Design and Implementation of a Real-Time IoT Monitoring System for Smart Manufacturing Environments

Abstract

The success of smart manufacturing, as promised high and low by the industry 4.0 revolution, depends on the integration of physical manufacturing systems with digital monitoring and control technologies. This research proposes a smart factory solution for retrofitting conventional manufacturing equipment into a real-time Internet of Things (IoT) monitoring system. The main objective is to enable continuous monitoring of critical production parameters, particularly moisture levels in raw plastic materials, to improve product quality and operational efficiency. The proposed system integrates industrial machines with IoT sensors and a smart gateway for in situ data acquisition and remote management. The system can also be used in time response by case study in a plastic manufacturing facility. The system was deployed in a real plastic manufacturing facility (using dehumidifying dryers for raw materials) to evaluate performance under normal and abnormal conditions (e.g., abnormal moisture levels). The architecture consists of a cloud-connected monitoring server, a web dashboard for real-time data visualization, and a caching system to process high-frequency sensor data efficiently. Unlike existing approaches, the proposed system emphasizes low-cost and non-intrusive integration with legacy equipment without requiring full system replacement. We show that the use of this IoT-based monitoring approach improves operational insight and responsiveness. Experimental results indicate a reduction in defective product rates and faster response to process anomalies, with data latency maintained within 1–2 seconds as results indicate a marked improvement of defective product rates via timely interventions and data processing performance via an optimized cache. This work provides a practical framework to upgrade legacy production systems using IoT technology, enhancing production reliability, reducing downtime, and enabling data-driven decision-making, so as to implement innovations improving manufacturing efficiency and pave the way to further improvements of smart factories in the future.