The development of machine tools in the last twenty years includes, among other things, the application of mechanisms with a non-linear kinematic structure as the mechanical basis of machines. This results in significant improvements in kinematic characteristics and problems related to non-linear dependencies of the accuracy of the drive elements and the realization of movement in the machine’s external coordinates. The paper presents an approach to machine tool calibration based on the original O-X glide mechanism based on the ISO 230-4 standard with the mono- and bi-directional compensation of systematic errors and adaptation to the specifics of the mechanism’s kinematics. A machine tool prototype was designed and built for the research presented in the paper. The obtained results indicate the possibility of applying the existing recommendations and standards for testing the accuracy of machine tools with the need to correct the methodology by using linear and non-linear kinematic structures in machine tools.
This paper presents research aimed at detecting and quantifying backlash in the feed motion subsystem of machine tools using positioning accuracy test results. By applying shallow neural networks, we not only estimate backlash magnitude but also analyse the impact of key parameters on its occurrence. This approach enables continuous, data-driven monitoring and prediction of backlash variation, while reducing machine tool calibration time in industrial settings. The experimental study followed ISO 230-2, using two standard motion methods while monitoring machine and ambient temperature, atmospheric pressure, and humidity. The results show how experimental parameters affect detected backlash. A feed-forward neural network predicts current backlash at specific measurement points. The results demonstrate high accuracy in backlash estimation, significantly simplifying machine calibration during maintenance and providing a foundation for real-time error compensation.
This paper presents research aimed at detecting and quantifying backlash in the feed motion subsystem of machine tools using positioning accuracy test results. By applying shallow neural networks, we not only estimate backlash magnitude but also analyse the impact of key parameters on its occurrence. This approach enables continuous, data-driven monitoring and prediction of backlash variation while reducing machine tool calibration time in industrial settings. The experimental study used two standard motion methods while monitoring machine and ambient temperature, atmospheric pressure, and humidity. The results show how experimental parameters affect detected backlash. A feed-forward neural network predicts current backlash at specific measurement points. The results demonstrate high accuracy in backlash estimation, significantly simplifying machine calibration during maintenance and providing a foundation for real-time error compensation.