基于LSTM-UPF混合驱动方法的燃料电池寿命预测

doi:10.19799/j.cnki.2095-4239.2023.0705

摘要/Abstract

摘要：

燃料电池的寿命预测是燃料电池健康管理的重要组成部分，可为燃料电池的运行和维护提供指导性意见。为提高寿命预测的工况适应性并保证预测精度，本工作结合长短期记忆神经网络（long short-term memory neural network，LSTM）和无迹粒子滤波（unscented particle filter， UPF）两种算法的优势，提出了一种LSTM-UPF混合驱动方法进行稳态和准动态工况下燃料电池的寿命预测。该方法首先优化训练预测模型的实验数据并采用离散小波变换（discrete wavelet transform， DWT）技术将其分解为高频部分和低频部分，使用LSTM算法对这两部分分别进行预测实现对燃料电池长期老化趋势的预测，并使用修正因子对趋势预测结果进行漂移修正，然后利用得到的燃料电池长期老化趋势，根据UPF算法对燃料电池的剩余使用寿命（remaining useful life， RUL）进行估计。采用预测寿命终点、预测寿命误差、置信区间宽度、RUL预测误差等评价指标对不同寿命预测方法进行对比分析，结果表明，LSTM-UPF混合预测方法对燃料电池稳态工况和准动态工况的RUL预测误差分别为4.1%和3.4%，比基于模型的PF和UPF方法具有更精确的RUL预测结果与高质量的预测置信区间，工况适应性良好。本研究有助于提高多工况下的燃料电池寿命预测精度和置信度。

关键词: 质子交换膜燃料电池, 寿命预测, 长短期记忆神经网络, 无迹粒子滤波

Abstract:

Life prediction for fuel cells is crucial to fuel cell health management, offering their operation and maintenance guidance. Advantages of a long short-term memory neural network (LSTM) and an unscented particle filter (UPF) algorithm are combined to enhance condition adaptability in life prediction and ensure accuracy. The proposed LSTM-UPF hybrid method is designed to predict fuel cell life under steady-state and quasidynamic conditions. Initially, experimental data used for model training is optimized and decomposed into high-frequency and low-frequency components using the discrete wavelet transform technique. The LSTM algorithm predicts these components, forecasting the long-term aging trend of fuel cells. Drift correction is then applied to refine the trend prediction results. The fuel cell's remaining useful life (RUL) is estimated using the UPF algorithm based on the long-term aging trend. Evaluation indexes, including prediction life end, life prediction error, confidence interval width, and RUL prediction error, are adopted to assess different life prediction methods. Comparative results demonstrate that the LSTM-UPF hybrid life prediction method yields RUL prediction errors of 4.1% and 3.4% for steady-state and quasidynamic conditions, respectively. Moreover, it exhibits more accurate RUL predictions, high-quality confidence intervals, and strong adaptability in both scenarios. This study enhances the accuracy and confidence level of fuel cell life predictions.

Key words: proton exchange membrane fuel cell, life prediction, long short-term memory neural network, unscented particle filter

中图分类号:

TK 91

曾其权, 罗马吉, 杨印龙, 黄庆泽. 基于LSTM-UPF混合驱动方法的燃料电池寿命预测[J]. 储能科学与技术, 2024, 13(3): 963-970.

Qiquan ZENG, Maji LUO, Yinlong YANG, Qingze HUANG. Life prediction of fuel cells based on the LSTM-UPF hybrid method[J]. Energy Storage Science and Technology, 2024, 13(3): 963-970.

图/表 11

图1

表1

图2

图3

图4

图5

图6

表2

图7

图8

表3

参考文献 20

1	刘应都, 郭红霞, 欧阳晓平. 氢燃料电池技术发展现状及未来展望[J]. 中国工程科学, 2021, 23(4): 162-171.
	LIU Y D, GUO H X, OUYANG X P. Development status and future prospects of hydrogen fuel cell technology[J]. Strategic Study of CAE, 2021, 23(4): 162-171.
2	FAN L X, TU Z K, CHAN S H. Recent development of hydrogen and fuel cell technologies: A review[J]. Energy Reports, 2021, 7: 8421-8446.
3	YUE M L, JEMEI S, ZERHOUNI N, et al. Proton exchange membrane fuel cell system prognostics and decision-making: Current status and perspectives[J]. Renewable Energy, 2021, 179: 2277-2294.
4	HUA Z G, ZHENG Z X, PAHON E, et al. A review on lifetime prediction of proton exchange membrane fuel cells system[J]. Journal of Power Sources, 2022, 529: 231256.
5	LIN X F, HU Y Y. State of health estimation for proton exchange membrane fuel cell using strong tracking filter[C]//2020 35th Youth Academic Annual Conference of Chinese Association of Automation (YAC). Zhanjiang, China. IEEE, 2020: 379-383.
6	LIU J W, LI Q, CHEN W R, et al. Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks[J]. International Journal of Hydrogen Energy, 2019, 44(11): 5470-5480.
7	LI H L, CHEN Q H, ZHANG L Y, et al. Degradation prediction of proton exchange membrane fuel cell based on the multi-inputs Bi-directional long short-term memory[J]. Applied Energy, 2023, 344: 121294.
8	ZHANG F, WANG B W, GONG Z C, et al. Short-term performance degradation prediction of proton exchange membrane fuel cell based on discrete wavelet transform and Gaussian process regression[J]. Next Energy, 2023, 1(3): 100052.
9	SUN X L, XIE M K, FU J Q, et al. An improved neural network model for predicting the remaining useful life of proton exchange membrane fuel cells[J]. International Journal of Hydrogen Energy, 2023, 48(65): 25499-25511.
10	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.
11	CHEN J Y, ZHOU D, LYU C, et al. A novel health indicator for PEMFC state of health estimation and remaining useful life prediction[J]. International Journal of Hydrogen Energy, 2017, 42(31): 20230-20238.
12	WANG Y P, WU K C, ZHAO H H, et al. Degradation prediction of proton exchange membrane fuel cell stack using semi-empirical and data-driven methods[J]. Energy and AI, 2023, 11: 100205.
13	TIAN Q C, CHEN H T, DING S, et al. Remaining useful life prediction method of PEM fuel cells based on a hybrid model[J]. Electronics, 2023, 12(18): 3883.
14	ZHANG Z D, WANG Y X, HE H W, et al. A short- and long-term prognostic associating with remaining useful life estimation for proton exchange membrane fuel cell[J]. Applied Energy, 2021, 304: 117841.
15	谢滟馨, 王顺利, 史卫豪, 等. 一种用于高保真锂电池SOC估计的无迹粒子滤波新方法[J]. 储能科学与技术, 2021, 10(2): 722-731.
	XIE Y X, WANG S L, SHI W H, et al. A new method of unscented particle filter for high-fidelity lithium-ion battery SOC estimation[J]. Energy Storage Science and Technology, 2021, 10(2): 722-731.
16	FCLAB Research. IEEE PHM 2014 DATA CHALLENGE[OL]. Belfort, France: 2014. [2020-12-20]. http://eng.fclab.fr/ieee-phm-2014-data-challenge/.
17	王英楷, 张红, 王星辉. 基于1DCNN-LSTM的锂离子电池SOH预测[J]. 储能科学与技术, 2022, 11(1): 240-245.
	WANG Y K, ZHANG H, WANG X H. Hybrid 1DCNN-LSTM model for predicting lithium ion battery state of health[J]. Energy Storage Science and Technology, 2022, 11(1): 240-245.
18	SRINIVASAN D. Energy demand prediction using GMDH networks[J]. Neurocomputing, 2008, 72(1/2/3): 625-629.
19	黄庆泽. 混合驱动的质子交换膜燃料电池寿命预测方法研究[D]. 武汉: 武汉理工大学, 2022.
	HUANG Q Z. Study on hybrid driven life prediction methods of proton exchange membrane fuel cell[D]. Wuhan: Wuhan University of Technology, 2022.
20	BENAGGOUNE K, YUE M L, JEMEI S, et al. A data-driven method for multi-step-ahead prediction and long-term prognostics of proton exchange membrane fuel cell[J]. Applied Energy, 2022, 313: 118835.

参量	控制范围
气体温度	20~80 ℃
气体湿度	0~100%
冷却液温度	20~80 ℃
冷却液流量	0~10 L/min
空气流量	0~100 L/min
氢气流量	0~30 L/min
气体压力	0~200 kPa

算法评估指标	PF方法	UPF方法	混合驱动方法
预测寿命终止点/h	686	771	802
预测寿命误差/h	106	21	10
置信区间宽度/h	96	5	11
RUL预测误差/％	43.8	8.7	4.1

算法评估指标	PF方法	UPF方法	混合驱动方法
预测寿命终止点/h	738	802	764
预测寿命误差/h	35	29	9
置信区间宽度/h	106	8	16
RUL预测误差/％	13.3	11.0	3.4

[1]	白静, 范惠芳, 崔四齐, 许闯, 张毅, 关斯泽, 杨涵斐, 贾一飞, 耿树伟, 郑慧凡. 车用燃料电池散热性能实验研究[J]. 储能科学与技术, 2024, 13(2): 390-395.
[2]	张宇波, 王有元, 黄洞宁, 王子懿, 陈伟根. 面向变工况条件的锂离子电池寿命退化预测方法[J]. 储能科学与技术, 2023, 12(7): 2238-2245.
[3]	禹永帅, 刘永峰, 裴普成, 张璐, 姚圣卓. 阴极相对湿度对PEMFC电解质水含量及性能的影响[J]. 储能科学与技术, 2023, 12(6): 1755-1764.
[4]	李林泽, 张向文. 基于组合频率阻抗特征的锂离子电池健康状态估算[J]. 储能科学与技术, 2023, 12(5): 1705-1712.
[5]	王朋凯, 张新燕, 张光昊. 基于ResNet-Bi-LSTM-Attention的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2023, 12(4): 1215-1222.
[6]	王星, 孙俊, 陈宁芳, 闫立. 基于Simscape的质子交换膜燃料电池冷却系统建模与温度控制策略[J]. 储能科学与技术, 2023, 12(3): 857-869.
[7]	李路路, 陶正顺, 潘庭龙, 杨玮林, 胡官洋. 锂电池分数阶建模及SOC估计策略[J]. 储能科学与技术, 2023, 12(2): 544-551.
[8]	刘轲轲, 刘永峰, 裴普成, 姚圣卓, 张璐. 基于科赫曲线的PEMFC新型流道设计[J]. 储能科学与技术, 2023, 12(11): 3361-3368.
[9]	宋兴海, 张小乾, 梁惠施, 史梓男, 李棉刚, 周奎, 贡晓旭. 基于SDAE-Transformer-ECA网络的锂电池剩余使用寿命预测[J]. 储能科学与技术, 2023, 12(10): 3181-3190.
[10]	刘芊彤, 邢远秀. 基于VMD-PSO-GRU模型的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2023, 12(1): 236-246.
[11]	易顺民, 谢林柏, 彭力. 基于VF-DW-DFN的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2022, 11(7): 2305-2315.
[12]	胡冶州, 王双, 申涛, 朱叶, 王得丽. 限域型贵金属氧还原反应电催化剂研究进展[J]. 储能科学与技术, 2022, 11(4): 1264-1277.
[13]	肖浩逸, 何晓霞, 梁佳佳, 李春丽. 一种基于模态分解和机器学习的锂电池寿命预测方法[J]. 储能科学与技术, 2022, 11(12): 3999-4009.
[14]	史永胜, 李锦, 任嘉睿, 张凯. 基于WOA-XGBoost的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2022, 11(10): 3354-3363.
[15]	李志浩, 彭浩, 陈亚琴. 质子交换膜燃料电池膜电极组件温度分布的神经网络预测模型[J]. 储能科学与技术, 2021, 10(6): 2053-2059.