Transforming Vehicle Diagnostics: A Multimodal Approach to Error Patterns Prediction

TL;DR

This paper introduces BiCarFormer, a multimodal Transformer model that combines diagnostic trouble codes and environmental data to improve vehicle error pattern prediction, leading to more accurate diagnostics and maintenance.

Contribution

It presents the first multimodal approach integrating DTC sequences and environmental data for vehicle error classification using a bidirectional Transformer.

Findings

Significant performance improvement over sequence-only models

Effective modeling of complex relationships between codes and environmental factors

Demonstrated on a large real-world automotive dataset

Abstract

Accurately diagnosing and predicting vehicle malfunctions is crucial for maintenance and safety in the automotive industry. While modern diagnostic systems primarily rely on sequences of vehicular Diagnostic Trouble Codes (DTCs) registered in On-Board Diagnostic (OBD) systems, they often overlook valuable contextual information such as raw sensory data (e.g., temperature, humidity, and pressure). This contextual data, crucial for domain experts to classify vehicle failures, introduces unique challenges due to its complexity and the noisy nature of real-world data. This paper presents BiCarFormer: the first multimodal approach to multi-label sequence classification of error codes into error patterns that integrates DTC sequences and environmental conditions. BiCarFormer is a bidirectional Transformer model tailored for vehicle event sequences, employing embedding fusions and a co-attention mechanism to capture the relationships between diagnostic codes and environmental data. Experimental results on a challenging real-world automotive dataset with 22,137 error codes and 360 error patterns demonstrate that our approach significantly improves classification performance compared to models that rely solely on DTC sequences and traditional sequence models. This work highlights the importance of incorporating contextual environmental information for more accurate and robust vehicle diagnostics, hence reducing maintenance costs and enhancing automation processes in the automotive industry.