IOT INTEGRATION IN INTELLIGENT LUBRICATION SYSTEMS FOR PREDICTIVE MAINTENANCE AND PERFORMANCE OPTIMIZATION IN ADVANCED MANUFACTURING INDUSTRIES

Abstract

This study investigates how the integration of Internet of Things (IoT) technologies into intelligent lubrication systems enhances predictive maintenance capability and supports performance optimization within advanced manufacturing industries. The research addresses a critical empirical gap: although Maintenance 4.0 frameworks widely highlight the strategic role of smart lubrication and sensor-embedded subsystems, there remains insufficient quantitative evidence regarding how IoT-enabled lubrication solutions influence plant-level operational outcomes such as equipment availability, unplanned downtime, throughput stability, and overall equipment effectiveness (OEE). To respond to this gap, the study develops and empirically tests a conceptual model that links IoT integration, predictive maintenance effectiveness, and multidimensional performance outcomes in cloud-connected, data-driven manufacturing environments. A quantitative, cross-sectional, case-based survey design was adopted, utilizing a structured five-point Likert questionnaire administered to maintenance, reliability, production, and engineering professionals working in plants that have deployed IoT-driven lubrication and condition monitoring technologies. A total of 210 usable responses were collected, reflecting an effective response rate of 80.8 percent and representing diverse industrial contexts with varying levels of digital maturity. The model incorporated key variables including IoT integration in intelligent lubrication systems, predictive maintenance effectiveness, operational performance outcomes, and user acceptance—recognized in technology adoption theory as a critical enabler of system effectiveness. Data analysis involved multiple stages, beginning with descriptive statistics and reliability assessments to verify internal consistency across constructs, followed by Pearson correlation analysis to establish initial relationships among variables. A series of multiple regression models and mediation–moderation analyses, supplemented with bootstrapping procedures, were employed to rigorously test the hypothesized relationships. Results indicated that IoT integration exerted a strong and statistically significant positive effect on predictive maintenance effectiveness (β = 0.66, R² = 0.54), confirming that advanced, sensor-enabled lubrication systems materially enhance a plant’s capability to anticipate equipment failures and prevent lubrication-related anomalies. Further, IoT integration and predictive maintenance jointly accounted for 63 percent of the variance in multidimensional performance outcomes, highlighting the centrality of intelligent lubrication systems as a technological lever for improving OEE and reliability-centered performance metrics. Mediation results showed that predictive maintenance partially mediated the IoT–performance relationship (indirect effect = 0.34), indicating that IoT-generated condition data translate into performance gains primarily through improved diagnostic and prognostic capabilities. Additionally, user acceptance significantly moderated the IoT–predictive maintenance pathway, demonstrating that even sophisticated digital lubrication and monitoring architectures require high levels of user readiness, trust, and operational engagement to deliver their full value.