Surface textured sliding tribological contacts
Data-driven optimization of surface textures for sliding tribological contacts
Motivation
In recent years, the high potential of surface texture technology in reducing friction, wear and fatigue of highly loaded tribological contacts, like sliding or rolling element bearings, has been demonstrated. Especially in operation points near the transition between hydrodynamic and mixed-lubrication conditions, textured systems show a superior tribological performance. However, the texture design parameters, e.g. the texture’s geometry and positioning for a given system, lead to a large amount of degrees of freedom, which makes the optimization of surface textured tribological contacts a challenging task. Artificial Intelligence (AI) has gained a significant amount of attention due to its high adaptability and time-efficiency for above-mentioned multi-variate optimization problems. However, to improve the performance of an AI approach, a large amount of data must be available. Experimental data often provides limited information and is accompanied with high costs. Therefore, this project will use the domain knowledge of physics-based numerical models as a cost-efficient alternative. Further emphasis will be put on the input parameter restrictions determined by the manufacturing procedure. Optimization targets can be low friction and wear as well as an efficient texturing procedure.
Research objectives
Development of an AI model to predict and optimize surface textured tribological contacts with the subsequent sub-models
- Physics-based numerical models to predict the EHL and wear behavior data of surface textured bearings under mixed-friction conditions
- AI model to time-efficiently predict tribological performance of surface textured bearings under mixed-friction conditions
- AI model to optimize surface textures for fixed and free design parameters robustly
Promoted by
China Scholarship Council-RWTH Aachen University Joint Program
Project sponsor
China Scholarship Council