Full Text:   <549>

Summary:  <20>

CLC number: 

On-line Access: 2022-05-10

Received: 2021-12-04

Revision Accepted: 2021-12-27

Crosschecked: 2022-05-11

Cited: 0

Clicked: 661

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

He XU

https://orcid.org/0000-0003-3333-2880

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE A 2022 Vol.23 No.4 P.303-313

http://doi.org/10.1631/jzus.A2100598


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


Author(s):  Feng SUN, He XU, Yu-han ZHAO, Yu-dong ZHANG

Affiliation(s):  College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, China

Corresponding email(s):   railway_dragon@sohu.com

Key Words:  Control valve, Missing data, Fault diagnosis, Mathematical model (MM), Deep residual shrinkage network (DRSN)


Feng SUN, He XU, Yu-han ZHAO, Yu-dong ZHANG. Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network[J]. Journal of Zhejiang University Science A, 2022, 23(4): 303-313.

@article{title="Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network",
author="Feng SUN, He XU, Yu-han ZHAO, Yu-dong ZHANG",
journal="Journal of Zhejiang University Science A",
volume="23",
number="4",
pages="303-313",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A2100598"
}

%0 Journal Article
%T Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network
%A Feng SUN
%A He XU
%A Yu-han ZHAO
%A Yu-dong ZHANG
%J Journal of Zhejiang University SCIENCE A
%V 23
%N 4
%P 303-313
%@ 1673-565X
%D 2022
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A2100598

TY - JOUR
T1 - Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network
A1 - Feng SUN
A1 - He XU
A1 - Yu-han ZHAO
A1 - Yu-dong ZHANG
J0 - Journal of Zhejiang University Science A
VL - 23
IS - 4
SP - 303
EP - 313
%@ 1673-565X
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A2100598


Abstract: 
A control valve is one of the most widely used machines in hydraulic systems. However, it often works in harsh environments and failure occurs from time to time. An intelligent and robust control valve fault diagnosis is therefore important for operation of the system. In 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 data. The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method. The effects of the proposed method in missing data imputation and fault diagnosis are analyzed. Compared 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 a 20.00% 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.

数据驱动的基于数学模型插补和改进深度残差收缩网络的调节阀状态监控

作者:孙丰,徐贺,赵宇晗,张渝东
机构:哈尔滨工程大学,机电工程学院,中国哈尔滨,150001
目的:故障诊断在系统可靠性增强方面具有重要作用。调节阀通常运行在恶劣的环境下,故调节阀的故障时有发生。因此一种智能、稳健的调节阀健康状态检测方法对于系统的运行至关重要。针对调节阀数据驱动模型易受工况变化和数据缺失影响的问题,本文提出一种基于数学模型估算和改进深度残差收缩网络(MDRSN)的故障诊断方法。
方法:1.采集调节阀在不同开度的多个传感器时间序列样本。2.使用数学模型插补模型对不完整数据集进行补足,并使用MDRSN对调节阀的不同工况进行故障诊断。3.分析该方法在缺失数据估计和故障诊断中的准确率。
结论:本文利用调节阀的数学模型对缺失数据进行处理,并提出将MDRSN用于调节阀故障诊断。基于补全后获得的完整样本,对调节阀的故障诊断模型进行分析和训练,以提高故障诊断的准确性。结果表明,在基于数学模型插补的完整数据集上使用MDRSN的在线故障诊断效果较好。

关键词:调节阀;数据缺失;故障诊断;数学模型;MDRSN

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]DesboroughLD, MillerRM, 2001. Increasing customer value of industrial control performance monitoring—Honeywell’s experience. Proceedings of the Chemical Process Control–VI AIChE Symposium Series Tuscon Arizona, p.98.

[2]DuJH, HuMH, ZhangWN, 2020. Missing data problem in the monitoring system: a review. IEEE Sensors Journal, 20(23):13984-13998.

[3]DuttaN, PalanisamyK, SubramaniamU, et al., 2020. Identification of water hammering for centrifugal pump drive systems. Applied Sciences, 10(8):2683.

[4]FangL, TangL, WangJD, et al., 2016. A semi-physical model for pneumatic control valves. Nonlinear Dynamics, 85(3):1735-1748.

[5]GuoC, HuWK, YangF, et al., 2020. Deep learning technique for process fault detection and diagnosis in the presence of incomplete data. Chinese Journal of Chemical Engineering, 28(9):2358-2367.

[6]HeX, WangZD, WangXF, et al., 2014. Networked strong tracking filtering with multiple packet dropouts: algorithms and applications. IEEE Transactions on Industrial Electronics, 61(3):1454-1463.

[7]JardineAKS, LinDM, BanjevicD, 2006. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7):1483-1510.

[8]KayihanA, DoyleIII FJ, 2000. Friction compensation for a process control valve. Control Engineering Practice, 8(7):799-812.

[9]KimYS, KimDW, LeeBO, et al., 2016. Experimental study of operating parameters for pneumatic control valve in abnormal conditions. Transactions of the Korean Society of Mechanical Engineers A, 40(6):613-619.

[10]LeiYG, YangB, JiangXW, et al., 2020. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical Systems and Signal Processing, 138:106587.

[11]LiuH, WangYY, ChenWG, 2020. Three-step imputation of missing values in condition monitoring datasets. IET Generation, Transmission & Distribution, 14(16):‍3288-3300.

[12]Llanes-SantiagoO, Rivero-BenedicoBC, Galvez-VieraSC, et al., 2018. A fault diagnosis proposal with online imputation to incomplete observations in industrial plants. Revista Mexicana de Ingenieria Quimica, 18(1):83-98. https://doi.‍org/10.24275/uam/izt/dcbi/revmexingquim/2019v18n1/Llanes

[13]LvQ, YuXL, MaHH, et al., 2021. Applications of machine learning to reciprocating compressor fault diagnosis: a review. Processes, 9(6):909.

[14]Razavi-FarR, Farajzadeh-ZanjaniM, SaifM, et al., 2020. Correlation clustering imputation for diagnosing attacks and faults with missing power grid data. IEEE Transactions on Smart Grid, 11(2):1453-1464.

[15]SharifKM, RahmanMM, AzmirJ, et al., 2014. Experimental design of supercritical fluid extraction–a review. Journal of Food Engineering, 124:105-116.

[16]SheesleyJH, 1990. Quality engineering in production systems. Technometrics, 32(4):457-458.

[17]SoleimaniM, CampeanF, NeaguD, 2021. Diagnostics and prognostics for complex systems: a review of methods and challenges. Quality and Reliability Engineering International, 37(8):3746-3778.

[18]TripathyAK, NambiarP, PereiraA, et al., 2015. Pressure surge analysis in pump systems. Proceedings of the International Conference on Technologies for Sustainable Development, p.1-5.

[19]XieG, SunLL, WenT, et al., 2021. Adaptive transition probability matrix-based parallel IMM algorithm. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(5):2980-2989.

[20]YangJ, XieG, YangYX, 2020. An improved ensemble fusion autoencoder model for fault diagnosis from imbalanced and incomplete data. Control Engineering Practice, 98:104358.

[21]YuanY, MaGJ, ChengC, et al., 2020. A general end-to-end diagnosis framework for manufacturing systems. National Science Review, 7(2):418-429.

[22]ZhaoMH, ZhongSS, FuXY, et al., 2020. Deep residual shrinkage networks for fault diagnosis. IEEE Transactions on Industrial Informatics, 16(7):4681-4690.

[23]ZhuJL, GeZQ, SongZH, et al., 2018. Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data. Annual Reviews in Control, 46:107-133.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE