检索结果-内蒙古大学图书馆

2nd Asia Power and Electrical technology Conference, APET 2023

作者： Long, Chen Tian-Xiang, Chen Long-Shan, Yang Meng, Wang Chao-Xu, Zeng Sen, Yang College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (纸本)9798350359428

In order to study whether the vegetation touching single-phase conductor faults of low voltage distribution lines can lead to hill fires, a 400V low voltage bare conductor simulated tree line fault experimental platform was built. The possibility of vegetation ignition caused by vegetation contact fault in low voltage distribution lines is studied by analyzing the leakage current flowing through vegetation., the temperature rise of vegetation and the traces of carbonization on the surface. The results show that the bamboo with high water content touches the single-phase conductor fault temperature rise obviously., there are obvious charring traces near the fault point in the test., and the maximum temperature reaches 95.3 °C, the maximum leakage current is 180mA., and there is no discharge phenomenon in the test. High water content will limit the maximum temperature near the fault point to be less than the boiling point of water., and the temperature rise will accelerate the loss of water., leading to a decrease in leakage current., and eventually the temperature drop at the fault point gradually stabilizes., indicating that a single-phase conductor fault on a low voltage distribution line with vegetation touching it will not cause a fire. The results of the study are of great significance for the prevention of hill fires on low voltage distribution lines through forested areas. © 2023 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Quantitative algorithm for airborne gamma spectrum of large sample based on improved shuffled frog leaping-particle swarm optimization convolutional neural network

引用

nuclear Science and Techniques 2023年第7期34卷 242-252页

作者： Fei Li Xiao-Fei Huang Yue-Lu Chen Bing-Hai Li Tang Wang Feng Cheng Guo-Qiang Zeng Mu-Hao Zhang College of Nuclear Technology and Automation Engineering Chengdu University of TechnologyChengdu 610000China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu 610000China Airborne Survey and Remote Sensing Center of Nuclear Industry Shijiazhuang 050000China Hebei Key Laboratory of Airborne Detection and Remote Sensing Technology Shijiazhuang 050000China

In airborne gamma ray spectrum processing,different analysis methods,technical requirements,analysis models,and calculation methods need to be *** meet the engineering practice requirements of airborne gamma-ray measurements and improve computational efficiency,an improved shuffled frog leaping algorithm-particle swarm optimization convolutional neural network(SFLA-PSO CNN)for large-sample quantitative analysis of airborne gamma-ray spectra is proposed *** method was used to train the weight of the neural network,optimize the structure of the network,delete redundant connections,and enable the neural network to acquire the capability of quantitative spectrum *** full-spectrum data processing,this method can perform the functions of energy spectrum peak searching and peak area *** network training,the mean SNR and RMSE of the spectral lines were 31.27 and 2.75,respectively,satisfying the demand for noise *** test the processing ability of the algorithm in large samples of airborne gamma spectra,this study considered the measured data from the Saihangaobi survey area as an example to conduct data spectral *** results show that calculation of the single-peak area takes only 0.13~0.15 ms,and the average relative errors of the peak area in the U,Th,and K spectra are 3.11,9.50,and 6.18%,indicating the high processing efficiency and accuracy of this *** performance of the model can be further improved by optimizing related parameters,but it can already meet the requirements of practical engineering *** study provides a new idea for the full-spectrum processing of airborne gamma rays.

关键词： Large sample Airborne gamma spectrum(AGS) Shuffled frog leaping algorithm(SFLA) Particle swarm optimization(PSO) Convolutional neural network(CNN)

来源：评论

学校读者我要写书评

暂无评论

The Influence of Radiation Distance on Microwave Coupling Efficiency in Microwave-assisted Rock Breakage

The Influence of Radiation Distance on Microwave Coupling Ef...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Zhao, Xiaoyun Chengdu University of Technology School of Nuclear Technology and Automation Engineering Chengdu610059 China

ISBN: (纸本)9798350375909

High power microwave early irradiation has a great potential in assisting excavators in breaking hard and abrasive rocks, radiation efficiency is a very important issue. The paper studied the radiation of standard rectangular waveguides on rocks at different working distances, obtained the minimum S11 parameter through CST simulation, and determined the corresponding optimal radiation position, at a working distance of 0.31λ, the S11 is minimum, which is the optimal position of the sample relative to the microwave antenna. Using this method, we can quickly and accurately obtain the efficiency of microwave coupling into rocks, can guide practical engineering applications. © 2024 IEEE.

关键词： Microwave irradiation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sola Forecasting Accuracy: A Fusion of Sky Images and Meteorological Data with Channel-Wise Attention

Enhancing Sola Forecasting Accuracy: A Fusion of Sky Images ...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Jonathan, Anto Leoba Cai, Dongsheng Bamisile, Olusola Nkou, Joseph Junior Nkou Agobah, Harriet Huang, Qi School of Nuclear and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (纸本)9798350352290

Accurate solar forecasting is crucial for efficient integration of solar power into the electricity grid. While sky image-based methods are introduced to overcome the low capability of numerical data to capture some features, enhancing forecasting accuracy remains an active area of research. In this paper we paper combine numerical data and sky images to improve the accuracy of solar forecasting. A new framework is proposed based on a convolutional neural network model with a channel-wise attention mechanism for 10 minutes ahead of solar forecasting using sky images and meteorological data. The model utilizes a series of convolutional blocks to extract spatial features from input sky images, followed by channel-wise attention layers to focus on the most salient features. Numerical data such as historical irradiance value, time, Tower Dry Bulb Temperature (TDBT), Total Cloud Cover (TCC), and Average Wind Speed (AWGS) are also incorporated through a separate extraction branch. The extracted sky image features and numerical representations are fused and fed into the model to forecast the global horizontal irradiance (GHI). An evaluation of real-world datasets demonstrates the effectiveness of the proposed method. The channel-wise attention mechanism helps improve model interpretability by highlighting influential image regions. Compared to benchmark persistence and CNN models, the proposed approach achieves 8% lower error in 10 minutes ahead of forecasts. An error analysis indicates its superior performance under abrupt cloud conditions that are difficult to predict. © 2024 IEEE.

关键词： Solar irradiance

来源：评论

学校读者我要写书评

暂无评论

Verification of Solver for Coupled Simulation of Fluid and Fuel Pin in LFR Based on Openfoam 23rd

Verification of Solver for Coupled Simulation of Fluid and F...

引用

23rd Pacific Basin nuclear Conference, PBNC 2022

作者： Ou, Wenlan Gong, Zhengyu Pan, Qiwen Zhang, Ling Dai, Jianing Gu, Zhixing College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9789819910229

The Computational Fluid Dynamics (CFD)-based thermal-hydraulics and safety analyses of Lead-based Fast Reactor (LFR) have attracted great attentions in recent years. Commercial CFD tools have been widely used in the 3D simulations of pool-type reactors owing to their powerful abilities in geometric modeling and meshing. Compared with the commercial CFD tools, OpenFOAM is a free open-source CFD code, which is more flexible to perform multi-physics coupling activities. In this paper, in order to develop a solver for simulating the coupled flow and heat transfer behaviors of fluid (coolant) and fuel pin in LFR, the fuel pin Heat Conduction (HC) model was coupled to the modified icoFoam solver of OpenFOAM. Verifications were conducted by the steady-state coupled simulation of fluid and fuel pin heat transfer behaviors, comparing with the MPC-LBE code which has been verified by the benchmarks for LFR fuel pin channel. The results simulated by the coupled solver proposed in this paper agreed well with the ones provided by the MPC-LBE code. This study lays a foundation for the further development of transient safety analysis code for LFR in our future work. © 2023, The Author(s).

关键词： Fast reactors

来源：评论

学校读者我要写书评

暂无评论

Development and Verification of Solver for Natural Circulation Flow and Heat Transfer Simulation Base on Openfoam 23rd

Development and Verification of Solver for Natural Circulati...

引用

23rd Pacific Basin nuclear Conference, PBNC 2022

作者： Gong, Zhengyu Liang, Miao Ou, Wenlan Pan, Qiwen Zhang, Ling Gu, Zhixing College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9789811987793

For the advanced liquid metal cooled pool-type reactors, natural circulation of coolant is essentially important to ensure reactor safety under either normal or accident conditions, thus the thermal-hydraulic analysis of natural circulation behaviors is significant. Compared with the commercial Computational Fluid Dynamics (CFD) software, such ANSYS Fluent, OpenFOAM is one of the most common open-source CFD codes, which has more free programming environment and advantages of convenient function development. In this study, a new solver GTFoam for the natural circulation simulation was developed by adding energy conservative equation model and natural circulation model into the original icoFoam solver of OpenFOAM. For the above GTFoam solver, code verification was carried out by using the square cavity flow driven by regional heat source, and results were compared with the ones calculated by ANSYS Fluent. It was demonstrated that the results simulated by GTFoam solver agreed well with the ones calculated by ANSYS Fluent. This study can be used in the further development of transient safety analysis solver based on OpenFOAM for LFR in our future work. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Study on the 3-D Natural Circulation Characteristics of LFR Under Steady State by Using Ansys Fluent 23rd

Study on the 3-D Natural Circulation Characteristics of LFR ...

引用

23rd Pacific Basin nuclear Conference, PBNC 2022

作者： Dai, Jianing Yan, Yulin Li, Erhao Gong, Zhengyu Zhang, Ling Gu, Zhixing College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9789819910229

As one of the Generation IV reactors, Lead-based Fast Reactor (LFR) has been considered to be great promising owing to its advantages in nuclear safety, sustainable development of nuclear energy and nuclear waste disposal. Owing to the excellent thermal expansion characteristics of Lead-based coolant materials, the primary cooling system of LFR can operate in natural circulation driven mode. The CFD (Computational Fluid Dynamics)-based thermal-hydraulics and safety analyses of nuclear reactors, especially liquid metal pool-type reactors have attracted great attentions in recent years. In this paper, the entire 3-D geometric model of a 10 MWth natural circulation driven LFR primary cooling system was established and simulated by ANSYS Fluent, in which the mesh was partitioned by utilizing structured meshing technology, and the porous medium model was utilized to fine the reactor core simulation. The results showed that the above LFR can operate safely in natural circulation mode, and has excellent natural circulation characteristics for the primary cooling system. © 2023, The Author(s).

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Algorithm of Gradient Boosted Decision Tree and Multiple Linear Regression and Its Application on Decesion Prediction 3

Hybrid Algorithm of Gradient Boosted Decision Tree and Multi...

引用

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

作者： Wen, Yingzi He, Xin Lv, Dawei Li, Fei College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China College of Management Science Chengdu University of Technology Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9798350333862

Gradient boosted decision tree is a supervised learning algorithm model constructed by improving tree structure, replacing residual with gradient and using the concept of entropy in informatics. GBDT produces classification bias due to the imbalance of the sample. Therefore, we propose a way to accelerate the output quality of a decision tree by combining linear regression and GBDT and preprocessing sample data through linear regression before training. In the experiment, the new algorithm is applied to the nonlinear classification decision. It is found that the regression coefficient of the apportion of independent directors is 0.034, the regression coefficient is 0.712, the regression coefficient for table size is 0.197, the regression coefficient for the size of the board of directors is -0.197, and the regression coefficient for the share of institutional investors is -0.018. The regression coefficient for the institutional investor share is -0.018. It is found that this algorithm effectively improves classification accuracy and has good practical value. © 2023 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

SIMULATION AND EXPERIMENTAL STUDY OF LOW-ENERGY FLUORESCENCE X-RAYS 10

SIMULATION AND EXPERIMENTAL STUDY OF LOW-ENERGY FLUORESCENCE...

引用

10th International Symposium on Test automation and Instrumentation, ISTAI 2024

作者： Dai, Derong Guo, Siming Ding, Pingping Wang, Zhen Li, Zhiwei Li, Wen College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China National Institute of Metrology Beijing China

ISBN: (纸本)9781837242672

Fluorescence X-rays have the advantages of good monochromaticity, high flux and stable dose rate. Carried out simulation and experimental studies of fluorescence X-rays in the (4.5 ~ 25.3) KeV energy range. The energy spectra produced by different radiators were simulated using Monte Carlo simulation software to obtain the theoretical spectra. The Kp and L fluorescence X-rays were also filtered in the simulation by choosing different materials of secondary filter materials for each radiator. Measurement experiments were carried out using a HPGe detector to obtain experimental spectra. The simulation results match the experimental results, verifying the correctness of the experimental measurements. The fluorescence yield and Ka fluorescence purity of the radiator were calculated, in which the fluorescence yield of Zn reached percent 95.2 and the purity of Ka fluorescence of Cd reached percent 82.8. The factors affecting the fluorescence yield experiment are the secondary filter corresponding to the radiator, which can be subsequently optimized in the selection of secondary filter. © The Institution of engineering & technology 2024.

关键词： Radiators

来源：评论

学校读者我要写书评

暂无评论

Dual-head alternating attention-based adaptive convolutional framework for improving low-resource and imbalanced text classification

引用

Neural Computing and Applications 2025年 1-21页

作者： Agbesi, Victor Kwaku Chen, Wenyu Hossin, Md Altab Ukwuoma, Chiagoziem C. School of Computer Science and Engineering University of Electronic Science and Technology of China No. 2006 Xiyuan Ave West Hi-Tech Zone Sichuan Chengdu China School of Innovation and Entrepreneurship Chengdu University No. 2025 Chengluo Avenue 610106 Sichuan Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Low-resource imbalance texts pose significant challenges due to class imbalance, adversely affecting the performance of deep learning approaches. To address this issue, we propose a dual-head alternating attention-based adaptive convolutional framework with label embedding (AltXLM-AdaCLE), a novel framework designed for imbalanced text classification in low-resourced datasets. Our framework features a new alternating attention model, which combines a dual-head attention mechanism with a bidirectional long short-term memory network, facilitating dynamic filter generation that adapts to the input data’s characteristics and enhances the capture of relevant features and long-range dependencies. A key innovation in this study is the dual-head attention mechanism, which utilizes an alternating reading sequence to extract information from multiple document segments, thereby minimizing information loss and improving the understanding of complex relationships. Furthermore, we introduce a method for embedding class labels in a shared vector space with the text, allowing the model to leverage label information throughout the classification process, which is particularly beneficial for imbalanced datasets. Our framework also incorporates an adaptive convolutional layer that processes text features and label embeddings, generating more representative features of the underlying data distribution and improving classification performance. Experimental results on six low-resourced imbalance text datasets validate the effectiveness of AltXLM-AdaCLE with an average AUC gain of 26.42%, demonstrating its superiority over existing methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Vector spaces

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：