A physics-informed generative framework produces plausible four- and five-bladed propeller geometries conditioned on thrust, power, and diameter targets, then refines them with fast neural surrogates and evolutionary optimization.
Evolutionary optimisation for reduc- tionofthelow-frequencydiscrete-spectrumforceofmarine propellerbasedonadata-drivensurrogatemodel
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AI-Driven Performance-to-Design Generation and Optimization of Marine Propellers
A physics-informed generative framework produces plausible four- and five-bladed propeller geometries conditioned on thrust, power, and diameter targets, then refines them with fast neural surrogates and evolutionary optimization.