Recognition Algorithm Based on Convolution Neural Network for the Mechanical Parts

  • Duan SuolinEmail author
  • Yin Congcong
  • Liu Maomao
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 484)


For the problems that the traditional mechanical parts identification algorithm needs to design and extract relevant features artificially, so that the process is complex and time consuming in the computation is larger as well as identification accuracy is easily affected by the diversity of parts morphology, a mechanical part identification algorithm based on convolutional neural network is proposed in this paper. The Leaky ReLU function algorithm as an activation function is used to improve the pooling method, and a SVM classifier is combined to construct a convolutional neural network WorkNet-2 for the recognition of mechanical parts. In the recognition experiments of common four kinds of mechanical parts, the trained WorkNet-2 network’s recognition accuracy on the test set reached 97.82%. The experimental results show that compared with the traditional mechanical parts recognition algorithm, this algorithm can extract the high-level features of the target parts, and has the advantages of small influence of parts shape diversity, the recognition rate is higher and good real-time performance.


Identification of the parts Extraction of feature Convolutional Neural Network Pooling method 



This study was funded by the project of Jiangsu science and technology plan (BEK2013671); grants from the Jiangsu Province University Academic Degree Graduates Scientific Research and Innovation Plan (KYLX16_0630).


  1. 1.
    Zhao, P.: Machine Vision Theory and Application, pp. 28–29. Electronic Industry Press (2011)Google Scholar
  2. 2.
    Yang, D., Zhang, Z.: Research on the method of workpiece location and recognition using image segmentation. Small Microcomput. Syst. 37(9), 2070–2073 (2016)Google Scholar
  3. 3.
    Liu, P., Shen, Y., Yao, F., et al.: Region-based moving object detection using HU moments. In: IEEE International Conference on Information and Automation, pp. 1590–1593. IEEE (2015)Google Scholar
  4. 4.
    Cao, J., Yuan, A., Yu, L.: A part recognition algorithm based on SURF feature. Comput. Appl. Softw. 32(1), 186–189 (2015)Google Scholar
  5. 5.
    He, X., Xie, Q., Xu, H.: Part recognition system based on LabVIEW and BP neural network. Instrum. Technol. Sens. (1), 119–122 (2017)Google Scholar
  6. 6.
    Chang, L., Deng, X., Zhou, M., et al.: Convolution neural network in image understanding. Autom. J. 42(9), 1300–1312 (2016)zbMATHGoogle Scholar
  7. 7.
    Dong, J., Jin, L., Zhou, F.: Summary of convolution neural network research. Acta Comput. Sci. 40(6), 1229–1251 (2017)Google Scholar
  8. 8.
    Li, T., Li, X., Ye, M.: Summary of research on target detection based on convolution neural network. Comput. Appl. Res. 34(10), 2881–2886 (2017)MathSciNetGoogle Scholar
  9. 9.
    Deng, L., Wang, Z.J.: Vehicle recognition based on deep convolution neural network. Comput. Appl. Res. 33(3), 930–932 (2016)Google Scholar
  10. 10.
    Gold, J., Liu, W., Wang, X.: Traffic sign recognition based on optimized convolution neural network. Comput. Appl. 37(2), 530–534 (2017)Google Scholar
  11. 11.
    Hua, K.L., Hsiao, Y.S., Sanchez-Riera, J., et al.: A comparative study of data fusion for RGB-D based visual recognition. Pattern Recognit. Lett. 73(10), 1–6 (2016)Google Scholar
  12. 12.
    Huang, G., Sun, L., Wu, X.: Fast vision recognition and localization algorithm for industrial sorting robot based on deep learning. Robot 38(6), 711–719 (2016)Google Scholar
  13. 13.
    Chen, T., Wang, N., Xu, B., et al.: Empirical evaluation of rectified activations in convolutional network. Comput. Sci. 209–213 (2015)Google Scholar
  14. 14.
    He, K., Ren, S., Zhang, X., et al.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  15. 15.
    He, K., Ren, S., Zhang, X., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)CrossRefGoogle Scholar
  16. 16.
    Jiang, S.: Image Recognition based on Convolution Neural Network, pp. 14–17. Jilin University (2017)Google Scholar
  17. 17.
    Dong, L., Li, P., Xiao, H., et al.: A cloud image detection method based on SVM vector machine. Neurocomputing 169, 34–42 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Mechanical EngineeringChangzhou UniversityChangzhouChina

Personalised recommendations