OPTIMIZATION OF PREDICTION AND PREVENTION OF DEFECTS ON METAL BASED ON AI USING VGG16 ARCHITECTURE

Abstract

Manufacturing is one of the most valuable industries in the world, it can be automated without limits but still stuck in traditional manual and slow processes. Industry 4.0 is racing to define a new era in digital manufacturing through the implementation of Machine Learning methods. In this era, Machine learning has been widely applied to various fields and will certainly be very good applied in the manufacturing world. One of them is used to predict and prevent defects in metal. The process of predicting and preventing defects in metal is one of the important efforts in improving and maintaining production quality. Accuracy in predicting and preventing defects in metal can be an innovation and competitiveness in technology, both in production methods, and improving product safety and its users. Human operators and inspectors without digital assistance generally can spend a lot of time researching visual data, especially in high-volume production environments. For this reason, there needs to be research in developing Machine Learning technology in an effort to prevent the occurrence of defects in metal. And one of the development of this technology by using Convolutional Neural Network (CNN) architecture Visual Geometry Group 16 layer (VGG16). As for the metal defect dataset with 10 classes with details for training data as many as 17221, and test dataset as many as 4311, From the use of methods and datasets available, has been done training model used and produce very good accuracy, that is equal to 89% and testing with accuracy equal to 76%. And also done Interpreter process against new input data, to know metal defect type, prediction accuracy and appropriate action to prevent and overcome metal defect type result of Interpreter process application.