Automotive Multilingual Fault Diagnosis

TL;DR

This paper demonstrates that multilingual pre-trained Transformers can effectively classify automotive fault descriptions across 38 languages, improving troubleshooting accuracy and aiding diagnostics in the automotive industry.

Contribution

It introduces a novel multilingual classification approach for automotive fault descriptions, addressing the challenge of diverse languages and large class sets.

Findings

Over 80% accuracy for high-frequency classes

Above 60% accuracy for low-frequency classes

Multilingual classification benefits automotive troubleshooting

Abstract

Automated fault diagnosis can facilitate diagnostics assistance, speedier troubleshooting, and better-organised logistics. Currently, AI-based prognostics and health management in the automotive industry ignore the textual descriptions of the experienced problems or symptoms. With this study, however, we show that a multilingual pre-trained Transformer can effectively classify the textual claims from a large company with vehicle fleets, despite the task's challenging nature due to the 38 languages and 1,357 classes involved. Overall, we report an accuracy of more than 80% for high-frequency classes and above 60% for above-low-frequency classes, bringing novel evidence that multilingual classification can benefit automotive troubleshooting management.