检索结果-内蒙古大学图书馆

multi-objective optimization of the refrigerant-direct convective-radiant cooling system considering the thermal and economic performances

引用

ENERGY AND BUILDINGS 2022年第0期254卷 111609-111609页

作者： Jiang, Tingting You, Shijun Wu, Zhangxiang Zhang, Huan Wang, Yaran Wei, Shen Tianjin Univ Sch Environm Sci & Engn Tianjin 300350 Peoples R China Tianjin Univ Minist Educ China Key Lab Efficient Utilizat Low & Medium Grade Ene Tianjin 300350 Peoples R China Univ Coll London UCL Bartlett Sch Sustainable Construct 1-19 Torrington Pl London WC1E 7HB England

The refrigerant-direct convective-radiant cooling (RCC) system is attracting widespread concern due to its advantages of good thermal comfort, high energy efficiency and simple structure. However, researches on thermal and economic optimization of this system are rare. In this study, a novel heuristic approach is proposed to optimize the aluminum column-wing type refrigerant-direct convective-radiant cooling (ACT-RCC) system, which adopts artificial neural network (ANN) integrated with multi-objective genetic algorithm (MOGA). The numerical and economic models of the ACT-RCC terminal are developed and the numerical model is validated by the experimental data. Besides, the ANN model is adopted to accelerate the prediction of the thermal and economic performances of this system. Results show that the training values of the ANN model are fitted well with simulated results and the ANN model can greatly improve the runtime in comparison with original numerical and economic models. Based on the heuristic optimization approach, the optimal structure of the ACT-RCC terminal is the copper pipe diameter with 8.7 mm, the copper pipe spacing with 25.5 mm and the rib height with 30.3 mm. Compared with the original structure, the cooling capacity of the improved ACT-RCC system is enhanced by 16.0% and the initial cost is reduced by 10.0%. The appearance area equals to the direct product of the length and width, and results show that the appearance area of the improved ACT-RCC terminal is decreased from 1.04 m(2) to 0.78 m(2). Therefore, the proposed heuristic approach provides guidance for improving the thermal and economic performances of the RCC systems. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Refrigerant-direct convective-radiant cooling system Thermal and economic optimization Artificial neural network multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted multi-objective genetic algorithms for Fuzzy Rule-Based Classification

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2018年第6期20卷 1938-1955页

作者： Kalia, Harihar Dehuri, Satchidananda Ghosh, Ashish Cho, Sung-Bae Seemanta Engn Coll Dept Comp Sci Mayurbhanj 757086 Odisha India Fakir Mohan Univ Dept Informat & Commun Technol Balasore 756019 Odisha India Indian Stat Inst Machine Intelligence Unit 203 BT Rd Kolkata 700108 India Indian Stat Inst Ctr Soft Comp Res 203 BT Rd Kolkata 700108 India Yonsei Univ Dept Comp Sci Soft Comp Lab 134 Shinchon Dong Seoul 120749 South Korea

In this paper, we present a surrogate-assisted multi-objective genetic algorithm to mine a small number of linguistically interpretable fuzzy rules for high-dimensional classification task in the realm of data mining. However, the difficulties like (1) handling of high-dimensional problems by fuzzy rule-based systems (i.e., the exponential increase in the number of fuzzy rules with the number of input variables), (2) the deterioration in the comprehensibility of fuzzy rules when they involve many antecedent conditions, and (3) the optimization of multiple objectives in fuzzy rule-based system may stand as pertinent issues. Hence, to combat with the aforesaid issues, we design the problem as a combinatorial optimization problem with three objectives: to maximize the number of correctly classified training patterns, minimize the number of fuzzy rules, and minimize the total number of antecedent conditions. We optimize these objectives of the fuzzy rule-based system by using a multi-objective genetic algorithm. Further to reduce the number of required evaluations to approximate the Pareto front of computationally expensive multi-objective genetic algorithm for fuzzy rule-based system, a radial basis neural network surrogate model is adapted. This approach searches for non-dominated rule sets with respect to these three objectives. The performance of the surrogate-assisted model is evaluated through a few benchmark datasets obtained from knowledge extraction based on evolutionary learning data repository. The experimental outcome confirm that this model is competitive compared to the non-surrogate-assisted model. However, the performance of the model has drawn a clear edge over rule mining approaches like Decision Table, JRip, OneR, PART, and ZeroR.

关键词： Classification rule Fuzzy set genetic algorithm multi-objective genetic algorithm Surrogate-assisted model

来源：评论

学校读者我要写书评

暂无评论

Modeling of solid oxide fuel cell (SOFC) electrodes from fabrication to operation: Microstructure optimization via artificial neural networks and multi-objective genetic algorithms

引用

ENERGY CONVERSION AND MANAGEMENT 2019年 198卷 111916-000页

作者： Yan, Z. He, A. Hara, S. Shikazono, N. Univ Tokyo Inst Ind Sci Meguro Ku Komaba 4-6-1 Tokyo 1538505 Japan Chiba Inst Technol Dept Mech Engn Fac Engn Tsudanuma 2-17-1 Narashino Chiba 2750016 Japan

In this study, a modeling framework is proposed for the optimization of the solid oxide fuel cell (SOFC) electrode microstructures. This involves sequential simulations of the SOFCs from initial powder to final electrochemical performance with artificial intelligence-assisted multi-objective optimization. The effects of starting powder parameters such as particle size, particle size distribution (PSD) and pore former content on cathodic overpotential and degradation rate of SOFCs are studied. It is shown that fine particle size and/or low pore former content lead to low cathodic overpotential but high degradation rate in the investigated range of the parameters. Predictive models for the cathode overpotential and degradation rate are established by an artificial neural network using the simulation data. The Sobol global sensitivity study suggests that particle size and pore former content play important roles in determination of the cathode overpotential and degradation rate while the PSD effect is insignificant. A multi-objective genetic algorithm (MOGA) is used to minimize both the overpotential and degradation rate of the cathode. The Pareto front is obtained for the optimal design of cathode microstructures. Compared to the grid search method, the MOGA proves to be more robust and efficient for SOFC electrode microstructure optimization.

关键词： Solid oxide fuel cells Microstructure optimization Artificial neural network Parameter sensitivity multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective vehicle delivery path optimization model based on improved constrained evolutionary control operator 2021

Multi-objective vehicle delivery path optimization model bas...

引用

2nd International Conference on Artificial Intelligence and Information Systems (ICAIIS )

作者： Ma, Tianxing Bai, Pengyu Zhang, Hekai Cent South Univ Changsha Hunan Peoples R China Emory Univ 1380 Oxford Rd NE Atlanta GA 30322 USA Heilongjiang Univ Harbin Heilongjiang Peoples R China

ISBN: (纸本)9781450390200

By designing a constraint control evolutionary operator that considers the infeasible solution, the traditional multi-objective genetic algorithm can not deal with the complex constraints. In this paper, a multi-objective vehicle distribution path optimization model with the shortest path in the form of a vehicle is established to achieve the system's multi-objective optimization. Besides, considering the constraints of vehicle driving distance, the working time constraints of distribution personnel, and the unique constraints, the model is changed into a constraint optimization model. The results show that the computational cost is low, the iterative convergence speed is fast, and the satisfactory solution can be obtained within the acceptable time range.

关键词： Rich-VRP multi-objective genetic algorithm constrained control evolutionary operator

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of a dual mass flywheel with centrifugal pendulum vibration absorbers in a single-shaft parallel hybrid electric vehicle powertrain for torsional vibration reduction

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2022年 163卷 108152-108152页

作者： Lee, Hyung Joon Shim, Jae Kyung Korea Univ Dept Automot Convergence Engn Seoul 02841 South Korea Korea Univ Sch Mech Engn Seoul 02841 South Korea

This research deals with an optimization of a dual mass flywheel (DMF) with centrifugal pendulum vibration absorbers (CPVAs) used in a single-shaft parallel hybrid electric vehicle (HEV) powertrain for the reduction of the torsional vibration at the rotor of the electric motor and the total moment of inertia of the DMF and CPVAs. Unlike the previous studies, this research considers the overall behavior of an entire powertrain with an in-line four-cylinder engine and a five-speed automatic transmission for the optimization of the DMF with CPVAs. For this purpose, the multibody dynamics model of the HEV powertrain is constructed and used to analyze the transient response of the system for a given gas pressure map and acceleration condition of the vehicle. Then, a multi-objective genetic algorithm is applied to determine the Pareto optimal front that yields the design parameter values of the DMF and CPVAs effective in the torsional vibration reduction and inertia minimization. The result of the optimization is compared with the HEV powertrain system with a flywheel only, and shows that the vibrations transmitted to the motor are significantly reduced in all the solutions of the Pareto front. By using the method proposed in this research, various parameter combinations of the DMF and CPVAs can be considered in the early design process.

关键词： Dual mass flywheel (DMF) Single-shaft parallel hybrid electric vehicle (HEV) powertrain multibody dynamics Transient analysis multi-objective genetic algorithm Centrifugal pendulum vibration absorber (CPVA)

来源：评论

学校读者我要写书评

暂无评论

Numerical and experimental investigation of erosive wear in Francis runner blade optimized for sediment laden hydropower projects in Nepal

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2022年 51卷

作者： Gautam, Saroj Acharya, Nirmal Lama, Ram Chitrakar, Sailesh Neopane, Hari Prasad Zhu, Baoshan Kathmandu Univ KU Dept Mech Engn Turbine Testing Lab Kathmandu Nepal Norwegian Univ Sci & Technol NTNU Waterpower Lab Trondheim Norway Tsinghua Univ THU Dept Energy & Power Engn Beijing Peoples R China

The design of the Francis turbine aims to maximize its performance in terms of efficiency. This design approach has overlooked effects on the turbine due to sediment erosion for power plants operating under high sediment load. In this paper, a multi-objective design procedure to develop a Francis turbine runner for maximizing efficiency, as well as minimizing sediment erosion is discussed. Parameterized runner designs obtained from the design algorithm are implemented in the Design of Experiment (DOE) to get sample runners. These sample runners are investigated using a commercial CFD tool and validating with an experiment in a model turbine test rig to obtain efficiency and sediment erosion data. Subsequently, a multi-objective genetic algorithm (MOGA) is implemented to generate the optimized runner blades. Two different optimized runners are selected after the optimization. The optimized runner generated from this technique is further investigated experimentally in the laboratory scale sediment erosion test rig. From both numerical and experimental results, it is found that the optimized runner blade has improved erosion handling capability. Implementation of the procedure discussed in this article can be a crucial step for designing the turbines which are vulnerable to sediment erosion.

关键词： Francis Turbine Design of Experiment multi-objective genetic algorithm Sediment Erosion Efficiency

来源：评论

学校读者我要写书评

暂无评论

Structure optimization of neural network for dynamic system modeling using multi-objective genetic algorithm

引用

NEURAL COMPUTING & APPLICATIONS 2012年第6期21卷 1281-1295页

作者： Loghmanian, Sayed Mohammad Reza Jamaluddin, Hishamuddin Ahmad, Robiah Yusof, Rubiyah Khalid, Marzuki Univ Teknol Malaysia Ctr Artificial Intelligence & Robot CAIRO Kuala Lumpur 54100 Malaysia Univ Teknol Malaysia Fac Mech Engn Dept Appl Mech Johor Baharu 81310 Malaysia

The problem of constructing an adequate and parsimonious neural network topology for modeling non-linear dynamic system is studied and investigated. Neural networks have been shown to perform function approximation and represent dynamic systems. The network structures are usually guessed or selected in accordance with the designer's prior knowledge. However, the multiplicity of the model parameters makes it troublesome to get an optimum structure. In this paper, an alternative algorithm based on a multi-objective optimization algorithm is proposed. The developed neural network model should fulfil two criteria or objectives namely good predictive accuracy and minimum model structure. The result shows that the proposed algorithm is able to identify simulated examples correctly, and identifies the adequate model for real process data based on a set of solutions called the Pareto optimal set, from which the best network can be selected.

关键词： Artificial neural network multi-objective genetic algorithm NSGA-II System identification Model structure selection

来源：评论

学校读者我要写书评

暂无评论

Inventory model with fuzzy lead-time and dynamic demand over finite time horizon using a multi-objective genetic algorithm

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2012年第6期64卷 1822-1838页

作者： Bera, U. K. Maiti, M. K. Maiti, M. Natl Inst Technol Dept Math Jirania 799055 West Tripura India Mahishadal Raj Coll Dept Math Purba Medinipur 721628 WB India Vidyasagar Univ Dept Math Paschim Medinipur 700114 WB India

The real-world inventory control problems are normally imprecisely defined and human interventions are often required in solving these decision-making problems. In this paper, a realistic inventory problem with an infinite rate of replenishment over a prescribed finite but imprecise time horizon is formulated considering time dependent ramp type demand, which increases with time. Lead time is also assumed as fuzzy in nature. Shortages are allowed and backlogged partially. Two models are considered depending upon the ordering policies of the decision maker (DM). The imprecise parameters are first transformed to corresponding nearest interval numbers depending upon some distance metric on fuzzy numbers and then following the interval mathematics, the objective function for total profit from the planning horizon is obtained (which is an interval function). Then interval objective decision making problem is reduced to multi-objective problems using different approaches. Finally a fast and elitist multi-objective genetic algorithm (FEMOGA) is used for solving these multi-objective models to find pareto-optimal decisions for the DM. The models are illustrated numerically. As a particular case, the results due to linear trended and constant demands have been presented. (c) 2012 Elsevier Ltd. All rights reserved.

关键词： Fuzzy lead-time Interval number multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Integration of life cycle assessment, artificial neural networks, and metaheuristic optimization algorithms for optimization of tomato-based cropping systems in Iran

引用

INTERNATIONAL JOURNAL OF LIFE CYCLE ASSESSMENT 2020年第3期25卷 620-632页

作者： Pishgar-Komleh, Seyyed Hassan Akram, Asadollah Keyhani, Alireza Sefeedpari, Paria Shine, Philip Brandao, Miguel Univ Tehran Fac Agr Engn & Technol Dept Agr Machinery POB 4111 Karaj Iran State Res Inst Inst Soil Sci & Plant Cultivat Dept Bioecon & Syst Anal Pulawy Poland Czech Univ Life Sci Fac Econ & Management Dept Econ Prague Czech Republic Cork Inst Technol Dept Proc Energy & Transport Engn Cork Ireland KTH Royal Inst Technol Dept Sustainable Dev Environm Sci & Engn Seed Div Sustainabil Assessment & Management S-10044 Stokholm Sweden

Purpose The main purpose of this study was to evaluate the use of an integrated life cycle assessment (LCA), artificial neural network, and metaheuristic optimization model to improve the sustainability of tomato-based cropping systems in Iran. The model outputs the combination of input usage in a tomato cropping system, which leads to the highest economic output and the least environmental impact. Methods The LCA inventory was created using data from 114 open-field tomato farms in the Alborz Province of Iran during one growing period in 2015. Among all management components, the main focus was on irrigation management systems. The optimization problem was designed by integrating three indicators: carbon footprint (CF), benefit-cost ratio (BCR), and energy use efficiency (EUE) as the objective of field tomato production. The functional unit was 1 kg of tomato aligned with the system boundary of the cradle to market life cycle. Three artificial neural networks (ANNs) were applied to model relationships between the inputs and three indices (CF, BCR, and EUE) as the objective functions. multi-objective genetic algorithm (MOGA) and multi-objective particle swarm optimization (MOPSO) were used to minimize the CF and maximize the BCR and EUE indicators. The abovementioned aims have been pursued by developing codes in MATLAB software. Results and discussion CF, BCR, and EUE were calculated to be 0.26 kg CO2-eq (kg tomato)(-1), 1.8, and 0.5, respectively. MOGA results envisage the possibility of an increase of 86% and 50% in the EUE and BCR and a 43% reduction in the CF of tomato production systems. Moreover, EUE and BCR increased by 83% and 49%, and CF was reduced by 39% from the optimum results obtained from the MOPSO algorithm. It was revealed that in order to optimize field tomato production with the target objectives of this study, a large additional use for irrigation pipes, plastic, and machinery in comparison to current situation is required, while a large reduction

关键词： Artificial neural networks Benefit-cost ratio Carbon footprint Energy use efficiency Field tomato Iran Life cycle assessment multi-objective genetic algorithm multi-objective particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A new accessibility based team orienteering approach for urban tourism routes optimization (A Real Life Case)

引用

COMPUTERS & OPERATIONS RESEARCH 2022年 138卷 105620-105620页

作者： Heris, Fateme Sadat Moosavi Ghannadpour, Seyed Farid Bagheri, Morteza Zandieh, Fatemeh Iran Univ Sci & Technol Dept Ind Engn Tehran *** Iran Iran Univ Sci & Technol Sch Railway Engn Tehran *** Iran

One of the most crucial issues in the tourism industry that can help attract more tourists is to design optimal travel routes for tourists. The Team Orienteering Problem with Time Windows (TOPTW) is one of the approaches that can solve Tourist Trip Design Problem (TTDP). In this study, TOPTW has been applied to design a multiobjective model to determine the optimal travel routes, considering the accessibility. The present study aims 1) to maximize the profit from visiting the Points of Interest (POIs) to increase the satisfaction level of the travel agency, and 2) to maximize the number of visited POIs to improve the satisfaction level of the tourists. Two concepts of "indirect coverage" and "neighborhood radius" are applied to increase the accessibility of the tourist attractions and POIs. Thus, around each POI, a small radius and a large radius are considered, and if the points are in the radius coverage of the points located in the main routes, they can receive indirect coverage from those points. Also the time-window overlap issue for POIs is vital to determine the possibility of indirect coverage and makes the conceptual model of the research closer to reality. Also, several indicators are proposed for calculating accessibility. A multi-objective genetic algorithm (MOGA) is formulated to solve the studied problem, and the results obtained by the proposed algorithm are compared with those of CPLEX software (for small-scale) and NSGA-II algorithm (for large-scale). The findings indicate that the genetic algorithm outperforms the NSGA-II algorithm. A sensitivity analysis is also performed to evaluate the effects of the proposed model parameters on the optimization process. Finally, the model applicability in practice is examined based on a case study in Tehran, the capital of Iran.

关键词： Tourism Team orienteering problem with time windows Profit Accessibility Indirect coverage 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：