As a key pressure-bearing component of a cubic press, the hinge-beam structure is subjected to a multi-stage ultra-high-pressure synthesis process, including pressure ramp-up and pressure holding. The lug region is prone to fatigue fracture, which makes the requirements for larger-scale cubic presses difficult to satisfy. Real-time monitoring of the hinge-beam structure can be achieved through the rapid acquisition of stress and strain under different operating conditions based on real-time simulation. A method integrating a finite element simulation model of the hinge beam, a lightweight digital twin model, and a global surrogate model was established, and a real-time simulation method for the hinge-beam structure of a cubic press was proposed. Firstly, a finite element simulation of the hinge-beam structure was performed, and a mesh simplification algorithm based on edge collapse and an improved quadric error metric was adopted to generate a lightweight virtual simulation model. Then, a global surrogate model based on the random forest (RF) algorithm was constructed to achieve fast prediction and high-accuracy estimation of the structural state. Finally, a digital twin platform for real-time state assessment of the hinge-beam structure was developed. Experimental results demonstrate that a coefficient of determination of 0.98 is achieved by the surrogate model, and the average evaluation time is approximately 48 ms per prediction, indicating a balance between real-time performance and computational accuracy.
NIE Fu-quan, WANG Kai, LI Hao, XIE Gui-zhong, WANG Liang-wen, PANG Wen-long, WANG Shu-guang.
Real-time Simulation Method for Hinge Beam Structure of Cubic Press Based on Digital Twin[J].
Science Technology and Engineering, 2026, 26(29): 12604-12617 DOI:10.12404/j.issn.1671-1815.2507733
XieG, ZhangS, LiH, et al. A double-layer optimization method for forging process parameters of hinge beam structure and size of intermediate billet[J]. Journal of Mechanical Science and Technology, 2023, 37(10): 5307-5319.
LiuJianshe, WangShuguang, WangLiangwen, et al. A review on development path of super-hard material synthetic equipment and technology in China[J]. Superhard Material Engineering, 2024, 36(1): 41-49.
YuYannan, QiQisong, DongQing, et al. Finite element analysis and optimal design of bridge crane under multiple working conditions[J]. Science Technology and Engineering, 2021, 21(31): 13334-13341.
[6]
LeivaN G, HerreraR A, MassoneL M, et al. Numerical modeling of beam plastic hinges in steel moment resisting frames including local buckling and stiffness/strength degradation[J]. Structures, 2024, 69: 11.
[7]
ShangJ, SunX, LiuT, et al. An efficient structural optimization method for the hinge beam of a cubic press[J]. Machines, 2023, 11(5): 503.
WangLiangwen, LiuFeifei, WangShuguang, et al. Multi-parameter optimization of forging die structure for hinge beam of large cavity hexa hedral top diamond press[J]. Journal of Plasticity Engineering, 2024, 31(5): 94-105.
[10]
XieG, ZhangS, WangL, et al. Lightweight design of hinge beam based on Kriging agent model[J]. Journal of Mechanical Science and Technology, 2022, 36(7): 3585-3595.
[11]
SunX, LiuT, JiaJ, et al. Multi-objective optimization design of the hinge sleeve of cubic based on Kriging[J]. Science Progress, 2023, 106(3): 00368504231203108.
[12]
SongX G, LaiX N, HeX W, et al. Key technologies of shape-performance integrated digital twin for major equipment[J]. Journal of Mechanical Engineering, 2022, 58(10): 298-325.
[13]
GrievesM. Intelligent digital twins and the development and management of complex systems[J]. Digital Twin, 2024, 1(1): 8.
[14]
ZhangC, ShuJ, ZhangH, et al. Estimation of load-carrying capacity of cracked RC beams using 3D digital twin model integrated with point clouds and images[J]. Engineering Structures, 2024, 310: 118126.
[15]
HinchyE, CarcagnoC, O'dowdN P, et al. Using finite element analysis to develop a digital twin of a manufacturing bending operation[J]. Procedia CIRP, 2020, 93: 568-574.
[16]
TanY, ZhangY, LiuL, et al. Spindle system digital twin for dynamics characteristic monitoring[J]. China Mechanical Engineering, 2020, 31(18): 2231.
[17]
TripathiV, CaizzoneS. Virtual validation of in-flight GNSS signal reception during jamming for aeronautics applications[J]. Aerospace, 2024, 11(3): 204.
WangHaoqi, LiXupeng, LiHao, et al. Rapid modeling method of digital twin workshop based on dynamic and static fusion of human-machine-environment[J]. Aeronautical Manufacturing Technology, 2024, 67(11): 14-22.
LiHao, XingZhiyuan, LiLinli, et al. Cloud-edge-device system architecture and key technologies of industrial digital twin system based on multi-agent[J]. Computer Integrated Manufacturing Systems, 2024, 30(11): 3755-3770.
XueXiangdong, HuGuangzhong, WangPing, et al. Prediction of residual life of high temperature and high pressure vessels based on digital twin[J]. Science Technology and Engineering, 2024, 24(15): 6320-6328.
TaoFei, LiuWeiran, ZhangMeng, et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1): 1-18.
HeWenbin, YaoGangsheng, WangShuguang, et al. Optimization of hinge beam of cylinder beam integrated cubic press based on response surface method[J]. Diamond & Abrasives Engineering, 2023, 43(4): 523-530.
[28]
LiuH T, GillespieM, ChislettB, et al. Surface simplification using intrinsic error metrics[J]. ACM Transactions on Graphics, 2023, 42(4): 1-17.
ZhangYun, WangShuying, ZhengQing, et al. Lightweight algorithm for 3D mesh models preserving detailed geometric features[J]. Computer Applications, 2023, 43(4): 1226-1232.
[31]
LiZ, ZhaoZ, GaoW, et al. An algorithm for simplifying 3D building models with consideration for detailed features and topological structure[J]. ISPRS International Journal of Geo-Information, 2024, 13(10): 356.
XiaoXingyu. Modeling and scene simulation of digital twin system of photovoltaic cell production line based on Unity3D[D]. Xi'an: Xidian University, 2024.
[34]
ChaiB X, EisenbartB, NikzadM, et al. Application of KNN and ANN metamodeling for RTM filling process prediction[J]. Materials, 2023, 16(18): 6115.
[35]
DengY, JiangW, LingZ, et al. Revealing the driving factors of urban wetland park cooling effects using random forest regression and SHAP algorithm[J]. Sustainable Cities and Society, 2025, 120: 106151.
LiuHao, XiaoYunlong, XiaoYanshan, et al. Automated synchronization technology of digital twin of nuclear power steam system[J]. Science Technology and Engineering, 2024, 24(29): 12576-12583.
[38]
CuiH, XiangB, MoS, et al. Real-time state evaluation system of antenna structures in radio telescopes based on a digital twin[J]. Applied Sciences, 2025, 15(6): 3325.
[39]
RasintaI. Identification of tomato ripeness levels (Lycopersicum esculentum Mill) using android-based digital image processing[C]// IOP Conference Series: Earth and Environmental Science. Bristol: IOP Publishing, 2023: 012003.