.png){kind=icon}
.png){kind=icon}
Return
Research on data-driven and model-driven methods for compensating machine tool feed system transient errors
.png){kind=icon}
PRE
AI
DOI：10.1088/1361-6501/ae01c9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
During the operation of the machine tool feed system, transient errors arise from factors such as system vibration, inertia, transmission chain stiffness, and friction, significantly affecting positioning accuracy. Therefore, this study proposes a transient error compensation method for the machine tool feed system based on data-driven and model-driven approaches. This study employs screw theory to develop the machine tool error model and proposes a system-oriented error compensation architecture to facilitate interaction and feedback among the models. A multi-source sensor data acquisition scheme is established, along with a data-driven multi-source data model to obtain comprehensive operational data. Based on the model-driven architecture, a transient error prediction model for the mechanical subsystem of the feed system is developed to enable transient error prediction for the complex feed system. The maximum prediction error is 6.2%. An experimental platform for transient error compensation of the machine tool feed system, based on data-driven and model-driven approaches, has been established. The results demonstrate that the transient error of the machine tool feed system can be reduced by 71.96%, significantly improving motion accuracy and achieving transient error compensation.
Journal
IF:
3.4
Papers:
2.6K
Citations:
2.3W