h1

h2

h3

h4

h5
h6
%0 Thesis
%A Lee, Seong-Ryeol
%T Machine learning assisted EHL simulation for enhancing tribological performance of hydraulic axial piston pumps
%V 118
%I RWTH Aachen University
%V Dissertation
%C Düren
%M RWTH-2025-06526
%@ 978-3-8191-0082-6
%B Reihe Fluidtechnik. D
%P 1 Online-Ressource : Illustrationen
%D 2025
%Z Druckausgabe: 2025. - Auch veröffentlicht auf dem Publikationsserver der RWTH Aachen University
%Z Dissertation, RWTH Aachen University, 2025
%X Machine Learning (ML) algorithms, situated within the realm of Artificial Intelligence (AI), are being investigated across diverse branches of engineering. The prime goal of AI application is to increase system performance through optimization procedures. Also in the hydraulic field, this AI-assisted engineering has attracted significant interest and attention. So far, AI has been widely used in various detailed areas such as system configuration, system optimization, condition monitoring, and component design. The aim of this thesis is to develop a conceptualization of the design process for hydraulic axial piston pumps using ML-assisted elasto-hydrodynamic lubrication (EHL) simulations. As an application example, a slipper in a high-speed axial piston pump is selected for validation in electro-hydraulic actuators (EHA). For this purpose, the pump configuration and operating principle, as well as the tribological performance at the slipper-swash plate contact, are explained. The EHL simulation is described in detail, including the theoretical background, simulation configuration, calculation process, and meshing technique. The configuration of a test bench for measuring the tribological performance of the slipper to validate the EHL simulation is explained, and a cross-validation of the measurement data and simulation results is performed. In the second part of the work, the application of the Bayesian optimization method to the simulation of component design is presented. Design parameters used in the design of a conventional slipper are selected as design variables for the optimization problem, and tribological performance is proposed as the objective function. Furthermore, an application of the clustering method using k-means algorithm is presented for detailed and efficient classification of the operating scenarios of components. By considering the expected real operating conditions, the optimal component design within set design variables is derived to meet the operating requirements.
%F PUB:(DE-HGF)11 ; PUB:(DE-HGF)3
%9 Dissertation / PhD ThesisBook
%R 10.2370/9783819100826
%U https://publications.rwth-aachen.de/record/1015687