检索结果-内蒙古大学图书馆

Performance investigation and power prediction of a trifunctional heat pump system

APPLIED THERMAL ENGINEERING 2025年 266卷

作者： Han, Youhua Zhang, Jili Ma, Liangdong Lu, Shixiang Lv, Hui Gong, Jian Nanchang Hangkong Univ Sch Civil Engn & Transportat Nanchang 330063 Jiangxi Peoples R China Dalian Univ Technol Dept Civil Engn Dalian 116024 Liaoning Peoples R China Zhongyuan Univ Technol Sch Energy & Environm Zhengzhou 450007 Peoples R China

In this work, a trifunctional direct-expansion photovoltaic thermal heat pump system was constructed to provide domestic hot water, photovoltaic power, and chilled water. Experiments and power prediction models of the trifunctional direct-expansion photovoltaic thermal heat pump system were conducted. First, the photovoltaic, heating, and cooling performances were investigated to evaluate the comprehensive performance of the system with a vapor injection cycle. The experimental results revealed that the average electrical power and photoelectric conversion efficiency of the photovoltaic thermal array were 1.01 kW and 14.71 %, respectively. The average heating power, coefficient of performance, equivalent coefficient of performance, cooling power, and energy efficiency ratio of the system were 7.46 kW, 3.64, 6.87, 4.07 kW, and 1.94, respectively. The electrical and heating performance of the system was sensitive to solar irradiation, and the cooling performance was sensitive to the ambient temperature and wind speed. Afterwards, based on the experimental data, a back- propagation neural network model combined with particle swarm optimization, a genetic algorithm, and a time correlation series were proposed to forecast the tri-generation of the direct-expansion photovoltaic thermal heat pump system. The prediction results show that the proposed neural network prediction model has high prediction accuracy and robustness. The normalized root mean square error and mean absolute percentage error of the model were 2.00 % and 2.23 %, respectively, for electrical power prediction;1.03 % and 1.28 %, respectively, for heating power prediction;and 3.34 % and 4.29 %, respectively, for cooling power prediction.

关键词： Photovoltaic thermal heat pump system Tri-generation performance Experimental study Artificial neural network optimization algorithm Prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Grouping and Routing with Cooperative Tasks

引用

JOURNAL OF AEROSPACE INFORMATION SYSTEMS 2025年第3期22卷 163-176页

作者： Choi, Euihyeon Ahn, Jaemyung Korea Adv Inst Sci & Technol KAIST Dept Aerosp Engn 291 Daehak Ro Daejeon 34141 South Korea

This paper introduces a grouping and routing problem of multiple agents for cooperative missions. The introduced problem, referred to as the Vehicle Grouping and Routing Problem with Profits, aims to maximize the total reward obtained by conducting a multi-agent mission (e.g., cooperative reconnaissance) while reducing its makespan by appropriately grouping the agents and determining their routes under operational constraints (e.g., fuel, endurance). A mixed-integer linear programming formulation and a conservative column generation-based solution procedure for the problem are proposed. A case study with homogeneous and heterogeneous agents and numerical experiments involving a cooperative reconnaissance mission with multiple unmanned aerial vehicles demonstrate the validity of the proposed formulation and solution procedure.

关键词： Unmanned Aerial Vehicle Mixed Integer Linear Programming optimization algorithm Flight Dynamics Autonomous Technology Planetary Science and Exploration Aerospace Engineering

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach for oil production prediction and water injection recommendation in well groups

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2025年 247卷

作者： Yang, Chunyi Chen, Yan Li, Yangbing Chen, Peng Southwest Petr Univ Sch Comp Sci & Software Engn Chengdu 610500 Sichuan Peoples R China Engn Res Ctr Intelligent Oil & Gas Explorat & Dev Chengdu 610500 Sichuan Peoples R China Engn Technol Co Tianjin Dept CNOOC Energy Dev Co Ltd Tianjin 300452 Peoples R China

In oilfield water injection and production, accurate oil production predictions and effective water injection schemes are crucial for improving the oilfield development efficiency and economic benefits. However, most existing data-driven methods primarily focus on single-well production prediction and lack comprehensive evaluation methods for optimizing water injection. This study proposed a new approach to address these issues. First, we proposed a well group oil production prediction (WGOPP) model that can predict the total oil production of a well group over a specified period. Second, we designed a multi-index dynamic normalized comprehensive evaluation (MDNCE) method using comprehensive evaluation coefficient I as the criterion for selecting the optimal optimization algorithm. Finally, we proposed a well group water injection recommendation (WGWIR) method based on the adaptive particle swarm optimization (APSO) algorithm, which provides quantitative injection schemes for wells within the well group. The experimental results showed that the average R 2 of the WGOPP model on the test set was greater than 0.95, and the APSO algorithm had the highest I value among the seven optimization algorithms, reaching 0.8554. After applying the WGWIR method, the average production growth rate of the well groups increased by more than 15%. The code is available at https://***/yangchunyi/Well_Group_Production_Prediction_and_Injection_optimization.

关键词： Data-driven optimization algorithm Oil production prediction Time series Water injection recommendation

来源：评论

学校读者我要写书评

暂无评论

Interpolant Method in Analyzing the Laser-Induced Plasma Spectroscopy

引用

JOURNAL OF THERMOPHYSICS AND HEAT TRANSFER 2025年第1期39卷 150-158页

作者： Wu, Jieer Zhou, Yu Luo, Wenchen Song, W. G. Han, Xiao Jiangsu Univ Sci & Technol Sch Sci Zhenjiang 212003 Jiangsu Peoples R China Cent South Univ Sch Phys Changsha 410083 Hunan Peoples R China Natl Univ Def Technol Div Basic Researches Changsha 210039 Jiangsu Peoples R China Queen Mary Univ Sch Math Sci London E1 4NS England

A numerical algorithm that effectively solves the Abel integral equation in laser-induced plasma spectroscopy is introduced. The proposed algorithm utilizes a barycentric interpolation and a collocation method with second-kind Chebyshev nodes. This approach reduces the Abel integral equation to a linear system of equations, resulting in efficient approximate solutions. Analytical studies provide an error estimation for the proposed method, which further validates its effectiveness. Through numerical experiments, we demonstrate the ease of implementation and showcase the efficiency of the proposed method. Our results indicate that the proposed algorithm can provide valuable insight for researchers in the field of laser-induced plasma spectroscopy and beyond.

关键词： Spectroscopy Numerical Simulation optimization algorithm Thermodynamic Properties Plasma Environment Derivative Free Method Numerical Interpolation Kinetic Energy Propellant Rocket Propulsion System

来源：评论

学校读者我要写书评

暂无评论

The Impact of Energy Storage System Control Parameters on Frequency Regulation Strategies

引用

IEEE ACCESS 2025年 13卷 34010-34022页

作者： Chang, Chia-Ming Chang, Hong-Chan Hung, Chun-Chun Kuo, Cheng-Chien Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei 10607 Taiwan

The large-scale development of battery energy storage systems (BESS) has enhanced grid flexibility in power systems. From the perspective of power system planners, it is essential to consider the reliability of BESS to ensure stable grid operation amid a high reliance on renewable energy. Therefore, this paper investigates BESS models and dynamic parameters used in planning future grids from the viewpoint of power planners. By measuring output response data from BESS units of three companies, dynamic responses are converted into WECC second generic model parameters using optimization algorithms, allowing their use in power system analysis software. Subsequently, using Taiwan's actual power system as the simulation background, N-1 simulations are conducted to explore the impact and benefits of BESS parameters when implementing frequency regulation strategies under two different BESS capacity specifications: 2 MW and 10 MW. In the 2 MW scenario, a comparison of the parameters from the three BESS units under frequency regulation strategies shows slight differences in the rise times of their output responses. However, for a 2 MW capacity, the frequency nadir in the power system remains consistently at 58.692 Hz. The simulation results based on the parameters defined in this research demonstrate the importance of using accurately measured and solved parameters in simulations. In the 10 MW scenario, the BESS capacity can offset the generator trip capacity, thereby revealing differences in response time between different parameters, with the frequency nadirs for the solved parameters being 59.755 Hz, 59.773 Hz, and 59.762 Hz, respectively.

关键词： Power system dynamics Frequency control Renewable energy sources Reactive power control Power control Voltage control Reactive power Power systems Integrated circuit modeling Software Battery energy storage systems (BESS) dynamic parameters frequency nadir frequency regulation optimization algorithm power conversion system (PCS) rate of change of frequency (RoCoF)

来源：评论

学校读者我要写书评

暂无评论

Innovative Study on Volatility Prediction Model for New Energy Stock Indices

引用

IEEE ACCESS 2025年 13卷 29754-29777页

作者： Li, Yanguo Long, Chao Yunnan Univ Finance & Econ Sch Econ Kunming 650221 Peoples R China Yunnan Univ Finance & Econ Finance Res Inst Kunming 650221 Peoples R China

Stock market volatility is a pivotal research area in finance, and accurately forecasting stock market volatility has long been a challenge for both academia and practice. The emergence of the new energy industry has drawn widespread attention to new energy stock indices;however, research on forecasting their volatility remains limited. To address this, this paper proposes a deep learning ensemble model based on decomposition optimization for predicting the volatility of new energy stock indices. The model comprises three components: variational mode decomposition (VMD), sparrow search algorithm (SSA), and echo state network (ESN). Initially, this paper employs VMD to decompose the original volatility series of new energy stock indices into multiple subsequences. Subsequently, SSA is utilized to optimize ESN. Finally, the constructed VMD-SSA-ESN model is employed to forecast the volatility of new energy stock indices. Through comparative analysis with other forecasting models, this paper finds that the VMD-SSA-ESN model exhibits significantly better forecasting performance across all selected new energy stock index volatility predictions. The research results indicate that the model constructed in this paper can adequately capture the characteristics of the volatility series, and both VMD and SSA effectively enhance the model's forecasting accuracy and stability. This study can provide robust support for investment decision-making and risk management in the new energy stock market.

关键词： Predictive models Indexes Forecasting Prediction algorithms Industries Stock markets Deep learning Computational modeling Analytical models Accuracy Volatility prediction deep learning variational mode decomposition optimization algorithm new energy

来源：评论

学校读者我要写书评

暂无评论

Squeeze-Inception V3 with Slime Mould algorithm-based CNN features for lung cancer detection

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 100卷

作者： Lakshmi, Geethu G. Nagaraj, P. Kalasalingam Acad Res & Educ Dept Comp Sci & Engn Srivilliputhur Tamil Nadu India

Worldwide, lung cancer is considered a highly fatal disease, affecting both women and men;it needs additional consideration while assessing several diseases. Moreover, early lung disease detection is highly significant in raising the survival rate of affected persons. There are numerous approaches to detecting lung cancer, yet it can be highly complicated to place the affected region because of the minimal visibility of the tumor section and error rates. In order to diagnose lung cancer accurately, this work created a technique, named as SqueezeInception V3 with Slime Mould algorithm (SMA)-based Convolutional Neural Network (CNN) features. Here, SMA-CNN is proposed for extracting CNN features from preprocessed images since training CNN using SMA enhances the performance. Subsequently, the features are fed to the classification for detecting lung cancer. The classification into normal/abnormal is done using the proposed Squeeze-Inception V3, which is designed by integrating the SqueezeNet and Inception v3 architectures. Finally, the analysis is performed with accuracy, sensitivity, as well as specificity rates of 95 %, 98 %, and 93 %, and reveals that the performance of proposed technique is superior to comparative models.

关键词： Lung cancer CNN features SqueezeNet Inception V3 optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Tempered fractional neural grey system model with Hermite orthogonal polynomial

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 123卷 403-414页

作者： Xu, Zhenguo Liu, Caixia Liang, Tingting Qufu Normal Univ Sch Commun Rizhao Peoples R China Jiangsu Normal Univ Coll Intelligent Educ Xuzhou Peoples R China

Recently, the study of fractional calculus has emerged as a thriving field in academic research. The rise of artificial intelligence technology has fueled researchers' extensive exploration of neural network models, leading to an abundance of practical applications. Consequently, this paper aims to propose an innovative neural grey system model that integrates neural network technology with fractional calculus theory. By utilizing the remarkable features of Hermite polynomials, we have developed a scalable model. The model parameters are determined directly through the least squares method, simplifying the computational complexity. Moreover, we present a hyperparameter determination method using simulation techniques and intelligent optimization algorithms. To assess the effectiveness of the proposed model, we conduct fitting experiments on 12 real datasets to evaluate its accuracy. Comparative analysis with classical fractional grey models and machine learning models provides substantial evidence of the superior performance of our model. The proposed model can not only improve the ability of sorting nonlinear data by polynomials, but also can greatly improve the prediction accuracy by new fractional order accumulation and difference operators.

关键词： Neural grey system model Fractional-order accumulation optimization algorithm Predictive model

来源：评论

学校读者我要写书评

暂无评论

Designing Routes in Terminal Maneuvering Area Using Hybrid Simulated Annealing

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第3期48卷 615-629页

作者： Zhou, Jun Wang, Xujie Hu, Xiaobing Civil Aviat Univ China Sino European Inst Aviat Engn Coll Safety Sci Lab Complex Syst Safety & Intelligent Decis Tianjin 300300 Peoples R China Civil Aviat Univ China Coll Safety Sci & Engn Lab Complex Syst Safety & Intelligent Decis Tianjin 300300 Peoples R China

To ensure the safe and efficient operation of flights in terminal maneuvering areas, airports establish standard arrival and departure procedures. However, designing these procedures is typically time-consuming and challenging for quantitative path length optimization. This paper presents an efficient optimization method for designing multiple arrival and departure procedures, taking into account the configuration of the airport and the nearby environment. The objective is to minimize the total length of routes while satisfying related operational constraints, such as obstacle avoidance and route separation. Each route is modeled in three dimensions, consisting of a horizontal polygonal line and a vertical cone. Considering the actual procedures' merging or diverging configuration characteristics, multiple arrival or departure routes are then modeled as a tree-like topology structure. A hybrid algorithm, integrating simulated annealing and an improved A* algorithm, is developed for automated problem-solving. Simulation results, based on tests at Sweden's Arlanda Airport, exhibit advantages over existing related research in terms of both total route length and computing time. Tests at Shanghai Pudong Airport show an 8% reduction in total path length compared to actual procedures, demonstrating the proposed method's effectiveness and potential contributions to energy savings and emissions reduction.

关键词： Annealing Terminal Manoeuvring Area Obstacle Avoidance Computing and Informatics optimization algorithm Initial Approach Fix Standard Terminal Arrival Route Air Navigation Service Provider Standard Instrument Departure Airspace Management

来源：评论

学校读者我要写书评

暂无评论

Active learning Kriging approach for creep-fatigue reliability assessment of turbine disk

引用

STRUCTURAL AND MULTIDISCIPLINARY optimization 2025年第4期68卷 1-22页

作者： Huang, Ying Zhang, Jianguo Wang, Bowei Song, Lukai Wei, Yanxu Zhang, Wei Beihang Univ Sch Reliabil & Syst Engn Beijing 100191 Peoples R China Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China Hong Kong Polytech Univ Dept Mech Engn Hong Kong 100872 Peoples R China Beihang Univ Res Inst Aero Engine Beijing 102206 Peoples R China Taiyuan Univ Technol Coll Mech & Vehicle Engn Taiyuan 030024 Peoples R China

The active metamodel is hard to represent the creep-fatigue failure, which hinders the application of efficient active metamodeling technique in creep-fatigue reliability estimation. To improve the computing efficiency and accuracy of creep-fatigue reliability assessment for turbine disk involving complex coupling of multi-layer, multi-disciplinary, and multi-uncertainty, the efficient active metamodeling technique is first pushed deep into complex creep-fatigue reliability evaluation. By integrating the synergic surrogate strategy into the active metamodeling, a multi-layer surrogate control-based synergic enhanced Kriging (MSC-SEK) approach is proposed: Firstly, to precisely describe the complicated creep-fatigue strong-coupling relationships, a synergic enhanced Kriging (SEK) is established by organically synergizing multiple Kriging models, where a multi-colony multi-mutation artificial bee colony algorithm is designed to enhance the Kriging surrogate quality;further, to obtain high-quality modeling dataset, a novel MSC learning function is developed by synthetically considering multi-surrogate entropy and reliability-sensitive information. The superiority of MSC-SEK is validated by studying the creep-fatigue reliability evaluation of a typical aeroengine turbine disk. The current efforts open up an effective way to achieve high-accuracy and high-efficiency engineering creep-fatigue reliability evaluation.

关键词： Reliability evaluation Creep-fatigue Kriging Active metamodeling Turbine disk optimization 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：