检索结果-内蒙古大学图书馆

第25届中国控制与决策会议

作者： Yong Li Xinhua Zhao Yu Wang Mingxu Ren School of Electrical Engineering Shenyang University of Technology Department of Automatic Control Shenyang Aerospace University

ISBN: (纸本)9781467355322

An opposition learning multi-objective genetic algorithm based multi-objective optimization approach of rolling schedules for tandem hot rolling is proposed. According to actual rolling process, the power distribution and rolling energy consumption are selected as cost functions. Then the multi-objective model of rolling schedules is established. The opposition learning multi-objective genetic algorithm is applied to the model. Result shows that the proposed method decreases the values of two objective functions simultaneously compared to actual rolling schedules. Furthermore the proposed approach archives better Pareto solution set of rolling schedules with less running time compared with NSGA II. The validity of the proposed approach is confirmed.

关键词： opposition based learning multi-objective genetic algorithm tandem hot rolling optimization of rolling schedules

来源：评论

学校读者我要写书评

暂无评论

Research on a multi-objective genetic algorithm for rational Agent learning model

引用

International Conference on Information Technology for Manufacturing Systems (ITMS 2011)

作者： Li Ming Xiao Zhenhong Xie Zanfu Mo Xiaoyun Guangdong Polytech Normal Univ Coll Comp Sci Guangzhou Guangdong Peoples R China

ISBN: (纸本)9783037851494

As a software component which is capable of learning in an autonomous way, software agent should have the capability of learning in a dynamic environment. genetic algorithm has a wide perspective in the machine learning because of its unique characteristic (e.g. dynamic adaptability, self-organization, global convergence and robustness). But when applying GA to agent's dynamic learning model, it encounters a series of problem. In this paper, a Modifided multi-objective genetic algorithm(MMOGA) will be introduced to solve these problems. Finally, an Agent's Dynamic learning model based on a MMOGA which has the flexible dynamic learning capability, better global convergence and performance, will be introduced.

关键词： multi-Agent System agent technology multi-objective genetic algorithm Dynamic learning model

来源：评论

学校读者我要写书评

暂无评论

MOSAT: Finding Safety Violations of Autonomous Driving Systems using multi-objective genetic algorithm 2022

MOSAT: Finding Safety Violations of Autonomous Driving Syste...

引用

30th ACM Joint European Software Engineering Conference / Symposium on the Foundations of Software Engineering (ESEC/FSE)

作者： Tian, Haoxiang Jiang, Yan Wu, Guoquan Yan, Jiren Wei, Jun Chen, Wei Li, Shuo Ye, Dan Univ Chinese Acad Sci State Key Lab Comp Sci ISCAS Beijing Peoples R China Univ Chinese Acad Sci Nanjing Coll Joint Lab Cyberspace Secur China Southern Power Grid Beijing Peoples R China Univ Chinese Acad Sci Chongqing Sch Beijing Peoples R China Univ Chinese Acad Sci Nanjing Coll Beijing Peoples R China Nanjing Inst Software Technol Nanjing Peoples R China

ISBN: (纸本)9781450394130

Autonomous Driving Systems (ADSs) are safety-critical systems, and safety violations of Autonomous Vehicles (AVs) in real traffic will cause huge losses. Therefore, ADSs must be fully tested before deployed on real world roads. Simulation testing is essential to find safety violations of ADS. This paper proposes MOSAT, a multi-objective search-based testing framework, which constructs diverse and adversarial driving environment to expose safety violations of ADSs. Specifically, based on atomic driving maneuvers, MOSAT introduces motif pattern, which describes a sequence of maneuvers that can challenge ADS effectively. MOSAT constructs test scenarios by atomic maneuvers and motif patterns, and uses multi-objective genetic algorithm to search for adversarial and diverse test scenarios. Moreover, in order to test the performance of ADS comprehensively during long-mile driving, we design a novel continuous simulation testing technique, which runs the scenarios generated by multiple parallel search processes alternately in the simulator and can continuously create different perturbations to ADS. We demonstrate MOSAT on an industrial-grade platform, Baidu Apollo, and the experimental results show that MOSAT can effectively generate safety-critical scenarios to crash ADSs and it exposes 11 distinct types of safety violations in a short period of time. It also outperforms state-of-the-art techniques by finding more 6 distinct safety violations on the same road.

关键词： Autonomous Driving System Safety Violation multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

An Approach for Optimizing Group Stock Portfolio Using multi-objective genetic algorithm 5

An Approach for Optimizing Group Stock Portfolio Using Multi...

引用

5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC)

作者： Chen, Chun-Hao Chiang, Bing-Yang Hong, Tzung-Pei Tamkang Univ Dept Comp Sci & Informat Engn Taipei Taiwan Natl Sun Yat Sen Univ Comp Sci & Engn Kaohsiung Taiwan Natl Kaohsiung Univ Comp Sci & Informat Engn Kaohsiung Taiwan

ISBN: (纸本)9781728102078

Stock portfolio optimization is always an attractive research topic because of the variety of financial markers. In the past decade, lots of approaches have been proposed to deal with the problem. Previously, an algorithm was also designed for the group stock portfolio optimization problem. In that approach, portfolio satisfaction and group balance are utilized to evaluate the goodness of possible solutions. However, there is trade-off between those factors. In this paper, we thus design an approach for finding group stock group portfolios using the multi-objective genetic algorithm. Two objective functions, Sharpe ratio and group balance, are employed to derive possible Pareto solutions. Experiments on a real dataset were conducted to verity the effectiveness of the proposed approach.

关键词： Portfolio optimization group stock portfolio genetic algorithm grouping genetic algorithm multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

An Interactive Evaluation Method of Decentralized Procurement Plan by multi-objective genetic algorithm 10

An Interactive Evaluation Method of Decentralized Procuremen...

引用

10th International Conference on E-Business (ICE-B)

作者： Kobayashi, Ryoji Mori, Masakatsu Samejima, Masaki Komoda, Norihisa Osaka Univ Grad Sch Informat Sci & Technol 2-1 Yamadaoka Suita Osaka Japan Hitachi Ltd Yokohama Res Lab Totsuka Ku Yokohama Kanagawa 2440817 Japan

ISBN: (纸本)9789897581281

This paper addresses evaluation of a decentralized procurement plan for the support of the discussion among decision-makers with considering a catastrophic disaster. For the evaluation of the decentralized procurement plan, we have formulated the decentralized procurement planning problem as 3-objective optimization problem. However, multiple-objective genetic algorithms (MOGA) to solve the problem take several minutes and display many Pareto solutions. We propose the interactive evaluation method of the decentralized procurement plan that is an expanded interactive MOGA (iMOGA) with loss evaluation simulator and solution selection by characteristics of the decentralized procurement plan. Experimental results show that the proposed method can allow the decision-makers to find their preference solutions with 38% fewer interactions than the basic iMOGA can.

关键词： Supply Chain Decentralized Procurement Plan multi-objective genetic algorithm Interactive Evaluation

来源：评论

学校读者我要写书评

暂无评论

Scheduling of a flexible job-shop using a multi-objective genetic algorithm

引用

JOURNAL OF ADVANCES IN MANAGEMENT RESEARCH 2012年第2期9卷 178-188页

作者： Agrawal, Rajeev Pattanaik, L. N. Kumar, S. Birla Inst Technol Dept Prod Engn Mesra India GLA Univ Dept Mech Engn Mathura India

Purpose - The purpose of this paper is to solve a flexible job shop scheduling problem where alternate machines are available to process the same job. The study considers the Flexible Job Shop Problem (FJSP) having n jobs and more than three machines for scheduling. Design/methodology/approach - FJSP for n jobs and more than three machines is non polynomial (NP) hard in nature and hence a multi-objective genetic algorithm (GA) based approach is presented for solving the scheduling problem. The two objective functions formulated are minimizations of the make-span time and total machining time. The algorithm uses a unique method of generating initial populations and application of genetic operators. Findings - The application of GA to the multi- objective scheduling problem has given optimum solutions for allocation of jobs to the machines to achieve nearly equal utilisation of machine resources. Further, the make span as well as total machining time is also minimized. Research limitations/implications - The model can be extended to include more machines and constraints such as machine breakdown, inspection etc., to make it more realistic. Originality/value - The paper presents a successful implementation of a meta-heuristic approach to solve a NP-hard problem of FJSP scheduling and can be useful to researchers and practitioners in the domain of production planning.

关键词： Programming and algorithm theory Production scheduling Job sequence loading Flexible job shop problem Make-span Scheduling multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Trading Strategy Optimisation with a multi-objective genetic algorithm 11

Trading Strategy Optimisation with a Multi-objective Genetic...

引用

11th International Conference on Information Technology - IoT and Smart City (ITIoTSC)

作者： Liu, Yu Univ Western Australia Dept Comp Sci & Software Engn Perth WA 6009 Australia

ISBN: (纸本)9798350328356;9798350328349

algorithmic trading, a significant area of research in artificial intelligence, faces the challenges of interpreting and processing extensive and dynamic data. This environment is ideal for implementing adaptive algorithms, such as the evolutionary algorithm NSGA-II used in this paper, notable for its effectiveness in multi-objective optimisation problems. We apply this algorithm, in conjunction with technical indicators, to explore and exploit the search space provided by BTC/AUD market data for a specific trading strategy. Our objective is to demonstrate how NSGA-II, with an optimal parameter configuration, can balance net profit and risk to optimise trading outcomes, as evidenced in the Pareto-front results. Our findings show that by optimizing the parameter values, our NSGA-II driven strategy significantly outperformed a buy-and-hold strategy over the same period.

关键词： BTC/AUD Trading multi-objective genetic algorithm Optimization Risk and Return Evaluation

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of a STATCOM based on Cascaded multi-Level Converter Topology Using multi-objective genetic algorithm 23

Performance Optimization of a STATCOM based on Cascaded Mult...

引用

23rd Iranian Conference on Electrical Engineering

作者： Tousi, S. M. Reza Aznavi, Sima Bu Ali Sina Univ Fac Engn Dept Elect Engn Hamadan Iran

ISBN: (纸本)9781479919710

In this paper, a comprehensive study in component sizing of a cascaded multi-level inverter based static synchronous compensator (STATCOM) is presented. multi-objective genetic algorithm (MOGA) is utilized to optimize the performance of STATCOM. "Equivalent dynamic capacitance" concept is considered in order to simplify the complex structure of the multi-level inverter based STATCOM. Cascaded multi-level inverter parameters such as DC capacitance, initial capacitor charge, switching angles and also power system parameters including buffer inductance, transformer ratio and transformer inductance are to be found using optimization algorithm. In contrast with previous researches which have tried to optimize the objectives independently, in this paper the aim of using MOGA is optimizing losses, total harmonic distortion (THD) and maximum DC voltage ripple simultaneously, providing designing constraints with respect to the "equivalent dynamic capacitance" concept. The results show that better performance of STATCOM can be achieved via a thorough analysis by considering all parameters of STATCOM and components of power system as decision variables of a multi-objective optimization problem.

关键词： Static Synchronous Compensator (STATCOM) Cascaded multi-Level Converter Performance Optimization multi-objective genetic algorithm Equivalent Dynamic Capacitance

来源：评论

学校读者我要写书评

暂无评论

Motor velocity based multi-objective genetic algorithm controlled navigation method for two-wheeled pioneer P3-DX robot in V-REP scenario

引用

International Journal of Information Technology (Singapore) 2021年第5期13卷 2101-2108页

作者： Panwar, Vikas Singh Pandey, Anish Hasan, Md. E. School of Mechanical Engineering KIIT Deemed To Be University Patia Bhubaneswar PIN - 751024 India

This paper proposes the right and left motor velocity based multi-objective genetic algorithm controlled navigation method for Two-Wheeled Pioneer P3-DX Robot (TWPR) in Virtual Robot Experimentation Platform (V-REP) software scenarios. The first objective function is made by taking front, left, and right ultrasonic sensors data and right motor velocity. Similarly, the second objective function is designed using front, left, and right ultrasonic sensors data and left motor velocity. Next, the sensor data are considered independent variables or inputs. The velocities of the motors are chosen as dependent variables or outputs for making multi-objective fitness functions for genetic algorithm (GA). This multi-objective GA makes a sensor-actuator control architecture and helps the TWPR to avoid the obstacles in the simulated scenarios. Further, the successful simulation test results show that the multi-objective GA provided a collision-free smooth, and shortest path for TWPR compared to the previously developed benchmark single objective GA. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： multi-objective genetic algorithm Navigation method Sensor Single objective genetic algorithm Two-wheeled pioneer P3-DX robot Virtual robot experimentation platform

来源：评论

学校读者我要写书评

暂无评论

Application of multi-objective genetic algorithm (MOGA) for Design Optimization of Valve Timing at Various Engine Speeds

Application of Multi-objective Genetic Algorithm (MOGA) for ...

引用

International Conference on Advances in Materials and Processing Technologies (AMPT)

作者： Mohiuddin, A. K. M. Rahman, Md. Ataur Shin, Yap Haw Int Islamic Univ Malaysia IIUM Dept Mech Engn Kuala Lumpur Malaysia

ISBN: (纸本)9783037850534

This paper aims to demonstrate the effectiveness of multi-objective genetic algorithm Optimization and its practical application on the automobile engine valve timing where the variation of performance parameters required for finest tuning to obtain the optimal engine performances. The primary concern is to acquire the clear picture of the implementation of multi-objective genetic algorithm and the essential of variable valve timing effects on the engine performances in various engine speeds. Majority of the research works in this project were in CAE software environment and method to implement optimization to ID engine simulation. The paper conducts robust design optimization of CAMPRO 1.6L (S4PH) engine valve timing at various engine speeds using multi-objective genetic algorithm (MOGA) for the future variable valve timing (VVT) system research and development. This paper involves engine modelling in ID software simulation environment, GT-Power. The GT-Power model is run simultaneously with mode Frontier to perform multi-objective optimization.

关键词： Optimization Valve timing multi-objective genetic algorithm GT-Suite

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：