Development of IoT-Enabled Real-Time Production Monitoring System for Manufacturing Efficiency

Thesis Abstract

The increasing complexity and competitiveness of modern manufacturing environments necessitate the deployment of advanced monitoring systems to enhance operational efficiency and reduce production downtime. Traditional production monitoring methods are often characterized by delayed data collection, limited real-time insights, and insufficient responsiveness to machine faults or process deviations, thereby constraining decision-making and operational agility. Addressing these challenges, this study aims to develop an IoT-enabled real-time production monitoring system to optimize manufacturing efficiency. The specific objectives include designing a scalable IoT architecture suitable for diverse manufacturing contexts, identifying key parameters influencing production performance, implementing sensor-based data acquisition and transmission mechanisms, and evaluating the system’s impact on operational metrics such as throughput, downtime, and defect rates. The research adopts a mixed-methods approach within a scientific pragmatic paradigm. The quantitative component involves deploying the developed monitoring system across a sample of 15 industrial manufacturing units within an automotive component plant, with a total of 200 machinery assets monitored over a six-month period. Stratified random sampling ensures representative inclusion of different machinery types and production lines. Data collection instruments comprise IoT sensors (for temperature, vibration, and operational status), a centralized data aggregation platform, and performance logs. Qualitative data are gathered through semi-structured interviews with manufacturing managers and operators to contextualize quantitative findings. Data analysis employs descriptive statistics to outline baseline operational parameters; regression analysis to identify relationships between monitored variables and key performance indicators; and ANOVA to assess differences pre- and post- system deployment. Thematic analysis interprets qualitative insights, complementing quantitative results. Expected findings suggest that the integration of IoT sensors into the production environment facilitates near-instantaneous detection of machine anomalies, enabling prompt maintenance interventions and reducing unplanned downtime by approximately 25%. Additionally, the system is anticipated to improve overall equipment effectiveness (OEE) by 15%, facilitate data-driven decision-making, and foster proactive maintenance scheduling. The analytical model is expected to demonstrate significant correlations between real-time monitored parameters and production efficiency metrics, validating the system’s capability to enhance operational productivity. The findings will also reveal critical factors affecting IoT system adoption, including technical infrastructure, personnel training, and data security considerations. This research contributes to the existing body of knowledge by providing an empirically validated framework for designing and implementing IoT-enabled production monitoring systems in manufacturing settings, emphasizing their role in achieving Industry 4.0 objectives. It advances understanding of how sensor-based data can be harnessed to address operational inefficiencies and promotes the integration of IoT technologies within industrial engineering practices. The integration of multiple theories, including the Technology Acceptance Model (TAM) and the Diffusion of Innovations Theory, underscores the importance of user acceptance and innovation adoption processes in the successful deployment of IoT infrastructure. The main conclusion asserts that IoT-enabled real-time monitoring systems significantly enhance manufacturing efficiency when appropriately tailored to the organizational context, supported by robust technical infrastructure and comprehensive staff training. Recommendations include strategic investment in sensor technology and network infrastructure, development of standardized protocols for data management, and continuous capacity building for production personnel. Future research directions involve exploring the integration of machine learning algorithms for predictive maintenance and expanding the system’s applicability to other manufacturing sectors. This study provides a practical blueprint for manufacturing firms seeking to leverage IoT solutions for operational excellence, contributing both to academic theory and industrial practice.