检索结果-内蒙古大学图书馆

Computer Information Science and Application technology (CISAT), International Conference on

作者： Yukun Wang College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Biological evolution has deepened our understanding of nature. Since the advent of civilization, humans have continually explored ways to record what they see and hear, from cave sketches to camera photography, with clarity being a consistent goal. Image super-resolution technology has made significant progress, but early methods like interpolation and filtering couldn’t effectively restore details. Traditional convolution methods require high computational and storage resources, limiting their use in hardware-constrained scenarios. Therefore, finding a method that reduces computational resources while ensuring effectiveness is crucial. This paper proposes the Residual Swin Transformer Block based on the Swin Transformer and designs the SR-Swin deep learning model for super-resolution image processing. Experiments show it achieves an average PSNR value of 30.6 dB, indicating good performance.

关键词： Photography Technological innovation Computational modeling Superresolution Refining Network architecture Transformers Image restoration Research initiatives Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Design of a New Consequent-Pole Hybrid Excited Machine with Segmented Stator

Design of a New Consequent-Pole Hybrid Excited Machine with ...

引用

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Guangyu Qu Yingcan Liu Jinyi Yu Wei Liu College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (数字)9798350362213

ISBN: (纸本)9798350362220

In this paper, a new consequent-pole hybrid excited (HE) machine with segmented stator (CHE-SS machine) is proposed, which can be applied in some variable speed applications. To decrease the torque ripple, the segmented structure is adopted in the stator. The stator tooth can be divided into two types: the primary tooth and the secondary tooth. The field winding is placed on the primary tooth. The armature winding is placed on the secondary tooth. The U-typed permanent magnets (PMs) are placed in the rotor to improve the torque density and the rigidity. To validate the superiority of the proposed machine, some electromagnetic properties, such as the back electromotive force (back-EMF), the output torque and the cogging torque are simulated and analyzed by the finite element (FE) method. The FE-predicted results show that this proposed machine can exhibit excellent performances.

关键词： Magnetic flux Forging Torque Windings Stator windings Rotors Magnetic analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent Strawberry Ripeness and Disease Detection Classification System Based on Deep Learning 3

Intelligent Strawberry Ripeness and Disease Detection Classi...

引用

3rd International Conference on Electronics and Information technology, EIT 2024

作者： Li, Jiajun Yang, Xin Qian, Songcheng Xu, Junjie Sun, Lei Zeng, Zhaoning University of Electronic Science and Technology of China School of Automation Engineering Chengdu China Chengdu University of Technology College of Energy Chengdu China Yunnan University School of Earth Science Yunnan China

ISBN: (纸本)9798350369151

In modern agricultural production, timely detection of crop diseases and accurate assessment of ripeness are crucial for reducing yield loss and enhancing product quality. Strawberries, being a widely popular and economically valuable fruit, are particularly sensitive to diseases and strict in ripeness requirements, making quality control during their production critical. This paper develops a classification system for strawberry ripeness and pest disease detection based on the YOLOv5 deep learning model and automated robotic arm technology. The YOLOv5 model, known for its high efficiency, accurately identifies strawberries and assesses their ripeness and pest conditions, thereby enhancing the precision and speed of detection. The automated robotic arm technology utilizes the detection results from the YOLOv5 model to perform efficient and accurate automated sorting and grading of strawberries, significantly reducing labor costs and human error. By integrating deep learning and automation technologies, this system substantially increases strawberry yield and quality, alleviates labor burdens, and enhances agricultural production efficiency. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Control Method for Nonlinear Characteristics of Variable Frequency Regulation for Wide-Distance-Range Adaptive WPT System

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 10221-10241页

作者： Xia, Ziyi Dai, Xin Li, Yanling Wang, Liuping Chen, Fengwei Ma, Jun Chongqing University College of Automation Chongqing400044 China Xihua University School of Electrical Engineering and Electronic Information Chengdu610039 China Royal Melbourne Institute of Technology School of Engineering MelbourneVIC3000 Australia

In the realm of output control for wireless power transfer (WPT) systems, variable frequency (VF) regulation of the transmitter inverter stands out as a leading and sophisticated research direction, as it facilitates the adjustment of the voltage conversion ratio and holds significant promise for long-distance power transfer applications. However, the VF regulation process in WPT systems is characterized by strong nonlinearity and is highly sensitive to variations in the inverter driving frequency. In addition, increasing transfer distances exacerbate these nonlinearities due to changing mutual inductances. Consequently, traditional approaches to VF regulation are constrained by a limited operating range, which impedes the application of WPT technology in scenarios involving varying distances. To address these challenges and enhance the system's adaptability to different power transmission distances while managing multiparametric uncertainties in WPT systems, this article develops a data-driven model-free adaptive control (MFAC) method. Initially, an online modeling approach utilizing dynamic linearization is proposed to characterize the VF regulation process using solely system input-output data. Subsequently, a switched control strategy based on the estimated data model is devised to calculate the optimal operating frequency for the WPT system. Finally, a prototype with maximum output of 3.88 kW is constructed to demonstrate the feasibility of the proposed approach. The results indicate that the data-driven control system exhibits a robust dynamic response and strong resilience across varying transfer distances ranging from 5 to 65 cm, corresponding to a distance-diameter ratio of 0.125-1.625. © 1986-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Application of Fuzzy BP Neural Network to Evaluate Effectiveness of Curriculum Teaching Reform of nuclear Radiation Detection technology 5

Application of Fuzzy BP Neural Network to Evaluate Effective...

引用

5th IEEE Eurasian Conference on Educational Innovation, ECEI 2022

作者： Jiang, Jianfeng Li, Fei Gu, Yi Gu, Zhixing Ge, Liangquan Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu Chengdu China

ISBN: (纸本)9781665433181

In the context of curriculum teaching reform, it is of great significance to evaluate its effectiveness. In the paper, the teaching reform of the nuclear radiation detection technology curriculum is studied and analyzed by using the fuzzy BP neural network model. According to the investigation of the evaluation factors of education reform, four primary evaluation indexes and nine corresponding secondary indexes are selected: teaching ability, classroom order, after school learning, and teaching effectiveness. The preliminary data set is obtained in the form of a questionnaire. The fuzzy theory and analytic hierarchy process are used to construct and calculate the evaluation index to provide samples for the learning of neural networks. On this basis, the fuzzy BP neural network model is constructed by combining BP neural network with a fuzzy system. After testing, the relative error of the output prediction score is less than 0.0002, which well predicts the evaluation results and provides an effective method for the evaluation of curriculum teaching reform. © 2022 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical Parallel Trajectory Tracking Control of Maritime Autonomous Surface Ships Based on Integral Control Barrier Functions

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-10页

作者： Xu, Jiaxue Gu, Nan Wang, Dan Li, Tieshan Han, Bing Peng, Zhouhua School of Marine Electrical Engineering Dalian Maritime University Dalian China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China College of Physics and Electronic Information Engineering Minjiang University Fujian China

This article investigates the parallel trajectory tracking control of fully-actuated maritime autonomous surface ships (MASSs) in the presence of multiple stationary/moving ocean obstacles. A safety-critical parallel control architecture is proposed for the trajectory tracking control of MASSs. Specifically, an artificial MASS system is constructed based on a data-driven learning predictor where real-time and historical navigation data are both utilized to achieve the estimation of the unknown weights of Taylor polynomials and Fourier series. Then, a parallel trajectory tracking control law is designed based on the artificial system such that the MASS is capable of track the reference trajectory positively. Finally, integral control barrier functions are employed to encode input and safety constraints. A safety optimization signal is augmented to the designed parallel control law to achieve the collision avoidance of all ocean obstacles. Based on the stability and safety analyses, the tracking errors of the actual MASS system are verified to be uniformly ultimately bounded and the MASS system is safe. Numerical examples confirm the effectiveness of the designed safety-critical parallel trajectory tracking control scheme for the MASS. IEEE

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Analysis of Teaching Influencing Factors and Teaching Reform of Numerical Analysis Course Based on BP Neural Network 5

Analysis of Teaching Influencing Factors and Teaching Reform...

引用

5th IEEE Eurasian Conference on Educational Innovation, ECEI 2022

作者： Qin, Qingao Li, Fei Gu, Yi Gu, Zhixing Ge, Liangquan Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9781665433181

Numerical analysis course has important guiding significance for data analysis ability of science and engineering graduate students. Based on BP neural network, we study the teaching influencing factors and teaching reform analysis of numerical analysis course. The teaching quality evaluation of numerical analysis is constructed based on BP neural network. The course of numerical analysis is evaluated from the aspects of classroom teaching, extracurricular development, students' knowledge reserve, and teaching results. 0.820675 is the related coefficient between the predicted value of the neural network and the actual value of questionnaire results, which shows that the constructed teaching quality evaluation model is reliable. Through the related coefficient analysis of the data, the main factors affecting the quality of teaching are obtained to provide new direction and orientation for teaching reform. © 2022 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Neural Network Radionuclide Identification Algorithm Based on Exponential Smoothing

Neural Network Radionuclide Identification Algorithm Based o...

引用

2022 International Conference on Computation, Big-Data and engineering, ICCBE 2022

作者： Wang, Tang He, Xin Ge, Liangquan Li, Fei Gu, Yi Gu, Zhixing Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu China

ISBN: (数字)9781665470551

ISBN: (纸本)9781665470551

The development of nuclear energy and the application of nuclear technology is inseparable from the detection of radionuclides. Considering the incomplete utilization of ?-spectral information in traditional spectral analysis methods, the accuracy is not high. In this study, exponential smoothing is performed on the energy spectrum signal of length 1024 to eliminate the influence of the statistical fluctuation of the detector, and then it is used as the input of the neural network to realize the full spectrum analysis. The method avoids the complex feature extraction process and can identify a single radionuclide in real time. © 2022 IEEE.

关键词： Radioisotopes

来源：评论

学校读者我要写书评

暂无评论

PETRFusion: Multi-Sensor Fusion Based BEV Semantic Segmentation Network for Autonomous Driving 27

PETRFusion: Multi-Sensor Fusion Based BEV Semantic Segmentat...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Zhao, Yang Du, Jingyu Yang, Qihang Cai, Ningze Peng, Zhinan Zhan, Huiqin Cheng, Hong School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Glasgow College University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331505929

Bird's Eye View (BEV) based perception algorithms are receiving increasing attention in the field of autonomous driving, how to more effectively utilize multi-sensor data in BEV is a challenge. In this paper, we propose PETRFusion, a BEV segmentation network that integrates multiple cameras with a LiDAR sensor. We focus on the task of BEV segmentation, designing the network architecture based on the similarity between LiDAR point clouds and semantic segmentation maps. The proposed method uses point cloud features as queries for semantic segmentation and employs Transformers to fuse image features with point cloud features, thereby maximizing the preservation of 3D spatial information from the point cloud. Additionally, we enhance the 3D positional encoder of PETR to provide more reliable 3D image features. We conduct detailed validation on the nuScenes dataset and achieve state-of-the-art results. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Semi-empirical and semi-quantitative lightweight shielding design method

引用

nuclear Science and Techniques 2023年第3期34卷 109-124页

作者： Song-Chuan Zheng Qing-Quan Pan Huan-Wen Lv Song-Qian Tang Xiao-Jing Liu College of Smart Energy Shanghai Jiao Tong UniversityShanghai 200240China School of Nuclear Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of ChinaChengdu 610200China

The lightweight shielding design of small reactors is a popular research *** on a small helium-xenon-cooled solid reactor,the effects of neutron and photon shielding sequence and the number of shielding layers on the radiation dose were first *** was found that when photons were shielded first and the number of shielding layers was odd,the radiation dose could be significantly *** reduce the weight of the shielding body,the relative thickness of the shielding layers was optimized using the genetic *** optimized scheme can reduce the radiation dose by up to 57%and reduce the weight by 11.84%.To determine the total thickness of the shielding layers and avoid the local optimal solution of the genetic algorithm,a series of formulas that describes the relationship between the total thickness and the radiation dose was developed through large-scale calculations.A semi-empirical and semi-quantitative lightweight shielding design method is proposed to integrate the above shielding optimization method that verified by the Monte Carlo ***,a code,SDIC1.0,was developed to achieve the optimized lightweight shielding design for small *** was verified that the difference between the SDIC1.0 and the RMC code is approximately 10%and that the computation time is shortened by 6.3 times.

关键词： Small reactor Lightweight Shielding calculation Genetic algorithm

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：