基于CNN-BiLSTM双通道特征融合的PEMFC水淹故障识别方法

赵旭阳; 袁裕鹏; 童亮; 朱小芳; 李骁

doi:10.19912/j.0254-0096.tynxb.2023-2028

PDF(2421 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (4) : 30-38. DOI: 10.19912/j.0254-0096.tynxb.2023-2028

基于CNN-BiLSTM双通道特征融合的PEMFC水淹故障识别方法

赵旭阳^1,2, 袁裕鹏^1,3, 童亮^1,3, 朱小芳³, 李骁⁴

作者信息 +

PEMFC FLOODING FAULT IDENTIFICATION METHOD BASED ON CNN-BILSTM DUAL-CHANNEL FEATURE FUSION

Zhao Xuyang^1,2, Yuan Yupeng^1,3, Tong Liang^1,3, Zhu Xiaofang³, Li Xiao⁴

Author information +

文章历史 +

摘要

为及时准确地识别质子交换膜燃料电池（PEMFC）水淹故障,提出基于卷积神经网络（CNN）和双向长短期记忆网络（BiLSTM）双通道特征融合的PEMFC水淹故障识别方法。首先,采用归一化消除原始特征之间的量纲;在此基础上利用随机森林（RF）评估数据的特征重要性进行特征筛选;采用并联式结构将CNN与BiLSTM结合分别提取空间特征和时间特征并进行串联融合;最后利用支持向量机（SVM）进行水淹故障识别。实例分析表明,所提方法可快速准确地识别PEMFC的正常状态和水淹故障,总体分类准确率为99.08%,测试用时为0.0929 s,可有效提高故障分类的准确率。

Abstract

In order to identify the flooding fault of proton exchange membrane fuel cell （PEMFC） in a timely and accurate manner, a PEMFC flooding fault identification method based on the dual-channel feature fusion of convolutional neural network （CNN） and bidirectional long short-term memory network （BiLSTM） is proposed. Firstly, normalization is used to eliminate the effect of dimension of the original features. On this basis, random forest （RF） is used to evaluate the feature importance of the data. The CNN and the BiLSTM are used to extract spatial features and temporal features, respectively. Then, these features are fused in series. Finally, the support vector machine （SVM） is used to identify the flooding fault. The case analysis shows that the proposed method can quickly and accurately identify the normal state and the flooding fault state of PEMFC, with an overall classification accuracy of 99.08% and a test time of 0.0929 s, which can effectively improve the accuracy of fault classification.

导出引用

赵旭阳, 袁裕鹏, 童亮, 朱小芳, 李骁. 基于CNN-BiLSTM双通道特征融合的PEMFC水淹故障识别方法[J]. 太阳能学报. 2025, 46(4): 30-38 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2028

Zhao Xuyang, Yuan Yupeng, Tong Liang, Zhu Xiaofang, Li Xiao. PEMFC FLOODING FAULT IDENTIFICATION METHOD BASED ON CNN-BILSTM DUAL-CHANNEL FEATURE FUSION[J]. Acta Energiae Solaris Sinica. 2025, 46(4): 30-38 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2028

中图分类号： TM911.4

参考文献

[1] 张诚, 檀志恒, 晁怀颇. “双碳” 背景下数据中心氢能应用的可行性研究[J]. 太阳能学报, 2022, 43(6): 327-334.
ZHANG C, TAN Z H, CHAO H P.Feasibility study of hydrogen energy application on data center under “carbon peaking and neutralization” background[J]. Acta energiae solaris sinica, 2022, 43(6): 327-334.
[2] 胡兵, 王小娟, 徐立军, 等. 基于KMO-PCA-BP的燃料电池堆输出电压预测方法[J]. 太阳能学报, 2022, 43(3): 12-19.
HU B, WANG X J, XU L J, et al.Output voltage prediction method of fuel cell stack based on KMO-PCA-BP[J]. Acta energiae solaris sinica, 2022, 43(3): 12-19.
[3] 杨卫战, 谈金祝, 刘嘉然, 等. 模拟PEM燃料电池环境下质子交换膜损伤研究[J]. 太阳能学报, 2022, 43(9): 493-498.
YANG W Z, TAN J Z, LIU J R, et al.Study on degradation of proton exchange membrane in simulated PEM fuel cell environments[J]. Acta energiae solaris sinica, 2022, 43(9): 493-498.
[4] YU X Z, ZHANG C Z, FAN M, et al.Experimental study of dynamic performance of defective cell within a PEMFC stack[J]. International journal of hydrogen energy, 2022, 47(13): 8480-8491.
[5] DAS V, PADMANABAN S, VENKITUSAMY K, et al.Recent advances and challenges of fuel cell based power system architectures and control: a review[J]. Renewable and sustainable energy reviews, 2017, 73: 10-18.
[6] BENMOUNA A, BECHERIF M, DEPERNET D, et al.Fault diagnosis methods for proton exchange membrane fuel cell system[J]. International journal of hydrogen energy, 2017, 42(2): 1534-1543.
[7] DAVIES B, JACKSON L, DUNNETT S.Expert diagnosis of polymer electrolyte fuel cells[J]. International journal of hydrogen energy, 2017, 42(16): 11724-11734.
[8] HISSEL D, PERA M C.Diagnostic & health management of fuel cell systems: issues and solutions[J]. Annual reviews in control, 2016, 42: 201-211.
[9] 陈维荣, 刘嘉蔚, 李奇, 等. 质子交换膜燃料电池故障诊断方法综述及展望[J]. 中国电机工程学报, 2017, 37(16): 4712-4721.
CHEN W R, LIU J W, LI Q, et al.Review and prospect of fault diagnosis methods for proton exchange membrane fuel cell[J]. Proceedings of the CSEE, 2017, 37(16): 4712-4721.
[10] 赵越, 张国庆, 苗盼盼. 质子交换膜燃料电池系统远程状态监控和故障诊断综述[J]. 时代汽车, 2023(20): 22-24.
ZHAO Y, ZHANG G Q, MIAO P P.A review on remote condition monitoring and fault diagnosis for proton exchange membrane fuel cell systems[J]. Auto time, 2023(20): 22-24.
[11] HUO H B, CHEN J J, WANG K, et al.State estimation of membrane water content of PEMFC based on GA-BP neural network[J]. Sustainability, 2023, 15(11): 9094.
[12] 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.
[13] 杜董生, 盛远杰, 赵环宇, 等. 基于VMD的质子交换膜燃料电池系统故障诊断[J]. 控制工程, 2023, 30(7): 1190-1197.
DU D S, SHENG Y J, ZHAO H Y, et al.Fault diagnosis for proton exchange membrane fuel cell system based on VMD[J]. Control engineering of China, 2023, 30(7): 1190-1197.
[14] 黄亮, 彭清, 谢长君, 等. 基于差分进化优化的支持向量机燃料电池故障诊断[J]. 电源技术, 2021, 45(10): 1316-1319.
HUANG L, PENG Q, XIE C J, et al.Fuel cell fault diagnosis for support vector machines optimized based on differential evolution algorithm[J]. Chinese journal of power sources, 2021, 45(10): 1316-1319.
[15] XIAO F, CHEN T, ZHANG J W, et al.Water management fault diagnosis for proton-exchange membrane fuel cells based on deep learning methods[J]. International journal of hydrogen energy, 2023, 48(72): 28163-28173.
[16] ZHANG H, LIU Z Y, LIU W L, et al.Diagnosing improper membrane water content in proton exchange membrane fuel cell using two-dimensional convolutional neural network[J]. Energies, 2022, 15(12): 4247.
[17] MAO L, DAVIES B, JACKSON L.Application of the sensor selection approach in polymer electrolyte membrane fuel cell prognostics and health management[J]. Energies, 2017, 10(10): 1511.
[18] MAO L, JACKSON L, DAVIES B.Investigation of PEMFC fault diagnosis with consideration of sensor reliability[J]. International journal of hydrogen energy, 2018, 43(35): 16941-16948.
[19] 张雪霞, 蒋宇, 孙腾飞, 等. 质子交换膜燃料电池水淹和膜干故障诊断研究综述[J]. 西南交通大学学报, 2020, 55(4): 828-838, 864.
ZHANG X X, JIANG Y, SUN T F, et al.Review on fault diagnosis for flooding and drying in proton exchange membrane fuel cells[J]. Journal of Southwest Jiaotong University, 2020, 55(4): 828-838, 864.
[20] MAO L, JACKSON L, HUANG W G, et al.Polymer electrolyte membrane fuel cell fault diagnosis and sensor abnormality identification using sensor selection method[J]. Journal of power sources, 2020, 447: 227394.
[21] ZUO B, ZHANG Z H, CHENG J S, et al.Data-driven flooding fault diagnosis method for proton-exchange membrane fuel cells using deep learning technologies[J]. Energy conversion and management, 2022, 251: 115004.
[22] LIU J W, LI Q, YANG H Q, et al.Sequence fault diagnosis for PEMFC water management subsystem using deep learning with t-SNE[J]. IEEE access, 2019, 7: 92009-92019.
[23] 陈元峰, 马溪原, 程凯, 等. 基于气象特征量选取与SVM模型参数优化的新能源超短期功率预测[J]. 太阳能学报, 2023, 44(12): 568-576.
CHEN Y F, MA X Y, CHENG K, et al.Ultra-short-term power forecast of new energy based on meteorological feature selection and SVM model parameter optimization[J]. Acta energiae solaris sinica, 2023, 44(12): 568-576.
[24] 王晨辉, 王恩东, 高晓锋. 基于CNN-BiLSTM特征融合的异常检测算法[J]. 计算机应用与软件, 2022, 39(12): 272-277, 340.
WANG C H, WANG E D, GAO X F.Anomaly detection algorithm based on CNN-BiLSTM feature fusion[J]. Computer applications and software, 2022, 39(12): 272-277, 340.