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.

Geometric physically-based simulation systems for milling processes can provide the possibility to analyze and predict characteristically behaviors of a certain process. The parametrization of the simulation models is a crucial task when optimizing the quality of the simulation prediction. In order to determine tool load, process forces have to be calculated. Thus, the parametrization of the cutting force model that is mainly subject to the processed material and tool characteristics has a versatile impact on the simulation results. However, the tool state is expected to be constant within common milling simulations and therefore tool state variations like several tool wear effects are not represented. The tool state is defined through the geometric constitution of the cutting edges of the tool. This paper aims to analyze tool wear effects by re-calibrating the parameter values of the force model within the simulation system. To validate the simulation system, several milling experiments were conducted. In order to induce a fast change of the tool state within the process and to provoke high tool loads, the powder metallurgic high speed steel 1.3344 was machined. Advanced surrogate modeling techniques from the design and analysis of computer experiments (DACE) were applied to analyze the contribution of the force model parameter values. The fitting of the surrogate model is performed by means of sequential design of experiments. This allows the retrieval of sets of fitting parameter combinations for each tool state with a relatively small amount of simulation runs compared to genetic algorithms or gradients based methods. The surrogate models are exploited to analyze the behavior of the force model parameter values over the varying tool states. Approaches for further research are recommended and potential practical applications are discussed.