检索结果-内蒙古大学图书馆

3rd International Conference on Robotics and Artificial Intelligence, JCRAI 2023

作者： Yue, Wenqiang Chen, Li'an Huang, Haiyan School of Electrical Engineering and Automation Xiamen University of Technology China School of Electrical Engineering and Automation Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control Xiamen University of Technology China Xiamen Minghan Electric Co. Ltd. China

ISBN: (纸本)9798400707704

With the development of environmental sensor technology, more and more environmental sensors are widely used in various fields, such as environmental monitoring, smart home, smart city and so on. However, due to the complexity and diversity of environmental sensor data, there are a high number of anomalous data in sensor data, which can lead to misjudgment and false positives, compromising data reliability and accuracy. Therefore, the detection method of abnormal data in different dimensions of environmental sensors based on machine learning algorithms were studied in this paper. Firstly, the environmental sensor data of IBRL (Intel Berkeley Research Lab) data set was preprocessed, including data cleaning, data normalization and feature extraction. Then, the simulation experiment was completed using the data set, and the data of different dimensions was detected using machine learning algorithms such as OneClass Support Vector Machine algorithm, Local Outlier Factor algorithm, and Isolation Forest algorithm. Finally, through experimental comparison and analysis of the application effects of the above three algorithms in anomaly detection of environmental data in different dimensions, the Isolation Forest algorithm with the best comprehensive detection effect was finally selected for practical engineering projects. In practical engineering projects, maintenance costs can be effectively reduced, project safety and reliability can be improved, and the purpose of improving project efficiency can ultimately be achieved by the proposed method. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Factors Affecting Compensated Capacitor Faults Based on Nonparametric Test Methods 8

Factors Affecting Compensated Capacitor Faults Based on Nonp...

引用

8th International Conference on Electromechanical control Technology and Transportation, ICECTT 2023

作者： Fan, Xiaoxu Kuang, Wenzhen School of Automation and Electrical Engineering Lanzhou Jiaotong University China Gansu Industrial Transportation Automation Engineering Technology Research Center Lanzhou Jiaotong University China Gansu Rail Transit Signal and Control Evaluation Industry Technology Center Lanzhou Jiaotong University China

ISBN: (纸本)9781510668331

Uninsulated track circuits are a key part of the train operation control system, and in uninsulated track circuits, compensation capacitor faults lead to reduced transmission distances due to increased transmission decay. In this paper, the sample nonparametric test method is used to analyze the difference of the compensating capacitor fault samples according to the different carrier frequencies, and the influence of different carrier frequencies on the compensating capacitor faults is excluded. On this basis, the spatiotemporal distribution of the fault capacitor is analyzed, and the main factors affecting the fault of the compensated capacitor are identified. © 2023 SPIE.

关键词： Failure (mechanical)

来源：评论

学校读者我要写书评

暂无评论

Efficient temporal alignment network for smoke detection

Efficient temporal alignment network for smoke detection

引用

2023 Jiangsu Annual Conference on automation, JACA 2023

作者： Li, Weitai Lu, Xiaobo Cao, Yichao School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9781839539848

Smoke is a distinctive feature of pre-fire combustion and it is critical to prevent fires by detecting smoke. Previous work has demonstrated that deep learning methods have a wide range of applications in the field of smoke detection. However, existing methods still have some problems, i.e., it is difficult to balance the relationship between accuracy and speed. In order to solve the existing problems, we proposed Efficient Temporal Alignment Network (ETAN) for Video Smoke Detection. Feature Aggregation Module (FAM) was designed to extract the dynamic features between frames, and we proposed Recursive Memory Feature Update (RMFU) module to maintain the features of past frames and fuse the current features to boost detection performance. Finally, experiments demonstrated that the proposed method improved about 3.8 mAP compared with base detector with little increase in the number of parameters, and outperformed all the single-frame detection methods with the same amount of parameters. Compared with video smoke detection methods, the detection achieved close to the same accuracy while 6.1 times faster than multi-frame methods. © The Institution of engineering & Technology 2023.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Overview on Contact Bounce Phenomena of Electromagnetic Type Switch Electrical Apparatus 11th

Overview on Contact Bounce Phenomena of Electromagnetic Type...

引用

11th Frontier Academic Forum of Electrical engineering, FAFEE 2024

作者： Wang, Zhiyong Zhu, Zhongheng Wang, Xili Zhao, Qi Faculty of Electrical and Control Engineering Liaoning Technical University Huludao125105 China Huludao Jili Industrial Control Automation Technology Co. Ltd. Huludao125001 China Guoneng Nortel Shengli Energy Co. Ltd. Xilingol026000 China

ISBN: (纸本)9789819788156

This article initially presents the working principle of electromagnetic switching devices and the significance of the contact system, distinguishing contact vibration into contact closure bounce and contact release rebound. It emphasizes that these phenomena are crucial factors influencing the lifespan and reliability of electrical devices. Subsequently, through the analysis of domestic and international literature, the paper discusses the academic community's progress in understanding and improving these vibration phenomena. The study shows that closure bounce and release rebound are affected by factors such as structural parameters and the contact engagement method. Notably, scholars have proposed innovative solutions, such as employing the principle of eccentric impact with inclined stationary contacts to suppress closure bounce, and adding limit stop plates between moving and stationary contact leaves to significantly mitigate release rebound, thereby markedly improving the appearance of contact vibration. Finally, the paper summarizes the current state of research on contact vibration in electromagnetic switches, pointing out the deficiencies in existing studies. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

INN: A Deep Correction Network for High-Dynamic Inertial Navigation 4

INN: A Deep Correction Network for High-Dynamic Inertial Nav...

引用

4th International Conference on Industrial automation, Robotics and control engineering, IARCE 2024

作者： Gu, Tao Cong, Li Yang, Jing Guo, Yuzhu Wang, Lina School of Automation Science and Electrical Engineering Beihang University Beijing China School of Electronic Information Beihang University Engineering dept. Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China

ISBN: (纸本)9798350380323

Inertial navigation has gained extensive application because it solely relies on built-in Inertial Measurement Unit (IMU) devices. Nevertheless, due to its inherent accumulative integral error, inertial navigation is often integrated with other external devices in practical situations, which unfortunately leads to unavoidable privacy breaches. To address these issues, an Inertial Navigation Neural Network (INN) is designed to generate high-precision position estimations without relying on any other auxiliary information. The INN model consists of attitude correction and velocity regression modules. The attitude module employs a convolutional network to correct the attitude information, and the obtained rotation matrices are then fed into a recurrent neural network to regress incremental velocities and produce high-precision positions. The proposed model is validated on the simulated trajectories based on the Precise Strapdown Inertial Navigation System (PSINS) toolbox. Experimental studies demonstrated that the proposed method has a significant corrective effect on high-dynamic strapdown inertial navigation settings. The accumulated position errors are an order of magnitude smaller than those of traditional track reckoning algorithms and achieved a comparable performance with integrated navigation. © 2024 IEEE.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

Bearing Remaining Useful Life Prediction Combining Trajectory Similarity and Relevance Vector Machine 41

Bearing Remaining Useful Life Prediction Combining Trajector...

引用

第41届中国控制会议

作者： Zhuyi Li Kesen Fan Cong Zhang Sihang Zhang Yiming Wan Key Laboratory of Image Processing and Intelligent Control Ministry of Education Chinaand School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Beijing Institute of Control Engineering

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Bearing remaining useful life(RUL) prediction is critical for safe operation of rotating *** this paper,we propose a combined RUL prediction approach that leverages both trajectory similarity and relevance vector machine(RVM).The similarity based prediction relies on historical degradation trajectories that are highly similar to the online data,hence would perform poorly if all historical trajectories have low similarity with the online *** RVM based prediction relies solely on a regression model learned from the available online data,thus gives an inaccurate prediction when insufficient data are available in the early stage of degradation.A weighted sum of these above two predictions is proposed to address the limitation of each single prediction method,whose weights are determined by solving a non-negative least squares fitting *** further improve RUL prediction accuracy,we distinguish between fast and slow degradation modes,so that each mode uses a different set of historical degradation trajectories and kernel *** doing so,we predict RUL under the identified *** case study using the PHM2012 dataset demonstrates the effectiveness of the proposed RUL prediction approach.

关键词： Bearing degeneration remaining useful life prediction relevance vector machine trajectory similarity

来源：评论

学校读者我要写书评

暂无评论

Time of flight improved thermally grown oxide thickness measurement with terahertz spectroscopy

引用

Frontiers of Mechanical engineering 2022年第4期17卷 205-215页

作者： Zhenghao ZHANG Yi HUANG Shuncong ZHONG Tingling LIN Yujie ZHONG Qiuming ZENG Walter NSENGIYUMVA Yingjie YU Zhike PENG Fujian Provincial Key Laboratory of Terahertz Functional Devices and Intelligent Sensing School of Mechanical Engineering and AutomationFuzhou UniversityFuzhou 350108China Institute of Precision Instrument and Intelligent Measurement&Control Fuzhou UniversityFuzhou 350108China School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200072China School of Mechanical Engineering Ningxia UniversityYinchuan 750000China

As a nondestructive testing technique,terahertz time-domain spectroscopy technology is commonly used to measure the thickness of ceramic coat in thermal barrier coatings(TBCs).However,the invisibility of ceramic/thermally grown oxide(TGO)reflective wave leads to the measurement failure of natural growth TGO whose thickness is below 10μm in *** detect and monitor TGO in the emergence stage,a time of flight(TOF)improved TGO thickness measurement method is proposed.A simulative investigation on propagation characteristics of terahertz shows the linear relationship between TGO thickness and phase shift of feature *** accurate TOF increment could be acquired from wavelet soft threshold and cross-correlation function with negative effect reduction of environmental noise and system ***,the TGO thickness could be obtained efficiently from the TOF increment of the monitor area with different heating *** averaged error of 1.61μm in experimental results demonstrates the highly accurate and robust measurement of the proposed method,making it attractive for condition monitoring and life prediction of TBCs.

关键词： thermal barrier coatings thermally grown oxide terahertz spectroscopy time of flight

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heat Load of Thermal Station Based on Neural Network 24

Prediction of Heat Load of Thermal Station Based on Neural N...

引用

6th International Conference on control and Computer Vision, ICCCV 2024

作者： Zhu, Xinying Geng, Liqing Yang, Genghuang Huo, Yang Xu, Shiyuan Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin University of Technology and Education School of Automation and Electrical Engineering Tianjin University of Technology and Education China Co. Ltd China

ISBN: (纸本)9798400718045

To solve the problem of improving the prediction accuracy of thermal station, multi-strategy fusion Sparrow Search Algorithm to optimize the Neural Network prediction method. First, the acquired data is preprocessed to ensure the continuity of the data;second, the Pearson Correlation Coefficient method is used to determine the input feature variables and construct the data set through the data;and finally, Sparrow Search Algorithm and multi-strategy fusion Sparrow Search Algorithm respectively optimizes Back Propagation Neural Network and Long Short-Term Memory Neural Network models for heat supply prediction. After example verification and comparison, the multi-strategy fusion Sparrow Search Algorithm optimizes the Back Propagation Neural Network model with the minimum prediction error, which effectively improves the prediction accuracy. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Design and research of GIS bushing with 72.5kV environmental protection gas insulationper Title 4

Design and research of GIS bushing with 72.5kV environmental...

引用

4th International Conference on Electrical engineering and control Science, IC2ECS 2024

作者： Zhao, Jing Zhou, Yichen Chen, Zhikun Tu, Di School of Electrical Engineering and Automation Xiamen University of Technology Xiamen China Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control Xiamen China Electric Group Xiamen China

ISBN: (纸本)9798331510107

Aiming at the 72.5 kV metal-enclosed combination electrical appliance (GIS) in which the bushing is prone to local discharge and discharge along the surface, a bushing optimization design method is proposed. Firstly, the dry air insulated GIS bushing model in the paper follows the SF6 gas insulated bushing model and carries out electric field simulation calculations on it, and the simulation results show that the electric field distribution is not uniform at the high-voltage end of the shielding cover and the outer surface of the epoxy resin and there is a high electric field in the local area, which is 20.03 kV/mm and 7.94 kV/mm, respectively, and it can not satisfy the dry air insulation. Secondly, two structural optimization schemes are proposed for the existence of high electric field: optimizing the structure of bushing high-voltage end shielding cover;proposing to add grounded shielding net inside the bushing, and analyzing the influence of the shielding net length in the range of 30-80mm on the electric field distribution of the bushing. The two optimization schemes reduce the electric field of the high-voltage end shield and the outer surface of epoxy resin to 10.60kV/mm and 4.84kV/mm respectively, and the maximum field strength of the epoxy resin casting body is lower than that of the epoxy resin with a maximum endurance strength of 30kV/***, the optimized bushing is subjected to the frequency withstand voltage test, partial discharge test and the lightning impact investigative test, and the results of which show that the bushing meets the design requirements. The test results show that the bushing meets the design requirements.t. © 2024 IEEE.

关键词： Bushings

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition in Chinese Medical Texts Based on RoBERTa-WWM-IDCNN-CRF 25

Named Entity Recognition in Chinese Medical Texts Based on R...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Tang, Lan Kong, Jie Xu, Liang Xi'an Shiyou University School of Computer Xi'an China Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical Engineering and Automation Tianjin China

ISBN: (纸本)9798350366600

Electronic medical records and doctor-patient conversations contain a wealth of useful information, such as disease symptoms, drug names, and cure cycles. Traditional deep learning approaches utilize bidirectional recurrent neural networks to encode text, which cannot effectively capture long-distance dependencies in text. In order to identify medical entity types in various texts more accurately, a named entity recognition approach based on RoBERTa-WWM-IDCNN-CRF is proposed. This approach introduces the RoBERTa-WWM pre-trained model, in order to improve the overall understanding of long Chinese texts for the first time. The model generates semantic representations containing prior knowledge. Then, the generated semantic representations are feed to the IDCNN to extract sentence level characteristics. Finally, the global optimal solution is obtained and the results of the named entity are produced through the CRF. The experiment indicates that the improvement of F1 score, accuracy, and recall of RoBERTa-WWM-IDCNN-CRF model are 7.94%, 4.52% and 10.02% comparing with the classical BiLSTM-CRF model. © 2024 IEEE.

关键词： Convolutional neural networks

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：