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

doi:10.1007/s40436-024-00543-8

Advances in Manufacturing ›› 2025, Vol. 13 ›› Issue (4): 831-846.doi: 10.1007/s40436-024-00543-8

• • 上一篇

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

Tong Zhu¹, Carman K. M. Lee², Sandy Suet To²

1. Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, HK SAR, People's Republic of China;
2. State Key Laboratory of Ultra-precision Machining Technology, Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, People's Republic of China

收稿日期:2023-11-28 修回日期:2024-02-23 发布日期:2025-12-06
通讯作者: Carman K. M. Lee Email:E-mail:ckm.lee@polyu.edu.hk E-mail:ckm.lee@polyu.edu.hk
作者简介:Tong Zhu is PhD candidate of Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University. Her research area is to integrate machine learning and digital twin approach for ultra-precision machining processes. She obtained Champion Award in the “CA Paper Award Competition (Postgraduate level) 2022/2023” organized by the Hong Kong Institution of Engineers (HKIE) – Control, Automation and Instrumentation Division (CAD) and co-organized by the Institute of Measurement and Control.
Carman K. M. Lee is currently an associate professor at Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong. She is the program leader of the Hons (BSc) Enterprise Engineering with Management. Her main research areas include logistics and supply chain management, industrial internet of things (IIoT), wireless sensor and actuator networks (WSAN), cloud computing and big data analytics. Dr Lee also serves as the Lab-in-Charge of PolyU’s Cyber-Physical Systems Laboratory.
Sandy Suet To is a professor of Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, associate director of State Key Laboratory of Ultra-precision Machining Technology and Advanced Optics Manufacturing Centre. She is an active researcher focusing on ultraprecision machining and materials science. Her research interests include Ultra-precision Machining, advanced optics manufacturing technology, ultraprecision machining of micro/ nano-structure and effect on materials. She has published 3 research books, more than 250 international SCI referred journal papers and over 150 international conference papers, as well as obtained more than 20 patents in China and USA.
基金资助:
This study was supported by the State Key Laboratory of Ultra-precision Machining Technology (The Hong Kong Polytechnic University).

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

Tong Zhu¹, Carman K. M. Lee², Sandy Suet To²

1. Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, HK SAR, People's Republic of China;
2. State Key Laboratory of Ultra-precision Machining Technology, Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, People's Republic of China

Received:2023-11-28 Revised:2024-02-23 Published:2025-12-06
Contact: Carman K. M. Lee Email:E-mail:ckm.lee@polyu.edu.hk E-mail:ckm.lee@polyu.edu.hk
Supported by:
This study was supported by the State Key Laboratory of Ultra-precision Machining Technology (The Hong Kong Polytechnic University).

摘要/Abstract

摘要： 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.

The full text can be downloaded at https://doi.org/10.1007/s40436-024-00543-8

关键词: Data-driven model, Ultra-precision machining (UPM), Machining cycle time, Interpolation, Neural networks

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.

The full text can be downloaded at https://doi.org/10.1007/s40436-024-00543-8

Key words: Data-driven model, Ultra-precision machining (UPM), Machining cycle time, Interpolation, Neural networks

Tong Zhu, Carman K. M. Lee, Sandy Suet To. Data-driven model for predicting machining cycle time in ultra-precision machining[J]. Advances in Manufacturing, 2025, 13(4): 831-846.

参考文献

[1] Zhang SJ, To S, Wang SJ et al (2015) A review of surface roughness generation in ultra-precision machining. Int J Mach Tools Manuf 91:76-95
[2] Lamikiz A, López de Lacalle LN, Celaya A (2009) Machine tool performance and precision. In: Lamikiz A (eds), Machine tools for high performance machining, Springer, London, pp 219-260
[3] Yip WS, To S, Zhou H (2021) Current status, challenges and opportunities of sustainable ultra-precision manufacturing. J Intell Manuf 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] Niazi A, Dai JS, Balabani S et al (2006) Product cost estimation: technique classification and methodology review. J Manuf Sci Eng 128:563-575
[6] Monreal M, Rodriguez CA (2003) Influence of tool path strategy on the cycle time of high-speed milling. Comput Aided Des 35:395-401
[7] Chu HY, Ke D, Jun Y et al (2023) Flexible process planning based on predictive models for machining time and energy consumption. Int J Adv Manuf Technol 128(3/4):1763-1780
[8] Abdul Kadir A, Xu X, H?mmerle E (2011) Virtual machine tools and virtual machining—a technological review. Robotics Comput Integr Manuf 27:494-508
[9] Petrá?ek P, Fojt? P, Kozlok T et al (2022) Effect of CNC interpolator parameter settings on toolpath precision and quality in corner neighborhoods. Appl Sci 12:9496. https://doi.org/10.3390/app12199496
[10] Liu C, Li Y, Wang W et al (2013) A feature-based method for NC machining time estimation. Robotics Comput Integr Manuf 29:8-14
[11] Zhong WB, Luo XC, Chang WL et al (2019) Toolpath interpolation and smoothing for computer numerical control machining of freeform surfaces: a review. Int J Autom Comput 17:1-16
[12] Fan W, Gao XS, Yan W et al (2012) Interpolation of parametric CNC machining path under confined jounce. Int J Adv Manuf Technol 62:719-739
[13] Tajima S, Sencer B (2019) Accurate real-time interpolation of 5-axis tool-paths with local corner smoothing. Int J Mach Tools Manuf 142:1-15
[14] Tajima S, Sencer B (2017) Global tool-path smoothing for CNC machine tools with uninterrupted acceleration. Int J Mach Tools Manuf 121:81-95
[15] Ward R, Sencer B, Jones B et al (2021) Accurate prediction of machining feedrate and cycle times considering interpolator dynamics. Int J Adv Manuf Technol 116:417-438
[16] Altintas Y, Brecher C, Weck M et al (2005) Virtual machine tool. CIRP Ann 54:115-138
[17] Tang PY, Lin MT, Tsai MS et al (2022) Toolpath interpolation with novel corner smoothing technique. Robotics Comput Integr Manuf 78:102388. https://doi.org/10.1016/j.rcim.2022.102388
[18] Oláh J, Aburumman N, Popp J et al (2020) Impact of Industry 4.0 on environmental sustainability. Sustainability 12:4674. https://doi.org/10.3390/su12114674
[19] Tao F, Qi Q, Liu A et al (2018) Data-driven smart manufacturing. J Manuf Syst 48:157-169
[20] Solomatine D, See LM, Abrahart RJ (2008) Data-driven modelling: concepts, approaches and experiences. In: Abrahart RJ, See LM, Solomatine DP (eds) Practical hydroinformatics: computational intelligence and technological developments in water applications, Springer, Berlin, pp 17-30
[21] Altintas Y, Tulsyan S (2015) Prediction of part machining cycle times via virtual CNC. CIRP Ann 64:361-364
[22] Endo M, Sencer B (2022) Accurate prediction of machining cycle times by data-driven modelling of NC system’s interpolation dynamics. CIRP Ann 71:405-408
[23] Sun C, Dominguez-Caballero J, Ward R et al (2022) Machining cycle time prediction: data-driven modelling of machine tool feedrate behavior with neural networks. Robotics Comput Integr Manuf 75:102293. https://doi.org/10.1016/j.rcim.2021.102293
[24] Katal A, Singh N (2022) Artificial neural network: models, applications, and challenges. In: Tomar R, Hina MD, Zitouni R et al (eds) Innovative trends in computational intelligence, Springer International Publishing, Cham, pp 235-257
[25] Choi YK, Banerjee A, Lee JW (2007) Tool path generation for free form surfaces using Bézier curves/surfaces. Comput Ind Eng 52:486-501
[26] Ma Q, Yu H (2023) Artificial intelligence-enabled mode-locked fiber laser: a review. Nanomanuf Metrol 6:36. https://doi.org/10.1007/s41871-023-00216-3

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

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	Zhong-Jie Yue, Qiu-Ren Chen, Zu-Guo Bao, Li Huang, Guo-Bi Tan, Ze-Hong Hou, Mu-Shi Li, Shi-Yao Huang, Hai-Long Zhao, Jing-Yu Kong, Jia Wang, Qing Liu. Improving RSW nugget diameter prediction method: unleashing the power of multi-fidelity neural networks and transfer learning[J]. Advances in Manufacturing, 2024, 12(3): 409-427.
[2]	Jon Martin Fordal, Per Schj?lberg, Hallvard Helgetun, Tor ?istein Skjermo, Yi Wang, Chen Wang. Application of sensor data based predictive maintenance and artificial neural networks to enable Industry 4.0[J]. Advances in Manufacturing, 2023, 11(2): 248-263.
[3]	Annamaria Gisario, Mehrshad Mehrpouya, Atabak Rahimzadeh, Andrea De Bartolomeis, Massimiliano Barletta. Prediction model for determining the optimum operational parameters in laser forming of fiber-reinforced composites[J]. Advances in Manufacturing, 2020, 8(2): 242-251.