Secure Explainable-AI Approach for Brake Faults Prediction in Heavy Transport

Abstract

Ensuring the safety of vehicles requires the critical responsibility of diagnosing and correcting brake faults. Implementing this proactive measure to address brake faults not only ensures the protection of lives but also enhances the efficiency and cost-effectiveness of repair processes conducted on-site. Machine learning technology has recently contributed to a significant rise in the popularity of predictive maintenance. The objective of this study is to provide a method for identifying issues with the air pressure system (APS) of air brake systems in heavy-duty vehicles. The data obtained by sensors has been used to analyse the APS failure in this Scania Truck. After examining numerous classification methods, Random Forest was determined to have the greatest performance, with a classification accuracy of 99.4%. Moreover, the implementation of eXplainable Artificial Intelligence has included the use of SHapley Additive exPlanation (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) to provide explanations for the contributions of features in model predictions. We picked 20 features from the wheel speed sensor data received from several Internet of Things (IoTs) sensors, which significantly influenced our final selection. By repeatedly applying random forest to these 20 features, we achieved the same degree of accuracy as previously. Consequently, our suggested approach used a reduced amount of computer resources and was less intricate to execute in terms of calculation.

Keywords

• Predictive maintenance
• machine learning
• eXplainable AI (XAI)
• SHAP
• smart transportation system