Answers are grounded in this paper and cite their sources.
Recent advancements in the field of physics-informed neural networks (PINNs) hold great potential for solving the tribology-related problems, and areas for their applications are systematically reviewed in this article. The tribological applications are viewed as fundamentally dependent on the variety of multiphysics phenomena, which must be taken into account when developing PINNs. Materials data, topology and surface roughness, and analytical tribometry data can be used as multiphysics input for the PINNs specialized in solving friction, lubrication, wear, wetting, heat transfer, structural and phase transitions, chemical reactions, cracking, and fretting problems. Creating multi-PINNs that synthesize the individual tribology phenomena into the complex multiagent approach is viewed as a practically important and challenging issue that is yet to be addressed.
No takes yet. Share an insight, caveat, or question.
Kokhanovskiy et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: