Enhancing Electrical Audits Through AI-Powered for Motor Nameplate Analysis

Abstract

This project presents a deep learning-powered system for automating the extraction and analysis of electrical motor nameplate parameters, addressing inefficiencies in traditional manual methods used in electrical audits.  Users upload a nameplate image through a React-based interface, initiating a process where the backend, powered by the Gemini API and OCR-enabled deep learning models, extracts critical parameters such as voltage, power, current rating, RPM, insulation type, and temperature ratings. This extracted data undergoes post-processing to generate actionable insights and audit reports, categorised into a Simple Suggestion Report for basic recommendations and an Overall Detail Report for comprehensive analysis, displayed in a user-friendly output panel. By automating this process, the system significantly reduces time, effort, and errors associated with manual extraction, enabling auditor companies to deliver more accurate and efficient reports, paving the way for advanced automation in electrical audits and optimizing motor performance, maintenance, and energy efficiency in industrial and residential settings.