Semi-supervised learning with co-training for data-driven prognostics

Traditional data-driven prognostics often requires a large amount of failure data for the offline training in order to achieve good accuracy for the online prediction. However, in many engineered systems, failure data are fairly expensive and time-consuming to obtain while suspension data are readily available. In such cases, it becomes essentially critical to utilize suspension data, which may carry rich information regarding the degradation trend and help achieve more accurate remaining useful life (RUL) prediction. To this end, this paper proposes a co-training-based data-driven prognostic algorithm, denoted by Cop rog, which uses two individual data-driven algorithms with each predicting RULs of suspension units for the other. The confidence of an individual data-driven algorithm in predicting the RUL of a suspension unit is quantified by the extent to which the inclusion of that unit in the training data set reduces the sum square error (SSE) in RUL prediction on the failure units. After a suspension unit is chosen and its RUL is predicted by an individual algorithm, it becomes a virtual failure unit that is added to the training data set. Results obtained from two case studies suggest that Coprog gives more accurate RUL predictions compared to any individual algorithm without the consideration of suspension data and that Coprog can effectively exploit suspension data to improve the accuracy in data-driven prognostics.

[1]  Bo-Suk Yang,et al.  Application of relevance vector machine and logistic regression for machine degradation assessment , 2010 .

[2]  F.O. Heimes,et al.  Recurrent neural networks for remaining useful life estimation , 2008, 2008 International Conference on Prognostics and Health Management.

[3]  Rommert Dekker,et al.  Applications of maintenance optimization models : a review and analysis , 1996 .

[4]  Zhi-Hua Zhou,et al.  Semisupervised Regression with Cotraining-Style Algorithms , 2007, IEEE Transactions on Knowledge and Data Engineering.

[5]  Byeng D. Youn,et al.  Ensemble of Data-Driven Prognostic Algorithms with Weight Optimization and K-Fold Cross Validation , 2010 .

[6]  Friedhelm Schwenker,et al.  Three learning phases for radial-basis-function networks , 2001, Neural Networks.

[7]  Günther Palm,et al.  Semi-supervised Learning for Regression with Co-training by Committee , 2009, ICANN.

[8]  Kaisa Simola,et al.  Application of stochastic filtering for lifetime prediction , 2006, Reliab. Eng. Syst. Saf..

[9]  J.W. Hines,et al.  Prognostic algorithm categorization with PHM Challenge application , 2008, 2008 International Conference on Prognostics and Health Management.

[10]  Sze-jung Wu,et al.  A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[11]  Zhigang Tian,et al.  A neural network approach for remaining useful life prediction utilizing both failure and suspension histories , 2010 .

[12]  Krishna R. Pattipati,et al.  Model-Based Prognostic Techniques Applied to a Suspension System , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[13]  Mark Schwabacher,et al.  A Survey of Data -Driven Prognostics , 2005 .

[14]  K. Goebel,et al.  Fusing competing prediction algorithms for prognostics , 2006, 2006 IEEE Aerospace Conference.

[15]  Jooyoung Park,et al.  Approximation and Radial-Basis-Function Networks , 1993, Neural Computation.

[16]  Matthew J. Watson,et al.  ELECTROCHEMICAL CELL DIAGNOSTICS USING ONLINE IMPEDANCE MEASUREMENT, STATE ESTIMATION AND DATA FUSION TECHNIQUES , 2001 .

[17]  P. D. McFadden,et al.  Model for the vibration produced by a single point defect in a rolling element bearing , 1984 .

[18]  Bo-Suk Yang,et al.  Application of relevance vector machine and survival probability to machine degradation assessment , 2011, Expert Syst. Appl..

[19]  Byeng D. Youn,et al.  A Generic Bayesian Framework for Real-Time Prognostics and Health Management (PHM) , 2009 .

[20]  Enrico Zio,et al.  Model-based Monte Carlo state estimation for condition-based component replacement , 2009, Reliab. Eng. Syst. Saf..

[21]  Joseph Mathew,et al.  Intelligent condition-based prediction of machinery reliability , 2009 .