A new online fuzzy modelling method considering prior information with its application in PHM

Prognostic modelling methods play a key role in prognostics and health management (PHM). Over recent years, a number of researches have been undertaken to establish the prognostic models, roughly divided into physical models, knowledge-based models, and data-driven models. Currently, data-driven modelling methods have received considerable attention with the development of high technologies, especially digital computer and advanced sensor techniques. Adaptive fuzzy systems belong to the data-driven modelling methods, but the fuzzy model is different from many other data-driven modelling methods owing to its advantage of using not only quantitative data but also qualitative information with fuzzy uncertainty. Compared with the prediction from an offline fuzzy model, an online prediction is more desired, since we can monitor the health condition of a system and predict its trend in real time. However, most of the existing online fuzzy modelling methods neglect the full utilization of the offline information. In this paper, a new online fuzzy modelling method considering prior information is proposed for prognosis, which is briefly called off-online fuzzy modelling method here. The results of the case studies show that our developed method gains a significant improvement over the existing fuzzy modelling methods in terms of accuracy and the corresponding prognosis algorithm is effective.

[1]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[2]  Paramasivan Saratchandran,et al.  Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction , 2006, Fuzzy Sets Syst..

[3]  Wenbin Wang,et al.  An off-online fuzzy modelling method for fault prognosis with an application , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[4]  Liao Long.  T-S Fuzzy Model Identification with Growing and Pruning Rules for Nonlinear Systems , 2007 .

[5]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[6]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[7]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[8]  Liu Datong,et al.  A review: Prognostics and health management , 2010 .

[9]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[10]  Hu Chang,et al.  An RVM Fuzzy Model Identification Method and Its Application to Fault Prediction , 2011 .

[11]  Loon Ching Tang,et al.  Application of neural networks in forecasting engine systems reliability , 2003, Appl. Soft Comput..

[12]  M.G. Pecht,et al.  Prognostics and health management of electronics , 2008, IEEE Transactions on Components and Packaging Technologies.

[13]  Ming Dong,et al.  Equipment PHM using non-stationary segmental hidden semi-Markov model , 2011 .