检索结果-内蒙古大学图书馆

multi-objective Optimization of Different Management Scenarios to Control Seawater Intrusion in Coastal Aquifers

WATER RESOURCES MANAGEMENT 2015年第6期29卷 1843-1857页

作者： Javadi, Akbar Hussain, Mohammed Sherif, Mohsen Farmani, Raziyeh Univ Exeter Sch Engn Comp Sci & Math Exeter EX4 4QF Devon England UAE Univ Civil & Environm Engn Dept Fac Engn Al Ain U Arab Emirates

Seawater intrusion (SWI) is a widespread environmental problem, particularly in arid and semi-arid coastal areas. Therefore, appropriate management strategies should be implemented in coastal aquifers to control SWI with acceptable limits of economic and environmental costs. This paper presents the results of an investigation on the efficiencies of different management scenarios for controlling saltwater intrusion using a simulation-optimization approach. A new methodology is proposed to control SWI in coastal aquifers. The proposed method is based on a combination of abstraction of saline water near shoreline, desalination of the abstracted water for domestic consumption and recharge of the aquifer by deep injection of the treated wastewater to ensure the sustainability of the aquifer. The efficiency of the proposed method is investigated in terms of water quality and capital and maintenance costs in comparison with other scenarios of groundwater management. A multi-objective genetic algorithm based evolutionary optimization model is integrated with the numerical simulation model to search for optimal solution of each scenario of SWI control. The main objective is to minimize both the total cost of management process and the total salinity in aquifer. The results indicate that the proposed method is efficient in controlling SWI as it offers the least cost and least salinity in the aquifer.

关键词： Seawater intrusion Simulation-optimization multi-objective genetic algorithm Treated wastewater Management scenarios

来源：评论

学校读者我要写书评

暂无评论

Optimization design of trapezoidal flow field proton exchange membrane fuel cell combined with computational fluid dynamics, surrogate model, and multi-objective optimization algorithm

引用

IONICS 2024年第6期30卷 3375-3389页

作者： Wang, Changjiang Yu, Zeting Wu, Haonan Wang, Daohan Shandong Univ Sch Energy & Power Engn Jinan 250061 Peoples R China Shandong Univ Sch Elect Engn Jinan 250061 Peoples R China

The flow field structure plays the key roles in the operating reliability and power output of proton exchange membrane fuel cell (PEMFC). This study investigates and compares two typical structural parameters of PEMFC with the trapezoidal flow channel (TFC) and the trapezoidal flow channel with block (TFCB). A three-dimensional (3-D) multiphase TFC model is first developed, and then the multi-objective optimization is performed by using the trained artificial neural network (ANN) surrogate model and non-dominated sorting genetic algorithm (NSGA-II). Finally, the technique for order preference by similarity to an ideal solution (TOPSIS) is used to investigate the optimized structural parameters of TFC. The results show the net power output and the oxygen uniformity index of the optimized TFC are increased by 19.77% and 21.92% compared with the straight flow channel (SFC). Furthermore, it is also found using block in the trapezoidal flow channel (TFCB) can increase the performance of PEMFC, and it exhibits a 25.10% improvement for the net power output and 27.88% for oxygen uniformity index, respectively.

关键词： Proton exchange membrane fuel cell Trapezoidal flow field optimization Block Computational fluid dynamics Artificial neural network multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A multi-objective optimization approach for green supply chain network design for the sea cucumber ( Apostichopus japonicus ) industry

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2024年 927卷 172050页

作者： Ren, Anqi Yu, Lixingbo Zhao, Xintao Jia, Fei Han, Fengfan Hou, Haochen Liu, Ying Dalian Ocean Univ Minist Educ Key Lab Environm Controlled Aquaculture 52 Heishijiao St Dalian 116023 Peoples R China Dalian Ocean Univ Coll Marine Technol & Environm 52 Heishijiao St Dalian 116023 Peoples R China Dalian Bangchui Isl Sea Cucumber Dev Co Ltd 987 Wuyi Rd Dalian 116100 Peoples R China Zhejiang Univ Coll Biosyst Engn & Food Sci 866 Yuhangtang Rd Hangzhou 310058 Peoples R China

In China, aquatic supply chain network design does not include the green concept or the coordination of environmental and economic performance. Sea cucumber ( Apostichopus japonicus ) is an aquatic product of high economic value;however, studies on sea cucumber supply chain network optimization are lacking. This study is the first to design the sea cucumber supply chain and construct an optimization model. Considering the characteristics of the sea cucumber industry, LCA for Experts software and the CML-IA-Aug. 2016 -world method were used to assess each aquaculture model ' s global warming potential (GWP), as the environmental performance indicator. In addition, multi -objective genetic algorithm (MOGA) coupled with Modified Technique for Order of Preference by Similarity to Ideal Solution (M-TOPSIS) integrates yield production, economic benefits, and environmental performance. The results demonstrated that cage seed rearing (CSR) combined bottom sowing aquaculture (BSA) represents the best production strategy upstream of the sea cucumber supply chain. In the downstream, the best proportion of sales channels in supermarkets, boutique stores and online shops accounted for 14.79 %, 58.02 % and 27.19 % of the production, respectively. The proposed optimization scenario 4 (S4) can increase product profit by 27.88 % and reduce GWP by 56.89 %. The following improvement measures are proposed: using sea cucumber aquaculture industry standards (cleaner production and green supplier selection) to regulate the behavior of enterprises, adopting an ecological and green production strategy, eliminating highenergy consumption and high emission production practices, and promoting widespread adoption of green consumption concepts. Finally, these measures may improve the sea cucumber supply chain, achieve coordinated environmental and economic performance development in the sea cucumber industry, and provide guidance for green optimization of other aquatic product supply chains in C

关键词： Life cycle assessment Green supply chain Network design multi-objective genetic algorithm M-TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2022年第2期8卷 542-556页

作者： Perenda, Erma Rajendran, Sreeraj Bovet, Gerome Pollin, Sofie Zheleva, Mariya Katholieke Univ Leuven ESAT WaveCore Leuven Belgium EluciDATA Lab Sirris Belgium Armasuisse Sci & Technol Swiss Dept Def CH-3602 Thun Switzerland SUNY Albany Dept Comp Sci Albany NY 12222 USA

Automatic modulation classification receives significant interest in the context of current and future wireless communication systems. Deep learning emerged as a powerful tool for modulation classification, as it allows for joint discriminative features learning and signal classification. However, the optimization of deep neural network architectures for modulation classification is a manual and time-consuming process that requires profound domain knowledge and much effort. Most state-of-the-art solutions focus mainly on classification accuracy, while optimization of network complexity is neglected. This paper presents a novel bi-objective memetic algorithm, BO-NSMA, to search optimal deep neural network architectures for modulation classification to maximize classification accuracy and minimize network complexity. The experiments show that BO-NSMA, with an initial population of six individuals and only ten generations, finds a deep neural network architecture that outperforms all human-crafted architectures. Furthermore, BO-NSMA discovered the first low-complexity Convolutional neural network architecture, which achieves slightly better performance than costly Recurrent neural network architectures, allowing a 2.9-fold reduction in network complexity with 1.43% performance improvement. Compared to counterparts from network architecture search, BO-NSMA finds the best architecture, which achieves up to 18.73% accuracy gain and up to an 82-fold reduction in network complexity. The results are validated using the Wilcoxon signed-rank test.

关键词： Modulation classification deep learning network architecture search multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective parametric optimization on machining with wire electric discharge machining

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2012年第5-8期62卷 617-633页

作者： Kumar, Kapil Agarwal, Sanjay Bundelkhand Inst Engn & Technol Dept Mech Engn Jhansi 284128 Uttar Pradesh India

The selection of optimum machining conditions, during wire electric discharge machining process, is of great concern in manufacturing industries these days. The increasing quality demands, at higher productivity levels, require the wire electric discharge machining process to be executed more efficiently. Specifically, the material removal rate needs to be maximized while controlling the surface quality. Despite extensive research on wire electric discharge machining process, determining the desirable operating conditions in industrial setting still relies on the skill of the operators and trial-and-error methods. In the present work, an attempt has been made to optimize the machining conditions for maximum material removal rate and maximum surface finish based on multi-objective genetic algorithm. Experiments, based on Taguchi's parameter design, were carried out to study the effect of various parameters, viz. pulse peak current, pulse-on time, pulse-off time, wire feed, wire tension and flushing pressure, on the material removal rate and surface finish. It has been observed that a combination of factors for optimization of each performance measure is different. So, mathematical models were developed between machining parameters and responses like metal removal rate and surface finish by using nonlinear regression analysis. These mathematical models were then optimized by using multi-objective optimisation technique based on Non-dominated Sorting genetic algorithm-II to obtain a Pareto-optimal solution set.

关键词： WEDM Taguchi technique multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of hybrid backorder inventory model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2016年 51卷 76-84页

作者： Srivastav, Achin Agrawal, Sunil Pandit Dwarka Prasad Mishra Indian Inst Informat Jabalpur MP India Pandit Dwarka Prasad Mishra Indian Inst Informat Dept Mech Engn Jabalpur Dumna Airport RdPO Khamaria Jabalpur MP India Flat E-801 Jaipur 302001 Rajasthan India

This paper addresses inventory problem for the products that are sold in monopolistic and captive markets experiencing hybrid backorder (i.e., fixed backorder and time-weighted backorder). The problem with stochastic demand is studied first by developing single objective (cost) inventory model. Computational results of a numerical problem show the effectiveness of hybrid backorder inventory model over fixed backorder inventory model. The model is later extended to multi-objective inventory model. Three objectives of multi-objective inventory model are the minimization of total cost, minimization of stockout units and minimization of the frequency of stockout. A multi-objective particle swarm optimization (MOPSO) algorithm is used to solve the inventory model and generate Pareto curves. The Pareto curves obtained for hybrid backorder inventory model are compared with the existing Pareto curves that are based on fixed backorder. The results show a substantial reduction in stockout units and frequency of stockout with a marginal rise in cost with proposed hybrid backorder inventory system in comparison to existing fixed backorder inventory system. Sensitivity analysis is done to study the robustness of total cost, order quantity, and safety stock factor with the change in holding cost. In the end, the performance of the MOPSO algorithm is compared with the multi-objective genetic algorithm (MOGA). The metrics that are used for the performance measurement of the algorithms are error ratio, spacing and maximum spread. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Backorder Inventory multi-objective particle swarm optimization Pareto multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy force learning controller of flexible wiper system

引用

NEURAL COMPUTING & APPLICATIONS 2016年第2期27卷 483-493页

作者： Zolfagharian, Ali Valipour, P. Ghasemi, S. E. Univ Teknol Malaysia Dept Syst Dynam & Control Johor Baharu Johor Malaysia Islamic Azad Univ Dept Text & Apparel Qaemshahr Branch Qaemshahr Iran Islamic Azad Univ Young Reseachers & Elite Club Qaemshahr Branch Qaemshahr Iran

Wiper blade of automobile is among those types of flexible system that is required to be operated in quite high velocity to be efficient in high load conditions. This causes some annoying noise and deteriorated vision for occupants. The modeling and control of vibration and low-frequency noise of an automobile wiper blade using soft computing techniques are focused in this study. The flexible vibration and noise model of wiper system are estimated using artificial intelligence system identification approach. A PD-type fuzzy logic controller and a PI-type fuzzy logic controller are combined in cascade with active force control (AFC)-based iterative learning (IL). A multiobjective genetic algorithm is also used to determine the scaling factors of the inputs and outputs of the PID-FLC as well as AFC-based IL gains. The results from the proposed controller namely fuzzy force learning (FFL) are compared with those of a conventional lead-lag-type controller and the wiper bang-bang input. Designing controllers based on classical methods could become tedious, especially for systems with high-order model. In contrast, FFL controller design requires only tuning of some scaling factors in the control loop and hence is much simpler and efficient than classical design methods.

关键词： Automotive wiper System identification Intelligent control multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Scheduling of virtual manufacturing cells with outsourcing allowed

引用

INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2014年第12期27卷 1079-1089页

作者： Arkat, Jamal Ghahve, Homa Univ Kurdistan Dept Ind Engn Sanandaj Iran

This paper presents a bi-objective mixed integer programming model for operations scheduling in virtual manufacturing cells where outsourcing is allowed, and set-up times are considered to be sequence dependent. Two objective functions of the model are the minimisation of the maximum completion time (or makespan) and the minimisation of the total cost of inter and intra-plant transportation. Two multi-objective solution algorithms are then developed to solve the proposed model. The first algorithm is an epsilon-constraint method which can find the exact set of efficient solutions for small-size problems. Since the investigated problem is non-polynomial (NP) hard, exact algorithms cannot be used for large-scale real-world cases and, therefore, a bi-objective genetic algorithm (GA) is developed as the second algorithm. A numerical example is given to evaluate the effectiveness of the proposed model and solution algorithms. The results reveal the superiority of the proposed model over the base models and demonstrate that in comparison with the epsilon-constraint method, the proposed GA can obtain efficient solutions in much less computational time.

关键词： virtual manufacturing cell scheduling outsourcing multi-objective genetic algorithm epsilon-constraint method

来源：评论

学校读者我要写书评

暂无评论

Performance enhancement of a small-scale organic Rankine cycle radial-inflow turbine through multi-objective optimization algorithm

引用

ENERGY 2017年 131卷 297-311页

作者： Al Jubori, Ayad M. Al-Dadah, Raya Mahmoud, Saad Univ Birmingham Sch Engn Birmingham B15 2TT W Midlands England Univ Technol Baghdad Baghdad Iraq

An effective methodology that encompasses a mean-line design, three-dimensional CFD analysis and optimization and ORC system modelling of the small-scale ORC radial-inflow turbine is presented. Three-dimensional CFD analysis and a multi-objective optimization algorithm were achieved using ANSYS (R)(17) CFX and Design Exploration based on 3D RANS with a k-omega SST turbulence model. The 3D optimization technique combines a design of the experiment, a response surface method and multi-objective method. The optimization of the blade geometry was performed using 20 design points for both nozzle and rotor blades, based on the B-splines' technique to represent the blade angles and thickness distribution. The number of blades and rotor tip clearance were included as design parameters. The isentropic,efficiency and power output were introduced as an optimization objective with two organic working fluids, namely isopentane and R245fa. The results of the optimized geometry with R245fa showed that the turbine's and cycle's thermal efficiencies were higher by 13.95% and 1738% respectively, compared with a base-line design with a maximum power output of 5.415 kW. Such methodology is proved to be effective as it allows the enhancing of the turbine's and the ORC's system performance throughout to find the optimum blade shape of the turbine stage. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Small-scale radial-inflow turbine Preliminary mean-line design ORC 3D CFD optimization multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Method for Design of a Growing Complex Network

引用

ELECTRONICS AND COMMUNICATIONS IN JAPAN 2014年第1期97卷 70-81页

作者： Mizuno, Haruki Okamoto, Takashi Koakutsu, Seiichi Hirata, Hironori Chiba Univ Chiba Japan Chiba Univ Grad Sch Engn Chiba Japan

A complex network design method that finds a desired network structure can be a powerful tool in large-scale system design. Conventional complex network design methods tackle only static networks, that is, they do not consider growth of the target network. In this paper, we propose a new method for the design of a growing complex network. First, we consider evaluation functions which quantitatively represent the characteristics of desired structures by using feature quantities. Then, we formulate the design problem of a growing complex network as a multi-objective optimization problem in order to determine the connection targets of new nodes by using the evaluation functions. By solving the problem, we grow the network, thus obtaining the desired network. We try to generate networks which have the desired clustering coefficient and average path length concurrently. Through numerical experiments, we confirm that the proposed method is effective as a method for the design of growing complex networks. (c) 2013 Wiley Periodicals, Inc. Electron Comm Jpn, 97(1): 70-81, 2014;Published online in Wiley Online Library (***). DOI 10.1002/ecj.10382

关键词： complex network multi-objective optimization growing network network design 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：