Surface Defect Classification of Steel Strip with Few Samples Based on Dual‐Stream Neural Network

Zhang, Jiaqiao; Li, Shihao; Yan, Yan; Zhang, Ni; Ni, Hongjun

doi:10.1002/srin.202100554

Cited by 16 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Deep Dual-Stream Neural Network, inspired by the biological visual system, constructs a structure consisting of two independent neural network branches, with each branch responsible for a different input data stream. The key feature of the Deep Dual-Stream Neural Network is its parallel structure, where each branch independently conducts feature extraction operations [31,32]. These branches can have different types of loss functions, weight coefficients, or even network structures.…”

Section: Deep Dual-stream Neural Networkmentioning

confidence: 99%

Infrared image fault diagnosis based on dual-stream attention convolution network

Lu,

Yang,

Ming

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

The development of infrared image detection technology has improved the real-time performance and safety of fault diagnosis. To address the problem of insufficient features caused by the low resolution of infrared images, a fault diagnosis model for induction motor infrared images based on Dual-Stream Attention Convolutional (DSAC) is proposed. Firstly, this model employs a dual-stream convolutional neural network to extract spatial features in the X and Y directions of the infrared images separately. This dual-stream structure allows the network to simultaneously learn and utilize information from both X and Y directions, enabling a more comprehensive capture of temperature distribution and variation trends in the infrared images. Then, a convolutional attention mechanism is introduced to assign weights to the obtained features. The attention maps generated by the convolutional attention layer enhance key features while suppressing unimportant information, thereby enhancing the focusing performance of the DSAC model on critical features. Finally, the weighted dual-stream features are fused to achieve the goal of fault diagnosis for induction motor infrared images. The DSAC model is validated using the induction motor infrared image dataset fromBabol Noshirvani University of Technology, demonstrating excellent diagnostic accuracy and speed. Moreover, it alleviates the problem of sample imbalance to some extent in small-sample datasets, providing a feasible solution for fault diagnosis of induction motor infrared images.

show abstract

Section: Deep Dual-stream Neural Networkmentioning

confidence: 99%

Infrared image fault diagnosis based on dual-stream attention convolution network

Lu,

Yang,

Ming

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…Traditional machine vision‐based methods offer poor detection adaptiveness and slow detection speed. With the development of deep learning, convolutional neural networks are used to solve the problems of steel defect detection [51, 52]. Soukup et al.…”

Section: Related Workmentioning

confidence: 99%

FSSDD: Few‐shot steel defect detection based on multi‐scale semantic enhancement representation and mask category information mapping

Liu,

Guo,

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Steel defect detection is important for industry production as it is tied to the product quality and production efficiency. However, previous steel defect detection methods based on deep convolutional neural networks heavily rely on large‐scale data for training and tend to have poor generalization ability for a novel defect category. In this paper, a novel few‐shot steel defect detection model based on multi‐scale semantic enhancement representation and mask category information mapping is introduced, where only a few annotated samples are acquired for the novel defect category. More concretely, three main components are built: an information‐guidance enhanced multi‐head detector is proposed to improve the representation of information in meta‐feature maps, a mask category representation module is designed to enhance the category feature representation of the mask region in the support set, and a novel multi‐scale category edge loss function is designed to assist the generation of category reweighting vector. Extensive experiments on the North‐east University few‐shot steel defect data set demonstrate that the proposed method significantly outperforms the state‐of‐the‐art methods and verify its effectiveness through ablation studies.

show abstract

“…CNNs are a DL algorithm that is widely used in image [42] and video recognition, natural language processing, and other applications that require the processing of sequential data. They are intensively applied also in steel production for a quite wide range of tasks, such as, for instance, shape and surface defects detection and classification, [43][44][45] microstructure analysis and classification, [46,47] prediction of the end point of the converter, [48] and processing temperature data in continuous casting. [49] The key idea behind CNNs is to use a series of convolutional layers to extract features from an input image, followed by one or more fully connected layers to classify the image.…”

Section: Cnnsmentioning

confidence: 99%

A Deep Learning‐Based Approach to the Estimation of Jominy Profile of Medium‐Carbon Quench Hardenable Steels

Colla,

Vannucci,

Matino

et al. 2023

steel research int.

View full text Add to dashboard Cite

The possibility to estimate the Jominy profile of steel based on its chemical composition is of utmost importance and high practical relevance for industries, at enables a preliminary assessment of the suitability of a specific steel grade to a particular application or to the requirements of a customer, by saving time and resources as the Jominy end‐quench test is costly and time consuming. More importantly, an estimator can be used in steel grade design, by supporting the investigation of the most suitable chemistry to meet some given specifications. The paper proposes a novel approach to estimate the hardenability profile of medium Carbon quench hardenable steels, which exploits the potential of deep learning to correlate the steel metallurgy to the entire shape of the curve rather than to its single points, by thus being adaptable to a wide range of steel grades while providing very accurate estimates. Moreover, the proposed approach is suitable implement a transfer learning paradigm, as it can exploit the knowledge acquired by training on a specific dataset to adapt the model to different steel grades for which less data or data holding different features are available.This article is protected by copyright. All rights reserved.

show abstract

Surface Defect Classification of Steel Strip with Few Samples Based on Dual‐Stream Neural Network

Cited by 16 publications

References 38 publications

Infrared image fault diagnosis based on dual-stream attention convolution network

Infrared image fault diagnosis based on dual-stream attention convolution network

FSSDD: Few‐shot steel defect detection based on multi‐scale semantic enhancement representation and mask category information mapping

A Deep Learning‐Based Approach to the Estimation of Jominy Profile of Medium‐Carbon Quench Hardenable Steels

Contact Info

Product

Resources

About