Abstract
With the advancement of industrial intelligence, defect recognition has become an indispensable part of facilitating surface quality in the steel manufacturing process. To assure product quality, most previous studies were typically trained with many defect samples. Nonetheless, a large quantity of defect samples is difficult to obtain, owing to the rare occurrence of defects. In general, deep learning-based methods underperformed as they have inherent limitations due to inadequate information, thereby restraining the application of models. In this study, a two-level Gaussian pyramid is applied to decompose raw data into different resolution levels simultaneously filtering the noises to acquire compact and representative features. Subsequently, a multi-receptive field fusion-based network (MRFFN) is developed to learn the hierarchical features and synthesize the respective prediction scores to form the final recognition result. As a result, the proposed method is capable of exhibiting an outstanding performance of 99.75% when trained using a lightweight dataset. In addition, the experiments conducted using the disturbance defect dataset showed the robustness of the proposed MRFFN against common noises and motion blur.
Highlights
Towards smart factory for Industry 4.0, steel strip has become a ubiquitous material in most manufacturing workshops
50 images of each defect were randomly selected as the training data, and the remaining images served as the testing data
This discussion will be separated into two parts: (a) the improvement of the proposed method, which is trained by the interference defect dataset, and (b) a comparison of the results between the conventional pre-trained deep learning (DL) models and the multi-receptive field fusion-based network (MRFFN)
Summary
Towards smart factory for Industry 4.0, steel strip has become a ubiquitous material in most manufacturing workshops. In reality, owing to external factors such as equipment fatigue, human negligence, and external force, the steel surface may contain various types of defects. These surface defects potentially affect the capability of steel products such as wear resistance, fatigue strength, and residual life [1,2], leading to huge economic losses for manufacturers and posing a high risk to worker safety. Defect inspection is performed manually by experienced laborers. This inspection task is time-consuming, inefficient, highly subjective, and unreliable under the heavy workload in the high-speed production line. Inspectors can only cover approximately 0.05% of total steel production [3], and the metal surface defects recognition rate is about 80%, despite most of them being trained professionally [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
