Anzeige
Erschienen in:
2021 | OriginalPaper | Buchkapitel
Development of a Temperature Strategy for Motor Spindles with Synchronous Reluctance Drive Using Multiple Linear Regression and Neural Network
verfasst von : M. Weber, F. He, M. Weigold, E. Abele
Erschienen in: Production at the leading edge of technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
One central aspect of future high speed machining is the knowledge of the thermal behaviour of the machine tool and its motor spindle. A new temperature control for motor spindles with energy efficient synchronous reluctance drive is developed. In the first instance a finite element method model (FEM) is set up. This FEM aims to analyse the use case of nearly constant bearing temperatures within a defined range throughout the machining operation. By means of design of experiments (DOE), selected operating points of the speed-torque-characteristics are simulated with FEM considering different cooling parameters such as volume flow and inlet temperature. Machine learning algorithms are used to model the input-output-relationship in order to reduce the complex thermal motor spindle FEM. The applied algorithms are multiple linear regression and artificial neural network. The concept of temperature strategy, the FEM simulation results and the thermal models using machine learning algorithms are presented.