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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bey-Temsamani, A., Engels, M., Motten, A., Vandenplas, S., Ompusunggu, A.P.: A Practical Approach to Combine Data Mining and Prognostics for Improved Predictive Maintenance. In: The Data Mining Case Studies Workshop (DMCS), 15th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2009), Paris, pp. 37–44 (2009)
Caruana, R.: Multitask Learning. Machine Learning 28, 41–75 (1997)
Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)
Ducange, P., Lazzerini, B., Marcelloni, F.: Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets. Soft Computing - A Fusion of Foundations, Methodologies and Applications (in press), doi:10.1007/s00500-009-0460-y
Gusikhin, O., Rychtyckyj, N., Filev, D.: Intelligent systems in the automotive industry: applications and trends. Knowl. Inf. Syst. 12(2), 147–168 (2007)
Last, M.: Multi-Objective Classification with Info-Fuzzy Networks. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 239–249. Springer, Heidelberg (2004)
Last, M., Danon, G., Biderman, S., Miron, E.: Optimizing a Batch Manufacturing Process through Interpretable Data Mining Models. Journal of Intelligent Manufacturing 20(5), 523–534 (2009)
Last, M., Elnekave, S., Naor, A., Shonfeld, V.: Predicting Wine Quality from Agricultural Data with Single-Objective and Multi-Objective Data Mining Algorithms. In: Warren Liao, T., Triantaphyllou, E. (eds.) Recent Advances on Mining of Enterprise Data: Algorithms and Applications. Series on Computers and Operations Research, vol. 6, pp. 323–365. World Scientific, Singapore (2007)
Last, M., Maimon, O.: A Compact and Accurate Model for Classification. IEEE Transactions on Knowledge and Data Engineering 16(2), 203–215 (2004)
Schwall, M., Gerdes, J.C., Bäker, B., Forchert, T.: A probabilistic vehicle diagnostic system using multiple models. In: 15th Innovative Applications of Artificial Intelligence Conference (IAAI 2003), Acapulco, Mexico, pp. 123–128 (2003)
Suzuki, E., Gotoh, M., Choki, Y.: Bloomy Decision Tree for Multi-objective Classification. In: Siebes, A., De Raedt, L. (eds.) PKDD 2001. LNCS (LNAI), vol. 2168, pp. 436–447. Springer, Heidelberg (2001)
Wu, S., Gebraeel, N., Lawley, M., Yih, Y.: A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy. IEEE Transactions on Systems, Man and Cybernetics-Part A 37(2), 226–236 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Last, M., Sinaiski, A., Subramania, H.S. (2010). Predictive Maintenance with Multi-target Classification Models. In: Nguyen, N.T., Le, M.T., Świątek, J. (eds) Intelligent Information and Database Systems. ACIIDS 2010. Lecture Notes in Computer Science(), vol 5991. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12101-2_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-12101-2_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12100-5
Online ISBN: 978-3-642-12101-2
eBook Packages: Computer ScienceComputer Science (R0)