|
|
|
| Enhanced Whale Optimization Algorithm-Based CNN-BiGRU-AT Model for Aging Prediction of Fuel Cell |
| Quan Rui1, Cheng Gong1, Zhou Yulong1, Zhang Guoguang1, Quan Jin2 |
1. Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of Technology Wuhan 430068 China;
2. Wuhan Hyvitech Co. Ltd Wuhan 430000 China |
|
|
|
Abstract Fuel cells (FCs) are widely used due to their high energy conversion rate, low noise level and no pollutant emissions. However, the internal components of FCs will irreversibly degrade over time, and under certain complex operating conditions, their aging rate will limit their long-term applications. Therefore, accurate prediction of the remaining useful life (RUL) of FCs is essential to extend their service time, reduce operating costs and ensure their durability.
Currently, RUL prediction for FCs is classified into model-based, data-driven and hybrid prediction methods. Model-based prediction methods use the physicochemical reactions inside the FCs to create models and make predictions, with the advantage of obtaining decay parameters to characterize the internal aging state, but it is difficult to establish an accurate mechanistic model for the complex physicochemical reactions inside the FCs. Data-driven approaches do not rely on mechanistic models and can learn from large amounts of experimental test data to make accurate RUL predictions. However, some traditional deep learning models, such as long short term memory (LSTM) neural networks, recurrent neural networks (RNN), and gated recurrent unit (GRU) have obvious limitations. They rely only on historical data to predict the RUL of FC without considering the before and after information of FC degradation. In addition, they cannot effectively exploit the spatial correlation existing in the test data, and the accuracy of RUL prediction needs to be further improved. The hybrid prediction method is to merge or fuse various models to make full use of the respective advantages of different models to improve the prediction accuracy. However, it relies on the establishment of an accurate model, and the accuracy and robustness of the model are difficult to guarantee due to the complexity of the degradation mechanism of the FCs, coupled with environmental disturbances and measurement noise. In addition, hybrid methods based on multiple data-driven approaches need to annotate a large amount of data, consume a lot of computational resources and time, and it is difficult to ensure the interpretability of the prediction results. To address these challenges, this paper proposed a hybrid model combining with convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU) and attention mechanism (AT) to further improve the RUL forecasting accuracy of FCs.
Firstly, the FCs’ aging data recorded by the FCLAB Research Federation were preprocessed using singular spectrum analysis to eliminate noise and obtain effective information, the spatio-temporal features, historical and future information of FCs were extracted with CNN-BiGRU model, the spatio-temporal correlation was explored with AT, and the hyperparameters of the model were optimized with an enhanced whale optimization algorithm (EWOA) to reduce human intervention error.
Subsequently, the root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and relative error (RE) were designed to evaluate the RUL forecasting accuracy of the proposed hybrid model by comparing with other deep learning models such as LSTM, CNN, GRU, CNN-LSTM, CNN-GRU, CNN-BiGRU, BiGRU-AT, CNN-BiGRU-AT, and CNN-BiGRU-AT optimized with bayesian optimization (BO), WOA, sparrow search algorithm (SSA), grey wolf optimization (GWO) and black widow optimization algorithm(BWOA).
The following conclusions can be drawn from the results: (1) Compared with LSTM, CNN, GRU, CNN- LSTM, CNN-GRU, CNN-BiGRU, BiGRU-AT, CNN-BiGRU-AT, BO-CNN-BiGRU-AT, WOA-CNN-BiGRU-AT, SSA-CNN-BiGRU-AT, GWO-CNN-BiGRU-AT and BWO-CNN-BiGRU-AT, the proposed EWOA-optimized CNN-BiGRU-AT model has the smallest RMSE, MAE, MAPE and RE, which is 0.202 1%, 0.127 8%,0.033% and 0.027%, respectively. (2) The proposed model still maintains superior RUL prediction robustness with 60% missing data, the minimum RMSE, MAE, MAPE and RE are 0.387 9%, 0.255 9%, 0.081 1% and 0.32%, respectively. (3) Compared with the CNN, GRU, CNN-GRU, CNN-BiGRU and CNN-BiGRU models, the EWOA-optimized CNN-BiGRU-AT model can more accurately describe the twelve-, twenty-four-, and forty- eight-step aging curves of the FCs with higher reliability.
|
|
Received: 18 October 2024
|
|
|
|
|
|
[1] 赵洪山, 潘思潮, 马利波, 等. 基于分类回放双延迟贝叶斯深度确定性策略梯度的燃料电池温度控制[J]. 电工技术学报, 2024, 39(13): 4240-4256.
Zhao Hongshan, Pan Sichao, Ma Libo, et al.Control of fuel cell temperature based on classified replay twin delayed Bayesian deep deterministic policy gradient[J]. Transactions of China Electrotechnical Society, 2024, 39(13): 4240-4256.
[2] 高锋阳, 高翾宇, 张浩然, 等. 全局与瞬时特性兼优的燃料电池有轨电车能量管理策略[J]. 电工技术学报, 2023, 38(21): 5923-5938.
Gao Fengyang, Gao Xuanyu, Zhang Haoran, et al.Management strategy for fuel cell trams with both global and transient characteristics[J]. Transactions of China Electrotechnical Society, 2023, 38(21): 5923-5938.
[3] 敖文杰, 陈家伟, 陈杰, 等. 燃料电池-锂电池混合供电系统的无源控制策略及参数设计方法[J]. 电工技术学报, 2024, 39(2): 580-594.
Ao Wenjie, Chen Jiawei, Chen Jie, et al.Passivity-based control strategy and parameter design method for fuel cell-lithium battery hybrid power supply system[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 580-594.
[4] Huang Jiaqiang, Yu Zongxue, Tang Junlei, et al.A review on anion exchange membranes for fuel cells: anion-exchange polyelectrolytes and synthesis strategies[J]. International Journal of Hydrogen Energy, 2022, 47(65): 27800-27820.
[5] 汪建锋, 王荣杰, 林安辉, 等. 质子交换膜燃料电池退化预测方法[J]. 电工技术学报, 2024, 39(11): 3367-3378.
Wang Jianfeng, Wang Rongjie, Lin Anhui, et al.Degradation prediction method of proton exchange membrane fuel cell[J]. Transactions of China Electro-technical Society, 2024, 39(11): 3367-3378.
[6] Hou Yongping, Yang Zhihua, Wan Gang.An improved dynamic voltage model of PEM fuel cell stack[J]. International Journal of Hydrogen Energy, 2010, 35(20): 11154-11160.
[7] Ou Mingyang, Zhang Ruofan, Shao Zhifang, et al.A novel approach based on semi-empirical model for degradation prediction of fuel cells[J]. Journal of Power Sources, 2021, 488: 229435-229445.
[8] Kandidayeni M, Macias A, Amamou A A, et al.Comparative analysis of two online identification algorithms in a fuel cell system[J]. Fuel Cells, 2018, 18(3): 347-358.
[9] Silva R E, Gouriveau R, Jemeï S, et al.Proton exchange membrane fuel cell degradation prediction based on adaptive neuro-fuzzy inference systems[J]. International Journal of Hydrogen Energy, 2014, 39(21): 11128-11144.
[10] 杨淇, 陈景文, 华志广, 等. 基于集成型极限学习机的氢燃料电池寿命预测[J]. 电工技术学报, 2025, 40(3): 964-974.
Yang Qi, Chen Jingwen, Hua Zhiguang, et al.Research on PEMFC lifetime prediction based on ensemble extreme learning machine[J]. Transactions of China Electrotechnical Society, 2025, 40(3): 964-974.
[11] Zhang Zhendong, Wang Yaxiong, He Hongwen, 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.
[12] Ma Rui, Li Zhongliang, Breaz E, et al.Data-fusion prognostics of proton exchange membrane fuel cell degradation[J]. IEEE Transactions on Industry Applica-tions, 2019, 55(4): 4321-4331.
[13] Liu Hao, Chen Jian, 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.
[14] Zhou Daming, Gao Fei, Breaz E, et al.Degradation prediction of PEM fuel cell using a moving window based hybrid prognostic approach[J]. Energy, 2017, 138: 1175-1186.
[15] Zhang Yanxin, Zhang Zili, Chen Jing, et al.The adaptive kernel-based extreme learning machine for state of charge estimation[J]. Ionics, 2023, 29(5): 1863-1872.
[16] Wu Xiaojuan, Ye Qianwen, Wang Junhao.A hybrid prognostic model applied to SOFC prognostics[J]. International Journal of Hydrogen Energy, 2017, 42(39): 25008-25020.
[17] Pan Mingzhang, Hu Pengfei, Gao Ran, et al.Multistep prediction of remaining useful life of proton exchange membrane fuel cell based on temporal convolutional network[J]. International Journal of Green Energy, 2023, 20(4): 408-422.
[18] Sun Xilei, Xie Mingke, Fu Jianqin, 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.
[19] 张林, 山世玉, 宋展鹏, 等. 基于深度学习的氢燃料电池输出特性建模及退化趋势预测[J/OL]. 电源学报, 2025: 1-13. (2025-09-18). https://kns.cnki.net/kcms/detail/12.1420.TM.20250918.1228.015.html.
Zhang Lin, Shan Shiyu, Song Zhanpeng, et al. Deep learning-based modeling and degradation trend prediction for hydrogen fuel cell output characteristics [J/OL]. Journal of Power Supply, 2025: 1-13. (2025-09-18). https://kns.cnki.net/kcms/detail/12.1420.TM.20250918.1228.015.html.
[20] 韩烨宸, 贺兴, 艾芊. 基于GRU-EEMD算法的非侵入式配电网功率欠定盲源分离[J]. 电力系统自动化, 2023, 47(14): 64-71.
Han Yechen, He Xing, Ai Qian.Non-intrusive underde-termined blind power source separation for distribu-tion network based on gate recurrent unit and ensemble empirical mode decomposition algorithm[J]. Automa-tion of Electric Power Systems, 2023, 47(14): 64-71.
[21] She Daoming, Jia Minping.A BiGRU method for remaining useful life prediction of machinery[J]. Measurement, 2021, 167: 108277.
[22] Yu Yang, Yu Qinghua, Luo Runsen, et al.Deep learning with dual-stage attention mechanism for interpretable prediction of proton exchange membrane fuel cell performance degradation[J]. International Journal of Hydrogen Energy, 2024, 58: 902-911.
[23] Wilberforce T, Alaswad A, Garcia-Perez A G, et al. Remaining useful life prediction for proton exchange membrane fuel cells using combined convolutional neural network and recurrent neural network[J]. International Journal of Hydrogen Energy, 2023, 48(1): 291-303.
[24] Wang F K, Amogne Z E, Tseng C, et al.A hybrid method for online cycle life prediction of lithium-ion batteries[J]. International Journal of Energy Research, 2022, 46(7): 9080-9096.
[25] 赵洪山, 吴雨晨, 温开云, 等. 基于时空注意力机制的台区多用户短期负荷预测[J]. 电工技术学报, 2024, 39(7): 2104-2115.
Zhao Hongshan, Wu Yuchen, Wen Kaiyun, et al.Short-term load forecasting for multiple customers in a station area based on spatial-temporal attention mechanism[J]. Transactions of China Electrotechnical Society, 2024, 39(7): 2104-2115.
[26] 刘刚, 高成龙, 胡万君, 等. 基于鲸鱼优化算法超参数优化的径向基函数响应面模型的油浸式变压器绕组挡板结构优化[J]. 电工技术学报, 2024, 39(17): 5331-5343.
Liu Gang, Gao Chenglong, Hu Wanjun, et al.Optimization of winding block washer structure for oil immersed transformers based on radial basis func-tion response surface model with whale optimization algorithm hyper-parameters optimization[J]. Transactions of China Electrotechnical Society, 2024, 39(17): 5331-5343.
[27] Zhang Minghui, Wang Baozhu, Zhou Yatong, et al.WOA-based echo state network for chaotic time series prediction[J]. Journal of the Korean Physical Society, 2020, 76(5): 384-391.
[28] Harel F, Hissel D, Turpin C, et al. IEEE PHM Data Challenge2014 (2021)[DB/OL]. (2024-03-25)[2024-07-01]. https://search-data.ubfc.fr/FR-18008901306731-2021-07-19_IEEE-PHM-Data-Challenge-2014.html.
[29] Ghodsi M, Hassani H, Rahmani D, et al.Vector and recurrent singular spectrum analysis: which is better at forecasting?[J]. Journal of Applied Statistics, 2018, 45(10): 1872-1899. |
|
|
|
2025, Vol. 40 
