Unsupervised construction of health indicator for rotating machinery via multi-criterion feature selection and attentive variational autoencoder

作     者：LI XinYu CHENG ChangMing PENG ZhiKe LI XinYu;CHENG ChangMing;PENG ZhiKe

作者机构：State Key Laboratory of Mechanical System and VibrationShanghai Jiao Tong UniversityShanghai200240China School of Mechanical EngineeringNingxia UniversityYinchuan750021China 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2024年第67卷第5期

页      面：1524-1537页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 080201[工学-机械制造及其自动化] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key Research and Development Program of China(Grant No.2021YFB3400700) the China Academy of Railway Sciences Corporation Limited within the major issues of the fund(Grant No.2021YJ212) the National Natural Science Foundation of China(Grant Nos.12072188,12121002) the Natural Science Foundation of Shanghai(Grant No.20ZR1425200) 

主　　题：health indicator(HI) unsupervised learning multi-criterion feature selection global variability attention mechanism 

摘      要：Health indicator(HI)construction is a crucial task in degradation evaluation and facilitates the prognostic and health management(PHM)of rotating *** interference from artificial labeling,the HI construction approaches in an unsupervised manner have attracted substantial ***,current unsupervised methods generally struggle with two problems:(1)ignorance of both redundancy between features and global variability of features during the feature selection process;(2)inadequate utilization of information from different sampling *** tackle these problems,this work develops a novel unsupervised approach for HI construction that integrates multi-criterion feature selection and the Attentive Variational Autoencoder(Attentive VAE).Explicitly,a multi-criterion feature selection(Mc FS)algorithm together with an elaborately designed metric is proposed to determine a superior feature subset,considering the relevance,the redundancy,and the global variability of features ***,for the adequate utilization of the information from distinct sampling moments,a deep learning model named Attentive VAE is *** Attentive VAE is solely fed with the selected features in the health state for model training and the HI is derived through the reconstruction error to reveal the degradation degree of *** case studies based on genuine experimental datasets are involved to quantitatively evaluate the superiority of the developed approach,demonstrating its superiority over other unsupervised methods for characterizing degradation *** effectiveness of both the Mc FS algorithm and the Attentive VAE is verified by ablation experiments,respectively.