No abstract

He received his B. Eng. degree in computer engineering from Tribhuvan University, Nepal in 2006 and received his master's degree from Stockholm University, Sweden in 2013. His current research areas are data mining and machine learning. Tony Lindgren Tony Lindgren was born in Hä gersten, Stockholm in 1974. He received his master degree in computer and system sciences in 1999. In 2006 he received his Ph.D. degree in computer and system sciences. He has worked both in academia and industry since 2008, he is the inventor of numerous patents and has a permanent position as lecturer at the Department of Computer and System Sciences at Stockholm University since 2012. His main interest is in the field of machine learning, artificial intelligence and constraint programming.Henrik Boström is a professor in computer sciencedata science systems at KTH Royal Institute of Technology. His expertise is within machine learning, primarily ensemble learning, rule and decision tree learning and conformal prediction. He is an action editor of the machine learning journal and on the editorial boards of Journal of Machine Learning Research, Knowledge Discovery and Data Mining, and Intelligent Data Analysis.

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 maintenanceservice 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.

No abstract

No abstract