Abstract

The ability of manufacturing organisations to generate defect-free, high-quality products is critical to their long-term success in the marketplace. Despite increased product diversity and complexity, as well as the necessity for cost-effective manufacturing, it is frequently important to conduct a thorough and reliable quality examination. There are bottlenecks in the manufacturing process because there are so many checks done. In this paper, we aim to automate the process of quality control in industries using a machine learning classifier that monitors the manufactured product namely the central processing unit via imaging technique. Development of a model with high quality control improves the productivity and efficacy of production that rejects the malignant and defect pieces from the supply chain. The use of imaging systems or high-speed camera enables the improvement of software quality, where the analysis is built using high clarity input images. The data processed by these imaging systems are transferred to the cyber-physical system for secured access within an organization. The results of classification of input images and process via machine learning improves the efficacy of the model over various machine learning models.