Evolutionary design

We propose a novel application of similarity-based
evaluation for layout design. Basing evaluations on a
pool of existing designs or quickly delivered graphical
specifications enables an Evolutionary Algorithm to
become an open-ended system, where problem
definitions can be kept open for fast updating.Through
its flexible and open-ended aspects, the approach is
able to develop draft layouts for an unlimited variety of
tasks, which are not implied within the initial task
definition.This enables a versatile computational layout
design assistant, which can be easily adopted within
regular design processes through usual graphic media.
In this paper, the functioning of the approach is
described and verified; the versatility of the resulting
assistant, its intuitive graphical interface, and its usage
scenario are demonstrated.

This paper describes the conceptual framework of a general strategy for developing an engine crankshaft based on computer-aided innovation, together with an introduction to the methodologies from which our strategy evolves. It begins with a description of two already popular disciplines, which have their roots in computer science and natural evolution: evolutionary design (ED) and genetic algorithms (GAs). A description of some optimization processes in the field of mechanical design is also presented. We explain our approach to multi-objective optimization and show how tools like the Pareto diagram can help in identifying conflicts. The concepts presented here are exemplified through the optimization of a combustion engine crankshaft. The main premise of the paper is the possibility to optimize the imbalance of a crankshaft using tools developed in this methodology. This study brings together techniques that have their origins in the fields of optimization and new tools for innovation. We reflect on how computers can have an active role in the conceptual design process, and explain how TRIZ (Theory of Inventive Problem Solving) can enrich the discipline of ED. The aim of our research is to extend the search for solutions with GAs and present creative, innovative alternatives to the designer. Similarities between GAs and TRIZ regarding ideality and evolution are presented. We also explain how geometric optimization systems (size, shape, topology and topography) offer hints about the next generation of optimization tools. The role of splines in this context is found to be closely integrated with GAs in enabling this development on a computer-aided design and engineering (CAD&CAE) software interface, and in enabling integration with Java programming language for automation of the development.

This paper describes the construction of an information flow that combines parametric modelling and genetic algorithms to optimize both the total weight of a structured steel roof and the shape of its surface to maximize the generation potential of photovoltaic energy. Through the systematization of a design process using genetic algorithms integrated with generative design as an architectural design method, architects can work with problem parameterization, going one step further than the mere formal proposition of solutions. As a result, we present a process in which there is a dialogical relationship between the architect and project in a continuous flow of information in the initial steps of the design process, guided by predefined optimization objectives. Therefore, it is relevant to note that the designer accepts a reduced creative control over the final shape in favor of control over the core principles that constitute the optimization algorithms. An approach that involved the designer in a process of post computational processing evaluations is also highlighted, giving them better support to discuss and analyze the design options.

This research spotlights the issue that decisions made at the early stages of building design have the greatest and impact on cost implications for construction and the building lifecycle. While the design of services (heating, ventilation and air-conditioning) constitutes a large part of the construction cost, they are traditionally not considered at the early stages of design. Methods such as

Within the software engineering community it is widely accepted that design patterns are very helpful to develop well-structured software. The same kind of support is expected of HCI-Patterns. In this paper we discuss an approach integrating the usage of patterns into a model-based development process. A GUI-editor is presented that has been extended by features allowing the application instances of

The theory of evolution was possibly the most crucial discovery in the history of mankind. Its changes in the field of biology were ground-breaking. With further research, it has also impacted the field of computing and given rise to some of the most powerful software and hardware used today. However, the impact in the field of design seems not to have taken place. Why is this so ? Why would such a powerful algorithm as the one for evolution be ignored in the process of design ?
I childishly thought I would find a revolutionary method that would change the process of design forever. I thought media designs could become autonomous self-evolving digital organisms, exceeding their expected lifetime, forever adapting to the needs of the designer.
With a short historical overview and a piecemeal decomposition of the evolutionary dynamics based on books such as On the Origin of Species by Darwin and The Selfish Gene by Dawkins, this thesis attempts to show the relevance and potential usefulness of Evolution-Assisted Design by computers. Through case analyses and the creation of genetic algorithms, one will see why the creation of autonomously evolving designs cannot happen in a desired fashion without the careful interventions of a watchful guardian. Nevertheless, certain solutions may permit designers to consider the use of such algorithms for their own adaptable projects ; forcing the designer to adopt a radically different approach.

Most evolutionary computation (EC) applications in design fields either assume simplified, static, performance-oriented procedures for design or focus on well-defined sub-problems, to be able to impose problem-solving and optimization schemes on design tasks, which render known EC techniques directly applicable. However, in most design situations, well-defined and static problems are not given, but must be constructed from messy situations, and the definition of a problem takes place during the solution process. Thus, evolutionary design requires contextual and dynamic problem definition and evaluation procedures, which has not yet been realized through EC. This study sets out for a critical reappraisal of EC for design, and proposes a conceptual framework as a research tool for the exploration of dynamic evolutionary design. After a critical review of EC in design, the article discusses its claims with reference to design theory, outlines the framework, and examines dynamic evolutionary strategies and required intelligent technologies. Although tackling a practical task, or solving the problem of dynamic evolution are not aimed in this study, an experimental application based on the framework will be presented in detail, to exemplify a mapping between the rather abstract concepts of the framework and the operators of a specific evolutionary algorithm.

Evolvable hardware (EHW) is a set of techniques that are based on the idea of combining reconfiguration hardware systems with evolutionary algorithms. In other word, EHW has two sections; the reconfigurable hardware and evolutionary algorithm where the configurations are under the control of an evolutionary algorithm. This paper, suggests a method to design and optimize the synchronous sequential circuits. Genetic algorithm (GA) was applied as evolutionary algorithm. In this approach, for building input combinational logic circuit of each DFF, and also output combinational logic circuit, the cell arrays have been used. The obtained results show that our method can reduce the average number of generations by limitation the search space.

This study involves analysis of the sketches and the drawings produced during the design process of a house designed by Mario Botta and evaluation of the process itself. The conjecture/analysis model of design is assumed. The main outcome of the study is the findings, observations, and interpretations related with the nature of the analyzed design process. It is expected that the concerned outcomes will provide a basis, a departure point for the reconsideration, advance, and a consequent evolution of the assumed model, and a basis for further research following the same line of inquiry. ÖZET: Bu makale Mario Botta tarafından tasarlanmış bir evin tasarım süreci boyunca üretilmiş eskiz ve çizimlerinin çözümlemesini ve tasarım sürecinin değerlendirmesini içermektedir. Çözümlemede, conjecture/analysis olarak bilinen tasarım modeli kabul edilmiştir. Çalışmanın ana çıktısı incelenen tasarım sürecinin doğasına ilişkin bulgular, gözlemler ve yorumlardır. Bu çıktıların başlangıçta kabul edilen conjecture/analysis modelinin yeniden değerlendirilip, gelişmesi ve evrimleşmesinin yanısıra, bu çizgide geliştirilebilecek başka araştırmalar için bir temel, bir başlangıç noktası oluşturacağı düşünülmüştür.

IntroductionThis chapter describes our work in evolution of buildable designs using miniature plasticbricks as modular components. Lego1bricks are well known for their flexibility when it comes tocreating low cost, handy designs of vehicles and structures. Their simple modular concept make toybricks a good ground for doing evolution of computer simulated structures which can be built anddeployed.Instead of incorporating an expert

This paper is focused on the study, analysis and development of code for the defuzzification stage of type-2 fuzzy systems, through the average of two type-1 fuzzy systems. This proposal is based on the average method for systems where the type-2 membership functions of the inputs and output, have no uncertainty in the mean or center. The codification is done using the hardware description language VHDL, and it was exported to Simulink through the Xilinx System Generator (XSG). Comparative tests were conducted between the type-2 fuzzy systems for different number of bits and noise levels.

Modern CAD systems ofier the most simple and natural way to represent complex mechanical structures heavily constrained through a variety of functional, aesthetic, and manufacturing demands. We present two concepts for evolutionary design op- timization directly relying on CAD-based design encodings of arbitrary mechanical structures. One relies on the associative-parametric description of the design. Its full potential is shown by

Die im vorliegenden Buch dokumentierten Untersu- chungen befassen sich mit der Entwicklung von Methoden zur algorithmischen Lösung von Layout- aufgaben im architektonischen Kontext. Layout bezeichnet hier die gestalterisch und funktional sinnvolle Anordnung räumlicher Elemente, z.B. von Parzellen, Gebäuden, Räumen auf bestimmten Maß stabsebenen. Die vorliegenden Untersuchun- gen sind im Rahmen eines von der Deutschen Forschungsgemeinschaft geförderten Forschungs- projekts entstanden. gefördert

This paper is focused on the study, analysis and development of code for the defuzzification stage of type-2 fuzzy systems, through the average of two type-1 fuzzy systems. This proposal is based on the average method for systems where the type-2 membership functions of the inputs and output, have no uncertainty in the mean or center. The codification is done using the hardware description language VHDL, and it was exported to Simulink through the Xilinx System Generator (XSG). Comparative tests were conducted between the type-2 fuzzy systems for different number of bits and noise levels.

We describe the first steps in the adoption of Shape Gram-mars with Grammatical Evolution for application in Evo-lutionary Design. Combining the concepts of Shape Gram-mars and Genetic Programming opens up the exciting pos-sibility of truly generative design assist tools. In this ini-tial study we provide some background on the adoption of grammar-based Genetic Programming for Evolutionary De-sign, describe Shape Grammars, and give a brief overview of Grammatical Evolution before detailing how Grammatical Evolution used Shape Grammars to successfully rediscover some benchmark target structures.