PROACTIVE QUALITY EVALUATION: A NOVEL STRATEGY-ASSISTED EARLY DETECTION IN MANUFACTURING

Abstract

The proactive exploration and avoidance of errors or variations from quality standards during the manufacturing process is referred to as “early quality detection” in the manufacturing industry. Post-production inspection, which can be expensive and time-consuming, is used in traditional quality control systems. To overcome this, we proposed a Modified gravitational search algorithm-based decision tree (MGSA-DT) to predict the quality of manufacturing processes at an early stage. We gathered sensors data in the manufacturing industry. In order to prepare the data for principal component analysis (PCA), Z-score normalization is used. Then, the essential features are extracted from the preprocessed data. To assess the effectiveness of the suggested approach in terms of accuracy (98.4%), precision (97.6%) and recall (97.2%), respectively. Implementing early quality detection techniques in manufacturing has demonstrated encouraging outcomes in enhancing the overall quality of products and decreasing production expenses.

Keywords

• manufacturing industry
• quality
• modified gravitational search algorithm-based decision tree (egsa-dt)
• z-score normalization
• principal component analysis (pca).