Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network

作     者：Feng SUN He XU Yu-han ZHAO Yu-dong ZHANG Feng SUN;He XU;Yu-han ZHAO;Yu-dong ZHANG

作者机构：College of Mechanical and Electrical EngineeringHarbin Engineering UniversityHarbin150001China 

出 版 物：《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 (浙江大学学报（英文版）A辑（应用物理与工程）)

年 卷 期：2022年第23卷第4期

页      面：303-313页

核心收录：

学科分类：080704[工学-流体机械及工程] 08[工学] 0807[工学-动力工程及工程热物理] 

基　　金：supported by the National Natural Science Foundation of China(No.51875113) the Natural Science Joint Guidance Foundation of the Heilongjiang Province of China(No.LH2019E027) the PhD Student Research and Innovation Fund of the Fundamental Research Funds for the Central Universities(No.XK2070021009),China 

主　　题：Control valve Missing data Fault diagnosis Mathematical model(MM) Deep residual shrinkage network(DRSN) 

摘      要：A control valve is one of the most widely used machines in hydraulic ***,it often works in harsh environments and failure occurs from time to *** intelligent and robust control valve fault diagnosis is therefore important for operation of the *** this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing *** multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed *** effects of the proposed method in missing data imputation and fault diagnosis are *** with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.