A Kepler optimization algorithm improved using a novel Lévy-Normal mechanism for optimal parameters selection of proton exchange membrane fuel cells: A comparative study DOI Creative Commons
Mohamed Abdel‐Basset, Reda Mohamed, Karam M. Sallam

и другие.

Energy Reports, Год журнала: 2024, Номер 11, С. 6109 - 6125

Опубликована: Июнь 1, 2024

Proton exchange membrane fuel cells (PEMFCs) are considered a promising renewable energy source and have sparked lot of interest over the last few years due to their robust efficiency, low operating temperature, longevity. The PEMFC's electrochemical model has seven unknown parameters, which not given in manufacturer's datasheets need be accurately estimated present more accurate model, leading improved efficiency performance PEMFC systems. estimation those parameters been dealt with as complex non-linear optimization problem that needs powerful algorithm solve it. existing algorithms still some disadvantages, such falling into local minima convergence speed, make them ineligible this complicated acceptable accuracy computational cost. Therefore, study presents new parameter technique for estimating accurately, thereby achieving precise modeling PEMFCs. This called IKOA is based on integrating Kepler (KOA) novel Lévy-Normal (LN) mechanism strengthen its exploration exploitation capabilities against multimodal problem. Lévy flight aims improve KOA's operator accelerate speed toward near-optimal solution, thus minimizing cost; meanwhile, normal distribution used operator, aiding escape minima. proposed KOA herein evaluated several rival using six well-known commercial stacks highlight effectiveness. Key metrics cost, fitness measures, statistical validation through Wilcoxon rank-sum test IKOA's effective enhancing predictive operational numerical findings show high superiority all optimizers solved benchmarks.

Язык: Английский

A novel method for remaining useful life of solid-state lithium-ion battery based on improved CNN and health indicators derivation DOI

Yan Ma,

Zhenxi Wang,

Jinwu Gao

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 220, С. 111646 - 111646

Опубликована: Июль 1, 2024

Язык: Английский

Процитировано

19
Heuristic Optimization Algorithm of Black-Winged Kite Fused with Osprey and Its Engineering Application DOI Creative Commons
Zheng Zhang, Xiangkun Wang, Yinggao Yue

и другие.

Biomimetics, Год журнала: 2024, Номер 9(10), С. 595 - 595

Опубликована: Окт. 1, 2024

Swarm intelligence optimization methods have steadily gained popularity as a solution to multi-objective issues in recent years. Their study has garnered lot of attention since problems hard high-dimensional goal space. The black-winged kite algorithm still suffers from the imbalance between global search and local development capabilities, it is prone even though combines Cauchy mutation enhance algorithm's ability. heuristic fused with osprey (OCBKA), which initializes population by logistic chaotic mapping fuses improve performance algorithm, proposed means enhancing ability (BKA). By using numerical comparisons CEC2005 CEC2021 benchmark functions, along other swarm solutions three engineering problems, upgraded strategy's efficacy confirmed. Based on experiment findings, revised OCBKA very competitive because can handle complicated high convergence accuracy quick time when compared comparable algorithms.

Язык: Английский

Процитировано

7
Fuel cell temperature control based on nonlinear transformation mitigating system nonlinearity DOI
Yaowang Pei, Fengxiang Chen, Jieran Jiao

и другие.

Renewable Energy, Год журнала: 2024, Номер 230, С. 120814 - 120814

Опубликована: Июнь 13, 2024

Язык: Английский

Процитировано

5
Short-term wind power prediction based on IBOA-AdaBoost-RVM DOI Creative Commons
Yongliang Yuan,

Qingkang Yang,

Jianji Ren

и другие.

Journal of King Saud University - Science, Год журнала: 2024, Номер 36(11), С. 103550 - 103550

Опубликована: Ноя. 22, 2024

Язык: Английский

Процитировано

5
Combined improved tuna swarm optimization with graph convolutional neural network for remaining useful life of engine DOI
Yongliang Yuan,

Qingkang Yang,

Guohu Wang

и другие.

Quality and Reliability Engineering International, Год журнала: 2024, Номер 41(1), С. 174 - 191

Опубликована: Авг. 28, 2024

Abstract Accurate prediction of the engine's remaining useful life (RUL) is essential to ensure safe operation aircraft because. However, traditional deep‐learning based methods for RUL has been limited by interpretability and adjustment hyperparameters in practical applications due intricate potential relations during degradation process. To address these dilemmas, an improved multi‐strategy tuna swarm optimization‐assisted graph convolutional neural network (IMTSO‐GCN) developed achieve this work. Specifically, mutual information used describe relationships among measured parameters so that they could be utilized building edges parameters. Besides, considering not all relational nodes will positively affect inherent GCN are high‐dimensional. Inspired “No Free Lunch (NFL)”, IMTSO proposed reduce optimization cost hyperparameters, which cycle chaotic mapping employed initialization population improving uniformity initial distribution. a novel adaptive approach enhance exploration exploitation (TSO). The CMAPSS dataset was validate effectiveness advancedness IMTSO‐GCN, experimental results show R 2 IMTSO‐GCN greater than 0.99, RMSE less 3, Score error within 1.

Язык: Английский

Процитировано

4
Short-term electrical load forecasting based on pattern label vector generation DOI
Haozhe Zhu,

Qingcheng Lin,

Xuefeng Li

и другие.

Energy and Buildings, Год журнала: 2025, Номер unknown, С. 115383 - 115383

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Improved sand cat swarm optimization algorithm assisted GraphSAGE-GRU for remaining useful life of engine DOI Creative Commons
Yongliang Yuan, Ruifang Li, Guohu Wang

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 26, 2025

Abstract With the development of deep learning, potential for its use in remaining useful life (RUL) has substantially increased recent years due to powerful data processing capabilities. However, relationships and interdependencies operation parameters non-Euclidean space are ignored utilizing current learning-based methods during degradation process engine. To address this challenge, an improved sand cat swarm optimization-assisted Graph SAmple aggregate gate recurrent unit (ISCSO-GraphSage-GRU) is proposed achieve RUL prediction work. Firstly, maximum information coefficient (MIC) utilized describing interdependent relations measured parameters. Building on foundation, constructed graph used as input GraphSage-GRU so overcoming shortcomings existing learning methods. Additionally, work optimization (ISCSO) improve predicted performance GraphSage-GRU, including tent mapping population initialization a novel adaptive approach enhance exploration exploitation optimization. The CMAPSS dataset validate effectiveness advancedness ISCSO-GraphSage-GRU, experimental results show that R 2 ISCSO-GraphSage-GRU greater than 0.99, RMSE less 6.

Язык: Английский

Процитировано

0
Joint Prediction of Li-Ion Battery Cycle Life and Knee Point Based on Early Charging Performance DOI Open Access

Xinru Cui,

Jinlong Zhang, Di Zhang

и другие.

Symmetry, Год журнала: 2025, Номер 17(3), С. 351 - 351

Опубликована: Фев. 26, 2025

With the rapid development of lithium-ion batteries, predicting battery life is critical to safe operation devices such as electric ships, vehicles, and energy storage systems. Given complexity internal aging mechanism their process exhibits prominent nonlinear characteristics. Knee point, a distinctive sign this process, plays crucial role in battery’s lifetime. In paper, cycle knee point are firstly predicted using time dimension space features early external characteristics battery, respectively. Then, capture batteries more comprehensively, we innovatively propose joint prediction method point. incorporated into model fully account for batteries. The experimental validation results show that TECAN model, which combines series information, performs well, with root mean square error (RMSE) 106 cycles absolute percentage (MAPE) only 12%.

Язык: Английский

Процитировано

0
A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models DOI
Hussein Mohammed Ridha, Hashim Hizam, Seyedali Mirjalili

и другие.

Next Energy, Год журнала: 2025, Номер 8, С. 100256 - 100256

Опубликована: Фев. 26, 2025

Язык: Английский

Процитировано

0
Semi-analytical dynamic modeling and impact mechanism analysis of a hard-coating cylindrical shell with arbitrary circular perforations DOI Creative Commons
Jian Yang, Yue Zhang

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 7, 2025

In this paper, an innovative axial domain decomposition method, which uniquely integrates and circumferential perforation parameters, is developed for semi-analytical modeling of free vibration a hard-coating cylindrical shell with arbitrary perforations, based on the Love's first-order shear deformation theory Rayleigh-Ritz method. The concept method to decompose into two types domains at upper lower boundaries circular perforations. generalized formulas perforated composite can be derived by assembling separated energy expressions each domain. Moreover, result analysis find that intrinsic influence mechanism number characteristics, is, precipitous alteration in natural frequency occurs only when ratio wave equals one divided odd as well even·number. special phenomenon provide important support reduction design shells aerospace engine.

Язык: Английский

Процитировано

0