检索结果-内蒙古大学图书馆

Optimizing of working conditions of vanadium redox flow battery based on artificial neural network and genetic algorithms

引用

JOURNAL OF ENERGY STORAGE 2024年 100卷

作者： Wang, Qiong Yan, Ruijie Ren, Longhui Qu, Zhiguo Jiang, Zhiyuan Wang, Zhengdong Zhang, Cheng Wang, Juan Xian Univ Architecture & Technol Sch Mech & Elect Engn 13 Yanta Rd Xian 710055 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Energy & Power Engn 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Chem Engn & Technol 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China Coventry Univ Inst Clean Growth & Future Mobil CALPS Cheetah Rd Coventry CV12TL England Xian Univ Architecture & Technol Sch Mech & Elect Engn Shanxi Key Lab Nanomat & Nanotechnol 13 Yanta Rd Xian 710055 Shaanxi Peoples R China

The integration of electrode compression in a vanadium redox flow battery (VRFB) with optimized operating conditions is essential for achieving the maximum net discharge power. This study presents the development of a 3D steady-state model for VRFB aimed at maximizing net discharge power (Pnet) by optimizing key working conditions, including electrode compression ratio (CR), applied current density (Iapp), and electrolyte inflow rate (Qin). The comprehensive impacts of CR, Iapp, and Qin on VRFB charging and discharging curves, energy efficiency (EE), and system efficiency (SE), and Pnet were investigated. Subsequently, the optimization of CR and Qin under a fixed applied current density range of 20-400 mA/cm2 was carried out employing a hybrid methodology integrating artificial neural network (ANN) and genetic algorithms (GA). Results reveals that increasing CR does not linearly improve system efficiency and net discharge power, with an optimal CR identified to maximize net discharge power. The optimal CR varies with operating conditions and is influenced by factors such as Qin and Iapp. Notably, both CR and Qin negatively impact net discharge power due to increased pump losses, while Iapp and state of charge (SOC) positively affect net discharge power through enhanced electron transfer and higher active substance concentration, respectively. The optimal CR is identified around 65 % for Iapp exceeding 60 mA/ cm2. Furthermore, the optimal Qin correlates directly with increasing Iapp, as higher Iapp rates necessitate greater Qin to sustain active species supply. This study offers an optimization approach for addressing coupled operating conditions and provides insights for achieving high net discharge power in VRFB operation.

关键词： Vanadium redox flow battery Net discharge power Compression ratio Flow rate Current density optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Double Decomposition-Based Wind Speed Prediction Model for Urad Area 2022

Double Decomposition-Based Wind Speed Prediction Model for U...

引用

6th International Conference on Machine Learning and Soft Computing (ICMLSC)

作者： Liu, Chuyi Zheng, Fengfeng Wan, Jianxiong Li, Leixiao Ma, Zhiqiang Wang, Yongsheng Inner Mongolia Univ Technol Hohhot Inner Mongolia Peoples R China Inner Mongolia Autonomous Reg Engn & Technol Res Hohhot Inner Mongolia Peoples R China

ISBN: (纸本)9781450387477

Renewable energy becomes progressively more important as time goes on. Wind, as one of the main rapidly developing renewable energy, is free, widely distributed, clean, environmental protection and sustainable development. The uncertainty of wind power which causes the inaccuracy of traditional wind speed prediction has become great challenge for wind power utilization. This paper predicts the wind speed by analyzing the measured data of 70-100m wind tower in Urad area. Handling the high-frequency sub-sequences after the first-level decomposition which cause the inaccuracy, a double decomposition based on EWT-VMD is proposed, which uses SampEn to determine the parameters of them. And then applied LSTM neural network to predict the wind speed one step in advance. The MAE, RMSE and R-2 of the proposed model improved by at least 10.5%, 11.4% and 1.5% when comparing with other models.

关键词： wind energy wind speed prediction optimization algorithm decomposition algorithm

来源：评论

学校读者我要写书评

暂无评论

A Sectorized FCS-MPC Transformerless SST For Power Transmission Application 24

A Sectorized FCS-MPC Transformerless SST For Power Transmiss...

引用

24th European Conference on Power Electronics and Applications (EPE ECCE Europe)

作者： Bacheti, Gabriel Gaburro Camargo, Renner Sartorio Bueno, Emilio Jose Liserre, Marco Encarnacao, Lucas Frizera Fed Univ Espirito Santo UFES Dept Elect Engn Ave Fernando Ferrari 514 BR-29075910 Vitoria Brazil Fed Inst Espirito Santo IFES Dept Control & Automat Engn Rod ES010 BR-29173087 Serra Brazil Alcala Univ UAH Dept Elect Pl San Diego Madrid 28801 Spain Univ Kiel Chair Power Elect Kaiserstr 2 Kiel Germany

ISBN: (纸本)9789075815399

This work proposes a sectorized optimization with Graph Theory applied in cascaded multilevel transformerless SST. The sectorized optimization can reduce the FCS-MPC combinational explosion due to the multiple cascaded H-bridges cells, while the proposed control is capable to avoid the prohibitive states maintaining the converter controllability and power quality.

关键词： Multi-level converters Model predictive control High voltage power converters SolidState Transformer optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Performance of 3D Printed Miniature GIS Spacer according to FGM Electrical Design and Designed Composition using Meta-Heuristic of NSGA-II 6

Evaluation of Performance of 3D Printed Miniature GIS Spacer...

引用

6th International Conference on Electric Power Equipment - Switching Technology (ICEPE-ST)

作者： Yo-Han, Noh Han-Goo, Cho EPLUS Elect CO LTD Dept Res & Dev Suwoni South Korea

ISBN: (纸本)9781665448673

Recently, with the miniaturization of GIS, there is a need for the miniaturization of spacers as accessories. Miniaturized spacers make it difficult to secure adequate insulation distances, resulting in a more concentrated electric field at the triple junction of high-voltage (HV) conductor-insulator (spacer)-insulation gas (SF6), which is a weakness in GIS. Therefore, by introducing a new concept design technology, functionally graded material (FGM), which is recently applied to various materials and parts industries, three-dimensional control of permittivity distribution in a spacer can be expected to alleviate triple-junction electric field occupancy and improve insulation performance. In this study, we propose an optimized model using NSGA-II to optimize the permittivity distribution of FGM applied spacer.

关键词： GIS Spacer FGM(Functional Graded Materials) Electric field relaxation NSGA-II optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Forecasting very short-term wind power generation using deep learning, optimization and data decomposition techniques 24

Forecasting very short-term wind power generation using deep...

引用

24th International Conference on Electrical Machines and Systems (ICEMS)

作者： Hossain, Md Alamgir Gray, Evan MacA Islam, Md Rabiul Chakrabortty, Ripon K. Pota, Hemanshu R. Griffith Univ Queensland Micro & Nanotechnol Ctr Nathan Qld 4111 Australia Univ New South Wales Canberra Sch Engn & IT Campbell ACT 2612 Australia

ISBN: (纸本)9788986510218

Although accurate wind power prediction can improve the reliability, security and economic operation of a power system, the prediction task is complex due to the intermittent nature of wind speed its strong dependence on weather conditions. This paper proposes a novel framework, consisting of hybrid deep learning models, an optimization algorithm and a data decomposition technique, to improve the forecasting accuracy of ultra-short-term wind power generation. The data of the wind power generation collected from a real wind farm are pre-processed and decomposed using a variational mode decomposition (VMD). A deep-learning model (long short-term memory (LSTM) with dropout regularization) is designed to accurately predict the decomposed spectra. The hyper-parameters of the model are optimized by applying the grey-wolf optimization (GWO) algorithm to choose the best hyper-parameters. The combination of deep learning and optimization algorithm plays a key role in achieving better prediction accuracy. The effectiveness of the proposed framework is measured by applying it to two data sets, and the framework is compared with other forecasting models, such as a hybrid deep-learning and empirical wavelet transform (EWT) with LSTM. Comparison with experimental results demonstrates that the novel hybrid framework has the best prediction accuracy in forecasting ultra short-term wind power generation.

关键词： Very-short term prediction wind power generation VMD data decomposition deep learning optimization algorithm Boco Rock wind farm

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Bayesian optimization for Multi-objective Industrial Applications

Computationally Efficient Bayesian Optimization for Multi-ob...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech Forum)

作者： Pandita, Piyush Ghosh, Sayan Wang, Liping GE Res Probabilist & Optimizat Grp Niskayuna NY 12309 USA

ISBN: (数字)9781624106095

ISBN: (纸本)9781624106095

Industrial problems often take the form of expensive laboratory experiments or computationallyheavy simulations. These expensive experiments or simulations provide valuable information about the underlying latent physical process being modeled. One is often faced with the problem of optimizing the quantity of interest (QoI) being represented by the information source. Querying the information source tens of thousands of times, generally required by state-of-the-art optimization algorithms, is practically infeasible. The problem becomes cumbersome when the number of objectives being optimized is greater than one. In such multi-objective optimization (MOO) scenarios, expected improvement (EI)-based methods have demonstrated great efficiency in converging to the optimal solution while taking into consideration a fixed budget. The EI-based methods, used for expensive MOO problems, are broadly called EI-hypervolume (EIHV) methods. The EI-based algorithm called, Bayesian global optimization (BGO), builds cheap probabilistic models of the objectives, using Gaussian process regression(GPR), and selects the next input to query the information source from amongst a finite set of candidate inputs. The EIHV weighs the potential improvement associated with each of the candidate designs. This iterative process continues until one exhausts the budget. The evaluation of the EIHV becomes painfully expensive, scales exponentially, as the number of objectives increases. The finite set of possible inputs, used to evaluate the EIHV and select the next query, ceases to be a computationally feasible option in order for the overall optimization to proceed. In this work, we aim to investigate the performance of an EI-based algorithm, for optimizing the EIHV for MOO problems. At each iteration of the optimization problem, we optimize the EIHV using EI-based BGO, in order to be computationally efficient. We demonstrate the approach on two mathematical MOO problems and one challenging industri

关键词： Bayesian optimization Gaussian Process Industrial Applications optimization algorithm Pareto Frontier Black Box Surrogate Model Evolutionary algorithm Design of Experiments Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A wind power prediction model with meteorological time delay and power characteristic

AIMS ENERGY

引用

AIMS ENERGY 2025年第3期13卷 517-539页

作者： Tian, Feng Shenyang Inst Engn Shenyang 110136 Peoples R China

Wind energy, as a widely distributed, pollution-free energy, is strongly supported by the government. Accurate wind power forecasting technology ensures the balance of the power system and enhances the security of the system. In this paper, a wind power prediction model with the improved long short-term memory (LSTM) network and Adaboost algorithm was constructed based on the mismatch of data and power climb. This method was based on mutual information (MI) and power division (PD), named MI-PD-AdaBoost-LSTM. MI was used for quantifying the time delay between variables and power. Furthermore, to solve the relationship between wind speed and power in different weather fluctuation processes, the method of power fluctuation process division was proposed. Moreover, the asymmetric loss function of AdaBoost-LSTM was constructed to deal with the asymmetric characteristics of wind power. An improved artificial bee colony (ABC) algorithm, which overcame the local optimal problem, was used to optimize the asymmetric loss function parameters. Finally, the performance of different deep learning prediction models and the proposed prediction model was analyzed in the experiment. Numerical simulations showed that the proposed algorithm effectively improves the power prediction accuracy with different time scales and seasons. The designed model provides guidance for wind farm power prediction.

关键词： wind power prediction renewable energy deep learning wind power asymmetry characteristics optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for load shifting operation of water pumping stations

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2021年第4期36卷 2081-2093页

作者： Kucuk, Hayri Turan, Mustafa Yarali, Kadir Al-Sanabani, Hussein Iskefiyeli, Murat Sakarya Univ Fac Engn Dept Elect & Elect Engn TR-54050 Sakarya Turkey Sakarya Univ Fac Comp & Informat Sci Dept Comp Engn TR-54050 Sakarya Turkey

The highest cost item in the operation of water distribution systems is the energy cost used for pumping. With regard to Time-of-Use (TOU) electricity tariffs and urban water demand, the optimization of the pumping schedule of the stations in the water distribution systems can be modeled mathematically. In this study, a new algorithm (SDPA- simplified dynamic programming algorithm) was used to solve the pumping schedule optimization problem in order to reduce the pumping energy cost. By shifting the energy demand during the on-peak period to the off-peak period, SDPA was applied to a pumping station belonging to a water distribution system in Sakarya province, a 12% saving on the cost of energy was realized. In comparison to the IDPA (Improved dynamic programming algorithm), and CWLC (conventional water level control) approach, the simulation results showed that SDPA can achieve more savings in energy cost generated. In addition, SDPA managed to keep the count of pump on-off decisions quite small by preventing the problem of increasing pump operating frequency while the decision period getting very smaller than the decision period in IDPA approach. Therefore, we can conclude that using SDPA to reconfigure the pumping schedule without any additional investment in the pumping stations of water distribution systems, can achieve significant energy savings.

关键词： Energy efficiency load shifting optimal pumping scheduling optimization algorithm water distribution system

来源：评论

学校读者我要写书评

暂无评论

Prediction of abrasion resistance characteristics of sintered aggregates from coal gangue and feldspar powder based on optimized BP-ANN neural network

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 487卷

作者： Deng, Wei Xiong, Rui Wang, Haoyu Zong, Youjie Sheng, Yanping Guan, Bowen Chang, Mingfeng Changan Univ Sch Mat Sci & Engn Xian 710061 Peoples R China Univ Nottingham Sch Civil Engn Nottingham NG1 4BU England

Developing new high-quality utilization pathways for coal gangue is crucial for precise absorption. The abrasion resistance of coal gangue-feldspar powder sintered aggregates (GFAA) is evaluated using Vickers hardness and crystallinity as indicators. The impact of sintering conditions on the physical properties and crystallization process of GFAA is investigated through correlation matrices and principal component analysis. A backpropagation artificial neural network (BP-ANN) predictive model with a topology of 6-7-1 is designed and optimized using PSO (Particle Swarm optimization) and GA (Genetic algorithm) to enhance the accuracy of a multi-index evaluation model. The results indicate that optimizing raw material proportions and increasing sintering temperatures significantly enhance the performance of GFAA. Additionally, the incorporation of fluxing components is shown to accelerate the depolymerization of the glass network structure and reduce the system's liquid-phase viscosity, with GFAA exhibiting Vickers hardness significantly greater than that of natural aggregates. High accuracy is demonstrated by both the BP-ANN and its optimized models;the models optimized using PSO and GA result in reductions in RMSE of 19.43 % and 15.31 % for Vickers hardness predictions and 26.30 % and 28.07 % for crystallinity predictions, respectively, thereby showcasing superior accuracy and generalization ability. Consequently, the high predictive accuracy of the optimized models provides valuable guidance for the design of mixed proportions of high abrasion-resistant aggregates developed from solid waste.

关键词： Artificial aggregate Machine learning optimization algorithm Abrasion resistance Liquid viscosity

来源：评论

学校读者我要写书评

暂无评论

Optimizing manufacturing plant layouts using AI and heuristic algorithms

引用

INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM 2025年 1-11页

作者： Raju, G. S. Vizhian, S. Paul Kumar, M. Vijay Sufyan, Md Saeb Madhusudan, M. Gururaja, M. N. Prasad, C. Durga Mohan, Dhanesh G. Hanumanthappa, Harish Bangalore Univ Dept Mech Engn UVCE Bengaluru 560001 Karnataka India JSS Sci & Technol Univ Dept Mech Engn SJCE Mysore 570006 Karnataka India Govt Engn Coll Dept Civil Engn Nawada 805111 India Dayananda Sagar Coll Engn Dept Mech Engn Bengaluru 560111 Karnataka India Dayananda Sagar Acad Technol & Management Dept Mech Engn Kanakapura Rd Bengaluru 560082 Karnataka India RV Inst Technol & Management Dept Mech Engn Bengaluru 560076 Karnataka India Univ Sunderland Fac Technol Sch Engn Sunderland England Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura Punjab India RV Univ Sch Comp Sci & Engn Bengaluru Karnataka India

The study outlines an artificial intelligence-based methodology for defining manufacturing plant layout in the context of mass customisation, where a significant amount of part variability needs to be controlled. A variety of actions are suggested, with an emphasis on data transformations that make it possible to retrieve pertinent information for the plant layout design of the manufacturing facility. The article also uses optimization algorithms and simulation techniques for designing plant layouts and how those methods have changed throughout time as a result of the development of computer systems and artificial intelligence methods. A variety of layout metrics, including the number of facilities and temporary storage space, are gathered to determine the plan's efficiency. With the revised layout, the suggested solution boosts layout efficiency while reducing operator mobility and temporary storage space. Starting with the production routing of each product, the proposed algorithms would enable manufacturing companies to automate plant layout design in the context of mass customization using artificial intelligence techniques. It also emphasizes how important it is to review the layout design procedure whenever new products are introduced.

关键词： Manufacturing Plant layout optimization algorithm Artificial intelligence

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：