检索结果-内蒙古大学图书馆

10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Zhao, Wenhao Liu, Wei Qu, Guangyu Jing, Hailian Huang, Jiancheng Chengdu University of Technology College of Nuclear Technology and Automation Engineering China

ISBN: (纸本)9798350351330

The rotor of a large-capacity flywheel energy storage system will cause energy loss due to air and mechanical resistance during high-speed operation, and the traditional PID control cannot take into account the system robustness under the large-sized and heavy-loaded rotor of the electromagnetic bearing system. This paper takes the heavy-duty electromagnetic bearing system as the research object, builds a fractional-order PID controller suitable for this system, and compares and analyses the operating characteristics of the electromagnetic bearing with that of the electromagnetic bearing under traditional PID control. The study shows that for the large-capacity energy storage flywheel heavy-duty electromagnetic bearing system, the use of fractional-order PID control technology can provide better control performance and anti-jamming ability, and thus ensure the stability and safety of the energy storage flywheel system. © 2024 IEEE.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

Enhancing traffic light recognition in autonomous vehicles: A novel convolutional neural network approach for fog removal using efficient channel attention 4

Enhancing traffic light recognition in autonomous vehicles: ...

引用

4th International Conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Ji, Shuai Zhang, Huangnian Dong, Xingwen The College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Adverse environmental conditions such as haze, rain, and dust can significantly impair visibility for vehicles in motion, leading to blurred vision. Traditional de-fogging techniques often encounter limitations, including reliance on pre-existing assumptions, color distortion, and inadequate real-time performance. Consequently, these methods may fail to effectively distinguish traffic light images post-de-fogging, thereby hindering target recognition in autonomous driving systems. This study introduces a convolutional neural network that integrates deep and shallow feature fusion utilizing the Efficient Channel Attention mechanism. By employing an atmospheric scattering model, shallow features from fogged images are extracted through convolutional layer operations, while deep features are obtained using parallel multi-scale convolution kernels. The integration of shallow and deep features is achieved through a series of fusion steps, enhanced by the application of an effective channel attention mechanism. Ultimately, a transmittance map corresponding to the fog map is derived through nonlinear regression, facilitating the recovery of fog-free images and improving the recognition capabilities of the YOLOv8 model. Experimental results demonstrate that this approach effectively identifies traffic light targets during simulations of vehicles navigating traffic intersections. Furthermore, the quality of fog removal achieved by this method surpasses that of other algorithms, as evidenced by both subjective evaluations and objective analyses. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Implementation of a wristwatch for dose measurement based on CsI detector 4

Implementation of a wristwatch for dose measurement based on...

引用

4th International Conference on Mechanical, Electronics, and Electrical and automation Control, METMS 2024

作者： Chen, Jiongrui Qin, Zhangjian Zhao, Chengfeng College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China

ISBN: (数字)9781510679887

ISBN: (纸本)9781510679870

We have implementation a wristwatch that utilizes a Silicon Photomultiplier (SiPM) and a CsI(Tl) crystal for radiation dose rate detection. Compared to traditional personal dosimeters, it offers advantages such as high detection efficiency and portability. The measurement module incorporates a scintillation detector, a composite material comprised of CsI(Tl) crystal and SiPM, complemented by a signal conditioning module that boasts a pulse shaping circuit. The wristwatch, utilizing the functionalities of the CH579M microcontroller and advanced design algorithms, can rapidly respond to sudden fluctuations in environmental radiation levels. After testing, the detector's signal-to-noise ratio was measured at 12 dB, with a pulse width of 25 µs. The actual measurement range of the wristwatch is from 0. 1 to 250 μSv/h. © 2024 SPIE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A model for image super-resolution based on Swin Transformer 7

A model for image super-resolution based on Swin Transformer

引用

7th International Conference on Computer Information Science and Application technology, CISAT 2024

作者： Wang, Yukun Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu610059 China

ISBN: (纸本)9798350375107

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. © 2024 IEEE.

关键词： deep learning Image Super Resolution Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Masked hybrid attention with Laplacian query fusion and tripartite sequence matching for medical image segmentation

引用

Neural Computing and Applications 2025年第8期37卷 5891-5911页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Wang, Xiangxiang Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Medical image segmentation is pivotal in computer-aided diagnosis systems, demanding high precision and contextual understanding. Vision Transformer-based approaches have gained much attention recently due to their excellent performance and ability to capture long-range dependencies in medical images. However, research shows they suffer from inadequate multi-scale feature integration, poor object localization, and inconsistent mask predictions, leading to sub-optimal segmentation performance. This paper addresses these challenges by redefining semantic medical image segmentation through learnable object queries within an enhanced transformer framework with a masked hybrid attention querying mechanism, optimizing multi-scale feature fusion, object localization, and instance-specific segmentation. First, this study presents a novel transformer-based masked hybrid attention mechanism using Laplacian query fusion on learnable query features and incorporating a novel tripartite sequence matching technique as part of the enhanced decoder block to improve the consistency of mask predictions and optimize decoder queries. The designed hybrid multi-head self- and cross-attention mechanisms aim to selectively integrate multi-scale features, ensuring optimal feature combinations for precise segmentation. Secondly, multiple class tokens are incorporated to improve object localization and capture class-specific characteristics within the transformer framework, leveraging the transformer decoders’ ability to learn distinct instance representations. Experimental results and extensive ablation studies demonstrate the effectiveness of the proposed approach on three publicly available datasets, obtaining better segmentation results compared to various state-of-the-art approaches using various evaluation metrics. Specifically, the proposed model achieves a Dice Score of 95.25%, 92.75%, and 85.25% on LUNA, ISIC, and DRIVE datasets, respectively. © The Author(s), under exclusive licence

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

Effect of contact materials on the transient characteristics of vacuum arc plasma and anode erosion

引用

Plasma Science and technology 2024年第11期26卷 170-180页

作者： Ze YANG Dongsheng CAI Qi HUANG Lijun WANG College of Nuclear Technology and Automation Engineering Chengdu University of TechnologyChengdu 610059People’s Republic of China Postdoctoral Mobile Station in Nuclear Science and Technology Chengdu University of TechnologyChengdu 610059People’s Republic of China School of Information Engineering Southwest University of Science and TechnologyMianyang 621010People’s Republic of China State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’an 710049People’s Republic of China

In this study, the mechanisms of the anode phenomena and anode erosion with various contact materials were investigated. Arc parameters were calculated, and the anode temperature was predicted with a transient self-consistent model. The simulation results predicted a constricted arc column and obvious anode phenomena in Cu–Cr alloy contacts than in W–Cu alloy *** observation could be the reason for the concentrated anode erosion in Cu–Cr alloys. For the contacts made by pure tungsten(W) and W–Cu alloy, the anode temperature increased rapidly because of the low specific heat of W. However, the maximum energy flux from the arc column to the anode surface was lower than in other cases. The simulation results were compared with experimental results.

关键词： vacuum arc MHD model anode erosion contact materials

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Analysis of Local Extreme Cold Events in the Context of Global Warming: Causes and Predictions 5

Neural Network-Based Analysis of Local Extreme Cold Events i...

引用

5th International Conference on Artificial Intelligence and Computer engineering, ICAICE 2024

作者： Zhang, Mao Peng, Ying Zeng, Yuming Chen, Yabing The College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

ISBN: (纸本)9798331528911

Global warming is a pressing issue, accompanied by both rising temperatures and local extreme cold events. This paper analyzes the relationship between global warming and extreme weather events through quantitative analysis of climate data. Focusing on the United States as a representative of regions experiencing extreme cold, a neural network model is developed to predict these events. Results indicate that rising global temperatures positively correlate with increased snowfall in the US, while negatively impacting US winter temperatures. This suggests that as global average temperatures increase, US winters become colder with more snow. The study concludes that global warming and local extreme cold events are not contradictory but strongly correlated phenomena. © 2024 IEEE.

关键词： Extreme weather

来源：评论

学校读者我要写书评

暂无评论

Design of a new in situ monitoring device for aquaculture 3

Design of a new in situ monitoring device for aquaculture

引用

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

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

A nuclide identification method ofγspectrum and model building based on the transformer

引用

nuclear Science and Techniques 2025年第1期36卷 80-93页

作者： Fei Li Chu-Yang Luo Ying-Zi Wen Sheng Lv Feng Cheng Guo-Qiang Zeng Jian-Feng Jiang Bing-Hai Li College of Nuclear Technology and Automation Engineering Chengdu University of TechnologyChengdu 610000China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu 610000China Department of Physics Universitat Politècnica de CatalunyaBarcelona 08028Spain Airborne Survey and Remote Sensing Center of Nuclear Industry Shijiazhuang 050000China Hebei Key Laboratory of Airborne Detection and Remote Sensing Technology Shijiazhuang 050000China

In current neural network algorithms for nuclide identification in high-background,poor-resolution detectors,traditional network paradigms including back-propagation networks,convolutional neural networks,recurrent neural networks,etc.,have been limited in research on γ spectrum analysis because of their inherent mathematical *** is difficult to make progress in terms of training data requirements and prediction *** contrast to traditional network paradigms,network models based on the transformer structure have the characteristics of parallel computing,position encoding,and deep stacking,which have enabled good performance in natural language processing tasks in recent ***,in this paper,a transformer-based neural network (TBNN) model is proposed to achieve nuclide identification for the first ***,the Geant4 program was used to generate the basic single-nuclide energy spectrum through Monte Carlo simulations.A multi-nuclide energy spectrum database was established for neural network training using random matrices of γ-ray energy,activity,and *** on the encoder–decoder structure,a network topology based on the transformer was built,transforming the 1024-channel energy spectrum data into a 32×32 energy spectrum sequence as the model *** experiments and adjustments of model parameters,including the learning rate of the TBNN model,number of attention heads,and number of network stacking layers,the overall recognition rate reached 98.7%.Additionally,this database was used for training AI models such as back-propagation networks,convolutional neural networks,residual networks,and long shortterm memory neural networks,with overall recognition rates of 92.8%,95.3%,96.3%,and 96.6%,*** indicates that the TBNN model exhibited better nuclide identification among these AI models,providing an important reference and theoretical basis for the practical application of transformers in the qualitative and quantitativ

关键词： Nuclide identification Neural network Transformer

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：