重庆理工大学学报2025，Vol.39Issue(7)：35-41,7.DOI:10.3969/j.issn.1674-8425(z).2025.04.005
融合鲸鱼优化与动态时间规整的新能源汽车故障诊断方法
The whale optimization-based dynamic time warping method for fault diagnosis for new energy vehicles
摘要
Abstract
To address the low accuracy and low efficiency of the traditional fault classification for new energy vehicles,this paper proposes a new energy vehicle fault diagnosis model(WPPD)based on whale optimization-dynamic time warping.It combines principal component analysis(PCA),piecewise aggregate approximation(PAA)and dynamic time warping(DTW).Moreover,it employs the whale optimization algorithm(WOA)to optimize key parameters to achieve high-precision fault diagnosis.First,the two-step dimensionality reduction of vehicle fault data is conducted by PCA and PAA to compress the features and approximate the time series by piecewise aggregation.Then,DTW and KNN are integrated for fault classification of the processed time series.Fault identification is conducted by calculating the similarity between different time series.Finally,WOA is introduced to optimize the number of features after PCA reduction,the number of PAA segments,and the k value in DTW to improve diagnostic performance and classification accuracy.Results show compared with traditional models,the fault diagnosis model markedly improves the recall and F1 score.关键词
故障诊断/鲸鱼优化算法/动态时间规整/主成分分析/分段聚合近似Key words
fault diagnosis/WOA/DTW/PCA/PAA分类
交通运输引用本文复制引用
张丰硕,赵理,杨世超,张栋业..融合鲸鱼优化与动态时间规整的新能源汽车故障诊断方法[J].重庆理工大学学报,2025,39(7):35-41,7.基金项目
国家自然科学基金面上项目(52077007) （52077007）
