| 刘晓倩,崔焕勇,刘海宁,付宇,曾文胜,李发家.融合多特征选择和自注意力机制的LSTM燃料电池退化预测方法[J].电子测量与仪器学报,2024,38(5):219-228 |
| 融合多特征选择和自注意力机制的LSTM燃料电池退化预测方法 |
| Integrating multiple feature selection and self-attention mechanism inLSTM for fuel cell degradation prediction |
| |
| DOI： |
| 中文关键词: PEMFC 退化预测 XGBoost 自注意力机制 深度学习 |
| 英文关键词:PEMFC degradation prediction XGboost self-attention deep learning |
| 基金项目:山东省基金(ZR2021ME101)、山东省科技型中小企业创新能力提升工程(2021TSGC1413)项目资助 |
|
|
| Author | Institution |
| Liu Xiaoqian | School of Mechanical Engineering,University of Jinan, Jinan 250022,China |
| Cui Huanyong | 1.School of Mechanical Engineering,University of Jinan, Jinan 250022,China; 2.Shandong University of Technology,
Zibo 255000,China |
| Liu Haining | School of Mechanical Engineering,University of Jinan, Jinan 250022,China |
| Fu Yu | Shanghai Jichong Hydrogen Energy Technology Co.,Ltd, Shanghai 201800,China |
| Zeng Wensheng | China Aviation Hunan Power Machinery Research Institute, Zhuzhou 412002,China |
| Li Fajia | School of Mechanical Engineering,University of Jinan, Jinan 250022,China |
|
| 摘要点击次数: 166 |
| 全文下载次数: 10445 |
| 中文摘要: |
| 质子交换膜燃料电池的反应过程涉及多物理场、多部件、多因素的强耦合作用,其运行不可避免地伴随着长期的性能衰退及局部性能波动。然而,从多重耦合的众多监测参数中有效识别出关键特征并捕捉整体性能的衰退趋势变得异常困难。针对以上问题,提出一种基于XGBoost和Self-Atten-LSTM的PEMFC退化预测模型。首先,利用小波阈值去噪的方法剔除PEMFC原始数据中的噪声干扰;然后,采用XGBoost算法从众多参数中选择出对PEMFC性能影响显著的主要特征,实现关键特征的精确提取;最后,在LSTM中引入自注意力机制(self-attention)解决了其在处理长序列时的全局建模和多维向量间复杂交互关系不足的问题,通过自适应加权,更充分地利用了PEMFC的退化信息。与LSTM、Bi-LSTM、GRU模型相比,所提模型无论在稳态条件还是在动态条件下,都能较准确地预测燃料电池的退化,且模型平均绝对误差减小56.34%~77.04%,预测精度可达99.09%。该方法可广泛应用于制定车辆运行维护策略、提高系统可靠性等方面。 |
| 英文摘要: |
| The process of proton exchange membrane fuel cells (PEMFC) involves strong coupling of multiple physical fields, components, and factors, inevitably leading to prolonged performance degradation and local performance fluctuations during operation. However, effectively identifying key features from the multitude of parameters under the multiple couplings and capturing the overall performance degradation trend becomes exceptionally challenging. In response to these issues, a PEMFC degradation prediction model based on XGBoost and Self-Atten-LSTM is developed. First, a wavelet threshold denoising method is employed to remove noise interference from the original PEMFC data. Then, the XGBoost algorithm is used to select the main features significantly affecting PEMFC performance from the numerous parameters, achieving precise feature selection. Finally, the introduction of the self-attention mechanism in LSTM addresses its limitations in global modeling and complex interaction among multi-dimensional vectors when dealing with long sequences. Through adaptive weighting, it more effectively utilizes PEMFC degradation information. Compared to traditional LSTM, Bi-LSTM, and GRU models, the developed model can more accurately predict fuel cell degradation under both steady-state and dynamic conditions. The model exhibits a reduction in the average mean absolute error by 56.34% to 77.04%, with a predictive accuracy of up to 99.09%. This approach can find broad applications in developing vehicle operation and maintenance strategies and enhancing system reliability. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
