QI Jiyang, WANG Lingyun. Fault Diagnosis Method of Equipment based on Multi-information Fusion[J]. International Journal of Plant Engineering and Management, 2020, 25(2): 77-97

Fault Diagnosis Method of Equipment based on Multi-information Fusion
QI Jiyang1,2, WANG Lingyun1
1. School of Mechanical Engineering, Jiangsu University of Science and Technology, Jiangsu Zhenjiang 212003, China;
2. Jiangsu Key Laboratory of Recycling and Reusing Technology for Mechanical and Electronic Products, Jiangsu Changshu 215500, China
The traditional fault diagnosis method is completely based on the fault symptom without considering failure rate, so the fault diagnosis accuracy is not ideal. To improve the correctness rate of fault diagnosis, the paper proposes a fault diagnosis method of equipment based on failure rate and fault symptom. Firstly, an algorithm for calculating the equipment failure rate is proposed based on Weibull distribution model; Secondly, the probability of fault existence is evaluated based on fault symptom; Thirdly, a new fault diagnosis model is herein presented based on fault rate and fault symptom; Finally, the method is proved to be applicable through an example. The method takes failure rate, fault mechanism, fault symptom, difficulty degree of symptom acquisition and other factors into consideration, so the fault diagnosis accuracy is improved greatly.
Key words:    fault diagnosis    failure rate    fault symptom    weibull distribution   
Received:     Revised:
DOI: 10.13434/j.cnki.1007-4546.2020.0202
Funds: This paper is supported by Jiangsu Key Laboratory of Recycling and Reuse Technology for Mechanical and Electronic Products (RRME-KF1605)
Corresponding author:     Email:
Author description:
PDF(KB) Free
QI Jiyang
WANG Lingyun

[1] Zhou A M, Fu D J, Zhang W Y. A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA[J]. Advanced Engineering Informatics, 2015,29(1):115-125
[2] Muralidharan A, Sugumaran V, Soman K P, et al. Fault diagnosis of helical gear box using variational mode decomposition and random forest algorithm[J]. SDHM Structural Durability and Health Monitoring, 2015, 10(1):55-65
[3] Mansour M M, Wahab Mohamed A A, Soliman Wael M. Fault diagnosis system for large power generation station and its transmission lines based on fuzzy relations[J]. International Transactions on Electrical Energy Systems, 2015,25(5):753-769
[4] Tian J T, Wang R L, Wang B, et al. Fault diagnosis of digging robots hydraulic system based on fuzzy theory[J]. Fluid Power Transmission and Control,2014,(5):9-12(in Chinese)
[5] Sheng B, Deng C, Xiong Y, et al. Fault diagnosis for CNC machine tool based on graph theory[J]. Computer Integrated Manufacturing Systems, 2015,21(6):1559-1570(in Chinese)
[6] Feng J P, Liu H M. Diagnosis of CNC tool changer based on fuzzy fault tree[J]. Science Technology and Engineering, 2012, 12(28):7184-7187(in Chinese)
[7] Zhang S X, Liu F L, Chen J X. Multi-attribute fuzzy decision-making method of test interval based on Weibull proportional hazards model[J]. Journal of Academy of Armored Force Engineering, 2012, 26(2):20-23(in Chinese)
[8] Shu Z R, Li Q S, Chan P W. Investigation of offshore wind energy potential in Hong Kong based on Weibull distribution function[J]. Applied Energy, 2015. 156:362-373
[9] Almalki S J, Nadarajah S. A new discrete modified Weibull distribution[J]. IEEE Transactions on Reliability, 2014, 63(1):68-80
[10] Cong S H. Study of diesel engine fault diagnosis based on fuzzy diagnosis technique[D]. Tianjin:Tianjin University, 2005(in Chinese)
[11] Rao H, Fu M F, Jin Y H. Comparing and analyzing the membership function in fuzzy diagnosis[J]. Journal of Nanchang University, 2006,30(4):383-387(in Chinese)