Review of Automobile Engine Fault Diagnosis Technologies: From Traditional Methods to AI-based Intelligent Systems

Abstract

As the core power component of vehicle, the accuracy and efficiency of fault diagnosis of automobile engine are directly related to driving safety, economy and environmental protection. With the rapid development of the automobile industry, the engine structure is becoming more and more complex, and the degree of electronic control is increasing. The traditional diagnosis method based on manual experience has been difficult to meet the needs of modern maintenance. Based on a comprehensive review of representative studies sourced from the China National Knowledge Infrastructure (CNKI) database over the recent five years, this paper systematically reviews the evolution of automobile engine fault diagnosis technologies-from traditional manual approaches to AI-based intelligent systems. Firstly, the article reviews the traditional diagnostic methods that rely on manual experience and basic instruments, and analyzes their limitations. Secondly, it focuses on the modern detection technology based on vibration, sound, temperature and other signals, as well as the application of on-board diagnostic system ( OBD ). Then, the core algorithms and models of artificial intelligence technology represented by machine learning and deep learning in engine intelligent diagnosis are deeply analyzed, such as BP neural network, 1D-CNN, ELM, etc., and their performance advantages are compared through cases. Finally, the future trend of remote intelligent diagnosis and predictive maintenance integrating Internet of Things, big data and cloud computing is prospected. The research shows that the paradigm shift from " experience-driven " to " data-intelligent-driven " is the key path to improve the level of engine fault diagnosis. Multi-technology integration and real-time remote monitoring will become the main direction of future development.