检索结果-内蒙古大学图书馆

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

Research on control and optimization of heavy-duty electromagnetic bearing of large-capacity energy storage flywheel 10

Research on control and optimization of heavy-duty electroma...

引用

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

Design of weak current measurement system and research on temperature impact

引用

nuclear Science and Techniques 2024年第4期35卷 46-56页

作者： Chu-Xiang Zhao San-Gang Li Rong-Rong Su Li Yang Ming-Zhe Liu Qing-Yue Xue Shan Liao Zhi Zhou Qing-Shan Tan Xian-Guo Tuo Yi Cheng College of Nuclear Technology and Automation Engineering Chengdu University of Technology1#DongsanluErxianqiaoChengdu 610059China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu University of Technology1#DongsanluErxianqiaoChengdu 610059China University of Science and Technology of China Hefei 230026China School of Physics and Electronic Engineering Sichuan University of Science and EngineeringZigong 643000China

A dedicated weak current measurement system was designed to measure the weak currents generated by the neutron ionization *** system incorporates a second-order low-pass filter circuit and the Kalman filtering algorithm to effectively filter out noise and minimize interference in the measurement *** conducted under normal temperature conditions has demonstrated the system's high precision ***,it was observed that temperature variations can affect the measurement *** were collected across temperatures ranging from -20 to 70℃,and a temperature correction model was established through linear regression fitting to address this *** feasibility of the temperature correction model was confirmed at temperatures of -5 and 40℃,where relative errors remained below 0.1% after applying the temperature *** research indicates that the designed measurement system exhibits excellent temperature adaptability and high precision,making it particularly suitable for measuring weak currents.

关键词： Weak current measurement system Neutron ionization chamber Kalman filter algorithm Temperature correction model

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

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

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 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

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：