Thesis (M.S.)--Brigham Young University. Dept. of Mechanical Engineering, 2002. / Includes bibliographical references (p. 41-43).

Thesis (M. Eng.(Mechanical Engineering))--University of Pretoria, 2002. / Summaries in Afrikaans and English. Includes bibliographical references.

Machine learning techniques promise to greatly accelerate structural design and optimization. In this thesis, deep learning and active learning techniques are applied to different non-convex structural optimization problems. Finite Element Analysis (FEA) based standard optimization methods for aircraft panels with bio-inspired 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. The results show that DNNs obtained an accuracy of 95% for evaluating the buckling load. 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 bio-inspired curvilinearly stiffened panels. But, the approach could have disadvantages for being only specific to similar structural design problems, and requiring large datasets for DNNs training. An adaptive machine learning technique called active learning is used in this thesis to accelerate the evolutionary optimization of complex structures. The active learner helps the Genetic Algorithms (GA) by predicting if the possible design is going to satisfy the required constraints or not. The approach does not need a trained surrogate model prior to the optimization. The active learner adaptively improve its own accuracy during the optimization for saving the required number of FEA evaluations. The results show that the approach has the potential to reduce the total required FEA evaluations by more than 50%. Lastly, the machine learning is used to make recommendations for modeling choices while analyzing a structure using FEA. The decisions about the selection of appropriate modeling techniques are usually based on an analyst's judgement based upon their knowledge and intuition from past experience. The machine learning-based approach provides recommendations within seconds, thus, saving significant computational resources for making accurate design choices. / Doctor of Philosophy / This thesis presents an innovative application of artificial intelligence (AI) techniques for designing aircraft structures. An important objective for the aerospace industry is to design robust and fuel-efficient aerospace structures. The state of the art research in the literature shows that the structure of aircraft in future could mimic organic cellular structure. However, the design of these new panels with arbitrary structures is computationally expensive. For instance, applying standard optimization methods currently being applied to aerospace structures to design an aircraft, can take anywhere from a few days to months. The presented research demonstrates the potential of AI for accelerating the optimization of an aircraft structures. This will provide an efficient way for aircraft designers to design futuristic fuel-efficient aircraft which will have positive impact on the environment and the world.

This thesis gives a comprehensive study on the effect of using different structural idealizations on the design, analysis and optimization of thin walled semi-monocoque wing structures in the preliminary design phase. In the design part, wing structures are designed by employing two different structural idealizations that are typically used in the preliminary design phase. In the structural analysis part, finite element analysis of one of the designed wing configurations is performed using six different one and two dimensional element pairs which are typically used to model the sub-elements of semi-monocoque wing structures. The effect of using different finite element types on the analysis results of the wing structure is investigated. During the analysis study, depending on the mesh size used, conclusions are also inferred with regard to the deficiency of certain element types in handling the true external load acting on the wing structure. Finally in the optimization part, wing structure is optimized for minimum weight by using finite element models which have the same six different element pairs used in the analysis phase. The effect of using different one and two dimensional element pairs on the final optimized configurations of the wing structure is investigated, and conclusions are inferred with regard to the sensitivity of the optimized wing configurations with respect to the choice of different element types in the finite element model. Final optimized wing structure configurations are also compared with the simplified method based designs which are also optimized iteratively. Based on the results presented in the thesis, it is concluded that with the simplified methods, preliminary sizing of the wing structures can be performed with enough confidence, as long as the simplified method based designs are also optimized. Results of the simplified method of analysis showed that simplified method is applicable to be used as an analysis tool in performing the preliminary sizing of the wing structure before moving on to more refined finite element based analysis.

Steel space frames having irregular shapes when subjected to lateral loads caused by wind or earthquakes undergo twisting as a result of their unsymmetrical topology. As a result, torsional moment comes out which is required to be resisted by the three dimensional frame system. The members of such frame are generally made out of steel I sections which are thin walled open sections. The simple beam theory is not adequate to predict behavior of such thin-walled sections under torsional moments due to the fact that the large warping deformations occur in the cross section of the member. Therefore, it is necessary to consider the effect of warping in the design of the steel space frames having members of thin walled steel sections is significant. In this study the optimum design problem of steel space frames is formulated according to the provisions of LRFD-AISC (Load and Resistance factor design of American Institute of Steel Construction) in which the effect of warping is also taken into account. Ant colony optimization and harmony search techniques two of the recent methods in stochastic search techniques are used to obtain the solution of the design problem. Number of space frame examples is designed by the algorithms developed in order to demonstrate the effect of warping in the optimum design.