Virtual-sample-based defect detection algorithm for aluminum tube surface

Abstract

A surface defect is an important factor that affects product quality. However, due to the large differences in area of different surface defects, and noise on various surfaces, defect detection is challenging. The convolutional neural network (CNN)-based methods recently developed for defect detection produced higher recognition rates than traditional methods. However, they are typically trained using a supervised learning strategy and large defect sample sets which limits the practical use of these algorithms. This study proposes a novel virtual sample generation algorithm to solve the problem of insufficient defective samples and time-consuming manual annotation in current CNN-based defect detection algorithms. Next, an improved domain-adversarial neural network is proposed, which is trained on virtual and actual datasets to achieve unsupervised learning. Considering the imbalance in actual dataset, algorithm accuracy is improved by changing the proportions of defective and non-defective samples in the virtual sample set, and this strategy is experimentally verified. The performance of the proposed algorithm is compared with several top-performing defect inspection algorithms. The experimental results show that the proposed algorithm exhibits superior performance when compared to other algorithms.

Cross-domain few-shot defect recognition for metal surfaces

“…Song et al [5] proposed a novel domain adaptive network that only needs a few labeled target samples and achieves better transfer from the source domain in the real industrial scenario. Lang et al [6] designed a novel virtual sample generation algorithm to solve the problem of insufficient defective samples. These methods can address the data scarcity problem, but when the classes are different between the source and target domains, these methods cannot achieve good results.…”

“…In MA, the model parameters are updated by the combined loss. We use β to balance the original and augmented losses in equation (6). From the experiments, we choose β as 0.6.…”

“…as the defect recognition on metal surfaces [5][6][7] and fabric surfaces [8,9]. Many methods employ deep learning-based models, which learn strong predictors from large-scale data sets, and they achieve great performance.…”

Modeling and investigation of crack evaluation in metal tube based on magnetic field analysis method

“…As is known, metal tubes have been widely applied in power plants, petroleum, chemical, metallurgical, aeronautical and other industries, which have undertaken the task of transporting liquids and gases. On account of the extremely harsh working conditions of the tube, it is prone to get corroded, suffer from fatigue damage or even damages caused by inner defects [1][2][3]. Especially in the long-term use of oil and gas tube, due to the instability of surface foundation, medium corrosion and accidents, defects and damages are prone to occur.…”