Predicting NOx sensor failure in heavy duty trucks using histogram-based random forests



Published Nov 16, 2020
Ram B. Gurung Tony Lindgren Henrik Bostr¨om


Being able to accurately predict the impending failures of truck components is often associated with significant amount of cost savings, customer satisfaction and flexibility in maintenance
service plans. However, because of the diversity in the way trucks typically are configured and their usage under different conditions, the creation of accurate prediction models is not an easy task. This paper describes an effort in creating such a prediction model for the NOx sensor, i.e., a component measuring the emitted level of nitrogen oxide in the exhaust of the engine. This component was chosen because it is vital for the truck to function properly, while at the same time being very fragile and costly to repair. As input to the model, technical specifications of trucks and their operational data are used. The process of collecting the data and making it ready for training the model via a slightly modified Random Forest learning algorithm is described along with various challenges encountered during this process. The operational data consists of features represented as histograms, posing an additional challenge for the data analysis task. In the study, a modified version of the random forest algorithm is employed, which exploits the fact that the individual bins in the histograms are related, in contrast to the standard approach that would consider the bins as independent features. Experiments are conducted using the updated random forest algorithm, and they clearly show that the modified version is indeed beneficial when compared to the standard random forest algorithm. The performance of the resulting prediction model for the NOx sensor is promising and may be adopted for the benefit of operators of heavy trucks.

Abstract 236 | PDF Downloads 313



Histogram Features, NOx sensor prognostics, Histogram-based random forest

Bolander, N., Qiu, H., Eklund, N., Hindle, E.,&Rosenfeld, T. (2009). Physics-based remaining useful life prediction for aircraft engine bearing prognosis..
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Daigle, M. J., & Goebel, K. (2011). A model-based prognostics approach applied to pneumatic valves. International Journal of Prognostics and Health Management, 2, 84.
Devarakonda, M., Parker, G., & Johnson, J. (2012, July 31). Nox control systems and methods for controlling nox emissions. Google Patents. Retrieved from US8230677 (US Patent 8,230,677)
Devetyarov, D., & Nouretdinov, I. (2010). Prediction with confidence based on a random forest classifier. In Artificial intelligence applications and innovations.
Eyal, A., Rokach, L., Kalech, M., Amir, O., Chougule, R., Vaidyanathan, R., & Pattada, K. (2014). Survival analysis of automobile components using mutually exclusive forests. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 44, 246-253.
Frisk, E., Krysander, M., & Larsson, E. (2014). Datadriven lead-acid battery prognostics using random survival forests. In Annual conference of the prognostics and health management society 2014 (p. 92-101).
Gurung, R., Lindgren, T., & Bostr¨om, H. (2015). Learning decision trees from histogram data. In Proceed-ings of the 11th international conference on data mining (p. 139-145).
Gurung, R., Lindgren, T., & Bostr¨om, H. (2016). Learning decision trees from histogram data using multiple subsets of bins. In Proceedings of the 29th international florida artificial intelligence research society conference (flairs) (p. 430-435).
Ishwaran, H., Kogalur, U., Blackstone, E., & Lauer, M. (2008). Random survival forests. Ann. Appl. Statist., 2(3), 841–860.
Johansson, U., Bostrm, H., & Lfstrm, T. (2013). Conformal prediction using decision trees. In 2013 ieee 13th international conference on data mining (p. 330-339).
Lawless, J., Hu, J., & Cao, J. (1995). Methods for the estimation of failure distributions and rates from automobile warranty data. Lifetime Data Analysis, 1, 227-240.
Liao, L., & K¨ottig, F. (2016, July). A hybrid framework combining data-driven and model-based methods for system remaining useful life prediction. Appl. Soft Comput., 44(C), 191–199.
Lindgren, T.,Warnquist, H., & Eineborg, M. (2013). Improving the maintenance planning of heavy trucks using constraint programming. In Proceedings of the 12th international workshop on constraint modelling and reformulation co-located with the 19th international conference on principles and practice of constraint programming (modref) (p. 74-90).
Prytz, R., Nowaczyk, S., Rgnvaldsson, T., & Byttner, S. (2015). Predicting the need for vehicle compressor repairs using maintenance records and logged vehicle data. Engineering Applications of Artificial Intelligence, 41, 139 - 150.
Sawada, H., & Imamura, S. (2012, July 10). Nox sensor malfunction diagnostic device and malfunction diagnostic method. Google Patents. Retrieved from
US8219278 (US Patent 8,219,278)
Schubert, F., Wollenhaupt, S., Kita, J., Hagen, G., & Moos, R. (2016). Platform to develop exhaust gas sensors manufactured by glass-solder-support joining of sintered yttria-stabilized zirconia. Journal of Sensors and Sensor Systems, 5, 25-32.
Si, X.-S., Wang, W., Hu, C.-H., & Zhou, D.-H. (2011). Remaining useful life estimation-a review on the statistical data driven approaches. European Journal of Operational Research, 213, 1-14.
Zhou, Y., & McArdle, J. J. (2015). Rationale and applications of survival tree and survival ensemble methods. Psychometrika, 80, 811-833.
Technical Papers