TY - JOUR
T1 - A machine learning approach for propeller design and optimization
T2 - Part II
AU - Doijode, Pranav Sumanth
AU - Hickel, Stefan
AU - van Terwisga, Tom
AU - Visser, Klaas
PY - 2022
Y1 - 2022
N2 - We propose and analyse an optimization method that uses a machine learning approach to solve multi-objective, constrained propeller optimization problems. The method uses an online learning strategy where explainable supervised classifiers learn the location of the Pareto front and advise search strategies. The classifiers are trained with orthogonal features that capture geometric variation in radial distribution of pitch, skew, camber and chordlength. Based on orthogonal features, the classifiers predict whether or not a design lies on the Pareto front. If the design is predicted to lie on the Pareto front, the method verifies this with an evaluation. If the design is predicted to not lie on the Pareto front with a high confidence level, then the design is ignored. This skipped evaluation reduces the computational effort of optimization. The method is demonstrated on a cavitating, unsteady flow case of the Wageningen B-4 70 propeller with P/D = 1.0 operating in the Seiun-Maru wake. Compared to the classical Non-dominated Sorting Genetic Algorithm — III (NSGA-III) the optimization method is able to reduce 30% of evaluations per generation while reproducing a comparable Pareto front. Trade-offs between suction side, pressure side, tip-vortex cavitation and efficiency are identified from the Pareto front. The non-elitist NSGA-III search algorithm in conjunction with the explainable supervised classifiers also find very diverse solutions. Among the solutions, a design with no pressure side cavitation, low suction side cavitation and reasonable tip-vortex cavitation is found.
AB - We propose and analyse an optimization method that uses a machine learning approach to solve multi-objective, constrained propeller optimization problems. The method uses an online learning strategy where explainable supervised classifiers learn the location of the Pareto front and advise search strategies. The classifiers are trained with orthogonal features that capture geometric variation in radial distribution of pitch, skew, camber and chordlength. Based on orthogonal features, the classifiers predict whether or not a design lies on the Pareto front. If the design is predicted to lie on the Pareto front, the method verifies this with an evaluation. If the design is predicted to not lie on the Pareto front with a high confidence level, then the design is ignored. This skipped evaluation reduces the computational effort of optimization. The method is demonstrated on a cavitating, unsteady flow case of the Wageningen B-4 70 propeller with P/D = 1.0 operating in the Seiun-Maru wake. Compared to the classical Non-dominated Sorting Genetic Algorithm — III (NSGA-III) the optimization method is able to reduce 30% of evaluations per generation while reproducing a comparable Pareto front. Trade-offs between suction side, pressure side, tip-vortex cavitation and efficiency are identified from the Pareto front. The non-elitist NSGA-III search algorithm in conjunction with the explainable supervised classifiers also find very diverse solutions. Among the solutions, a design with no pressure side cavitation, low suction side cavitation and reasonable tip-vortex cavitation is found.
KW - Dynamic optimization
KW - Machine learning
KW - Orthogonal parametric model
KW - Propeller design and optimization
KW - Uncertainty
UR - http://www.scopus.com/inward/record.url?scp=85129946557&partnerID=8YFLogxK
U2 - 10.1016/j.apor.2022.103174
DO - 10.1016/j.apor.2022.103174
M3 - Article
AN - SCOPUS:85129946557
SN - 0141-1187
VL - 124
JO - Applied Ocean Research
JF - Applied Ocean Research
M1 - 103174
ER -