Efficient Inverse Design of 2D Elastic Metamaterial Systems using Invertible Neural Networks

Oddiraju, Manaswin; Behjat, Amir; Nouh, M.; Chowdhury, Souma

doi:10.2514/6.2021-3065

Cited by 3 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outside the realm of airfoil inverse design, Yu et al [18] demonstrated promise in the idea of developing neural network models for the inverse design of rocket nozzles when provided a desired pressure distribution, showcasing its excellent predictive accuracy. Additionally, Oddiraju et al [19] demonstrated the viability of developing neural network models to aid in the design of metamaterials when using desired bandgap specifications. Li et al [20] showcased the ability to use deep neural networks for prediction of 3-D wing shape designs when provided C L , C D , C M , and pressure coefficient (C P ) distributions, and how such a model could be leveraged by a gradient-based optimization framework for various wing design scenarios.…”

Section: Introductionmentioning

confidence: 99%

Mission-Driven Inverse Design of Blended Wing Body Aircraft with Machine Learning

Sharma,

Hosder

2024

Aerospace

View full text Add to dashboard Cite

The intent of this work was to investigate the feasibility of developing machine learning models for calculating values of airplane configuration design variables when provided time-series, mission-informed performance data. Shallow artificial neural networks were developed, trained, and tested using data pertaining to the blended wing body (BWB) class of aerospace vehicles. Configuration design parameters were varied using a Latin-hypercube sampling scheme. These data were used by a parametric-based BWB configuration generator to create unique BWBs. Performance for each configuration was obtained via a performance estimation tool. Training and testing of neural networks was conducted using a K-fold cross-validation scheme. A random forest approach was used to determine the values of predicted configuration design variables when evaluating neural network accuracy across a blended wing body vehicle survey. The results demonstrated the viability of leveraging neural networks in mission-dependent, inverse design of blended wing bodies. In particular, feed-forward, shallow neural network architectures yielded significantly better predictive accuracy than cascade-forward architectures. Furthermore, for both architectures, increasing the number of neurons in the hidden layer increased the prediction accuracy of configuration design variables by at least 80%.

show abstract

Section: Introductionmentioning

confidence: 99%