检索结果-内蒙古大学图书馆

1st International Artificial Intelligence Conference, IAIC 2023

作者： Han, Mengjie Cai, Daomeng Huo, Zhilin Shen, Zhao Tang, Lianghu Yang, Shan Wang, Cong School of Marxism University of Electronic Science and Technology of China Chengdu China University of Electronic Science and Technology of China Chengdu China School of Mechanical Engineering and Automation Beihang University Beijing China CSCC System Engineering Research Institute Beijing China The Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou China Department of Chemistry Physics and Atmospheric Sciences Jackson State University JacksonMS United States

ISBN: (纸本)9789819712762

AI-assisted personal educational career planning holds immense promise, especially with artificial neural network algorithms demonstrating significant potential in predicting graduate admission probabilities for specific schools. However, issues like graduate admission probability prediction are typical instances of small-sample learning problems. Overcoming neural network overfitting in small-sample learning is a major challenge. To address this, we first introduce a method that cyclically runs shallow neural networks to avoid the traditional use of a high number of epochs called Cyclic-LightNet(CLN). Secondly, in previous research, a validation set is typically employed to promptly detect overfitting. However, this approach further depletes the actual training data in the dataset. Consequently, we employ a dynamic training method during the training process called Dynamic Training Set Augmentation(DTSA), supplementing the training set with the validation set. This method effectively mitigates the risk of overfitting. Finally, we put CLN and DTSA into practice on publicly available small-sample datasets, achieving precise predictions of graduate admission probabilities. Experimental results demonstrate a significant improvement in prediction accuracy and effective resistance against overfitting risk. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An Angle and Position-Informed Method for Constructing Equivalent Detector Response Function in Nai and Labr3:Ce: Case Study for Geological Exploration

SSRN

引用

SSRN 2024年

作者： Ge, Yi Liang, Jingang Fan, Jilin Zhang, Qiong School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Institute of Nuclear and New Energy Technology Tsinghua University Beijing100084 China

NaI and LaBr3:Ce scintillation detectors are widely used in nuclear reactors, medical imaging, and nuclear well logging for their high gamma ray detection efficiency. The detector response function, crucial for converting incident gamma flux spectra into gamma response energy spectra or vice versa, is defined as the pulse-height distribution resulting from the interaction of single-energy gamma rays with the detector. The variability in the gamma rays' incident angles and positions introduces significant complexity to the gamma response energy spectrum, particularly in realistic detection scenarios where gamma rays are received from multiple directions. To address this challenge, a versatile, angle and position-informed method has been proposed using the Monte Carlo technique for constructing equivalent detector response functions. The method takes into account the influence of the gamma ray's incident angle and position on the response energy spectrum, and incorporates real-world detection scenarios. Initially, partial response energy spectra for a range of incident angles and positions are generated through Geant4 simulations and are used as the basis for interpolation to determine response energy spectra at arbitrary energies. The Levenberg-Marquardt algorithm then optimizes the contributions of various angles and positions by minimizing an objective function, resulting in the establishment of an equivalent detector response function. The efficacy of the method is demonstrated through simulations and experimental validations using two nuclear well logging tools employed in geological exploration as case studies: a Cs-137 chemical source gamma density tool and a pulsed neutron source element logging tool. The findings demonstrate that the mean absolute error in the gamma response energy spectra calculated using the proposed method is reduced by 2 to 5 times compared to those calculated using conventional method, providing a foundation for broader application beyon

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

A Novel All-phase Fast Fourier Transform-based Parameters Identification of High Frequency Oscillations

A Novel All-phase Fast Fourier Transform-based Parameters Id...

引用

Annual Meeting Industrial and Commercial Power Systems Technical Conference

作者： Feiyu Sun Dongsheng Cai Zhenyuan Zhang Qi Huang College of Nuclear Technology and Automation Engineering Chengdu University of Technology China Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Information Engineering Southwest University of Science and Technology Mianyang P.R. China

ISBN: (数字)9798350345308

ISBN: (纸本)9798350345315

Wind and solar energy inverter-based resources (IBRs) has been employed extensively with the aim of carbon neutrality. Power systems also make extensive use of power electronic converters, leading to interactions between IBRs and with the grid, causing high frequency oscillation (HFO) problems. It damages equipment and jeopardizes the security of the system. To identify HFO components above 100 Hz, this research use Phasor Measurement Unit (PMU) instantaneous value data to determine the HFO associated characteristics. To reduce the influence of spectral leakage and the fence effect, as well as to improve the identification accuracy of the related parameters, this paper adopts the RV self-convolutional window based Discrete Fourier Transform (DFT) and the Hanning double-window based all-phase Fast Fourier Transform (apFFT) hybrid algorithm to identify the HFO modal parameters. We take into account the identification accuracy in complex cases, such as non-nominal frequencies, with noise effects and multiple HFO modes. The simulation results show that the proposed method has high identification bandwidth, accuracy and strong flexibility.

关键词： Accuracy Wind energy Simulation Discrete Fourier transforms Noise Bandwidth Hafnium oxide

来源：评论

学校读者我要写书评

暂无评论

Defense strategy of URWPGSim2d simulation platform's survival challenge

Defense strategy of URWPGSim2d simulation platform's surviva...

引用

2021 International Conference on Artificial Intelligence and Information technology, ICAIIT 2021

作者： Peng, Haojin Wang, Luyao Zhao, Zixiang Huang, Chengyang Xu, Huikai College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Province 610059 China School of Economics Sichuan Agricultural University Sichuan Province Chengdu611130 China

In order to protect the regular fish efficiently in half-time when being the defense side in the survival challenge project, the tactics of human basketball game are introduced, and the defense strategy of urwpgsim2d simulation platform’s survival challenge is proposed, that is, the defensive strategy of the target defense based on the position of attacking fish. This paper first analyzes several problems appeared in the competition process, then, according to the rules and common problems of the competition, we formulated the survival strategies of No.2 and No.4 upper and lower double winding columns, as well as one-to-one defense of No.1 against No.3. In the process, the mathematical model of the common fish's avoiding and one-on-one protection is established. The results of a lot of experiments show that the strategy can avoid the attack of the other party effectively, improve the defense efficiency of our side, and provide reference for other counter games in the treatment of obstacles. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

STUDY ON RISK STATE IDENTIFICATION AND PREDICTION METHOD AND SOFTWARE TOOL DESIGN OF DIGITAL CONTROL SYSTEMS 30

STUDY ON RISK STATE IDENTIFICATION AND PREDICTION METHOD AND...

引用

30th International Conference on nuclear engineering, ICONE 2023

作者： Zhang, Chao Chen, Sijuan Zhu, Ruoyu Sun, Jiajun Dong, Xiaomeng Li, Weihao Yang, Ming Xu, Anqi Wang, Jipu Department of Science and Technology Innovation State Nuclear Power Automation System Engineering Company Shanghai China Institute for Advanced Study in Nuclear Energy & Safety College of Physics and Optoelectronic Engineering Shenzhen University Guangdong Province Shenzhen City China Power Plant Control Center State Nuclear Power Automation System Engineering Company Shanghai China Shenzhen University Guangdong Province Shenzhen City China

ISBN: (纸本)9784888982566

With the overall improvement of the digital and intelligent level in the nuclear power industry, the failure of the Digital Control System (DCS) has become one of the major factors affecting the stable operation of nuclear power units. DCS safety problems can easily lead to the unit outage or shutdown, power reduction operation, system or equipment degradation events and other serious consequences, which will significantly threaten the safety and reliability of the unit operation. This paper studies the real-time safety problem of DCS based on the monitoring data of DCS itself, focusing on DCS current operating risk state identification, operating risk state transition model construction, residual operating risk prediction, to evaluate DCS operating risk state and predict the risk evolution trend. Furthermore, this study focus on the design and development of the software tool for risk state identification and prediction of DCS, so as to implement the methods and algorithms presented herein. © 2023 by JSME.

关键词： Digital control systems

来源：评论

学校读者我要写书评

暂无评论

Modeling, Computation and Analysis of Gaussian-Based Probability Density Function and Conflict Potential Field for Cooperative Overtaking

Modeling, Computation and Analysis of Gaussian-Based Probabi...

引用

Chinese automation Congress (CAC)

作者： Wen He Menglin Lv Yong Chen Jinlong Hao Mingjie Liu Yuhao Jiang School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Automation Chongqing University of Posts and Telecommunications Chongqing China School of Automation Engineering University of Electronic Science and Technology Chengdu China Chongqing Chang'an Automobile Corp Chengdu China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The collaborative overtaking framework presents significant potential for advancing road traffic safety and operational efficiency in intelligent transportation systems. By enabling instantaneous communication among roadway infrastructure, proximate vehicles, and other traffic entities, the framework facilitates the seamless exchange of critical information. Recognized for its superior performance, it is poised to play a pivotal role in the evolution of next-generation Advanced Driver Assistance Systems (ADAS), particularly with the proliferation of 5G communication technologies. This paper examines fundamental challenges associated with the modeling, computation, and analysis of Gaussian-based probability density functions and conflict potential fields, applying these methodologies to coordinated overtaking systems. Specifically, a Gaussian-based conflict potential field model is introduced alongside a risk assessment methodology designed to enhance overtaking safety by evaluating collision risks through vehicle-to-vehicle communication. Empirical experiments further substantiate the efficacy of the proposed approach, demonstrating notable performance improvements under dynamic and unpredictable driving conditions.

关键词： Analytical models Systematics Computational modeling Roads Vehicular ad hoc networks Collaboration Probability density function Road traffic Vehicle dynamics Testing

来源：评论

学校读者我要写书评

暂无评论

Common Mode Voltage Suppression of Three-to-Six-Phase Indirect Matrix Converter Based on 6-Virtual Vector Method

Common Mode Voltage Suppression of Three-to-Six-Phase Indire...

引用

International Conference on Power Electronics and Motion Control (IPEMC)

作者： Kai Ma Ke Lu Jiling Guo Tianlong Xiao College of Electrical Engineering Southwest Jiaotong University Chengdu China National Rail Transit Electrification and Automation Engineering Technology Research Center Chengdu China

ISBN: (数字)9798350351330

ISBN: (纸本)9798350351347

This article proposes a new modulation method that can suppress the maximum common mode voltage of a six phase output indirect matrix converter by 50%, while also taking into account the suppression of multi-phase output harmonic ***, the size of common mode voltage was studied considering only the switching state of the inverter stage. Based on the principles of minimizing common mode voltage and synthesizing harmonic voltage to zero, a virtual vector of inverter stage 6 was constructed. Secondly, the magnitude of common mode voltage when the rectification stage vector and the inverter stage 6 virtual vector act together was studied. Based on this, the rectification stage vector and inverter stage virtual vector were selected based on the minimum common mode voltage of different sectors. This can suppress the common mode voltage generated by the effective vector of the six phase output indirect matrix converter to 0.29V in , and the common mode voltage generated by the zero vector to 0.5V in .

关键词： Phase modulation Rectifiers Voltage Switches Harmonic analysis Vectors Inverters

来源：评论

学校读者我要写书评

暂无评论

NARX Model-Based Data-Driven Secure Control for UMVs Under Asynchronous DoS Attacks

NARX Model-Based Data-Driven Secure Control for UMVs Under A...

引用

International Conference on Control and automation (ICCA)

作者： Huiying Liu Li-Ying Hao Hui Li Tieshan Li Dan Wang College of Marine Electrical Engineering Dalian Maritime University Dalian China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

In this paper, based on nonlinear auto-regressive model with exogenous inputs (NARX) neural network, a resilient data-driven multi-step error feedback secure control method is designed for unmanned marine vehicles (UMVs). And the asynchronous DoS attacks are considered in Sensor-Controller channel and Controller-Sensor channel. Significantly, the success probability of these DoS attacks varies due to energy constraints across distinct channels. To mitigate the negative impart of DoS attacks, a NARX model-based predictor is devised. And the predict error are considered to design control scheme, enhancing the control effect for UMVs under asynchronous DoS attacks. What's more, a resilient partial form multi-step error feedback control (PF-MSEFC) method is designed by incorporating the proportional control term, the different control term, and the quadratic difference control term, which improves the utilization of historical tracking error information and enhance the flexibility of the control scheme. Finally, the effectiveness of the proposed resilient NARX predictive model-based PF-MSEFC scheme is demonstrated through simulation examples.

关键词： automation Trajectory tracking Proportional control Neural networks Predictive models Trajectory Feedback control

来源：评论

学校读者我要写书评

暂无评论

Collision-Free Formation Finite-Time Prescribed Performance Control for Under-Actuated Unmanned Surface Vehicles

Collision-Free Formation Finite-Time Prescribed Performance ...

引用

International Conference on Electronic engineering and Informatics (EEI)

作者： Wei Wang Yang Wang Tieshan Li Navigation College Dalian Maritime University Dalian China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

This paper studies the distributed path-following time-varying formation control problem for a fleet of under-actuated unmanned surface vehicles (USVs) with collision avoidance and connectivity preservation. A finite-time-prescribed performance-based (FTPP) formation control scheme is proposed based on the error transformation. To provide transient and steady-state performance specifications on velocity errors, including convergence time and range, a finite-time performance function (FTPF) is introduced in the control design. Radial basis function neural network (RBF) is utilized to compensate the effects of uncertain dynamics in USVs. Finally, by Lyapunov stability analysis, it is shown that all error signals of the closed-loop system are uniformly ultimately bounded. Simulation results show the effectiveness of the proposed formation control scheme.

关键词： Simulation Formation control Stability analysis Steady-state Closed loop systems Collision avoidance Vehicle dynamics Transient analysis Autonomous vehicles Convergence

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Adaptive Fixed-Time Terminal Sliding Mode Control for Unknown Nonlinear Systems

Neural Network-Based Adaptive Fixed-Time Terminal Sliding Mo...

引用

2024 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2024

作者： Liu, Siwen Zuo, Yi Li, Tieshan Wang, Huanqing Gao, Xiaoyang Xiao, Yang The Navigation College Dalian Maritime University Liaoning Dalian China The School of Automation Engineering University of Electronic Science and Technology of China Sichuan Chengdu China The School of Mathematical Sciences Bohai University Liaoning Jinzhou China The University of Alabama Department of Computer Science Tuscaloosa United States

ISBN: (纸本)9798331504755

The adaptive fixed-time terminal sliding mode control (TSMC) problem will be discussed for unknown nonlinear strict-feedback systems. Neural networks are used to estimate the unknown nonlinearities existing in the systems. When the control scheme is designed, the dynamic surface control (DSC) method is applied to avert the derivation of the virtual control signal and a novel hyperbolic tangent filter is developed. Subsequently, the adaptive control method is introduced to proposed a terminal sliding surface (TSS). Consequently, an adaptive TSMC controller is developed. Using the Lyapunov stability theory, we prove that the tracking error inclines to the TSS and a small interval near zero, and the closed-loop signals are bounded within fixed time. Finally, the availability of the proposed scheme is demonstrated by the simulation example. © 2024 IEEE.

关键词： Sliding mode control

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：