Deep Learning Based Product Defect Detection for Sustainable Smart Manufacturing

A crucial component of quality control in manufacturing, automated product defect detection has a big impact on output effectiveness and product dependability. The YOLO model is one of the deep learning techniques that this study especially examines using to improve defect detection speed and accuracy. The main goal is to create a productive system that can identify and categorize product defects in real time, eliminating the need for manual inspections and decreasing human error. The YOLO model is used because it performs better in real-time applications and is renowned for its quick object identification abilities. The architecture of the model is optimized to forecast several bounding boxes and class probabilities simultaneously, which makes it a good choice for detecting many kinds of faults in a single pass. The training dataset comprises annotated images of products with and without defects, enabling the model to learn distinguishing features effectively. Results show that, in comparison to conventional techniques, the YOLO-based defect detection system achieves high accuracy rates and much faster processing times. The real-time detection capabilities and the model's ability to handle a variety of problem demonstrates how automated quality control methods have advanced. It increases overall product quality, lowers expenses related to defective items, and improves manufacturing efficiency. Businesses may increase the consistency and dependability of their products through the manufacturing process by incorporating deep learning techniques. This will increase consumer satisfaction and provide them a competitive edge in the market.