Article
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Design tools that aim not only to analyse and evaluate, but also to generate and explore alternative design proposals are now under development. An evolutionary paradigm is presented as a basis for creating such tools. First, the evolutionary paradigm is shown to be the only successful design system on which this new phase of design tool could be based. Secondly, any characterisation of design as a search problem is argued to be a serious misconception. Instead it is proposed that evolutionary design systems should be seen as generative processes that are able to evaluate their own output. Thirdly, a generic framework for generative evolutionary design systems is presented. Fourth, the generative process is introduced as a key element within this generic framework. The role of the environment within this process is fundamental. Finally, the direction of future research within the evolutionary design paradigm is discussed with possible short and long term goals being presented.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... A design schema is a highly customisable but generic working method. As an adaptable design model inserted into the design process, the design schema characterises the designer's style as an abstract conception of common features of their designs (Janssen, Frazer & Tang, 2002). The design schema is also employed to maintain the designer's creative expression as a central part of the design process. ...
... The concept of the designer as a tool maker (Janssen et al., 2002) is introduced here as the simulation of the project's environments are employed as a tool to aid in the generation of design solutions. ...
Article
Full-text available
This approach to sustainable design explores the possibility of creating an architectural design process which can iteratively produce optimised and sustainable design solutions. Driven by an evolution process based on genetic algorithms, the system allows the designer to “design the building design generator” rather than to “designs the building”. The design concept is abstracted into a digital design schema, which allows transfer of the human creative vision into the rational language of a computer. The schema is then elaborated into the use of genetic algorithms to evolve innovative, performative and sustainable design solutions. The prioritisation of the project’s constraints and the subsequent design solutions synthesised during design generation are expected to resolve most of the major conflicts in the evaluation and optimisation phases. Mosques are used as the example building typology to ground the research activity. The spatial organisations of various mosque typologies are graphically represented by adjacency constraints between spaces. Each configuration is represented by a planar graph which is then translated into a non-orthogonal dual graph and fed into the genetic algorithm system with fixed constraints and expected performance criteria set to govern evolution. The resultant Hierarchical Evolutionary Algorithmic Design System is developed by linking the evaluation process with environmental assessment tools to rank the candidate designs. The proposed system generates the concept, the seed, and the schema, and has environmental performance as one of the main criteria in driving optimisation.
... Based on the introduced and discussed literature throughout the paper, in this section we propose an alternative transitional workflow. With the rapid adoption of digital design techniques in architectural design, "machine intelligence had been overestimated and the complexities of the design process had been underestimated [39]." The transitional method fuses machine potential with the creative input of the designer to inform each stage of the design with the feedback received from both platforms. ...
... As a result of this study, maintaining an equilibrium between physical and digital mediums manifested a cyclical feedback exchange throughout the design process. In an iterative design process, search for conceptual and structural design solutions will continuously redefine the problem [39]. Benefiting from creative skills of the designer and machine capability to the same degree originated quick and efficient solutions by linking design exploration to material realization ( Figure 4) [44]. ...
Conference Paper
Full-text available
As design thinking shifted away from conventional methods with the rapid adoption of computer-aided design and fabrication technologies, architects have been seeking ways to initiate a comprehensive dialogue between the virtual and the material realms. Current methodologies do not offer embodied workflows that utilize the feedback obtained through a subsequent transition process between physical and digital design. Therefore, narrowing the separation between these two platforms remains as a research problem. This literature review elaborates the divide between physical and digital design, testing and manufacturing techniques in the morphological process of architectural form. We first review the digital transformation in the architectural design discourse. Then, we proceed by introducing a variety of methods that are integrating digital and physical workflows and suggesting an alternative approach. Our work unveils that there is a need for empirical research with a focus on integrated approaches to create intuitively embodied experiences for architects. ACM Link: https://dl.acm.org/citation.cfm?doid=3290605.3300290
... In design domain, evolution also can explore a search space for novel designs [Bentley and Corne, 2002b]. Janssen et al. (2002) described how generative evolutionary design tool provides guidance and inspiration for designers to help the designers' creativity. ...
... EC now provides solutions for applications in creative areas such as architecture, art, music and design. Some design-aid systems also have been developed using EC [Janssen et al., 2002;Liu et al., 2004]. ...
Article
In the field of industry design, the affective response characteristic can plays a significant role that could grasp customer's attention in product. Especially, the design strategy of “affection-prerequisite” shows the importance of the trend of customer-oriented for the industry products. Up to date, in consideration of the rapidly life-cycle on industrial design field, however, how designers can retrieve customer's affective response promptly and using such information into their design work efficiently are significant, but not discussed yet. Based on this concept, the objective of this research is to present a creative stimulation system for designers. The “wisdom of crowds” was collected via the Web in order to ascertain customers' affective responses to product shapes. This data was used to create an evolutionary design system platform by using a design alternatives generation mechanism. The study involved integrating an interactive genetic algorithm into the mechanism to generate an interactive creative stimulation system. An affective design of the shape of a mobile phone was used as an example of implementation and also used as a proof of the research concept.Relevance to industryHIGA and ESC methods proposed in this research provide the usage of the affective evaluation system for acquiring the customers' affective responses in the conceptual design process of a mobile phone. This design-generation process allows the design stakeholders to realize their customers' affective responses interactively with sharing floating data among them according to the daily update of customer's evaluations.
... With this type of technology, the intentions of designers are undetermined and system boundaries are often unclear (Garud et al., 2008). Digital technologies tend to adhere an evolutionary design (Janssen, Frazer, & Ming-Xi, 2002) characterized by the fact that their makers have a general sense of where they are going but do not have a precise target or goal in mind, and they leave to the users to define the trajectory of the system. In fact, in situ accounts of the design of modern technology report the chaotic and improvised nature of the IT development process because part of it is handed to the user (Bansler & Havn, 2004). ...
... ✗ (Janssen et al., 2002) Evolutionary design paradigm ...
Conference Paper
Full-text available
Information Technologies (IT) have gradually transformed into complex digital artefacts with blurred and constantly changing functional boundaries. While this shift offers promising venues that unfold in front of our eyes every day, it also challenges the deeply entrenched knowledge structures on which ordinary users rely to learn about unfamiliar technologies. We propose to take a step back in order to theorize the ambiguous nature of modern IT and to speculate on how users learn to use them. This paper revisits a wide array of management (BYOD, Gamification) and IS design trends (generativity, everyday computing, incompleteness) through the lens of the categorization framework. Our review of the literature on ambiguous products suggests that users exposed to ambiguous technologies may experience a categorization difficulty that disrupts the process of learning how to use them. This difficulty stems from a user's belief that there are multiple or inconsistent interpretations of why and how to use an IT, as well as a perception that a given IT has some attributes in common with one or several seemingly unrelated ITs. We build on this theorization to propose a research agenda and discuss the expected practical implications of this path of research.
... GA is based on the adaptive process of natural evolution, using operators such as crossover, mutation, and selection of survival to solve optimization problems. 16 In the operation of GA, a fitness function is defined to evaluate the probability of survival of each individual. Based on the probability values, the operations of selection, crossover and mutation are performed, and then new individuals are generated. ...
... 12,17 Comparing application with GA and IGA method in design and art, GA's fitness functions for formulating the human mind (considering aesthetics, experience, emotion, and preference) is very difficult. 16 IGA can be used solve problems that cannot be easily solved by GA. 17 Kim 17 presented a fashion design aid system based on IGA that recommended the best fashion design scheme by designer's evaluation. IGA is also applied in three-dimensional (3D) computer-aided design in the research of Graham et al. 18 Their system was also based on the designer's evaluation and provides inspiration of design form. ...
Article
In the early stage of a design process, it is important to create numerous and varied possible color plans for the target consumer group. These color plans help individual designers quickly find a few good color design schemes and give the design team ideas for brainstorming. The color plan of a product consists of the color combinations of its components and decorative patterns, which strongly influence the feelings of customers and thus their desire to purchase. However, very few studies have discussed these issues. In this study, a consultation and simulation system for product color planning that helps designers obtain the optimal color planning for components and decorative patterns of a product is proposed. This system includes two parts: one uses the interactive genetic algorithm to establish a creative evolutionary system that can interact with a designer to explore novel design schemes; the other extends the boundary extract algorithm to establish a color simulation system that can apply colors to the areas of product components and decorative patterns for color simulation. Finally, a case study of color planning for a motorcycle model is used to verify the feasibility of the proposed system. © 2012 Wiley Periodicals, Inc. Col Res Appl, 38, 375–390, 2013
... Nevertheless, analogue design exploration is cumbersome and tedious, as changes require lots of effort. For this, specifically dedicated digital design tools are constantly developed for more than two decades, not only to analyze and evaluate, but also to generate and explore alternative design candidates (Janssen et al. 2002). Woodbury et al. (2000), broadly acknowledges such tools as design space explorers intended to provide novel and effective design candidates. ...
... Applying ideas from complex systems to architecture is a relatively new one. An early pioneer in the field was John Frazer who started working on these ideas as early as in the 1960s [3] He has also advocated the concept of creative design tools [4]. Developing software design tools based on the principles of complex systems was pursued by the Emergent Design Group (EDG) at MIT. Between 1997 and 2001, the group produced a number of different generative design tools. ...
Article
Full-text available
In this paper we describe the Evolutionary Component Surface System (ECSS). It is a software tool for generating, analyzing and optimizing structural component surfaces. The surfaces are created from a limited set of architectural parts. We can create a large number of different surface articulations using simple rules of connectivity. The generated structures are self supporting envelopes. Through their articulation the surfaces create inhabitable space and where they reach the ground they define their own points of support. The form-generating process is complemented with an evolutionary algorithm to help search the space of possible outcomes. An important aspect of the tool is that design as well as structural and fabrication aspects have been considered from the outset.
... Current practice is supporting a transition away from a linear work flow that promotes engineering as mere support for architectural design, toward a multidisciplinary approach where performance-based tools and processes provide the mediation between the participants and the design (Janssen, Frazer, & Tang, 2002). More consideration is being given to whole of building lifecycle considerations earlier on in the design process, which is necessitating the embrace of integrated design policies, technologies and processes (Succar, 2009). ...
Article
Full-text available
Decisions made in the earliest stage of architectural design have the greatest impact on the construction, lifecycle cost and environmental footprint of buildings. Yet the building services, one of the largest contributors to cost, complexity, and environmental impact, are rarely considered as an influence on the design at this crucial stage. In order for efficient and environmentally sensitive built environment outcomes to be achieved, a closer collaboration between architects and services engineers is required at the outset of projects. However, in practice, there are a variety of obstacles impeding this transition towards an integrated design approach. This paper firstly presents a critical review of the existing barriers to multidisciplinary design. It then examines current examples of best practice in the building industry to highlight the collaborative strategies being employed and their benefits to the design process. Finally, it discusses a case study project to identify directions for further research.
... The tools went beyond the standard, poorly understood stereographic projections . Frazer has also embraced the idea of creative design tools [52] [7] and in particular he has advocated the use of EC for exploration rather than optimization [21]. CAs have been used by other architecture researchers to generate form and structure. ...
Article
Full-text available
We present an algorithmic growth process that is an extension of Lindenmayer’s Map L-systems. This growth process relies upon a set of rewrite rules, a map axiom and a geometric interpreter which is integrated with a 3D simulated environment. The outcome of the growth process is a digital surface in 3D space which has “grown” within and in response to its environment. We have developed a complementary evolutionary algorithm that is able to take over the task of generating the rewrite rules set for a growth process. Using a quantitative multi-objective fitness function that evaluates a variety of surface properties, the integrated system (evolutionary algorithm and growth process) can explore and generate diverse and interesting surfaces with a resemblance of organic form. The algorithms have been implemented to create a design tool for architects called Genr8.
... The latter are formulated by setting a domain of possible solutions, some test for measuring the fitness of a candidate solution and some method for generating candidate solutions. There are some criticisms of this definition, most notably Janssen et al. [2002] argue that design cannot be seen as a 'search-space' problem which is a common theme in Artificial Intelligence programming, but is rather a generative process that unfolds through the project. With regard to design as a 'knowledge-activity' as designers normally use stored knowledge to perform their tasks, Mitchell writes that first-order predicate calculus was considered during the 70s. ...
Thesis
Full-text available
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 Multi-Objection Design Optimisation (MDO) generate many variations of the design object virtually, in order to negotiate what constitutes the optimum solution. This thesis examines the strategies faced when utilizing such techniques for the integration of service design at the early stages of building design - the means of representation and the mechanism of optimisation used to describe each instanced design variation - noting the complexity of handling both qualitative and quantitative criteria and ideas.
... The idea that there might exist a single optimal solution to a certain design 'problem' has already been countered by what might be described as Humphrey's oblivion argument. Many researchers in the field of design have highlighted various incompatibilities between design and search (Janssen 2001). For example Horst Rittel (Churchman, 1967;Rittel and Webber 1973) describes certain types of problems as "wicked problems". ...
... A key element in this method is an algorithmic model created by a designer that defines how design variants are developed and evaluated. This algorithmic model is referred to as the design schema (Janssen et al., 2000(Janssen et al., , 2002Janssen, 2004). The design schema captures the identifiable character of a family of designs. ...
Conference Paper
Full-text available
Visual programming languages enable users to create computer programs by manipulating graphical elements rather than by entering text. The difference between textual languages and visual languages is that most textual languages use a procedural programming model, while most visual languages use a dataflow programming model. When visual programming is applied to design, it results in a new modelling approach that we refer to 'visual dataflow modelling' (VDM). Recently, VDM has becoming increasingly popular within the design community, as it can accelerate the iterative design process, thereby allowing larger numbers of design possibilities to be explored. Furthermore, it is now also becoming an important tool in performance-based design approaches, since it may potentially enable the closing of the loop between design development and design evaluation. A number of CAD systems now provide VDM interfaces, allowing designers to define form generating procedures without having to resort to scripting or programming. However, these environments have certain weaknesses that limit their usability. This paper will analyse these weaknesses by comparing and contrasting three VDM environments: McNeel Grasshopper, Bentley Generative Components, and Sidefx Houdini. The paper will focus on five key areas: * Conditional logic allow rules to be applied to geometric entities that control how they behave. Such rules will typically be defined as if-then-else conditions, where an action will be executed if a particular condition is true. A more advanced version of this is the while loop, where the action within the loop will be repeatedly executed while a certain condition remains true. * Local coordinate systems allow geometric entities to be manipulated relative to some convenient local point of reference. These systems may be either two-dimensional or three-dimensional, using either Cartesian, cylindrical, or spherical systems. Techniques for mapping geometric entities from one coordinate system to another also need to be considered. * Duplication includes three types: simple duplication, endogenous duplication, and exogenous duplication. Simple duplication consists of copying some geometric entity a certain number of times, producing identical copies of the original. Endogenous duplication consist of copying some geometric entity by applying a set of transformations that are defined as part of the duplication process. Lastly, exogenous duplication consists of copying some geometric entity by applying a set of transformations that are defined by some other external geometry. * Part-whole relationships allow geometric entities to be grouped in various ways, based on the fundamental set-theoretic concept that entities can be members of sets, and sets can be members of other sets. Ways of aggregating data into both hierarchical and non-hierarchical structures, and ways of filtering data based on these structures need to be considered. * Spatial queries include relationships between geometric entities such as touching, crossing, overlapping, or containing. More advanced spatial queries include various distance based queries and various sorting queries (e.g. sorting all entities based on position) and filtering queries (e.g. finding all entities with a certain distance from a point). For each of these five areas, a simple benchmarking test case has been developed. For example, for conditional logic, the test case consists of a simple room with a single window with a condition: the window should always be in the longest north-facing wall. If the room is rotated or its dimensions changed, then the window must re-evaluate itself and possibly change position to a different wall. For each benchmarking test-case, visual programs are implemented in each of the three VDM environments. The visual programs are then compared and contrasted, focusing on two areas. First, the type of constructs used in each of these environments are compared and contrasted. Second, the cognitive complexity of the visual programming task in each of these environments are compared and contrasted.
... Evolutionary algorithms are loosely based on the neo-Darwinian model of evolution through natural selection. Such algorithms consist of a cyclical process whereby whole populations of individuals are continuously being generated and manipulated in order to ensure that members of the population gradually evolve and adapt [32]. ...
Article
Full-text available
The authors have been involved in the use of generative techniques for building envelope design since 1968 and the use of genetic algorithms since 1990. Recent work has focused on incorporating optimisation functions into form generating processes in order for new forms responding to varied design environments to be created and determined. This paper will summarise the authors' previous work in this field and explain the theory behind this approach, and illustrate recent developments. While the initial implementation of a new building envelope design system is reported in more details in a related paper at this conference, this paper outlines its main features and points out the direction at which it is to be fully developed and further improved.
... The design system was used for visual inspiration of designers like the conceptual approach reported in Singh et al (2019). The generative system built on extensive research in "Evolutionary Design Systems and Generative Processes", as published for example by Janssen et al (2002). The integration of quantitative performance measures closed "the loop of design and analysis", as discussed earlier by Toth et al (2011). ...
... Evolutionary algorithms (EAs) are a class of algorithms inspired by the process of biological evolution by natural selection. They have been used by many researchers to explore and optimise in the area of design (Bentley, 1998;Rosenman, 1997;Watabe and Okino, 1993;Yang and Soh, 2002;Gero, 1996;Hemberg and O'Reilly, 2002;Janssen et al., 2004;Gero et al., 1996Gero et al., , 1994Hornby and Pollack, 2001a;Hemberg and O'Reilly, 2004;O'Reilly and Hemberg, 2007). ...
Article
Full-text available
Evolutionary methods afford a productive and creative alternative design workflow. Crucial to success is the choice of formal representation of the problem. String-rewriting context-free grammars (CFGs) are one common option in evolutionary computation, but their suitability for design is not obvious. Here, a CFG-based evolutionary algorithm for design is presented. The process of meta-design is described, in which the CFG is created and then refined to produce an improved design language. CFGs are contrasted with another grammatical formalism better known in architectural design: Stiny's shape grammars. The advantages and disadvantages of the two types of grammars for design tasks are discussed.
... One of the reasons relies on the fact that technical detail on the algorithm behind GD tools are not disclosed by the software house [11] and, to the authors' knowledge, open-source solutions are not available yet. One of the first definitions is proposed by Frazer, who shows that the engineering applications of the evolutionary approach are interested in convergence on an optimal solution in response to clearly defined computable criteria for selection, define as "convergent evolution by natural selection" [12]. Instead, regarding the aims Shea et al. summarize the purpose as: "generative design systems are aimed at creating new design processes that produces spatially novel yet efficient and buildable designs through exploitation of current computing and manufacturing capabilities" [13]. ...
Conference Paper
In the last past years, computer-aided technologies to improve existing products by widening the design space have been largely investigated. Topology optimization and generative design are two of the most representative technologies of such kind. This paper aims at investigating the use of generative design and topology optimization techniques to improve products whose design has not changed radically over the years. The product under investigation is a disk brake floating caliper that is the most common solution for commercial vehicles. In general, increasing the stiffness of the floating caliper while keeping its weight under control is desirable both from performance and fuel consumption point of view. The solution here proposed aims at exploiting two new ways to approach the engineering design process and evaluate which one is more suitable for problems of this kind. Starting from the original carrier shape, acquired with laser scanning, the two technologies have been applied on the same initial conditions. The initial design space volume corresponds to the acquired shape, the loads and the constraints for the simulation have been drawn reasonably to resemble the actual operating conditions. Keeping the input parameters constants, two different off-the-shelf software packages have been used to perform the computation and with the objective of maximizing the stiffness of the carrier while reducing its mass. The comparison and the improvements on the final designs have been drawn taken as reference to the original caliper.
... For instances, customer needs was identified using the concepts of Quality Function Deployment (QFD) and fuzzy set theory [113][114] and fuzzy inference [115]. Product form was automatically created using EA [42,[116][117][118], fuzzy logic [119] hybrid of fuzzy, neural network and GA [120], and hybrid of neural network and kansei expert system [121]. Fuzzy logic technique was also applied to evaluate and select design concepts [122][123][124][125]. Affective user satisfaction was analyzed and modeled using a fuzzy rule-based method [126]. ...
Article
Full-text available
The paper reviews the existing and state-of-the-art computer-aided technologies and computational techniques, which can be applied to jewelry design and casting. A broad array of techniques are selected and ordered into three key parts: design; model-making; and casting, that outline the core of computer-aided jewelry design and casting. Computer-aided design and haptic technologies are surveyed in the purposes of supporting the design of jewelry and shape modeling. Rapid prototyping and computer numerical controlled machines are reviewed in the functions of fabricating physical jewelry models and developing the direct tools. Computer-aided engineering technologies are investigated in the rationales of simulating lost-wax casting process and optimizing process parameters. Artificial intelligence techniques are reviewed in intentions of developing algorithmic designs, and assisting hard computations and parameter optimizations in designing and casting. With those computer advanced technologies, major challenges and solutions are systematically discussed and commented to address new developments for jewelry industry.
Article
This paper reports a computer program to generate novel designs for the arrangement of furniture within a simulated room. It is based on the engagement-reflection computer model of the creative processes. During engagement the system generates material in the form of sequences of actions (e.g. change the colours of the walls, include some furniture in the room, modify their colour, and so on) guided by content and knowledge constraints. During reflection, the system evaluates the composition produced so far and, if it is necessary, modifies it. We discuss the implementation of the system and some of its most salient features, especially the use of a computational model for creativity in the terrain of design. We argue that this kind of model opens new possibilities for the simulation of the design processes as well as the development of tools.
Article
This paper presents a methodology for producing good solutions for spatial form for non-routine design more efficiently. The methodology is based on augmenting a conventional evolutionary design approach with a method for improving suboptimal design solutions using domain-specific knowledge. This approach is based conceptually on the practice of plastic surgery, i.e. making minor adjustments to an entity, based on some desired qualities. While a conventional evolutionary design approach can produce reasonably good design solutions in an environment of knowledge uncertainty, plastic surgery, using domain-specific knowledge to manipulate the phenotype, can further improve such solutions in an efficient manner. This paper demonstrates how such a technique can be applied to the generation of spatial form.
Article
This thesis argues that natural complex systems can provide an inspiring example for creating software which incorporates emergent, self-organizing and adaptive properties. The advantages of complex sys- tems are their natural resilience, redundancy and adaptivity. A generalization of neural networks and boolean networks called computational networks is presented as a model for complex systems. It is argued that this model satisfies the required properties for modeling complex systems. Furthermore, it is asserted that a computational network, being a network of mathematical functions, is appropriate for solving classification problems. For the design of computational networks an evolutionary design algorithm is constructed. Additionally, four extensions of this algorithm are presented. Each extension is inspired by natural evolution and theories from the evolutionary computing literature. An impor- tant component is a novel generative representation which can reuse substructures of computational networks. Experiments with this component have shown that it facilitates a higher level of complexity in the solution space, improving the computational network performance for more complex problems. Other components steer the evolutionary process towards a desired solution, either by introducing spe- cial stages during evolution, or by smoothing the fitness landscape. The experiments show that complex systems can be evolutionary designed to act as a classifier. The resulting computational network has a better performance on the Iris dataset compared to every classifier in the Weka classifier collection. Furthermore, an experiment was conducted using the TIMIT read speech dataset, the classifier was evo- lutionary designed using only 13 MFCC features, and a very small train set. Although the performance is not good enough to be of any practical use, the results are adequate given the limitations of the train data.
Article
xvi, 201 leaves : ill. ; 30 cm. PolyU Library Call No.: [THS] LG51 .H577P SD 2007 LeeH This thesis has developed an interactive system that uses parametric 2D and 3D shape grammars incorporating an evolutionary algorithm for exploring product forms at the early stage of design process. The evolutionary algorithm allows designers to explore product forms by modifying the control parameters of shapes and changing the application of shape grammar rules based on the interaction between designers and the system. In recent years, shape grammars have been used in Computer-Aided Design (CAD) systems for generating stylistically consistent and novel designs. In this approach to design concept generation, human subjective selections and evaluations are involved in controlling the parametric modification of the shapes and shape grammar rules. System based on this approach is referred to as Interactive Grammar Based Design System (IGBDS). An IGBDS is capable of reproducing large numbers of stylistically consistent designs as well as exploring novel designs. The design approach based on shape grammars, however, relies on the identification of quality shape grammar rules with sufficient accuracy but in the meantime maintaining a high degree of generality, in order for the system to generate forms with enough variations. The formulation of shape grammar rules useful for different specific design requirements in a computational system is difficult and time consuming in the domain of product form design, due to the complexity in the product surface modelling. This is so because the development of shape grammar rules requires tremendous amount of work in capturing the knowledge from the existing designs. However, most of the existing designs have different form features. It is difficult to find the consensus in generalizing the existing designs into shape grammar rules. In run time, the selection and evaluation processes of the shape parameters and the shape grammar rules are time consuming due to limited speed in rating and interaction between designers and the computer. To address these problems and to enhance the generative capability of shape grammars in supporting product design, this research focuses on two issues: 1) The development of systematic approach to the formulation of shape grammars combining 2D and 3D forms and 2) Extending the generative capability of the product design support systems which use shape grammars. The aim of these two focuses is to enhance the power of shape grammar based design approach in terms of dealing with complexity of real design applications and to explore the potential of integrating evolutionary methods with shape grammars for increasing diversity in product design. The motivation for such an integration is based on the hypothesis that shape grammar rules modified by the genetic code scripts of an evolutionary method (such as genetic algorithm) define a new combination of shape features for alternative designs. In this way, traditional shape grammars are extended to an interactive context in which generative and evolutionary computing methods are utilized with better potential of supporting product component design and configuration. Different scenarios in which designers interact with the implemented system in real design applications are studied and evaluated. The first issue involves an analytical approach to understanding the relations between product design and form complexity, by identifying and analysing the information associated with complex form creation. The research on this issue included the development of methods for the classification of product components, the definition of design spaces for the component configuration, the specification of design constraints and the spatial relationships among components. The second issue involves the development of a computational system for enhancing the generative capability of IGBDS in the product form exploration, by integrating an evolutionary algorithm with an IGBDS. This integration allows shape grammar rules to be modified at run time. This relied on a careful planning in retrieving the significant elements from the complex information network of shape grammars and encoding all the necessary information into genetic representation. A new representation scheme utilising both the power of genetic programming and shape grammar rule representations is developed, together with the control strategies for manipulating this new representation during an evolutionary design process. With such a method and system, the designers come to interact with the enhanced IGBDS to evaluate the designs and corresponding rules by determining the control parameters and control strategies in the evolutionary cycle. The system provides the visualisation of virtual 3D objects for the designers for their evaluation and selection, and allows them to explore alternative designs with shape grammar rules containing parametric variation potentials, through the integration of Genetic Algorithm (GA), Genetic Programming (GP) and parametric 2D and 3D shape grammars with labels. The methodology for research carried out in this thesis follows the analytical study of shape grammars and product forms with the development of new computational representations for the integration of evolutionary methods with shape grammars. The implemented system and knowledge base of the shape grammars are tested with realistic design examples. The research involves three major steps: 1) The development of the methods of deriving shape grammar rules in a product design domain, 2) The formulation of genetic representation and control strategies, and 3) The exploration of design and evaluation of the integrated IGBDS with real design examples. With the system developed in this research the designers can explore design with more flexibility in varying the weighting factors, determining the control parameters for the shape grammar rules, selecting appropriate control strategies for specific design characteristics, controlling order sequences of shape grammar rule application, and exploring form and configuration designs. For the evaluation of the proposed method, representation and implementation of an enhanced IGBDS, a shape grammar rule base for digital camera design is developed and two prototype systems are implemented using this rule base in order to study the feasibility of proposed system with its supporting components, including the integration with an external 3D solid modelling kernel. The development and experiments of two prototype evolutionary IGBDS illustrated the flexibility in using parametric 2D and 3D shape grammars with labels to explore a wide range of engineering and industrial design problems involving complex and intuitive conception of forms and products. Both implemented systems are interactive, with the first one using a normal evolutionary algorithm, and the second one using genetic programming with parametric shape grammars. The experiments showed that the second prototype is more flexible, while more complex to implement, for the exploration of forms in terms of variety with the parameters within shape grammar rules being changed by the evolutionary algorithms. Based on the analysis and the evaluation of the results achieved in the context of real product design, the thesis concludes on the applicability of shape grammars to real product design and proposes several strategies with which this research can be further advanced for complex form design and visualisation in product design. Ph.D., School of Design, The Hong Kong Polytechnic University, 2007
Article
The two critical issues related to product design exploration are addressed: the balance between stylistic consistency and innovation, and the control of design process under a great diversity of requirements. To address these two issues, the view of understanding product design exploration is first sought. In this view, the exploration of designs is not only categorized as a problem-solving activity but also as a problem-finding activity. A computational framework is developed based on this view, and it encompasses the belief that these two activities go hand in hand to accomplish the design tasks in an interactive design environment. The framework adopts an integration approach of two key computational techniques, shape grammars and evolutionary computing, for addressing the above two critical issues. For the issues of stylistic consistency, this paper focuses on the computational techniques in balancing the conflicts of stylistic consistency and innovation with shape grammars. For the issues of controlling design process, the practical concerns of monitoring the design process through various activities starting from the preparation works to the implementation of shape grammars have been emphasized in the development of this framework. To evaluate the effectiveness of the framework, the experiments have been set up to reflect the practical situations with which the designers have to deal. The system generates a number of models from scratch with numerical analysis that can be evaluated effectively by the designers. This reduces the designers' time and allows the designers to concentrate their efforts on performing higher level of design activities such as evaluation of designs and making design decisions.
Conference Paper
Full-text available
There is a growing need for parametric design software that communicates building performance feedback in early architectural exploration to support decision-making. This paper examines how the circuit of design and analysis process can be closed to provide active and concurrent feedback between architecture and services engineering domains. It presents the structure for an openly customisable design system that couples parametric modelling and energy analysis software to allow designers to assess the performance of early design iterations quickly. Finally, it discusses how user interactions with the system foster information exchanges that facilitate the sharing of design intelligence across disciplines.
Article
Once recorded in a sketch or model, the formal composition of a building influences its subsequent development. Each change or addition must fit together visually with the rest. This contextual influence is rarely supported by generative systems, which favor a top-down derivation of solutions from goals. In contrast, this research investigates the potential of generative systems to support the bottom-up process of exploring a formal situation and following its visual cues. The paper defines human–computer interaction guidelines for such a system and then examines a prototype. Results suggest that generative systems can provide context-sensitive support and that tacit methods of human–computer interaction could make generative systems more palatable to architectural designers.
Conference Paper
This paper introduces a platform that combines shape grammars with conventional simulation and analysis methods. The premise of this combination is to create an approach to synthesizing optimal shapes considering criteria requiring heat transfer and stress analysis for their evaluation. The necessary mechanisms and issues for integrating shape grammars with standard simulation systems are described. The benefits, challenges and future outlook of this approach with regards to traditional design synthesis systems are explored. Further, possible future research projects to extend the work are presented.
Chapter
The preconceptions that designers bring to the table when they are considering a particular design task are an unavoidable and necessary part of the design process. This paper first reviews the literature relating to the role of preconceptions in design, and then goes on to discuss computational tools that support the development and expression of such design preconceptions. As an example of such a tool, an outline is given of a generative evolutionary design system that allows designers to evolve families of designs that embody preconceived values and ideas.
Article
The preconceptions that designers bring to the table when they are considering a particular design task are an unavoidable and necessary part of the design process. This paper first reviews the literature relating to the role of preconceptions in design, and then goes on to discuss computational tools that support the development and expression of such design preconceptions. As an example of such a tool, an outline is given of a generative evolutionary design system that allows designers to evolve families of designs that embody preconceived values and ideas.
Article
Full-text available
We present a developmental genotype-phenotype growth process, or embryogeny, which is used to evolve, in silico, efficient three-dimensional structures that exhibit real-world architectural performance. The embryogeny defines a sequential assembly of architectural components within a three-dimensional volume, and indirectly establishes a regulatory network of components based on the principles of gene regulation. The implicitly regulated phenotypes suggest advances for the automatic design of physical structures, by improving scalability of the genotype encoding and embedding real-world constraints. We demonstrate that our model can evolve novel, yet efficient, architectural structures which exhibit emergent shape, topology and material distribution. Finally, we compare evolved structures against a "hand-coded" solution to illustrate that our model produces competitive results without prior knowledge of the design solution or direct human guidance.
Article
A platform for experimenting with population-based design exploration algorithms is presented, called Dexen . The platform has been developed in order to address the needs of two distinct groups of users loosely labeled as researchers and designers . Whereas the researchers group focuses on creating and testing customized toolkits, the designers group focuses on applying these toolkits in the design process. A platform is required that is scalable and extensible: scalable to allow computationally demanding population-based exploration algorithms to be executed on distributed hardware within reasonable time frames, and extensible to allow researchers to easily implement their own customized toolkits consisting of specialized algorithms and user interfaces. In order to address these requirements, a three-tier client–server system architecture has been used that separates data storage, domain logic, and presentation. This separation allows customized toolkits to be created for Dexen without requiring any changes to the data or logic tiers. In the logic tier, Dexen uses a programming model in which tasks only communicate through data objects stored in a key-value database. The paper ends with a case study experiment that uses a multicriteria evolutionary algorithm toolkit to explore alternative configurations for the massing and façade design of a large residential development. The parametric models for developing and evaluating design variants are described in detail. A population of design variants are evolved, a number of which are selected for further analysis. The case study demonstrates how evolutionary exploration methods can be applied to a complex design scenario without requiring any scripting.
Article
Parametric modelling run by the explicitly defined algorithms generating synchronically auditable dynamic forms and patterns, has become a prominent method especially in architecture. Though the use of parametric models has got wider in urban design, the critical reflection on the actual and possible application of the method in urbanism has fallen limited so far. The paper tends to relate parametric design with the contemporary understanding of urbanism with regards to the idea of design control in the the context of complexity. From this perspective, the actual performance of the model application in urban context is discussed with the renowned project of Kartal-Pendik Masterplan (Zaha Hadid Architects) in Istanbul, Turkey.
Article
Machines would be more useful if they could learn to perform tasks for which they were not given precise methods. Difficulties that attend giving a machine this ability are discussed. It is proposed that the program of a stored-program computer be gradually improved by a learning procedure which tries many programs and chooses, from the instructions that may occupy a given location, the one most often associated with a successful result. An experimental test of this principle is described in detail. Preliminary results, which show limited success, are reported and interpreted. Further results and conclusions will appear in the second part of the paper.
Article
Scitation is the online home of leading journals and conference proceedings from AIP Publishing and AIP Member Societies
Article
Rapid progress in the modeling of biological structures and simulation of their development has occurred over the last few years. It has been coupled with the visualization of simulation results, which has led to a better understanding of morphogenesis and given rise to new procedural techniques for realistic image synthesis. This paper reviews selected models of morphogenesis with a significant visual component.
Book
Genetic algorithms are founded upon the principle of evolution, i.e., survival of the fittest. Hence evolution programming techniques, based on genetic algorithms, are applicable to many hard optimization problems, such as optimization of functions with linear and nonlinear constraints, the traveling salesman problem, and problems of scheduling, partitioning, and control. The importance of these techniques is still growing, since evolution programs are parallel in nature, and parallelism is one of the most promising directions in computer science. The book is self-contained and the only prerequisite is basic undergraduate mathematics. This third edition has been substantially revised and extended by three new chapters and by additional appendices containing working material to cover recent developments and a change in the perception of evolutionary computation.
Article
Design as seen from the designer's perspective is a series of amazing imaginative jumps or creative leaps. But design as seen by the design historian, is a smooth progression or evolution of ideas that seems inevitable with hindsight. It is a characteristic of great ideas that they seem self-evident and inevitable after the event. But the next step is anything but obvious for the artist/creator/inventor/ designer stuck at that point just before the creative leap. They know where they have come from and have a general sense of where they are going, but often do not have a precise target or goal. This is why it is misleading to talk of design as a problem-solving activity—it is better defined as a problem-finding activity. This has been very frustrating for those trying to assist the design process with computer-based, problem-solving techniques. By the time the problem is defined, it has been solved. Indeed the solution is often the very definition of the problem. Design must be creative or it is mere imitation. Conceptual analogies such as search, search spaces and fitness landscapes aim to elucidate the design process.
Article
This part provides one of the links to the sister book 'Evolutionary Design by Computers' (Morgan Kaufmann,1999) by returning to the subject of creative evolutionary design. As before, this part explores the abilities of evolution to aid designers by generating novel and "creative" design solutions. Here we see both types of creative evolutionary system: methods designed to expand the creativity of designers and methods that produce novel and creative solutions automatically.
Article
: The problem of complex adaptations is studied in two largely disconnected research traditions: evolutionary biology and evolutionary computer science. This paper summarizes the results from both areas and compares their implications. In evolutionary computer science it was found that the Darwinian process of mutation, recombination and selection is not universally effective in improving complex systems like computer programs or chip designs. For adaptation to occur, these systems must possess "evolvability", i.e. the ability of random variations to sometimes produce improvement. It was found that evolvability critically depends on the way genetic variation maps onto phenotypic variation, an issue known as the representation problem. The genotype-phenotype map determines the variability of characters, which is the propensity to vary. Variability needs to be distinguished from variation, which are the actually realized differences between individuals. The genotype-phenotype map is the ...
An analysis of behaviour of a class of genetic adap-tive systems Doctoral Dissertation
  • K De
  • Jong
K De Jong, " An analysis of behaviour of a class of genetic adap-tive systems, " Doctoral Dissertation, University of Michigan, Dissertation Abstract International, 36(10), 5140B. (University Microfilms No 76-9381).
Universal Darwinism,” in Evolution from Molecules to Men
  • R Dawkins
A conceptual seeding technique for architectural design
  • J J H Frazer
  • Connor