Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks

2021 ◽  
pp. 1-8
Author(s):  
Ihor Konovalenko ◽  
Pavlo Maruschak ◽  
Vitaly Brevus
Keyword(s):  
Neural Networks ◽  
Steel Surface ◽  
Production Efficiency ◽  
Surface Defects ◽  
Model Parameters ◽  
Feature Maps ◽  
Defect Diagnostics ◽  
Neuron Activation ◽  
Surface Defect Detection

Abstract Steel defect diagnostics is important for industry task as it is tied to the product quality and production efficiency. The aim of this paper is evaluating the application of residual neural networks for recognition of industrial steel defects of three classes. Developed and investigated models based on deep residual neural networks for the recognition and classification of surface defects of rolled steel. Investigated the influence of various loss functions, optimizers and hyperparameters on the obtained result and selected optimal model parameters. Based on an ensemble of two deep residual neural networks ResNet50 and ResNet152, a classifier was constructed to detect defects of three classes on flat metal surfaces. The proposed technique allows classifying images with high accuracy. The average binary accuracy of classifying the test data is 96.7% for all images (including defect-free ones). The fields of neuron activation in the convolutional layers of the model were investigated. Feature maps formed in the process were found to reflect the position, size and shape of the objects of interest very well. The proposed ensemble model has proven to be robust and able to accurately recognize steel surface defects. Erroneous recognition cases of the classifier application are investigated. It was shown that errors most often occur in ambiguous situations, where surface artifacts of different types are similar.

scholarly journals Recognition of Scratches and Abrasions on Metal Surfaces Using a Classifier Based on a Convolutional Neural Network

Metals ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 549
Author(s):  
Ihor Konovalenko ◽  
Pavlo Maruschak ◽  
Vitaly Brevus ◽  
Olegas Prentkovskis
Keyword(s):  
Neural Network ◽  
Steel Industry ◽  
Network Architecture ◽  
Metal Surfaces ◽  
Surface Defects ◽  
High Accuracy ◽  
Feature Maps ◽  
Neural Network Architecture ◽  
Neuron Activation

Classification of steel surface defects in steel industry is essential for their detection and also fundamental for the analysis of causes that lead to damages. Timely detection of defects allows to reduce the frequency of their appearance in the final product. This paper considers the classifiers for the recognition of scratches, scrapes and abrasions on metal surfaces. Classifiers are based on the ResNet50 and ResNet152 deep residual neural network architecture. The proposed technique supports the recognition of defects in images and does this with high accuracy. The binary accuracy of the classification based on the test data is 97.14%. The influence of a number of training conditions on the accuracy metrics of the model have been studied. The augmentation conditions have been figured out to make the greatest contribution to improving the accuracy during training. The peculiarities of damages that cause difficulties in their recognition have been studied. The fields of neuron activation have been investigated in the convolutional layers of the model. Feature maps which developed in this case have been found to correspond to the location of the objects of interest. Erroneous cases of the classifier application have been considered. The peculiarities of damages that cause difficulties in their recognition have been studied.

scholarly journals Automatic Detection and Classification of Steel Surface Defect Using Deep Convolutional Neural Networks

Metals ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 388 ◽  
Author(s):  
Shuai Wang ◽  
Xiaojun Xia ◽  
Lanqing Ye ◽  
Binbin Yang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Steel Surface ◽  
Surface Defects ◽  
Automatic Detection ◽  
Deep Convolutional Neural Networks ◽  
Data Set ◽  
Running Time ◽  
Average Running Time

Automatic detection of steel surface defects is very important for product quality control in the steel industry. However, the traditional method cannot be well applied in the production line, because of its low accuracy and slow running speed. The current, popular algorithm (based on deep learning) also has the problem of low accuracy, and there is still a lot of room for improvement. This paper proposes a method combining improved ResNet50 and enhanced faster region convolutional neural networks (faster R-CNN) to reduce the average running time and improve the accuracy. Firstly, the image input into the improved ResNet50 model, which add the deformable revolution network (DCN) and improved cutout to classify the sample with defects and without defects. If the probability of having a defect is less than 0.3, the algorithm directly outputs the sample without defects. Otherwise, the samples are further input into the improved faster R-CNN, which adds spatial pyramid pooling (SPP), enhanced feature pyramid networks (FPN), and matrix NMS. The final output is the location and classification of the defect in the sample or without defect in the sample. By analyzing the data set obtained in the real factory environment, the accuracy of this method can reach 98.2%. At the same time, the average running time is faster than other models.

scholarly journals Steel Surface Defect Diagnostics Using Deep Convolutional Neural Network and Class Activation Map

2019 ◽  
Vol 9 (24) ◽  
pp. 5449 ◽  
Author(s):  
Soo Young Lee ◽  
Bayu Adhi Tama ◽  
Seok Jun Moon ◽  
Seungchul Lee
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Product Quality ◽  
Real Time ◽  
Steel Surface ◽  
Production Efficiency ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Diagnostic Model ◽  
Defect Diagnostics

Steel defect diagnostics is considerably important for a steel-manufacturing industry as it is strongly related to the product quality and production efficiency. Product quality control suffers from a real-time diagnostic capability since it is less-automatic and is not reliable in detecting steel surface defects. In this study, we propose a relatively new approach for diagnosing steel defects using a deep structured neural network, e.g., convolutional neural network (CNN) with class activation maps. Rather than using a simple deep learning algorithm for the classification task, we extend the CNN diagnostic model for being used to analyze the localized defect regions within the images to support a real-time visual decision-making process. Based on the experimental results, the proposed approach achieves a near-perfect detection performance at 99.44% and 0.99 concerning the accuracy and F-1 score metric, respectively. The results are better than other shallow machine learning algorithms, i.e., support vector machine and logistic regression under the same validation technique.

scholarly journals Detection of Various Types of Metal Surface Defects Based on Image Processing

2021 ◽  
Vol 38 (4) ◽  
pp. 1071-1078
Author(s):  
Peng Xue ◽  
Changhong Jiang ◽  
Huanli Pang
Keyword(s):  
Image Processing ◽  
Metal Surface ◽  
Production Efficiency ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Production Equipment ◽  
Single Shot ◽  
Target Image ◽  
Nonlocal Means ◽  
Surface Defect Detection

Machine vision is a promising technique to promote intelligent production. It strikes a balance between product quality and production efficiency. However, the existing metal surface defect detection algorithms are too general, and deviate from electrical production equipment in the level of response time to the target image. To address the two problems, this paper designs a detection algorithm for various types of metal surface defects based on image processing. Firstly, each metal surface image was preprocessed through average graying and nonlocal means filtering. Next, the principle of the composite model scale expansion was explained, and an improved EfficientNet was constructed to classify metal surface defects, which couples spatial attention mechanism. Finally, the backbone network of the single shot multi-box detector (SSD) network was improved, and used to fuse the features of the target image. The proposed model was proved effective through experiments.

scholarly journals Classification of surface defects on steel sheet using convolutional neural networks

2017 ◽  
Vol 51 (1) ◽  
pp. 123-131 ◽  
Author(s):  
Shiyang Zhou ◽  
Youping Chen ◽  
Dailin Zhang ◽  
Jingming Xie ◽  
Yunfei Zhou
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Steel Sheet ◽  
Surface Defects
Sign in / Sign up

Export Citation Format

Share Document