检索结果-内蒙古大学图书馆

multi-objective optimization for site location problems through hybrid genetic algorithm with neural networks

JOURNAL OF CHEMICAL ENGINEERING OF JAPAN 1999年第1期32卷 51-58页

作者： Shimizu, Y Toyohashi Univ Technol Toyohashi Aichi 4418580 Japan

With the aim of developing a flexible optimization method for managing conflict resolution, this paper concerns itself with site location problems under multi-objectives. As known from the term NIMBY (Not In My Back Yard), disposal site location problems of hazardous waste is an eligible case study associated with environmental and economic concerns. After describing the problem generally as a multi-objective mixed-integer program, we have proposed an intelligence supported approach that extends the hybrid genetic algorithm developed by the author to derive the best-compromise solution, For this purpose, we have developed a novel modeling method of value function using neural networks, and incorporated it into the approach. As a result, we can provide a practical and effective method in which the hybrid strategy maintains its advantages of relying on good matches between the solution methods and the problem properties such as a genetic algorithm for unconstrained discrete optimization and a mathematical program for constrained continuous ones. Finally, by taking an example formulated as a multi-objective mixed-integer linear program, we have examined the effectiveness of the proposed approach numerically.

关键词： process systems multi-objective genetic algorithm neural networks mixed-integer programs disposal site location

来源：评论

学校读者我要写书评

暂无评论

Machine learning and genetic algorithm as tools for single and multi-objective shape optimization of micromixers with Cantor fractal structure

引用

BRAZILIAN JOURNAL OF CHEMICAL ENGINEERING 2024年第4期41卷 1327-1344页

作者： Cao, Jingzhi Chen, Xueye Ludong Univ Sch Chem & Mat Sci 186 Middle Hongqi Rd Yantai 264025 Shandong Peoples R China Ludong Univ Coll Transportat Yantai 264025 Shandong Peoples R China

Shape optimization of micromixers with Cantor fractal structures on the top and bottom walls has been conducted using a combination of three-dimensional Navier-Stokes analysis, Machine Learning (ML), and multi-objective genetic algorithm (MOGA) for both single and multi-objective optimization objectives. Numerical analysis has been systematically conducted employing two distinct working fluids, namely water and ethanol, while operating at a Reynolds number (Re) of unity (Re = 1). The optimization endeavor has been executed by manipulating two design variables that pertain to dimensionless geometric parameters. The single-objective optimization is centered on the selection of mixing effectiveness as the primary objective function, whereas the multi-objective optimization entails the consideration of two objective functions, specifically, the pressure drop and the mixing index at the exit. The Latin hypercube sampling (LHS) method is employed as an experimental design technique to systematically explore the parameter space within the design domain. It is utilized for the purpose of strategically selecting design points within this domain. Additionally, surrogate models for the objective functions are established through the application of ML. In the context of single-objective optimization, the Sequential Linear Programming (SLP) method is employed to iteratively derive the optimal objective function. Meanwhile, for multi-objective optimization, the genetic algorithm (GA) is applied to delineate the Pareto optimal frontier (POF) of the micromixer. Subsequently, K-means clustering is utilized as a technique for the purpose of classifying the optimized outcomes, followed by the selection of representative points within the solution space. In the context of single-objective optimization, it is observed that the micromixer featuring a Cantor fractal structure exhibits a noteworthy enhancement in mixing efficiency, surpassing that of the reference design (RD) by a substant

关键词： multi-objective genetic algorithm Machine learning Pareto optimal front Single and multi-objective shape optimization Cantor fractal structure

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of sheet metal forming process using Pareto-based genetic algorithm

引用

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 2008年第1-3期208卷 499-506页

作者： Liu Wei Yang Yuying Harbin Inst Technol Sch Mat Sci & Engn Harbin 150001 Peoples R China

Finite element analysis and optimization technique have been integrated to solve the optimal process parameters of sheet metal forming by transforming multi-objective problem into a single-objective problem in many studies. In this paper, a Pareto-based multi-objective genetic algorithm was applied to optimize sheet metal forming process. in the proposed optimal model, blank-holding force and draw-bead restraining force were optimized as design variables in order to make objective functions of fracture, wrinkle, insufficient stretching and thickness varying minimized simultaneously. The steps of optimization procedure include the using of Latin hypercube design for sample producing, response surface model for coarse fitting and incremental finite element analysis program for exact solving. An auto-body panel stamping case shows that this approach is more effective and accurate than traditional finite element analysis method and the 'trial and error' procedure. (C) 2008 Elsevier B.V. All rights reserved.

关键词： Sheet metal forming Finite element analysis Latin hypercube design Response surface model multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimisation of injector and diesel engine by genetic algorithm: Nu-SVR modelling

引用

INTERNATIONAL JOURNAL OF HEAVY VEHICLE SYSTEMS 2020年第3期27卷 340-358页

作者： Taghavifar, Hadi Anvari, Simin Malayer Univ Fac Engn Dept Mech Engn Malayer Iran Xi An Jiao Tong Univ Sch Chem Engn & Technol Xian Peoples R China

The current study deals with application of evolutionary multi-objective genetic algorithm (MOGA) in a 1.8 L Ford diesel engine to enhance the power, fuel consumption, and air-fuel uniformity. To do so, four design parameters of engine geometry and injector parameters are defined and three sub-objectives are considered to get either maximised or minimised On the sub-objectives, constraints are imposed to introduce the feasible solutions. The best solution is obtained at RunID66 from 70 design points. The results showed that increasing bowl radius after a certain point is not useful for enhancement of the mixture homogeneity. In the second part of the study, support vector regression (SVR) technique is applied on the input and output data to make a model to predict the engine power.

关键词： diesel engine diesel injector Nu-SVR MOGA multi-objective genetic algorithm Pareto front

来源：评论

学校读者我要写书评

暂无评论

multi-objective multi-population biased random-key genetic algorithm for the 3-D container loading problem

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2015年 89卷 80-87页

作者： Zheng, Jia-Nian Chien, Chen-Fu Gen, Mitsuo Natl Tsing Hua Univ Hsinchu 30013 Taiwan Fuzzy Log Syst Inst Iizuka Fukuoka 8200067 Japan

The container loading problem (CLP) has important industrial and commercial application for global logistics and supply chain. Many algorithms have been proposed for solving the 2D/3D container loading problem, yet most of them consider single objective optimization. In practice, container loading involves optimizing a number of objectives. This study aims to develop a multi-objective multi-population biased random-key genetic algorithm for the three-dimensional single container loading problem. In particular, the proposed genetic algorithm applied multi-population strategy and fuzzy logic controller (PLC) to improve efficiency and effectiveness. Indeed, the proposed approach maximizes the container space utilization and the value of total loaded boxes by employing Pareto approach and adaptive weights approach. Numerical experiments are designed to compare the results between the proposed approach and existing approaches in hard and weak heterogeneous cases to estimate the validity of this approach. The results have shown practical viability of this approach. This study concludes with discussions of contributions and future research directions. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Container loading genetic algorithm multi-objective genetic algorithm Fuzzy logic controller Cutting and packing

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of membrane structures based on Pareto genetic algorithm

引用

Journal of Harbin Institute of Technology(New Series) 2010年第5期17卷 622-630页

作者：伞冰冰孙晓颖武岳 School of Civil Engineering Harbin Institute of Technology

A multi-objective optimization method based on Pareto genetic algorithm is presented for shape design of membrane structures from a structural view *** non-dimensional variables are defined as optimization variables,which are decision factors of shapes of membrane *** objectives are proposed including maximization of stiffness,maximum uniformity of stress and minimum reaction under external *** multi-objective genetic algorithm is introduced to solve the Pareto ***,the dependence of the optimality upon the optimization variables is derived to provide guidelines on how to determine design ***,several examples illustrate the proposed methods and *** study shows that the multi-objective optimization method in this paper is feasible and efficient for membrane structures;the research on Pareto solutions can provide explicit and useful guidelines for shape design of membrane structures.

关键词： membrane structures multi-objective optimization Pareto solutions multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of cooling air distributions of grate cooler with different clinker particles diameters and air chambers by genetic algorithm

引用

APPLIED THERMAL ENGINEERING 2017年 111卷 77-86页

作者： Shao, Wei Cui, Zheng Cheng, Lin Shandong Univ Inst Thermal Sci & Technol Jinan 250061 Peoples R China

The paper proposes a multi-objective optimization model of cooling air distributions of grate cooler in cement plant based on convective heat transfer principle and entropy generation minimization analysis. The heat transfer and flow models of clinker cooling process are brought out at first. Then the modified entropy generation numbers caused by heat transfer and viscous dissipation are considered as objective functions respectively which are optimized by genetic algorithm simultaneously. The design variables are superficial velocities of air chambers and thicknesses of clinker layer on different grate plates. The model is verified by a set of Pareto optimal solutions and scattered distributions of design variables. Sensitive analysis of average diameters of clinker particles and amount of air chambers are carried out based on the optimization model. The optimal cooling air distributions are compared by heat recovered, energy consumption of cooling fans and heat efficiency of grate cooler. And all of them are selected from the Pareto optimal solutions based on energy consumption of cooling fans minimization. The results show that the most effective and economic average diameter of clinker particles is 0.02 m and the amount of air chambers is 9. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Cooling air distribution of grate cooler multi-objective genetic algorithm Clinker particles diameter Air chambers amount

来源：评论

学校读者我要写书评

暂无评论

CBGA-ES⁺: A Cluster-Based genetic algorithm with Non-Dominated Elitist Selection for Supporting multi-objective Test Optimization

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2021年第1期47卷 86-107页

作者： Pradhan, Dipesh Wang, Shuai Ali, Shaukat Yue, Tao Liaaen, Marius Simula Res Lab POB 134 N-1325 Lysaker Norway Univ Oslo Problemveien 7 N-0315 Oslo Norway Testify As POB 134 N-1325 Lysaker Norway Simula Res Lab POB 134 N-1325 Lysaker Norway Cisco Syst Oslo Norway

Many real-world test optimization problems (e.g., test case prioritization) are multi-objective intrinsically and can be tackled using various multi-objective search algorithms (e.g., Non-dominated Sorting genetic algorithm (NSGA-II)). However, existing multi-objective search algorithms have certain randomness when selecting parent solutions for producing offspring solutions. In a worse case, suboptimal parent solutions may result in offspring solutions with bad quality, and thus affect the overall quality of the solutions in the next generation. To address such a challenge, we propose CBGA-ES+, a novel cluster-based genetic algorithm with non-dominated elitist selection to reduce the randomness when selecting the parent solutions to support multi-objective test optimization. We empirically compared CBGA-ES+ with random search and greedy (as baselines), four commonly used multi-objective search algorithms (i.e., multi-objective Cellular genetic algorithm (MOCell), NSGA-II, Pareto Archived Evolution Strategy (PAES), and Strength Pareto Evolutionary algorithm (SPEA2)), and the predecessor of CBGA-ES+ (named CBGA-ES) using five multi-objective test optimization problems with eight subjects (two industrial, one real world, and five open source). The results showed that CBGA-ES+ managed to significantly outperform the selected search algorithms for a majority of the experiments. Moreover, for the solutions in the same search space, CBGA-ES+ managed to perform better than CBGA-ES, MOCell, NSGA-II, PAES, and SPEA2 for 2.2, 13.6, 14.5, 17.4, and 9.9 percent, respectively. Regarding the running time of the algorithm, CBGA-ES+ was faster than CBGA-ES for all the experiments.

关键词： Elitist selection multi-objective genetic algorithm multi-objective test optimization search

来源：评论

学校读者我要写书评

暂无评论

Pareto design of Load Frequency Control for interconnected power systems based on multi-objective uniform diversity genetic algorithm (MUGA)

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2016年第0期80卷 333-346页

作者： Nikmanesh, E. Hariri, O. Shams, H. Fasihozaman, M. Univ Illinois Dept Mech & Ind Engn Chicago IL 60607 USA Islamic Azad Univ Dept Elect Engn South Tehran Branch Tehran Iran Univ Guilan Dept Mech Engn Rasht Iran

In this study, it is tried to employ a state-of-the-art multi-objective uniform-diversity genetic algorithm (MUGA) for Pareto optimization of PI/PID controllers in Load Frequency Control (LFC) of power systems. At first, multi objective optimization of a linear non-reheat two-area interconnected power system is conducted with respect to three conflicting objective functions. Gains of PI and PID controllers are considered as design variables while the objective functions are Integral Time multiply Absolute Error (ITAE), minimum damping ratio of dominant eigenvalues, and settling times in frequency and tie-line power deviations. To illustrate superiority of MUGA in finding optimum values of the deign variables, the proposed designs by MUGA are compared with those proposed by single and multi-objective optimization methods such as BFOA, hBFOA-PSO, and NSGA-II;the results indicate there is a noticeable improvement in response of the system. Further, robustness of the proposed designs is demonstrated by varying the system parameters from their nominal values and monitoring sensitivity of the system response to the variations. At the end, to take nonlinearities and physical constraints into account and to evaluate performance of MUGA in more complex system, a three unequal area hydro thermal system with generation rate constraints is considered. (c) 2016 Elsevier Ltd. All rights reserved.

关键词： multi-area power systems Load Frequency Control (LFC) PID controller Generation rate constraint (GRC) Pareto optimization multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective aero acoustic optimization of rear end in a simplified car model by using hybrid Robust Parameter Design, Artificial Neural Networks and genetic algorithm methods

引用

COMPUTERS & FLUIDS 2014年 90卷 123-132页

作者： Beigmoradi, Sajjad Hajabdollahi, Hassan Ramezani, Asghar SAIPA Automot Ind Res & Innovat Ctr Tehran Iran Vali e Asr Univ Rafsanjan Dept Mech Engn Rafsanjan Iran Zamyad Co Tehran Iran

In this paper, optimization of rear end of a simplified car model is performed considering aerodynamic and acoustic objectives. Slant angle, rear box angle, boat tail angle, and rear box length are considered as main variables of the rear end. For numerical simulation of flow around the model and studying aerodynamic noise, realizable turbulent model and broad band noise model are used, respectively. Simulation results are validated by the experimental results reported in the literature. To reduce number of simulations to reach optimum values of parameters, Taguchi method has been used. The results of Taguchi are in good agreement with simulation results. Then, the results of Taguchi have been used to obtain a relation between parameters and objectives employing Artificial Neural Networks. Optimization of the model has been conducted by the Neural Network and multi objective genetic algorithm methods. Finally, flow around the optimized model has been studied by numerical simulation and results have been reported. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Computational Fluid Dynamics Drag coefficient Aerodynamic noise Taguchi method Neural Networks multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：