Abstract
Roughness prediction of ground surfaces is critical in understanding and optimizing the grinding process. However, it is hitherto difficult to predict accurately the ground surface roughness by theoretical and empirical models due to the complexity of grinding process. BP neural network (BPNN), which can be used to establish the relationship between processing parameters and surface roughness, avoids the difficulty of revealing the complex physical mechanism and thus has unique potential in automatic optimization of grinding process in industrial practice. Activation function is one of the most important factors affecting the efficiency and accuracy of BPNN. Nevertheless, it is often selected arbitrarily or at most by trials or tuning. This paper proposes an activation function selection approach in which virtual data generated from the approximate physical model are employed to evaluate the performance of the BPNN in practice application. The results show that with tansig as the activation function of hidden layer and purelin as the activation function of output layer, the BPNN model can obtain the highest learning efficiency. Moreover, when the activation function of hidden layer is sigmoid, whose shape factor is 1–3, and the output layer activation function is purelin, the model can predict more precisely. Finally, the proposed approach is validated by comparing the performance of BPNN obtained from the virtual data and the experimental data. Obtained results showed that the proposed approach is a simple and effective way to determine the activation function of BPNN.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abraham, A. (2004). Meta learning evolutionary artificial neural networks. Neurocomputing, 56, 1–38. https://doi.org/10.1016/S0925-2312(03)00369-2.
Agarwal, S., & Rao, P. V. (2005). A probabilistic approach to predict surface roughness in ceramic grinding. International Journal of Machine Tools and Manufacture, 45(6), 609–616. https://doi.org/10.1016/j.ijmachtools.2004.10.005.
Agarwal, S., & Venkateswara Rao, P. (2010). Modeling and prediction of surface roughness in ceramic grinding. International Journal of Machine Tools and Manufacture, 50(12), 1065–1076. https://doi.org/10.1016/j.ijmachtools.2010.08.009.
Agarwal, S., & Venkateswara Rao, P. (2012). Predictive modeling of undeformed chip thickness in ceramic grinding. International Journal of Machine Tools and Manufacture, 56, 59–68. https://doi.org/10.1016/j.ijmachtools.2012.01.003.
Bai, Y., Zhang, H., & Hao, Y. (2009). The performance of the backpropagation algorithm with varying slope of the activation function. Chaos, Solitons & Fractals, 40(1), 69–77. https://doi.org/10.1016/j.chaos.2007.07.033.
Benardos, P. G., & Vosniakos, G. C. (2003). Predicting surface roughness in machining: A review. International Journal of Machine Tools and Manufacture, 43(8), 833–844. https://doi.org/10.1016/S0890-6955(03)00059-2.
Chandrasekaran, M., & Devarasiddappa, D. (2014). Artificial neural network modeling for surface roughness prediction in cylindrical grinding of Al-SiCp metal matrix composites and ANOVA analysis. Advances in Production Engineering & Management, 9(2), 59–70. https://doi.org/10.14743/apem2014.2.176.
Chen, T. W. L. L. (1994). A neural network approach for grinding processes: Modelling and optimization. International Journal of Machine Tools and Manufacture, 7(34), 919–937. https://doi.org/10.1016/0890-6955(94)90025-6.
Darafon, A., Warkentin, A., & Bauer, R. (2013). 3D metal removal simulation to determine uncut chip thickness, contact length, and surface finish in grinding. The International Journal of Advanced Manufacturing Technology, 66(9–12), 1715–1724. https://doi.org/10.1007/s00170-012-4452-1.
Deng, Z. H., Zhang, X. H., Liu, W., & Cao, H. (2009). A hybrid model using genetic algorithm and neural network for process parameters optimization in NC camshaft grinding. The International Journal of Advanced Manufacturing Technology, 45(9–10), 859–866. https://doi.org/10.1007/s00170-009-2029-4.
Ding, W., Dai, C., Yu, T., Xu, J., & Fu, Y. (2017). Grinding performance of textured monolayer CBN wheels: Undeformed chip thickness nonuniformity modeling and ground surface topography prediction. International Journal of Machine Tools and Manufacture, 122, 66–80. https://doi.org/10.1016/j.ijmachtools.2017.05.006.
Ertuğrul, Ö. F. (2018). A novel type of activation function in artificial neural networks: Trained activation function. Neural Networks, 99, 148–157. https://doi.org/10.1016/j.neunet.2018.01.007.
Gopan, V., Wins, K. L. D., & Surendran, A. (2018). Integrated ANN-GA approach for predictive modeling and optimization of grinding parameters with surface roughness as the response. Materials Today: Proceedings, 5(5), 12133–12141. https://doi.org/10.1016/j.matpr.2018.02.191.
Govindhasamy, J. J., McLoone, S. F., Irwin, G. W., French, J. J., & Doyle, R. P. (2005). Neural modelling, control and optimisation of an industrial grinding process. Control Engineering Practice, 13(10), 1243–1258. https://doi.org/10.1016/j.conengprac.2004.11.006.
Hecht-Nielsen, R. (1987). Kolmogorov’s mapping neural network existence theorem. In IEEE First international conference on neural networks (pp. 11–14).
Hou, Z. B., & Komanduri, R. (2003). On the mechanics of the grinding process—Part I. Stochastic nature of the grinding process. International Journal of Machine Tools and Manufacture, 43(15), 1579–1593. https://doi.org/10.1016/s0890-6955(03)00186-x.
Jiang, J. L., Ge, P. Q., Bi, W. B., Zhang, L., Wang, D. X., & Zhang, Y. (2013). 2D/3D ground surface topography modeling considering dressing and wear effects in grinding process. International Journal of Machine Tools and Manufacture, 74, 29–40. https://doi.org/10.1016/j.ijmachtools.2013.07.002.
Kahraman, M. F., & Öztürk, S. (2019). Experimental study of newly structural design grinding wheel considering response surface optimization and Monte Carlo simulation. Measurement, 147, 106825. https://doi.org/10.1016/j.measurement.2019.07.053.
Li, Z., Zhang, F., Luo, X., Chang, W., Cai, Y., Zhong, W., et al. (2019). Material removal mechanism of laser-assisted grinding of RB-SiC ceramics and process optimization. Journal of the European Ceramic Society, 39(4), 705–717. https://doi.org/10.1016/j.jeurceramsoc.2018.11.002.
Liang, Z., Liao, S., Wen, Y., & Liu, X. (2019). Working parameter optimization of strengthen waterjet grinding with the orthogonal-experiment-design-based ANFIS. Journal of Intelligent Manufacturing, 30(2), 833–854. https://doi.org/10.1007/s10845-016-1285-z.
Lian-qing, C., Jian-liang, G., Xun, Y., Jun, C., & Xia, Z. (2013). Grinding roughness prediction model based on evolutionary artificial neural network. Computer Integrated Manufacturing Systems, 19(11), 2854–2863. https://doi.org/10.13196/j.cims.2013.11.chenlianqing.2854.10.20131123.
Lipiński, D., Bałasz, B., & Rypina, A. (2018). Modelling of surface roughness and grinding forces using artificial neural networks with assessment of the ability to data generalisation. The International Journal of Advanced Manufacturing Technology, 94(1–4), 1335–1347. https://doi.org/10.1007/s00170-017-0949-y.
Liu, C., Ding, W., Li, Z., & Yang, C. (2017). Prediction of high-speed grinding temperature of titanium matrix composites using BP neural network based on PSO algorithm. The International Journal of Advanced Manufacturing Technology, 89(5–8), 2277–2285. https://doi.org/10.1007/s00170-016-9267-z.
Liu, Q., & Wang, J. (2008). A one-layer recurrent neural network with a discontinuous activation function for linear programming. Neural Computation, 20(5), 1366–1383. https://doi.org/10.1162/neco.2007.03-07-488.
Malkin, S. (1989). Grinding technology: Theory and applications of machining with abrasives. New York: Wiley and Sons.
Neşeli, S., Asiltürk, O., & Çelik, L. (2012). Determining the optimum process parameter for grinding operations using robust process. Journal of Mechanical Science and Technology, 26(11), 3587–3595. https://doi.org/10.1007/s12206-012-0851-3.
Pahlitzsch, H. H. (1943). Determination and significance of chip thickness in grinding. Workshop Technology, 12, 397–401.
Prabhu, S., Uma, M., & Vinayagam, B. K. (2015). Surface roughness prediction using Taguchi-fuzzy logic-neural network analysis for CNT nanofluids based grinding process. Neural Computing and Applications, 26(1), 41–55. https://doi.org/10.1007/s00521-014-1696-8.
Qu, S., Gong, Y., Yang, Y., Cai, M., & Sun, Y. (2018). Surface topography and roughness of silicon carbide ceramic matrix composites. Ceramics International, 44(12), 14742–14753. https://doi.org/10.1016/j.ceramint.2018.05.104.
Ren, C., An, N., Wang, J., Li, L., Hu, B., & Shang, D. (2014). Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting. Knowledge-Based Systems, 56, 226–239. https://doi.org/10.1016/j.knosys.2013.11.015.
Sedighi, M., & Afshari, D. (2010). Creep feed grinding optimization by an integrated GA-NN system. Journal of Intelligent Manufacturing, 21(6), 657–663. https://doi.org/10.1007/s10845-009-0243-4.
Sivatte-Adroer, M., Llanas-Parra, X., Buj-Corral, I., & Vivancos-Calvet, J. (2016). Indirect model for roughness in rough honing processes based on artificial neural networks. Precision Engineering, 43, 505–513. https://doi.org/10.1016/j.precisioneng.2015.09.004.
Sun, S., Tang, J., Shao, W., Chen, C., & Liu, Y. (2019). Research on the matching relationship between ultrasonic-assisted grinding parameters and workpiece surface roughness. The International Journal of Advanced Manufacturing Technology, 102(1–4), 487–496. https://doi.org/10.1007/s00170-018-3195-z.
Tong, X., Wu, X., Zhang, F., Ma, G., Zhang, Y., Wen, B., et al. (2019). Mechanism and parameter optimization in grinding and polishing of M300 steel by an elastic abrasive. Materials, 12(3), 340. https://doi.org/10.3390/ma12030340.
Yin, S., Nguyen, D., Chen, F., Tang, Q., & Duc, L. A. (2019). Application of compressed air in the online monitoring of surface roughness and grinding wheel wear when grinding Ti-6Al-4 V titanium alloy. The International Journal of Advanced Manufacturing Technology, 101(5), 1315–1331. https://doi.org/10.1007/s00170-018-2909-6.
Zhang, Y., Fang, C., Huang, G., & Xu, X. (2018). Modeling and simulation of the distribution of undeformed chip thicknesses in surface grinding. International Journal of Machine Tools and Manufacture, 127, 14–27. https://doi.org/10.1016/j.ijmachtools.2018.01.002.
Acknowledgments
The authors appreciate the financial support from the National Natural Science Foundation of China (51875078, 51991372, 51975094), and the Science Fund for Creative Research Groups of NSFC of China (51621064).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pan, Y., Wang, Y., Zhou, P. et al. Activation functions selection for BP neural network model of ground surface roughness. J Intell Manuf 31, 1825–1836 (2020). https://doi.org/10.1007/s10845-020-01538-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-020-01538-5