Abstract
In industrial manufacturing processes, detection of defects on the surfaces of metal plates supplied from iron and steel main industry manufacturers to be processed by machining and non-machining methods has an important place in estimating the values of the relevant plate such as safety and maintenance cost. With the developing technology and computer vision and deep learning applications finding a place in the industry, it has become possible to detect and classify metal plate surface defects more quickly and effectively with a lower error rate at an advanced technological level. Within the scope of this study, a deep learning model was created by using the TensorFlow library in the Python environment with using NEU Metal Surface Defects Dataset to detect metal plate surface defects. Then as an industrial application, a device prototype developed using Nvidia Jetson Nano and USB Camera, in order to test this model under real conditions.
Published Version
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