A Generative Design Method Based on a Graph Transformation System

2021 ◽  
pp. 367-378
Author(s):  
Grażyna Ślusarczyk ◽  
Barbara Strug ◽  
Ewa Grabska
2021 ◽  
Vol 1104 (1) ◽  
pp. 012036
Author(s):  
Rajneesh Jaisawal ◽  
Vandana Agrawal

Arts ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 103
Author(s):  
Pippin Barr

Film adaptation is a popular approach to game design, but it prioritizes blockbuster films and conventional “game-like” qualities of those films, such as shooting, racing, or spatial exploration. This leads to adaptations that tend to use the aesthetics and narratives of films, but which miss out on potential design explorations of more complex cinematic qualities. In this article, I propose an experimental game design method that prioritizes an unconventional selection of films alongside strict game design constraints to explore tensions and affinities between cinema and videogames. By applying this design method and documenting the process and results, I am able both to present an experimental set of videogame film adaptations, along with potentially generative design and development themes. In the end, the project serves as an illustration of the nature of adaptation itself: a series of pointed compromises between the source and the new work.


Author(s):  
Zhen Han ◽  
Wei Yan ◽  
Gang Liu

AbstractIn recent years, generative design methods are widely used to guide urban or architectural design. Some performance-based generative design methods also combine simulation and optimization algorithms to obtain optimal solutions. In this paper, a performance-based automatic generative design method was proposed to incorporate deep reinforcement learning (DRL) and computer vision for urban planning through a case study to generate an urban block based on its direct sunlight hours, solar heat gains as well as the aesthetics of the layout. The method was tested on the redesign of an old industrial district located in Shenyang, Liaoning Province, China. A DRL agent - deep deterministic policy gradient (DDPG) agent - was trained to guide the generation of the schemes. The agent arranges one building in the site at one time in a training episode according to the observation. Rhino/Grasshopper and a computer vision algorithm, Hough Transform, were used to evaluate the performance and aesthetics, respectively. After about 150 h of training, the proposed method generated 2179 satisfactory design solutions. Episode 1936 which had the highest reward has been chosen as the final solution after manual adjustment. The test results have proven that the method is a potentially effective way for assisting urban design.


2021 ◽  
Vol 6 (1) ◽  
pp. 36-47
Author(s):  
Sawan Kumar Rai ◽  
Harit Keawmuang ◽  
Himanshu Variyavwala ◽  
Laith Shatnawi

The constant need for improvement drives humans to look for the best possible option in every field. Computer Aided Design (CAD) is no exception, to follow the best method of designing a product and finalizing it, researchers came up with an idea to generate multiple designs using fixed input values and finalizing the most appropriate one. The objective is achieved using an iterative design process based on algorithms by a specific software. Generative design introduces a new experience based on the Integration of machine dynamics in the manufacturing of objects and about experience. In this work generative design method was investigated on an articulated rod, one of the most important components of the rotary engine, to effectively improve the overall working performance of the engine and enhance its performance by decreasing its mass. Since fuel consumption by the machine can be greatly reduced by lowering the mass, so the goal is to minimize the weight of the rod while mechanical characteristics have to be within the acceptable values. Also, finite element analysis (FEA) was investigated on the part as to ensure the reliability of the rod before and after optimization.


2021 ◽  
Vol 12 (23) ◽  
pp. 22-32
Author(s):  
Anton Kralj ◽  
◽  
Davor Skejić ◽  

Structural project is based on technical regulations, structural codes, construction conditions, and client requirements. Through the structural design process, some important decisions that can significantly affect the final result must be implemented. The most important factor for optimal design is the reduction in material and overall work costs. Selecting appropriate joint configurations that can reduce the overall weight and work on the structure is critical. To examine a significant number of possible configurations and their effect on structural behavior, the generative design method (GDM) is used. In this study, software is custom developed, and a relevant example of generative joint structural design is provided. The methodology for the optimal joint and structure design is described comprehensively. The final results show that the GDM is an effective methodology for application in the design of steel structures.


Sign in / Sign up

Export Citation Format

Share Document