Classification of Surface Defects in Steel Sheets Using Developed NasNet-Mobile CNN and Few Samples

Abstract

Rolled steel is a major product of ferrous metalworking. It is a popular metal structure construction technology. Though a big amount of the finished product may be flawed, the process of manufacturing must be improved. It is critical to correctly classify hot-rolled strip faults. As a result, in recent years, numerous machine-learning-based automated visual inspection (AVI) systems have been created. However, these approaches lack several critical components, such as insufficient RAM, which causes complexity and slowness during implementation. Long execution durations, in general, cause the process to be delayed or completed later than expected. A shortage of faulty samples is also a significant difficulty in steel defect detection, as the imbalance between the huge number of non-defective photos and the defective ones causes the algorithm to be unfair in categorization. To address these three issues, a deep CNN model is created in this study. The backbone architecture is a pre-trained NasNet-Mobile that has been fine-tuned with particular parameters to be compatible with the required data. Despite having 27 times less data than other articles' datasets, the model detects steel surface photos with six defects with 99.51% accuracy, exceeding earlier methodologies. This study is useful for surface fault classification when the sample size is small, the software is not quite as effective, or time is limited. Avoiding these issues will help the steel industry improve safety and end product quality while also saving time and money.