Abstract

The rapid convergence of ICT (Information and Communication Technology) with various fields in modern society has led to the emergence of smart factories in the manufacturing industry. These factories leverage artificial intelligence and automation technology to enhance productivity and efficiency by collecting real-time data and making optimal decisions through analysis. In this study, we aimed to develop machine learning and deep learning models to improve manufacturing processes in smart factories. Firstly, we implemented a model using logistic regression, random forest, gradient boosted trees, and support vector machine to classify defects based on process environment data, including temperature and pressure. Next, we applied convolutional neural network models such as AlexNet, VGG-16, and ResNet to classify defective welding images captured after the welding process. We evaluated the performance of these models using metrics like accuracy, precision, and recall for each dataset and selected the top-performing model as the final choice.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call