Revolutionizing System Operation and Maintenance in the Automobile Industry Through Machine Learning Applications

Abstract

The necessity to digitalize the processes in the automobile industry becomes stronger by the day challenging the system operation and maintenance, in such a competitive field. Issues like passive fault identification, routine tasks, and dependency on Standard Operating Procedures (SOPs) describe the current status of a system in operating and maintaining processes used in the automotive industry. To address these challenges, this paper introduces an innovative approach: a machine learning system on operation and maintenance knowledge base for providing optimal solutions based on the automotive industry. More specifically, Scrap crawler is used to gather historical system data and after that, the decision tree algorithm is used to determine the specific insights. The acquired findings are further represented to facilitate comprehension and application of the results to strengthen the operation and maintenance management processes.