Digital Twin-driven Performance Modeling and Dynamic Optimization Methodology for Precision Milling Machines

doi:10.3969/j.issn.1004-132X.2026.04.012

Abstract

Abstract:

A digital twin-based dynamic multi-objective optimization method for machining processes was proposed herein. By integrating historical machining data with real-time operational data， a digital twin system was established， comprising geometric， physical， behavioral， and rule-based sub-models. This system combined an Optuna-GBR model and an IMORIME to dynamically adjust machining parameters. The cutting force fluctuations were monitored in real time by the digital twin system. When the fluctuations exceeded the adaptive threshold， a dynamic optimization process was triggered， during which a new Pareto solution set was regenerated and the optimal machining parameter combination was determined using the entropy-weighted technique for order preference by similarity to an ideal solution（TOPSIS） method. Experimental validation under actual machining conditions demonstrates that the dynamic optimization method of the digital twin system achieves a 19.99% reduction in spindle energy consumption， a 29.02% reduction in specific cutting energy， and an 11.22% reduction in machining noise. These results indicate a significant improvement in machining efficiency and a remarkable reduction in spindle energy consumption and machining noises.

Key words: digital twin, dynamic optimization, Optuna-optimized gradient boosting regression （Optuna-GBR）, improved multi-objective rime optimization algorithm （IMORIME）, adaptive threshold

摘要：

提出了一种面向机床加工过程的数字孪生动态多目标优化方法。该方法融合历史加工数据与机床实时运行数据，构建由几何模型、物理模型、行为模型和规则模型组成的数字孪生系统，并结合基于Optuna优化的梯度提高回归（Optuna-GBR）预测模型与改进的多目标雾凇优化算法（IMORIME）实现加工工艺参数的动态调整。数字孪生系统对切削力波动进行实时监测，当切削力波动超出自适应阈值时，触发动态优化过程，重新生成Pareto解集并通过熵权-逼近理想解排序法（TOPSIS）决策出最优工艺参数组合。实验验证表明，数字孪生系统的动态优化方法使主轴能耗较优化前降低19.99%，切削比能降低29.02%，加工噪声降低11.22%，显著提高加工效率，降低主轴能耗及加工噪声。

关键词: 数字孪生, 动态优化, 基于Optuna优化的梯度提高回归, 改进多目标雾凇优化算法, 自适应阈值

CLC Number:

TH17

MEI Shulong, XIE Yang, ZHANG Chaoyong, WU Jianzhao, LIU Jinfeng. Digital Twin-driven Performance Modeling and Dynamic Optimization Methodology for Precision Milling Machines[J]. China Mechanical Engineering, 2026, 37(4): 875-884.

梅术龙, 谢阳, 张超勇, 吴剑钊, 刘金锋. 精密铣削机床效能孪生模型构建及动态优化方法[J]. 中国机械工程, 2026, 37(4): 875-884.

Figures/Tables 13

Fig.1 Framework of the five-dimensional digital twin model for CNC machine tools

Fig.2 Construction of the digital twin virtual model for CNC machine tools

Fig.3 Actual and simulated spindle power values

Fig.4 Cyber-physical interaction-driven dynamic optimization workflow for machining parameters

Fig.5 Experimental setup of the milling process

Fig.6 Real-time monitoring interface of the machine tool

Fig.7 Digital twin predictive simulation interface

Fig.8 Multi-objective predicted vs. actual values comparison

Tab.1 Statistical comparison of predictive model performance

评估指标	评估对象	MAE	MBE	RMSE	R²
Optuna-GBR	E_c	177.002	$-$ 31.753	211.940	0.959
Optuna-GBR	T_SCE	4.643	0.401	7.679	0.981
Optuna-GBR	L_RMS	0.072	0.024	0.092	0.959
GBR	E_c	262.869	$-$ 40.646	315.720	0.909
GBR	T_SCE	10.418	3.254	17.919	0.950
GBR	L_RMS	0.104	0.040	0.133	0.910
XGBoost	E_c	254.580	$-$ 8.976	313.52	0.910
XGBoost	T_SCE	8.158	7.740	10.738	0.982
XGBoost	L_RMS	0.084	0.031	0.125	0.924

Tab.1 Statistical comparison of predictive model performance

评估指标	评估对象	MAE	MBE	RMSE	R²
Optuna-GBR	E_c	177.002	$-$ 31.753	211.940	0.959
Optuna-GBR	T_SCE	4.643	0.401	7.679	0.981
Optuna-GBR	L_RMS	0.072	0.024	0.092	0.959
GBR	E_c	262.869	$-$ 40.646	315.720	0.909
GBR	T_SCE	10.418	3.254	17.919	0.950
GBR	L_RMS	0.104	0.040	0.133	0.910
XGBoost	E_c	254.580	$-$ 8.976	313.52	0.910
XGBoost	T_SCE	8.158	7.740	10.738	0.982
XGBoost	L_RMS	0.084	0.031	0.125	0.924

Fig.9 Hypervolume （HV） and inverted generational distance （IGD） box plots

Fig.10 Real-time cutting force and error percentage curves

Fig.11 Time-evolving Pareto front visualization in dynamic optimization

Tab.2 Pre- vs post-optimization comparison

参数	实验值	动态优化前	动态优化后
n/（r·min $- 1$ ）	7000.00	5924.32	5219.51
v_f/（mm·min $- 1$ ）	420.00	402.20	391.61
a_p/mm	0.60	0.57	0.66
a_e/mm	0.70	0.77	0.68
E_c/J	3324.17	2942.22	2659.50
T_SEC/（J·mm $- 3$ ）	32.98	26.98	23.41
L_RMS	1.87	1.70	1.66

Tab.2 Pre- vs post-optimization comparison

参数	实验值	动态优化前	动态优化后
n/（r·min $- 1$ ）	7000.00	5924.32	5219.51
v_f/（mm·min $- 1$ ）	420.00	402.20	391.61
a_p/mm	0.60	0.57	0.66
a_e/mm	0.70	0.77	0.68
E_c/J	3324.17	2942.22	2659.50
T_SEC/（J·mm $- 3$ ）	32.98	26.98	23.41
L_RMS	1.87	1.70	1.66

References 17

[1]	XIE Y， DAI Y， ZHANG C， LIU J. An Integration Model Enabled Deep Learning for Energy Prediction of Machine Tools［J］. Journal of Cleaner Production， 2025， 495： 145075.
[2]	XIE Y， LIAN K， LIU Q， et al. Digital Twin for Cutting Tool： Modeling， Application and Service Strategy［J］. Journal of Manufacturing Systems， 2021， 58： 305-312.
[3]	ZHANG L， LIU J， ZHUANG C. Digital Twin Modeling Enabled Machine Tool Intelligence： a Review［J］. Chinese Journal of Mechanical Engineering， 2024， 37（1）： 47.
[4]	赵希坤，李聪波，杨勇，等. 数据-机理混合驱动下考虑刀具柔性的柔性加工工艺参数能效优化方法［J］. 机械工程学报， 2024， 60（7）： 236-248.
	ZHAO Xikun， LI Congbo， YANG Yong， et al. A Data and Model Hybrid Driven Cutting Parameter Energy-efficiency Optimization Method for Flexible Machining Process Considering Cutting Tool Flexibility［J］. Journal of Mechanical Engineering， 2024， 60（7）： 236-248.
[5]	鄢威，王欣怡，张华，等. 考虑切削能耗和表面质量的碳纤维增强树脂基复合材料加工工艺参数优化决策［J］. 中国机械工程，2024，35（10）：1834-1844.
	YAN Wei， WANG Xin， ZHANG Hua， et al. Optimization Decision of CFRP Processing Parameters Considering Cutting Energy Consumption and Surface Quality［J］. China Mechanical Engineering， forthcoming，2024，35（10）：1834-1844.
[6]	JIA S， WANG S， LI S， et al. Integrated Multi-objective Optimization of Rough and Finish Cutting Parameters in Plane Milling for Sustainable Machining Considering Efficiency， Energy， and Quality［J］. Journal of Cleaner Production， 2024， 471： 143406.
[7]	ZHAO X， LI C， TANG Y， et al. Reinforcement Learning-based Cutting Parameter Dynamic Decision Method Considering Tool Wear for a Turning Machining Process［J］. International Journal of Precision Engineering and Manufacturing-Green Technology， 2024， 11： 1053-1070.
[8]	易茜，李聪波，潘建，等. 薄板类零件加工精度可靠性分析及工艺参数优化［J］. 中国机械工程， 2022， 33（11）： 1269-1277.
	YI Qian， LI Congbo， PAN Jian， et al. Reliability Analysis of Machining Accuracy and Processing Parameter Optimization for Thin-plate Parts［J］. China Mechanical Engineering， 2022， 33（11）： 1269-1277.
[9]	LIU Z， LANG Z Q， GUI Y， et al. Digital Twin-based Anomaly Detection for Real-time Tool Condition Monitoring in Machining［J］. Journal of Manufacturing Systems， 2024， 75： 163-173.
[10]	李聪波，孙鑫，侯晓博，等. 数字孪生驱动的数控铣削刀具磨损在线监测方法［J］. 中国机械工程， 2022， 33（1）： 78-87.
	LI Congbo， SUN Xin， HOU Xiaobo， et al. Online Monitoring Method for NC Milling Tool Wear by Digital Twin-driven［J］. China Mechanical Engineering， 2022， 33（1）： 78-87.
[11]	巩超光，胡天亮，叶瑛歆. 基于数字孪生的铣削参数动态多目标优化策略［J］. 计算机集成制造系统， 2021， 27（2）： 478-486.
	GONG Chaoguang， HU Tianliang， YE Yinxin. Dynamic Multi-objective Optimization Strategy of Milling Parameters Based on Digital Twin［J］. Computer Integrated Manufacturing Systems， 2021， 27（2）： 478-486.
[12]	陶飞，刘蔚然，张萌，等. 数字孪生五维模型及十大领域应用［J］. 计算机集成制造系统， 2019， 25（1）： 1-18.
	TAO Fei， LIU Weiran， ZHANG Meng， et al. Five-dimension Digital Twin Model and Its Ten Applications ［J］. Computer Integrated Manufacturing Systems， 2019， 25（1）： 1-18.
[13]	ZUO Y， YOU H， ZOU X， et al. Digital Twin Enhanced Quality Prediction Method of Powder Compaction Process［J］. Robotics and Computer-Integrated Manufacturing， 2024， 89： 102762.
[14]	谢阳，戴逸群，张超勇，等. 融合集成模型与深度学习的机床能耗识别与预测方法［J］. 中国机械工程， 2023， 34（24）： 2963-2974.
	XIE Yang， DAI Yiqun， ZHANG Chaoyong， et al. A Method for Identifying and Predicting Energy Consumption of Machine Tools by Combining Integrated Models and Deep Learning［J］. China Mechanical Engineering， 2023， 34（24）： 2963-2974.
[15]	ZHAO J， LI L， NIE H， et al. Multi-objective Integrated Optimization of Tool Geometry Angles and Cutting Parameters for Machining Time and Energy Consumption in NC Milling［J］. The International Journal of Advanced Manufacturing Technology， 2021， 117（5）： 1427-1444.
[16]	LI J， WANG Y， LIU K， et al. Tough-brittle Transition Mechanism and Specific Cutting Energy Analysis During Cryogenic Machining of Ti–6Al–4V Alloy［J］. Journal of Cleaner Production， 2023， 383： 135533.
[17]	MEI S， XIE Y， LIU J， et al. Physics-based Modeling and Intelligent Optimal Decision Method for Digital Twin System towards Sustainable CNC Equipment ［J］. Robotics and Computer-Integrated Manufacturing， 2025， 95： 103028.