Computer Science

Computer Science ›› 2020, Vol. 47 ›› Issue (11A): 57-63.doi: 10.11896/jsjkx.190900174

• Artificial Intelligence • Previous Articles     Next Articles

System Fault Diagnosis Method Based on Mahalanobis Distance Metric

LIN Yi1, JI Hong-jiang2, HAN Jia-jia3, ZHANG De-ping3   

  1. 1 Unit 91776 of the PLA,Beijing 100084,China
    2 China Shipbuilding IT CO.,LTD.,Beijing 100861,China
    3 College of Computer Science and Technology,Nanjing University of Aeronautics & Astronautics,Nanjing 210000,China
  • Online:2020-11-15 Published:2020-11-17
  • About author:LIN Yi,born in 1982,master,assistant research fellow.His main research interests include military big data,military modeling and simulation,and evaluating effectiveness of military system.
    JI Hong-jiang,born in 1987,master,engineer.His main research interests include military and industrial big data and artificial intelligence,information integration and modeling.
  • Supported by:
    This work was supported by the General Assembly Pre Research Project Fund(41402020501).

PDF (PC)

819

Abstract: In view of the multi-index related problems in previous fault diagnosis methods and the shortcomings of the calculated complication and low efficiency when considering multiple integrals,a system fault diagnosis method based on Mahalanobis Distance (MD) metrics is proposed to improve these problems.For the system performance state data monitored on a certain device,the proposed method is to calculate the MD area metric method to compare the distribution of the Mahalanobis Distances of the known data samples with the distribution of the Mahalanobis Distances of the observed data samples.Specifically,the MD method is firstly used to convert multivariate data into univariate data,and the correlation between multivariable is eliminated,and the complexity and uncertainty of multivariate joint distribution using multiple integrals are avoided.Then the area metric is used to compare the difference between the cumulative distribution functions of the univariate data,and the area value between the distribution curves is calculated according to the definite integral,and the smaller area value is the category of the sample fault.By comparing with common fault diagnosis methods (BP neural network and Naïve Bayes),it shows that the proposed method is simple and effective,the fault diagnosis rate is high,and the calculation cost is greatly reduced,and the system fault diagnosis efficiency is improved.

Key words: Area metric, Cumulative distribution function, Fault diagnosis, Mahalanobis distance (MD)

CLC Number: 

  • TP311
[1] CHEN Y.Theories and methods of automobile engine fault diagnosis[J].Industry Press,2016(6):56-57.
[2] MENG X P,LI J L,ZHANG Y W.Fault Diagnosis of Building Automation System Based on Expert System[J].Computer Engineering,2011,37(21):273-275.
[3] ZHAO L,LU Z,YUN W,et al.Validation metric based on Mahalanobis distance for models with multiple correlated responses[J].Reliability Engineering & System Safety,2017,159:80-89.
[4] SIDHU A,IZADIAN A,ANWAR S.Adaptive NonlinearMo-del-Based Fault Diagnosis of Li-Ion Batteries[J].Industrial Electronics IEEE Transactions on,2014,62(2):1002-1011.
[5] KARGAR S M,SALAHSHOOR K,YAZDANPANAH M J.Integrated nonlinear model predictive fault tolerant control and multiple model based fault detection and diagnosis[J].Chemical Engineering Research & Design Transactions of the Inst,2014,92(2):340-349.
[6] ZHENG Q,WANG Y,UNIVERSITY Q N.Fault Diagnosis of Generator Sets Based on Fault Tree Analysis[J].Marine Electric & Electronic Engineering,2017.
[7] REN Y,YAXIONG B I,WANG D,et al.Fault tree intelligent diagnosis technology for wind turbine drivetrain[J].Journal of Drainage & Irrigation Machinery Engineering,2016.
[8] ENRIQUE SUCAR L,BIELZA C,MORALES E F,et al.Multi-label classification with Bayesian network-based chain classifiers[J].Pattern Recognition Letters,2014,41(1):14-22.
[9] HE S,WANG Z,WANG Z,et al.Fault Detection and Diagnosisof Chiller Using Bayesian Network Classifier with Probabilistic Boundary[J].Applied Thermal Engineering,2016,107:37-47.
[10] CAI B,HUANG L,XIE M.Bayesian Networks in Fault Diagnosis[J].IEEE Transactions on Industrial Informatics,2017,PP(99):1-1.
[11] XUE S S,LI X C,XU X Y.Fault Tree and Bayesian Network Based Scraper Conveyer Fault Diagnosis[M]//Proceedings of the 22nd International Conference on Industrial Engineering and Engineering Management 2015.Atlantis Press,2016.
[12] KOWALSKI P A,KULCZYCKI P.Interval probabilistic neural network[J].Neural Computing & Applications,2017,28(4):1-18.
[13] 王子健.基于概率神经网络的发动机失火故障诊断[D].长春:吉林大学,2016.
[14] XU S,LIU D,LIU B.Application of fuzzy algorithm-based multiple cmac neural networks in coagulant dosing system [J].Computer Applications & Software,2016(3):23-28.
[15] WANG D,ZHAO X J.A simple and fast guideline for generating enhanced/squared envelope spectra from spectral coherence for bearing fault diagnosis[J].Mechanical Systems and Signal Processing,2019,122:754-768.
[16] ZONG M,MENG H,GU W,et al.Rolling Bearing Fault Diagnosis Method Based on LMD Multi-scale Entropy and Probabilistic Neural Network[J].China Mechanical Engineering,2016.
[17] FERNÁN D M,CISNEROSRUIZ A J,CALLEJÓNGIL Á.Applying a probabilistic neural network to hotel bankruptcy prediction[J].Tourism & Management Studies,2016,12(1):40-52.
[18] LIU D,ZENG H,XIAO Z,et al.Fault diagnosis of rotor using EMD thresholding-based de-noising combined with probabilistic neural network[J].Journal of Vibroengineering,2017,19(8).
[19] ZHAO L,LU Z,YUN W,et al.Validation metric based on Mahalanobis distance for models with multiple correlated responses[J].Reliability Engineering & System Safety,2017,159:80-89.
[20] LEI Y,LI N.Machinery health prognostics:a systematic review from data acquisition to RUL prediction[J].Mech.Syst.Signal Process,2018,104:799-834.
[21] MELLIT A,TINA G M,KALOGIROU S A.Fault detection and diagnosis methods for photovoltaic systems:A review[J].Renewable and Sustainable Energy Reviews,2018,91:1-17.
[22] COWLING B J,HEDLEY A J.The Mahalanobis Distance[M].BMJ,2017.
[23] MEI J,LIU M,WANG Y F,et al.Learning a Mahalanobis Distance-Based Dynamic Time Warping Measure for Multivariate Time Series Classification[J].IEEE Transactions on Cyberne-tics,2016,46(6):1363-1374.
[1] LEI Jian-mei, ZENG Ling-qiu, MU Jie, CHEN Li-dong, WANG Cong, CHAI Yong. Reverse Diagnostic Method Based on Vehicle EMC Standard Test and Machine Learning [J]. Computer Science, 2021, 48(6): 190-195.
[2] WANG Tao, ZHANG Shu-dong, LI An, SHAO Ya-ru, ZHANG Wen-bo. Anomaly Propagation Based Fault Diagnosis for Microservices [J]. Computer Science, 2021, 48(12): 8-16.
[3] ZHU Xiao-ling, LI Kun, ZHANG Chang-sheng, DU Fu-xin. Elevator Boot Fault Diagnosis Method Based on Gabor Wavelet Transform and Multi-coreSupport Vector Machine [J]. Computer Science, 2020, 47(12): 258-261.
[4] GUO Yang, LIANG Jia-rong, LIU Feng, XIE Min. Novel Fault Diagnosis Parallel Algorithm for Hypercube Networks [J]. Computer Science, 2019, 46(5): 73-76.
[5] WANG Yan, LUO Qian, DENG Hui. Bearing Fault Diagnosis Method Based on Variational Bayes [J]. Computer Science, 2019, 46(11): 323-327.
[6] ZHANG Gang, GAO Jun-peng, LI Hong-wei. Research on Stochastic Resonance Characteristics of Cascaded Three-steady-state and Its Application [J]. Computer Science, 2018, 45(9): 146-151.
[7] ZHANG Bin,TENG Jun-jie,MAN Yi. Application Research of Improved Parallel Fp-growth Algorithm in Fault Diagnosis
of Industrial Equipment [J]. Computer Science, 2018, 45(6A): 508-512.
[8] XUE Shan-liang, YANG Pei-ru and ZHOU Xi. WSN Wireless Data Transceiver Unit Fault Diagnosis with Fuzzy Neural Network [J]. Computer Science, 2018, 45(5): 38-43.
[9] ZHANG Ni, CHE Li-zhi and WU Xiao-jin. Present Situation and Prospect of Data-driven Based Fault Diagnosis Technique [J]. Computer Science, 2017, 44(Z6): 37-42.
[10] CHEN Miao-jiang, LIANG Jia-rong and ZHANG Qian. Hypercube Network Diagnosis Algorithm under Comparison Model [J]. Computer Science, 2017, 44(6): 83-90.
[11] ZHOU Xi and XUE Shan-liang. WSN Fault Diagnosis with Improved Rough Set and Neural Network [J]. Computer Science, 2016, 43(Z11): 21-25.
[12] CHEN Yun-feng, WANG Hong-jun and YANG Yan. Fault Diagnosis of High-speed Rail Based on Clustering Ensemble [J]. Computer Science, 2015, 42(6): 233-238.
[13] WANG Xue-jie and HUANG Hai-yan. Fault Diagnosis Method Based on Immunodominance Clone Cultural Algorithm and its Application in TE Process [J]. Computer Science, 2015, 42(5): 255-259.
[14] JIA Zhi-chun and XING Xing. Diagnosis of Web Service Based on Bayes and Multi-faults Reasoning [J]. Computer Science, 2014, 41(6): 225-230.
[15] FANG Huan,FANG Xian-wen and LI De-quan. Review on Fault Diagnosis Theory and Application Based on Petri Nets [J]. Computer Science, 2014, 41(3): 17-22.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.