Deep Learning Methods for Detecting ImageBased Defects in Manufacturing Processes

In this study, we investigate how deep learning techniques may be used to spot manufacturing flaws in digital images. Our research shows that considerable advancements in manufacturing quality control are possible by using a diversified dataset and a tailored Convolutional Neural Network (CNN) architecture. As a result of its high levels of accuracy, precision, and recall, the proposed model has the potential to automate fault identification, boost productivity, and guarantee product safety in a variety of sectors. Grad-CAM visualization, which is emphasized in the study, is interpreted in order to help in decision-making and process optimization. This study lays a solid groundwork for the advancement of manufacturing in the future by opening up avenues for customization, real-time integration, and moral reflection. The key to more dependable, efficient, and competitive production in the industrial industry lies at the junction of human knowledge and artificial intelligence.