检索结果-内蒙古大学图书馆

Ball mill pulverizing system optimization algorithm based on fuzzy time series data mining

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument 2007年第SUPPL. 5期28卷 304-308页

作者： Cao, Hui Si, Gangquan Zhang, Yanbin Jia, Lixin School of Electrical Engineering Xi'an Jiaotong University Xi'an 710049 China

Focusing on the disadvantages of the current ball mill pulverizing system optimization approaches, a ball mill pulverizing system optimization algorithm based on fuzzy time series data mining is proposed. The proposed algorithm uses the fuzzy partition and the sliding time window to perform the fuzzy time series data mining on the field data and the association rules of the operational variables can be obtained. Based on the association rules, the control set values are determined and the control system can control the ball mill pulverizing system real-time and keep it working stably and economically all along. The experimental results and the statistic data verify that the proposed algorithm not only can determine the control set values of the work condition successfully but also has higher energy-saving effectiveness.

关键词： Ball mill pulverizing system Fuzzy partition optimization algorithm Time series data mining

来源：评论

学校读者我要写书评

暂无评论

Multiobjective multistage robust integer optimization model and algorithm for oilfield development planning

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2021年 159卷 107497-107497页

作者： Yan, Sen Ji, Xiaoyu Fang, Yanjun Sun, Hongguo Renmin Univ China Sch Business Beijing 100872 Peoples R China Daqing Oilfield Co Ltd Explorat & Dev Res Inst Daqing 163712 Peoples R China

This paper discusses the long-term planning problem of oilfield development. The planning aims to deploy the workload of stimulation treatments with uncertain indicators. And the uncertainties of initial stimulation effect, annual effect error and new recoverable reserves are considered. With their uncertainty sets and the adaptability of decisions, a multiobjective multistage robust integer optimization model is constructed. In this model, the total development cost is minimized and the total new recoverable reserves is maximized. And the model makes decisions on the workload of each stimulation treatment in each year under constraints of annual oil production and workload balance. In addition, an algorithm for solving multiobjective multistage robust integer optimization model is proposed, which can obtain the finitely adaptive robust efficient solution set. Finally, a numerical example of long-term oilfield development planning is presented. The planning model with given uncertainty sets is solved, to verify the validity of the proposed model and algorithm.

关键词： Oilfield development planning Multiobjective robust optimization Multistage robust optimization Integer programming optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Test and optimization of a control algorithm for demand-oriented operation of CHP units using hardware-in-the-loop

引用

APPLIED ENERGY 2021年 294卷 116974-116974页

作者： Haase, Patrick Thomas, Bernd Reutlingen Univ Reutlingen Ctr Energy Res REZ Alteburgstr 150 D-72762 Reutlingen Germany

This paper covers test and verification of a forecast-based Monte Carlo algorithm for an optimized, demandoriented operation of combined heat and power (CHP) units using the hardware-in-the-loop approach. For this purpose, the optimization algorithm was implemented at a test bench at Reutlingen University for controlling a CHP unit in combination with a thermal energy storage, both in real hardware. In detail, the hardwarein-the-loop tests are intended to reveal the effects of demand forecasting accuracy, the impact of thermal energy storage capacity and the influence of load profiles on demand-oriented operation of CHP units. In addition, the paper focuses on the evaluation of the content of energy in the thermal energy storage under practical conditions. It is shown that a 5-layer model allows to determine the energy stored quite accurately, which is verified by experimental results. The hardware-in-the-loop tests disclose that demand forecasting accuracies, especially electricity demand forecasting, as well as load profiles strongly impact the potential for CHP electricity utilization on-site in demand-oriented mode. Moreover, it is shown that a larger effective capacity of the thermal energy storage positively affects demand-oriented operation. In the hardware-in-the-loop tests, the fraction of electricity generated by the CHP unit utilized on-site could thus be increased by a maximum of 27% compared to heat-led operation, which is still the most common modus operandi of small-scale CHP plants. Hence, the hardware-in-the-loop tests were adequate to prove the significant impact of the proposed algorithm for optimization of demand-oriented operation of CHP units.

关键词： optimization algorithm Demand-oriented Monte Carlo method CHP unit Hardware-in-the-Loop Thermal energy storage

来源：评论

学校读者我要写书评

暂无评论

Design optimization of moderately thick hexagonal honeycomb sandwich plate with modified multi-objective particle swarm optimization by genetic algorithm (MOPSOGA)

引用

COMPOSITE STRUCTURES 2020年 252卷 112626-112626页

作者： Namvar, A. R. Vosoughi, A. R. Shiraz Univ Sch Engn Dept Civil & Environm Engn Shiraz Iran

Design optimization of moderately thick hexagonal honeycomb sandwich plate has been investigated via employing an improved multi-objective particle swarm optimization with genetic algorithm (MOPSOGA). Based on the first-order shear deformation theory (FSDT), governing equations of the plate are obtained. The equations are solved analytically. Total weight and maximum deflection of the plate under static gravity loads are considered to be objective functions of the problem. Core height, faces thickness, cell walls thickness, vertical and inclined cell wall length and the angle between inclined cell wall and horizontal line are set to be design variables of the problem. The geometrical and failure constrains are chosen to have desirable performance and stability of the sandwich plate. In the used multi-objective optimization technique, the optimum velocity parameter, inertia weight and acceleration coefficients for next iteration of the MOPSO are obtained by employing the genetic algorithm via minimizing generational distance between the sets of dominated and non-dominated particles in the previous iteration. Efficiency and accuracy of the proposed solution procedure are demonstrated and effects of different parameters on design optimization of the plate are studied. Also, TOPSIS multi-criteria decision-making method has been selected to report appreciate results from the Pareto-front curve of the MOPSOGA.

关键词： Hexagonal honeycomb sandwich plate Design optimization of cellular material First-order shear deformation theory Modified multi-objective particle swarm optimization algorithm Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

optimization Model and algorithm for Multi-Label Learning

引用

Journal of Applied Mathematics and Physics 2021年第5期9卷 969-975页

作者： Zhengyang Li Fuzhou University Fuzhou China

This paper studies a kind of urban security risk assessment model based on multi-label learning, which is transformed into the solution of linear equations through a series of transformations, and then the solution of linear equations is transformed into an optimization problem. Finally, this paper uses some classical optimization algorithms to solve these optimization problems, the convergence of the algorithm is proved, and the advantages and disadvantages of several optimization methods are compared.

关键词： Operations Research Multi-Label Learning Linear Equations Solving optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing parameters in swarm intelligence using reinforcement learning: An application of Proximal Policy optimization to the iSOMA algorithm

引用

SWARM AND EVOLUTIONARY COMPUTATION 2024年 85卷

作者： Klein, Lukas Zelinka, Ivan Seidl, David VSB Tech Univ Ostrava Dept Comp Sci FEI Ostrava 70800 Czech Republic VSB Tech Univ Ostrava ENET Ctr Ostrava 70800 Czech Republic

This paper presents a new algorithm for optimizing parameters in swarm algorithm using reinforcement learning. The algorithm, called iSOMA-RL, is based on the iSOMA algorithm, a population-based optimization algorithm that mimics the competition-cooperation behavior of creatures to find the optimal solution. By using reinforcement learning, iSOMA-RL can dynamically and continuously optimize parameters, which can play a crucial role in determining the performance of the algorithm but are often difficult to determine. The reinforcement learning technique used is the state -of -the -art Proximal Policy optimization (PPO), which has been successful in many areas. The algorithm was compared to the original iSOMA algorithm and other algorithms from the SOMA family, showing better performance with only constant increase in computational complexity depending on number of function evaluations. Also we examine different sets of parameters to optimize and different reward functions. We also did comparison to widely used and state -of -the -art algorithms to illustrate improvement in performance over the original iSOMA algorithm.

关键词： Self-Organizing Migrating algorithm optimization algorithm Swarm intelligence Numerical optimization Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of an optimization Management algorithm on a Multi-generation Small Size Power Plant

引用

Energy Procedia 2016年 101卷 566-573页

作者： Piero Danti Lorenzo Pezzola Sandro Magnani Yanmar R&D Europe Firenze 50125 Italy

In the last years, the carbon footprint reduction has gained great relevance in the energy industry. Thus, it is necessary to choose approaches that weight the results not only evaluating economic benefits but also emphasizing the environmental impact. In order to measure this impact, the key parameter is the CO 2 emission in the atmosphere. The most powerful mean to satisfy this compromise between economic benefits and emission decrease is represented by the concept of Smart Grid. A Smart Grid implies a joint participation between information network and electric grid. In order to acquire the data from the electric grid, transmit them through the IT network, compute and translate them into commands to the plant devices, an ‘intelligent brain’ is necessary. In order to embed a small local network in the larger VPP a delocalized intelligent device is necessary, able to interface with the Smart Grid. An optimization algorithm performs this function of intelligent delocalized brain by setting different set-points for the energy devices on field. In this paper a purposefully developed optimization algorithm is described, with the aim of optimizing the operations of an existent trigeneration plant managing both RES and fossil energy sources. The plant analysed is a real plant located in central Italy, provided by several generators (PV, CHP, absorption chiller, electric chiller, gas boiler and a wind turbine). The results are yielded by a MATLAB/Simulink simulation tool, where all plant devices are characterized by datasheet information and on-field measurements. The benefits evaluation of the algorithm optimized management is obtained by embedding inside Simulink the optimization logic and executing it during the simulation runtime. The performance is compared with conventional thermal led management operations simulated in the same platform. The comparison is mainly based on economic costs but also considers CO 2 emissions and primary energy consumption. The analysis t

关键词： CHP optimization algorithm Genetic algorithm Thermal Led

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “A novel efficient optimization algorithm for parameter estimation of building thermal dynamic models” [Build. Environ. 153 (2019) 233–240]

引用

Building and Environment 2020年 176卷

作者： Jiangyu Wang Huanxin Chen Yue Yuan Yao Huang Department of Refrigeration and Cryogenic Engineering School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan PR China China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan PR China

Parameter estimation applied to gray-box modeling approaches is of great importance for advanced building control and demand response. Stochastic optimization algorithms based on the swarm intelligence, e.g. generic algorithm, have been applied widely. However, these algorithms are time-consuming to accomplish optimization due to the large populations employed in random searching. To overcome this problem, this paper presents, for the first time, a novel efficient optimization algorithm so-called Beetle Swarm Antennae Search (BSAS) to estimate parameters of a resistance-capacitance(RC) model using simulated data collected from EnergyPlus. Furthermore, this paper also investigates the application of BSAS and four other widely used optimization algorithms including genetic algorithm(GA), particle swarm optimization(PSO), differential evolution(DE) and beetle antennae search(BAS) on parameter estimation. A case study is conducted on a single-room building simulated by EnergyPlus. BSAS and four other algorithms are employed to estimate the parameters of a 4R3C model for this tested building. The results demonstrate that the BSAS can achieve good performance on parameter estimation with sufficient accuracy and less computational cost by comparison with other algorithms. More specifically, the computational cost of the proposed algorithm is only about one third of the GA and a quarter of the DE while the mean fitness index is very close.

关键词： Gray-box thermal model System identification optimization algorithm Building simulation

来源：评论

学校读者我要写书评

暂无评论

optimization Model and algorithm for Multi-Label Learning

Optimization Model and Algorithm for Multi-Label Learning

引用

作者： Zhengyang Li Fuzhou University

This paper studies a kind of urban security risk assessment model based on multi-label learning, which is transformed into the solution of linear equations through a series of transformations, and then the solution of linear equations is transformed into an optimization problem. Finally, this paper uses some classical optimization algorithms to solve these optimization problems,the convergence of the algorithm is proved, and the advantages and disadvantages of several optimization methods are compared.

关键词： Operations Research Multi-Label Learning Linear Equations Solving optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on multi-objective optimization design of the nuclear island cold chain system in HPR1000 based on a new hybrid genetic algorithm

引用

PROGRESS IN NUCLEAR ENERGY 2025年 180卷

作者： Zhao, Weiguang Yu, Pei Zeng, Xiaobo Fan, Guangming Meng, Zhaoming Yan, Changqi Harbin Engn Univ Coll Nucl Sci & Technol Harbin 150001 Peoples R China Harbin Engn Univ Fundamental Sci Nucl Safety & Simulat Technol Lab Harbin 150001 Peoples R China China Nucl Power Engn Co Ltd Beijing 100870 Peoples R China

Currently, the design of the cold chain system for the HPR1000 nuclear island does not take a unified approach and largely relies on the design experience of the respective designers. The various subsystems contain numerous devices, and the cumulative design margins often result in many unreasonable parameters in the original design scheme of the cold chain system. To address this issue, this paper establishes a mathematical model for the cold chain system to assist in its design. Based on genetic algorithms and the simplex algorithm, adaptive relaxation constraint dominance relations and two improved NSGA-II multi-objective handling methods are introduced, leading to the development of a new hybrid multi-objective genetic algorithm. The performance of this algorithm is verified using optimized benchmark testing functions, thus allowing for the scientific optimization of the cold chain system design scheme. A sensitivity analysis is conducted on the design parameters of the ventilation system, refrigeration system, component cooling system, and seawater system within the cold chain system to explore the impact of these parameters on performance indicators. optimization design calculations for the cold chain system are performed under safe and feasible conditions, resulting in an optimization scheme. The results indicate that the developed algorithm is effective in addressing the complex optimization problems of the cold chain system, and the optimized cold chain system can reduce weight by up to 18.4 %, volume by up to 18.6 %, investment costs by up to 5.7%, and system energy consumption by up to 7.5 %.

关键词： HPR1000 optimization algorithm Nuclear island cold chain system (NICCS) Multi-objective optimization design Performance evaluation model

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：