检索结果-内蒙古大学图书馆

Optimisation of pin-fin heat sink design for CPV systems using machine learning-driven multi-objective approaches

Energy Conversion and Management 2025年 340卷

作者： Javad Mohammadpour Danah Ruth Cahanap Danish Ansari Christophe Duwig Fatemeh Salehi School of Engineering Macquarie University NSW 2109 Australia Department of Chemical Engineering Royal Institute of Technology Stockholm Sweden

Concentrated photovoltaic (CPV) systems, with their high efficiency and compact design, support green hydrogen production and contribute to United NationsSustainable Development Goal 7 (Affordable and Clean Energy). However, their performance and longevity can be significantly compromised by inadequate thermal management. To address this challenge, this study proposes a data-driven framework that enhances CPV thermal optimisation while reducing reliance on computationally intensive simulations. A novel variable pin–fin height heat sink is evaluated with the aim of minimising maximum temperature rise, temperature non-uniformity, and pressure drop. Five tree-based machine learning (ML) models, including Decision Tree, Random Forest, Gradient Boosting, XGBoost, and CatBoost, are assessed, with CatBoost demonstrating the highest predictive accuracy. This model is used as a surrogate for high-fidelity simulations, enabling efficient multi-objective optimisation using the non-dominated sorting genetic algorithm III (NSGA-III). To identify the most balanced configuration among the Pareto-optimal solutions, six multi-criteria decision-making (MCDM) models are applied. Results indicate that PROBID and PROMETHEE II, among the six MCDM models, effectively balance the competing objectives, producing a configuration that reduces temperature non-uniformity by 70.48 % and pressure drop by 41.84 % compared to a conventional uniform design. Validation against high-fidelity simulations confirms the accuracy of ML predictions, with an error margin between 0 and 0.063 %. This integrated surrogate-based approach offers a cost- and time-efficient solution for optimising CPV systems and other high-density thermal applications.

关键词： Concentrating photovoltaic ML surrogate model Multi-objective optimisation Multi-criteria decision-making non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Leveraging genetic algorithms and neural networks to optimise a UAV support arm for stiffness and weight efficiency

引用

Materials & Design 2025年

作者： Iuri H. Müller José Humberto S. Almeida Sandro C. Amico Maikson L.P. Tonatto Mechanics of Materials and Structures Group Federal University of Santa Maria Cachoeira do Sul Brazil Department of Mechanical Engineering LUT University Lappeenranta Finland PPGE3M/PROMEC Federal University of Rio Grande do Sul Porto Alegre Brazil

The increasing demand for lightweight and high-performance structures in aerospace applications has spurred the development of advanced design frameworks for 3D-printed composite components. This study proposes a multi-objective optimisation approach that integrates the non-dominated sorting genetic algorithm II (NSGA-II) with an Artificial Neural Network (ANN) to optimise the design of a UAV support arm. The dual objectives are to minimise weight and maximise stiffness. A finite element (FE) database is first constructed using four geometric parameters: height, width, lattice element count, and thickness; under combined thrust and torsional loading. This is expanded with three additional parameters − edge thickness, lower reinforcement thickness, and upper reinforcement width − for ANN training. The ANN predicts mass and stiffness with over 99% accuracy while reducing computational time by 99% compared to full FE simulations. NSGA-II then generates a Pareto front, from which an optimal design is selected and fabricated using fused filament fabrication (FFF) with polylactide (PLA). The final prototype achieves a 42% weight reduction and a 51% increase in specific stiffness relative to the baseline, demonstrating the potential of the proposed framework for solving complex composite design problems.

关键词： Multi-objective optimisation non-dominated sorting genetic algorithm Artificial neural network Composite structures Additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in Cloud Computing Environment based on NSGA-Ⅱ

Resource Allocation in Cloud Computing Environment based on ...

引用

作者： Hesheng Gong College of Economics and Management Nanjing University of Aeronautics and Astronautics

In the cloud computing environment,physical resources are abstracted into the same virtual resource,but the allocation of virtual resources also needs to be scheduled to make the entire allocation system more reasonable,rapid,efficient and minimize the total *** to schedule virtual resources to physical resources is a basic and complex problem in cloud *** scheduling of virtual resources is modeled and proved difficult to *** solution of the model is transformed into a multi-objective optimization problem with system load balancing as the optimization objective,and an improved genetic algorithm based on nondominated sorting(NSGA-Ⅱ) is *** solve this problem,genetic algorithm is used to finally map out the best scheduling scheme through the termination population *** with scheduling algorithms for specific environments,abstract models are more representative of virtual resource scheduling problems in typical cloud computing ***,the proposed model was simulated,and the quota of different resources of each virtual machine was restricted when the initial population was generated;the load balancing idea was considered when designing the fitness function,and based on this,the formula for the measurement standard was carried *** experimental results show the effectiveness of the model and the feasibility of the NSGA-Ⅱ algorithm to solve the problem.

关键词： Cloud computing multi-objective optimization non-dominated sorting genetic algorithm scheduling

来源：评论

学校读者我要写书评

暂无评论

Cutting parameter optimization for machining operations considering carbon emissions

引用

JOURNAL OF CLEANER PRODUCTION 2019年 208卷 937-950页

作者： Zhou, Guanghui Lu, Qi Xiao, Zhongdong Zhou, Ce Tian, Changle Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710054 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Management Xian 710049 Peoples R China

With the aggravation of global warming and implementation of carbon policies such as carbon tax and carbon labeling, manufacturing enterprises have to cope with the stress from eco-environment and production cost. Cutting parameters in the part machining process have a huge impact on energy and material consumption, cutting time and economy of manufacturing system. The traditional cutting parameters are always selected based on human experience and handbooks, which lacks the attention on energy and material saving. In this paper, a cutting parameter optimization method for machining operations considering carbon emissions is proposed to balance cutting indexes, i.e., carbon emissions, cutting time and cutting cost, in the part machining process. Firstly, the numerical relationships between cutting parameters and cutting indexes are analyzed. Particularly, considering the processing capacity of a workshop and machining features, formalized tables named c-PBOM-W (Carbon emissions integrated Process Bill of Material for Workshop) and c-PBOM-P (Carbon emissions integrated Process Bill of Material for Part) are designed to evaluate carbon emissions easily. Then, a multi-objective parameter optimization model is proposed. By introducing non-cooperative game theory, an improved algorithm, non-cooperative Game theory Integrated NSGA-II (NG-NSGA-II), is developed to solve the model. Finally, a cylindrical turning is taken as a case to illustrate the rationality of the proposed cutting parameter optimization method. The simulation results show that the NG-NSGA-II has a better performance than NSGA-II. Thus, the proposed method could provide the optimal cutting parameters in the part machining process to decrease carbon emissions, cutting time, and cutting cost. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Carbon emissions Cutting parameters Multi-objective optimization non-cooperative game theory non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved genetic algorithm based on particle swarm optimization-inspired reference point placement

引用

ENGINEERING OPTIMIZATION 2019年第7期51卷 1097-1114页

作者： Essiet, Ima O. Sun, Yanxia Wang, Zenghui Univ Johannesburg Dept Elect & Elect Engn Sci Johannesburg South Africa Univ South Africa Dept Elect & Min Engn Pretoria South Africa

This article investigates the use of optimal reference point placement to improve performance of non-dominated sorting genetic algorithm (NSGA). Placement of reference points for many-objective optimization is inspired by wheel and Von Neumann topologies of Particle Swarm Optimization (PSO). Results obtained show that the pattern of reference point placement determines performance efficiency of NSGA. The better-performing wheel topology (called wheel reference point genetic algorithm (wRPGA), is compared to three other many-objective evolutionary algorithms: knee-driven evolutionary algorithm (KnEA), non-dominated sorting genetic algorithm III (NSGAIII) and multi-objective evolutionary algorithm based on dominance and decomposition (MOEAD/D). The selected many-objective benchmark problems are Walking Fish Group 2 (WFG2) and Deb-Thiele-Laumanns-Zitzler 2 (DTLZ2). It is also tested on a 3-objective cost function for a hypothetical model of a stand-alone microgrid. Through the simulations, the wheel configuration performed 88.9% better than the Von Neumann configuration. The wheel topology also achieved better performance with respect to inverted generational distance (IGD) compared to KnEA, NSGAIII and MOEAD/D for 7 out of 15 IEEE Congress on Evolutionary Computation (CEC) 2017 benchmark problems. wRPGA gave a good approximation of the Pareto front for the 3-objective model representing the hypothetical microgrid.

关键词： non-dominated sorting genetic algorithm reference points optimization inverted generational distance hyper-plane

来源：评论

学校读者我要写书评

暂无评论

Fuel consumption potential of different external combustion gas-turbine thermodynamic configurations for extended range electric vehicles

引用

ENERGY 2019年 175卷 900-913页

作者： Reine, Alexandre Nader, Wissam Bou ENSPM Rueil Malmaison France PSA Grp Ctr Tech Velizy Velizy Villacoublay France

External combustion gas-turbine (ECGT) systems are among potential multi-fuel energy converters to substitute the internal combustion engine (ICE) as auxiliary power unit (APU) in future extended range hybrid electric vehicle (EREV) powertrains. Fuel consumption of these APUs in EREV strongly relies on the energy converter efficiency and power to weight ratio as well as on the energy management strategy deployed on-board. This paper presents a technological analysis and investigates the potential of fuel consumption savings of an EREV using different ECGT-system thermodynamic configurations. These include a simple ECGT (S-ECGT), a downstream simple ECGT (DS-ECGT), a downstream intercooled ECGT (DS-ECGT) and a downstream intercooled reheat ECGT (DIRe-ECGT). An energetic and technological analysis is conducted to identify the systems' efficiency and power to weight ratio for different operating temperatures. An EREV model is developed and the different ECGT-system configurations are integrated as APUs. A bi-level optimization method is proposed to optimize the powertrain. It consists of coupling the non-dominated sorting genetic algorithm (NSGA) to the dynamic programing (DP) in order to minimize the fuel consumption and the number of switching On/Off of the APU, which impacts its durability. Fuel consumption simulations are performed on the worldwide-harmonized light vehicles test cycle (WLTC). Results show that the DIRe-ECGT-APU presents an improved fuel consumption compared to the other investigated ECGT-systems and a good potential for implementation in EREVs. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： External combustion gas-turbine Extended-range-electric-vehicle Technological analysis non-dominated sorting genetic algorithm Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Optimal control of novel fuel cell-based DVR using ANFISC-MOSSA to increase FRT capability of DFIG-wind turbine

引用

SOFT COMPUTING 2019年第15期23卷 6633-6655页

作者： Falehi, Ali Darvish Rafiee, Mansour Shahid Beheshti Univ Dept Elect Engn Tehran Iran

Although Doubly fed induction generator (DFIG)-based wind turbine has several significant advantages, any voltage fluctuation can severely disturb its normal and safe operation, i.e., it is characteristically very sensitive. Hence, fault ride-through is determined as a prominent benchmark for DFIG which must be enhanced by a voltage compensator. Dynamic voltage restorer (DVR), a voltage fluctuation mitigator, is connected in-series with distribution and sub-transmission lines so that DFIG can appropriately operate during any type of disturbance. In this paper, a new two switches boost converter (TSBC) coupled with quinary multilevel inverter (QMLI) is proposed which is fed by fuel cell to produce staircase sinusoidal voltage for DVR. The proposed step-up DC/DC presents two important advantages: low current ripple and low switch stress, while QMLI can create high-step staircase sinusoidal voltage without considering a number of switches. TSBC-QMLI-based DVR has been controlled by neuro fuzzy inference system controller (ANFISC). As the control problem is multi-objective and complex, Multi-Objective Salp Swarm algorithm (MOSSA) has been applied to optimally tune the ANFISC's parameters, and then compared with non-dominated sorting genetic algorithm II (NSGA-II). To verify and validate the compensation capability of proposed DVR, it has been thoroughly evaluated under different voltage disturbances. Eventually, the simulation results have validated the compensation capability of the suggested TSBC-QMLI-based DVR which is accurately controlled by MOSSA-based ANFISC to mitigate the balanced and unbalanced voltage sag and swell along with the flicker and harmonic voltage.

关键词： Fuel cell Wind turbine Dynamic voltage restorer Doubly fed induction generator Multi-Objective Salp Swarm algorithm non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

An NSGA-II-based multiobjective approach for real-time routing selection in a flexible manufacturing system under uncertainty and reliability constraints

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2019年第9-12期100卷 2813-2829页

作者： Souier, Mehdi Dahane, Mohammed Maliki, Fouad Univ Tlemcen MELT PB 230 Tilimsen 13000 Algeria High Sch Management Tlemcen PB 1085 Tilimsen 13000 Algeria Univ Lorraine LGIPM F-57000 Metz France High Sch Appl Sci Tlemcen BP 165 Tilimsen 13000 Algeria

Routing flexibility is one of the most common types of flexibilities of manufacturing systems. It allows the system to continue producing given part types despite uncertainties. Its main purpose is to maintain a high level of performance so that the system can deal with disturbances (failures, maintenance actions,...). This type of flexibility occurs when there are alternative or redundant machine tools in the system. However, due to resource and alternative routing limitations, the scheduling problems in such systems can become very complex. Furthermore, though routing flexibility aims to enhance system responsiveness, it still depends on the reliability and availability of machines and individual components in a system. The present paper aims to investigate the scheduling problem in a flexible manufacturing system (FMS) with routing flexibility under uncertainties related to the random arrival of parts orders and machines failures, by considering reliability and maintenance constraints. The real-time decisions for part routing selection are made using a non-dominated sorting genetic algorithm (NSGA-II), by considering the workload, utilization level, and reliability of machines in a workstation, in order to minimize the deadlocks and maximize the overall system reliability. The simulation results obtained showed that, for an overloaded system, the proposed NSGA-II algorithm induces the best performance in terms of total profit, system productivity, and machines utilization.

关键词： Flexible manufacturing system Routing flexibility non-dominated sorting genetic algorithm Reliability Maintenance

来源：评论

学校读者我要写书评

暂无评论

PSS design for damping low-frequency oscillations in a multi-machine power system with penetration of renewable power generations

引用

IET RENEWABLE POWER GENERATION 2019年第1期13卷 116-127页

作者： Kahouli, Omar Jebali, Mariam Alshammari, Badr Abdallah, Hsan Hadj Natl Engn Sch Sfax Control & Energies Management CEM Lab Route Sokra Km 3-5BP 1173-3038 Sfax Tunisia Hail Univ Fac Engn POB 2440 Hail Saudi Arabia

This study focused on the use of the non-dominated sorting genetic algorithm (NSGA-II) to achieve an optimal power system stabiliser (PSS) parameters for a given operating point with a renewable source of energy so as to increase the system damping and guarantee enough stability margin. The parameters tuning was formulated using an eigenvalue-based multi-objective function. In recent years, the changeability and fluctuation of the wind power injected into the network have led to new challenges in small signal stability (SSS). These wind speed change and load demand change perturbations take place routinely and cause the variation of the operating conditions. However, as the conventional PSS is conceived for a fixed operating point in order to obtain the linearised transfer function model, it cannot yield good results when the operating range is too wide. To this end, the adaptive neuro-fuzzy inference system was proposed to estimate the stabiliser parameters in real time after a learning phase. The nine-bus Western System Coordinating Council and the obtained simulations results were assessed using Matlab/Simulink package. The validity of the proposed methodology was checked through the PSS parameters evolution simulation for daily load forecast curves and monthly wind speed prediction curves.

关键词： power system stability genetic algorithms eigenvalues and eigenfunctions power engineering computing wind power plants transfer functions damping fuzzy neural nets PSS design multimachine power system NSGA-II optimal power system stabiliser parameters system damping stability margin parameters tuning changeability wind power operating conditions conventional PSS fixed operating point linearised transfer function model operating range adaptive neuro-fuzzy inference system nine-bus Western System Coordinating Council PSS parameters evolution simulation monthly wind speed prediction curves low-frequency oscillations damping non-dominated sorting genetic algorithm small signal stability wind speed change renewable power generation penetration eigenvalue-based multiobjective function load demand change perturbations

来源：评论

学校读者我要写书评

暂无评论

Agent-Based Modeling for Evaluation of Crop Pattern and Water Management Policies

引用

WATER RESOURCES MANAGEMENT 2019年第11期33卷 3707-3720页

作者： Nouri, Alireza Saghafian, Bahram Delavar, Majid Bazargan-Lari, Mohammad Reza Islamic Azad Univ Dept Civil Engn Sci & Res Branch Tehran Iran Tarbiat Modares Univ Dept Water Resources Engn Tehran Iran Islamic Azad Univ East Tehran Branch Dept Civil Engn Tehran Iran

The objective of the present paper is to propose a framework for development of an optimal cropping pattern aimed at ground water recovery using an agent based approach. In the proposed agent-based model (ABM), the agents' learning from each other as well as their self-learning from their own behavioral feedback was studied through simulation of the behavior of agricultural agents using fuzzy inference system (FIS). Moreover, the agents' behavior were determined using linear programming in order to maximize the farmers' income. The governmental agent regulated the interactions between agricultural and environmental agents by imposing its policies in the form of scenarios. The efficiency of the presented methodology was evaluated using hydrological data of Najaf Abad region, located in Iran's central plain, on the basis of three hydrological scenarios (wet, normal, and dry) subject to governmental policy of aquifer recovery. The results showed that in a normal scenario with current groundwater withdrawal, the water level reduced by an average of 0.18 m per year. In contrast, the water level increased by an average of 0.48 m under aquifer recovery scenario. Furthermore, despite 17% reduction in water rights of agricultural agents in the study area, the total long-term agricultural income declined only by less than 4%, and in the planning horizon, their average annual income associated with these two management scenarios were estimated at 123.5 and 119 million US dollars, respectively.

关键词： Agent Based Model Fuzzy Inference System Behavioral Constraints Ground Water Recovery non-dominated sorting 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：