Fusion of ML with numerical simulation for optimized propeller design

TL;DR

This paper introduces Surrogate Assisted Optimization (SAO), a hybrid method combining machine learning surrogates with traditional optimization to efficiently find optimal propeller designs in high-dimensional, computationally cheap design spaces.

Contribution

The paper proposes a novel hybrid optimization approach that uses ML surrogates as inverse problem solvers to accelerate design optimization processes.

Findings

SAO finds better designs with fewer evaluations.

SAO reduces computational time in propeller design.

Hybrid approach outperforms traditional methods in efficiency.

Abstract

In computer-aided engineering design, the goal of a designer is to find an optimal design on a given requirement using the numerical simulator in loop with an optimization method. In this design optimization process, a good design optimization process is one that can reduce the time from inception to design. In this work, we take a class of design problem, that is computationally cheap to evaluate but has high dimensional design space. In such cases, traditional surrogate-based optimization does not offer any benefits. In this work, we propose an alternative way to use ML model to surrogate the design process that formulates the search problem as an inverse problem and can save time by finding the optimal design or at least a good initial seed design for optimization. By using this trained surrogate model with the traditional optimization method, we can get the best of both worlds. We call this as Surrogate Assisted Optimization (SAO)- a hybrid approach by mixing ML surrogate with the traditional optimization method. Empirical evaluations of propeller design problems show that a better efficient design can be found in fewer evaluations using SAO.