A multi-indicator modeling method for similarity-based residual useful life estimation with two selection processes

The similarity-based residual useful life prediction (SbRLP) approach, a burgeoning technique, plays an increasingly important role in the residual useful life (RUL) prediction. Currently, studies on taking (a) the selection of degradation indicatorsf; and (b) the selection of reference samples into account are rare. While they have positive influence on improving the performance of the SbRLP method with multiple degradation indicator (MSbRLP). Driven by the abovementioned gap, two novel selection processes are advanced by this article and thus an improved MSbRLP method is developed. Then, in case study of the gyroscope RUL estimation, two selection processes and the improved MSbRLP method are illustrated to be reasonable and effective by comparison with the classical MSbRLP method. Furthermore, implementing results reveal that the existence of degradation indicator having bad reflection effect will truly increase the recognition error of the degradation state and hence decrease the accuracy of RUL estimation.

[1]  Wenyuan Lv,et al.  A novel method using adaptive hidden semi-Markov model for multi-sensor monitoring equipment health prognosis , 2015 .

[2]  Piero P. Bonissone,et al.  An Instance-Based Method for Remaining Useful Life Estimation for Aircraft Engines , 2008 .

[3]  Enrico Zio,et al.  A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system , 2010, Reliab. Eng. Syst. Saf..

[4]  Noureddine Zerhouni,et al.  Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction , 2016, J. Intell. Manuf..

[5]  Guang Meng,et al.  A Framework of Similarity-Based Residual Life Prediction Approaches Using Degradation Histories With Failure, Preventive Maintenance, and Suspension Events , 2013, IEEE Transactions on Reliability.

[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]  Khac Tuan Huynh,et al.  Maintenance Decision-Making for Systems Operating Under Indirect Condition Monitoring: Value of Online Information and Impact of Measurement Uncertainty , 2012, IEEE Transactions on Reliability.

[8]  Xing Wang,et al.  A dynamic multi-scale Markov model based methodology for remaining life prediction , 2011 .

[9]  Guang Meng,et al.  Toward effective utilization of similarity based residual life prediction methods: Weight allocation, prediction robustness, and prediction uncertainty , 2013 .

[10]  Weifeng Tian,et al.  EMD-and SVM-based temperature drift modeling and compensation for a dynamically tuned gyroscope (DTG) , 2007 .

[11]  Noureddine Zerhouni,et al.  Joint Prediction of Continuous and Discrete States in Time-Series Based on Belief Functions , 2013, IEEE Transactions on Cybernetics.

[12]  Lingling Wang,et al.  A D-optimal Multi-position Calibration Method for Dynamically Tuned Gyroscopes , 2011 .

[13]  Qing Zhang,et al.  Remaining useful life estimation for mechanical systems based on similarity of phase space trajectory , 2015, Expert Syst. Appl..

[14]  Donghua Zhou,et al.  Remaining Useful Life Estimation Based on a Nonlinear Diffusion Degradation Process , 2012, IEEE Transactions on Reliability.

[15]  G. Meng,et al.  A generalized similarity measure for similarity-based residual life prediction , 2011 .

[16]  Jianbo Yu,et al.  A similarity-based prognostics approach for Remaining Useful Life estimation of engineered systems , 2008, 2008 International Conference on Prognostics and Health Management.

[17]  Li Fu,et al.  A novel calibration procedure for dynamically tuned gyroscope designed by D-optimal approach , 2013 .

[18]  Hong-xing Li,et al.  Fuzzy decision making based on variable weights , 2004 .

[19]  Yaguo Lei,et al.  A Model-Based Method for Remaining Useful Life Prediction of Machinery , 2016, IEEE Transactions on Reliability.