基于数据驱动的预测方法可实现质子交换膜燃料电池（PEMFC）的寿命预测。为提高质子交换膜燃料电池（PEMFC）寿命预测精度,提出将集成经验模态分解（EEMD）和粒子群算法（PSO）优化极限学习机（ELM）相结合的PEMFC剩余使用寿命预测方法。首先,采用移动平均滤波法在滤除噪声和尖峰的同时,保留原始数据的主要趋势;其次,通过EEMD对原始数据进行多时间尺度分解,得到不同时间尺度下PEMFC的老化信息;最后,将分解后的本征模函数分别通过PSO优化的ELM模型进行预测,能在保证预测精度的情况下降低运算复杂度。通过与经典的极限学习机模型预测结果进行对比,该方法能更加准确地预测PEMFC的老化趋势。
Abstract
The data-driven prediction method can predict the lifetime of proton exchange membrane fuel cells （PEMFC）. To improve the accuracy of PEMFC lifetime prediction, this paper proposes a PEMFC remaining useful life prediction method that combines the ensemble empirical mode decomposition （EEMD） and extreme learning machine （ELM） optimized by particle swarm algorithm （PSO）. First, the moving average filter method is used to retain the main trends of the original data while filtering out noise and spikes. Second, the original data are decomposed in multiple time scales by EEMD to obtain the aging information of PEMFC in different time scales. Last, the intrinsic mode functions are respectively predicted by the PSO-ELM model, which can reduce the computational complexity while ensuring the prediction accuracy. By comparing the prediction results with the classical ELM model, this method can predict the aging trend of PEMFC more accurately.
关键词
质子交换膜燃料电池 /
预测 /
经验模态分解 /
极限学习机
Key words
proton exchange membrane fuel cell /
prediction /
empirical mode decomposition /
extreme learning machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陶丽蓉, 刘煜, 孔红兵, 等. 质子交换膜燃料电池整车辅助散热系统设计建模及分析[J]. 太阳能学报, 2023, 44(4): 299-305.
TAO L R, LIU Y, KONG H B, et al.Design, modeling and analysis of auxiliary heat dissipation system for proton exchange membrane fuel cell vehicle[J]. Acta energiae solaris sinica, 2023, 44(4): 299-305.
[2] 刘川毓, 张雪霞, 蒋宇, 等. 基于MFDFA的PEMFC水淹和膜干故障诊断[J]. 太阳能学报, 2023, 44(8): 85-91.
LIU C Y, ZHANG X X, JIANG Y, et al.Fault diagnosis of PEMFC flooding and membrane drying based on MFDFA[J]. Acta energiae solaris sinica, 2023, 44(8): 85-91.
[3] ZUO J, CADET C, LI Z L, et al.A deterioration-aware energy management strategy for the lifetime improvement of a multi-stack fuel cell system subject to a random dynamic load[J]. Reliability engineering & system safety, 2024, 241: 109660.
[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] VASILYEV A, ANDREWS J, JACKSON L M, et al.Component-based modelling of PEM fuel cells with bond graphs[J]. International journal of hydrogen energy, 2017, 42(49): 29406-29421.
[6] LIU H, CHEN J, HISSEL D, et al.Remaining useful life estimation for proton exchange membrane fuel cells using a hybrid method[J]. Applied energy, 2019, 237: 910-919.
[7] CHEN K, LAGHROUCHE S, DJERDIR A.Degradation model of proton exchange membrane fuel cell based on a novel hybrid method[J]. Applied energy, 2019, 252: 113439.
[8] 金晓航, 泮恒拓, 徐正国. 数据驱动的风电机组变桨系统状态监测[J]. 太阳能学报, 2022, 43(4): 409-417.
JIN X H, PAN H T, XU Z G.Condition monitoring of wind turbine pitch system using data-driven approach[J]. Acta energiae solaris sinica, 2022, 43(4): 409-417.
[9] JAVED K, GOURIVEAU R, ZERHOUNI N, et al.Prognostics of proton exchange membrane fuel cells stack using an ensemble of constraints based connectionist networks[J]. Journal of power sources, 2016, 324: 745-757.
[10] 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.
LIU J W, LI Q, CHEN W R, 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.
[11] ZHANG X X, YU Z X, CHEN W R.Life prediction based on D-S ELM for PEMFC[J]. Energies, 2019, 12(19): 3752.
[12] CHEN K, LAGHROUCHE S, DJERDIR A.Proton exchange membrane fuel cell prognostics using genetic algorithm and extreme learning machine[J]. Fuel cells, 2020, 20(3): 263-271.
基金
国家自然科学基金（52307251）; 陕西自然科学基金（2023-YGBY-105）; 中国博士后科学基金（2023TQ0277）
PDF(2625 KB)
