Remaining Useful Life Prediction Method of PEMFC Based on Kernel Extreme Learning Machine and Locally Weighted Scatterplot Smoothing

被引：0

作者：

Liu J. ^{[1
]}

Li Q. ^{[1
]}

Chen W. ^{[1
]}

Wang X. ^{[1
]}

Yan Y. ^{[1
]}

机构：

[1] School of Electrical Engineering, Southwest Jiaotong University, Chengdu, 611756, Sichuan Province

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2019年 / 39卷 / 24期

基金：

国家重点研发计划; 中国国家自然科学基金;

关键词：

Data driven; Kernel extreme learning machine; Proton exchange membrane fuel cell; Remaining useful life prediction;

D O I：

10.13334/j.0258-8013.pcsee.181614

中图分类号：

学科分类号：

摘要：

In order to solve the remaining useful life (RUL) problem of proton exchange membrane fuel cell (PEMFC), a novel RUL prediction method of PEMFC based on kernel extreme learning machine (KELM) and locally weighted scatterplot smoothing (LOESS) was proposed. The method used equal interval sampling and LOESS to realize data reconstruction and data smoothing. Not only can the main trend of the original data be preserved, but noise and spikes can be effectively removed. The KELM was adopted to predict the remaining life of the test data. This method can greatly reduce the computational complexity while ensuring the prediction accuracy. 1154-hour experimental analysis of PEMFC aging shows that the prediction accuracy of the novel method is 99.23%, the operation time is 0.0146 seconds, the mean absolute error and root mean square error are 0.0028 and 0.0037 respectively. The comparison analysis shows that the prediction accuracy of the novel method is 28.46% higher than that of BP neural network. The operation time, relative error, mean absolute error and root mean square error are all much less than that of BP neural network. Therefore, the novel method can quickly and accurately predict the remaining service life of PEMFC. © 2019 Chin. Soc. for Elec. Eng.

引用

页码：7272 / 7279

页数：7

共 18 条

[1] Chen W., Liu J., Li Q., Et al., Review and prospect of fault diagnosis methods for proton exchange membrane fuel cell, Proceedings of the CSEE, 37, 16, pp. 4712-4721, (2017)
[2] Zhao S., Wang B., Xie Y., Et al., Linear temperature sweep experimental study on proton exchange membrane fuel cell without external humidification, Proceedings of the CSEE, 34, 26, pp. 4528-4533, (2014)
[3] Li X., Cao G., Zhu X., Fuzzy modeling for PEMFC stack temperature characteristic, Journal of Shanghai Jiaotong University, 39, pp. 187-188, (2005)
[4] Zhao D., Hua Z., Zhang L., Et al., Flow control of fuel cell centrifugal compressor based on sliding modevariable structure, Journal of Northwestern Polytechnical University, 35, 3, pp. 374-379, (2017)
[5] Liu J., Luo W., Yang X., Et al., Robust model-based fault diagnosis for PEM fuel cell air-feed system, IEEE Transactions on Industrial Electronics, 65, 5, pp. 3261-3269, (2016)
[6] Xie C., Xu X., Bujlo P., Et al., Fuel cell and lithium iron phosphate battery hybrid powertrain with an ultracapacitor bank using direct parallel structure, Journal of Power Sources, 279, pp. 487-494, (2015)
[7] Hong L., Chen J., Liu Z., Et al., A nonlinear control strategy for fuel delivery in PEM fuel cells considering nitrogen permeation, International Journal of Hydrogen Energy, 42, 2, pp. 1565-1576, (2017)
[8] Yin L., Li Q., Hong Z., Et al., FFRLS Online identification and real-time optimal temperature generalized predictive control method of pemfc power generation system, Proceedings of the CSEE, 37, 11, pp. 3223-3235, (2017)
[9] Deng H., Li Q., Chen W., Research on HOSM observer for OER estimation of PEMFC system, Proceedings of the CSEE, 37, 17, pp. 5058-5068, (2017)
[10] Bressel M., Hilairet M., Hissel D., Et al., Extended kalman filter for prognostic of proton exchange membrane fuel cell, Applied Energy, 164, pp. 220-227, (2016)

← 1 2 →