基于C3D-APReLU的工业过程视频故障诊断
Video Fault Diagnosis of Industrial Process Based on C3D-APReLU
摘要: 近些年来，人们对生产安全的要求越来越高。随着图像采集设备在工业过程监控中的普及，基于视频的深度学习故障诊断技术得到了快速的发展。然而使用传统激活函数的深度学习方法只能提供相同的非线性映射，这不利于模型对输入信号特征的学习和分类。针对这个问题，本文提出了一种用于视频分类模型的、可以自适应调整参数的激活函数APReLU-3D。该激活函数内嵌了一个可以对输入信号进行学习从而对坡度自动做出相应调整的子网络，使得每个输入信号都可以有自己的非线性映射。本文将APReLU-3D应用于视频分类模型C3D中，提出了C3D-APReLU模型。采用PRONTO工业数据集中的视频数据对该方法进行对比实验，结果表明，C3D-APReLU实现了比使用ReLU激活函数的C3D更好的故障诊断性能，其平均精度为0.978。
Abstract: In recent years, people have higher and higher requirements for production safety. With the pop-ularity of image acquisition equipment in industrial process monitoring, video-based deep learning fault diagnosis technology has been developed rapidly. However, the deep learning method using the traditional activation function can only provide the same nonlinear mapping, which is not conducive to the learning and classification of input signal features. To solve this problem, this paper proposes a new activation function APReLU-3D which can adjust parameters adaptively for video classification model. The activation function is embedded with a subnetwork that can learn from the input signal and automatically adjust the slope accordingly, so that each input signal can have its own nonlinear mapping. In this paper, APReLU-3D is applied to video classification model C3D, and a model of C3D-APReLU is proposed. The method was compared using video data from PRONTO industrial dataset. The results show that C3D-APReLU achieves better fault diagnosis performance than C3D using ReLU activation function, with an average accuracy of 0.978.
文章引用：宋启哲, 田颖, 李嘉乐. 基于C3D-APReLU的工业过程视频故障诊断[J]. 理论数学, 2023, 13(3): 381-394. https://doi.org/10.12677/PM.2023.133042

参考文献

[1] 欧敬逸, 田颖, 向鑫, 宋启哲. 基于迁移BN-CNN框架的小样本工业过程故障诊断[J]. 电子科技, 2022.
[2] Itti, L., Koch, C. and Niebur, E. (1998) A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 1254-1259. [Google Scholar] [CrossRef] 
[3] 贾澎涛, 杨丽娜. 基于多特征的视频场景分类[J]. 计算机应用研究, 2018, 35(11): 3472-3475.
[4] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[5] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017) Imagenet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. [Google Scholar] [CrossRef] 
[6] Karpathy, A., Toderici, G., Shetty, S., et al. (2014) Large-Scale Video Classification with Convolutional Neural Networks. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 1725-1732. [Google Scholar] [CrossRef] 
[7] Simonyan, K. and Zisserman, A. (2014) Two-Stream Convolutional Networks for Action Recognition in Videos. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. and Weinberger, K.Q., Eds., Advances in Neural Information Processing Systems 27 (NIPS 2014), Curran Associates, Inc., Red Hook.
[8] Ji, S., Xu, W., Yang, M. and Yu, K. (2012) 3D Convolutional Neural Networks for Human Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 221-231. [Google Scholar] [CrossRef] 
[9] He, M., Li, B. and Chen, H. (2017) Multi-Scale 3D Deep Convolu-tional Neural Network for Hyperspectral Image Classification. 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 17-20 September 2017, 3904-3908. [Google Scholar] [CrossRef] 
[10] Li, Y., Zhang, H. and Shen, Q. (2017) Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network. Remote Sensing, 9, Article No. 67. [Google Scholar] [CrossRef] 
[11] Tran, D., Bourdev, L., Fergus, R., Torresani, L. and Paluri, M. (2015) Learning Spatiotemporal Features with 3D Convolutional Networks. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 4489-4497. [Google Scholar] [CrossRef] 
[12] Qiao, Y., Guo, Y., Yu, K. and He, D. (2022) C3D-ConvLSTM Based Cow Behaviour Classification Using Video Data for Precision Livestock Farming. Computers and Electronics in Agriculture, 193, Article ID: 106650. [Google Scholar] [CrossRef] 
[13] 李燕, 何敏. 基于C3D和CBAM-ConvLSTM的犯罪事件视频场景分类[J]. 刑事技术, 2022, 47(5): 448-457.
[14] Xu, H., Das, A. and Saenko, K. (2017) R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 5794-5803. [Google Scholar] [CrossRef] 
[15] Zhao, M., Zhong, S., Fu, X., et al. (2020) Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis. IEEE Transactions on Industrial Electronics, 68, 2587-2597. [Google Scholar] [CrossRef] 
[16] Nair, V. and Hinton, G.E. (2010) Rectified Linear Units Improve Restricted Boltzmann Machines. Proceedings of the 27th International Conference on International Conference on Machine Learning, Haifa, 21-24 June 2010, 807-814.
[17] Maas, A.L., Hannun, A.Y. and Ng, A.Y. (2013) Rectifier Nonlinearities Improve Neural Network Acoustic Models. Proceedings of the 30th International Conference on Machine Learning, 16-21 June 2013, Atlanta.
[18] He, K., Zhang, X., Ren, S. and Sun, J. (2015) Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1026-1034. [Google Scholar] [CrossRef] 
[19] Ioffe, S. and Szegedy, C. (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, 6-11 July 2015.
[20] Stief, A., Tan, R., Cao, Y., et al. (2019) A Heterogeneous Benchmark Dataset for Data Analytics: Multiphase Flow Facility Case Study. Journal of Process Control, 79, 41-55. [Google Scholar] [CrossRef] 
[21] LeCun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444. [Google Scholar] [CrossRef] [PubMed]
[22] van der Maaten, L. and Hinton, G. (2008) Visualizing Data Using t-SNE. Journal of Machine Learning Research, 9, 2579-2605.
[23] Shi, X., Chen, Z., Wang, H. and Yeung, D.-Y. (2015) Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M. and Garnett, R., Eds., Advances in Neural Information Processing Systems 28 (NIPS 2015), Curran Associates, Inc., Red Hook.
[24] Carreira, J. and Zisserman, A. (2017) Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 4724-4733. [Google Scholar] [CrossRef] 
[25] Tran, D., Wang, H., Torresani, L., et al. (2018) A Closer Look at Spatiotemporal Convolutions for Action Recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 6450-6459. [Google Scholar] [CrossRef] 

为你推荐