质子交换膜燃料电池输出电压为燃料电池健康状态和故障诊断的重要指标,输出电压受单电池电压、工作温度、气体流量、物质流量等参数的影响难以准确预测。为此根据燃料电池实验平台采集的数据集,进行KMO（Kaiser Meyer Olkin）相关性分析,验证数据集适合主成分分析。采用主成分分析随原始数据进行降维处理,确定影响燃料电池输出电压的12个主成分,建立基于KMO测度-主成分分析（principal component analysis,PCA）-BP神经网络（back propagation,BP）的燃料电池输出电压预测模型,并与BP预测模型进行对比分析,验证算法的优越性。采用间隔1.0和0.5 h的数据集进行对比验证,验证算法的泛化能力,预测结果表明,KMO-PCA-BP预测模型能准确预测燃料电池堆的输出电压,具有预测准确率高、预测速度快、泛化能力强的优点。
Abstract
The output voltage of the proton exchange membrane fuel cell is an important indicator of the health status and fault diagnosis of fuel cells. It is difficult to accurately predict the effect of the output voltage by parameters such as single cell voltage, operating temperature, gas flow and material flow, etc. For this reason, according to the data set collected by the fuel cell experimental platform, KMO correlation analysis is carried out to verify that the data set is suitable for principal component analysis. We use principal component analysis to reduce the dimensionality of the original data, and determine the 12 principal components that affect the output voltage of the fuel cell, as well as establish a fuel cell output voltage prediction model based on KMO measure （Kaiser Meyer Olkin, KMO）-Principal Component Analysis （PCA）-BP neural network （Back Propagation, BP）. And we compared with the BP prediction model to verify the superiority of the algorithm. We use the data sets with an interval of 1 hour and 0.5 hours for comparison and verification to verify the generalization ability of the algorithm. The results of prediction show that the KMO-PCA-BP prediction model can accurately predict the output voltage of the fuel cell stack, and has high prediction accuracy and speed and strong generalization ability. It provides reference for fuel cell stack output voltage prediction, health management and fault diagnosis.
关键词
燃料电池 /
质子交换膜 /
输出电压 /
预测方法 /
PCA /
BP
Key words
fuel cells /
proton exchange membrane /
output voltage /
prediction method /
PCA /
BP
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 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.Summary of research on water flooding and membrane dry fault diagnosis of proton exchange membrane fuel cells[J]. Journal of Southwest Jiaotong University, 2020, 55(4): 828-838, 864.
[2] JAVED K, GOURIVEAU R, ZERHOUNI N, et al.Improving accuracy of long-term prognostics of PEMFC stack to estimate remaining useful life[C]//Proceedings of the 2015 IEEE International Conference on Industrial Technology(ICIT), Seville, Spain, 2015.
[3] 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.
[4] JOUIN M, GOURIVEAU R, HISSEL D, et al.Joint particle filters prognostics for proton exchange membrane fuel cell power prediction at constant current solicitation[J]. IEEE transactions on reliability, 2015, 65(1): 336-349.
[5] LI Y K, ZHAO X Q, LIU Z X, et al.Experimental study on the voltage uniformity for dynamic loading of a PEM fuel cell stack[J]. International journal of hydrogen energy, 2015, 40(23): 7361-7369.
[6] LIU P C, XU S C.Experimental study on voltage uniformity for proton exchange membrane fuel cell stack[C]//SAE 2020 Vehicle Electrification and Autonomous Vehicle Technology Forum, Shanghai, China, 2020.
[7] 戴朝华, 史青, 陈维荣, 等. 质子交换膜燃料电池单体电压均衡性研究综述[J]. 中国电机工程学报, 2016, 36(5): 1289-1302.
DAI C H, SHI Q, CHEN W R, et al.Review of the research on the voltage balance of proton exchange membrane fuel cells[J]. Proceedings of the CSEE, 2016, 36(5): 1289-1302.
[8] ZOU W, FRONING D, SHI Y, et al.A least-squares support vector machine method for modeling transient voltage in polymer electrolyte fuel cells[J]. Applied energy, 2020, 271: 115092.
[9] ZHOU X Y, CHEN X L, LI B, et al.Durability performance of polymer electrolyte membrane fuel cells under open-circuit voltage[C]//New Energy & Intelligent Connected Vehicle Technology Conference, Shanghai, China, 2019.
[10] HAN M S, SHUL Y G, LEE H J, et al.Accelerated testing of polymer electrolyte membranes under open-circuit voltage conditions for durable proton exchange membrane fuel cells[J]. International journal of hydrogen energy, 2017, 42(52): 30787-30791.
[11] 董超, 李鸿鹏, 胡艳珍. 质子交换膜燃料电池输出电压性能优化的研究[J]. 计算机仿真, 2017, 34(9): 94-98.
DONG C, LI H P, HU Y Z.Research on the optimization of output voltage performance of proton exchange membrane fuel cell[J]. Computer simulation, 2017, 34(9): 94-98.
[12] VINU R, PAUL V.Performance analysis of artificial intelligent controllers in PEM fuel cell voltage tracking[J]. Cluster computing, 2019, 22(2): 4443-4455.
[13] 胡捷, 苏建徽, 杜燕, 等. 基于最小二乘法的 PEMFC 电堆模型参数辨识[J]. 太阳能学报, 2021, 42(6): 1-4.
HU J, SU J H, DU Y, et al.PEMFC reactor model parameter identification based on least square method[J]. Acta energia solaris sinica, 2021, 42(6): 1-4.
[14] 黄健, 詹跃东, 王华. PEMFC输出性能的主要影响因素及其评价方法[J]. 电源技术, 2010, 34(4): 355-359.
HUANG J, ZHAN Y D, WANG H.The main influencing factors and evaluation methods of PEMFC output performance[J]. Power supply technology, 2010, 34(4): 355-359.
[15] 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.
[16] KAISER H F, RICE J.Little jiffy, mark IV[J]. Educational and psychological measurement, 1974, 34(1): 111-117.
[17] 周松林, 茆美琴, 苏建徽. 基于主成分分析与人工神经网络的风电功率预测[J]. 电网技术, 2011, 35(9): 128-132.
ZHOU S L, MAO M Q, SU J H.Prediction of wind power based on principal component analysis and artificial neural network[J]. Power system technology, 2011, 35(9): 128-132.
[18] MA W H, LI Q F, LI J W, et al.A method for weighing broiler chickens using improved amplitude-limiting filtering algorithm and BP neural networks[J]. Information processing in agriculture, 2021, 8(2): 299-309.
[19] SANG B.Application of genetic algorithm and BP neural network in supply chain finance under information sharing[J]. Journal of computational and applied mathematics, 2021, 384: 113170.
[20] YU Z X, QIN L, CHEN Y J, et al.Stock price forecasting based on LLE-BP neural network model[J]. Physica A: Statistical mechanics and its applications, 2020, 553: 124197.
基金
国家自然科学基金（51967020）; 新疆维吾尔自治区自然科学基金（2021D01A66）（2019D01A30）; 自治区区域协同创新专项（科技援疆计划）（2021E02044）; 乌鲁木齐市优秀青年科技人才项目：新疆地区风电制氢关键技术研究
PDF(2361 KB)
