Machine prognostics based on survival analysis and support vector machine
Intelligent machine prognostics system estimates the remaining useful life of machine components. It deals with prediction of machine health condition based on past measured data from condition monitoring (CM). It has benefits to reduce the production downtime, spare-parts inventory, maintenance cost, and safety hazards. Many papers have reported the valuable models and methods of prognostics systems. However, it was rarely found the papers deal with censored data, which was common in machine condition monitoring practice. This work concerns with developing intelligent machine prognostics system using survival analysis (SA) and support vector machine (SVM). Survival analysis utilizes censored and uncensored data collected from condition monitoring routine then estimates the survival probability of failure time of machine components. SVM was trained by data input from CM data that corresponds to target vectors of estimated survival probability. After validation, SVM is addressed to predict survival probability of individual unit of machines. Progressive bearing degradation data were simulated and trained to validate the proposed method. The result shows the proposed method is promising to be a probability-based machine prognostics system.
KeywordsSupport Vector Machine Survival Probability Target Vector Machine Component Prognostic System
Unable to display preview. Download preview PDF.
- 3.Heng A, Tan A, and Mathew J. (2008) Asset health prognosis incorporating reliability data and condition monitoring histories. In Gao J, Lee J, Ni J, Ma L, and Mathew J. Proceeding of the 3rd World Congress Engineering Asset Management and Intelligent Maintenance System (WCEAM-IMS 2008). Beijing, China. pp. 666-672. London: Springer-Verlag.Google Scholar
- 8.Haykin S. (1999) Neural Network 2nd Ed. New Jersey, Upper Saddle River: Prentice-Hall.Google Scholar