Automated fault diagnosis can facilitate diagnostics assistance, speed up troubleshooting, and lead to better-organized logistics in all sorts of industries. Tony Lindgren, John Pavlopoulos and Korbinian Randl from the Department of Computer and Systems Sciences, Stockholm University, are exploring this important area in their research.
They recently presented their paper “Automotive Fault Nowcasting with Machine Learning and Natural Language Processing” at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML–PKDD) which was held in Turin, Italy, September 18–22, 2023. The paper has also been accepted for publication in the journal of Machine Learning.
“Currently, most AI-based prognostics and health management in the automotive industry ignore textual descriptions of the experienced problems or symptoms. With this study, however, we propose a machine learning assisted workflow for automotive fault nowcasting that improves on current industry standards. We show that a multilingual pre-trained Transformer model can effectively classify the textual symptom claims from a large company with vehicle fleets, despite the task’s challenging nature due to the 38 languages and 1,357 classes”, says Tony Lindgren.
The team sees excellent opportunities to apply the knowledge gained from the automotive industry to an equally complex system – food.
“Future direction of this work is to use a similar methodology in other areas, where results are of high value for all actors with a need for the predictions on complex systems. Food risk prevention is one such domain that we plan on applying this methodology to”, says Tony Lindgren.
Interested to learn more?
By Marilena Dimitrakopoulou, Research Project Manager, Agroknow. Last month, our project coordinator, Agroknow, travelled
By Tony Lindgren, Head of the Systems Analysis and Security Unit, Department of Computer
A Machine Learning Approach for automative fault nowcasting By John Pavlopoulos, assistant professor at