An Integrated Approach for Design Optimization in AI-Driven CAE

Main Article Content

DongWook Yang
Younju Kim
Sungil Jang

Abstract

Prior to actual testing, performance evaluation is conducted through Computer-Aided Engineering (CAE) in design process. The analysis results are scrutinized to verify whether the design meets the intended performance. If not satisfied, the conditions are modified, and the analysis is iteratively performed until the desired performance is achieved. However, this iterative process poses challenges in terms of both time and cost.


To address this, machine learning and deep learning methodologies have been developed. Nevertheless, existing models do not consider the condition that multiple design parameters can satisfy a given performance, leading to not only performance degradation but also overlooking the possibility of better outcomes. In this study, we propose a method to obtain the multiple design parameters that satisfy the desired performance with high accuracy, without the need for iterative tasks.


We modify the model to predict various design parameters by applying monte carlo dropout and bayesian neural network to the tandem network, which outputs only one design parameter fitted to the training data. Furthermore, we propose a 2-stage methodology for exploring local minima by performing bayes optimization based on multiple candidate values derived from the tandem network. The proposed model significantly reduces the number of iterations required for design optimization and predicts multiple possible design parameters. Experimental results using data from rear-wheel steering and braking simulations demonstrate the overwhelming performance and diverse design parameters provided by our proposed model.

Article Details

How to Cite
An Integrated Approach for Design Optimization in AI-Driven CAE. (2024). Engineering Modelling, Analysis and Simulation, 2(1). https://doi.org/10.59972/j92qm86n
Section
Articles

How to Cite

An Integrated Approach for Design Optimization in AI-Driven CAE. (2024). Engineering Modelling, Analysis and Simulation, 2(1). https://doi.org/10.59972/j92qm86n

References

Liu. D, Tan. Y, Khoram. E, Yu. Z, “Training deep neural networks for the inverse design of nanophotonic structures”, Acs Photonics, 2018, 5(4), 1365-1369.

Gal. Y, Ghahramani. Z, “Dropout as a bayesian approximation: Representing model uncertainty in deep learning”, In international conference on machine learning, PMLR, 2016, 1050-1059.

Jospin. L. V, Laga. H, Boussaid. F, Buntine. W, Bennamoun, M, “Hands-on Bayesian neural networks—A tutorial for deep learning users”, IEEE Computational Intelligence Magazine, 2022, 17(2), 29-48.

Hwang. H, Cho. Y, Hwang. S, Kim. S, “Optimal Tire Design Using Machine Learning and Bayesian Optimization”, Journal of the Korean Institute of Industrial Engineers, 2022, 48(4), 433-440.

Bank. D, Koenigstein. N, Giryes. R, “Autoencoders”, Machine learning for data science handbook: data mining and knowledge discovery handbook, 2023, 353-374.

Wang. H, van Stein. B, Emmerich. M, Back. T, “A new acquisition function for Bayesian optimization based on the moment-generating function”, In 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017, 507-512.

Noever‐Castelos. P, Ardizzone. L, Balzani. C, “Model updating of wind turbine blade cross sections with invertible neural networks”, Wind Energy, 2022, 25(3), 573-599.