|
|
基于脉冲卷积神经网络的带钢表面缺陷识别
|
Abstract:
针对目前热轧带钢表面缺陷识别存在训练样本量小、识别效率低等问题，提出了一种基于脉冲卷积神经网络的带钢表面缺陷识别分类方法。为提高模型泛化性，首先利用扩散模型(Diffusion Model)对不平衡小样本数据集进行数据增强扩充，然后搭建脉冲卷积神经网络，并通过引入代理梯度方法进行网络监督训练，同时加入注意力模块来提高特征提取效率。实验结果表明：本文提出的脉冲卷积神经网络模型在保证识别率的基础上具有较强的生物合理性，为深度脉冲卷积神经网络在实际工程的应用提供借鉴。
A pulse convolutional neural network-based classification method for identifying surface defects on hot-rolled strip steel is proposed to address the issues of small training sample size and low recog-nition efficiency. To enhance the model’s generalization ability, a diffusion model is first utilized to augment and expand the imbalanced small sample dataset. Then, a pulse convolutional neural network is constructed and supervised training is conducted using a proxy gradient method. Addi-tionally, an attention module is introduced to improve feature extraction efficiency. Experimental results demonstrate that the proposed pulse convolutional neural network model not only ensures high recognition accuracy but also possesses strong biological plausibility, which provides valuable insights for the practical application of deep pulse convolutional neural networks in engineering.
| [1] | 刘杰. 探究钢铁表面缺陷检测的研究与实现[J]. 中国设备工程, 2023(6): 172-174. |
| [2] | 高祥明. 努力巩固去产能成果提高钢铁行业运行质量和效益——在中国钢铁工业协会五届十次常务理事(扩大)会议上的讲话[J]. 冶金财会, 2019, 38(8): 11-16. |
| [3] | 胡慧君, 李元香, 刘茂福. 基于机器学习的带钢表面缺陷分类方法研究[J]. 计算机工程与设计, 2014, 35(2): 620-624. |
| [4] | 徐科, 杨朝霖, 周鹏. 热轧带钢表面缺陷在线检测的方法与工业应用[J]. 机械程学报, 2009, 45(4): 111-114. |
| [5] | 张翔宇, 王燕霜, 张仕海. 钢板表面缺陷在线视觉检测系统[J]. 机床与液压, 2019, 47(4): 120-123. |
| [6] | Arjun, V., Sasi, B., Rao, B.P.C., et al. (2015) Optimisation of Pulsed Eddy Current Probe for Detection of Sub-Surface Defects in Stainless Steel Plates. Sensors and Actuators A: Physical, 226, 69-75.
https://doi.org/10.1016/j.sna.2015.02.018 |
| [7] | Tsukada, K., Majima, Y., Nakamura, Y., et al. (2017) Detection of Inner Cracks in Thick Steel Plates Using Unsaturated AC Magnetic Flux Leakage Testing with a Magnetic Resistance Gradiometer. IEEE Transactions on Magnetics, 53, 1-5. https://doi.org/10.1109/TMAG.2017.2713880 |
| [8] | 李维刚, 徐康, 李金灵, 等. 热轧带钢表面缺陷识别算法研究与应用[J]. 钢铁, 2022, 57(10): 139-147. |
| [9] | 宗德祥, 蒋渝, 何永辉. 基于集成学习算法的带钢表面缺陷分类算法研究[J]. 宝钢技术, 2021(3): 16-21. |
| [10] | Feng, X., Gao, X. and Luo, L. (2021) A Res-Net50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel. Mathematics, 9, 2359-2373. https://doi.org/10.3390/math9192359 |
| [11] | Wan, X., Zhang, X. and Liu, L. (2021) An Improved VGG19 Transfer Learn-ing Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets. Applied Sciences-Basel, 11, 2606-2629.
https://doi.org/10.3390/app11062606 |
| [12] | Maass, W. (1997) Networks of Spiking Neurons: The Third Generation of Neural Network Models. Neural Networks, 10, 1659-1671. https://doi.org/10.1016/S0893-6080(97)00011-7 |
| [13] | Caporale, N. and Dan, Y. (2008) Spike Timing-Dependent Plasticity: A Hebbian Learning Rule. Annual Review of Neuroscience, 31, 25-46. https://doi.org/10.1146/annurev.neuro.31.060407.125639 |
| [14] | Xiang, S., Zhang, Y., Gong, J., et al. (2019) STDP-Based Unsupervised Spike Pattern Learning in a Photonic Spiking Neural Network with VCSELs and VCSOAs. IEEE Journal of Se-lected Topics in Quantum Electronics, 25, Article ID: 1700109. https://doi.org/10.1109/JSTQE.2019.2911565 |
| [15] | Shrestha, S.B. and Song, Q. (2015) Adaptive Learning Rate of SpikeProp Based on Weight Convergence Analysis. Neural Networks, 63, 185-198. https://doi.org/10.1016/j.neunet.2014.12.001 |
| [16] | Ponulak, F. and Kasiński, A. (2010) Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting. Neural Computation, 22, 467-510. https://doi.org/10.1162/neco.2009.11-08-901 |
| [17] | Neftci, E.O., Mostafa, H. and Zenke, F. (2019) Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks. IEEE Signal Processing Magazine, 36, 51-63.
https://doi.org/10.1109/MSP.2019.2931595 |
| [18] | Qiao, G.C., Ning, N., Zuo, Y., et al. (2021) Direct Training of Hard-ware-Friendly Weight Binarized Spiking Neural Network with Surrogate Gradient Learning towards Spatio-Temporal Event-Based Dynamic Data Recognition. Neurocomputing, 457, 203-213. https://doi.org/10.1016/j.neucom.2021.06.070 |
| [19] | Feng, X., Gao, X. and Luo, L. (2021) X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection. Symmetry-Basel, 13, 706-721. https://doi.org/10.3390/sym13040706 |
| [20] | Ho, J., Jain, A. and Abbeel, P. (2020) Denoising Diffusion Probabilistic Mod-els. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6-12 December 2020, 6840-6851. |
| [21] | Liu, Y., Shao, Z., Teng, Y., et al. (2021) NAM: Normaliza-tion-Based Attention Module. |
