Search

Opposition-based differential evolution (ODE) is a well-known DE variant that employs opposition-based learning (OBL) to accelerate the convergence speed. However, the existing OBL variants are population-based, which causes many shortcomings. The value of the jumping rate is not self-adaptively adjusted, so the algorithm easily traps into local optima. The population-based OBL wastes fitness evaluations when the algorithm converges to sub-optimal. In this paper, we proposed a novel OBL called subpopulation-based OBL (SPOBL) with a self-adaptive parameter control strategy. In SPOBL, the jumping rate acts on the individual, and the subpopulation is selected according to the individual’s jumping rate. In the self-adaptive parameter control strategy, the surviving individual’s jumping rate in each iteration will participate in the self-adaptive process. A generalized Lehmer mean is introduced to achieve an equilibrium between exploration and exploitation. We used DE and advanced DE variants combined with SPOBL to verify performance. The results of performance are evaluated on the CEC 2017 and CEC 2020 test suites. The SPOBL shows better performance compared to other OBL variants in terms of benchmark functions as well as real-world constrained optimization problems.

A collaborative design method for multi-types of graphite end plates geometric parameters, membrane electrolyte assembly physical parameters, and operating parameters, was novelly developed to break bounds of parameter types for design stage and operational stage matching in fuel cells. A multi-step design method, assisted by a surrogate-assisted hierarchical particle swarm optimization algorithm, was used for the optimal design of multi-type parameters. During this multi-step design process, the initial experiments are implemented following the design of experiments, and further experiments are adaptively carried out under the guidance of the layered optimization method. Experimental evidence of cell performance response to the coupled effects of multi-parameters was firstly provided and discussed in details. The collaborative design of multi-type parameters realized using the proposed multi-step design method was proven to improve the energy conversion efficiency by 10.9%. Different performance requirements, from single to multiple objectives in various types of fuel cells, were also shown to be fulfilled using this collaborative design method.

Automatic driving of trains can significantly reduce the energy cost and enhance the operating efficiency and safety. The automatic train driving system has to be an embedded system that can run onboard with low power, which necessitates an efficient inference model. In this article, a level-wise driving knowledge induction approach is proposed for embedded automatic train driving systems. The coincident driving patterns in the records of drivers with different experience levels suggest the suitability of a driving experience knowledge rule induction approach. We design a two-level learning approach to obtain both the driving experience pattern in fuzzy rule-based knowledge form and the detailed parameters of velocity and gear by regression learning methods. With 8.93% energy consumption reduction compared with average human drivers, the experiments indicate the effectiveness of our approach.

One new cycloartane triterpene bisdesmoside, soulieoside U, was isolated from the rhizomes of Actaea vaginata. Its structure was elucidated by extensive analysis of the NMR and MS data. Soulieoside...

The “Curse of Dimensionality” induced by the rapid development of information science might have a negative impact when dealing with big datasets, and it also makes the problems of symmetry and asymmetry increasingly prominent. Feature selection (FS) can eliminate irrelevant information in big data and improve accuracy. As a recently proposed algorithm, the Sparrow Search Algorithm (SSA) shows its advantages in the FS tasks because of its superior performance. However, SSA is more subject to the population’s poor diversity and falls into a local optimum. Regarding this issue, we propose a variant of the SSA called the Tent Lévy Flying Sparrow Search Algorithm (TFSSA) to select the best subset of features in the wrapper-based method for classification purposes. After the performance results are evaluated on the CEC2020 test suite, TFSSA is used to select the best feature combination to maximize classification accuracy and simultaneously minimize the number of selected features. To evaluate the proposed TFSSA, we have conducted experiments on twenty-one datasets from the UCI repository to compare with nine algorithms in the literature. Nine metrics are used to evaluate and compare these algorithms’ performance properly. Furthermore, the method is also used on the coronavirus disease (COVID-19) dataset, and its classification accuracy and the average number of feature selections are 93.47% and 2.1, respectively, reaching the best. The experimental results and comparison in all datasets demonstrate the effectiveness of our new algorithm, TFSSA, compared with other wrapper-based algorithms.

A new cycloartane triterpene bisdesmoside, soulieoside T (1), and one known compound, oleanolic acid (2), were isolated from the ethanolic extract of the rhizomes of Actaea vaginata. Their structures were elucidated by spectroscopic methods and by comparison with data reported in the literature. Compound 1 was evaluated for cytotoxic activities against three human cancer cell lines.

Non-uniform cross-sectional designs of serpentine channel in direct methanol fuel cells are systematically studied in the present work. A parametric design is proposed to describe and classify channel geometries whose effects on cell performance are numerically and experimentally analyzed. Numerical results show that the non-uniform converging designs are beneficial for both in- and through-plane methanol transportations, and thus to enhance the peak power generation performance as much as 12 % at high-current-density operations. Effectiveness of non-uniform designs for power generation enhancements is also validated by experimental studies which consider various operating conditions, and significant enhancement of power generation ( 18.4 % ) is noticed by the usage of non-uniform converging design. Optimal application conditions for the non-uniform converging designs are determined to be the high-current-density operations with high temperatures.

One new cycloartane triterpene bisdesmoside, soulieoside U, was isolated from the rhizomes of

An adaptive control strategy is developed for active degradation compensation of fuel cells, so as to improve output performance stability during long-time operation. Two groups of long-time tests of DMFC under different operating parameters are designed and implemented. The parameter adjustment significance that defines the adjusting priority is obtained from experimental analyses, based on which, the adaptive control strategy is developed and systematically tested. The results show that temporary degradation and permanent degradation for fuel cell performance could be differentiated in the process of performance degradation and recovery. The operation condition which would bring a higher energy conversion efficiency may lead to more serious degradations. The developed control strategy could help to adaptively alleviate fuel cell degradation during long-time operation. The temporary degradation and permanent degradation rates both decreased in daily operation, and the errors between output voltage and objective values are controlled within 2 %. The study provides an effective reference for improving the fuel cell stability during long-time operation and prolonging its service life.

Considering the effects of unpredictable disturbances, a robustness criterion is newly proposed to develop an integrated evaluation with modified efficiency criterion, for comprehensive assessments of energy conversion performances in direct methanol fuel cells. The effectiveness of developed criteria in various situations (including some extreme operating conditions) has been carefully analyzed based on both experimental and numerical results. For undisturbed operations, the modified efficiency criterion could help to avoid potential misinterpretations of energy conversion process in existing criteria. For disturbed operations, the robustness criterion concerning the effects of uncertainty propagations is shown to be an effective guidance for the determination of appropriate operating current densities to design efficiency-stabilized operations. Systematic analysis on its applications in different situations proves that, the integrated efficiency and robustness evaluations can effectively differentiate the effects of operating conditions and membrane types, which is highly beneficial for one’s optimal designs of stable and efficient DMFC operations.

A new cycloartane triterpene bisdesmoside, soulieoside T (

An adaptive operation strategy for on-demand control of active direct methanol fuel cells (DMFCs) is proposed as an alternative method to enhance the voltage stability. A simplified semi-empirical model is firstly developed to describe I-V relationships based on uniform-designed experiments. It is then embedded into multi-objective optimizations to construct the adaptive operation strategy. Experimental studies are implemented on different DMFC systems to validate the proposed semi-empirical model, control strategy and system response to operational adjustments. Numerical simulations are also performed to investigate the underlying mechanisms of the proposed adaptive operation strategy. The results show that the adaptive operation strategy provides possibilities for voltage stability enhancement without the sacrifice of energy conversion efficiency. The adaptive operations are also found to be able to extend the range of operating current density or to decrease the voltage deviation according to one's requirements. Moreover, the response of DMFCs to operational adjustments is quick, which further validates the effectiveness and feasibility of the adaptive operation strategy in practical applications. The proposed strategy contributes to a guideline for the better control of output voltage from operating DMFC systems., Comment: 36 pages, 10 figures

In this study, 12 known cycloartane triterpenoids (1–12) with four different skeletons isolated from the roots of Souliea vaginata were screened for the first time for in vitro anti-HIV activity using AZT as a standard. Among the compounds, beesioside I (1) showed the highest potency against HIV-1NL4-3 with an EC50 value of 2.32 μM (CC50 > 40 μM). Preliminary structure-activity relationship (SAR) studies on 1 indicated that simple modification of its aglycone (13) could significantly influence the antiviral activity. Particularly, the introduction of an acyl group at the C-3 position of 13 led to significant improvement in both anti-HIV potency and selectivity index. Among all synthetically modified derivatives, compound 13g was the most potent compound with an EC50 value of 0.025 μM and TI value greater than 800, comparable to those of 3-O-(3′,3′-dimethylsuccinyl)-betulinic acid (DSB, bevirimat). Other analogues exhibited strong to weak inhibition of HIV-1 replication in MT-4 cells. The length, carboxylic terminus, and C-3′ dimethyl substitution of the C-3 side chain substantially affected the anti-HIV activity. Finally, compound 13g was an effective agent against HIV with high potential for further investigation.

A joint operation method is proposed in this study for collaborative design of multi-type parameters in direct methanol fuel cell system. This method consists of adaptive numerical simulation for fuel cell operation and adaptive optimal design of the fuel cell system. The simulation key coefficients are designed to be changed following the multi-type parameters variations in order to achieve adaptive numerical simulation. An efficient optimization method surrogate-assisted meta-heuristic optimization algorithm is designed for adaptive optimal design. The data transmission would be realized between optimal design method and simulation process to serve for the joint operation process. The results show that adaptive numerical simulation could guarantee the simulation accuracy under different values of multi-type parameters. Meanwhile, the joint operation could significantly improve the efficiency for optimal design of parameters in DMFC system. Furthermore, the performance improvement has been validated by experiments with a 7.32% increment of energy conversion performance.

Railway transportation systems are the backbone of smart cities. With the rapid increasing of railway mileage, the energy consumption of train becomes a major concern. The uniqueness of train operations is that the geographic characteristics of each route is known a priori. On the other hand, the parameters (e.g., loads) of a train varies from trip to trip. Such a specialty determines that an energy-optimal driving profile for each train operation has to be pursued by considering both the geographic information and the inherent train conditions. The solution of the optimization problem, however, is hard due to its high dimension, nonlinearity, complex constraints and time-varying characteristics of a control sequence. As a result, an energy-saving solution to the train control optimization problem has to address the dilemma of optimization quality and computing time. This work proposes an energy-efficient train control framework by integrating both offline and onboard optimization techniques. The offline processing builds a decision tree based sketchy solution through a complete flow of sequence mining, optimization and machine learning. The onboard system feeds the train parameters into the decision tree to derive an optimized control sequence. A key innovation of this work is the identification of optimal patterns of control sequence by data mining the driving behaviors of the experienced train drivers and then apply the patterns to online trip planning. The proposed framework efficiently find an optimized driving solution by leveraging the training results derived with a compute-intensive offline learning flow. The framework was already testified in a smart freight train system. It was demonstrated an average of $9.84$ percent energy-saving can be achieved.

Hot plane strain compression tests of 6013 aluminum alloy were conducted within the temperature range of 613–773 K and the strain rate range of 0.001–10 s −1 . Based on the corrected experimental data with temperature compensation, Kriging method is selected to model the constitutive relationship among flow stress, temperature, strain rate and strain. The predictability and reliability of the constructed Kriging model are evaluated by statistical measures, comparative analysis and leave-one-out cross-validation (LOO-CV). The accuracy of Kriging model is validated by the R -value of 0.999 and the AARE of 0.478%. Meanwhile, its superiority has been demonstrated while comparing with the improved Arrhenius-type model. Furthermore, the generalization capability of Kriging model is identified by LOO-CV with 25 times of testing. It is indicated that Kriging method is competent to develop accurate model for describing the hot deformation behavior and predicting the flow stress even beyond the experimental conditions in hot compression tests.

Two-pass hot plane strain compression tests of 6013 aluminum alloy were conducted at different temperatures, strain rates, and holding times. Using the experimental data, four popular metamodel types – Kriging, radial basis function, polynomial regression and artificial neural network – were investigated as potential methods for global modeling of the flow behavior during two-pass deformation. The global model developed from the Kriging method was superior in terms of the accuracy and stability of the prediction. Furthermore, this model was successfully used to predict not only the two-pass deformation behavior beyond the experimental conditions, but also the multipass deformation behavior. It is proved that the Kriging method is an effective and reliable approach to develop a global model for optimization of the hot forming process.

An adaptive operation strategy for on-demand control of DMFC system is proposed as an alternative method to enhance the voltage stability. Based on a single-cell DMFC stack, a newly simplified semi-empirical model is developed from the uniform-designed experimental results to describe the I-V relationship. Integrated with this model, the multi-objective optimization method is utilized to develop an adaptive operation strategy. Although the voltage instability is frequently encountered in unoptimized operations, the voltage deviation is successfully decreased to a required level by adaptive operations with operational adjustments. Moreover, the adaptive operations are also found to be able to extend the range of operating current density or to decrease the voltage deviation according to ones requirements. Numerical simulations are implemented to investigate the underlying mechanisms of the proposed adaptive operation strategy, and experimental adaptive operations are also performed on another DMFC system to validate the adaptive operation strategy. Preliminary experimental study shows a rapid response of DMFC system to the operational adjustment, which further validates the effectiveness and feasibility of the adaptive operation strategy in practical applications. The proposed strategy contributes to a guideline for the better control of output voltage from operating DMFC systems.

The effect of flow field plate designs on the performance of a single-cell direct methanol fuel cell (DMFC) stack was investigated. Different from the regular serpentine flow field design in a square area, a novel variable length serpentine flow field in a circular area is designed. The two designs take the same channel width, channel depth, rib width and active area. Based on the experiments, a computational fluid dynamics (CFD) model was developed and simulated to investigate the reasons for this change in performances between two designs. The CFD simulation showed that fuel distribution and the local current density distribution on the catalyst layer was more uniform for the variable length serpentine flow field. Furthermore, the generated current density from the DMFC with variable length serpentine flow field is also higher than the regular serpentine flow field.

A new sampling method, namely weighted sequential sampling method, is introduced in this research to improve accuracy and efficiency of adaptive metamodeling considering influences of sample quality measures in both input and output parameter spaces. In this method, sample quality measures in input and output parameter spaces are associated with weighting factors. Values of these weighting factors are changed in sequential sampling considering the different levels of contributions of these sample quality measures in the input and output parameter spaces during the adaptive metamodeling process. Since quality of the metamodel developed through weighted sequential sampling is good in the whole design space, quality of global optimization can be improved through adaptive metamodeling based on weighted sequential sampling.

In this research, influences of two factors in adaptive metamodeling, noise level of samples and initial size of samples, are investigated through comparative study. Two cases of adaptive metamodeling considering the best output point for optimization and the best fit in a specific output parameter space are considered. Three different metamodels, kriging, radial basis function, and multivariate polynomial, are employed in this study. Various test functions are used to create the sample data and evaluate the quality and efficiency of the adaptive metamodeling methods considering influences of noise and initial size of samples. The results of this research provide guidelines for selecting appropriate adaptive metamodeling methods to solve various engineering problems. Effectiveness of the developed guidelines has been demonstrated through case study applications.

Modeling material flow behavior is an essential step to design and optimize the forming process. In this context, four popular metamodel types Kriging, radial basis function, multivariate polynomial, and artificial neural network are investigated as potential methods for modeling the flow behavior of 6013 aluminum alloy. Based on the experimental data from hot compression tests, the modeling performance of these four methods was tested and subsequently compared from different aspects. It is found that all the methods are capable of constructing models for describing the hot deformation behavior. The merits of Kriging method over other three methods are highlighted when the sample size for modeling is decreased. Furthermore, the applicability of Kriging method is validated while decreasing the sample uniformity with respect to temperature or strain rate. It is proved that Kriging method is competent in modeling the material flow behavior and is the most effective one among the four popular types of metamodeling method.

The control sequence optimization problem is difficult to solve due to its high nonlinearity, various constraints and the possible changes in the sequence of comprising elements at any instant of time. The optimization of train trip running profile is a typical control sequence optimization problem, whose optimization object is to minimize the energy consumption as well as the time deviation under various constraints. Engineers always have to face the trade-off between the optimization performance and calculation time for an onboard control system for such problems. This paper mainly proposed a framework of an offline to onboard system solution for control sequence optimization problems, specifically using on the train trip profile optimization problems. The framework choose the parameter-decision tree solution for the onboard control system, and then a series of offline procedures including sequence mining, optimal computation, and machine learning is proposed for getting the parameter-decision tree. The framework inherits the good optimization performance of offline systems, as well as guaranteed the onboard calculation time for real-time control. Performance on using such a framework for solving train trip profile optimization problems is shown in the literature, which shows the potentials of using such frameworks on solving related control sequence optimization problems.

A modified 3D numerical model on the energy conversion process in the anode side of a Direct Methanol Fuel Cell (DMFC) system was constructed and validated to published experimental results. Systematic simulations were performed to investigate the underlying mechanisms of the energy conversion process, and the combined effects of inlet flow rate and input methanol concentration were summarized systematically. The increase of flow rate was found to be an effective strategy to accelerate the internal flow fields, while the diffusion layer was proposed to be a critical component in the design of high-performance DMFC. The frontier for optimal conditions of DMFC’s output was also determined, which can be helpful to improve the energy conversion performance of DMFC in practical applications.

Published version of an article in the journal: Mathematical Problems in Engineering. Also available from the publisher at: http://dx.doi.org/10.1155/2014/965157 The performance index of a suspension system is a function of the maximum and minimum values over the parameter interval. Thus metamodel-based techniques can be used for designing suspension system hardpoints locations. In this study, an adaptive metamodel-based optimization approach is used to find the proper locations of the hardpoints, with the objectives considering the kinematic performance of the suspension. The adaptive optimization method helps to find the optimum locations of the hardpoints efficiently as it may be unachievable through manually adjusting. For each iteration in the process of adaptive optimization, prediction uncertainty is considered and the multiobjective optimization method is applied to optimize all the performance indexes simultaneously. It is shown that the proposed optimization method is effective while being applied in the kinematic performance optimization of a McPherson suspension system. © 2014 Qinwen Yang et al.