Data-driven model for predicting machining cycle time in ultra-precision machining

Abstract

This study aims to present a data-driven method to accurately predict the machining cycle time for an ultra-precision machining (UPM) milling machine, considering the four most common interpolation types in the target machine tool: full-stop linear, non-stop linear, circular, and Bezier interpolation. Regarding these interpolation types, four artificial neural network (ANN) models were developed to predict the machining times for each command line in each numerical control (NC) program. Using the proposed data-driven method, the motion type of each command line in the NC program is first identified. The corresponding features are then extracted from the specific command line, which is considered the input of the model, while the estimated machining time is the output. After training and tunning, all four models achieved extremely high prediction accuracies (>95%), which were further validated through cutting experiments. Moreover, the influence of different feedrates on the machining time prediction accuracy in UPM was explored for the first time, demonstrating the excellent robustness of the proposed models at high feedrate compared with the CAM-based method. This strategy is easily applicable to other CNC machine tools, and the compact structure of the ANN model and its low computation consumption enable its deployment in edge devices. With the addition of more datasets, the accuracy and robustness of the proposed model can be further enhanced.

Keywords

Data-driven model / Ultra-precision machining (UPM) / Machining cycle time / Interpolation / Neural networks / Information and Computing Sciences / Artificial Intelligence and Image Processing

References

[1] ZhangSJ, ToS, WangSJ, et al. . A review of surface roughness generation in ultra-precision machining. Int J Mach Tools Manuf, 2015, 91: 76-95.

[2] LamikizA, López de LacalleLN, CelayaALamikizA. Machine tool performance and precision. López de Lacalle LN, 2009Springer, LondonMachine tools for high performance machining219-260

[3] YipWS, ToS, ZhouH. Current status, challenges and opportunities of sustainable ultra-precision manufacturing. J Intell Manuf, 2021, 33: 2193-2205.

[4] Precision engineering machines market report (2028) https://www.grandviewresearch.com/industry-analysis/precision-engineering-machines-market-report. Accessed 12 May 2023

[5] NiaziA, DaiJS, BalabaniS, et al. . Product cost estimation: technique classification and methodology review. J Manuf Sci Eng, 2006, 128: 563-575.

[6] MonrealM, RodriguezCA. Influence of tool path strategy on the cycle time of high-speed milling. Comput Aided Des, 2003, 35: 395-401.

[7] ChuHY, KeD, JunY, et al. . Flexible process planning based on predictive models for machining time and energy consumption. Int J Adv Manuf Technol, 2023, 1283–41763-1780.

[8] Abdul KadirA, XuX, HämmerleE. Virtual machine tools and virtual machining—a technological review. Robotics Comput Integr Manuf, 2011, 27: 494-508.

[9] PetráčekP, FojtůP, KozlokT, et al. . Effect of CNC interpolator parameter settings on toolpath precision and quality in corner neighborhoods. Appl Sci, 2022, 12: 9496.

[10] LiuC, LiY, WangW, et al. . A feature-based method for NC machining time estimation. Robotics Comput Integr Manuf, 2013, 29: 8-14.

[11] ZhongWB, LuoXC, ChangWL, et al. . Toolpath interpolation and smoothing for computer numerical control machining of freeform surfaces: a review. Int J Autom Comput, 2019, 17: 1-16.

[12] FanW, GaoXS, YanW, et al. . Interpolation of parametric CNC machining path under confined jounce. Int J Adv Manuf Technol, 2012, 62: 719-739.

[13] TajimaS, SencerB. Accurate real-time interpolation of 5-axis tool-paths with local corner smoothing. Int J Mach Tools Manuf, 2019, 142: 1-15.

[14] TajimaS, SencerB. Global tool-path smoothing for CNC machine tools with uninterrupted acceleration. Int J Mach Tools Manuf, 2017, 121: 81-95.

[15] WardR, SencerB, JonesB, et al. . Accurate prediction of machining feedrate and cycle times considering interpolator dynamics. Int J Adv Manuf Technol, 2021, 116: 417-438.

[16] AltintasY, BrecherC, WeckM, et al. . Virtual machine tool. CIRP Ann, 2005, 54: 115-138.

[17] TangPY, LinMT, TsaiMS, et al. . Toolpath interpolation with novel corner smoothing technique. Robotics Comput Integr Manuf, 2022, 78. 102388

[18] OláhJ, AburummanN, PoppJ, et al. . Impact of Industry 4.0 on environmental sustainability. Sustainability, 2020, 12: 4674.

[19] TaoF, QiQ, LiuA, et al. . Data-driven smart manufacturing. J Manuf Syst, 2018, 48: 157-169.

[20] SolomatineD, SeeLM, AbrahartRJAbrahartRJ, SeeLM, SolomatineDP. Data-driven modelling: concepts, approaches and experiences. Practical hydroinformatics: computational intelligence and technological developments in water applications, 2008BerlinSpringer17-30.

[21] AltintasY, TulsyanS. Prediction of part machining cycle times via virtual CNC. CIRP Ann, 2015, 64: 361-364.

[22] EndoM, SencerB. Accurate prediction of machining cycle times by data-driven modelling of NC system’s interpolation dynamics. CIRP Ann, 2022, 71: 405-408.

[23] SunC, Dominguez-CaballeroJ, WardR, et al. . Machining cycle time prediction: data-driven modelling of machine tool feedrate behavior with neural networks. Robotics Comput Integr Manuf, 2022, 75. 102293

[24] KatalA, SinghNTomarR, HinaMD, ZitouniR, Ramdane-CherifA. Artificial neural network: models, applications, and challenges. Innovative trends in computational intelligence, 2022ChamSpringer International Publishing235-257.

[25] ChoiYK, BanerjeeA, LeeJW. Tool path generation for free form surfaces using Bézier curves/surfaces. Comput Ind Eng, 2007, 52: 486-501.

[26] MaQ, YuH. Artificial intelligence-enabled mode-locked fiber laser: a review. Nanomanuf Metrol, 2023, 6: 36.

Funding

State Key Laboratory of Ultra-precision Machining Technology(1-ZE0G)

RIGHTS & PERMISSIONS

Shanghai University and Periodicals Agency of Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature