{"title":"Multi‐step performance degradation prediction method for proton‐exchange membrane fuel cell stack using 1D convolution layer and CatBoost","authors":"Zehui Zhang, Tianhang Dong, Xiaobin Xu, Weiwei Huo, Bin Zuo, Leiqi Zhang","doi":"10.1002/acs.3860","DOIUrl":null,"url":null,"abstract":"The increasing environmental issues such as climate change and air pollution require energy saving and emission reduction in various fields, such as manufacturing, building, and transportation. To address the above problem, proton‐exchange membrane fuel cells (PEMFC) gradually become promising green energy conversion device due to the advantages of zero pollution, high efficiency, and low operating noise. However, the durability problem has extremely limited the PEMFC large‐scale commercial application. To prolong the service life of PEMFC, performance degradation prediction is an effective method. This paper proposes a multi‐step performance degradation prediction method for proton‐exchange membrane fuel cells based on CatBoost feature selection, convolution computing, and interactive learning mechanism. CatBoost is used to evaluate the importance of the monitor parameters on performance degradation. The evaluation results and PEMFC degradation mechanism analyses are used to select the monitor parameters for construing the prediction model. Based on the 1D convolutional layer and the interactive learning mechanism, the prediction model is proposed to extract the deep features from the monitor data to predict the performance degradation of the fuel cell system. In particular, the multi‐step prediction is performed by the configurable sliding window. The effectiveness of the proposed method is verified on real experiment datasets, and the experiment results show that the proposed method is particularly effective for multi‐step degradation prediction and decreases the computation by feature selection and 1D convolution layer.","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Adaptive Control and Signal Processing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1002/acs.3860","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
The increasing environmental issues such as climate change and air pollution require energy saving and emission reduction in various fields, such as manufacturing, building, and transportation. To address the above problem, proton‐exchange membrane fuel cells (PEMFC) gradually become promising green energy conversion device due to the advantages of zero pollution, high efficiency, and low operating noise. However, the durability problem has extremely limited the PEMFC large‐scale commercial application. To prolong the service life of PEMFC, performance degradation prediction is an effective method. This paper proposes a multi‐step performance degradation prediction method for proton‐exchange membrane fuel cells based on CatBoost feature selection, convolution computing, and interactive learning mechanism. CatBoost is used to evaluate the importance of the monitor parameters on performance degradation. The evaluation results and PEMFC degradation mechanism analyses are used to select the monitor parameters for construing the prediction model. Based on the 1D convolutional layer and the interactive learning mechanism, the prediction model is proposed to extract the deep features from the monitor data to predict the performance degradation of the fuel cell system. In particular, the multi‐step prediction is performed by the configurable sliding window. The effectiveness of the proposed method is verified on real experiment datasets, and the experiment results show that the proposed method is particularly effective for multi‐step degradation prediction and decreases the computation by feature selection and 1D convolution layer.
期刊介绍:
The International Journal of Adaptive Control and Signal Processing is concerned with the design, synthesis and application of estimators or controllers where adaptive features are needed to cope with uncertainties.Papers on signal processing should also have some relevance to adaptive systems. The journal focus is on model based control design approaches rather than heuristic or rule based control design methods. All papers will be expected to include significant novel material.
Both the theory and application of adaptive systems and system identification are areas of interest. Papers on applications can include problems in the implementation of algorithms for real time signal processing and control. The stability, convergence, robustness and numerical aspects of adaptive algorithms are also suitable topics. The related subjects of controller tuning, filtering, networks and switching theory are also of interest. Principal areas to be addressed include:
Auto-Tuning, Self-Tuning and Model Reference Adaptive Controllers
Nonlinear, Robust and Intelligent Adaptive Controllers
Linear and Nonlinear Multivariable System Identification and Estimation
Identification of Linear Parameter Varying, Distributed and Hybrid Systems
Multiple Model Adaptive Control
Adaptive Signal processing Theory and Algorithms
Adaptation in Multi-Agent Systems
Condition Monitoring Systems
Fault Detection and Isolation Methods
Fault Detection and Isolation Methods
Fault-Tolerant Control (system supervision and diagnosis)
Learning Systems and Adaptive Modelling
Real Time Algorithms for Adaptive Signal Processing and Control
Adaptive Signal Processing and Control Applications
Adaptive Cloud Architectures and Networking
Adaptive Mechanisms for Internet of Things
Adaptive Sliding Mode Control.