检索结果-内蒙古大学图书馆

Adaptive Neural Fixed-Time Control for Uncertain Nonlinear Systems

IEEE Transactions on Circuits and Systems II: Express Briefs 2024年第2期71卷 637-641页

作者： Liu, Siwen Wang, Huanqing Li, Tieshan Xu, Ke Navigation College Dalian Maritime University Dalian116026 China College of Mathematical Sciences Bohai University Jinzhou121000 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu610054 China

This brief addresses the adaptive fixed-time system control problem subject to unknown nonlinear functions. By employing backstepping technique, fixed-time control, and neural networks (NNs), an adaptive fixed-time control approach is developed. NNs are utilized to package the unknown nonlinearities in the controlled system. The hyperbolic tangent functions are firstly utilized to solve the singular problem, which may exist in the derivation of virtual controller. Meanwhile, the jitter phenomenon is avoided. The developed controller design scheme not only assures the signals' boundedness within fixed-time interval, but also makes the tracking error converge. Finally, on the aid of the simulation results, the effective of the designed control technique is shown. © 2024 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Towards in X-Ray Induced Acoustic Imaging for Nasopharyngeal Carcinoma Radiotherapy with a Multidimensional Information Fusion Network 3

Towards in X-Ray Induced Acoustic Imaging for Nasopharyngeal...

引用

3rd International Conference on Computer Applications technology, CCAT 2024

作者： Jiang, Xin Chen, Zhi-Chao Sun, Zheng Liu, Ming-Zhe Chongqing University of Technology School of Artificial Intelligence Chongqing401135 China Chongqing University Cancer Hospital Department of Radiology Chongqing400030 China Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu610000 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325000 China

ISBN: (纸本)9798331539795

X-ray-induced acoustic computed tomography (XACT) imaging is an emerging noninvasive imaging technique with wide applications in various clinical medicine fields. However, traditional XACT imaging methods often suffer from low imaging quality and increased noise artifacts, particularly notable under sparse sampling conditions. To overcome these challenges, we propose a hybrid supervised reconstruction method based on deep learning. Specifically, we extract and integrate information from XACT thermoacoustic signals and XACT images reconstructed by traditional methods to leverage complementary feature information from both modalities. To adapt to imaging under sparse sampling, we define multiple sparse conditions based on real-world imaging environments and validate them using a real radiotherapy dataset of head and neck cancer patients. The results demonstrate the adaptability of our method to sparse conditions and its capability to enhance XACT imaging quality under such circumstances. Additionally, we validate the feasibility of X-ray thermoacoustic imaging for 3D dose monitoring. © 2024 IEEE.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

Development of a Leakage Current Measurement System for Semiconductor Detectors

Development of a Leakage Current Measurement System for Semi...

引用

China Instrument and Control Society (ACCIS), Academic Conference of

作者： Bowen Yang Chuahao Hu Guoqiang Zeng Dan Li Honglin Zhao Haotian Li The College of Nuclear Techology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (数字)9798350350326

ISBN: (纸本)9798350350333

In this article, we examine a high-precision leakage current measurement system with a semiconductor detector and automatic range switching. The system consist of two main modules: the leakage current measurement module and the control and display module. The leakage current measurement module is based on the transresistance amplifier principle and builds an I-V conversion circuit. A large measuring range from nA to pA is achieved through range switching via a relay-controlled mechanism. The control and display module has an automatic range switching algorithm developed using the STM32 microprocessor. This algorithm accurately measures the leakage current of the semiconductor detector by controlling the relay via the GPIO port. In addition, a detector detection platform is set up to judge whether the detector has been damaged based on the measured leakage current data. The system designed in this paper can measure leakage currents ranging from 1 pA to 2000 nA with a margin of error of less than 0.32%. Its performance has been successfully validated with a variety of detectors.

关键词： Semiconductor device measurement Measurement errors Semiconductor detectors Microcontrollers Current measurement Measurement uncertainty Switches Control systems Leakage currents Relays

来源：评论

学校读者我要写书评

暂无评论

Multi-Object Detection and Tracking of Foggy Vehicles Based on iMproved YOLOV5s and Optimized Deepsort

Multi-Object Detection and Tracking of Foggy Vehicles Based ...

引用

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Jiayu Chen Xingwen Dong Yuting Zheng Bo Li School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

In view of the problems of ID false detection and missing detection often occur in the multi-target detection and tracking of the vehicle in front of the autonomous vehicle in hazy days, this paper proposes a new de-fog algorithm based on dark channel prior to improve the quality of the input image. CBAM-Net was embedded into the CSPDarknet53 backbone network of YOLOv5s model to improve the feature extraction capability and optimize the detection effect. A new CMTIOU loss algorithm is proposed to replace the IOU in Deepsort, and comprehensively consider the factors of time, feature and location geometry to improve the tracking effect and HOTA index. The experimental results show that the MOTA and HOTA of the proposed algorithm are 77.6% and 78.8% respectively compared with the traditional algorithm.

关键词： YOLO Geometry Accuracy Correlation Force Feature extraction Indexes Convolutional neural networks Autonomous vehicles Meteorology

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

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

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Yingzi Wen Xin He Dawei Lv Fei Li 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 Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu China

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on dynamic wear evolution of modified gear rack considering the real-time variation of contact characteristics

引用

Wear 2025年

作者： Zeng, Liyuan Deng, Xingqiao Li, Fan Dong, Chenglong Wang, Shisong Yang, Hongjuan Tang, Chuan Li, Yuhang School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China School of Mechanical and Electrical Engineering Chengdu University of Technology Chengdu610059 China

Tooth profile modification (TPM) is an essential process in the design of open gear rack, which plays an important role in improving the meshing performance and reducing the tooth surface wear. However, TPM and tooth surface wear cause significant alterations to the tooth profile, which in turn affects the contact characteristics on the tooth surface. This poses a significant challenge for predicting the dynamic wear evolution of modified gear rack. In this paper, a dynamic wear evolution model of modified gear rack considering the real-time variation of contact characteristics is proposed. Firstly, a wear model of gear rack under mixed elastohydrodynamic lubrication (EHL) is established, considering the lubrication state of the tooth surface. By incorporating the effects of TPM and tooth surface wear, a modified time-varying meshing stiffness (TVMS) model and a contact load distribution model are proposed. Based on the proposed model, the dynamic wear evolution of modified gear rack under mixed EHL is accurately predicted, by employing a cyclic iterative method to determining the real-time contact characteristics under the wear degradation of the tooth profile. After validating the effectiveness of the model, the dynamic wear evolution of the gear rack driving mechanism of a rack rail train is investigated, and a quantitative analysis of the effect of TPM parameters on wear depth is conducted. This study holds significant implications for unveiling the wear failure mechanism of modified gear rack and optimizing the design of TPM parameters. © 2025 Elsevier B.V.

关键词： Gear teeth

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning control of lateral vibration of high-speed train carbody 4

Reinforcement learning control of lateral vibration of high-...

引用

2024 4th International Conference on Mechatronics, automation and Intelligent Control, MAIC 2024

作者： Mou, Ruqiang Chen, Chunjun School of Mechanical Engineering Southwest Jiaotong University Sichuan Chengdu610031 China Department of Automation Engineering The Engineering & Technical College of Chengdu University of Technology Sichuan Leshan614000 China

Increasing speed is one of the effective ways to raise high-speed train (HST) transportation capacity. However, increasing speed leads to greater vibration of HST with passive suspension, which can reduce the smoothness and safety of HST. Thus, a twin delayed deep deterministic policy gradient (TD3) control strategy was designed to reduce the lateral vibration of the HST carbody. The 3-degree-of-freedom (DOF) and 17-DOF models were utilized in designing the TD3 controller and simulation, respectively. In addition, the ballastless track spectrum of the Chinese high-speed railway was utilized to obtain the irregularities of the track. A reward function containing cost and penalty was designed to raise TD3 controller training efficiency. A linear quadratic optimal cost function and a step penalty function were designed, respectively. The control effect of the TD3 strategy was studied by simulation. The results indicate that TD3 can effectively reduce root-mean-square (RMS) and peak values for lateral acceleration at the front and rear ends of the HST carbody, and significantly improve the lateral smoothness of the HST carbody, which verifies validity of TD3 strategy. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming Based Strategies of Future Crop Plant 24

Dynamic Programming Based Strategies of Future Crop Plant

引用

Proceedings of the 2024 5th International Conference on Big Data Economy and Information Management

作者： Beining Zhang Xueying Wang Yongkang Deng Kai Chen Qinglang Liu Measurement and Control Technology and Instruments School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu Sichuan China School of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu Sichuan China

ISBN: (纸本)9798400711862

In this paper, we develop a decision model based on dynamic programming to create an optimal crop plan for 2024-2030 in rural northern China. Considering different marketing scenarios, uncertainties, and crop substitutions and complementarities, this paper solves the problem with three sub-problems. First, the optimal cropping plan for 2024-2030 is calculated based on the cropping scenario for 2023. It is assumes that expected sales, cropping costs, yields and marketing prices are stable. Secondly, a multi-objective planning model was developed. It aimed at profitability and stability and took into account uncertainties. Finally, the planting plan was further optimised and it considered crop substitutability and complementarity, and the relationship between expected sales and selling prices and planting costs. Through dynamic planning and Monte Carlo simulation, this paper takes into account uncertainty and crop relationships and it solves the optimal crop planting plan for the years 2024-2030 with a maximum profit of about $7.737 million. Therefore, this paper proposes a decision model based on dynamic programming and it takes into account various factors of the planting plan for the next seven years. An effective method is provided for solving the crop planting strategy problem in sustainable agricultural development.

关键词： Dynamic Programming

来源：评论

学校读者我要写书评

暂无评论

Optimization scheme for rapid analysis of copper ore grade using EDXRF

Optimization scheme for rapid analysis of copper ore grade u...

引用

2023 International Conference on Computer Application and Information Security, ICCAIS 2023

作者： Li, Wen Lai, Wanchang Chen, Dongdong Ma, Yutian Yang, Bingsong Zhang, Diancheng College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China National Key Laboratory of Ni&Co Associated Minerals Resources Development and Comprehensive Utilization China Gansu Jinchuan Intelligent Measurement and Control Technology Co. Ltd. China

ISBN: (纸本)9781510675032

In order to optimize the method and technology for the rapid determination of copper ore grade using Energy Dispersive X-ray Fluorescence (EDXRF), improve the accuracy of EDXRF analysis, guide the development and utilization of copper ore resources, and enhance production efficiency, the optimal operating conditions for the EDXRF analyzer were determined using Monte Carlo (MC) simulation and physical experiments. The recommended settings were a tube voltage of 40 kV and a tube current of 10 μA. Under these optimal conditions, the copper (Cu) content in various types of copper ore samples was analyzed. The copper ore was categorized into geological samples (including raw ore samples and tailings samples), copper concentrates, and matte. The correction of matrix effects was carried out using a binary regression method. Experimental results showed that the average absolute error of analyzing geological samples by EDXRF was 0.035%, with an average relative error of 4.08%. The average absolute error for analyzing copper concentrates was 0.238%, with an average relative error of 1.01%. For matte analysis, the average absolute error was 0.421%, with an average relative error of 1.01%. The accuracy and precision of the method meet the production requirements of enterprises, and it holds promising prospects for widespread application. © 2024 SPIE.

关键词： Ores

来源：评论

学校读者我要写书评

暂无评论

Dynamics Characteristics Analysis of Rack Railway Guiding Equipment of Mountain Rack Railway Train with Considering Wheel-Rail Contact

Dynamics Characteristics Analysis of Rack Railway Guiding Eq...

引用

International Conference on Mechanical Design, ICMD 2023

作者： Wang, Haowen Xiang, Quanming Liu, Weiping Gao, Chang Liu, Jialin Wang, Shisong Deng, Xingqiao College of Mechanical and Electrical Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Dujin Mountain Rail Transit Co. Ltd. Sichuan Chengdu611830 China Sichuan Shudao New System Rail Group Co. Ltd. Sichuan Chengdu610072 China School of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

ISBN: (纸本)9789819709212

A multi-body dynamic simulation model is established to study the rack railway guiding equipment (RRGE) in the mountain rack railway train system. This model incorporates the effects of wheel rail-rack rail contact and linear spring damper, which can accurately depict the dynamic response of RRGE. Considering the factors such as train passing speed, vertical distance, and initial gear posture, the model is first applied to analyze the dynamic characteristics of the gear. Then according to the gear entry condition and gear rotational speed, the vibration response of RRGE when the gear passing through rollers is analyzed. Finally, the dynamic characteristics of gear and RRGE under two extreme conditions are comparatively analyzed, and a set of parameters are proposed to ensure the smooth transition of the train. The simulation results show that, to ensure the safety of the mountain rack railway train, it is recommended to set the vertical distance at 173 mm and the initial gear posture at tooth contact. Furthermore, when selecting the train passing speed, factors such as gear entry condition, train operation efficiency, and shock vibration level should be taken into consideration. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Railroads

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：