Predictive maintenance with multi-target classification models

Authors:
Mark Last;Alla Sinaiski;Halasya Siva Subramania
Affiliations:
Department of Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel;Department of Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel;India Science Lab, General Motors Global Research and Development, GM Technical Centre India Pvt Ltd, International Tech Park Ltd., Bangalore, India
Venue:
ACIIDS'10 Proceedings of the Second international conference on Intelligent information and database systems: Part II
Year:
2010

Citing 7
Cited 0

Multitask Learning

Machine Learning - Special issue on inductive transfer
Bloomy Decision Tree for Multi-objective Classification

PKDD '01 Proceedings of the 5th European Conference on Principles of Data Mining and Knowledge Discovery
A Compact and Accurate Model for Classification

IEEE Transactions on Knowledge and Data Engineering
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Intelligent systems in the automotive industry: applications and trends

Knowledge and Information Systems
Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets

Soft Computing - A Fusion of Foundations, Methodologies and Applications
A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unexpected failures occurring in new cars during the warranty period increase the warranty costs of car manufacturers along with harming their brand reputation. A predictive maintenance strategy can reduce the amount of such costly incidents by suggesting the driver to schedule a visit to the dealer once the failure probability within certain time period exceeds a pre-defined threshold. The condition of each subsystem in a car can be monitored onboard vehicle telematics systems, which become increasingly available in modern cars. In this paper, we apply a multi-target probability estimation algorithm (M-IFN) 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 multi-target algorithm performance is compared to a single-target probability estimation algorithm (IFN) and reliability modeling based on Weibull analysis.