Automotive Multilingual Fault Diagnosis
This work addresses the challenge of multilingual fault diagnosis for automotive companies with vehicle fleets, though it is incremental as it applies an existing method to a new domain.
The study tackled the problem of AI-based fault diagnosis in the automotive industry by using a multilingual pre-trained Transformer to classify textual claims across 38 languages and 1,357 classes, achieving over 80% accuracy for high-frequency classes and above 60% for above-low-frequency classes.
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.