Intelligent IoT–Fuzzy Logic Framework for Preventive Maintenance and Electronic Equipment Health Management in Educational Computer Laboratories

This paper presents the development of an intelligent preventive maintenance framework that integrates Internet of Things (IoT) sensing and fuzzy logic for managing electronic equipment and forecasting the equipment health risks in educational computer laboratories. The framework aims to optimize device performance and mitigate the likelihood of system failures. The designed electronic equipment management system consists of the following modules: (a) an IoT-enabled power monitoring and electronic switching module (IPMESM) that protects lab equipment from damage due to overvoltage or undervoltage conditions; (b) an IoT-based environment monitoring module for computer system (IEMMCS) that collects data from sensors to determine the operating conditions of equipment in computer laboratories; (c) an alert notification module using GSM that sends SMS to the laboratory technician when critical operating parameters were detected; (d) cloud-based platforms that store data from the various modules, allowing real-time data access; and (e) fuzzy logic-based equipment health assessment model as a preventive maintenance mechanism that analyzes data from the monitoring modules to determine whether or not the computers are at risk. Preliminary results from the IPMESM showed voltage readings comparable with an industry-grade test device, as indicated by a paired t-test with 76 samples, a two-tailed ρ-value of 0.185, and a mean difference of 0.079. Moreover, the IEMMCS provided temperature, relative humidity, and PM2.5 dust particle metrics that were nearly identical to those obtained from a commercial air quality detector, with a percentage difference of less than 5%. In comparison to the manufacturer's specifications, published recommendations, and expert computer technician’s laboratory practices, the fuzzy logic-based preventive maintenance model was able to identify the risk posed to equipment health with 96% accuracy.