AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (7.4 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Adaptive Model Compression for Steel Plate Surface Defect Detection: An Expert Knowledge and Working Condition-Based Approach

School of Computer Science and Engineering, Southeast University, Nanjing 211189, China, and also with Najing Iron and Steel Co., Nanjing 210035, China
School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
Show Author Information

Abstract

The steel plate is one of the main products in steel industries, and its surface quality directly affects the final product performance. How to detect surface defects of steel plates in real time during the production process is a challenging problem. The single or fixed model compression method cannot be directly applied to the detection of steel surface defects, because it is difficult to consider the diversity of production tasks, the uncertainty caused by environmental factors, such as communication networks, and the influence of process and working conditions in steel plate production. In this paper, we propose an adaptive model compression method for steel surface defect online detection based on expert knowledge and working conditions. First, we establish an expert system to give lightweight model parameters based on the correlation between defect types and manufacturing processes. Then, lightweight model parameters are adaptively adjusted according to working conditions, which improves detection accuracy while ensuring real-time performance. The experimental results show that compared with the detection method of constant lightweight parameter model, the proposed method makes the total detection time cut down by 23.1%, and the deadline satisfaction ratio increased by 36.5%, while upgrading the accuracy by 4.2% and reducing the false detection rate by 4.3%.

References

[1]

G. Wang, Q. Xiao, M. Guo, and J. Yang, Optimal frequency of AC magnetic flux leakage testing for detecting defect size and orientation in thick steel plates, IEEE Trans. Magn., vol. 57, no. 9, p. 6200708, 2021.

[2]

C. Song, J. Chen, Z. Lu, F. Li, and Y. Liu, Steel surface defect detection via deformable convolution and background suppression, IEEE Trans. Instrum. Meas., vol. 72, p. 5017709, 2023.

[3]

R. Hao, B. Lu, Y. Cheng, X. Li, and B. Huang, A steel surface defect inspection approach towards smart industrial monitoring, J. Intell. Manuf., vol. 32, no. 7, pp. 1833–1843, 2021.

[4]
X. Xiang, Z. Wang, J. Zhang, Y. Xia, P. Chen, and B. Wang, AGCA: An adaptive graph channel attention module for steel surface defect detection, IEEE Trans. Instrum. Meas., vol. 72, p. 5008812, 2023.
[5]

D. He, K. Xu, and P. Zhou, Defect detection of hot rolled steels with a new object detection framework called classification priority network, Comput. Ind. Eng., vol. 128, pp. 290–297, 2019.

[6]

A. I. Kusuma and Y.-M. Huang, Product quality prediction in pulsed laser cutting of silicon steel sheet using vibration signals and deep neural network, J. Intell. Manuf., vol. 34, no. 4, pp. 1683–1699, 2023.

[7]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.
[8]

Y. Liang, J. Li, J. Zhu, R. Du, X. Wu, and B. Chen, A lightweight network for defect detection in nickel-plated punched steel strip images, IEEE Trans. Instrum. Meas., vol. 72, p. 3505515, 2023.

[9]

X. Zhao, Y. Chen, J. Guo, and D. Zhao, A spatial-temporal attention model for human trajectory prediction, IEEE/CAA J. Autom. Sin., vol. 7, no. 4, pp. 965–974, 2020.

[10]
B. Guo, Y. Wang, S. Zhen, R. Yu, and Z. Su, SPEED: Semantic prior and extremely efficient dilated convolution network for real-time metal surface defects detection, IEEE Trans. Ind. Inform., vol. 19, no. 12, pp. 11380–11390, 2023.
[11]

V. Sampath, I. Maurtua, J. J. Aguilar Martín, A. Rivera, J. Molina, and A. Gutierrez, Attention-guided multitask learning for surface defect identification, IEEE Trans. Ind. Inform., vol. 19, no. 9, pp. 9713–9721, 2023.

[12]

D. Bang, J. Lee, and H. Shim, Distilling from professors: Enhancing the knowledge distillation of teachers, Inf. Sci., vol. 576, pp. 743–755, 2021.

[13]

S.-K. Yeom, P. Seegerer, S. Lapuschkin, A. Binder, S. Wiedemann, K.-R. Müller, and W. Samek, Pruning by explaining: A novel criterion for deep neural network pruning, Pattern Recognit., vol. 115, p. 107899, 2021.

[14]

Y. Huang, Y. Hao, J. Xu, and B. Xu, Compressing speaker extraction model with ultra-low precision quantization and knowledge distillation, Neural Netw., vol. 154, pp. 13–21, 2022.

[15]

R. Hao, B. Lu, Y. Cheng, X. Li, and B. Huang, A steel surface defect inspection approach towards smart industrial monitoring, J. Intell. Manuf., vol. 32, no. 7, pp. 1833–1843, 2021.

[16]

S. Zhang, Q. Zhang, J. Gu, L. Su, K. Li, and M. Pecht, Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network, Mech. Syst. Signal Process., vol. 153, p. 107541, 2021.

[17]

Z. Liu, B. Yang, G. Duan, and J. Tan, Visual defect inspection of metal part surface via deformable convolution and concatenate feature pyramid neural networks, IEEE Trans. Instrum. Meas., vol. 69, no. 12, pp. 9681–9694, 2020.

[18]

Y. He, K. Song, Q. Meng, and Y. Yan, An end-to-end steel surface defect detection approach via fusing multiple hierarchical features, IEEE Trans. Instrum. Meas., vol. 69, no. 4, pp. 1493–1504, 2020.

[19]
W. Wang, M. Chen, S. Zhao, L. Chen, J. Hu, H. Liu, D. Cai, X. He, and W. Liu, Accelerate CNNs from three dimensions: A comprehensive pruning framework, in Proc. 38th International Conference on Machine Learning, Virtual Event, 2021, pp. 10717–10726.
[20]
J. Kennedy and R. Eberhart, Particle swarm optimization, in Proc. ICNN'95 - Int. Conf. Neural Networks, Perth, Australia, 1995, pp. 1942–1948.
[21]
Q. Li, C. Li, and H. Chen, Filter pruning via probabilistic model-based optimization for accelerating deep convolutional neural networks, in Proc. 14th ACM Int. Conf. Web Search and Data Mining, Virtual Event, 2021. pp. 653–661.
[22]
W. Wen, C. Wu, Y. Wang, Y. Chen, and H. Li, Learning structured sparsity in deep neural networks, in Proc. 30 th Conference on Neural Information Processing Systems, Barcelona, Spain, 2016, pp. 2082–2090.
[23]

Y. Liu, W. Zhang, and J. Wang, Adaptive multi-teacher multi-level knowledge distillation, Neurocomputing, vol. 415, pp. 106–113, 2020.

[24]

M. Gao, Y. Wang, and L. Wan, Residual error based knowledge distillation, Neurocomputing, vol. 433, pp. 154–161, 2021.

[25]

J. Gou, L. Sun, B. Yu, S. Wan, W. Ou, and Z. Yi, Multilevel attention-based sample correlations for knowledge distillation, IEEE Trans. Ind. Inform., vol. 19, no. 5, pp. 7099–7109, 2023.

[26]

Z. Wang, F. Li, G. Shi, X. Xie, and F. Wang, Network pruning using sparse learning and genetic algorithm, Neurocomputing, vol. 404, pp. 247–256, 2020.

[27]

C. Yang and H. Liu, Channel pruning based on convolutional neural network sensitivity, Neurocomputing, vol. 507, pp. 97–106, 2022.

[28]

Q. Guo, X.-J. Wu, J. Kittler, and Z. Feng, Weak sub-network pruning for strong and efficient neural networks, Neural Netw., vol. 144, pp. 614–626, 2021.

[29]
Y. Liu, W. Zhang, and J. Wang, Zero-shot adversarial quantization, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021, pp. 1512–1521.
[30]
Z. Li, J. Xiao, L. Yang and Q. Gu, Repq-vit: Scale reparameterization for post-training quantization of vision transformers. in Proc. IEEE/CVF Int. Conf. on Computer Vision (ICCV), Vancouver, Canada, 2023, pp. 17227–17236.
[31]
Z. Liu, K. Cheng, D. Huang, E. P. Xing, and Z. Shen, Nonuniform-to-uniform quantization: Towards accurate quantization via generalized straight-through estimation, in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 4942–4952.
Tsinghua Science and Technology
Pages 1851-1871
Cite this article:
Sun M, Dong F, Huang Z, et al. Adaptive Model Compression for Steel Plate Surface Defect Detection: An Expert Knowledge and Working Condition-Based Approach. Tsinghua Science and Technology, 2024, 29(6): 1851-1871. https://doi.org/10.26599/TST.2024.9010039

74

Views

6

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics

Received: 30 November 2023
Revised: 02 February 2024
Accepted: 22 February 2024
Published: 20 June 2024
© The Author(s) 2024.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return