Condition-based Maintenance with Multi-Target Classification Models 1 Condition-based Maintenance with Multi- Target Classification Models Mark LAST and Alla SINAISKI Ben-Gurion University of the Negev Beer-Sheva 84105 ISRAEL Halasya Siva SUBRAMANIA India Science Lab, General Motors Global Research and Development GM Technical Centre India Pvt Ltd Creator Building, International Tech Park Ltd. Whitefield Road, Bangalore - 560 066, INDIA mlast@bgu.ac.il,sinaiski@gmail.com,halasyasiva.subramania@gm.com Received 15 November 2010 Abstract Condition-based maintenance (CBM) recommends mainte- nance actions based on the information collected through condition mon- itoring. In many modern cars, the condition of each subsystem can be monitored by onboard vehicle telematics systems. Prognostics is an im- portant aspect in a CBM program as it deals with prediction of future faults. In this paper, we present a data mining approach to prognosis of vehicle failures. A multi-target probability estimation algorithm (M-IFN) is applied to an integrated database of sensor measurements and warranty claims with the purpose of predicting the probability and the timing of a failure in a given subsystem. The results of the multi-target algorithm are shown to be superior to a single-target probability estimation algorithm (IFN) and reliability modeling based on Weibull analysis. Keywords Condition-based Maintenance, Telematics, Prognostics, Ve- hicle Health Management, Reliability, Multi-Target Classification, Info- Fuzzy Networks.