AI Driven Quality Assurance in Electronics: Utilizing Convolutional Neural Networks for Efficient Visual Inspection Frameworks

Abstract

In the rapidly evolving electronics manufacturing industry, ensuring product quality while promoting environmental sustainability has become paramount. This study explores the integration of Convolutional Neural Networks (CNNs) in visual inspection frameworks to enhance the quality assurance process for electronic components. By leveraging advanced image processing techniques, the proposed AI-driven system effectively identifies and categorizes defects in Printed Circuit Boards (PCBs), significantly improving detection accuracy and operational efficiency. The CNN model achieved an impressive accuracy rate of 95.4%, demonstrating its capability to reduce false positives and negatives, thus enhancing overall product reliability. Moreover, the implementation of energy-efficient practices, including Dynamic Voltage Scaling (DVS), led to a 20% reduction in energy consumption compared to traditional inspection methods. This dual focus on quality and sustainability positions AI as a critical driver in modern manufacturing, enabling companies to align with eco-friendly practices while maintaining high-quality standards. The findings of this research provide valuable insights for manufacturers seeking to integrate AI technologies into their quality assurance processes, ultimately contributing to a more sustainable future in electronics manufacturing.