基于集成型极限学习机的PEMFC寿命预测研究

doi:10.19595/j.cnki.1000-6753.tces.240123

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3047 KB)
输出: BibTeX | EndNote (RIS)

摘要

基于数据驱动的寿命预测方法能精准预测质子交换膜燃料电池（PEMFC）的剩余使用寿命,预测性能的提高是当前寿命预测领域的研究热点。针对PEMFC寿命预测过程中预测精度与鲁棒性的提升问题,基于统计学原理的寿命预测方法,提出一种集成极限学习机（EELM）结构,对PEMFC的寿命进行长期预测。集成结构中包含了50次重复测试,通过局部强化优化器算法对每次测试结果进行优化,提升了寿命预测精度。在长期预测的结果中,给出了EELM预测结果的平均值和95%置信区间,提升了系统的鲁棒性。最后采用稳态电流、准动态电流条件和动态电流下的老化数据集验证了所提出方法的有效性与可行性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨淇
	陈景文
	华志广
	李祥隆
	赵冬冬
	兰天一
	窦满峰

关键词 ：质子交换膜燃料电池, 极限学习机, 集成结构, 局部强化优化器

Abstract：

Data-driven methods can accurately predict the remaining useful lifetime of the proton exchange membrane fuel cell (PEMFC), the improvement of the prediction performance is the current research hotspot in the field of lifetime prediction. Aiming to improve prediction accuracy and robustness in the lifetime prediction field of PEMFC, an ensemble extreme learning machine (ELM) structure is proposed to predict the lifetime of PEMFC in the long term based on the statistical lifetime prediction principle. The ensemble structure contains 50 times repetitive tests, and for each ELM, it is optimized by the partial reinforcement optimizer algorithm, which improves the lifetime prediction accuracy.
Firstly, the aging data were filtered by the moving average filtering method to filter out the noise and spikes to get smooth data. Then an ensemble extreme learning machine (EELM) model is introduced to predict the lifetime of the PEMFC in the long term by independent ELMs in the ensemble structure. The EELM model adopts a multi-input structure and optimizes the input weights and hidden layer bias by Partial Reinforcement Optimizer to improve the model's generalization ability and prediction accuracy. After that, the prediction results are assembled, and the ensemble structure contains 50 independent ELMs, and the 50 times prediction results are statistically analyzed. Assuming the weights of the 50 times predictions are the same, the final prediction value is obtained by averaging the predictions at each time point. In the results of the long-term prediction, the average and 95% confidence interval of the prediction results of the ensemble ELM are given. To verify the validity and feasibility of the proposed method, three sets of aging data sets under steady-state, quasi-dynamic and dynamic conditions are verified. Based on the experiments, it can be obtained that the RMSE of the proposed method is 0.010 44 and the MAPE is 0.221 8% under steady state, 0.023 73 and 0.6296% under quasi-dynamic, and 0.004 861 and 7.716% under dynamic. Comparing the prediction results with the cycle reservoir with jump (CRJ), echo state network (ESN), and group method of data handling (GMDH) in the past literature, the EELM model can obtain more accurate results with less training data. This effectively reflects the fact that EELM has a stronger generalization ability. The robustness of the EELM is also analyzed in these three conditions. For the robustness analysis, the ELM and EELM are subjected to 50 repetitions of experiments, and the RMSE is used as the evaluation index. The experimental results show that the prediction accuracy of the EELM is higher than that of most of the independent ELMs, and the prediction results of EELM are less fluctuating and more centrally distributed. This indicates that the EELM prediction is more stable, and the ensemble structure effectively improves the robustness of the ELM.
The validation results show that: (1) the randomness of input weights and hidden layer bias will directly affect the results of lifetime prediction, which is statistically analyzed by the EELM structure with 95% confidence intervals, and the distribution of the prediction results can be observed. The prediction accuracy can be improved by averaging the prediction results. (2) The robustness is improved. Statistical analysis of the prediction results through the ensemble structure can improve the stability and accuracy of the prediction, which is more obvious in the quasi-dynamic and dynamic conditions. Getting the prediction results through ensemble averaging can improve the prediction accuracy and enhance the system's robustness. (3) Combining ELM with other prediction methods to find methods that can effectively implement online prediction and improve prediction accuracy will be the focus of research in future work.

Key words： Proton exchange membrane fuel cell (PEMFC) extreme learning machine (ELM) ensemble structure partial reinforcement optimizer

收稿日期: 2024-01-18

PACS:

TM911.42

基金资助:

国家自然科学基金（52307251,52277226）和中国博士后科学基金（2023TQ0277,2023M742840）资助

通讯作者: 华志广男,1990年生,教授、博导,研究方向为氢燃料电池寿命预测与健康管理。E-mail：zhiguang.hua@nwpu.edu.cn

作者简介: 杨淇男,2000年生,硕士研究生,研究方向为氢燃料电池寿命预测与健康管理。E-mail：yan9qi97@163.com

引用本文:

杨淇, 陈景文, 华志广, 李祥隆, 赵冬冬, 兰天一, 窦满峰. 基于集成型极限学习机的PEMFC寿命预测研究[J]. 电工技术学报, 0, (): 2492905-2492905. Yang Qi, Chen Jingwen, Hua Zhiguang, Li Xianglong, Zhao Dongdong, Lan Tianyi, Dou Manfeng. Research on PEMFC Lifetime Prediction Based on Ensemble Extreme Learning Machine. Transactions of China Electrotechnical Society, 0, (): 2492905-2492905.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.240123 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/2492905

[1] 陈锦洲, 林飞, 何洪文, 等. 质子交换膜燃料电池/电解槽系统建模及负荷追踪策略[J]. 电工技术学报, 2020, 35(增刊2): 636-643.
Chen Jinzhou, Lin Fei, He Hongwen, et al.Modeling and load tracking strategy of proton exchange membrane fuel cell/electrolyzer system[J]. Transactions of China Electrotechnical Society, 2020, 35(S2): 636-643.
[2] 潘光胜, 顾伟, 张会岩, 等. 面向高比例可再生能源消纳的电氢能源系统[J]. 电力系统自动化, 2020, 44(23): 1-10.
Pan Guangsheng, Gu Wei, Zhang Huiyan, et al.Electricity and hydrogen energy system towards accomodation of high proportion of renewable energy[J]. Automation of Electric Power Systems, 2020, 44(23): 1-10.
[4] Li Qi, Wang Tianhong, Li Shihan, et al.Online extremum seeking-based optimized energy management strategy for hybrid electric tram considering fuel cell degradation[J]. Applied Energy, 2021, 285: 116505.
[4] 张雪霞, 黄平, 蒋宇, 等. 动态机车工况下质子交换膜燃料电池电堆衰退性能分析[J]. 电工技术学报, 2022, 37(18): 4798-4806.
Zhang Xuexia, Huang Ping, Jiang Yu, et al.Degradation performance analysis of proton exchange membrane fuel cell stack under dynamic locomotive conditions[J]. Transactions of China Electrotechnical Society, 2022, 37(18): 4798-4806.
[5] Jouin M, Gouriveau R, Hissel D, et al.Prognostics of PEM fuel cell in a particle filtering framework[J]. International Journal of Hydrogen Energy, 2014, 39(1): 481-494.
[6] Chen Kui, Laghrouche S, Djerdir A.Fuel cell health prognosis using Unscented Kalman Filter: Postal fuel cell electric vehicles case study[J]. International Journal of Hydrogen Energy, 2019, 44(3): 1930-1939.
[7] Bressel M, Hilairet M, Hissel D, et al.Remaining useful life prediction and uncertainty quantification of proton exchange membrane fuel cell under variable load[J]. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2569-2577.
[8] Zuo Jian, Lv Hong, Zhou Daming, et al.Deep learning based prognostic framework towards proton exchange membrane fuel cell for automotive application[J]. Applied Energy, 2021, 281: 115937.
[9] 唐钧涛, 戚志东, 裴进, 等. 基于电荷泵的燃料电池有源网络升压变换器[J]. 电工技术学报, 2022, 37(4): 905-917.
Tang Juntao, Qi Zhidong, Pei Jin, et al.An active network DC-DC boost converter with a charge pump employed in fuel cells[J]. Transactions of China Electrotechnical Society, 2022, 37(4): 905-917.
[10] Tang Xingwang, Qin Xiaojin, Wei Kai, et al.A novel online degradation model for proton exchange membrane fuel cell based on online transfer learning[J]. International Journal of Hydrogen Energy, 2023, 48(36): 13617-13632.
[11] Peng Yulin, Chen Tao, Xiao Fei, et al.Remaining useful lifetime prediction methods of proton exchange membrane fuel cell based on convolutional neural network-long short-term memory and convolutional neural network-bidirectional long short-term memory[J]. Fuel Cells, 2023, 23(1): 75-87.
[12] He Kai, Mao Lei, Yu Jianbo, et al.Long-term performance prediction of PEMFC based on LASSO-ESN[J]. IEEE Transactions on Instrumentation and Measurement, 1964, 70: 3511611.
[13] Jin Jiashu, Chen Yuepeng, Xie Changjun, et al.Remaining useful life prediction of PEMFC based on the multi-input cycle reservoir with jump network[J]. International Journal of Hydrogen Energy, 2023, 48(34): 12844-12860.
[14] Zhang Chu, Hu Haowen, Ji Jie, et al.An evolutionary stacked generalization model based on deep learning and improved grasshopper optimization algorithm for predicting the remaining useful life of PEMFC[J]. Applied Energy, 2023, 330: 120333.
[15] 赵波, 张领先, 章雷其, 等. PEMFC剩余使用寿命直接预测的混合方法[J/OL]. 中国电机工程学报, 2023: 1-14. https://doi.org/10.13334/j.0258-8013.pcsee.230769.
Zhao Bo, Zhang Lingxian, Zhang Leiqi, Xie Changjun, Chen Zhe, Liu Xiangwan. A Hybrid Method for Direct Prediction of PEMFC Remaining Useful Life[J]. Proceedings of the CSEE, 2023: 1-14. https://doi.org/10.13334/j.0258-8013.pcsee.230769.
[16] Ma Rui, Xie Renyou, Xu Liangcai, et al.A hybrid prognostic method for PEMFC with aging parameter prediction[J]. IEEE Transactions on Transportation Electrification, 2021, 7(4): 2318-2331.
[17] Cheng Yujie, Zerhouni N, Lu Chen.A hybrid remaining useful life prognostic method for proton exchange membrane fuel cell[J]. International Journal of Hydrogen Energy, 2018, 43(27): 12314-12327.
[18] Chen Kui, Laghrouche S, Djerdir A.Degradation model of proton exchange membrane fuel cell based on a novel hybrid method[J]. Applied Energy, 2019, 252: 113439.
[19] Dong Qichao, Zhou Yafu, Lian Jing, et al.Online adaptive humidity monitoring method for proton exchange membrane fuel cell based on fuzzy C-means clustering and online sequence extreme learning machine[J]. Electrochimica Acta, 2022, 429: 141059.
[20] Xie Yucen, Zou Jianxiao, Li Zhongliang, et al.A novel deep belief network and extreme learning machine based performance degradation prediction method for proton exchange membrane fuel cell[J]. IEEE Access, 2020, 8: 176661-176675.
[21] Zhang Xuexia, Yu Zixuan, Chen Weirong.Life prediction based on D-S ELM for PEMFC[J]. Energies, 2019, 12(19): 3752.
[22] Deng Zhihua, Chan S H, Chen Qihong, et al.Efficient degradation prediction of PEMFCs using ELM-AE based on fuzzy extension broad learning system[J]. Applied Energy, 2023, 331: 120385.
[23] 刘嘉蔚, 李奇, 陈维荣, 等. 基于核超限学习机和局部加权回归散点平滑法的PEMFC剩余使用寿命预测方法[J]. 中国电机工程学报, 2019, 39(24): 7272-7279, 7500.
Liu Jiawei, Li Qi, Chen Weirong, et al.Remaining useful life prediction method of PEMFC based on kernel extreme learning machine and locally weighted scatterplot smoothing[J]. Proceedings of the CSEE, 2019, 39(24): 7272-7279, 7500.
[24] Li Changzhi, Lin Wei, Wu Hangyu, et al.Performance degradation decomposition-ensemble prediction of PEMFC using CEEMDAN and dual data-driven model[J]. Renewable Energy, 2023, 215: 118913.
[25] Xia Zetao, Wang Yining, Ma Longhua, et al.A hybrid prognostic method for proton-exchange-membrane fuel cell with decomposition forecasting framework based on AEKF and LSTM[J]. Sensors, 2022, 23(1): 166.
[26] Hua Zhiguang, Zheng Zhixue, Pahon E, et al.Remaining useful life prediction of PEMFC systems under dynamic operating conditions[J]. Energy Conversion and Management, 2021, 231: 113825.
[27] Hua Zhiguang, Zheng Zhixue, Pahon E, et al.A review on lifetime prediction of proton exchange membrane fuel cells system[J]. Journal of Power Sources, 2022, 529: 231256.
[28] Liu Hao, Chen Jian, Hou Ming, et al.Data-based short-term prognostics for proton exchange membrane fuel cells[J]. International Journal of Hydrogen Energy, 2017, 42(32): 20791-20808.
[29] Mezzi R, Morando S, Steiner N Y, et al.Multi-reservoir echo state network for proton exchange membrane fuel cell remaining useful life prediction[C]//IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA, 2018: 1872-1877.