In order to meet the needs of people's consumption quality upgrade, major manufacturers have put forward higher requirements for the machining accuracy, surface roughness and material properties of the workpiece. By building a prediction model (PM) to predict the surface of the formed parts with different process parameters Roughness, using NN to build a roughness prediction model (PM), adjust the process parameters through the model, and ensure the surface quality of the parts. Therefore, this paper discusses and studies the roughness PM based on neural network (NN). This paper firstly introduces the basic situation of the surface topography simulation system and the workflow of the PM in detail, and then builds the PM from the surface roughness measurement, data processing and overall parameter design, and finally compares the model results. Analysis and evaluation index analysis.

Hong Yang. Roughness Prediction Model Based on Neural Network. International Journal of Neural Network (2021), Vol. 2, Issue 4: 24-31. https://doi.org/10.38007/NN.2021.020404.

[1] Fakhri M, Dezfoulian R S. Pavement structural evaluation based on roughness and surface distress survey using NN model. Construction and Building Materials, 2019, 204(2019):768-780. https://doi.org/10.1016/j.conbuildmat.2019.01.142

[2] Daoud O A, Ksaibati K. Artificial NN-based roughness prediction models for gravel roads considering land use. Innovative Infrastructure Solutions, 2022, 7(3):1-11. https://doi.org/10.1007/s41062-022-00793-0

[3] Abdulateef O F. Surface Roughness Prediction in Turning Operation of Aluminum Alloy 6061using Artificial NN (Ann). Journal of Mechanical Engineering Research and Developments, 2020, 43(4):360-366.

[4] Jankovic P, Madic M, Radovanovic M, et al. Optimization of Surface Roughness from Different Aspects in High-Power CO_2 Laser Cutting of AA5754 Aluminum Alloy. Arabian Journal for Science and Engineering, 2019, 44(12):10245-10256. https://doi.org/10.1007/s13369-019-04037-9

[5] Maleki M, Amini J, Notarnicola C. Soil Roughness Retrieval from TerraSar-X Data Using NN and Fractal Method. Advances in Space Research, 2019, 64(5):1117-1129. https://doi.org/10.1016/j.asr.2019.04.019

[6] Khadar S. Evaluation of surface roughness in the turning of mild steel under different cutting conditions using backpropagation NN. Proceedings of the Estonian Academy of Sciences, 2020, 69(2):109-115. https://doi.org/10.3176/proc.2020.2.02

[7] Villegas J, Markov K, Perkins J, et al. Prediction of Creaky Speech by Recurrent NNs Using Psychoacoustic Roughness. IEEE Journal of Selected Topics in Signal Processing, 2020, 14(2):355-366. https://doi.org/10.1109/JSTSP.2019.2949422

[8] Mulay A, Ben B S, Ismail S , et al. Prediction of average surface roughness and formability in single point incremental forming using artificial NN. Archives of Civil and Mechanical Engineering, 2019, 19(4):1135-1149. https://doi.org/10.1016/j.acme.2019.06.004

[9] Pourseiedrezaei M, Loghmani A, Keshmlri M. Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial NN. Archives of acoustics, 2019, 44(3):561-573.

[10] Erygin E, Duyun T. Development of Nns for Forecasting Roughness When Milling Various Materials. Bulletin of Belgorod State Technological University named after V G Shukhov, 2020, 5(11):113-124. https://doi.org/10.34031/2071-7318-2020-5-11-113-124

[11] Beemaraj R K, Sekar M, Vijayan V. Computer vision measurement and optimization of surface roughness using soft computing approaches:. Transactions of the Institute of Measurement and Control, 2020, 42(13):2475-2481. https://doi.org/10.1177/0142331220916056

[12] H Gürbüz. Estimation of surface roughness and cutting speed in CNC WEDM by artificial NN that employed trainable activation function. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2021, 235(15):2737-2753. https://doi.org/10.1177/0954406221990057

[13] Vagheesan S, Govindarajalu J. Hybrid NN–particle swarm optimization algorithm and NN–genetic algorithm for the optimization of quality characteristics during CO 2 laser cutting of aluminium alloy. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2019, 41(8):1-15. https://doi.org/10.1007/s40430-019-1830-8

[14] Naguib A, El-Badawy S, Ibrahim M. International Roughness Index Predictive Model for Rigid Pavements based on LTPP Data(Dept. C (PUPLIC)). Bulletin of the Faculty of Engineering Mansoura University, 2020, 40(2):30-38. https://doi.org/10.21608/bfemu.2020.101239

[15]  Getmanov V G ,  Chinkin V E ,  Sidorov R V , et al. Geomagnetic Storm Prediction Based on the NN Digital Processing of Joint Observations of the URAGAN Muon Hodoscope and Neutron Monitor Stations. Geomagnetism and Aeronomy, 2022, 62(4):388-398. https://doi.org/10.1134/S0016793222040089

[16] Galati M, Rizza G, Defanti S, et al. Surface roughness prediction model for Electron Beam Melting (EBM) processing Ti6Al4V. Precision Engineering, 2021, 69(2):19-28. https://doi.org/10.1016/j.precisioneng.2021.01.002

[17] Kayser B, Gauvreau B, D Ecotière. Sensitivity analysis of a parabolic equation model to ground impedance and surface roughness for wind turbine noise. The Journal of the Acoustical Society of America, 2019, 146(5):3222-3231. https://doi.org/10.1121/1.5131652

[18] Ramesh P, Mani K. Prediction of surface roughness using machine learning approach for abrasive waterjet milling of alumina ceramic. The International Journal of Advanced Manufacturing Technology, 2022, 119(1):503-516. https://doi.org/10.1007/s00170-021-08052-9