Failure Mode and Effects Analysis in AI Enable Cars: A Study in Guwahati City

Abstract

The study explores the application of Failure Mode and Effects Analysis (FMEA) in Guwahati City's AI- enabled automobiles. Comprehending probable failure modes and their consequences is essential to improving vehicle safety and dependability as artificial intelligence technologies transform the automotive sector. In this study, different failure modes peculiar to AI-enabled cars functioning in Guwahati's distinct urban environment are identified and analysed. By means of an extensive assessment procedure, the research evaluates the degree, frequency, and identification of possible malfunctions, offering valuable perspectives on reducing the hazards linked to artificial intelligence-based features. The results are intended to aid in the creation of strong safety guidelines and legal frameworks for AI-powered automobile systems in city environments. The research methodology involves collecting real-world data from AI-enabled cars operating in Guwahati, analysing sensor performance, and identifying common failure points through expert interviews and historical incident reports. Specific attention is given to the impact of local weather conditions, road quality, and unpredictable traffic patterns on the reliability and safety of these vehicles. The study identifies several high-risk failure modes, such as sensor malfunctions in heavy rainfall, misinterpretation of road construction zones, and challenges in detecting sudden obstacles. The severity and occurrence of these failures are evaluated, and their effects on overall vehicle safety and performance are discussed. By addressing these failure modes, the study aims to contribute to the development of safer autonomous vehicles and inform future research and policy decisions in the deployment of AI-driven transportation