Study of degradation of fuel cell stack based on the collected high-dimensional data and clustering algorithms calculations

作     者：Tong Niu Weifeng Huang Caizhi Zhang Tao Zeng Jiawei Chen Yu Li Yang Liu 

作者机构：College of mechanical and vehicle engineeringThe State Key Laboratory of Mechanical TransmissionsChongqing Automotive Collaborative Innovation CentreChongqing UniversityChongqing 400044China School of Electrical EngineeringChongqing UniversityChongqing 400044China Propulsion Research Institute of Chongqing Changan New Energy Vehicle Technology Co.LtdChongqingChina School of AutomationChongqing UniversityChongqing 400044China Institute of Sustainable Energy/College of SciencesShanghai universityShanghai 200444China Sichuan Energy Internet Research InstituteTsinghua UniversityChengduSichuan 610213China Shaoxing Institute of TechnologyShanghai UniversityShaoxingZhejiang 312000China 

出 版 物：《能源与人工智能(英文)》 (Energy and AI)

年 卷 期：2022年第10卷第4期

页      面：29-40页

核心收录：

学科分类：08[工学] 0703[理学-化学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the special key project of Chongqing technological innovation and application development(cstc2019jscx-zdztzxX0033) the national key R&D plan of the Ministry of science and Technology(sub project)(2018YFB0105400) the National Natural Science Foundation of China(21908142) 

主　　题：Fuel cell vehicle Principal component analysis Clustering algorithms Degradation of fuel cell 

摘      要：Accurate perception of the performance degradation of fuel cell is very important to detect its health ***,inconsistent operating conditions of fuel cell vehicles in the test result in errors in the *** order to obtain a more credible degradation rate,this study proposes a novel method to classify the experimental data collected under different working conditions into similar operating conditions by using dimensionality reduction and clustering ***,the experimental data collected from fuel cell vehicles belong to high-dimensional *** projecting high-dimensional data into three-dimensional feature vector space via principal component analysis(PCA).The dimension-reduced three-dimensional feature vectors are input into the clustering algorithm,such as K-means and density-based noise application spatial clustering(DBSCAN).According to the clustering results,the fuel cell voltage data with similar operating conditions can be ***,the selected voltage data can be used to precisely represent the true performance degradation of an on-board fuel cell *** results show that the voltage using the K-means algorithm declines the fastest,followed by the DBSCAN algorithm, finally the original data, which indicates that the performance of the fuel cell actually declines faste. Early intervention can prolong its life to the greatest extent.