A support vector regression-based method for modeling geometric errors in CNC machine tools

Zhang, Chuanjing; Liu, Huanlao; Zhou, Qunlong; Wang, Yulin

doi:10.1007/s00170-023-12212-4

Cited by 4 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Omar et al 8 considered the effects of errors such as cutting force, tool runout and position tilt to predict the three-dimensional shape of the part surface. On the other hand, for the problem of geometric error prediction of CNC machine tools, Zhang et al 9 proposed an improved hybrid grey wolf optimization algorithm to optimize the geometric error modeling scheme of the support vector regression machine. Yu et al 10 established a new comprehensive error prediction model considering the inter-layer interference caused by tool rotation profile error, which incorporates a pre-existing prediction model dealing with a variety of errors such as geometric errors of machine tool, workpiece locating errors, and spindle thermal deflection errors.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Model Based Prediction of Machining Accuracy for Milling Machine

Huang,

Wang

2024

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The accuracy of machining can be predicted during the design process of CNC machine tools, while the prediction accuracy depends on the prediction model. However, when establishing the prediction model, the coupling effect among the machine tool’s different components is always ignored for modeling efficiency, so this will lead to its reliability cannot be guaranteed. To address this problem, the model reduction theory and the lumped parameter method are used in this study to set the state-space equations of the essential structural parts. Moreover, the electro-mechanical coupling parameter equation of the servo system is transformed into a state-space equation. Then the state-space equations of the components and the servo system are coupled to establish the machine tool dynamic model. Furthermore, a theoretical model of instantaneous undeformed chip thickness is found, and according to the linear relationship between the micro-cutting force and the instantaneous undeformed chip thickness, the instantaneous cutting force model of the cylindrical milling cutter is established. Based on these, the integrated model, which considers the mechanical structure, control system and cutting force, is obtained and further used in Simulink to build the machining accuracy prediction platform, as well as the accuracy of the integrated prediction model is verified. Moreover, the prediction model established by the integrated modeling method can effectively simulate the actual machining conditions of the machine tool, and the superiority of prediction is confirmed by comparing the simulated and measured results in peripheral milling applications. The results show the error in the system response efficiency is 14.8%, while the error in position accuracy and delay characteristics is less than 10%, the error between the predicted size of the prediction model and the actual size is within 28 μm, a minimum prediction error is 7 μm.

show abstract

Section: Introductionmentioning

confidence: 99%