Generative Design Approach Research Articles

Generative design of walkable urban cool spots using a novel heuristic GAN×GAN approach

Enhancing pedestrian-level outdoor thermal comfort (OTC) and walkability in urban environments is vital for mitigating thermal risks induced by global warming. This study introduces walkable urban cool spots (WUCS), a novel concept which incorporates pedestrian walkability into the design of thermally comfortable urban street blocks. The methodology combines OTC simulation, pedestrian walkability analyses, and surrogate models based on integrated generative adversarial networks (GAN×GAN)-enhanced genetic generative design (GGD) approach. And maximize the design metrics of WUCS through the multi objective optimization algorithm in GGD. The method is tested in To Kwa Wan, an urban renewal area in Hong Kong. Results demonstrate that it can efficiently identify high-performing WUCS solutions, with proportion of WUCS areas increasing from 53.3 % to 74 %, and the number of walkable urban cool spots increasing by 51 %. The average universal thermal climate index (UTCI) in high walkability areas decreasing from 31.7 °C to 30.5 °C, and total average UTCI during extreme heat days dropping from 31.73 °C to 31.22 °C. This research thus contributes an efficient design tool for enhancing both pedestrian-level OTC and walkability in urban environments.

A novel multi-objective generative design approach for sustainable building using multi-task learning (ANN) integration

Building Performance Optimization (BPO) plays a pivotal role in enhancing building performance, guaranteeing comfort while reducing resource consumption. Existing performance-driven generative design is computational demanding and difficult to be generalized to other similar buildings with difficult to be generalized to other building types or climate conditions. To fill this gap, this paper introduces a novel framework, which integrates multitask learning (MTL), code compliance check, and multi-objective optimization through NSGA-III algorithm. This framework is able to identify Paratoo Optimal design solutions, which comply with building codes, at low computation costs. The framework begins with selecting key design variables that are critical to building energy, comfort performance and life cycle cost. It then employs MTL to enhance the model's accuracy while reducing computational costs. Next, we designed a code compliance checking module followed by the NSGA-III optimization process, with the objective of identifying solutions that comply with existing building codes. The results indicate that the proposed MTL network achieved an R2 score of 0.983–0.993 on the test set. In the particular case study where equal weights are preferred, this approach yielded noteworthy reductions of 27.65%, 19.55%, and 31.13% in Building Energy Consumption (BEC), Life Cycle Cost (LCC), and Residue of continuous Daylight Autonomy (RcDA), respectively, for a rural dwelling, and exclude solutions that fail to satisfy regulatory standards. This framework allows designer to input the weights of each objective based on their preference and can be applied to other building types and climate regions. Last, we develop a solution selection tool based on the results output by the framework we proposed, which can be found at https://github.com/LiMingchen159/Village-House-Design-Strategy-in-Hebei-Province-China.

Research on computationally generative design of woven braced structure based on fiber composite material in architectural design industry

ABSTRACT With the intervention of computer algorithm-assisted design in the realm of contemporary architectural design, architectural spatial forms and corresponding design methods have improved significantly. However, the limitations of material strength and plasticity impose certain constraints on the architectural design of the new century. Based on this occurrence, this paper studies the development of a computational generative design system for woven braced structure composed of fiber-reinforced materials. Through experimental data of material performance, the research firstly argues feasibility of employing fiber composite materials to braced structure. The conclusion is that the structure designed and generated could produce a support of 1 ton per ㎡. Moreover, based on the ant colony algorithm and the algorithm principle of cellular automata on the Java platform, the study designs a generative system with iterative computing of force as the major axis to achieve the self-organization and adaptability of the braced structure. Above all, this paper proposes a design strategy engaging with computational generative design approach, as well as a design attempt for the material and form of architecture.

Form generative approach for front face design of electric vehicle under female aesthetic preferences

Vehicles are the most representative product of both transportation and industry. Fueled by the growing popularity of energy-saving and environmentally friendly ideas and policies, new energy technologies and their supporting industries are experiencing constant development and refinement. As a result, electric vehicles (EVs) are steadily displacing traditional fuel-powered vehicles as the dominant force in the vehicle market. The experience economy is driving a significant shift in the direction of EV development, which is transitioning from improving functionality to optimizing the emotional connection consumers have with their vehicles. This means the form factor of the vehicle itself is becoming a key element in attracting consumers and influencing purchasing decisions. Over half of China's EV consumer market is comprised of females. However, many companies continue to develop products solely from a male perspective, missing out on a vast market opportunity. Therefore, incorporating design elements that cater to female aesthetic preferences into EVs can undoubtedly play a crucial role in unlocking this significant segment of the market. Based on this, the paper proposes a form generative design approach that specifically caters to the preferences of female consumers within the theoretical framework of Kansei engineering.The research process begins by obtaining Kansei imagery through the collection and analysis of big data. Subsequently, eye-tracking experiments are conducted to define the key design elements of the automobiles. Concurrently, appropriate aesthetic measurement indicator (AMI) system is established. Next, AMI values are computed for the sample set. This data is then leveraged to create a mapping relationship with the Kansei imagery, enabling the objective reflection of subjective aesthetic evaluations. Finally, an integrated Kansei evaluation equation serves as the fitness function within a generative approach that utilizes genetic algorithms and visual AI to produce form design solutions for electric vehicles. The evaluation confirms that the proposed design approach successfully generates a substantial number of high-quality creative solutions that align with female aesthetic preferences, while maintaining low cost and high efficiency.

An improved generative design approach based on graph grammar for pattern drawing

An improved generative design approach based on graph grammar for pattern drawing

A Generative Design Approach to Improving the Environmental Performance of Educational Buildings in Hot Arid Climates. (Assiut National University as a Case Study)

The architectural design process is complex, involving diverse objectives that may be contradictory, and on which orientation exerts significant influence. The artificial intelligence application, Generative Design facilitates solving multi-objective design dilemmas through the creation and evaluation of numerous design alternatives. However, its exploration in educational buildings in hot arid climates remains limited. Given the impact of spaces’ function distribution, this study aims to optimize it in the typical plans of educational buildings. Employing a multi-objective design approach to enhance environmental performance. The study is conducted and evaluated in national universities in Egypt as a case study, specifically in Assiut City. The results revealed that the optimum design for a certain objective has not equated to optimal performance for other goals, highlighting an inherent contradiction between them. Among 26,334 possible alternatives for spaces’ function distribution, the difference between the optimal scenario and the least favourable one is significant for the parameters related to study spaces: natural daylighting, and visual comfort, ranging from 10% to 24%, besides around 1% difference for parameters related to the whole building, including energy consumption, thermal comfort, and carbon emission. This research offers a framework applicable to various building types. Additionally, it encourages decision-makers to adopt a no-cost sustainable design approach.

Data-driven modelling of building retrofitting with incomplete physics: A generative design and machine learning approach

Building performance simulation (BPS) based on physical models is a popular method for estimating the expected energy savings from energy-efficient building retrofitting. However, for many buildings, especially older buildings, built several decades ago, an operator do not have full access to the complete information for the BPS method. Incomplete information comes from the lack of detailed building physics, such as the thermal transmittance of some building components due to the deterioration of components over time. To address this challenge, this paper proposed a data-driven approach to support the decision-making of building retrofitting selections under incomplete information conditions. The data-driven approach integrates the backpropagation neural networks (BRBNN), fuzzy C-means clustering (FCM), and generative design (GD). It generates the required big database of building performance through generative design, which can overcome the problem of incomplete information during building performance simulation and energy-efficient retrofitting. The case study is based on old residential buildings in severe cold regions of China, using the proposed approach to predict energy-efficient retrofitting performance. The results indicated that the proposed approach can model the performance of residential buildings with more than 90% confidence, and show the variation of results. The core contribution of the proposed approach is to provide a way of performance prediction of individual buildings resulting from different retrofitting measures under the incomplete physics condition.

A vector encoding for topology finding of structured quad-based patterns for surface structures

Topology-optimisation strategies for structural design of discrete surface structures result in unstructured patterns that require post-rationalisation to limit the number and complexity of the various structural elements. Fabrication-related objectives still demand further processing. Designers need topology exploration, before topology optimisation, following a generative-design approach that is decoupled from density tuning and shape design, to produce high-quality patterns. Such an approach allows to flexibly embed multiple design constraints, benefit from state-of-the-art form-finding algorithms and explore design trade-offs of the multiple requirements related to architecture, engineering and construction. This research investigates a parameterisation strategy to encode topological exploration of structured patterns based on quad meshes. The focus is set on singular vertices, which connect an irregular number of blocks, cables, or beams. Singularities are independent from pattern density and geometry, and have a fundamental influence on the qualitative and quantitative performance of the structure. We introduce an L-system encoding a quad-mesh grammar into a string that describes topological transformations of these singularities. Design applications to a net and a gridshell demonstrate the influence of singularities on the design of surface structures, and highlight the flexibility and generality of the approach in terms of geometrical processing and performance metrics. Beyond exploration, this parameterisation strategy opens to novel applications of search and optimisation methods for generative design of singularities in structural patterns.

Investigation on Generative Designs for Fast Connector Socket (FCS) Using High-Strength Low-Alloy (HSLA) Steel

This study appears to focus on the application of metal additive manufacturing and generative designs to create more efficient and sustainable metallic components. The methodology developed in this study takes a comprehensive approach, from component selection to validation of outputs, which can lead to more efficient use of metallic parts in the future. Here CATIA V5 R20 used to create three new models of a fast connector socket (FCS) components, and then using ANSYS Workbench 16.0 apply the working load limit of 4.5 ton load with AISI 4142 380 qt steel alloy material used to the models to analysis. The Autodesk Fusion 360 software was then used to create generative designs for the fast connector socket models, which aimed to reduce mass, size, and material of the model while maintaining its effectiveness. The generative design approach used in this study is inspired by nature's evolutionary design process and considers production processes and cost restrictions. This approach can lead to the creation of more efficient and sustainable metallic components that can be used in various applications, including mechanical, marine, mining, construction, load lifting, pulling, and holding. Overall, this study highlights of the potential benefits. The comprehensive methodology used in this study can be applied to other metallic component designs to improve their efficiency and sustainability.

A Rule-Based Design Approach to Generate Mass Housing in Rural Areas of the North China Plain

Affected by the development strategy of Rural Space Reconstruction in China, the demand for rural mass housing has peaked in the North China Plain in the past 20 years. However, due to the inefficiency of conventional design methods, the rural houses built appear to have a noticeable trend of urbanization and homogeneity. To propose a more effective design approach to change the hitherto unsuccessful homogenized phenomenon of rural design, the study is based on investigating the composition, configuration and characteristics of the dwellings in some traditional villages of the eastern Shandong Province, and it compares and analyzes the differences between conventional methods and generation methods through three design tests: Test 1 is for the reappearance of a general mode of planning, Test 2 is based on the definition of shape-grammar-based rules and Test 3 is mainly used for the optimizing and programming of rules. Furthermore, based on the three prototypes of homestead combination, three-level rules are determined through the three tests mentioned above: Level-1 describes the housing prototype consisting of four homesteads, which generates a variety of spatial relations through the translation of homesteads. Level-2 describes a neighborhood prototype consisting of 16 homesteads, which generates various samples through splitting prototypes and expanding homesteads. Level-3 describes a block prototype consisting of 64 homesteads, which controls open space and identifies a given base during sample filling. Through the analysis of the tests results, the rationality and feasibility of the generative design approach are verified, proving that this approach effectively solves the design monotony problem that commonly exists in rural mass housing in the North China Plain.

Generative design approach to combine architected Voronoi foams with porous collagen scaffolds to create a tunable composite biomaterial

Regenerative biomaterials for musculoskeletal defects must address multi-scale mechanical challenges. Repairing craniomaxillofacial bone defects, which are often large and irregularly shaped, requires close conformal contact between implant and defect margins to aid healing. While mineralized collagen scaffolds can promote mesenchymal stem cell osteogenic differentiation in vitro and bone formation in vivo, their mechanical performance is insufficient for surgical translation. We report a generative design approach to create scaffold-mesh composites by embedding a macro-scale polymeric Voronoi mesh into the mineralized collagen scaffold. The mechanics of architected foam reinforced composites are defined by a rigorous predictive moduli equation. We show biphasic composites localize strain during loading. Further, planar and 3D mesh-scaffold composites can be rapidly shaped to aid conformal fitting. Voronoi-based composites overcome traditional porosity-mechanics relationship limits while enabling rapid shaping of regenerative implants to conformally fit complex defects unique for individual patients. Statement of SignificanceBiomaterial strategies for (craniomaxillofacial) bone regeneration are often limited by the size and complex geometry of the defects. Voronoi structures are open-cell foams with tunable mechanical properties which have primarily been used computationally. We describe generative design strategies to create Voronoi foams via 3D-printing then embed them into an osteogenic mineralized collagen scaffold to form a multi-scale composite biomaterial. Voronoi structures have predictable and tailorable moduli, permit stain localization to defined regions of the composite, and permit conformal fitting to effect margins to aid surgical practicality and improve host-biomaterial interactions. Multi-scale composites based on Voronoi foams represent an adaptable design approach to address significant challenges to large-scale bone repair.

Perfect prosthetic heart valve: generative design with machine learning, modeling, and optimization.

Majority of modern techniques for creating and optimizing the geometry of medical devices are based on a combination of computer-aided designs and the utility of the finite element method This approach, however, is limited by the number of geometries that can be investigated and by the time required for design optimization. To address this issue, we propose a generative design approach that combines machine learning (ML) methods and optimization algorithms. We evaluate eight different machine learning methods, including decision tree-based and boosting algorithms, neural networks, and ensembles. For optimal design, we investigate six state-of-the-art optimization algorithms, including Random Search, Tree-structured Parzen Estimator, CMA-ES-based algorithm, Nondominated Sorting Genetic Algorithm, Multiobjective Tree-structured Parzen Estimator, and Quasi-Monte Carlo Algorithm. In our study, we apply the proposed approach to study the generative design of a prosthetic heart valve (PHV). The design constraints of the prosthetic heart valve, including spatial requirements, materials, and manufacturing methods, are used as inputs, and the proposed approach produces a final design and a corresponding score to determine if the design is effective. Extensive testing leads to the conclusion that utilizing a combination of ensemble methods in conjunction with a Tree-structured Parzen Estimator or a Nondominated Sorting Genetic Algorithm is the most effective method in generating new designs with a relatively low error rate. Specifically, the Mean Absolute Percentage Error was found to be 11.8% and 10.2% for lumen and peak stress prediction respectively. Furthermore, it was observed that both optimization techniques result in design scores of approximately 95%. From both a scientific and applied perspective, this approach aims to select the most efficient geometry with given input parameters, which can then be prototyped and used for subsequent in vitro experiments. By proposing this approach, we believe it will replace or complement CAD-FEM-based modeling, thereby accelerating the design process and finding better designs within given constraints. The repository, which contains the essential components of the study, including curated source code, dataset, and trained models, is publicly available at https://github.com/ViacheslavDanilov/generative_design.

Customized shading solutions for complex building façades: the potential of an innovative cement-textile composite material through a performance-based generative design

PurposeThe paper aims to investigate the comfort-related performances of an innovative solar shading solution based on a new composite patented material that consists of a cement-based matrix coupled with a stretchable three-dimensional textile. The paper’s aim is, through a performance-based generative design approach, to develop a high-performance static shading system able to guarantee adequate daylit spaces, a connection with the outdoors and a glare-free environment in the view of a holistic and occupant-centric daylight assessment.Design/methodology/approachThe paper describes the design and simulation process of a complex static shading system for digital manufacturing purposes. Initially, the optical material properties were characterized to calibrate radiance-based simulations. The developed models were then implemented in a multi-objective genetic optimization algorithm to improve the shading geometries, and their performance was assessed and compared with traditional external louvres and overhangs.FindingsThe system developed demonstrates, for a reference office space located in Milan (Italy), the potential of increasing useful daylight illuminance by 35% with a reduced glare of up to 70%–80% while providing better uniformity and connection with the outdoors as a result of a topological optimization of the shape and position of the openings.Originality/valueThe paper presents the innovative nature of a new composite material that, coupled with the proposed performance-based optimization process, enables the fabrication of optimized shading/cladding surfaces with complex geometries whose formability does not require ad hoc formworks, making the process fast and economic.

Structural and thermal generative design using reinforcement learning-based search strategy for additive manufacturing

This paper proposes a reinforcement learning-based topology optimization (TO)/generative design approach using the Upper Confidence Bound (UCB) method to achieve a diverse set of optimal part designs for additive manufacturing. The UCB method has been integrated into two density-based TO problems – a compliance minimization problem and a thermal conduction problem along with Design for Additive Manufacturing (DfAM) filters to ensure improved additive manufacturability of the resultant topologies using different AM processes. The DfAM constraints are enforced by applying the support minimization filter and the thin feature minimization constraint in the TO model. The Solid Isotropic Material Penalization based TO model is perturbed to various levels of exploration and exploitation using the UCB exploration parameter to present different optimal designs. Unlike other data-reliant deep learning methods used in TO, the non-data-driven learning method proposed in this research is based on historical TO iterations integrated into a DfAM-constrained TO model, and it improves the method’s scalability to real-world and often computationally expensive part design applications. This paper fulfills a gap in computationally efficient methods for exploring generative designs of structural and thermal loaded parts with improved functional performance and additive manufacturability.

Proposing Digital Design Methodology for Furniture Products by Integrating Generative Design Approach to Conventional Process

Purpose: Considering the growing digital transformations in design field, this research aims to explore the advance language of design - generative design. The study focuses on integration of generative design and parametric modeling techniques with conventional furniture design process to develop a digital design and development methodology for furniture products by doing practical work in Rhino and Grasshopper.
 Methodology: For this purpose, a comparative analysis is drawn and three practicals performed in Rhino Grasshopper.
 Results: The author learned one of the design tool (Grasshopper) and investigate the possible ways to integrate this digital design process with the conventional process. These examples illustrate the liberty to design and explore any form that is imaginable and offers flexibility in the development process to make multiple design options. This digital way of designing leads to better accuracy, quicker adaptation to the initial concepts, ability to produce new alternatives, ease of revision, quality and realistic results and most importantly ready to manufacture products. This research was carried out, specifically, keeping the industrial environment of Pakistan Furniture Industry in reference.
 Unique Contribution to Theory, Policy and Practice: This research proposal helped the author to create an awareness at a very initial level in the targeted scope with the hope to encourage authorities to take some serious steps towards the institutionalization of technological advancement in the design education sector. This research not only honed the author’s knowledge in the state of the art but also enabled him to share more advance knowledge about CAD tools with his students. By following and integrating advance design tools to the design process, developments in furniture industry in Pakistan can be made possible in a short time.

Experimental and simulated study of 3D-printed couplings’ suitability for industrial application

This paper explores the possibility of applying reverse engineering to flexible coupling spare parts through additive manufacturing. Although couplings’ simplicity makes them go unnoticed, they connect elements that transmit power between two shafts, thus being an essential component for most of the machinery currently used in the industry. In this study, flexible couplings with different infill density (60% and 80%) were 3D printed by the fused filament fabrication technique. The original and the additive manufactured couplings were modelled to compare their compressive response and energy-absorbing characteristics, and experimental tests were performed to validate finite element analysis. To derive an optimal material distribution within coupling structure, a generative design approach was conducted through nTopology software. With this novel simulation-driven design, it is possible to reduce the weight of the redesigned part up to 15.8% by defining the wall thickness of the internal structure based on the results of finite element simulation, while maintaining its functionality. Moreover, an economic-environmental study was carried out. Results ensure that the 3D printed prototypes are suitable for replacing the original one under its current operating conditions. Additionally, the economic study shows that the redesigned couplings allow companies to save more than €2700 per coupling in relation to CO2 emission payments.

Direct additive manufacturing of metal parts for automotive applications

Additive manufacturing or three-dimensional (3D) printing offers tremendous opportunities for the automotive industry to reduce vehicle weight and improve vehicle performance through consolidating parts, tailoring material properties, enabling multifunctional components, and simplifying manufacturing processes. However, additive manufacturing research for direct manufacturing of automotive components is limited, partially because of the sheer volume of automotive production. In this paper, we explore the potential of direct manufacturing of metallic vehicle components using additive manufacturing coupled with the generative design approach. Using a radar mounting bracket as an example, we show that desired part strength and safety performance can be achieved with 42 % weight reduction and simplified manufacturing and assembly process. A production cost analysis was also conducted based on two mainstream additive manufacturing systems. The result suggests that the cost of metal powder is the limiting factor for wider adoption of additive manufacturing in the automotive industry.

Planning Walkable Cities: Generative Design Approach towards Digital Twin Implementation

The idea of a walkable city refers to the extent to which the built environment encourages people to walk by establishing comfortable pedestrian routes, which allows people to connect to numerous services with reasonable effort and time. Walkability is currently regarded as a “good to know about” rather than a “must-have” factor for sustainable development. A combination of walkability with a standard design strategy, such as generative design, may result in a more efficient way of planning a walkable city. Interestingly, the sole indicator taken into account for walkability in the generative design domain is “distance to amenities”, while in reality, other parameters, such as the comfort factor, could also influence walkability. Therefore, in this research, we developed a workflow based on the generative design, which considers the comfort dimension in combination with distance to amenities and street-level greeneries. We also included the human perspective, given that walkability is always personal. This research successfully generated three different scenarios of walkability-optimal urban plans, where the highest walkability is 82.43 (very walkable). Furthermore, the baseline scenario of two different locations also aligns with people’s perspectives when compared. In addition, we found that the inclusion of a temporal dimension, enhanced 3D-related indicators, and constraints should benefit future research.

Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers

Abstract Biological systems in nature have evolved for millions of years to adapt and survive the environment. Many features they developed can be inspirational and beneficial for solving technical problems in modern industries. This leads to a specific form of design-by-analogy called bio-inspired design (BID). Although BID as a design method has been proven beneficial, the gap between biology and engineering continuously hinders designers from effectively applying the method. Therefore, we explore the recent advance of artificial intelligence (AI) for a data-driven approach to bridge the gap. This paper proposes a generative design approach based on the generative pre-trained language model (PLM) to automatically retrieve and map biological analogy and generate BID in the form of natural language. The latest generative pre-trained transformer, namely generative pre-trained transformer 3 (GPT-3), is used as the base PLM. Three types of design concept generators are identified and fine-tuned from the PLM according to the looseness of the problem space representation. Machine evaluators are also fine-tuned to assess the mapping relevancy between the domains within the generated BID concepts. The approach is evaluated and then employed in a real-world project of designing light-weighted flying cars during its conceptual design phase The results show our approach can generate BID concepts with good performance.

Precision Calorimeter Model Development: Generative Design Approach

In a wide range of applications, heating or cooling systems provide not only temperature changes, but also small temperature gradients in a sample or industrial facility. Although a conventional proportional-integral-derivative (PID) controller usually solves the problem, it is not optimal because it does not use information about the main sources of change—the current power of the heater or cooler. The quality of control can be significantly improved by including a model of thermal processes in the control algorithm. Although the temperature distribution in the device can be calculated from a full-fledged 3D model based on partial differential equations, this approach has at least two drawbacks: the presence of many difficult-to-determine parameters and excessive complexity for control tasks. The development of a simplified mathematical model, free from these shortcomings, makes it possible to significantly improve the quality of control. The development of such a model using generative design techniques is considered as an example for a precision adiabatic calorimeter designed to measure the specific heat capacity of solids. The proposed approach, which preserves the physical meaning of the equations, allows for not only significantly improving the consistency between the calculation and experimental data, but also improving the understanding of real processes in the installation.