AI-Powered Fault Diagnosis System for Industrial Equipment

This paper presents an IoT-based AI-powered fault diagnosis system for real-time monitoring of industrial equipment. The proposed system uses an ESP32 microcontroller interfaced with vibration, temperature, and current sensors to continuously acquire machine condition data. The collected data are transmitted to a Firebase Realtime Database and processed using a Flask-based backend. A cloud-hosted web dashboard provides real-time visualization and fault alerts. Threshold-based anomaly detection is employed to identify abnormal operating conditions at an early stage. The system is low-cost, scalable, and remotely accessible, making it suitable for small- and medium-scale industries. Experimental results demonstrate effective fault detection with minimal latency, supporting predictive maintenance and improving equipment reliability.