A State Detection Method of Ball Milling Load Based on Deep Wide Residual Shrinkage Networks

被引：0
|
作者：
Gao Y. [1 ]
Meng X. [1 ]
Zhang Q. [1 ]
Wang Q. [2 ,3 ]
Yang J. [2 ,3 ]
Dong Y. [1 ]
机构：
[1] College of Electrical and Information Engineering, Hunan University, Changsha
[2] State Key Laboratory of Process Automation in Mining & Metallurgy, Beijing
[3] Beijing Key Laboratory of Process Automation in Mining & Metallurgy, Beijing
来源：
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2023年 / 50卷 / 02期
关键词：
attention mechanism; ball milling; deep residual shrinkage networks; load state;
D O I：
10.16339/j.cnki.hdxbzkb.2022247
中图分类号：
学科分类号：
摘要：
Aiming at the problem of accurate diagnosis of ball milling load state under complex grinding condi⁃ tions，a load state diagnosis method of ball milling based on Deep Wide Residual Shrinkage Networks（DWRSNs）is proposed. Firstly，a wide-convolutional neural network is used to extract the short-term features of the vibration sig⁃ nal，a three-layer deep residual shrinkage network is established，and a soft threshold function is used for nonlinear transformation. Then，the advanced features of the load state oriented are extracted based on the self-learning thresh⁃ old of the attention mechanism module. And discrimination of the load state of the ball milling is realized through the full-connection layer and the soft layer. The measured results prove that the DWRSNs method proposed in this paper is superior to the existing DCNN，ResNets，and DRSNs diagnostic methods in terms of fit，convergence speed，and learning ability. Meanwhile，the exacted vibration signal features are highly representative，the compactness within the cluster is high，and the boundary between the clusters is obvious after TSNE visualization. The accuracy of the DWRSNs diagnostic test set of the proposed method exceeds 99%，and the cross-entropy loss is 0.0772. Compared with the existing load state diagnosis method，it has higher accuracy and less time-consuming diagnosis and can achieve accurate identification of the load state of the ball milling and provide an effective and reliable criterion for optimizing the control of the process of beneficiation and grinding and improving the efficiency of grinding. © 2023 Hunan University. All rights reserved.
引用
收藏
页码：102 / 111
页数：9
相关论文
共 15 条
  • [11] YAN C M, WANG C．, Development and application of convolu⁃ tional neural network model ［J］, Journal of Frontiers of Computer Science and Technology, 15, 1, pp. 27-46, (2021)
  • [12] ZHANG X Y，, REN S Q, Deep residual learning for image recognition, 2016 IEEE Conference on Computer Vi⁃ sion and Pattern Recognition, pp. 770-778, (2016)
  • [13] ZHAO M H, ZHONG S S，, FU X Y, Deep residual shrinkage networks for fault diagnosis［J］, IEEE Transactions on Industrial Informatics, 16, 7, pp. 4681-4690, (2020)
  • [14] Learning where to attend with deep architectures for image tracking［J］, Neural Computation, 24, 8, pp. 2151-2184, (2012)
  • [15] AKBAR S, SALAMA S, The transition mod⁃ ule：a method for preventing overfitting in convolutional neural net⁃ works［J］, Computer Methods in Biomechanics and Biomedical Engineering：Imaging & Visualization, 7, 3, pp. 260-265, (2019)
12