Paper Title
Real-Time IoT-Based Fault Detection of Conveyor System for Throughput Optimization Using Response Surface Methodology

Abstract
Conveyor Belts are fundamental to any modern industrial or material-handling facility, but downtime has remained a major productivity drain due to such issues like motor overload, jamming, excessive wear and tear etc. which are difficult to predict. This paper proposes an IoT solution for statistical throughput optimization, defect identification autonomously and real-time condition monitoring of a laboratory level conveyor belt. A belt driven rig of size 150cm x 25cm was fitted with current, voltage, temperature, infrared proximity, load-cell and vibration sensors that were connected to an ESP32 microprocessor. A sensor was placed on the conveyor and sent data to a Google Sheet every 60 seconds, with a rule-based relay controller turning the power to the conveyor off if the following conditions were true: load > 4 kg, current > 4 A, voltage > 14 V, temperature > 40 °C, or jam detected. A three-level full-factorial Response Surface Methodology (RSM) design was subsequently employed to gain insight on the effect of using object weight (A) and inter object distance (B) on the performance of the system. The results of the Analysis of Variance (ANOVA) showed that there were significant linear terms (A and B), a two-factor interaction (AB), and the quadratic term A2 (P < 0.05). However, B2 did not appear to be significant (P = 0.3058). The regression model suggests a maximum throughput of 31.5 objects/min at the stationary point with the adjusted-R2>0.98. A combined measured weight/distance of 900 – 1200g and 30 – 35cm are known to work well for this equipment. Our results demonstrate that it is possible for low cost IoT sensing methods and Design of Experiments (DoE) to rapidly converge to safe, high-throughput operating regimes, without the necessity of costly industrial monitoring suites. Keywords - Conveyor belt, Design of Experiments,ESP32, Fault detection, Internet of Things, Response Surface Methodology, Throughput optimization.