IoT-Enabled Cyber-Physical System for Real-Time Predictive Maintenance and Automated Quality Inspection in Government Manufacturing and Transit Infrastructure

Abstract

The paper presents the design and implementation of an Internet of Things (IoT)-enabled predictive maintenance (PdM) system in smart manufacturing plants. The main aim of the study is to estimate the maintenance of the equipment by using the data received from the sensors using IoT and Machine learning and edge computing to minimize downtime. Through the integration of IoT sensors on the key equipment, edge computing for local processing, and cloud computing for analytics and machine learning model training. The main findings show that the system can significantly lower maintenance costs, enhance equipment dependability, and increase operational efficiency in manufacturing plants. Use of predictive maintenance system reduces unplanned downtime by 50% in the case of automotive industry. It boosts overall production uptime by 11.25%. Similarly high returns were observed in textile industry also. This research contributes with a scalable IoT-based PdM framework. The framework is demonstrated to provide improved cost and operational efficiency. Furthermore, actionable recommendations for the adoption of a PdM system are also provided for various industrial contexts.