Pipeline leakage aperture recognition based on lightweight neural network with the improved dense block

被引：0
|
作者：
Sun J. [1 ,2 ]
Wang L. [1 ,2 ]
Wen J. [3 ]
Xiao Q. [4 ]
机构：
[1] School of Information Science and Engineering, Yanshan University, Qinhuangdao
[2] Hebei Key Laboratory of Information Transmission and Signal Processing, Yanshan University, Qinhuangdao
[3] Key Laboratory of Measurement Technology and Instrumentation of Hebei Province, Yanshan University, Qinhuangdao
[4] School of Artificial Intelligence, Henan University, Zhengzhou
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2022年 / 43卷 / 03期
关键词：
Depth separable convolution; Hetconv; Lightweight neural network; Multi-convolution dense block; Pipeline leak aperture identification;
D O I：
10.19650/j.cnki.cjsi.J2108890
中图分类号：
学科分类号：
摘要：
The identification method of pipeline leakage aperture based on the deep neural network has a high identification rate. However, its application in industrial environment and real-time processing is greatly limited due to the large number of parameters and large memory consumption due to its complex structure. To address this issue, an optimized convolution improved dense block lightweight neural network is proposed for the pipeline leak aperture identification. Firstly, a new multi-convolutional dense block is constructed by combining the deeply separable convolution with the heterogeneous convolution to extract the features of leakage signals. Then, the convolutional attention mechanism is used to classify the weight of features to realize the importance distinction of features. Finally, the results are obtained by classifier. Experimental results show that the recognition accuracy of the proposed method is 96.59%, and the number of parameters is only 781 KB. While ensuring high recognition accuracy, the number of parameters and floating point numbers are greatly reduced, the training time is also reduced, and the real-time response ability is improved, which has guiding significance for practical industrial monitoring applications. © 2022, Science Press. All right reserved.
引用
收藏
页码：98 / 108
页数：10
相关论文
共 30 条
  • [11] LI J Y, ZHAO Y K, XUE ZH ER, Et al., A survey of model compression for deep neural networks, Journal of Engineering Science, 41, 10, pp. 1229-1239, (2019)
  • [12] GAO H, TIAN Y L, XU F Y, Et al., Survey of deep learning model compression and acceleration, Journal of Software, 32, 1, pp. 68-92, (2021)
  • [13] WANG P, HU Q, ZHANG Y, Et al., Two-step quantization for low-bit neural networks, Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4376-4384, (2018)
  • [14] YANG Y Z, YU J H, JOJIC N, Et al., FSNet: Compression of deep convolutional neural networks by filter summary, (2020)
  • [15] JIANG X, WANG N, XIN J, Et al., Learning lightweight super-resolution networks with weight pruning, Neural Networks, 144, pp. 21-32, (2021)
  • [16] CUI B Y, LI Y M, ZHANG ZH F., Joint structured pruning and dense knowledge distillation for efficient transformer model compression, Neurocomputing, 458, pp. 56-69, (2021)
  • [17] JIAO J Y, ZHAO M, LIN J, Et al., Deep coupled dense convolutional network with complementary data for intelligent fault diagnosis, IEEE Transactions on Industrial Electronics, 66, 12, pp. 9858-9867, (2019)
  • [18] GE D H, LI H SH, ZHANG L, Et al., Survey of lightweight neural network, Journal of Software, 31, 9, pp. 2627-2653, (2020)
  • [19] CHOLLET F., Xception: Deep learning with depthwise separable convolutions, Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1800-1807, (2017)
  • [20] HOWARD A G, ZHU M L, CHEN B, Et al., MobileNets: Efficient convolutional neural networks for mobile vision applications, Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 432-445, (2017)
123