Wire quality inspection is a critical process in manufacturing units to ensure the reliability and safety of wires before deployment. Additionally, assessing pre-installed wires in lead circuits and inspecting aging wires for damage is essential to prevent potential hazards and maintain operational efficiency. This study introduces Intelligent Wire Inspection System (IWIS), an advanced framework leveraging deep learning-powered live video processing for automated wire damage inspection. The proposed system replaces traditional manual inspection methods with an intelligent solution, employing PyTorch-SSD architecture with MobilenetV2 as the backbone, trained and optimized on a balanced dataset. IWIS utilizes an Nvidia RTX 3060 GPU to process live video feeds in real time, effectively detecting and classifying defects such as insulation wear, broken strands, and surface irregularities with high precision and recall. Designed for deployment in manufacturing units and maintenance environments, IWIS enhances quality control processes by reducing human intervention in hazardous conditions and ensuring consistent, reliable inspection of both newly manufactured and pre-installed wires. This approach demonstrates the transformative potential of deep learning in automating wire inspection processes, delivering accuracy, efficiency, and operational excellence.