Technology Category
Search and Optimization: Sampling/Simulation-based SearchMachine Learning: Deep Neural Architectures and Foundation ModelsComputer Vision: Learning & Optimization for CV
Accelerating shape optimization by deep neural networks with on-the-fly determined architecture
🤖 AI Summary
Shape optimization of engineering components—particularly those requiring thousands of high-fidelity simulations—is computationally prohibitive. Method: This paper proposes an acceleration framework integrating multi-objective evolutionary algorithms (MOEAs) with dynamically architected deep neural networks (DNNs). Its core innovation lies in online, data-driven co-optimization of DNN architecture and surrogate model accuracy during the evolutionary process, enabling real-time replacement of expensive simulations within a closed-loop simulation-learning cycle. The framework comprises MOEA-based global search, dynamic DNN architecture selection, incremental training on simulation data, and experimental validation via 3D printing. Contribution/Results: Benchmark evaluations demonstrate superior performance over state-of-the-art acceleration methods. Applied to single-phase ejector shape optimization, the framework reduces CPU time by several weeks. Four 3D-printed prototypes confirm both predictive accuracy and engineering feasibility.
Technology Category
Application Category
📝 Abstract
In component shape optimization, the component properties are often evaluated by computationally expensive simulations. Such optimization becomes unfeasible when it is focused on a global search requiring thousands of simulations to be evaluated. Here, we present a viable global shape optimization methodology based on multi-objective evolutionary algorithms accelerated by deep neural networks (DNNs). Our methodology alternates between evaluating simulations and utilizing the generated data to train DNNs with various architectures. When a suitable DNN architecture is identified, the DNN replaces the simulation in the rest of the global search. Our methodology was tested on five ZDT benchmark functions, showing itself at the level of and sometimes more flexible than other state-of-the-art acceleration approaches. Then, it was applied to a real-life optimization problem, namely the shape optimization of a single-phase ejector. Compared with a non-accelerated methodology, ours was able to save weeks of CPU time in solving this problem. To experimentally confirm the performance of the optimized ejector shapes, four of them were 3D printed and tested on the lab scale confirming the predicted performance. This suggests that our methodology could be used for acceleration of other real-life shape optimization problems.
Problem
Research questions and friction points this paper is trying to address.
Accelerates global shape optimization using deep neural networks
Reduces computational cost by replacing expensive simulations with DNNs
Applies methodology to real-world problems like ejector shape optimization
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deep neural networks accelerate shape optimization
On-the-fly architecture determination for DNNs
DNN replaces simulations in global evolutionary search
🔎 Similar Papers
No similar papers found.
