The thermo-elastic tool center point (TCP) error has been an ongoing research focus, due to its large effect on the workpiece quality. Existing models to compute the thermo-elastic TCP error already perform quite well regarding the accuracy and speed of computation. However, the models are often time consuming in their parameterization, expensive to apply or are error-prone due to the used model inputs. The work presented in this paper addresses these issues by introducing the encoder difference as model input. Since the encoder difference easy and inexpensive to measure, it yields a high potential for industrial use. Therefore, in this paper, the correlation between the encoder difference and the thermo-elastic TCP error is investigated. Since the physical relationship between the encoder difference and the thermo-elastic TCP error is complex, it is necessary to use an artificial neural network to compute the resulting TCP error. Due to the variety of artificial neural network (ANN) types, with different capabilities, a range of different networks is tested regarding their capability to compute the thermo-elastic TCP error. To conclude the paper, a method to parametrize such models is derived from the gathered results.
New approaches, using machine learning to model the thermo-elastic machine tool error, often rely on machine internal data, like axis speed or axis position as input data, which have a delayed relation to the thermo-elastic error. Since there is no direct relation to the thermo-elastic error, this can lead to an increased computation inaccuracy of the model or the need for expensive sensor equipment for additional input data. The encoder difference is easy to obtain and has a direct relationship with the thermo-elastic error and therefore has a high potential to improve the accuracy thermo-elastic error models. This paper first investigates causes of the encoder difference and its relationship with the thermo-elastic error. Afterwards, the model is presented, which uses the encoder difference to compute the thermo-elastic error. Due to the complexity of the relationship, it is necessary, to use a machine learning approach for this. To conclude, the potential of the encoder difference as an input of the model is evaluated.
Die Nachfrage nach präziseren Werkzeugmaschinen steigt kontinuierlich. Aus diesem Grund müssen thermo-elastische Fehlerkompensationsmethoden unter thermischen Echtzeitbedingungen genauer werden. Die korrekte Parametrierung eines modellbasierten Korrekturansatzes für die Kompensation thermo-elastischer Maschinenfehler hat einen maßgeblichen Einfluss auf die Modellgenauigkeit. Insbesondere für die Langzeitkompensation der Maschinenfehler benötigt das Modell eine hohe Anpassungsfähigkeit aufgrund variierender Lasten. In diesem Beitrag wird eine Simulationsmodellarchitektur vorgestellt, die ein FEM-basiertes thermo-elastisches White-Box-Modell der Werkzeugmaschine mit Temperaturmessungen der Maschinenstruktur kombiniert. Die Messdaten der Temperatursensoren werden für eine prozessparallele Anpassung thermischer Modellparameter genutzt, um die Genauigkeit der Kompensationsmethode zu steigern.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.