检索结果-内蒙古大学图书馆

Tuning a model predictive controller for doubly fed induction generator employing a constrained genetic algorithm

IET ELECTRIC POWER APPLICATIONS 2019年第6期13卷 819-826页

作者： Rodrigues, Lucas L. Potts, Alain S. Vilcanqui, Omar A. C. Sguarezi Filho, Alfeu J. Fed Univ ABC UFABC Santo Andre SP Brazil Fed Univ Acre UFAC Rio Branco AC Brazil

This study presents a model predictive control (MPC) for a doubly fed induction generator (DFIG) power control using a state-space prediction model. genetic algorithms (GAs) have demonstrated their potential in finding good solutions for complex problems. However, GA in its original form lacks a mechanism for handling constraints. In this way, a method for tuning the MPC based on a novel constrained GA is proposed. In this way, the method permits a good solution for the weighing matrices with predetermined maximum requirements, such as maximum overshoot, just using the DFIG control simulation. Finally, experimental results are presented to endorse the proposed theory.

关键词： genetic algorithms predictive control asynchronous generators power control state-space methods machine control model predictive controller doubly fed induction generator constrained genetic algorithm model predictive control MPC power control state-space prediction model genetic algorithms GA DFIG control simulation

来源：评论

学校读者我要写书评

暂无评论

Optimization for Line of Cars Manufacturing Plant using constrained genetic algorithm

引用

JOURNAL OF ROBOTICS NETWORKING AND ARTIFICIAL LIFE 2018年第2期5卷 131-134页

作者： Kamei, Keiji Arai, Takafumi Nishinippon Inst Technol Dept Prod Syst 1-11 Aratsu Fukuoka Fukuoka 8000394 Japan Nissan Motor Kyushu Co Ltd 1-3 Shinhama Cho Fukuoka Fukuoka 8000395 Japan

Recently, improvement of production efficiency on cars manufacturers is required. However, that improvements under existing circumstances are depending on experience and intuition by workers. We propose to objectively and efficiently improve a production line based on a GA. The difficulty of applying a GA is the number of racks and boxes is predetermined, and so we apply constrained GA. The results of simulation for virtual production line show that our proposal succeeded in reducing about 10 seconds per a car compared with random positioning.

关键词： constrained genetic algorithm Plant Optimization Industrial Application Car manufacturing

来源：评论

学校读者我要写书评

暂无评论

Multi-class financial distress prediction based on hybrid feature selection and improved stacking ensemble model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 282卷

作者： Chen, Xiaofang Liu, Jiaming Wu, Chong Harbin Inst Technol Sch Management Harbin Heilongjiang Peoples R China Beijing Technol & Business Univ Sch Comp Sci & Artificial Intelligence Beijing Peoples R China

Multi-class financial distress prediction (FDP) can accurately assess the corporate financial status. Improving its prediction performance is the academic focus. Feature selection and classifier models play a crucial role in the multi-class FDP model. Therefore, this paper proposes a new hybrid feature selection and an improved stacking ensemble model. The hybrid feature selection uses information gain and an improved particle swarm optimization to filter the indicators. The hyperopt hyperparameter optimization method is used to optimize the base learners of stacking ensemble model;The F1-score weighted optimization method is designed for dealing with the discrepancies of the base learners;To objectively solve the combination configuration problem of stacking ensemble model, a constrained genetic algorithm is proposed. The Chinese listed companies are used as research objects for empirical research. The results show that the hybrid feature selection outperforms other feature selection. The F1-score weighted optimized model has 8.97% higher accuracy than the unweighted optimized model. The proposed model performs better in terms of accuracy, robustness, and sensitivity compared to the baseline models and the classifier models in existing multi-class FDP studies. The proposed hybrid feature selection and the improved stacking ensemble model provide new and reliable research ideas for multi-class FDP.

关键词： Multi-class financial distress prediction Stacking ensemble model Hybrid feature selection constrained genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Efficient FIR Filter Designs using constrained genetic algorithms based Optimization 2

Efficient FIR Filter Designs using Constrained Genetic Algor...

引用

2nd International Conference on Communication Control and Intelligent Systems (CCIS)

作者： Rana, K. P. S. Kumar, Vineet Nair, Sreejith S. Netaji Subhas Inst Technol Instrumentat & Control Engn Dept Sect 3 New Delhi 110078 India

ISBN: (纸本)9781509032105

In this work, an application of constrained genetic algorithm (CGA) based optimization approach has been explored for design of low pass and high pass finite impulse response (FIR) digital filters. To accomplish the task of optimal filter design, a novel constraint function has been proposed and integrated with the fitness function in CGA environment. CGA minimizes the fitness function under supervision of the proposed constraint. Performances of designed FIR digital filters have been compared with the recently published designs of same order and the intensive MATLAB simulations based investigations have confirmed the superiority of the proposed designs in terms of smaller pass band and stop band ripples.

关键词： constrained genetic algorithm Digital Filters Finite Impulse Response Constraint Function Fitness Function

来源：评论

学校读者我要写书评

暂无评论

An evolutionary network model of epileptic phenomena

引用

NEUROCOMPUTING 2011年第4期74卷 617-628页

作者： Raiesdana, Somayeh Firoozabadi, S. Mohammad P. Gholpayegani, S. Mohammad Hashemi Islamic Azad Univ Dept Biomed Engn Sci & Res Branch Tehran Iran Tarbiat Modares Univ Dept Phys Med Tehran Iran Amirkabir Univ Technol Fac Biomed Engn Tehran Iran

A simulation study has been done to address how the connectivity structure of the brain complex network relates to its dynamics and its behavioral properties. In this study, we intend to find plausible candidates of structural organization for an epileptic network capable of exhibiting its characteristic dynamics/behavior. For this purpose, a network of hippocampus CA3 neuronal population was implemented and evolved structurally with a constrained genetic algorithm (CGA). This optimization technique was favored by maximizing synchronization among excitable neurons, simulating seizure focus. On the other hand it was constrained to conserve some prescribed characteristics by penalizing infeasible structures in search space. Meanwhile some structural and dynamical aspects of the network were investigated to characterize the evolution path as well as the structure/dynamic to which the network ultimately reaches. The results of our simulations show the following: (1) a network with this evolutionary rewiring process is convergent to a synchronized state where seizures can arise. (2) Numerical analysis of the dynamical origin of seizures, calculated in each generation of CGA, indicates a critical point where global synchrony among multiple neuronal clusters may occur. (3) Different graph topologies more or less have similar endings. Indeed, the search for optimal patterns of connectivity in physiological or pathological models of brain activity may shed light on some of issues that must be dealt with in real neuronal systems;e.g. the control of seizures in epileptogenesis. The present paper tries to step forward this aim. (c) 2010 Elsevier B.V. All rights reserved.

关键词： Seizure modeling Complexity Synchronization constrained genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Green modular design for material efficiency: a leader follower joint optimization model

引用

JOURNAL OF CLEANER PRODUCTION 2013年 41卷 187-201页

作者： Ji, Yangjian Jiao, Roger J. Chen, Liang Wu, Chunlong Zhejiang Univ Dept Mech Engn Ind Engn Ctr Hangzhou 310027 Zhejiang Peoples R China Georgia Inst Technol George W Woodruff Sch Mech Engn Atlanta GA 30332 USA

Green modular design can facilitate life-cycle material efficiency through component material reuse and minimizing resource commitment throughout the product realization process. Traditional modular design has been motivated toward delivering variety at low cost, but with little incentive for material efficiency per se. The key technical challenge for incorporating material efficiency considerations into the prevailing modularization theories and methods lies in that such material reuse modularity must be consistent with and conform to the legacy structure of a technical system. This paper is geared toward a total system approach and emphasizes leader follower joint optimization in order to leverage technical system modularity (TSM) and material reuse modularity (MRM) within a coherent framework. To measure component interactions and cluster components into modules, taxonomy of modularity metrics is developed encompassing the entire life cycle of material fulfillment. The quantification and aggregation of modularity measures are formulated by multi-attribute utilities of different dimensions of component similarity. Furthermore, a bilevel optimization model based on a constrained genetic algorithm is put forward for joint decisions of TSM and MRM. A case study of refrigerator green modular design is reported. Results and analyses reveal that the leader-follower bilevel optimization model is robust and excels in supporting green modular design with material reuse. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Green design Modularity Joint optimization constrained genetic algorithm Material reuse Material efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing the rule curves of multi-use reservoir operation using a genetic algorithm with a penalty strategy

引用

PADDY AND WATER ENVIRONMENT 2014年第1期12卷 125-137页

作者： Trieu Anh Ngoc Hiramatsu, Kazuaki Harada, Masayoshi Kyushu Univ Grad Sch Bioresource & Bioenvironm Sci Lab Water Environm EngnHigashi Ku Dept Agroenvironm SciCourse Bioprod Environm Sci Fukuoka 8128581 Japan Water Resources Univ Fac Water Resources Engn Hanoi Vietnam Water Resources Univ Div Appl Sci & Technol Base 2 Binh Thanh Ho Chi Minh Vietnam Kyushu Univ Lab Water Environm Engn Div Bioprod Environm Sci Fac AgrDept Agroenvironm SciHigashi Ku Fukuoka 8128581 Japan

This study aims to propose a methodology for establishing the optimal rule curves of reservoir operation based on a multi-use reservoir system. Located on the upper Saigon River, Dau Tieng Reservoir plays an important role in economic and social aspects: (1) flood control;(2) domestic and industrial demands;(3) flushing out salt water intrusion from the downstream area;and (4) agriculture irrigation. We propose a reservoir operation model using a constrained genetic algorithm (CGA), in which the fitness function was constrained by penalty functions. The proposed model was formulated by including various water demands configured into the objective function. The penalty functions were designed for various constraints and integrated into the objectives of the operation process to perform the fitness function. The model's performance was simulated for the last 20 years with 1-month intervals and evaluated through a generalized shortage index (GSI). The derived results of three CGA cases with associated environmental flow requirements significantly improved the efficiency and effectiveness of water supply capability to various water demands as compared to current operation. Among the three cases, CGA case 3 achieved much better water releases from the reservoir as indicated by a small derived GSI value (0.33), the smallest shortage of environmental water (0.11 m(3)/s) and the highest water usage (63.8 %). Thus, the derived results of CGA case 3 were presented as the best rule curves for reservoir operation. To summarize, CGA was demonstrated as an effective and powerful tool for optimal strategy searching for multi-use reservoir operations.

关键词： Objective function Water shortages constrained genetic algorithm Environmental requirement Dau Tieng Reservoir

来源：评论

学校读者我要写书评

暂无评论

Modeling and optimization of a multi-carrier renewable energy system for zero-energy consumption buildings

引用

Journal of Central South University 2022年第7期29卷 2330-2345页

作者： SOULEY AGBODJAN Yawovi LIU Zhi-qiang WANG Jia-qiang YUE Chang LUO Zheng-yi School of Energy Science and Engineering Central South UniversityChangsha 410083China College of Civil Engineering Hunan UniversityChangsha 410082China

For the carbon-neutral,a multi-carrier renewable energy system(MRES),driven by the wind,solar and geothermal,was considered as an effective solution to mitigate CO2emissions and reduce energy usage in the building sector.A proper sizing method was essential for achieving the desired 100%renewable energy system of *** paper presented a bi-objective optimization formulation for sizing the MRES using a constrained genetic algorithm(GA)coupled with the loss of power supply probability(LPSP)method to achieve the minimal cost of the system and the reliability of the system to the load real time *** optimization App has been developed in MATLAB environment to offer a user-friendly interface and output the optimized design parameters when given the load demand.A case study of a swimming pool building was used to demonstrate the process of the proposed design *** to the conventional distributed energy system,the MRES is feasible with a lower annual total cost(ATC).Additionally,the ATC decreases as the power supply reliability of the renewable system *** is a decrease of 24%of the annual total cost when the power supply probability is equal to 8%compared to the baseline case with 0%power supply probability.

关键词： multi-carrier renewable energy system constrained genetic algorithm loss of power supply probability(LPSP)method zero-energy consumption building optimal device capacity

来源：评论

学校读者我要写书评

暂无评论

Encoding consumer interests into product snippets with a multi-criteria genetic optimization approach

引用

INFORMATION & MANAGEMENT 2024年第8期61卷

作者： Mu, Yao Wei, Qiang Chen, Guoqing Shanghai Int Studies Univ Sch Business & Management Key Lab Brain Machine Intelligence Informat Behav Minist Educ & Shanghai Shanghai 201620 Peoples R China Tsinghua Univ Sch Econ & Management Beijing 100084 Peoples R China

As an essential product cue in consumer information foraging, textual snippets can convey valuable scents that attract consumers to further access products, paving the way for online sellers to seize a competitive advantage. Premised on shopping goals theory, this study proposes a novel approach to designing high-quality product snippets that are particularly enhanced with consumer interests. First, snippet encoding is formulated as a multicriteria optimization problem in which information sources are incorporated to distill consumer-appealing keywords considering both driving search and attracting selection, as well as to integrate the perspectives of sellers and consumers. Subsequently, a constrained genetic solution algorithm is developed, which copes well with the evolutionary nature of the problem to optimize snippets in an effective and efficient manner. Extensive experiments are conducted to verify the validity and superiority of the proposed approach.

关键词： Product snippets Shopping goals Consumer interests Multi-criteria optimization constrained 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：