A New Ensemble Approach based on Deep Convolutional Neural Networks for Steel Surface Defect classification

Wen, Chenglu; Gao, Yiping; Gao, Liang; Li, Xinyu

doi:10.1016/j.procir.2018.03.264

Cited by 44 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It has since become more common to use neural networks to process various datatypes, including time series data and images, which has led to a broader scope of applications such as prediction of roll force and other mechanical properties (9,10) , gearbox fault diagnosis (11) , and temperature control (12) . In the last decade, Convolutions Neural Networks (CNNs) and transfer learning have become increasingly popular in image classification: In the last decade, many applications of this technology in the steel industry have focused on the classification of steel surface defect images (13)(14)(15)(16) .…”

Section: Use Of Neural Network Technologies In the Steel Industrymentioning

confidence: 99%

Pre-Trained CNN for Classification of Time Series Images of Anti-Necking Control in a Hot Strip Mill

Latham

Giannetti

2021

The Proceedings of the 9th IIAE International Conference on Industrial Application Engineering 2020

View full text Add to dashboard Cite

The steel industry is highly competitive, and companies must make the most of their current resources to maximise efficiency and, therefore, profitability. In the age of Industry 4.0, data is one of the most valuable resources available and, with appropriate processing and analysis, can improve the quality and adaptability of various applications. One such application is the monitoring and classification of Anti-Necking Control in a Hot Strip Mill. This paper proposes a deep learning approach to this application through the use of a pre-trained Convolutional Neural Network. The proposed system binarily classifies the timing of Anti-Necking Control strokes and has been optimised using grid search optimisation in conjunction with k-fold cross validation to determine an optimal time series image classification model.

show abstract

Section: Use Of Neural Network Technologies In the Steel Industrymentioning

confidence: 99%

Pre-Trained CNN for Classification of Time Series Images of Anti-Necking Control in a Hot Strip Mill

Latham

Giannetti

2021

The Proceedings of the 9th IIAE International Conference on Industrial Application Engineering 2020

View full text Add to dashboard Cite

show abstract

“…This transfer learning method helps them reach a higher accuracy at 99.27%. Larger-size models can fit the dataset better, mentioned in Reference [56], Wide Residual Networks (WRN) [57] are used, and the WRN-28-20 gets the best-reported result at 99.89%. However, as shown in the Table 4, WRN has so many weights to train that results in a massive computation cost during training, as long as 2 days as their report, even if the input images were resized to 32 × 32.…”

Section: Classification On Neumentioning

confidence: 99%

A Compact Convolutional Neural Network for Surface Defect Inspection

Huang

Qiu

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

The advent of convolutional neural networks (CNNs) has accelerated the progress of computer vision from many aspects. However, the majority of the existing CNNs heavily rely on expensive GPUs (graphics processing units). to support large computations. Therefore, CNNs have not been widely used to inspect surface defects in the manufacturing field yet. In this paper, we develop a compact CNN-based model that not only achieves high performance on tiny defect inspection but can be run on low-frequency CPUs (central processing units). Our model consists of a light-weight (LW) bottleneck and a decoder. By a pyramid of lightweight kernels, the LW bottleneck provides rich features with less computational cost. The decoder is also built in a lightweight way, which consists of an atrous spatial pyramid pooling (ASPP) and depthwise separable convolution layers. These lightweight designs reduce the redundant weights and computation greatly. We train our models on groups of surface datasets. The model can successfully classify/segment surface defects with an Intel i3-4010U CPU within 30 ms. Our model obtains similar accuracy with MobileNetV2 while only has less than its 1/3 FLOPs (floating-point operations per second) and 1/8 weights. Our experiments indicate CNNs can be compact and hardware-friendly for future applications in the automated surface inspection (ASI). pixels into regions, with the intention to emphasize the regions corresponding to surface defects. For example, Reference [6] firstly preprocesses images using convex optimization, then segments wood defects with Otsu segmentation method. Reference [12] segments fabric defects by the Sobel and the watershed algorithm.These traditional methods involve image preprocessing, feature extraction, feature reduction, and classifier selection, which needs the experience of experts. Besides, most surface defects are tiny and very similar to their background, even the inspection for a single type of defect can be very difficult for these traditional methods. Although traditional algorithms are designed for specific surfaces, effective measures such as recall, precision, and accuracy can barely achieve the standard of industrial applications. This long-existing bottleneck has been restraining the growth of ASI.Convolutional neural networks (CNNs) greatly stimulate the development of ASI [3,13-15] as deep learning methods in computer vision are achieving the state-of-the-art in recent years. As end-to-end solutions, CNNs also simplify the procedures of ASI. For example, a fully convolutional network (FCN) can segment surface defects by supervised learning [16], without any extra pre-process or post-process.A notorious limitation of CNNs is computation. In many cases, expensive GPUs with high computing capabilities are necessary to support large workloads. However, in considering manufacturing cost, most core computing resources of ASI platforms are mainly the low-power CPUs of industrial personal computers (IPC), or even FPGAs (field programmable gate array). To take advantage...

show abstract

“…An image-based system, on the other hand, is developed to enable more elaborate, rapid and automatic inspection than the existing methods [6]. Furthermore, it is widely known that the surface defect accounts for more than 90% of entire defects in steel products, e.g., plate and strip [7]. Defects on the steel surface, e.g., scratches, patches, and inclusions exert maleficent influence on material properties, i.e., fatigue strength and corrosion resistance, as well as the appearance [8].…”

Section: Introductionmentioning

confidence: 99%

“…Some features are obtained from a set of extractors techniques for being used as the inputs of an SVM ensemble, where a combiner, called Bayes kernel is employed to fuse the results from SVM classifiers. Chen, et al [7] suggest an integrated framework with CNN and naïve Bayes data fusion scheme for detecting cracks in nuclear power plants. This work utilizes a data fusion strategy so that spatiotemporal features of the cracks in videos are efficiently used, showing improved achievement of 98.3% hit rate toward the traditional inspection system of a nuclear power plant.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

A New Ensemble Approach based on Deep Convolutional Neural Networks for Steel Surface Defect classification

Cited by 44 publications

References 11 publications

Pre-Trained CNN for Classification of Time Series Images of Anti-Necking Control in a Hot Strip Mill

Pre-Trained CNN for Classification of Time Series Images of Anti-Necking Control in a Hot Strip Mill

A Compact Convolutional Neural Network for Surface Defect Inspection

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

Contact Info

Product

Resources

About