An Extended Approach Using Rough Set Theory Enhanced Defect Detection and Decision-Making Leveraging Advanced Rough Set Techniques

Abstract

In the realm of printed circuit board (PCB) manufacturing, maintaining high-quality standards is critical due to the increasing complexity of electronic components and the stringent performance requirements of modern devices. Traditional quality control methods often fall short in addressing the multifaceted nature of PCB defects, leading to the need for more sophisticated approaches. This paper introduces an extended rough set theory (ERST) approach to enhance quality control in PCB manufacturing. Rough set theory, known for its capability to handle uncertainty and imprecision in data, is extended to address the specific challenges of PCB defect classification and analysis. The proposed methodology integrates rough set theory with advanced data mining techniques to improve the identification and management of defects.

In this study, a dataset comprising 10,000 PCB images with various types of defects was analyzed using the ERST approach. The methodology includes data preprocessing, feature extraction, and rule generation to classify defects with high precision. The results indicate that the ERST approach outperforms traditional methods, achieving an overall accuracy of 96.3%, with significant improvements in handling complex defect patterns and minimizing false positives and negatives. The integration of rough set theory allows for a more nuanced understanding of defect data, enabling better decision-making and quality control strategies.