Predictive Maintenance in Automotive Manufacturing: Leveraging Big Data, Advanced Algorithms, and AI for Early Failure Detection Through Engine Heartbeat Analysis

Abstract

Abstract- It investigates advanced algorithm and artificial intelligence integration in predictive maintenance in automotive engines with regard to the power of big data. In this work, Gradient Boosting, Random Forest, and K-Nearest Neighbors have been used to predict from huge amounts of recorded data of engine heartbeats. These complex models run datasets from engine sensors to analyze slight variations in RPM, temperature, and vibration, predicting failures before their occurrence. Big data assumes a relatively central role since the real-time analysis it provides continuously can have a dynamic and responsive approach toward the engine health management system. It serves to demonstrate how research into the exploitation of the sheer volume of data coming out of modern vehicles allows not only engine reliability but also reduces operational downtime and improves safety. While the models show remarkable predictive accuracy, challenges related to data imbalance and model sensitivity to failure detection still need to be overcome entirely. This study, however, indicates the potential of big data to change the face of automotive maintenance by providing actionable insights and leading to the development of even more efficient and reliable engines.