检索结果-内蒙古大学图书馆

International Journal of Advanced nuclear Reactor Design and technology 2025年第2期7卷 156-165页

作者： Han Yang Li Li Quanwei Liu Yingjie Ma Jianbin Zhou Liudong Hou Yongquan Qin Yantao Hu Jing Ma China Nuclear Power Engineering Co. Ltd Beijing 100840 China CNNC Engineering Research Center for Fuel Reprocessing Beijing 100840 China The College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu 610059 China

X-ray absorption spectroscopy stands as a non-destructive assay technique commonly employed in nuclear fuel reprocessing plants to analyze the concentration of elements such as uranium, plutonium,*** processing of absorption spectroscopy directly affects the measurement outcomes. In this study, an experimental setup for K -edge absorption spectrum has been established. Acknowledging the constraints of conventional K -edge absorption spectrum analysis, two improved methods are proposed, including the optimized method, and the cumulative counting method. A mixed sample of thorium and uranium was utilized to conduct an experimental study. Upon analyzing and experimental results, it was determined that the cumulative counting method offers better accuracy and simplicity in processing the absorption spectrum. During the spectrum processing, adopting a wide region of interest enhances the precision of results and reduce relative deviations, while omitting background subtraction aids in simplifying the process. The cumulative counting method can also be extended to the L -edge absorption spectrum.

关键词： X-ray Absorption spectroscopy K -edge Cumulative counting method

来源：评论

学校读者我要写书评

暂无评论

Target tracking method of Siamese networks based on the broad learning system

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 1043-1057页

作者： Dan Zhang C.L.Philip Chen Tieshan Li Yi Zuo Nguyen Quang Duy Navigation College Dalian Maritime UniversityDalianChina Innovation and Entrepreneurship Education College Dalian Minzu UniversityDalianChina Computer Science and Engineering College South China University of TechnologyGuangzhouChina Department of Computer and Information Science Faculty of Science and TechnologyUniversity of MacaoMacaoChina School of Automation Engineering University of Electronic Science and Technology of ChinaChengduChina Faculty of Navigation Vietnam Maritime UniversityHaiphongVietnam

Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other ***,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time *** based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time ***,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during ***,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time *** broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning *** at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is *** method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐*** broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the *** results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

关键词： broad learning system siamese network target tracking

来源：评论

学校读者我要写书评

暂无评论

Markov Latent Frequency Transition Analysis for Robust Bearing Diagnosis in Transient Noise Scenarios 15

Markov Latent Frequency Transition Analysis for Robust Beari...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Ma, Junxiao Wu, Yuhao Chen, Peng Zhou, Chengning He, Changbo Wei, Qingsheng College of Engineering Shantou University Guangdong Shantou China Key Laboratory of Intelligent Manufacturing Technology Ministry of Education of China Guangdong Shantou China Nuclear Power Institute of China Chengdu China College of Electrical Engineering and Automation Anhui University Hefei China

ISBN: (纸本)9798350354010

In real-world applications, the diagnostic accuracy of rolling bearings is often compromised by environmental factors such as variable rotational speeds, transient noises, and unexpected mechanical impacts. These factors can obscure damage symptoms, making precise detection of bearing failures challenging. Conventional diagnostic methods struggle to handle these complexities and often miss failure features hidden in multifaceted random transient noise. To address these issues, this research introduces the Markov Latent Frequency Transition Peak Rate (MLFTPR) methodology. MLFTPR focuses on accurately monitoring temporal state transitions and identifying anomalous signals, aiming to mitigate transient noise at the source and improve resistance to external disturbances. This enhances precision and reliability in demodulation band selection. Additionally, an amplitude interference-reduction feature is integrated to recognize and suppress transient noise effectively. Experimental results validate the efficacy of MLFTPR, demonstrating its capability to accurately diagnose bearing defects even amidst transient disturbances. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Research on Ensemble Convolutional Neural Networks in Digital Image Course experiments 4

Research on Ensemble Convolutional Neural Networks in Digita...

引用

2022 4th International Symposium on Robotics and Intelligent Manufacturing technology, ISRIMT 2022

作者： Zhang, Jiawei Liu, Huan Ge, Junwei Mei, Hao Yan, Xiaojun Cao, Yifan Luo, Yaoyao School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Sichuan AnxinKechuang Technology Co. Ltd Chengdu China School of Mechanical and Electrical Engineering Chengdu University of Technology Chengdu China

In various digital image processing courses, the accuracy of traditional expression recognition algorithms cannot meet practical needs. This paper studies facial expression recognition using a convolutional neural network and ensemble learning. We develop three subnetwork models based on the classical convolutional neural network, using the BN layer to increase the network convergence rate and regularization is used to prevent subnetwork overfitting. The optimization idea used in this paper is applicable to most experimental improvements and raises the standard of the experiments. © Published under licence by IOP Publishing Ltd.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Landslide Recognition in High Resolution Remote Sensing Images Based on Semantic Segmentation 10

Landslide Recognition in High Resolution Remote Sensing Imag...

引用

10th International Conference on Intelligent Computing and Wireless Optical Communications, ICWOC 2022

作者： Zhang, Qin Zhang, Jie Sun, Wencheng Qin, ZhangJian Chengdu University of Technology Mechanical and Electrical Engineering Chengdu China State Grid Corporation of China Southwest Division Chengdu China Chengdu University of Technology Nuclear Technology and Automation Engineering Chengdu China

ISBN: (纸本)9781665471534

In order to ensure the stable operation of high voltage transmission network, DeepLab V3+_SDF is proposed based on DeepLab V3+ for rapid and intelligent landslide detection from high resolution remote sensing images. Firstly, the backbone network is replaced by ResNet with squeeze-and-excitation (SE) attention mechanism to enhance the extraction of useful features. Secondly, astrous spatial pyramid pooling (ASPP) is reconstructed based on dense connection to expand the receptive field. More low-level features are then added to the decoder with feature pyramid networks plus (FPNP) to enhance detail recovery. Finally, a mixed loss function is proposed based on the pixel distribution to solve the sample imbalance problem. DeepLabV3+ _SDF is trained with self-made landslide remote sensing dataset. The experimental results show that the mean pixel accuracy(mPA) and mean intersection over union (mIoU) of DeepLab V3+_SDF on the landslide dataset reach 95.38 % and 85.27 %, which are 2.90 % and 7.76 % higher than those of DeepLabV3+. Finally, the trained DeepLab V3+_SDF is applied to Sichuan-Chongqing region in China, and the comparison results with manual interpretation show that the algorithm can be used for rapid identification of landslides in large-scale mountainous areas. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Preliminary Development and Verification of a Openfoam-Based Multi-Physics Coupling Safety Analysis Code for Lead-Based Reactor

SSRN

引用

SSRN 2023年

作者： Ou, Wenlan Gong, Zhengyu Gu, Zhi Xing Pan, Qiwen Zhang, Ling Dai, Jianing College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China

To overcome the complex multi-dimensional thermal hydraulic problems involved in LFR, CFD-based multi-physics coupling strategy has been treated as an effective solution. As a free open-source CFD code, OpenFOAM is undoubtedly a great platform to perform the multi-physics coupling simulations based on complicated coupling algorithms. By employing an explicit coupling framework, a new program for fluid-solid coupling solution of LFR fuel pin channel is developed based on OpenFOAM. The self-developed point kinetics and fuel pin heat conduction models are coupled to the modified icoFoam of OpenFOAM. Verifications are conducted by transient (BT, BOP and TOP) simulations of flow and heat transfer coupling behaviors in a single fuel pin channel of LFR, comparing with benchmarks-verified HC-PK-CFD code based on ANSYS Fluent. The results agree well with the ones provided by HC-PK-CFD code in ANSYS Fluent, demonstrating its ability of conducting coupled simulations involved in safety analysis of LFR with sufficient accuracy. © 2023, The Authors. All rights reserved.

关键词： Simulation platform

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

IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)

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

ISBN: (数字)9798350352290

ISBN: (纸本)9798350352306

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.

关键词： Accuracy Attention mechanisms Clouds Wind speed Predictive models Feature extraction Numerical models Convolutional neural networks Data mining Forecasting

来源：评论

学校读者我要写书评

暂无评论

Motion Simulation of Multi-type Surface Adsorption Robot for Power Energy Industry 8

Motion Simulation of Multi-type Surface Adsorption Robot for...

引用

8th International Conference on automation, Control and Robotics engineering, CACRE 2023

作者： Ma, Congjun Zhang, Hongxiang Li, Xiaolong Dian, Songyi Sichuan University College of Electrical Engineering Chengdu China Chengdu Haiguang Nuclear Power Technology Service Co. Itd Chengdu China

ISBN: (纸本)9798350302776

In the field of power energy industry, there exists a significant demand for equipment operation and maintenance. Amongst the various operation and maintenance scenarios, surface operation and maintenance is particularly ubiquitous. To overcome the challenge of surface operation and maintenance of key equipment in the power industry, an adsorption hexapod robot has been introduced in this study. The robot is capable of adapting to diverse surfaces and can achieve adsorption motion under specific configurations. In order to validate the robot's ability to adsorb and traverse across multiple surface types, a full-real simulation platform has been developed in this research. The simulation verification has been conducted for three typical curved scenes, namely gas insulated switchgear in power grid with cylindrical surface, steam generator in nuclear power with spherical surface and wind blade in wind power with edge surface. The simulation results demonstrate that the designed robot can adeptly perform adsorption motion on various typical surfaces. These results can be utilized as a reference for further work to build a robot prototype and conduct adsorption experiments. © 2023 IEEE.

关键词： Adsorption

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Optimal Control for Human in the Loop Multi-Agent Systems Under FDI Attacks 6

Event-Triggered Optimal Control for Human in the Loop Multi-...

引用

6th International Conference on Electronic engineering and Informatics, EEI 2024

作者： Xu, Yuanyuan Liang, Hongjing Li, Tieshan Long, Yue Liu, Qidong Yang, Ximing Huang, Zongsheng School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China College of Engineering China University of Petroleum-Beijing at Karamay Karamay834000 China

ISBN: (纸本)9798350353594

This paper investigates event-triggered optimal control for human-in-the-loop (HiTL) multi-agent systems (MASs) facing false data injection (FDI) attacks. An approach is introduced to enhance the security of sensor measurements against sparse attacks by employing a secure preselector, while also devising a state observer to estimate the system state, which is not directly measurable. Introducing an event-driven mechanism for solution transformation involves establishing a Hamilton-Jacobi-Bellman (HJB) equation, while employing a critic network along-side an experience replay technique to approximate it. Lyapunov stability theory is employed to derive an event-triggered condition ensuring the boundedness of consensus error and critic network weight error. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation Algorithm of Landslide Based on Remote Sensing Image and DEM 5

Semantic Segmentation Algorithm of Landslide Based on Remote...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Zhou, Yongxiu Wang, Honghui Yang, Ronghao Xie, Dalan Liu, Jie Chengdu University of Technology Key Laboratory of Earth Exploration and Information Technology of Ministry of Education Chengdu610059 China Chengdu University of Technology College of Computer Science and Cyber Security Chengdu610059 China Chengdu University of Technology College of Earth Sciences Chengdu610059 China Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu610059 China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

The fast landslide segmentation algorithm based on deep learning technology for remote sensing images can play an important role in disaster analysis and risk assessment. At this stage, deep learning-based landslide segmentation algorithms mainly use RGB images as training data for the models, and a few studies have started to add digital elevation models (DEMs) as training data. In order to study the effect of DEM as training data on the accuracy improvement of landslide segmentation algorithm, we use RGB remote sensing images and DEM as training data, use U-Net combined with pspnet network structure, add FCN network structure in the training process, and analyze the test results using various evaluation metrics. Finally, we conclude that compared with the model using only RGB images as input data, adding DEM as input data can effectively improve the overall accuracy of the landslide segmentation model and reduce the false accept rate of the model in complex terrain. © 2022 IEEE.

关键词： Semantics

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：