Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs

Jang, Seowoo; Yoo, Soyoung; Kang, Namwoo

doi:10.48550/arxiv.2008.07119

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reinforcement learning, combined with a simulated annealing algorithm and PSO, can improve the efficiency of searching for the optimal solution. By describing the generative design as a sequence problem and then using the given reference design to find the optimal combination of design parameters, RL is applied to the structural optimisation design of automobile wheels [13]. Q-learning of RL can be used for the design function of ship optimisation design to simulate the process of human designers using their experience for optimisation design [14].…”

Section: Reinforcement Learning For Engineering Designmentioning

confidence: 99%

Engineering design optimisation using reinforcement learning with episodic controllers

Yang

Cheng

Xiao

et al. 2022

Cognitive Comp and Systems

View full text Add to dashboard Cite

Engineers solving engineering design problems can be regarded as a gradual optimisation process that involves strategising. The process can be modelled as a reinforcement learning (RL) framework. This article presents an RL model with episodic controllers to solve engineering problems. Episodic controllers provide a mechanism for using the short‐term and long‐term memories to improve the efficiency of searching for engineering problem solutions. This work demonstrates that the two kinds of models of memories can be incorporated into the existing RL framework. Finally, an optimised design problem of a crane girder is illustrated by RL with episodic controllers. The work presented in this study leverages the RL model that has been shown to mimic human problem solving in engineering optimised design problems.

show abstract

Section: Reinforcement Learning For Engineering Designmentioning

confidence: 99%

Engineering design optimisation using reinforcement learning with episodic controllers

Yang

Cheng

Xiao

et al. 2022

Cognitive Comp and Systems

View full text Add to dashboard Cite

show abstract

“…Unlike a 2D pattern or structure, whose dimensions can be extracted using a coordinate system, [8] 3D geometric features of a complex structure embedded in a 2D image cannot be extracted easily without the aid of feature extraction tools. [12] As one of the most representative deep learning algorithms, the convolutional neural network (CNN) has been widely used in image classifications [13] and property prediction. [14] It was reported that the good performance of 3D features' extraction from a typical image was observed using the method in the study by Zhao et al [15] CNN has also shown its robust ability in predicting both local and global properties of a particular structure from 2D images, for example, in predicting the effective elastic stiffness of a specific 3D microstructure of composites (formed by a series of 2D images), [16] in predicting the effective thermal conductivity of composites from 2D cross-sections images, [17] and in predicting the main features of the stress-strain relationships of composite microstructures.…”

Section: Introductionmentioning

confidence: 99%

A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks

Hou

Saafi

et al. 2022

Advanced Intelligent Systems

View full text Add to dashboard Cite

Mechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design methods are promising tools for the design of advanced engineering systems. So far, there have been some studies of 2D patterns and structural designs based on ML techniques. However, a particular challenge remains in allowing complex 3D mechanical designs using ML techniques. Herein, a novel and experience‐free method to equip ML models with 3D design capabilities by combining a convolutional neuron network (CNN) with a deep convolutional generative adversarial network (DCGAN) is developed. The model directly receives 2D image‐based training data that define the complex 3D structures of a specific machine part. After the training process, an infinite number of new 3D designs can be generated by the proposed model, with their geometric and mechanical properties being accurately predicted at the same time. Moreover, the generated new designs can be fed back to expand the original input datasets for further ML model training and updating.

show abstract

“…Topology optimization creates one output optimized design from one existing part, while generative design creates many design options (Vlah et al, 2020). Generative design conducts design exploration and quickly generates thousands of design possibilities subject to given constraints (Jang et al, 2020). This too may be for a product which may not be in existence, while, topology optimization is well suited for scenarios where the designer already has the component's geometry and needs to reduce its weight.…”

Section: Introductionmentioning

confidence: 99%

Cars on Weight Loss: The Development of a Methodology for the Topology Optimization of Monolithic Components – Emerging Trends, Challenges and Opportunities

P. Chirinda,

Matope

2021

Proceedings of the International Conference on Industrial Engineering and Operations Management

View full text Add to dashboard Cite

Topology optimization plays a key role in the production of strong, lightweight functional parts. It uses mathematical algorithms to create optimized geometries under given constraints while at the same time improving performance. The conventional design process is time consuming and requires high technical expertise. The raisons d'etre for using algorithms is to reduce part development time and to keep the computational cost low. Further reduction in cost through weight savings can be realized though monolithic (one piece) design. In this method, weight reduction is achieved through the elimination of bolts, nuts and other joining material. Combining topology optimization with monolithic design also blends the benefit of weight reduction with the simplification of the assembly process. To reach optimum weight, an effective part development process requires a methodology which takes into account the objective function and all the constraints. The methodology can be used from the early stages, throughout the design process. This provides a step-by-step approach to the design process and keeps iterations to a minimum, thereby reducing the product development time. This research therefore focuses on the trends in the development of a methodology for the topology optimization of monolithic vehicle components. It also highlights the challenges and opportunities, placing emphasis on the vehicle aftermarket industry components.

show abstract

Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs

Cited by 3 publications

References 0 publications

Engineering design optimisation using reinforcement learning with episodic controllers

Engineering design optimisation using reinforcement learning with episodic controllers

A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks

Cars on Weight Loss: The Development of a Methodology for the Topology Optimization of Monolithic Components – Emerging Trends, Challenges and Opportunities

Contact Info

Product

Resources

About