Generative design

Last updated
Schema of generative design as an iterative process Generative Design Process.png
Schema of generative design as an iterative process
Samba, a piece of furniture created by Guto Requena with generative design Samba Collection.JPG
Samba, a piece of furniture created by Guto Requena with generative design

Generative design is an iterative design process that uses software to generate outputs that fulfill a set of constraints iteratively adjusted by a designer. Whether a human, test program, or artificial intelligence, the designer algorithmically or manually refines the feasible region of the program's inputs and outputs with each iteration to fulfill evolving design requirements. [1] By employing computing power to evaluate more design permutations than a human alone is capable of, the process is capable of producing an optimal design that mimics nature's evolutionary approach to design through genetic variation and selection.[ citation needed ] The output can be images, sounds, architectural models, animation, and much more. It is, therefore, a fast method of exploring design possibilities that is used in various design fields such as art, architecture, communication design, and product design. [2]

Contents

Generative design has become more important, largely due to new programming environments or scripting capabilities that have made it relatively easy, even for designers with little programming experience, to implement their ideas. [3] Additionally, this process can create solutions to substantially complex problems that would otherwise be resource-exhaustive with an alternative approach making it a more attractive option for problems with a large or unknown solution set. [4] It is also facilitated with tools in commercially available CAD packages. [5] Not only are implementation tools more accessible, but also tools leveraging generative design as a foundation. [6]

Generative design in architecture

Generative design in architecture is an iterative design process that enables architects to explore a wider solution space with more possibility and creativity. [7] Architectural design has long been regarded as a wicked problem. [8] Compared with traditional top-down design approach, generative design can address design problems efficiently, by using a bottom-up paradigm that uses parametric defined rules to generate complex solutions. The solution itself then evolves to a good, if not optimal, solution. [9] The advantage of using generative design as a design tool is that it does not construct fixed geometries, but take a set of design rules that can generate an infinite set of possible design solutions. The generated design solutions can be more sensitive, responsive, and adaptive to the problem.

Generative design involves rule definition and result analysis which are integrated with the design process. [10] By defining parameters and rules, the generative approach is able to provide optimized solution for both structural stability and aesthetics. Possible design algorithms include cellular automata, shape grammar, genetic algorithm, space syntax, and most recently, artificial neural network. Due to the high complexity of the solution generated, rule-based computational tools, such as finite element method and topology optimisation, are more preferable to evaluate and optimise the generated solution. [11] The iterative process provided by computer software enables the trial-and-error approach in design, and involves architects interfering with the optimisation process.

Historical precedent work includes Antoni Gaudí's Sagrada Família, which used rule based geometrical forms for structures, [12] and Buckminster Fuller's Montreal Biosphere where the rules to generate individual components is designed, rather than the final product. [13]

More recent generative design cases include Foster and Partners' Queen Elizabeth II Great Court, where the tessellated glass roof was designed using a geometric schema to define hierarchical relationships, and then the generated solution was optimized based on geometrical and structural requirement. [14]

Generative design in sustainable design

Generative design in sustainable design is an effective approach addressing energy efficiency and climate change at the early design stage, recognizing buildings contribute to approximately one-third of global greenhouse gas emissions and 30%-40% of total building energy use. [15] It integrates environmental principles with algorithms, enabling exploration of countless design alternatives to enhance energy performance, reduce carbon footprints, and minimize waste.

A key feature of generative design in sustainable design is its ability to incorporate Building Performance Simulations (BPS) into the design process. Simulation programs like EnergyPlus, Ladybug Tools, and so on, combined with generative algorithms, can optimize design solutions for cost-effective energy use and zero-carbon building designs. For example, the GENE_ARCH system used a Pareto algorithm with DOE2.1E building energy simulation for the whole building design optimization. [16] Generative design has improved sustainable facade design, as illustrated by the algorithm of cellular automata and daylight simulations in adaptive facade design. [17] In addition, genetic algorithms were used with radiation simulations for energy-efficient PV modules on high-rise building facades. [18] Generative design is also applied to life cycle analysis (LCA), as demonstrated by a framework using grid search algorithms to optimize exterior wall design for minimum environmental embodied impact. [19]

Multi-objective optimization embraces multiple diverse sustainability goals, such as interactive kinetic louvers using biomimicry and daylight simulations to enhance daylight, visual comfort and energy efficiency. [20] The study of PV and shading systems can maximize on-site electricity, improve visual quality and daylight performance. [21]

AI and machine learning (ML) further improve computation efficiency in complex climate-responsive sustainable design. one study employed reinforcement learning to identify the relationship between design parameters and energy use for a sustainable campus, [22] while some other studies tried hybrid algorithms, such as using the genetic algorithm and GANs to balance daylight illumination and thermal comfort under different roof conditions. [23] Other popular AI tools were also integrated, including deep reinforcement learning (DRL) and computer vision (CV) to generate an urban block according to direct sunlight hours and solar heat gains. [24] These AI-driven generative design methods enable faster simulations and design decision making, resulting in designs that are environmentally responsible.

Generative design in additive manufacturing

Additive manufacturing (AM) is a process that creates physical models directly from 3D data by joining materials layer by layer. It is used in industries to produce a variety of end-use parts, which are final components designed for direct application in products or systems. AM provides design flexibility and enables material reduction in lightweight applications, such as aerospace, automotive, medical, and portable electronic devices, where minimizing weight is critical for performance. Generative design, one of the four key methods for lightweight design in AM, is commonly applied to optimize structures for specific performance requirements. [25]

Generative design can help create optimized solutions that balance multiple objectives, such as enhancing performance while minimizing cost. [26] In design for additive manufacturing (DfAM), multi-objective topology optimization is used to generate a set of candidate solutions. Designers then assess these options using their expertise and key performance indicators (KPIs) to select the best option for implementation. [25]

However, integrating AM constraints (e.g.,speed of build, materials, build envelope, and accuracy) into generative design remains challenging, as ensuring all solutions are valid is complex. [25] Balancing multiple design objectives while limiting computational costs adds further challenges for designers. [27] To overcome these difficulties, researchers proposed a generative design method with manufacturing validation to improve decision-making efficiency. This method starts with a constructive solid geometry (CSG)-based technique to create smooth topology shapes with precise geometric control. Then, a genetic algorithm is used to optimize these shapes, and the method offers designers a set of top non-dominated solutions on the Pareto front for further evaluation and final decision-making. [27] By combining multiple techniques, this method can generate many high-quality solutions with smooth boundaries at lower computational costs, making it a practical approach for designing lightweight structures in AM.

Building on topology optimization methods, software providers introduced generative design features in their tools, helping designers set criteria and rank solutions. [25] Industry is driving advancements in generative design for AM, highlighting the need for tools that not only offer a range of solution choices but also streamline workflows for industrial use. [26]

See also

Related Research Articles

<span class="mw-page-title-main">Genetic algorithm</span> Competitive algorithm for searching a problem space

In computer science and operations research, a genetic algorithm (GA) is a metaheuristic inspired by the process of natural selection that belongs to the larger class of evolutionary algorithms (EA). Genetic algorithms are commonly used to generate high-quality solutions to optimization and search problems via biologically inspired operators such as selection, crossover, and mutation. Some examples of GA applications include optimizing decision trees for better performance, solving sudoku puzzles, hyperparameter optimization, and causal inference.

Global optimization is a branch of applied mathematics and numerical analysis that attempts to find the global minima or maxima of a function or a set of functions on a given set. It is usually described as a minimization problem because the maximization of the real-valued function is equivalent to the minimization of the function .

In computer science and mathematical optimization, a metaheuristic is a higher-level procedure or heuristic designed to find, generate, tune, or select a heuristic that may provide a sufficiently good solution to an optimization problem or a machine learning problem, especially with incomplete or imperfect information or limited computation capacity. Metaheuristics sample a subset of solutions which is otherwise too large to be completely enumerated or otherwise explored. Metaheuristics may make relatively few assumptions about the optimization problem being solved and so may be usable for a variety of problems. Their use is always of interest when exact or other (approximate) methods are not available or are not expedient, either because the calculation time is too long or because, for example, the solution provided is too imprecise.

Topology optimization is a mathematical method that optimizes material layout within a given design space, for a given set of loads, boundary conditions and constraints with the goal of maximizing the performance of the system. Topology optimization is different from shape optimization and sizing optimization in the sense that the design can attain any shape within the design space, instead of dealing with predefined configurations.

Model predictive control (MPC) is an advanced method of process control that is used to control a process while satisfying a set of constraints. It has been in use in the process industries in chemical plants and oil refineries since the 1980s. In recent years it has also been used in power system balancing models and in power electronics. Model predictive controllers rely on dynamic models of the process, most often linear empirical models obtained by system identification. The main advantage of MPC is the fact that it allows the current timeslot to be optimized, while keeping future timeslots in account. This is achieved by optimizing a finite time-horizon, but only implementing the current timeslot and then optimizing again, repeatedly, thus differing from a linear–quadratic regulator (LQR). Also MPC has the ability to anticipate future events and can take control actions accordingly. PID controllers do not have this predictive ability. MPC is nearly universally implemented as a digital control, although there is research into achieving faster response times with specially designed analog circuitry.

Protein design is the rational design of new protein molecules to design novel activity, behavior, or purpose, and to advance basic understanding of protein function. Proteins can be designed from scratch or by making calculated variants of a known protein structure and its sequence. Rational protein design approaches make protein-sequence predictions that will fold to specific structures. These predicted sequences can then be validated experimentally through methods such as peptide synthesis, site-directed mutagenesis, or artificial gene synthesis.

<span class="mw-page-title-main">Computer-aided architectural design</span> Way to visualize and design structures

Computer-aided architectural design (CAAD) software programs are the repository of accurate and comprehensive records of buildings and are used by architects and architectural companies for architectural design and architectural engineering. As the latter often involve floor plan designs CAAD software greatly simplifies this task.

<span class="mw-page-title-main">Building science</span>

Building Science is the science and technology-driven collection of knowledge to provide better indoor environmental quality (IEQ), energy-efficient built environments, and occupant comfort and satisfaction. Building physics, architectural science, and applied physics are terms used for the knowledge domain that overlaps with building science. In building science, the methods used in natural and hard sciences are widely applied, which may include controlled and quasi-experiments, randomized control, physical measurements, remote sensing, and simulations. On the other hand, methods from social and soft sciences, such as case study, interviews & focus group, observational method, surveys, and experience sampling, are also widely used in building science to understand occupant satisfaction, comfort, and experiences by acquiring qualitative data. One of the recent trends in building science is a combination of the two different methods. For instance, it is widely known that occupants' thermal sensation and comfort may vary depending on their sex, age, emotion, experiences, etc. even in the same indoor environment. Despite the advancement in data extraction and collection technology in building science, objective measurements alone can hardly represent occupants' state of mind such as comfort and preference. Therefore, researchers are trying to measure both physical contexts and understand human responses to figure out complex interrelationships.

Multi-objective optimization or Pareto optimization is an area of multiple-criteria decision making that is concerned with mathematical optimization problems involving more than one objective function to be optimized simultaneously. Multi-objective is a type of vector optimization that has been applied in many fields of science, including engineering, economics and logistics where optimal decisions need to be taken in the presence of trade-offs between two or more conflicting objectives. Minimizing cost while maximizing comfort while buying a car, and maximizing performance whilst minimizing fuel consumption and emission of pollutants of a vehicle are examples of multi-objective optimization problems involving two and three objectives, respectively. In practical problems, there can be more than three objectives.

Architectural design optimization (ADO) is a subfield of engineering that uses optimization methods to study, aid, and solve architectural design problems, such as optimal floorplan layout design, optimal circulation paths between rooms, sustainability and the like. ADO can be achieved through retrofitting, or it can be incorporated within the initial construction a building. Methods of ADO might include the use of metaheuristic, direct search or model-based optimisation. It could also be a more rudimentary process involving identification of a perceived or existing problem with a buildings design in the concept design phase.

Design Automation usually refers to electronic design automation, or Design Automation which is a Product Configurator. Extending Computer-Aided Design (CAD), automated design and Computer-Automated Design (CAutoD) are more concerned with a broader range of applications, such as automotive engineering, civil engineering, composite material design, control engineering, dynamic system identification and optimization, financial systems, industrial equipment, mechatronic systems, steel construction, structural optimisation, and the invention of novel systems.

<span class="mw-page-title-main">Grasshopper 3D</span> Programming language

Grasshopper is a visual programming language and environment that runs within the Rhinoceros 3D computer-aided design (CAD) application. The program was created by David Rutten at Robert McNeel & Associates. Programs are created by dragging components onto a canvas. The outputs of these components are then connected to the inputs of subsequent components.

<span class="mw-page-title-main">Parametric design</span> Engineering design method

Parametric design is a design method in which features, such as building elements and engineering components, are shaped based on algorithmic processes rather than direct manipulation. In this approach, parameters and rules establish the relationship between design intent and design response. The term parametric refers to the input parameters that are fed into the algorithms.

<span class="mw-page-title-main">Building performance simulation</span> Replication of aspects of building performance

Building performance simulation (BPS) is the replication of aspects of building performance using a computer-based, mathematical model created on the basis of fundamental physical principles and sound engineering practice. The objective of building performance simulation is the quantification of aspects of building performance which are relevant to the design, construction, operation and control of buildings. Building performance simulation has various sub-domains; most prominent are thermal simulation, lighting simulation, acoustical simulation and air flow simulation. Most building performance simulation is based on the use of bespoke simulation software. Building performance simulation itself is a field within the wider realm of scientific computing.

<span class="mw-page-title-main">Freeform surface machining</span> Machining techniques for complex surfaces

In manufacturing, freeform surface machining refers to the machining of complex surfaces that are not uniformly planar. The industries which most often manufactures free-form surfaces are basically aerospace, automotive, die mold industries, biomedical and power sector for turbine blades manufacturing. Generally 3- or 5-axis CNC milling machines are used for this purpose. The manufacturing process of freeform surfaces is not an easy job, as the tool path generation in present CAM technology is generally based on geometric computation so tool path are not optimum. The geometry can also be not described explicitly so errors and discontinuities occurrence in the solid structure cannot be avoided. Free-form surfaces are machined with the help of different tool path generation method like adaptive iso-planar tool path generation, constant scallop tool path generation, adaptive iso-parametric method, iso-curvature, isophote and by other methods. The different methods are chosen based on the parameters which is needed to be optimized.

<span class="mw-page-title-main">Simulation-based optimization</span>

Simulation-based optimization integrates optimization techniques into simulation modeling and analysis. Because of the complexity of the simulation, the objective function may become difficult and expensive to evaluate. Usually, the underlying simulation model is stochastic, so that the objective function must be estimated using statistical estimation techniques.

Design for additive manufacturing is design for manufacturability as applied to additive manufacturing (AM). It is a general type of design methods or tools whereby functional performance and/or other key product life-cycle considerations such as manufacturability, reliability, and cost can be optimized subjected to the capabilities of additive manufacturing technologies.

Design optimization is an engineering design methodology using a mathematical formulation of a design problem to support selection of the optimal design among many alternatives. Design optimization involves the following stages:

  1. Variables: Describe the design alternatives
  2. Objective: Elected functional combination of variables
  3. Constraints: Combination of Variables expressed as equalities or inequalities that must be satisfied for any acceptable design alternative
  4. Feasibility: Values for set of variables that satisfies all constraints and minimizes/maximizes Objective.
<span class="mw-page-title-main">Microstructures in 3D printing</span>

The use of microstructures in 3D printing, where the thickness of each strut scale of tens of microns ranges from 0.2mm to 0.5mm, has the capabilities necessary to change the physical properties of objects (metamaterials) such as: elasticity, resistance, and hardness. In other words, these capabilities allow physical objects to become lighter or more flexible. The pattern has to adhere to geometric constraints, and thickness constraints, or can be enforced using optimization methods. Innovations in this field are being discovered in addition to 3D printers being built and researched with the intent to specialize in building structures needing altered physical properties.

Power Surfacing is a computer-aided design software that allows users to create and edit complex freeform surfaces in SOLIDWORKS. It is developed by nPower Software, a division of IntegrityWare Inc., and is available as an add-in for SOLIDWORKS.

References

  1. ↑ Meintjes, Keith. ""Generative Design" – What's That? - CIMdata" . Retrieved 2018-06-15.
  2. ↑ ENGINEERING.com. "Generative Design: The Road to Production". www.engineering.com. Retrieved 2019-12-05.
  3. ↑ Schwab, Katharine (16 April 2019). "This is the first commercial chair made using generative design". Fast Company. Retrieved 13 August 2019.
  4. ↑ Prasanta, Rajamoney, Shankar A. Rosenbloom, Paul S.; Wagner, Chris Bose (2014-09-04). Compositional model-based design: A generative approach to the conceptual design of physical systems. University of Southern California. OCLC   1003551283.{{cite book}}: CS1 maint: multiple names: authors list (link)
  5. ↑ Barbieri, Loris; Muzzupappa, Maurizio (2022). "Performance-Driven Engineering Design Approaches Based on Generative Design and Topology Optimization Tools: A Comparative Study". Applied Sciences. 12 (4): 2106. doi: 10.3390/app12042106 .
  6. ↑ Anderson, Fraser; Grossman, Tovi; Fitzmaurice, George (2017-10-20). Trigger-Action-Circuits: Leveraging Generative Design to Enable Novices to Design and Build Circuitry. ACM. pp. 331–342. doi:10.1145/3126594.3126637. ISBN   9781450349819. S2CID   10091635.
  7. ↑ Krish, Sivam (2011). "A practical generative design method". Computer-Aided Design. 43 (1): 88–100. doi:10.1016/j.cad.2010.09.009.
  8. ↑ Rittel, Horst W. J.; Webber, Melvin M. (1973). "Dilemmas in a General Theory of Planning" (PDF). Policy Sciences. 4 (2): 155–169. doi:10.1007/bf01405730. S2CID   18634229. Archived from the original (PDF) on 30 September 2007.
  9. ↑ Mitchell, Melanie; Taylor, Charles E (1999). "Evolutionary computation: an overview". Annual Review of Ecology and Systematics. 30 (1): 593–616. Bibcode:1999AnRES..30..593M. doi:10.1146/annurev.ecolsys.30.1.593.
  10. ↑ Shea, Kristina; Aish, Robert; Gourtovaia, Marina (2005). "Towards integrated performance-driven generative design tools". Automation in Construction. 14 (2): 253–264. doi:10.1016/j.autcon.2004.07.002.
  11. ↑ Dapogny, Charles; Faure, Alexis; Michailidis, Georgios; Allaire, Grégoire; Couvelas, Agnes; Estevez, Rafael (2017). "Geometric constraints for shape and topology optimization in architectural design" (PDF). Computational Mechanics. 59 (6): 933–965. Bibcode:2017CompM..59..933D. doi:10.1007/s00466-017-1383-6. S2CID   41570887.
  12. ↑ Hernandez, Carlos Roberto Barrios (2006). "Thinking parametric design: introducing parametric Gaudi". Design Studies. 27 (3): 309–324. doi:10.1016/j.destud.2005.11.006.
  13. ↑ Edmondson, Amy C (2012). "Structure and pattern integrity". A Fuller explanation: The synergetic geometry of R. Buckminster Fuller (PDF). Springer Science & Business Media. pp. 54–60. doi:10.1007/978-1-4684-7485-5. ISBN   978-0-8176-3338-7.
  14. ↑ Williams, Chris JK (2001). Burry, Mark; Datta, Sambit; Dawson, Anthony; Rollo, John (eds.). The analytic and numerical definition of the geometry of the British Museum Great Court Roof (PDF). Proceedings of mathematics & design 2001: the third international conference. Vol. 200. Geelong Vic Australia: Deakin University. pp. 434–440. ISBN   0-7300-2526-8.
  15. ↑ Suphavarophas, Phattranis; Wongmahasiri, Rungroj; Keonil, Nuchnapang; Bunyarittikit, Suphat (May 2024). "A Systematic Review of Applications of Generative Design Methods for Energy Efficiency in Buildings". Buildings. 14 (5): 1311. doi: 10.3390/buildings14051311 . ISSN   2075-5309.
  16. ↑ Caldas, Luisa (2008-01-01). "Generation of energy-efficient architecture solutions applying GENE_ARCH: An evolution-based generative design system". Advanced Engineering Informatics. Intelligent computing in engineering and architecture. 22 (1): 59–70. doi:10.1016/j.aei.2007.08.012. ISSN   1474-0346.
  17. ↑ Kim, Jieun (2013-04-21). "Adaptive façade design for the daylighting performance in an office building: the investigation of an opening design strategy with cellular automata". International Journal of Low-Carbon Technologies. 10 (3): 313–320. doi:10.1093/ijlct/ctt015. ISSN   1748-1317.
  18. ↑ Vahdatikhaki, Faridaddin; Salimzadeh, Negar; Hammad, Amin (2022-03-01). "Optimization of PV modules layout on high-rise building skins using a BIM-based generative design approach". Energy and Buildings. 258: 111787. Bibcode:2022EneBu.25811787V. doi:10.1016/j.enbuild.2021.111787. ISSN   0378-7788.
  19. ↑ Hassan, Sally R.; Megahed, Naglaa A.; Abo Eleinen, Osama M.; Hassan, Asmaa M. (2022-07-15). "Toward a national life cycle assessment tool: Generative design for early decision support". Energy and Buildings. 267: 112144. Bibcode:2022EneBu.26712144H. doi:10.1016/j.enbuild.2022.112144. ISSN   0378-7788.
  20. ↑ Hosseini, Seyed Morteza; Heiranipour, Milad; Wang, Julian; Hinkle, Laura Elizabeth; Triantafyllidis, Georgios; Attia, Shady (2024-05-19). "Enhancing Visual Comfort and Energy Efficiency in Office Lighting Using Parametric-Generative Design Approach for Interactive Kinetic Louvers". Journal of Daylighting. 11 (1): 69–96. doi:10.15627/jd.2024.5. ISSN   2383-8701.
  21. ↑ Banti, Neri; Ciacci, Cecilia; Bazzocchi, Frida; Di Naso, Vincenzo (September 2024). "Enhancing Industrial Buildings' Performance through Informed Decision Making: A Generative Design for Building-Integrated Photovoltaic and Shading System Optimization". Solar. 4 (3): 401–421. doi: 10.3390/solar4030018 . hdl: 2158/1375896 . ISSN   2673-9941.
  22. ↑ Chang, Soowon; Saha, Nirvik; Castro-Lacouture, Daniel; Yang, Perry Pei-Ju (2019-09-01). "Multivariate relationships between campus design parameters and energy performance using reinforcement learning and parametric modeling". Applied Energy. 249: 253–264. Bibcode:2019ApEn..249..253C. doi:10.1016/j.apenergy.2019.04.109. ISSN   0306-2619.
  23. ↑ Yu, Zhongqi; Ge, Xinyi; Fan, Zhaoxiang; Zhou, Yihang; Lin, Dawei (2024-10-15). "Optimization framework for daylight and thermal environment of retractable roof natatoriums based on generative adversarial network and genetic algorithm". Energy and Buildings. 321: 114695. doi:10.1016/j.enbuild.2024.114695. ISSN   0378-7788.
  24. ↑ Han, Zhen; Yan, Wei; Liu, Gang (2021). "A Performance-Based Urban Block Generative Design Using Deep Reinforcement Learning and Computer Vision". In Yuan, Philip F.; Yao, Jiawei; Yan, Chao; Wang, Xiang; Leach, Neil (eds.). Proceedings of the 2020 DigitalFUTURES. Singapore: Springer. pp. 134–143. doi:10.1007/978-981-33-4400-6_13. ISBN   978-981-334-400-6.
  25. 1 2 3 4 Vaneker, Tom; Bernard, Alain; Moroni, Giovanni; Gibson, Ian; Zhang, Yicha (2020-01-01). "Design for additive manufacturing: Framework and methodology". CIRP Annals - Manufacturing Technology. 69 (2): 578–599. doi:10.1016/j.cirp.2020.05.006. ISSN   0007-8506.
  26. 1 2 Plocher, János; Panesar, Ajit (2019-12-05). "Review on design and structural optimisation in additive manufacturing: Towards next-generation lightweight structures". Materials & Design. 183: 108164. doi: 10.1016/j.matdes.2019.108164 . ISSN   0264-1275.
  27. 1 2 Wang, Zhiping; Zhang, Yicha; Bernard, Alain (2021-05-01). "A constructive solid geometry-based generative design method for additive manufacturing". Additive Manufacturing. 41: 101952. doi:10.1016/j.addma.2021.101952. ISSN   2214-8604.

Further reading

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.