A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Accelerated optimization of curvilinearly stiffened panels using deep learning
https://orcid.org/0000-0001-8465-3161
Abstract An important objective for the aerospace industry is to design robust and fuel efficient aerospace structures. Advanced manufacturing techniques like additive manufacturing have allowed structural designers to make use of curvilinear stiffeners for achieving better designs of stiffened plate and shell structures. Finite Element Analysis (FEA) based standard optimization methods for aircraft panels with arbitrary curvilinear stiffeners are computationally expensive. The main reason for employing many of these standard optimization methods is the ease of their integration with FEA. However, each optimization requires multiple computationally expensive FEA evaluations, making their use impractical at times. To accelerate optimization, the use of Deep Neural Networks (DNNs) is proposed to approximate the FEA buckling response, computed using MSC NASTRAN. The finite element model of a plate is verified with those found in the literature. Later, a Python script is used to generate a large data-set using parallel processing. The 80%, 10% and 10% of the generated data-set are used for training, validation and testing of DNNs, respectively. The results show that DNNs, optimized using Adam optimizer, obtained an accuracy of 95% on the test set for approximating FEA response within 10% of the actual value. To compare the efficiency of the DNN, the trained DNN is used in the optimization of curvilinearly stiffened panels by replacing the conventional FEA. The DNN accelerated the optimization by a factor of nearly 200. The presented work demonstrates the potential of DNN-based machine learning algorithms for accelerating the optimization of curvilinearly stiffened panels.
Graphical abstract Display Omitted
Highlights The use of Deep Neural Networks is proposed to approximate the FEA buckling response of curvilinearly stiffened panels. The results show that DNNs obtained an accuracy of 95% on the test set for approximating FEA response. One DNN can be used to predict FEA response for many curvilinearly stiffened panels under different load cases. The DNN accelerated the optimization by a factor of nearly 200.
Accelerated optimization of curvilinearly stiffened panels using deep learning
https://orcid.org/0000-0001-8465-3161
Abstract An important objective for the aerospace industry is to design robust and fuel efficient aerospace structures. Advanced manufacturing techniques like additive manufacturing have allowed structural designers to make use of curvilinear stiffeners for achieving better designs of stiffened plate and shell structures. Finite Element Analysis (FEA) based standard optimization methods for aircraft panels with arbitrary curvilinear stiffeners are computationally expensive. The main reason for employing many of these standard optimization methods is the ease of their integration with FEA. However, each optimization requires multiple computationally expensive FEA evaluations, making their use impractical at times. To accelerate optimization, the use of Deep Neural Networks (DNNs) is proposed to approximate the FEA buckling response, computed using MSC NASTRAN. The finite element model of a plate is verified with those found in the literature. Later, a Python script is used to generate a large data-set using parallel processing. The 80%, 10% and 10% of the generated data-set are used for training, validation and testing of DNNs, respectively. The results show that DNNs, optimized using Adam optimizer, obtained an accuracy of 95% on the test set for approximating FEA response within 10% of the actual value. To compare the efficiency of the DNN, the trained DNN is used in the optimization of curvilinearly stiffened panels by replacing the conventional FEA. The DNN accelerated the optimization by a factor of nearly 200. The presented work demonstrates the potential of DNN-based machine learning algorithms for accelerating the optimization of curvilinearly stiffened panels.
Graphical abstract Display Omitted
Highlights The use of Deep Neural Networks is proposed to approximate the FEA buckling response of curvilinearly stiffened panels. The results show that DNNs obtained an accuracy of 95% on the test set for approximating FEA response. One DNN can be used to predict FEA response for many curvilinearly stiffened panels under different load cases. The DNN accelerated the optimization by a factor of nearly 200.
Accelerated optimization of curvilinearly stiffened panels using deep learning
https://orcid.org/0000-0001-8465-3161
Abstract An important objective for the aerospace industry is to design robust and fuel efficient aerospace structures. Advanced manufacturing techniques like additive manufacturing have allowed structural designers to make use of curvilinear stiffeners for achieving better designs of stiffened plate and shell structures. Finite Element Analysis (FEA) based standard optimization methods for aircraft panels with arbitrary curvilinear stiffeners are computationally expensive. The main reason for employing many of these standard optimization methods is the ease of their integration with FEA. However, each optimization requires multiple computationally expensive FEA evaluations, making their use impractical at times. To accelerate optimization, the use of Deep Neural Networks (DNNs) is proposed to approximate the FEA buckling response, computed using MSC NASTRAN. The finite element model of a plate is verified with those found in the literature. Later, a Python script is used to generate a large data-set using parallel processing. The 80%, 10% and 10% of the generated data-set are used for training, validation and testing of DNNs, respectively. The results show that DNNs, optimized using Adam optimizer, obtained an accuracy of 95% on the test set for approximating FEA response within 10% of the actual value. To compare the efficiency of the DNN, the trained DNN is used in the optimization of curvilinearly stiffened panels by replacing the conventional FEA. The DNN accelerated the optimization by a factor of nearly 200. The presented work demonstrates the potential of DNN-based machine learning algorithms for accelerating the optimization of curvilinearly stiffened panels.
Graphical abstract Display Omitted
Highlights The use of Deep Neural Networks is proposed to approximate the FEA buckling response of curvilinearly stiffened panels. The results show that DNNs obtained an accuracy of 95% on the test set for approximating FEA response. One DNN can be used to predict FEA response for many curvilinearly stiffened panels under different load cases. The DNN accelerated the optimization by a factor of nearly 200.
Accelerated optimization of curvilinearly stiffened panels using deep learning
Singh, Karanpreet (author) / Kapania, Rakesh K. (author)
Thin-Walled Structures ; 161
2020-12-28
Article (Journal)
Electronic Resource
English
Buckling analysis of unitized curvilinearly stiffened composite panels
| British Library Online Contents | 2016
Optimization of Curvilinearly Stiffened Panels with Single Cutout Concerning the Collapse Load
| Online Contents | 2016
Free vibration analysis of isogeometric curvilinearly stiffened shells
| Elsevier | 2017