Learning-Based Prediction of Pose-Dependent Dynamics

Abstract

The constantly increasing demand for both, higher production output and more complex product geometries, which can only be achieved using five-axis milling processes, requires elaborated analysis approaches to optimize the regarded process. This is especially necessary when the used tool is susceptible to vibrations, which can deteriorate the quality of the machined workpiece surface. The prediction of tool vibrations based on the used NC path and process configuration can be achieved by, e.g., applying geometric physically-based process simulation systems prior to the machining process. However, recent research showed that the dynamic behavior of the system, consisting of the machine tool, the spindle, and the milling tool, can change significantly when using different inclination angles to realize certain machined workpiece shapes. Intermediate dynamic properties have to be interpolated based on measurements due to the impracticality of measuring the frequency response functions for each position and inclination angle that are used along the NC path. This paper presents a learning-based approach to predict the frequency response function for a given pose of the tool center point.

Minimisation of Pose-Dependent Regenerative Vibrations for 5-Axis Milling Operations

“…In order to keep the experimental effort for the parameterisation of the dynamics model as low as possible, it is not reasonable to determine the FRF of the machine tool experimentally for every possible position and pose in the workspace. Therefore, linear interpolation methods [16,17] as well as a machine learning approach [17] can be used in order to calculate FRFs at non-measured axis positions or tool poses, respectively. For the simulation-based optimisation of milling processes, several approaches exist which can be used to influence the manufacturing process in a positive way, e.g., the optimisation can be conducted by modifying an already existing NC path [4,18], by adapting process parameters [19][20][21], or by generating a new optimised NC path [22] or milling strategy [12].…”