Developing a Framework to Prevent Over-Maintenance in Automated Assembly Lines

Abstract

Automated assembly lines in modern manufacturing industries are often maintained using fixed time-based maintenance schedules without considering the actual operating condition of equipment. This practice can lead to unnecessary maintenance activities, increased spare parts usage, additional downtime, and higher operational cost. To address this issue, the present study proposes a condition-based maintenance (CBM) framework for reducing over-maintenance in automated assembly lines using sensor-based monitoring and AI-assisted predictive analysis. The proposed framework integrates LoRA fine-tuned predictive models, real-time sensor fusion, and an automated validation module aligned with ISO 55000 standards for maintenance decision support. The study utilizes 210 operational records collected from automated assembly systems for model training and validation. The developed system achieved 91% fault prediction accuracy while significantly reducing unnecessary maintenance recommendations through a three-stage validation process. Industrial validation conducted on four automated assembly lines showed improvement in maintenance efficiency, reduction in unplanned downtime, lower spare parts consumption, and improvement in Overall Equipment Effectiveness (OEE) when compared with conventional time-based maintenance practices. The framework also demonstrates potential applicability in other industrial sectors such as semiconductor manufacturing, pharmaceutical packaging, aerospace assembly, and food processing industries. The proposed approach provides a structured and practical framework for improving maintenance planning and reducing over-maintenance in data-constrained industrial environments.