A multi-agent based failure prediction method using neural network algorithm

A continuous monitoring system with high reliability is significantly important for complex equipment which is usually expensive, large-scale and sophisticated. Once a failure happens, it brings about not only serious economic losses, but also potential security hazards. In order to overcome outage damage caused by temporary failure and ensure excellent operation of the equipment, this paper presented an effective prediction model which combined the back propagation neural network (BPNN) with multi-agent cooperation grouping algorithm. The values of weights and thresholds of BPNN were obtained through optimization results of the multi-agent cooperation grouping algorithm. Based on above initialization parameters which met corresponding demands, repeated BPNN training was utilized to forecast fault. Case study on continuous casting equipment validated that the proposed model is valid for failure prognosis with forecasting accuracy elevated, compared with classical BPNN prediction method. Another comparison, function approximation experiment on the basis of a benchmark function, also showed that the suggested method is superior to BPNN in convergence speed.

[1]  Arya K. Bhattacharya,et al.  Recognition of Fault Signature Patterns Using Fuzzy Logic for Prevention of Breakdowns in Steel Continuous Casting Process , 2005, PReMI.

[2]  Yili Hong,et al.  Reliability Meets Big Data: Opportunities and Challenges , 2014 .

[3]  Y.S. Wong,et al.  Intelligent prediction monitoring system for predictive maintenance in manufacturing , 2005, 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005..

[4]  Cui Zhi-quan,et al.  Prediction of engine gas path parameter deviation based on fractional aggregation process neural network , 2013 .

[5]  Ping Chen,et al.  Study on the Prediction of Gas Content Based on Grey Relational Analysis and BP Neural Network , 2013, BIC-TA.

[6]  Enrico Sciubba,et al.  Automatic diagnostics and prognostics of energy conversion processes via knowledge-based systems , 2004 .

[7]  Lin Mi,et al.  Multi-steps degradation process prediction for bearing based on improved back propagation neural network , 2013 .

[8]  Zhong Shi-sheng Failure detection of aeroengine based on process neural network with double hidden-layers , 2006 .

[9]  Yang Jiangtian,et al.  APPLICATION OF GREY MODEL TO MACHINERY FAULTS PREDICTION , 2001 .

[10]  Suresh K. Choubey,et al.  Failure event prediction using the Cox proportional hazard model driven by frequent failure signatures , 2007 .

[11]  Jie Zhao,et al.  Equipment Fault Forecasting Based on ARMA Model , 2007, 2007 International Conference on Mechatronics and Automation.

[12]  Weiming Shen,et al.  A method for transformation of engineering bill of materials to maintenance bill of materials , 2014 .

[13]  Fei Yin,et al.  Back propagation neural network based calculation model for predicting wear of fine-blanking die during its whole lifetime , 2012 .