Accelerated optimization of curvilinearly stiffened panels using deep learning

Abstract

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.