Published Paper Details:

In electrical engineering, managing Bill of Materials (BOM), equipment manuals, standard drawings, and price lists is a critical yet time-consuming and error-prone process when handled manually. Traditional methods involve manual data extraction, validation, and organization, which often leads to inefficiencies, misclassifications, and procurement delays. To address these challenges, this research presents ElectroDrawManager, a machine learning (ML) and automation-driven solution for optimizing BOM management and document retrieval. ElectroDrawManager employs Optical Character Recognition (OCR) and Natural Language Processing (NLP) to extract data from PDF, DWG, and CSV files, ensuring structured storage in a centralized database. The system allows users to efficiently access equipment manuals, standard drawings, and price lists, reducing manual intervention and improving decision-making. Additionally, predictive analytics enhances the accuracy of BOM generation, ensuring better material forecasting and error detection. The proposed system integrates a user-friendly interface, enabling users to upload files, extract relevant information, and retrieve processed data seamlessly. Through automated classification and anomaly detection, ElectroDrawManager significantly improves workflow efficiency, data accuracy, and operational productivity in electrical engineering projects. This paper discusses the methodologies, technologies, and implementation strategies used to develop ElectroDrawManager, highlighting its potential in revolutionizing BOM and document management workflows.