NOx emissions were used to test the model under dynamic and stationary conditions, respectively. The models considered include Polynomial Regressor (PR), Support Vector Regressor (SVR), Random Forest Regressor (RF), Light Gradient Boosting Regressor (LightGBR) and Feed-Forward Neural Network (ANN). Ensemble methods such as Random Forest and LightGBR proved to have similar performances in terms of prediction accuracy, with LightGBR requiring a much lower training time. Afterwards, LightGBR predictions are compared with experimental NOx measurements in steady-state conditions and during two RDE cycles. Coefficient of determination (R2), normalized root mean squared error (nRMSE) and mean average percentage error (MAPE) are the main metrics used. The NOx emissions predicted by the LightGBR show good coherence with the experimental test set, both with the steady-state NOx map (R2 = 0.91 and MAPE = 6.42%) and with the RDE cycles (R2 = 0.95 and nRMSE = 0.04). [ABSTRACT FROM AUTHOR]

With advancements in big geospatial data and artificial intelligence, multi-source data and diverse data-driven methods have become common in dengue risk prediction. Understanding the current state of data and models in dengue risk prediction enables the implementation of efficient and accurate prediction in the future. Focusing on predictors, data sources, spatial and temporal scales, data-driven methods, and model evaluation, we performed a literature review based on 53 journal and conference papers published from 2018 to the present and concluded the following. (1) The predominant predictors include local climate conditions, historical dengue cases, vegetation indices, human mobility, population, internet search indices, social media indices, landscape, time index, and extreme weather events. (2) They are mainly derived from the official meteorological agency satellite-based datasets, public websites, department of health services and national electronic diseases surveillance systems, official statistics, and public transport datasets. (3) Country-level, province/state-level, city-level, district-level, and neighborhood-level are used as spatial scales, and the city-level scale received the most attention. The temporal scales include yearly, monthly, weekly, and daily, and both monthly and weekly are the most popular options. (4) Most studies define dengue risk forecasting as a regression task, and a few studies define it as a classification task. Data-driven methods can be categorized into single models, ensemble learning, and hybrid learning, with single models being further subdivided into time series, machine learning, and deep learning models. (5) Model evaluation concentrates primarily on the quantification of the difference/correlation between time-series observations and predicted values, the ability of models to determine whether a dengue outbreak occurs or not, and model uncertainty. Finally, we highlighted the importance of big geospatial data, data cloud computing, and other deep learning models in future dengue risk forecasting. [ABSTRACT FROM AUTHOR]

Copyright of e & i Elektrotechnik und Informationstechnik is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Grasping an object is usually only an intermediate goal for a robotic manipulator. To finish the task, the robot needs to know where the object is in its hand and what action to execute. This paper presents a general statistical framework to address these problems. Given a novel object, the robot learns a statistical model of grasp state conditioned on sensor values. The robot also builds a statistical model of the requirements for a successful execution of the task in terms of uncertainty in the state of the grasp. Both of these models are constructed by offline experiments. The online process then grasps objects and chooses actions to maximize likelihood of success. This paper describes the framework in detail, and demonstrates its effectiveness experimentally in placing, dropping, and insertion tasks. To construct statistical models, the robot performed over 8,000 grasp trials, and over 1,000 trials each of placing, dropping, and insertion. [ABSTRACT FROM AUTHOR]

In this paper, a novel framework for probabilistic wind speed forecasting (PWSF) based on variational recurrent autoencoders (VRAEs) via a generative perspective is proposed. Compared with a traditional optimization objective maximizing the conditional likelihood of the target wind speed directly, a novel optimization objective maximizing the likelihood of the complete wind speed sequence is proposed to better model the temporal relationship within the complete wind speed sequence. As directly maximizing the proposed objective is intractable, we show that it can be alternatively achieved via the help of the VRAE learning principle. The framework of the proposed VRAE based PWSF is composed of two phases, training a VRAE with maximizing the variational lower bound of the likelihood of the complete wind speed sequence and forecasting the target wind speed from the generative perspective through the approximate posterior learned by the VRAE. Computational results demonstrate that the proposed method outperforms other benchmarking deterministic and probabilistic forecasting models in terms of the negative form of continuous ranked probability score (CRPS*). Compared with other benchmarking models for probabilistic forecasting, the proposed method achieves better sharpness and overall quality of prediction intervals (PIs) as well as a comparable reliability. Results verify advantages of the proposed VARE based PWSF method. [ABSTRACT FROM AUTHOR]

In control processes, sometimes it would be necessary to know variables at locations that are barely accessible. In such cases, soft sensors (also known as “virtual sensors”) could really help. In fact, they are powerful instruments for the indirect measure of quantities that would not be measurable, if not with the installation of physical sensors that could perturbate the normal working conditions of the system under test. In this paper, the authors describe an approach to indirectly measure temperature values in a brew group of a professional coffee machine. A finite element (FE) model simulating both the fluid dynamics and the thermal distribution on the group was developed and validated by dedicated experimental tests. The FE model was then exploited to feed an autoregressive exogenous model [autoregressive with eXogenous input (ARX) model] linking the temperature in the boiler (i.e., a quantity ordinarily assessed in the coffee machine) and the one near the water output, where otherwise a hardware sensor would compromise the correct coffee brewing process and the safety/quality of the brewed coffee. The obtained data-driven soft sensor can help to improve the control unit architecture of the coffee machine. [ABSTRACT FROM AUTHOR]

The advent of machine learning has made a remarkable impact in the field of healthcare. Diabetes mellitus is a metabolism abnormality that is posing severe threat, exercising substantial pressure on human health worldwide. Diabetes mellitus is a public health problem around the world. In 1980, 108 million adults worldwide had diabetes. By 2040 the number is expected to reach 642 million adults. Hence extensive research in interdisciplinary field that uses skills from various fields such as statistics machine learning, artificial intelligence, visualization, etc. is carried out for better management of diabetes. In this paper, the focus is to use time series forecasting algorithms. Data-driven models in time series machine learning are used to derive meaningful and appropriate information from large volumes of blood glucose level and related data for precise forecasting of upcoming blood glucose level fluctuations. Not only can the patient and physician be informed beforehand, to avert complications, but also it aids in predicting response to certain medications with ease. In this case, univariate data-driven models from time series machine learning algorithms are implemented on 2 different continuous glucose monitoring sensor datasets: Libre Pro dataset of 10 patients and Ohio T1DM dataset of 6 patients. A comparison of performance evaluation metrics of the different time series machine learning algorithms is drawn based on root mean squared error (RMSE), mean average percentage error (MAPE) and Theil’s U, which are statistical analyses, and Clarke’s error grid, which is clinical analysis for prediction horizon from 15 to 45 min. Using Holt’s Linear AAN Algorithm on Libre Pro dataset with alpha and beta of 0.99 provided the least error among exponential smoothing algorithms with RMSE of 7.98 mg/dl for 15 min, 19.47 mg/dl for 30 min and 28.40 mg/dl for 45 min prediction horizon. Theil’s U coefficient was 0.12 for 15 min, 0.39 for 30 min and 0.72 for 45 min prediction horizon. Autoregressive Integrated Moving Average (ARIMA) Algorithm gave the best performance evaluation results with RMSE of 7.07 mg/dl for 15 min with a MAPE of 3.98. The performance results were on par when these algorithms were tested on Ohio T1DM dataset. ARIMA Algorithm gave the best performance evaluation results with RMSE of 13.14 mg/dl for 15 min with a MAPE of 8.213. The difference in the error coefficient for Ohio dataset was due to missing data. [ABSTRACT FROM AUTHOR]

Prognostics and health management (PHM) techniques for proton exchange membrane fuel cell (PEMFC) systems are of great importance for increasing their reliability and sustainability. PEMFC systems suffer from relatively poor long-term performance and durability, and prediction and prognosis can give early indications about when components should be fixed or replaced. Prognostics modeling needs to take account of a number of phenomena, including degradation mechanisms that are not easily measured. A number of works are currently investigating PHM in fuel cell systems, as well as the problem of estimating remaining useful lifetime. Any reduction in the volume of data required for making predictions is clearly advantageous. In this paper, a univariate prognostic approach based on signal processing, namely discrete wavelet transform (DWT), is proposed. The proposed approach aims at achieving an online prognostic for PEMFC systems. DWT is first introduced, and then, the predictions are built using the power signals of two different PEMFC stacks in two different scenarios, namely static and dynamic operating conditions. Results show that the method is reliable for online prediction of power, with prediction errors less than 3%. [ABSTRACT FROM PUBLISHER]

Machine learning models' performance in simulating monthly rainfall–runoff in subtropical regions has not been sufficiently investigated. In this study, we evaluate the performance of six widely used machine learning models, including Long Short-Term Memory Networks (LSTMs), Support Vector Machines (SVMs), Gaussian Process Regression (GPR), LASSO Regression (LR), Extreme Gradient Boosting (XGB), and the Light Gradient Boosting Machine (LGBM), against a rainfall–runoff model (WAPABA model) in simulating monthly streamflow across three subtropical sub-basins of the Pearl River Basin (PRB). The results indicate that LSTM generally demonstrates superior capability in simulating monthly streamflow than the other five machine learning models. Using the streamflow of the previous month as an input variable improves the performance of all the machine learning models. When compared with the WAPABA model, LSTM demonstrates better performance in two of the three sub-basins. For simulations in wet seasons, LSTM shows slightly better performance than the WAPABA model. Overall, this study confirms the suitability of machine learning methods in rainfall–runoff modeling at the monthly scale in subtropical basins and proposes an effective strategy for improving their performance. [ABSTRACT FROM AUTHOR]

The article provides a comprehensive review of the latest developments in the field of laser surface hardening (LSH) and its modeling techniques. LSH is a crucial process for enhancing the surface properties of metals, particularly their hardness and wear resistance, without compromising their bulk properties. This review highlights the fundamental principles of LSH, the types of lasers used, and the key parameters influencing the hardening process. It delves into various modeling approaches, including finite element method (FEM) simulations, analytical models, and empirical models (using statistical methods), emphasizing the integration of advanced computational techniques such as machine learning and artificial intelligence to improve the accuracy and efficiency of LSH simulations. The review also explores practical applications across different industries, showcasing how LSH models have been used to solve real-world challenges in the automotive, aerospace, and tool manufacturing sectors. Finally, it addresses current limitations and outlines future research directions, suggesting potential areas for further advancements in the modeling and application of LSH processes. [ABSTRACT FROM AUTHOR]

Accurate PV power forecasting techniques are a prerequisite for the optimal management of the grid and its stability. This paper presents a review of the recent developments in the field of PV power forecasting, mainly focusing on the literature which uses ML techniques. The ML techniques (sub-branch of artificial intelligence) are extensively used due to their ability to solve nonlinear and complex data structures. PV power forecasting can either be direct, or indirect, which involves solar irradiance forecast model, plane of array irradiance estimation model, and PV performance model. This paper presents a review of both of these pathways of PV power forecasting based on the proposed methodology, forecast horizons and the considered input parameters. In case of unavailability of historical PV power for a new PV plant and in case of failure of real-time data acquisition, indirect PV power forecasting can be a viable alternative. Although the performance ranking of various ML models is complicated and no model is universal, recent studies suggest that methodologies like deep neural networks and ensemble or hybrid models outperform conventional methods for short-term PV forecasting. Recent articles also present the various intelligent optimisation and data-preparation techniques to improve performance accuracy.

Digital twins are used to digitally map properties and states of real manufacturing systems. Based on relevant data-driven and physics-based digital models, digital twins are employed to monitor, analyze and predict aspects of the corresponding manufacturing system. Therefore, digital twins are used on different manufacturing levels, e.g. the factory, machine, or process level. This paper presents a concept for digital twins that are modeled by physics-based and data-driven models. Furthermore, this concept is validated with the help of a use case that controls an energy management system of a model-scale factory by finding the optimal time for charging and using the battery. [ABSTRACT FROM AUTHOR]

In response to national and international carbon reduction goals, renewable energy resources like photovoltaics (PV) and wind, and energy storage technologies like fuel-cells are being extensively integrated in electric grids. All these energy resources require power electronic converters (PECs) to interconnect to the electric grid. These PECs have different response characteristics to dynamic stability issues compared to conventional synchronous generators. As a result, the demand for validated models to study and control these stability issues of PECs has increased drastically. This paper provides a review of the existing PEC model types and their applicable uses. The paper provides a description of the suitable model types based on the relevant dynamic stability issues. Challenges and benefits of using the appropriate PEC model type for studying each type of stability issue are also presented.

The optimization of biological nitrogen removal (BNR) in sequencing batch reactors has become the aim of researchers worldwide in order to increase efficiency and reduce energy and operating costs. This research has focused on the nitrification phase as the limiting reaction rate of BNR. This paper analyzes different strategies and discusses different tools such as: factors for achieving partial nitrification, real-time control and monitoring for detecting characteristic patterns of nitrification/denitrification as end-points, use of modeling based on activated sludge models, and the use of data-driven modeling for estimating variables that cannot be easily measured experimentally or online. The discussion of this paper highlight the properties and scope of each of these strategies, as well as their advantages and disadvantages, which can be integrated into future works using these strategies according to legal and economic restrictions for a more stable and efficient BNR process in the long-term. [ABSTRACT FROM AUTHOR]

Effective fault diagnosis of compressors in heating, ventilation, and air conditioning (HVAC) systems is critical to ensure service reliability and boost energy efficiency. HVAC compressors are distributed in different areas and work under heterogeneous conditions, which poses emerging challenges to their data-driven modeling. Most existing methods assume multiple category-balanced source domains for model training. Although domain adaptation and generalization methods have emerged to address the data distribution discrepancies in cross-domain fault diagnosis, limited source domains and imbalanced fault categories across domains still constrain the real-world applicability of data-driven models in HVAC compressor fault diagnosis under unseen working conditions. Therefore, this paper studies a significant fault diagnosis problem named single imbalanced domain generalization (SIDG) and proposes a corresponding network (SIDGNet) for intelligent HVAC compressor fault diagnosis. Specifically, a rare fault diagnosis module combined with focal loss is introduced to tackle the class imbalance problem. To achieve better diagnostic boundaries and resist unknown data distribution discrepancies, joint supervised contrastive learning and adversarial learning with specialized data augmentation are introduced as auxiliary modules to improve the robustness and generalizability of SIDGNet. An improved uncertainty-based dynamic weighting mechanism is developed to intelligently balance the weights of module-specific losses during training, which ensures an efficient and stable optimization process. Extensive SIDG fault diagnosis experiments conducted on HVAC compressors demonstrate the superiority of SIDGNet over existing models in SIDG scenarios. [ABSTRACT FROM AUTHOR]

Waste-to-energy processes remain essential to ensure the safe and irreversible removal of materials and substances that are (or have become) unsuitable for reuse or recycling, and hence, to keep intended cycles of materials in the circular economy clean. In this paper, the behavior of inorganic compounds in waste-to-energy combustion processes are discussed from a multi-disciplinary perspective, against a background of ever tightening emission limits and targets of increasing energy efficiency and materials recovery. This leads to the observation that, due to the typical complexity of thermally treated waste, the intelligence of combustion control systems used in state-of-the-art waste-to-energy plants needs to be expanded to better control the behavior of inorganic compounds that typically end up in waste furnaces. This paper further explains how this goal can be achieved by developing (experimentally validated) predictive numerical models that are engineering-based and/or data-driven. Additionally, the significant economic potential of advanced thermochemical intelligence towards inorganic compounds in waste-to-energy combustion control systems is estimated on the basis of typical operational figures.

In the field of water supply management, multi-steps water demand forecasting plays a crucial role. While there have been many studies related to multi-steps water demand forecasting based on deep learning, little attention has been paid to the interpretability of forecasting models. Aiming to improve both the forecasting accuracy and interpretability of the model, a novel urban water demand forecasting neural network (UWDFNet) was presented in this paper. Compared with traditional deep learning models, it innovatively considered domain-specific prior knowledge from water supply management and incorporated the correlation relationship between different input variables into the design of the neural network structure, and verified the consistency between the knowledge learned by the model and prior knowledge through interpretability analysis. Additionally, a systematic performance evaluation was conducted and proved that UWDFNet possesses better accuracy and stability compared to other baseline models(e.g., gated recurrent unit network (GRUN), GRUN with a corrected Network (GRUN+CORRNet), GRUN+PID, GRUN+Kmeans).

In this overview paper, data-driven learning model-based cooperative localization and location data processing are considered, in line with the emerging machine learning and big data methods. We first review (1) state-of-the-art algorithms in the context of federated learning, (2) two widely used learning models, namely the deep neural network model and the Gaussian process model, and (3) various distributed model hyper-parameter optimization schemes. Then, we demonstrate various practical use cases that are summarized from a mixture of standard, newly published, and unpublished works, which cover a broad range of location services, including collaborative static localization/fingerprinting, indoor target tracking, outdoor navigation using low-sampling GPS, and spatio-temporal wireless traffic data modeling and prediction. Experimental results show that near centralized data fitting- and prediction performance can be achieved by a set of collaborative mobile users running distributed algorithms. All the surveyed use cases fall under our newly proposed Federated Localization (FedLoc) framework, which targets on collaboratively building accurate location services without sacrificing user privacy, in particular, sensitive information related to their geographical trajectories. Future research directions are also discussed at the end of this paper.

This paper presents a novel framework architecture for an online, real-time flexibility assessment and activation platform targeted at unlocking the flexibility potential of commercial buildings and smaller industrial sites, thereby enabling greater levels of renewable grid integration. Renewable integration targets in Europe of up to 40% of power generation from renewable sources by 2030 and over 90% by 2050 aim to decarbonize the electrical grid and increase electrification of transport, industry, and buildings. As renewable integration targets increase, participation in flexibility programs will be required from a much greater range of buildings and sites to balance grids hosting high levels of renewable generation. In this paper, an online implementation of a standardized flexibility assessment methodology, previously developed for offline contract negotiations between stakeholders, is modified to automate the assessment. The automated assessment is then linked to an aggregator-based multi-building or site optimization stage, enabling increased participation of multiple buildings and sites. To implement the assessment, models for individual flexible systems were reviewed, selected, and adapted, including physics-based, data-driven, and grey-box models. A review of optimization for flexibility found mixed-integer linear programming to be the optimal approach for the selection of flexible systems for demand response events. [ABSTRACT FROM AUTHOR]

ABSTRACTData-driven production scheduling and control systems are essential for manufacturing organisations to quickly adjust to the demand for a wide range of bespoke products, often within short lead times. This paper presents a self-learning framework that combines association rules and optimization techniques to create data-driven production scheduling. A new approach to predicting interruptions in the production process through association rules was implemented, using a mathematical model to sequence production activities in real or near real-time. The framework was tested in a case study of a ceramics manufacturer, updating confidence values by comparing planned values to actual values recorded during production control. It also sets a production corrective factor based on confidence value and success rate to avoid product shortages. The results were generated in just 1.25 seconds, resulting in a makespan reduction of 9% and 6% compared to two heuristics based on First-In-First-Out and Short Processing Time strategies.

The introduction of Industry 4.0 and its driving technologies enables companies to collect data from production systems. The increasing amount of data propels the development of data-driven methods for modeling and predictive analytics. The adoption of these models in battery cell production has been gaining attention over recent years, as the process chain, especially electrode production consists of complex and strongly interrelated process steps. This paper outlines a systematic approach for developing data-driven models in electrode production, including the topic of digitalization and identification of data points. The framework supports practitioners towards digitalization and analysis of interdependencies in electrode production. [ABSTRACT FROM AUTHOR]

Introduction: Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components. Method: A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy. Results: The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31–60 min in 34%, 61–90 min in 11%, 91–120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%). Conclusion: The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance.

The lack of gas turbine field data, especially faulty engine data, and the complexity of fault embedding into gas turbines on test benches cause difficulties in representing healthy and faulty engines in diagnostic algorithms. Instead, different gas turbine models are often used. The available models fall into two main categories: physics-based and data-driven. Given the models’ importance and necessity, a variety of simulation tools were developed with different levels of complexity, fidelity, accuracy, and computer performance requirements. Physics-based models constitute a diagnostic approach known as Gas Path Analysis (GPA). To compute fault parameters within GPA, this paper proposes to employ a nonlinear data-driven model and the theory of inverse problems. This will drastically simplify gas turbine diagnosis. To choose the best approximation technique of such a novel model, the paper employs polynomials and neural networks. The necessary data were generated in the GasTurb software for turboshaft and turbofan engines. These input data for creating a nonlinear data-driven model of fault parameters cover a total range of operating conditions and of possible performance losses of engine components. Multiple configurations of a multilayer perceptron network and polynomials are evaluated to find the best data-driven model configurations. The best perceptron-based and polynomial models are then compared. The accuracy achieved by the most adequate model variation confirms the viability of simple and accurate models for estimating gas turbine health conditions.

In this paper, we propose an evolutionary learning approach for flexible identification of custom composite models for classification problems. To solve this problem in an efficient way, the problem-specific evolutionary operators are proposed and the effectiveness of different modifications of the common genetic programming algorithm is investigated. Also, several implementations of caching for the fitted models were compared from the performance point of view. To verify the proposed algorithm, both synthetic and real-world classification cases are examined. The implemented solution can identify the structure of the composite models from scratch, as well as be used as a part of automated machine learning solutions. [ABSTRACT FROM AUTHOR]

This paper presents a novel framework architecture for an online, real-time flexibility assessment and activation platform targeted at unlocking the flexibility potential of commercial buildings and smaller industrial sites, thereby enabling greater levels of renewable grid integration. Renewable integration targets in Europe of up to 40% of power generation from renewable sources by 2030 and over 90% by 2050 aim to decarbonize the electrical grid and increase electrification of transport, industry, and buildings. As renewable integration targets increase, participation in flexibility programs will be required from a much greater range of buildings and sites to balance grids hosting high levels of renewable generation. In this paper, an online implementation of a standardized flexibility assessment methodology, previously developed for offline contract negotiations between stakeholders, is modified to automate the assessment. The automated assessment is then linked to an aggregator-based multi-building or site optimization stage, enabling increased participation of multiple buildings and sites. To implement the assessment, models for individual flexible systems were reviewed, selected, and adapted, including physics-based, data-driven, and grey-box models. A review of optimization for flexibility found mixed-integer linear programming to be the optimal approach for the selection of flexible systems for demand response events.

The availability of building operational data such as energy use and indoor temperature provides opportunities to enhance the traditional building energy performance calculation. Disaggregated building energy use facilitates informed decision-making to identify cost-saving measures efficiently at the individual building and building stock levels. The existing energy performance analysis techniques with measured input data in the literature are fragmented. Moreover, they frequently approach this issue with varying degrees of complexity depending on the available input data, expertise, and time. The procedure of choosing an appropriate method is often cumbersome with limited indication of the usefulness of the outcomes. This study proposes a data-driven framework for end-use load disaggregation through techniques that exploit various kinds of building consumption data. The results demonstrate the use of different techniques for varied applications. Calibrated theoretical calculation, data-driven heat loss coefficient (HLC), and energy signature curve (ESC) are among the proposed methods in the framework that facilitate individual, and urban scale energy decomposition. It is observed that different methods yield unalike outcomes, while their performance is predictable. While the HLC methods are flexible but also highly sensitive to the input parameters, the ESC needs high-frequency time series but provides stable energy decomposition. The ESC is efficient for large-scale analysis and the HLC method for detailed case-specific applications. Calibrated theoretical energy decomposition has a simple workflow and can supplement the current energy performance assessment method, although it entails sufficient input data. [ABSTRACT FROM AUTHOR]

Buildings' heating, ventilation, and air-conditioning (HVAC) systems account for significant global energy use. Proper maintenance can minimize their environmental footprint and enhance the quality of the indoor environment. The adoption of Internet of Things (IoT) sensors integrated into HVAC systems has paved the way for predictive maintenance (PdM) grounded in real-time operational metrics. However, HVAC systems without such sensors cannot leverage the advantages of current data-driven PdM techniques. This work introduces a novel data-driven framework, the health prognostics classification with autoencoders (HPC-AE), designed specifically for PdM. It utilizes solely HVAC power consumption and outside temperature readings for its operations, both of which are readily obtainable. The primary objective of the HPC-AE framework is to facilitate PdM through a health prognostic approach. The HPC-AE framework utilizes an autoencoder for feature enrichment and then applies an artificial neural network to classify the daily health condition of an HVAC system. A multi-objective evaluation metric is employed to ensure optimal performance of the autoencoder within this framework. This metric evaluates the autoencoder's proficiency in reducing reconstruction discrepancies in standard data conditions and its capability to differentiate between standard and degraded data scenarios. The HPC-AE framework is validated in two HVAC fault scenarios, including a clogged air filter and air duct leakage. The experimental results show that compared to methods used in similar studies, HPC-AE exhibits a 5.7% and 2.1% increase in the F1 score for the clogged air filter and duct leakage scenarios. [ABSTRACT FROM AUTHOR]

In-cylinder pressure is a key parameter for assessing marine engines health; therefore, its measurement or prediction is paramount for these engines' diagnosis. Thermodynamic models are typically employed for predicting the in-cylinder pressure, which, however, face challenges pertinent to their calibration and computational time requirements. Recent advances in the field of machine learning have leveraged the development of data-driven models. This study aims to compare two approaches for input features and six regression techniques to select the most effective combination for developing data-driven models to predict the in-cylinder pressure of marine four-stroke engines. Two approaches with different input and output features are initially compared. The first employs regression to directly predict the in-cylinder pressure signal, whereas the second predicts the harmonics coefficients by regression and subsequently estimates the in-cylinder pressure by using a Fourier series function. Typical regression techniques, including linear, elastic, and polynomial regression, support vector machines (SVM), decision trees (DT), and artificial neural networks (ANN), are employed to develop data-driven models based on the second approach. The required datasets for training and testing are derived by using a physical digital twin for the investigated marine engine, which is calibrated against the shop trials and acquired shipboard measurements. The accuracy of the data-driven models are estimated based on the root mean square error considering the testing datasets. For the data-driven model based on the second approach and the ANN regression, a sensitivity study is carried out considering the training datasets and the harmonics number to derive recommendations for these parameters' values. The results demonstrate that the second approach provides higher accuracy, whereas the ANN regression is the most effective technique for developing data-driven models to estimate the in-cylinder pressure, as the exhibited root mean square error is retained within ± 0.2 bar for the ANN trained with 20 samples. This study supports the development and use of data-driven models for marine engines health diagnosis. [ABSTRACT FROM AUTHOR]

Abstract: A bootstrap aggregated model approach to the estimation of product quality in refineries with varying crudes is proposed in this paper. The varying crudes cause the relationship between process variables and product quality variables to change, which makes product quality estimation by soft-sensors a difficult problem. The essential idea in this paper is to build an inferential estimation model for each type of feed oil and use an on-line feed oil classifier to determine the feed oil type. Bootstrap aggregated neural networks are used in developing the on-line feed oil classifier and a bootstrap aggregated partial least square regression model is developed for each data group corresponding to each type of feed crude oil. The amount of training data in crude oil distillation is usually small and this brings difficulties for classification and estimation modelling. In order to enhance model reliability and robustness, bootstrap aggregated models are developed. The inferential estimation results of kerosene dry point on both simulated data and industrial data show that the proposed method can significantly improve the overall inferential estimation performance. [Copyright &y& Elsevier]

Data-driven models based on thermal resistor-capacitor networks (RC models) are useful in enhancing the energy performance of buildings. This paper presents a simple yet effective methodology to obtain reliable RC models for thermal dynamics of houses. In this methodology, complex preliminary model structures are first created based on physical principles and then simplified by progressively removing non-identifiable parameters to obtain the most suitable model structures. Two important techniques are adopted in the simplification process: (1) a genetic algorithm is employed during model training to ensure satisfactory fitting ability of large model structures; (2) asymptotic confidence intervals are calculated for parameter estimates and used to define parameter non-identifiability. The methodology is illustrated using a case study of a low energy house. The case study shows that the uncertainty of the obtained model is low, and the model parameters can be easily physically interpreted. Furthermore, validations of the simplified model structure show that there is no evident decrease in the fitting accuracy and the obtained model is able to characterize temperature differences between adjacent thermal zones. [ABSTRACT FROM AUTHOR]

The various real-world tasks of environmental management make it necessary to obtain the hindcasts and forecasts of natural events (wind, ocean waves and currents, sea ice, etc.) using data-driven techniques for metocean processes simulation. The models can be fitted to specific fragments of the non-stationary multivariate time series individually to reproduce metocean environment with desired characteristics. In the paper, the approach based on the LASSO regularised regression is proposed for the environmental time series clustering. It allows the identify the situations with specific interaction between variables, that can be interpreted by the values regression coefficients. The weather generator was used to produce both synthetic time series similar to the general dataset and the identified clusters. The obtained results can be used to increase the quality of the computationally lightweight environmental models' identification and interpretation. [ABSTRACT FROM AUTHOR]