A hybrid method for remaining useful life prediction of fuel cells under variable loads

被引：1

作者：

Wang, Chu ^{[1
,2
]}

Li, Zhongliang ^{[1
]}

Outbib, Rachid ^{[1
]}

Dou, Manfeng ^{[2
]}

机构：

[1] Aix Marseille Univ, LIS Lab, UMR CNRS 7020, F-13397 Marseille, France

[2] Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China

来源：

2022 10TH INTERNATIONAL CONFERENCE ON SYSTEMS AND CONTROL (ICSC) | 2022年

关键词：

PROGNOSTICS;

D O I：

10.1109/ICSC57768.2022.9993918

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Cost and durability are crucial factors limiting the widespread commercialization of proton exchange membrane fuel cells (PEMFC). Prognostics, aiming at health indicator extraction and remaining useful life prediction, is a key issue for PEMFC durability enhancement. However, deploying prognostics for PEMFC under dynamic load still faces challenges in extracting health indicators reliably and predicting the degradation evolution efficiently. This work proposes a data-driven PEMFC prognostics approach, in which Hilbert-Huang transform is used to extract health indicator in dynamic operating conditions and symbolic- based gated recurrent unit model is used to predict the remaining useful life. The proposed method is tested using long-term dynamic load ageing experiments. The results show that the method can provide reliable prognostics horizons and improve real-time performance.

引用

页码：174 / 177

页数：4

共 18 条

[1] Remaining Useful Life Prediction and Uncertainty Quantification of Proton Exchange Membrane Fuel Cell Under Variable Load [J].

Bressel, Mathieu ;

Hilairet, Mickael ;

Hissel, Daniel ;

Bouamama, Belkacem Ould .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (04) :2569-2577

[2]

Cho KYHY, 2014, Arxiv, DOI [arXiv:1406.1078, DOI 10.48550/ARXIV.1406.1078]

[3]

Chung JY, 2014, Arxiv, DOI [arXiv:1412.3555, 10.48550/arXiv.1412.3555]

[4] ABBA: adaptive Brownian bridge-based symbolic aggregation of time series [J].

Elsworth, Steven ;

Guttel, Stefan .

DATA MINING AND KNOWLEDGE DISCOVERY, 2020, 34 (04) :1175-1200

[5] A review on lifetime prediction of proton exchange membrane fuel cells system [J].

Hua, Zhiguang ;

Zheng, Zhixue ;

Pahon, Elodie ;

Pera, Marie-Cecile ;

Gao, Fei .

JOURNAL OF POWER SOURCES, 2022, 529

[6] Remaining useful life prediction of PEMFC systems under dynamic operating conditions [J].

Hua, Zhiguang ;

Zheng, Zhixue ;

Pahon, Elodie ;

Pera, Marie-Cecile ;

Gao, Fei .

ENERGY CONVERSION AND MANAGEMENT, 2021, 231

[7] The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J].

Huang, NE ;

Shen, Z ;

Long, SR ;

Wu, MLC ;

Shih, HH ;

Zheng, QN ;

Yen, NC ;

Tung, CC ;

Liu, HH .

PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 1998, 454 (1971) :903-995

[8] Particle filter based hybrid prognostics of proton exchange membrane fuel cell in bond graph framework [J].

Jha, Mayank Shekhar ;

Bressel, Mathieu ;

Ould-Bouamama, Belkacem ;

Dauphin-Tanguy, Genevieve .

COMPUTERS & CHEMICAL ENGINEERING, 2016, 95 :216-230

[9]

Kurtz JM, 2019, Fuel cell electric vehicle durability and fuel cell performance

[10] Adaptive Prognostic of Fuel Cells by Implementing Ensemble Echo State Networks in Time-Varying Model Space [J].

Li, Zhongliang ;

Zheng, Zhixue ;

Outbib, Rachid .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2020, 67 (01) :379-389

← 1 2 →