Zusammenfassung
The work at hand addresses engineers, designers and scientists who face the challenging Task of devising concept structures in a virtual product design process that involves more and more sophisticated physical simulations. Using methods of evolutionary optimization and machine learning, this dissertation explores a novel generic topology optimization algorithm, which is able to provide concept designs even for problems involving complex, black-box simulations. A self-contained learning component utilizes physical simulation data to generate a search direction. The generic topology optimization is studied in conjunction with statistical models such as neural networks or support vector regression. In empirical experiments, the novel method reproduces reference structures with Minimum compliance and provides innovative solutions in the domain of vehicle crashworthiness optimization.
Contents
Symbols and Abbreviations XIV
Abstract XVII
Zusammenfassung XVIII
1 Introduction 1
2 Fundamentals...
Schlagworte
Topology Optimization Concept Design Local State Features Evolutionary / Computation Design Sensitivities Prediction Machine Learning Vehicle Crashworthiness- Kapitel Ausklappen | EinklappenSeiten
- 8–28 2 Fundamentals 8–28
- 150–154 7 Conclusions 150–154
- 155–160 A Theory 155–160
- 172–176 C Crashworthiness 172–176
- 177–202 Bibliography 177–202
7 Treffer gefunden
- „... process. In contrast to this, methods of design optimization aim at finding the best design parameters in ...” „... of constraints. Modern product-development processes use computational design and engineering tools ...” „... number of costly prototypes and an overall acceleration of the development processes. Tools, such as ...”
- „... developmental process, due to their pronounced similarity to cellular automata. However, computational steps of ...” „... for topology optimization and a developmental process that is influenced by environmental information ...” „... related to modelling the gradient of the objective function. Assuming a suitable learning process, we ...”
- „... stochastic optimization methods. The chapter is finalized with a summary in Sec. 2.4. 2.1 Background ...” „... structure. Sizing and shape optimization are commonly applied relatively late in the design process, when a ...” „... introducing topological changes in the structural optimization process. This problem marked starting point for ...”
- „... process only generates connected structures and crossover and mutation to the cost variables with a ...” „... rules or development processes that create the structure, are often inspired by onto- or morphogenesis ...” „... processes in nature and mimic various aspects at different levels of abstraction. 3.4.1 Lindenmayer System ...”
- „... . Response surface methodology: process and product optimization using designed experiments, volume 705. John ...” „... Bibliography [175] Spall, J. C. Introduction to stochastic search and optimization: estimation, simulation, and ...” „... process. PhD thesis, University of Notre Dame, 2004. [191] Tovar, A., Patel, N. M., Niebur, G. L., Sen, M ...”
- „... gradients are available. Concretely, the idea of the proposed method is to utilize a learning process that ...” „... formulations need to be found externally to the optimization process. One one hand, the advantage of this ...” „... process is that an accurate search direction is provided. On the other hand, the problem here is obviously ...”
- „... different random seeds. As can be expected for algorithms with stochastic components, there is variance in ...” „... account for the stochastic nature of the sampling 102 5 Studies on the Minimum Compliance Problem choice ...” „... . Similar to the strain energy density, stresses or strains, these LSFs implicitly process the information ...”