Interval Prediction of Fuel Cell Degradation Based on Voltage Signal Frequency Characteristics with TimesNet-GPR under Dynamic Conditions

IF 9.7 1区 环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL
Wenchao Zhu, Yongjia Li, Yafei Xu, Leiqi Zhang, Bingxin Guo, Rui Xiong, Changjun Xie
{"title":"Interval Prediction of Fuel Cell Degradation Based on Voltage Signal Frequency Characteristics with TimesNet-GPR under Dynamic Conditions","authors":"Wenchao Zhu, Yongjia Li, Yafei Xu, Leiqi Zhang, Bingxin Guo, Rui Xiong, Changjun Xie","doi":"10.1016/j.jclepro.2024.144503","DOIUrl":null,"url":null,"abstract":"Proton exchange membrane fuel cells (PEMFCs) are crucial modern sustainable energy generation devices. The accurate assessment of their state of health (SOH) and the forecast of their remaining useful life (RUL) are critical for their practical deployment. Current mainstream methods typically use time-domain voltage decay as the health indicator (HI) and rely on recurrent neural networks. However, PEMFC voltage decay results from multiple factors, including internal component degradation, changes in operating conditions, and environmental impacts. Low-frequency domain analysis can effectively detect degradation in the proton exchange membrane and gas diffusion layer, leading to more accurate SOH estimation for fuel cells. This study reshapes time-domain voltage signals into frequency factors in a 2D space based on frequency domain features to more accurately reflect the aging characteristics of PEMFCs. We propose a TimesNet-GPR method to accurately quantify the uncertainty in degradation prediction, demonstrating good adaptability with different lengths of training data and various dynamic conditions. This method uses TimesNet for point estimation prediction, overcoming the limitations of neural networks in capturing long-term dependencies, improving point estimation accuracy by 39.18% to 70.14% on dynamic cycling condition datasets. In order to evaluate uncertainty during point estimation and provide more accurate confidence interval predictions, Gaussian Process Regression (GPR), is utilized.","PeriodicalId":349,"journal":{"name":"Journal of Cleaner Production","volume":"1 1","pages":""},"PeriodicalIF":9.7000,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cleaner Production","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1016/j.jclepro.2024.144503","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Proton exchange membrane fuel cells (PEMFCs) are crucial modern sustainable energy generation devices. The accurate assessment of their state of health (SOH) and the forecast of their remaining useful life (RUL) are critical for their practical deployment. Current mainstream methods typically use time-domain voltage decay as the health indicator (HI) and rely on recurrent neural networks. However, PEMFC voltage decay results from multiple factors, including internal component degradation, changes in operating conditions, and environmental impacts. Low-frequency domain analysis can effectively detect degradation in the proton exchange membrane and gas diffusion layer, leading to more accurate SOH estimation for fuel cells. This study reshapes time-domain voltage signals into frequency factors in a 2D space based on frequency domain features to more accurately reflect the aging characteristics of PEMFCs. We propose a TimesNet-GPR method to accurately quantify the uncertainty in degradation prediction, demonstrating good adaptability with different lengths of training data and various dynamic conditions. This method uses TimesNet for point estimation prediction, overcoming the limitations of neural networks in capturing long-term dependencies, improving point estimation accuracy by 39.18% to 70.14% on dynamic cycling condition datasets. In order to evaluate uncertainty during point estimation and provide more accurate confidence interval predictions, Gaussian Process Regression (GPR), is utilized.
质子交换膜燃料电池(PEMFC)是现代可持续能源生产的关键设备。准确评估其健康状况(SOH)和预测其剩余使用寿命(RUL)对其实际应用至关重要。目前的主流方法通常使用时域电压衰减作为健康指标(HI),并依赖于递归神经网络。然而,PEMFC 电压衰减是由多种因素造成的,包括内部组件退化、运行条件变化和环境影响。低频域分析可有效检测质子交换膜和气体扩散层的退化,从而更准确地估计燃料电池的 SOH。本研究根据频域特征将时域电压信号重塑为二维空间中的频率因子,以更准确地反映 PEMFC 的老化特性。我们提出了一种 TimesNet-GPR 方法,用于准确量化降解预测中的不确定性,在不同长度的训练数据和各种动态条件下均表现出良好的适应性。该方法使用 TimesNet 进行点估算预测,克服了神经网络在捕捉长期依赖性方面的局限性,在动态循环条件数据集上提高了 39.18% 至 70.14% 的点估算精度。为了评估点估算过程中的不确定性,并提供更准确的置信区间预测,采用了高斯过程回归(GPR)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Cleaner Production
Journal of Cleaner Production 环境科学-工程:环境
CiteScore
20.40
自引率
9.00%
发文量
4720
审稿时长
111 days
期刊介绍: The Journal of Cleaner Production is an international, transdisciplinary journal that addresses and discusses theoretical and practical Cleaner Production, Environmental, and Sustainability issues. It aims to help societies become more sustainable by focusing on the concept of 'Cleaner Production', which aims at preventing waste production and increasing efficiencies in energy, water, resources, and human capital use. The journal serves as a platform for corporations, governments, education institutions, regions, and societies to engage in discussions and research related to Cleaner Production, environmental, and sustainability practices.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信