Fault diagnosability evaluation method based on multi-signal flow graph and similarity measure

被引：0

作者：

Qin Y. ^{[1
]}

Shi X. ^{[1
]}

机构：

[1] College of Coastal Defense Force, Naval Aviation University, Yantai

来源：

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2023年 / 45卷 / 01期

关键词：

diagnosability evaluation; Euclidean distance; fault diagnosability; multi-signal flow diagram; similarity measure;

D O I：

10.12305/j.issn.1001-506X.2023.01.35

中图分类号：

学科分类号：

摘要：

Aiming at the problem that the fault diagnosability of electronic system cannot be quantitatively evaluated based on qualitative model, the paper combines qualitative model with data-driven methods, and a method of fault diagnosability evaluation based on multi-signal flow graph and similarity measure is proposed. Firstly, the multi-signal flow graph model is established according to the composition of the system and the fault-test correlation matrix is obtained. Based on the fault-test correlation matrix, the fault diagnosability evaluation criteria is proposed. Secondly, the Shannon entropy of the wavelet packet of the test signal is extracted as the feature vector, and the Euclidean distance is used as the similarity measurement index. The problem of fault diagnosability quantitative evaluation is transformed into the similarity measure problem of the feature vector of the test signal under different fault modes. Then, the fault diagnosability evaluation matrix is constructed, and the system diagnosability indicators is proposed according to the fault diagnosability evaluation matrix. Finally, the effectiveness of the proposed method is verified by simulation analysis, and the results show that the method proposed in the paper can realize the quantitative evaluation of the fault diagnosability of electronic system without constructing mathematical model. © 2023 Chinese Institute of Electronics. All rights reserved.

引用

页码：302 / 312

页数：10

共 31 条

[21]

FU F Z, XUE T, WU Z G, Et al., A fault diagnosability evaluation method for dynamic systems without distribution knowledge, IEEE Trans.on Cybernetics, 52, 6, pp. 5113-5123, (2022)

[22]

SHAO J, ZHANG Y Q, Research on modeling method based on multi-signal flow model, Applied Mechanics and Materials, 494-495, pp. 983-988, (2014)

[23]

YANG C L, ZHANG S W, TONG C M, Et al., Research on testability modeling with Bayesian network based on multi-signal flow model, Proc. of the IEEE Conference on Industrial Electronics & Applications, pp. 1870-1873, (2013)

[24]

XIONG S C, ZHOU H D, HE S, Et al., Fault diagnosis of a rolling bearing based on the wavelet packet transform and a deep residual network with lightweight multi-branch structure, Measurement Science and Technology, 32, 8, pp. 85106-85115, (2021)

[25]

YU F J, LIU Y C, FENG Z Q., Compound fault diagnosis of gearbox based on wavelet packet transform and sparse representation classification, Proc. of the 32nd Chinese Control and Decision Conference, pp. 5339-5343, (2020)

[26]

LI G Q, DENG C, WU J, Et al., Rolling bearing fault diagnosis based on wavelet packet transform and convolutional neural network[J], Applied Sciences, 10, 3, (2020)

[27]

YI T Q, XIE Y Z, ZHANG H Y, Et al., Insulation fault diagnosis of disconnecting switches based on wavelet packet transform and PCA-IPSO-SVM of electric fields, IEEE Access, 8, pp. 176676-176690, (2020)

[28]

XIONG S C, ZHOU H D, HE S, Et al., A novel end-to-end fault diagnosis approach for rolling bearings by integrating wavelet packet transform into convolutional neural network structures, Sensors, 20, 17, (2020)

[29]

ZHAO G Q, JIANG Z D, HU C, Et al., Bearing fault diagnosis based on wavelet packet energy entropy and DBN, Journal of Electronic Measurement and Instrumentation, 33, 2, pp. 32-38, (2019)

[30]

HU G S, Modern signal processing tutorial, (2015)

← 1 2 3 4 →