Variable selection for heavy-duty vehicle battery failure prognostics using random survival forests



Published Jul 5, 2016
Sergii Voronov Daniel Jung Erik Frisk


Prognostics and health management is a useful tool for more flexible maintenance planning and increased system reliability. The application in this study is lead-acid battery failure
prognosis for heavy-duty trucks which is important to avoid unplanned stops by the road. There are large amounts of data available, logged from trucks in operation. However, data is not closely related to battery health which makes battery prognostic challenging. When developing a data-driven prognostics model and the number of available variables is large, variable selection is an important task, since including noninformative variables in the model have a negative impact on prognosis performance. Two features of the dataset has been identified, 1) few informative variables, and 2) highly correlated variables in the dataset. The main contribution is a novel method for identifying important variables, taking these two properties into account, using Random Survival Forests to estimate prognostics models. The result of the proposed method is compared to existing variable selection methods, and applied to a real-world automotive dataset. Prognostic
models with all and reduced set of variables are generated and differences between the model predictions are discussed, and favorable properties of the proposed approach are highlighted.

How to Cite

Voronov, S., Jung, D., & Frisk, E. (2016). Variable selection for heavy-duty vehicle battery failure prognostics using random survival forests. PHM Society European Conference, 3(1).
Abstract 93 | PDF Downloads 88



batteries, prognostics, feature selection, random survival forests

Cox, D. R., & Oakes, D. (1984). Analysis of survival data (Vol. 21). CRC Press.
Daigle, M., & Goebel, K. (2011). A model-based prognostics approach applied to pneumatic valves. International Journal of Prognostics and Health Management Volume 2 (color), 84.
Frisk, E., & Krysander, M. (2015). Treatment of accumulative variables in data-driven prognostics of lead-acid batteries. In Proceedings of ifac safeprocess’15. Paris, France.
Frisk, E., Krysander, M., & Larsson, E. (2014). Data-driven lead-acide battery prognostics using random survival forests. In Proceedings of the annual conference of the prognostics and health management society. FortWorth, Texas, USA.
Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, 1157–1182.
Harrell, F., Califf, R., Pryor, D., Lee, K., & Rosati, R. (1982). Evaluating the yield of medical tests. Jama, 247(18), 2543–2546.
Ishwaran, H., Kogalur, U., Blackstone, E., & Lauer, M. (2008). Random survival forests. The Annals of Applied Statistics, 841–860.
Ishwaran, H., Kogalur, U., Chen, X., & Minn, A. (2011). Random survival forests for high-dimensional data. Statistical Analysis and Data Mining: The ASA Data Science Journal, 4(1), 115–132.
Ishwaran, H., Kogalur, U., Gorodeski, E., Minn, A., & Lauer, M. (2010). High-dimensional variable selection for survival data. Journal of the American Statistical Association, 105(489), 205–217.
Si, X., Wang, W., Hu, C., & Zhou, D. (2011). Remaining useful life estimation–a review on the statistical data driven approaches. European Journal of Operational Research, 213(1), 1–14.
Voronov, S., Jung, D., & Frisk, E. (2016). Heavy-duty truck battery failure prognostics using random survival forests. In Proceedings of Advances in Automotive Control, (Accepted for publication). Norrk¨oping, Sweden.
Technical Papers