Artificial Intelligence (AI) in conjunction with the Internet of Things (IoT) provides new possibilities for predictive maintenance in automotive manufacturing. An AI based predictive maintenance systems collects real-time data using IoT-enabled sensors, applies algorithms that have an artificial intelligence/machine learning component to to predict equipment failures, new down time, and enables equipment sustainability through optimal operating efficiency. This review article provides an examination of the technical structures, methodologies, and applications of AI based predictive maintenance in automotive production systems with priority of focus on electric vehicle (EV) manufacturing and in-operations case examples of AI based predictive maintenance. The paper describes the processing of sensor data for machine learning modeling, integration of machine learning models into organizational decision-support systems, and layers of a predictive maintenance framework. The paper critically analyzes current limitations in predictive maintenance frameworks, ranging from data quality, update requirements, data design and analysis, explainability, enforceability and continued workforce modernization and development. The paper also identifies the future of predictive maintenance, including federated learning, digital twin technology, edge computing, and sustainable enhancement of operations. By evaluating the current state of research and industrial implementation of AI based predictive maintenance this paper shows how predictive maintenance represents a strategic component for efficiency, competitiveness, and sustainability, as a foundational component of next generation automotive manufacturing systems.
N. Rama Rao (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: