Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time

• Published in: Expert systems with applications Vol. 173; p. 114598
• Main Authors: Ayvaz, Serkan, Alpay, Koray
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 01.07.2021; Elsevier BV
• Subjects: Algorithms; Artificial intelligence; Assembly lines; Big data; Evaluation; Internet of things; Machine learning; Manufacturing; Manufacturing systems; Predictive maintenance; Production lines; Real time; Internet of things; Big data; Artificial intelligence; Machine learning; Predictive maintenance; Manufacturing systems
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2021.114598

•The study proposes predictive maintenance system for manufacturing production lines.•The system aims to predict signals for potential failures before they occur.•It uses machine learning methods on big data generated from sensors in real-time.•Real-world evaluations showed the system is effective in detecting production stops. In this study, a data driven predictive maintenance system was developed for production lines in manufacturing. By utilizing the data generated from IoT sensors in real-time, the system aims to detect signals for potential failures before they occur by using machine learning methods. Consequently, it helps address the issues by notifying operators early such that preventive actions can be taken prior to a production stop. In current study, the effectiveness of the system was also assessed using real-world manufacturing system IoT data. The evaluation results indicated that the predictive maintenance system was successful in identifying the indicators of potential failures and it can help prevent some production stops from happening. The findings of comparative evaluations of machine learning algorithms indicated that models of Random Forest, a bagging ensemble algorithm, and XGBoost, a boosting method, appeared to outperform the individual algorithms in the assessment. The best performing machine learning models in this study have been integrated into the production system in the factory.