scholarly journals Optimization Design System for Composite Structures Based on Grid Technology

2007 ◽  
Vol 20 (1) ◽  
pp. 55-59 ◽  
Author(s):  
Wen-yuan CHENG ◽  
Yan CHANG ◽  
De-gang CUI ◽  
Xiang-hui XIE
Keyword(s):  
Composite Structures ◽  
Optimization Design ◽  
Design System ◽  
Grid Technology

Composite Structure Optimization Design System Based on Grid Technology

2007 ◽  
Vol 334-335 ◽  
pp. 453-456
Author(s):  
Wen Yuan Cheng ◽  
De Gang Cui ◽  
Yan Chang ◽  
Xiang Hui Xie
Keyword(s):  
Genetic Algorithm ◽  
Composite Structure ◽  
Composite Structures ◽  
Optimization Design ◽  
Structure Design ◽  
Design System ◽  
Grid Technology ◽  
Great Effort ◽  
Optimization Approach ◽  
Element Analysis

In the traditional iterative design process for composite structures, it is difficult to achieve an optimal solution even though a great effort is made. A genetic optimization system based on grid technology offers an automatic and efficient approach for composite structure redesign and optimization. A genetic algorithm system, which integrates Genetic Algorithm Optimization (GAO) software and a Finite Element Analysis (FEA) based commercial package, has been developed as a tool for composite structure design and analysis. The GAO is capable of tailoring large number of composite design variables and taking the time-consuming FEA results to calculate objective function value and conduct optimization in high accuracy. By operating the system employing the Grid technology and Artificial Neural Network (ANN) method, significant time saving in numerical analysis can be achieved. A user friendly interface has also been built in the system. In the paper, aeroelastic tailoring of a composite wing has been taken as a numerical example to demonstrate the optimization approach. The numerical results show that an optimal design has been achieved to meet the design requirement.

scholarly journals Automatic Design System with Generative Adversarial Network and Convolutional Neural Network for Optimization Design of Interior Permanent Magnet Synchronous Motor

2021 ◽  
Author(s):  
Yuki Shimizu ◽  
Shigeo Morimoto ◽  
Masayuki Sanada ◽  
Yukinori Inoue
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Convolutional Neural Network ◽  
Permanent Magnet ◽  
Optimization Design ◽  
Design System ◽  
Automatic Design ◽  
Wide Range ◽  
Interior Permanent Magnet ◽  
Long Time

The optimal design of interior permanent magnet synchronous motors requires a long time because finite element analysis (FEA) is performed repeatedly. To solve this problem, many researchers have used artificial intelligence to construct a prediction model that can replace FEA. However, because the training data are generated by FEA, it takes a very long time to obtain a sufficient amount of data, making it impossible to train a large-scale prediction model. Here, we propose a method for generating a large amount of data from a small number of FEA results using machine learning. An automatic design system with a deep generative model and a convolutional neural network is then constructed. With its sufficient data, the proposed system can handle three topologies and three motor parameters in a wide range of current vector regions. The proposed system was applied to multi-objective optimization design, with the optimization completed in 13-15 seconds.

scholarly journals Automatic Design System with Generative Adversarial Network and Convolutional Neural Network for Optimization Design of Interior Permanent Magnet Synchronous Motor

2021 ◽  
Author(s):  
Yuki Shimizu ◽  
Shigeo Morimoto ◽  
Masayuki Sanada ◽  
Yukinori Inoue
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Convolutional Neural Network ◽  
Permanent Magnet ◽  
Optimization Design ◽  
Design System ◽  
Automatic Design ◽  
Wide Range ◽  
Interior Permanent Magnet ◽  
Long Time

The optimal design of interior permanent magnet synchronous motors requires a long time because finite element analysis (FEA) is performed repeatedly. To solve this problem, many researchers have used artificial intelligence to construct a prediction model that can replace FEA. However, because the training data are generated by FEA, it takes a very long time to obtain a sufficient amount of data, making it impossible to train a large-scale prediction model. Here, we propose a method for generating a large amount of data from a small number of FEA results using machine learning. An automatic design system with a deep generative model and a convolutional neural network is then constructed. With its sufficient data, the proposed system can handle three topologies and three motor parameters in a wide range of current vector regions. The proposed system was applied to multi-objective optimization design, with the optimization completed in 13-15 seconds.

Optimization Design for Laminated Composite Structure Based on Kriging Model

2012 ◽  
Vol 217-219 ◽  
pp. 179-183
Author(s):  
Wen Guo Zhu ◽  
Zhi Jun Meng ◽  
Jun Huang ◽  
Wei He
Keyword(s):  
Composite Structures ◽  
Optimization Design ◽  
Minimum Weight ◽  
Laminated Composite ◽  
Kriging Model ◽  
Optimization Method ◽  
Optimization Strategy ◽  
Laminated Composite Structures ◽  
Sample Points ◽  
Optimization Efficiency

An effective optimization method is developed for laminated composite structures using two-level optimization strategy based on Kriging model and genetic algorithm (GA). Firstly, the design of experiment (DOE) technique is used to create sample points and MSC.Nastran is employed to obtain the response (minimum weight subjected to bulking and strength constraints) of each sample point. Based on sample points and the corresponding responses, the Kriging model is formulated. Secondly, GA is performed to obtain the best thickness by optimizing the Kriging model as objective function. Then, the best stacking sequence is obtained basing on lamination parameters using GA. This paper takes a Z shape composite stiffened plate as example to verify the feasibility of the method above. The results illustrate that it can significantly save computational costs and can greatly improve the optimization efficiency.

scholarly journals Optimization Design and Application of Underground Reinforced Concrete Bifurcation Pipe

2015 ◽  
Vol 2015 ◽  
pp. 1-7
Author(s):  
Chao Su ◽  
Zhenxue Zhu ◽  
Yangyang Zhang ◽  
Niantang Jiang
Keyword(s):  
Mathematical Model ◽  
Reinforced Concrete ◽  
Optimization Design ◽  
Particle Swarm Optimization Algorithm ◽  
Design System ◽  
Hydropower Station ◽  
Optimization Analysis ◽  
Swarm Optimization ◽  
Working Status ◽  
Accuracy And Stability

Underground reinforced concrete bifurcation pipe is an important part of conveyance structure. During construction, the workload of excavation and concrete pouring can be significantly decreased according to optimized pipe structure, and the engineering quality can be improved. This paper presents an optimization mathematical model of underground reinforced concrete bifurcation pipe structure according to real working status of several common pipe structures from real cases. Then, an optimization design system was developed based on Particle Swarm Optimization algorithm. Furthermore, take the bifurcation pipe of one hydropower station as an example: optimization analysis was conducted, and accuracy and stability of the optimization design system were verified successfully.

O&M Management and Control Practices of OPRS System Application

2014 ◽  
Vol 912-914 ◽  
pp. 1657-1662
Author(s):  
Jiang Xie ◽  
Shu Bao Hu ◽  
Ji Min Guo ◽  
Gang Wu ◽  
Sha Lin ◽  
...  
Keyword(s):  
Optimization Design ◽  
Management Control ◽  
Parameters Optimization ◽  
Control Mode ◽  
Design System ◽  
Control Methods ◽  
Current Management ◽  
Existing Problems ◽  
Pumping Equipment ◽  
And Control

To improve the system efficiency of rod pumped wells is a systematical engineering which depends on various cost control methods during the operational process and technologies of improving equipment & system operational efficiency, and closely related to pumping equipment selection, production parameters optimization design and well management. This paper analyzes the existing problems under current management mode and proposes to establish management control mode where application and of rod pumped well engineering design system software is organically linked with maintenance from the perspective of the user.

scholarly journals Research of Synthetical Optimization Design System of Micro-components Based on RST and GA

2009 ◽  
Vol 2 (2) ◽  
pp. 1-9
Author(s):  
Gong Xiaoyan ◽  
◽  
Xue He ◽  
Jiang Pingy ◽  
◽  
...  
Keyword(s):  
Optimization Design ◽  
Design System
Sign in / Sign up

Export Citation Format

Share Document