Realising Quality Control of Metal Products Used in Industry Through Deep Learning

This study was carried out with the aim of detecting the defects on the surfaces of metallic products, which are frequently encountered in our daily lives and widely used in industry, with deep learning. Many metal products in the industry undergo different processes during the production phase. As a result of these processes, the detection of defects such as breakage, cracking, etc. on the surfaces of metal products is carried out by quality control personnel or production personnel. However, this error detection made by manpower both slows down production and causes overlooked errors. In order to easily detect these defects, in our study, we used a dataset consisting of 285 images in total with images of two different surface defects and images containing flawless metal parts and a CNN architecture, ResNet50 architecture, to defects. There are three classes in total in the dataset. Two of these classes consist of images of different types of defects on the surface of the metal piston part used in air conditioners, and one of them consists of images of perfect metal piston parts. Convolutional Neural Network (CNN) method was used to determine the features of the images. Precision, recall, F1-Score and accuracy metrics were used to measure the performance of the model. With the ResNet50 architecture, defects on the surfaces of metal piston parts are detected quickly and with high accuracy. As a result of the study, it was suggested that the proposed model can detect surface defects that occur in the usage areas of metal products in various sectors more quickly and accurately using deep learning. This shows that the quality control problems experienced in the industry can be reduced by using deep learning, saving time and manpower.