Application of Improved Genetic Programming for Feature Extraction in the Evaluation of Bearing Performance Degradation

In the evaluation of bearing performance degradation, discovering a good HI (Health Indicator) is one of the most crucial parts, because it determines whether a precise result can be obtained in the prediction of remaining useful life. In this paper, GP (Genetic Programming), which is a heuristic iterative search algorithm inspired by the theory of biological evolution, is improved in genetic operation and fitness function, and a feature weighted matrix is used in GP innovatively. The improved GP is applied to discover a HI by fusing multiple features, which is very close to linearity. Furthermore, by optimizing the discovered HIs, an optimization HI is obtained, which has a higher fitness and can get a more precise result in the prediction of RUL. The proposed approach is verified in the experimental data for the entire life of the bearing provided by 2012 IEEE PHM challenge, and a total of three bearings are used in the verification.

[1]  Peter W. Tse,et al.  Prognostics of slurry pumps based on a moving-average wear degradation index and a general sequential Monte Carlo method , 2015 .

[2]  Hsing-Chih Tsai,et al.  Determining ultimate bearing capacity of shallow foundations using a genetic programming system , 2012, Neural Computing and Applications.

[3]  Luc Boullart,et al.  Genetic programming: principles and applications , 2001 .

[4]  YangBo-Suk,et al.  Application of relevance vector machine and survival probability to machine degradation assessment , 2011 .

[5]  Alaa Elwany,et al.  Sensor-driven prognostic models for equipment replacement and spare parts inventory , 2008 .

[6]  Noureddine Zerhouni,et al.  Data-driven prognostics based on health indicator construction: Application to PRONOSTIA's data , 2013, 2013 European Control Conference (ECC).

[7]  Yaguo Lei,et al.  An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings , 2015, IEEE Transactions on Industrial Electronics.

[8]  Fulei Chu,et al.  Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography , 2004 .

[9]  David He,et al.  Gear Health Threshold Setting Based On a Probability of False Alarm , 2011 .

[10]  Ruoyu Li,et al.  Fault features extraction for bearing prognostics , 2012, J. Intell. Manuf..

[11]  Yanyang Zi,et al.  A Two-Stage Data-Driven-Based Prognostic Approach for Bearing Degradation Problem , 2016, IEEE Transactions on Industrial Informatics.

[12]  Linxia Liao,et al.  Discovering Prognostic Features Using Genetic Programming in Remaining Useful Life Prediction , 2014, IEEE Transactions on Industrial Electronics.

[13]  Pavle Boskoski,et al.  Bearing fault prognostics based on signal complexity and Gaussian process models , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[14]  Xiao-Sheng Si,et al.  An Age- and State-Dependent Nonlinear Prognostic Model for Degrading Systems , 2015, IEEE Transactions on Reliability.

[15]  Yaguo Lei,et al.  A New Method Based on Stochastic Process Models for Machine Remaining Useful Life Prediction , 2016, IEEE Transactions on Instrumentation and Measurement.

[16]  Yaguo Lei,et al.  Machinery health prognostics: A systematic review from data acquisition to RUL prediction , 2018 .

[17]  K. Loparo,et al.  Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling : A method for bearing prognostics , 2007 .

[18]  Yongyong He,et al.  Hidden Markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery , 2005 .

[19]  Peter Nordin,et al.  Genetic programming - An Introduction: On the Automatic Evolution of Computer Programs and Its Applications , 1998 .

[20]  Hong Guo,et al.  Automated feature extraction using genetic programming for bearing condition monitoring , 2004, Proceedings of the 2004 14th IEEE Signal Processing Society Workshop Machine Learning for Signal Processing, 2004..