检索结果-内蒙古大学图书馆

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Bian, Zhenxue Deng, Yongkang Lu, Bingshuo Liu, Chang Hu, Chuanhao College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

ISBN: (纸本)9781510681880

Aiming at the problems such as few probes, limited detection area and lack of nuclear radiation detection module in existing aquaculture monitoring devices, a new type of aquaculture in Situ monitoring device is designed. Based on the innovation of six-probe retractable mechanical structure, the cerium bromide scintillator detector is added compared with the traditional device, and the aquaculture monitoring sensor with six parameters is integrated to realize the three-dimensional monitoring of multi-parameter water quality information in the aquaculture area, ensuring the safety and reliability of the water quality in the aquaculture area. © 2024 SPIE.

关键词： Probes

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

Research on Application of Embedded AI in Fall Detection 5

Research on Application of Embedded AI in Fall Detection

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Liu, Yan Zhu, Xing College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China College of Computers and Cyber Security Chengdu University of Technology Chengdu China

ISBN: (纸本)9798350385557

The traditional elderly fall detection system has some shortcomings, such as high false alarm rate and large delay, which limits its reliability and practicability in practical application. In order to timely and accurately notify the guardian of the old man's fall information, a low-power fall detection system based on em-bedded artificial intelligence is proposed. The system is based on low-power ARM processor, coupled with low-power and small-volume MEMS acceleration sensor. By designing the overall structure of the system, the peripheral circuits of ARM processor and MEMS acceleration sensor, and writing embedded programs and embedded artificial intelligence algorithms, the core functions such as data acquisition, fall identification and fall state transmission are realized. In the experiment, an algorithm model of FDNet (Fall Detection Network) is proposed, and a lot of tests and evaluations are carried out. The experimental results show that the system can achieve 98% accuracy on embedded devices. In addition, the system also shows excellent environmental adaptability, low power consumption and small size, which makes it suitable for fall detection and early warning in various occasions. The successful application of the system is expected to provide effective protection for the health and safety of the elderly. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Research on the Time of Fire Initiation Caused by Tree Line Faults Under 35kV Transmission Lines 14

Research on the Time of Fire Initiation Caused by Tree Line ...

引用

14th International Conference on Power and Energy Systems, ICPES 2024

作者： Yang, Haohan Chen, Tianxiang Zeng, Yi Wang, Zheng The college of Nuclear Technology and Automation Engineering Chengdu University of Technology Cheng Du China

ISBN: (纸本)9798350391329

In recent years, forest fires caused by transmission line tree line faults occur frequently, transmission line tree line faults affect the safety and reliability of power grid operation, a serious threat to the safety of natural resources and people's property. In this paper, for the 35kV transmission line tree line faults caused by hill fire, built a 35kV line tree line fault experimental platform, in the capacitance current of 248 mA and 132 mA conditions, respectively, selected bamboo, pine and cedar three typical trees as a research sample, to carry out the three kinds of trees tree line fault fire time experiments. The burning phenomena, charring channels, and infrared images of different trees were recorded and analyzed, and the corresponding laws were drawn up to summarize the longest and shortest fire starting times of different capacitance currents and different trees. The research in this paper can provide technical reference for the development of measures to prevent fire caused by tree line faults in 35kV transmission lines. © 2024 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on the Effect of Temperature on tan δ Measurement of 110 kV Voltage Transformer 14

Experimental Study on the Effect of Temperature on tan δ Me...

引用

14th International Conference on Power and Energy Systems, ICPES 2024

作者： Gu, Hong Chen, Tianxiang Cai, Lehui Jiang, Zhuofeng The college of Nuclear Technology and Automation Engineering Chengdu University of Technology Cheng Du China

ISBN: (纸本)9798350391329

Voltage transformer as a substation important equipment, assuming the role of measurement, control and protection. Equipment in the operation process is susceptible to temperature and other factors that cause insulation defects, need to carry out regular insulation preventive testing. In this paper, we take 110 kV series-type voltage transformer as the research object, and use four different wiring methods to explore the changes of tanδ value and capacitance under different ambient temperatures, insulating oil temperatures, and insulating oil moisture conditions, to verify the applicability and reasonableness of the relevant values in the Regulations, and to provide an effective basis for the series-type voltage transformer to determine the insulation faults of the equipment through the tanδ value. The results show that the tanδ value increases with the rise of temperature under different wiring methods, while the capacitance is basically unchanged;the end shielding method is the most sensitive to the moisture of insulating oil under different temperature conditions;when the insulation is normal, the conventional inverse wiring is more sensitive to the temperature change;when the insulation is faulty, the conventional positive wiring is more sensitive;to determine whether there are insulation defects of voltage transformers should be measured by the tanδ value in lower temperature as the main criterion, and the Kegulations' will be used to determine whether there are insulation defects of the series type voltage transformer through the tanδ value. Judgment of whether the voltage transformer insulation defects should be measured at lower temperatures tanδ as the main criterion, Kegulations' in the relevant tanδ value criterion should be adjusted in a timely manner. © 2024 IEEE.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Research on the Characteristics of Leakage Current Changes in Tree Line Faults of 10Kv Distribution Lines 14

Research on the Characteristics of Leakage Current Changes i...

引用

14th International Conference on Power and Energy Systems, ICPES 2024

作者： Wang, Zheng Chen, Tianxiang Yang, Haohan Zeng, Yi The college of Nuclear Technology and Automation Engineering Chengdu University of Technology Cheng Du China

ISBN: (纸本)9798350391329

There are numerous cases of forest fires caused by tree line faults in distribution lines, and it is of great significance to study the characteristic signals when tree line faults occur to prevent mountain fire accidents. In this paper, through theoretical analyses and the construction of real experimental platform, we studied the change rule of leakage current when single-phase tree line fault occurs in different trees. Through the single-phase tree line fault experiment, the relationship between leakage current and tree species, capacitive current to ground and water content when different trees touch the line is studied. The results of the study show that: the occurrence of single-phase tree line fault leakage current for the first time to reach the maximum value of time and tree species, the first time to reach the maximum value of the water content of trees and ground capacitance related. © 2024 IEEE.

关键词： Water content

来源：评论

学校读者我要写书评

暂无评论

Characterization of the Effect of Different Flame Clusters on Gap Leakage Current Under 10Kv Line 14

Characterization of the Effect of Different Flame Clusters o...

引用

14th International Conference on Power and Energy Systems, ICPES 2024

作者： Zeng, Yi Chen, Tianxiang Wang, Zhen Yang, Haohan Chengdu University of Technology The college of Nuclear Technology and Automation Engineering Cheng Du China

ISBN: (纸本)9798350391329

In recent years, wildfires in the corridors of transmission and distribution lines have occurred frequently, posing a serious threat to the stable operation of the power grid. To study the influence of flame cluster number on the leakage current characteristics of gaps in 10 kV lines, experiments were conducted on the discharge characteristics of a 12 cm wire-board gap under different vegetation flame cluster conditions. The variations in leakage current amplitude under different capacitive current conditions were analyzed, clarifying two discharge forms under flaming conditions. The results indicate that the leakage current in single and multiple cluster vegetation flame conditions is inversely correlated with capacitive current and shows a negative correlation with the ash content of vegetation. Under capacitive currents of 1A and 5A, breakdown occurs in the gap under straw flame conditions, attributed to the highest ash and burning particle content in the straw. This demonstrates that temperature is not the primary factor affecting gap breakdown under straw flame conditions, with ash content being dominant. The findings provide technical references for using electrical signals from lines to warn of wildfires beneath and analyze the causes of incidents. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Multiscale modelling and control of inductively coupled plasma etching based on recurrent neural networks

引用

International Journal of Wireless and Mobile Computing 2025年第1期28卷 34-46页

作者： Zhu, Lihong Chen, Qingchuan Nie, Junwei Liu, Kewei Department of Automation Engineering The Engineering and Technical College of Chengdu University of Technology Chengdu Sichuan Leshan China Southwestern Institute of Physics Sichuan Chengdu China Engineering Training Centre The Engineering and Technical College of Chengdu University of Technology Chengdu Sichuan Leshan China

In order to deepen the understanding of the process flow and improve the process, the plasma etching simulation is an essential means, but the calculation cost of the traditional simulation system is too high. Therefore, this study proposes a multi-scale model optimisation algorithm and model prediction and control system based on recurrent neural network. The multiscale model optimisation algorithm adopts a recursive neural network model to achieve simulation acceleration of the multi-scale model. The model prediction science system uses model reduction and recurrent neural network models to achieve full state prediction of macroscopic plasma models. The experimental results indicate that the simulation model can achieve the expected simulation results within 7.3 seconds. Moreover, the average etching depth of the model predictive control system shall not exceed 4.6%. Consequently, the proposed simulation model optimisation algorithm and model prediction and control system can effectively optimise and control the plasma etching. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A method for correcting characteristic X-ray net peak count from drifted shadow peak

引用

nuclear Science and Techniques 2023年第11期34卷 155-167页

作者： Lin Tang Xing‑Ke Ma Kai‑Bo Shi Yeng‑Chai Soh Hong‑Tao Shen College of Electronic Information and Electrical Engineering Chengdu UniversityChengdu 610106China Guangxi Key Laboratory of Nuclear Physics and Nuclear Technology Guangxi Normal UniversityGuilin 541004China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application Anhui UniversityHefei 230039China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore College of Nuclear Technology and Automation Engineering Chengdu University of TechnologyChengdu 610059China

To correct spectral peak drift and obtain more reliable net counts,this study proposes a long short-term memory(LSTM)model fused with a convolutional neural network(CNN)to accurately estimate the relevant parameters of a nuclear pulse signal by learning of samples.A predefined mathematical model was used to train the CNN-LSTM model and generate a dataset composed of distorted pulse *** trained model was validated using simulated *** relative errors in the amplitude estimation of pulse sequences with different degrees of distortion were obtained using triangular shaping,CNN-LSTM,and LSTM *** a result,for severely distorted pulses,the relative error of the CNN-LSTM model in estimating the pulse parameters was reduced by 14.35%compared with that of the triangular shaping *** slightly distorted pulses,the relative error of the CNN-LSTM model was reduced by 0.33%compared with that of the triangular shaping *** model was then evaluated considering two performance indicators,the correction ratio and the efficiency ratio,which represent the proportion of the increase in peak area of the two characteristic peak regions of interest(ROIs)to the peak area of the corrected characteristic peak ROI and the proportion of the increase in peak area of the two characteristic peak ROIs to the peak areas of the two shadow peak ROI,*** measurement results of the iron ore samples indicate that approximately 86.27%of the decreased peak area of the shadow peak ROI was corrected to the characteristic peak ROI,and the proportion of the corrected peak area to the peak area of the characteristic peak ROI was approximately 1.72%.The proposed CNN-LSTM model can be applied to X-ray energy spectrum correction,which is of great significance for X-ray spectroscopy and elemental content analyses.

关键词： Peak correction Triangular shaping Deep learning Long short-term memory Convolutional neural network X-ray fluorescence spectroscopy Silicon drift detector

来源：评论

学校读者我要写书评

暂无评论

Experimental Study of Flame Impedance Characteristics under 35 kV Line 2

Experimental Study of Flame Impedance Characteristics under ...

引用

2nd Asia Power and Electrical technology Conference, APET 2023

作者： Meng, Wang Tianxiang, Chen Chaoxu, Zeng Sen, Yang Longshan, Yang Long, Chen College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (纸本)9798350359428

Hill fire hazards on transmission and distribution lines due to various factors affect the safe operation of the lines. The current study does not consider the effect of ground capacitance current on fire impedance characteristics under the line. This paper takes 35 kV line under the mountain fire flame impedance characteristics as the test object, build different to ground capacitance of the mountain fire test platform, put forward the mountain fire ground fault theoretical model, through simulated line under the mountain fire test on the flame completely bridged gap order eucalyptus, shrubs and straw flame impedance characteristics of curve fitting, verify the vegetation mountain fire triggered by the line single-phase grounding is a high resistance ground, research and analysis of the vegetation flame impedance characteristics of the impact mechanism. Experimental research shows that the occurrence of mountain fire fault line fault degree and ground capacitance current is positively correlated;flame temperature is one of the main factors affecting flame impedance, flame impedance and flame temperature does not strictly show a negative correlation;different vegetation types triggered by mountain fire flame impedance characteristics vary greatly, arc discharge will seriously weaken the vegetation flame insulation characteristics, flame completely bridged gap stage before and mid-term flame impedance of the main influencing factors are flame temperature and flame height, flame completely bridged gap stage late flame impedance of the main influencing factors into the ash content of vegetation. The study of vegetation flame impedance characteristics can provide technical reference for transmission and distribution lines to prevent line failures caused by hill fires. © 2023 IEEE.

关键词： Fires

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：