Research on Establishing a Predictive Model for Surface Roughness of Al6061 Aspherical Reflector in Single Point Diamond Turning Using Back Propagation Artificial Neural Networks
Main Article Content
Abstract
The paper presents establishing of a predictive model for surface roughness value of Al6061 material aspherical surface in ultra-precision turning using a single point diamond tool (SPDT). The model employs the structure of a back propagation artificial neural network (ANN). Three cutting parameters are considered, including spindle speed, feed rate, and depth of cut. An experimental matrix was established based on data from 30 actual experiments measuring surface roughness values of aspherical surfaces under corresponding machining conditions for the given parameter sets. Through the evaluation of six specific neural network structures (based on the number of layers and neurons in each layer), an optimal neuron ratio between layers was determined to optimize the predictive model. The ANN structure 3-5-15-1 yielded the best prediction results, as demonstrated by evaluation metrics such as: Coefficient of Determination (R2 equal 0.9999), Mean Square Error (MSE equal 2.6e-4), Root Mean Square Error (RMSE equal 0.0163) and Mean Absolute Percent Error (MAPE equal 0.6949%).Validation experiments, involving six training sessions using MATLAB software, confirmed the high feasibility of the predictive model. This was evidenced by the minimal error (1-2%) between the predicted surface roughness values and the experimental measured roughness values. This research is directly applied to predic surface roughness value of Al6061 aspherical surface in SPDT and serves as foundation for similar studies on different material or surface geometries of machined parts.
Keywords
Aspherical Surface, artificial neural network, diamond tools, single-point diamond turning, surface roughness.
Article Details
References
[2] Guo, J., Li, Q., Qin, P., Yuan, A., Lu, M., Ke, X., Zhang, Y., and Cheung, B. C. F., Internal surface finishing and roughness measurement: A critical review, Chinese Journal of Aeronautics, vol. 38, iss. 8, Aug. 2025, Art. no. 103303. https://doi.org/10.1016/j.cja.2024.11.013
[3] Yang, C., Su, H., Gao S., Fu Y., Ding W., and Xu J., Surface quality and geometric accuracy control of fuel nozzle single-pass honing, The International Journal of Advanced Manufacturing Technology, vol. 114, pp. 3325–3336, Apr. 2021. https://doi.org/10.1007/s00170-021-07103-5
[4] Sun, L., Duan, W., Wu, H., Chen, M., Zeng, J., Wu, Y., and Chen, Y., Investigation on the ultra-precision diamond turning of ZnSe aspheric surfaces using straight-nosed cutting tools, Journal of Manufacturing Processes, vol. 104, pp. 108–122, Oct. 2023. https://doi.org/10.1016/j.jmapro.2023.09.011
[5] Zhuang, G., Zong, W., and Tang, Y., Statistical analysis and suppression of vibration frequency bifurcation in diamond turning of Al 6061 mirror, Mechanical Systems and Signal Processing, vol. 198, Sep. 2023, Art. no. 110421. https://doi.org/10.1016/j.ymssp.2023.110421
[6] Chang, Z., Li, M., Zhu, K., Sun, L., Ye, R., Sang, M., Han, R., Jiang, Y., Li, S., Zhou, J., and Ge, R., Model predictive control of long Transfer-line cooling process based on Back-Propagation neural network, Applied Thermal Engineering, vol. 207, May 2022, Art. no. 118178. https://doi.org/10.1016/j.applthermaleng.2022.118178
[7] Dedeakayoğulları, H., Kaçal, A., and Keser, K., Modeling and prediction of surface roughness at the drilling of SLM-Ti6Al4V parts manufactured with pre-hole with optimized ANN and ANFIS, Measurement, vol. 203, Nov. 2022, Art. no. 112029. https://doi.org/10.1016/j.measurement.2022.112029
[8] Naga Malleswari, V., Kameswara Manaswy, G., and Pragvamsa, P. G., Prediction of surface roughness for fused deposition in fabricated work pieces by RSM and ANN technique, Materials Today: Proceedings, Mar. 2023. https://doi.org/10.1016/j.matpr.2023.03.378
[9] Trujillo, F. J., Martín-Béjar, S., Bañón, F., Andersson, T., and Sevilla, L., Ann-based predictive model of geometrical deviations in dry turning of AA7075 (Al-Zn) alloy, Measurement, vol. 243, Feb. 2025, Art. no. 116355. https://doi.org/10.1016/j.measurement.2024.116355
[10] Song, L., Xie, J., Jiang, Q., Wang, G., Zhong, S., Han, G., and Wu, J., A back-propagation neural network optimized by genetic algorithm for rock joint roughness evaluation, Journal of Rock Mechanics and Geotechnical Engineering, vol. 17, iss. 5, May 2025, pp. 3054–3072. https://doi.org/10.1016/j.jrmge.2024.10.022
[11] Maheshwera Reddy Paturi, U., Devarasetti, H., and Kumar Reddy Narala, S., Application of regression and artificial neural network analysis in modelling of surface roughness in hard turning of AISI 52100 steel, Materials Today: Proceedings, vol. 5, iss. 2, pp. 4766–4777. https://doi.org/10.1016/j.matpr.2017.12.050
[12] Gopal, M., Prediction of surface roughness in turning of duplex stainless steel (DSS) using response surface methodology (RSM) and artificial neural network (ANN), Materials Today: Proceedings, vol. 47, part 19, pp. 6704–6711, 2021. https://doi.org/10.1016/j.matpr.2021.05.118
[13] Gallo, C., Artificial Neural Networks Tutorial, IGI Global, Italy, pp. 6369–6378, 2014.
https://doi.org/10.4018/978-1-4666-5888-2.ch626
[14] Hasan, M. M., Rahman, M. M., Islam, M. S., Chan, W. H., Alginahi, Y. M., Kabir, M. N., Bakar, S. A., and Ramasamy, D., Artificial neural network modeling for predicting thermal conductivity of EG/water-based CNC nanofluid for engine cooling using different activation functions, Frontiers in Heat and Mass Transfer, vol. 22, no. 2, pp. 537–556, 2024.
https://doi.org/10.32604/fhmt.2024.047428
[15] Liu, Z., Bao, J., Hu, W., and Yan, H., Microstructure, interfacial reaction behavior, and mechanical properties of Ti3AlC2 reinforced Al6061 composites, Transactions of Nonferrous Metals Society of China, vol. 34, iss. 9, pp. 2756–2771, Sep. 2024. https://doi.org/10.1016/S1003-6326(24)66574-X
[16] Kefale Mangesha, Y., Nallamothu, R. B., Ancha, V. R., and Tesfaye Tefera, N., Optimization, production, and characterization of cottonseed methyl ester based on Box-Behnken in response surface design and gas Chromatography-Mass spectrum analysis, Energy Conversion and Management: X, vol. 23, Jul. 2024, Art. no. 100619.
https://doi.org/10.1016/j.ecmx.2024.100619
[17] Emeji, I. C., and Patel, B., Box-Behnken assisted RSM and ANN modelling for biodiesel production over titanium supported zinc-oxide catalyst, Energy, vol. 308, Nov. 2024, Art. no. 132765. https://doi.org/10.1016/j.energy.2024.132765
[18] Santhosh, A. J., Tura, A. D., Jiregna, I. T., Gemechu, W. F., Ashok, N., and Ponnusamy, M., Optimization of CNC turning parameters using face centred CCD approach in RSM and ANN-genetic algorithm for AISI 4340 alloy steel, Results in Engineering, vol. 11, Sep. 2021, Art. no. 100251. https://doi.org/10.1016/j.rineng.2021.100251
[19] Ruparelia, J. R., and Patel, H. K., Harnessing the chromium reduction potential of Pseudomonas aeruginosa JRHM33: A comprehensive study on bioinformatics, phenotype microarray, and CCD-RSM optimization, Heliyon, vol. 10, iss. 15, Art. no. e35650. https://doi.org/10.1016/j.heliyon.2024.e35650