Enhancing Automotive Safety and Maintenance: An Intelligent Fault Detection Approach Using Fuzzy Logic

The rise of intelligent systems in the automotive industry has paved the way for significant advancements in vehicle safety and maintenance. This paper presents an innovative fault detection system that integrates fuzzy logic with Support Vector Machine (SVM) to enhance automotive diagnostics. The system leverages fuzzy logic to handle imprecise and uncertain sensor data, providing an initial diagnosis that is refined by the SVM model through data-driven learning. The proposed hybrid system demonstrates high accuracy, precision, recall, and F1 score, outperforming traditional diagnostic methods and comparable advanced systems. A comprehensive methodology is detailed, including the hardware and software requirements, data preprocessing, feature selection, and the implementation of fuzzy logic principles and Mamdani's algorithm. The combination of these components ensures robust performance and scalability. The system’s capabilities are evaluated through performance metrics and comparative analysis, with results presented in both tabular and visual formats. Case studies further illustrate the system's effectiveness in real-world scenarios, highlighting its ability to prevent significant mechanical failures and reduce maintenance costs. The findings suggest that the intelligent fault detection system not only enhances diagnostic accuracy and reliability but also contributes to proactive vehicle maintenance, thereby improving overall automotive safety. This research underscores the potential of integrating fuzzy logic with machine learning techniques in developing advanced diagnostic tools, setting a new benchmark for automotive maintenance practices. The system's real-time diagnostics and remote monitoring capabilities, facilitated by IoT integration and secure internet connectivity, further emphasize its practical applications in modern vehicular environments.