Deep learning classification and recognition method for milling surface roughness combined with simulation data

Authors

  • Lingli Lu School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, 541006, People’s Republic of China
  • Huaian Yi School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, 541006, People’s Republic of China
  • Aihua Shu School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, 541006, People’s Republic of China
  • Jianhua Qin School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, 541006, People’s Republic of China
  • Enhui Lu School of Mechanical Engineering, Yangzhou University, Yangzhou, 225009, People’s Republic of China

DOI:

https://doi.org/10.24425/mms.2023.144401

Keywords

milling surface, classification, deep neural network, simulation

Abstract

To address the problem that a deep neural network needs a sufficient number of training samples to have a good prediction performance, this paper firstly used the Z-Map algorithm to generate a simulated profile of the milling surface and construct an optical simulation model of surface imaging to supplement the training sample size of the neural network. Then the Deep CORAL model was used to match the textures of the simulated samples and the actual samples across domains to solve the problem that the simulated samples were not in the same domain as the actual milling samples. Experimental results have shown that high texture matching could be achieved between optical simulation images and actual images, laying the foundation for expanding the actual milled workpiece images with the simulation images. The deep convolutional neural model Xception was used to predict the classification of six classes of data sets with the inclusion of simulation images, and the accuracy was improved from 86.48% to 92.79% compared with the model without the inclusion of simulation images. The proposed method solves the problem of the need for a large number of samples for deep neural networks and lays the foundation for similar methods to predict surface roughness for different machining processes.

References

[1] Wen, L., Ye, X., & Gao, L. (2020). A new automatic machine learning based hyperparameter optimization for workpiece quality prediction. Measurement and Control, 53(7-8), 1088-1098. https://doi.org/10.1177/0020294020932347

[2] Leelawattananon, T., Thowladda, W., & Chittayasothorn, S. (2015, August). Surface roughness measurement application using multi-frame techniques. In 2015 International Conference on Computer Application Technologies (pp. 86-91). IEEE. https://doi.org/10.1109/CCATS.2015.30

[3] Guo, R., & Tao, Z. (2011). Experimental investigation of a modified Beckmann-Kirchhoff scattering theory for the in-process optical measurement of surface quality. Optik, 122(21), 1890-1894. https://doi.org/10.1016/j.ijleo.2010.11.019

[4] Murugarajan, A., & Samuel, G. L. (2011). Measurement, modeling and evaluation of surface parameter using capacitive-sensor-based measurement system. Metrology and Measurement Systems, 18(3), 403-418. https://doi.org/10.2478/V10178-011-0007-9

[5] Hamed, A. M., El-Ghandoor, H., El-Diasty, F., & Saudy, M. (2004). Analysis of speckle images to assess surface roughness. Optics & Laser Technology, 36(3), 249-253. https://doi.org/10.1016/j.optlastec. 2003.09.005

[6] Jeyapoovan, T., & Murugan, M. (2013). Surface roughness classification using image processing. Measurement, 46(7), 2065-2072. https://doi.org/10.1016/j.measurement.2013.03.014

[7] Kamguem, R., Tahan, S. A., & Songmene, V. (2013). Evaluation of machined part surface roughness using image texture gradient factor. International Journal of Precision Engineering and Manufacturing, 14(2), 183-190. https://doi.org/10.1007/s12541-013-0026-x

[8] Lu, E., Liu, J., Gao, R., Yi, H., Wang, W., & Suo, X. (2018). Designing indices to measure surface roughness based on the color distribution statistical matrix (CDSM). Tribology International, 122, 96-107. https://doi.org/10.1016/j.triboint.2018.02.033

[9] Yi, H., Liu, J., Ao, P., Lu, E., & Zhang, H. (2016). Visual method for measuring the roughness of a grinding piece based on color indices. Optics Express, 24(15), 17215-17233. https://doi.org/10.1364/OE.24.017215

[10] Huaian, Y., Xinjia, Z., Le, T., Yonglun, C., & Jie, Y. (2020). Measuring grinding surface roughness based on singular value entropy of quaternion. Measurement Science and Technology, 31(11), 115006. https://doi.org/10.1088/1361-6501/ab9aa9

[11] Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527

[12] Liu, M., Cheung, C. F., Senin, N., Wang, S., Su, R., & Leach, R. (2020). On-machine surface defect detection using light scattering and deep learning. JOSA A, 37(9), B53-B59. https://doi.org/10.1364/JOSAA.394102

[13] Rifai, A. P., Aoyama, H., Tho N. H., et al. (2020). Evaluation of turned and milled surfaces roughness using convolutional neural network. J. Measurement, 161, 107860. https://doi.org/10.1016/j.measurement.2020.107860

[14] Saeedi, J., Dotta, M., Galli, A., Nasciuti, A., Maradia, U., Boccadoro, M., Gambardella, L. M. & Giusti, A. (2021). Measurement and inspection of electrical discharge machined steel surfaces using deep neural networks. Machine Vision and Applications, 32(1), 1-15. https://doi.org/10.1007/s00138-020-01142-w

[15] Yeganefar, A., Niknam, S. A., & Asadi, R. (2019). The use of support vector machine, neural network, and regression analysis to predict and optimize surface roughness and cutting forces in milling. The International Journal of Advanced Manufacturing Technology, 105(1), 951-965. https://doi.org/10.1007/s00170-019-04227-7

[16] Liu, M., Senin, N., Su, R., & Leach, R. (2020, April). Cascaded machine learning model for reconstruction of surface topography from light scattering. In Optics and Photonics for Advanced Dimensional Metrology (Vol. 11352, pp. 174-182). SPIE. https://doi.org/10.1117/12.2555035

[17] Zhang, H., Liu, J., Lu, E., Suo, X., & Chen, N. (2019). A novel surface roughness measurement method based on the red and green aliasing effect. Tribology International, 131, 579-590. https://doi.org/10.1016/j.triboint.2018.11.013

[18] Gorbenko, A., & Popov, V. (2012). Usage of the Laplace Transform as a Basic Algorithm of Railroad Tracks Recognition. International Journal of Mathematical Analysis, 6(48), 2413-2417. http://m-hikari.com/ijma/ijma-2012/ijma-45-48-2012/popovIJMA45-48-2012.pdf

[19] Sun, B., Feng, J., & Saenko, K. (2016, March). Return of frustratingly easy domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 30, No. 1). https://doi.org/10.1609/aaai.v30i1.10306

[20] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. https://dl.acm.org/doi/abs/10.1145/3065386

[21] Chen, Y., Yi, H., Liao, C., Huang, P., & Chen, Q. (2021). Visual measurement of milling surface roughness based on Xception model with convolutional neural network. Measurement, 186, 110217. https://doi.org/10.1016/j.measurement.2021.110217

[22] Wieczorowski, M., Kucharski, D., Sniatala, P., Krolczyk, G., Pawlus, P., & Gapinski, B. (2021, November). Theoretical considerations on application of artificial intelligence in coordinate metrology. In 2021 6th International Conference on Nanotechnology for Instrumentation and Measurement (NanofIM) (pp. 1-4). IEEE. https://doi.org/10.1109/NanofIM54124.2021.9737344

[23] Pawlus, P., Reizer, R., & Wieczorowski, M. (2021). Functional importance of surface texture parameters. Materials, 14(18), 5326. https://doi.org/10.3390/ma14185326

[24] Senin, N., & Leach, R. (2018). Information-rich surface metrology. Procedia CIRP, 75, 19-26. https://doi.org/10.1016/j.procir.2018.05.003

[25] Zhang, F. (2018). Instantaneous cutting behavior of high energy efficiency milling cutter and its evaluation method. Harbin University of Science and Technology. https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201901&filename=1018173174.nh (in Chinese)

[26] Hsu, P. L., & Yang, W. T. (1993). Realtime 3D simulation of 3-axis milling using isometric projection. Computer-Aided Design, 25(4), 215-224. https://doi.org/10.1016/0010-4485(93)90052-P

[27] Choi, B. K., Chung, Y. C., & Park, J. W. (1995). Application and extension of Z-map model. In Proc. of the 3rd Pacific Conference on Computer Graphics and Applications (pp. 363-382). https://xueshu.studiodahu.com/scholar?q=Application+and+extension+of+Z-map+model

[28] Nguyen, V., Dang, T., & Jin, F. (2018). Predict saturated thickness using TensorBoard visualization. Workshop on Visualisation in Environmental Sciences (EnvirVis). https://doi.org/10.2312/envirvis.20181135

[29] Vogelsang, D. C., & Erickson, B. J. (2020). Magician’s corner: 6. TensorFlow and TensorBoard. Radiology: Artificial Intelligence, 2(3). https://doi.org/10.1148/ryai.2020200012

[30] Liu, L., Zhang, Q., & Wei, X. (2012). A RGB image encryption algorithm based on DNA encoding and chaos map. Computers & Electrical Engineering, 38(5), 1240-1248. https://doi.org/10.1016/j.compeleceng.2012.02.007

[31] Al-Jubouri, Q., Al-Azawi, R. J., Al-Taee, M., & Young, I. (2018). Efficient individual identification of zebrafish using Hue/Saturation/Value color model. The Egyptian Journal of Aquatic Research, 44(4), 271-277. https://doi.org/10.1016/j.ejar.2018.11.006

Downloads

Published

2023-03-30

How to Cite

Lu, Lingli, et al. “Deep Learning Classification and Recognition Method for Milling Surface Roughness Combined With Simulation Data”. Metrology and Measurement Systems, vol. 30, no. 1, Mar. 2023, pp. 117-38, doi:10.24425/mms.2023.144401.

Issue

Vol. 30 No. 1 (2023)

Section

Articles