Search

In order to analyze various process characteristics, grinding simulations can be used, which need accurate models of the tool and the individual grains. For this purpose, grinding tools can be digitized. To identify characteristic grains from a large number of measurements, each individual grain has to be analyzed and separated from the bond manually. Therefore, a deep learning-based methodology was developed to achieve a high segmentation accuracy of the grain boundaries efficiently. Additionally, a data augmentation approach was investigated to limit the data necessary for learning. The model transferability was quantified by analyzing different states of tool wear.

In diesem Beitrag wird ein neuer Ansatz zum Erstellen von Maschinenprogrammen zur mikrofrästechnischen Oberflächenstrukturierung vorgestellt und die Anwendung der Prozesskette für ein komplexes, industrielles Verzahnungswerkzeug beschrieben. Durch die Reduzierung des Berechnungsaufwandes in der CAD/CAM (Computer-aided Design & Manufacturing)-Umgebung können die Limitierungen konventioneller Softwarelösungen umgangen und Bearbeitungsprogramme für komplexe Strukturierungsaufgaben effizient erstellt werden. A new method for generating machine programs for micromilling surface structuring is presented, and the application of the process chain to a complex, industrial gearing die is described. By reducing the computational effort in the CAD/CAM (Computer-aided Design & Manufacturing) environment, the problems of conventional software solutions can be avoided and complex machining programs can be created.

One of the major advantages of micromachining is the high achievable surface quality at highly flexible capabilities in terms of the machining of workpieces with complex geometric properties. Unfortunately, finishing operations often result in extensive process times due to the dependency of the resulting surface topography on the cutting parameter, e.g., the feed per tooth, fz. To overcome this dependency, special tool shapes, called wipers, have proven themselves in the field of turning. This paper presents the transfer of such tool shapes to solid carbide milling tools for micromachining. In this context, a material removal simulation (MRS) was used to investigate promising wiper geometries for micro end mills (d = 1 mm). Through experimental validation of the results, the surface topography, the resulting process forces, and tendencies in the residual stress state were investigated, machining the hot work tool steel (AISI H11). The surface-related results show a high agreement and thus the potential of MRS for tool development. Deviations from the experimental data for large wipers could be attributed to the non-modeled tool deflections, friction, and plastic deformations. Furthermore, a slight geometry-dependent increase in cutting forces and compressive stresses were observed, while a significant reduction in roughness up to 84% and favorable topography conditions were achieved by adjusting wipers and cutting parameters.

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.