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： Pan, Hongyu Xie, Chuan Zou, Jianxiao University of Electronic Science and Technology of China School of Automation Engineering Chengdu China

ISBN: (纸本)9798350351330

The repetitive controller (RC), owing to the capability of zero-error tracking periodical signals, is widely used to compensate for harmonics in the grid. Compared with Conventional RC, by eliminating specific order harmonics for different application scenarios, selective harmonic repetitive controller (SHRC) can simultaneously achieve high control accuracy and less computation burden. As SHRC is sensitive to frequency variations, it is improved to frequency adaptive SHRC (FA-SHRC) via adding filters to approximately compensate fractional-order delays caused by frequency variations. However, the external stability of FA-SHRC remains a problem. In the article, a detailed passivity-based designed approach of FA-SHRC is proposed. The proposed method can tune the impedance of the inverter with FA-SHRC passive for the full frequency range, which ensures the system is stable, dynamic, and adaptive regardless of grid impedance and frequency variations. Finally, experiments are performed to validate the superiority of the approach for designing FA-SHRC. © 2024 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Quantitative algorithm for airborne gamma spectrum of large sample based on improved shuffled frog leaping-particle swarm optimization convolutional neural network

引用

Nuclear Science and Techniques 2023年第7期34卷 242-252页

作者： Fei Li Xiao-Fei Huang Yue-Lu Chen Bing-Hai Li Tang Wang Feng Cheng Guo-Qiang Zeng Mu-Hao Zhang College of Nuclear Technology and Automation Engineering Chengdu University of TechnologyChengdu 610000China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu 610000China Airborne Survey and Remote Sensing Center of Nuclear Industry Shijiazhuang 050000China Hebei Key Laboratory of Airborne Detection and Remote Sensing Technology Shijiazhuang 050000China

In airborne gamma ray spectrum processing,different analysis methods,technical requirements,analysis models,and calculation methods need to be *** meet the engineering practice requirements of airborne gamma-ray measurements and improve computational efficiency,an improved shuffled frog leaping algorithm-particle swarm optimization convolutional neural network(SFLA-PSO CNN)for large-sample quantitative analysis of airborne gamma-ray spectra is proposed *** method was used to train the weight of the neural network,optimize the structure of the network,delete redundant connections,and enable the neural network to acquire the capability of quantitative spectrum *** full-spectrum data processing,this method can perform the functions of energy spectrum peak searching and peak area *** network training,the mean SNR and RMSE of the spectral lines were 31.27 and 2.75,respectively,satisfying the demand for noise *** test the processing ability of the algorithm in large samples of airborne gamma spectra,this study considered the measured data from the Saihangaobi survey area as an example to conduct data spectral *** results show that calculation of the single-peak area takes only 0.13~0.15 ms,and the average relative errors of the peak area in the U,Th,and K spectra are 3.11,9.50,and 6.18%,indicating the high processing efficiency and accuracy of this *** performance of the model can be further improved by optimizing related parameters,but it can already meet the requirements of practical engineering *** study provides a new idea for the full-spectrum processing of airborne gamma rays.

关键词： Large sample Airborne gamma spectrum(AGS) Shuffled frog leaping algorithm(SFLA) Particle swarm optimization(PSO) Convolutional neural network(CNN)

来源：评论

学校读者我要写书评

暂无评论

Hybrid Centralized-Decentralized Economic Dispatch Based on a Distributed Finite-Step Consensus Algorithm with Divided Regional Incremental Costs 14

Hybrid Centralized-Decentralized Economic Dispatch Based on ...

引用

14th International Conference on Information Science and technology, ICIST 2024

作者： Zhang, Hanwen Yang, Hanqing Li, Tieshan Long, Yue School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350353334

The economic dispatch problem of power systems, which is typically based on multi-agent networks, often necessitates conditions like full graph connectivity. However, as the scale of power systems expands, maintaining full graph connectivity in communication systems could result in increased costs and communication burdens. Consequently, this paper investigates a distributed finite-step c o nsensus m e thod t h at incorporates geographical region division, aiming to achieve economical power allocation without the need for full graph connectivity. In this method, we initially derive a Laplace matrix from the distributed topology of generators in multi-agent power systems. Subsequently, we construct another Laplace matrix by geographically dividing regions, thereby illustrating the communication relationships between these regions. Subsequently, we calculate the incremental cost of each region, taking into account the power constraints of the generators. Moreover, to expedite convergence, we employ a distributed finite-step c o nsensus algorithm to address the economic dispatch problem, leveraging the divided regional incremental costs. Finally, we validate the effectiveness and accuracy of the proposed method through results on various multi-agent topologies and comparisons with other iterative algorithms. © 2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Study of Current Distribution Characteristics of Automotive Fuel Cells with High-resolution Segmented Measurement Device 11

Study of Current Distribution Characteristics of Automotive ...

引用

11th International Conference on Power and Energy Systems engineering, CPESE 2024

作者： Shi, Chengyin Chen, Junxiong Song, Yating Tang, Hao University of Electronic Science and Technology of China School of Automation Engineering Chengdu China

ISBN: (纸本)9798350377439

Proton exchange membrane fuel cell (PEMFC) has the advantages of low operating temperature, fast start-up, high power density, etc., which has a wide application prospect in the field of automotive power. The fuel cell performance can be analyzed under different current densities by using the zonal current collection detection technique. However, the existing method has low resolution and cannot accurately reflect the current distribution inside the automotive fuel cell stack. In this paper, a high-resolution segmented measurement device with 396 points is used to experimentally test the local current density distribution characteristics of a 406 cm2 automotive fuel cell during a stepwise increase in load current, and the results are presented in three-dimensional data. The experimental results show that when the load current is 0.1 A/cm2, the current density at the hydrogen inlet is significantly higher than that at the oxygen inlet, with the highest current density of 0.154 A/cm2 and the lowest of 0.0489 A/cm2;when the load current is 0.6A/cm2, the current density at the oxygen inlet is higher than that at the hydrogen inlet, with the highest current density of 0.926 A/cm2 and the lowest current density of 0.375 A/cm2 with a difference of 0.551 A/cm2. The precise analysis of the current density distribution characteristics using the high-resolution segmented current collection measurement technique is of great importance in studying the control strategy of the fuel cell system and diagnosing the failure. © 2024 IEEE.

关键词： Automotive fuels

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Evaluation-Denoising Network for Motion Artifacts Removal from Single-Channel EEG 46

A Dynamic Evaluation-Denoising Network for Motion Artifacts ...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Li, Zhe Shi, Kecheng Li, Wenjiang Mu, Fengjun Zhang, Jingting Huang, Rui Cheng, Hong University of Electronic Science and Technology of China The School of Automation Engineering Chengdu China

ISBN: (纸本)9798350371499

Brain-computer interfaces (BCIs) have gained significant attention in rehabilitation research as a critical step in investigating neural remodeling techniques. However, most existing methods usually overlook the randomness and diversity of motion artifacts, thereby lacking the desired generalization ability and denoising precision, which limits their practical application. To address these limitations, we propose a Dynamic Evaluation Denoising Network (DED-Net) that incorporates an evaluation model with cross-domain feature fusion for artifact detection and classification. Then dynamically selecting Bidirectional Long Short-Term Memory (Bi-LSTM) networks with varying parameters for artifact removal, which achieves superior performance compared to state-of-the-art methods. Our experiment on a semi-simulated dataset constructed by EEGdenoiseNET demonstrates that the performance of DED-Net is advanced over the state-of-the-art method, i.e., SDNet, in terms of the signal-to-noise rate (SNR) and correlation coefficient (CC). Using our method, SNR and CC are 6.0597 dB and 95.28%, respectively increasing by 20.48% and 3.15%. Experiments on real EEG data demonstrate the superior performance of the proposed method in reconstructing EEG signals, in terms of the intent recognition tasks, achieving a remarkable accuracy of 88.89%, outperforming other methods. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Joint Spatial Similarity-based Attention for Retina Vessel Segmentation with Super Resolution Encoding 4

Joint Spatial Similarity-based Attention for Retina Vessel S...

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Cai, Jingye University of Electronic Science and Technology of China Information and Software Engineering Chengdu China Chengdu University of Technology Nuclear Technology and Automation Engineering Chengdu China

ISBN: (纸本)9798350324303

Machine learning methods based on fully convolutional networks have emerged as a viable choice for retinal vessel segmentation. However, when input samples significantly deviate from the training data distribution, these deep networks fail silently, posing serious challenges for automatic data processing pipelines. In our study, we question the effectiveness of randomly selecting unlabeled training target images for annotation and inclusion in the support set, as it may not facilitate an efficient fine-Tuning process. We propose a novel method to optimize the image selection procedure to address this. By utilizing our method, we can identify informative unlabeled target images by comparing the consistency of model predictions on these images under specific data augmentations. However, it should be noted that the model developed using the source datasets cannot accurately evaluate consistency on the target images. To overcome this issue, we suggest employing self-supervised pretext tasks to compute scores for unlabeled target images, resolving this limitation. The top few images with the lowest consistency scores can then be added to the support set and annotated by experts to fine-Tune the model for the target images. We introduce an upgraded encoder-decoder model which outperforms multi-scale prediction ensembling to address insufficient single-scale base learners. This paper proposes a novel module that uses joint spatial and channel attention and an auxiliary prototype similarity operation to enhance border localization and super-resolution in the encoder-decoder architecture. To evaluate the performance of our approach, we conducted experiments on two distinct datasets, integrating our joint spatial/channel attention-based module with auxiliary prototype similarity operation for super-resolution encoding. Our empirical results demonstrate the superiority of our proposed model over state-of-The-Art attention mechanisms used in super-resolution. © 2023 IEEE.

关键词： Decoding

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 3

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

引用

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

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

ISBN: (纸本)9798350333862

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. © 2023 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Structural Design and Analysis of a Bionic Metacellular Robot Chassis 7

Structural Design and Analysis of a Bionic Metacellular Robo...

引用

2022 7th International Seminar on Computer technology, Mechanical and Electrical engineering, ISCME 2022

作者： Yang, Peijie Yang, Jian Yang, Jiaxin Liu, Li Peng, Yujie Chen, Jianwei Zhang, Bei Nie, Xuan Tian, Yingyu Sang, Ziyang School of Mechanical and Electrical Engineering Chengdu University of Technology China College of Nuclear Technology and Automation Engineering Chengdu University of Technology China

Aiming at the problems of lack of stability, poor adaptability, and weak load capacity of existing robots in complex environments. The corresponding adaptation methods are proposed through the analysis of various harsh environments in nature, and statistics are made. On this basis, a new type of metamorphic structure based on metamorphic theory and bionics principle is proposed, and the relevant mechanical structure of the chassis of the metamorphic robot is designed;The mechanical system and motion are designed, optimized, and analyzed by using Solidworks and MATLAB joint simulation platform;The motion planning and kinematics simulation of the bionic metamorphic robot chassis are carried out through ADAMS software;Stress simulation of loaded parts is carried out based on ANSYS. The results show that the design size and motion planning are reasonable and meet the bionic metamorphic robot chassis requirements for working environment and grasping operation. © Published under licence by IOP Publishing Ltd.

关键词： Bionics

来源：评论

学校读者我要写书评

暂无评论

Sub-Classification and Type Identification of Weathering Silicate Glasses Based on Spectral Clustering

Sub-Classification and Type Identification of Weathering Sil...

引用

2023 International Conference on Computational and Mathematical Methods in engineering, CMME 2023

作者： Xie, Kunshuo Tang, Ge Lu, Boyu Liu, Hao Wang, Linlin College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

Ancient glass products are often weathered to varying degrees after excavation. Detection and analysis of their chemical composition will help to study the ancient glass making process. In this paper, we take a group of ancient glass products as samples, and study the sub-classification and type identification of weathered silicate glasses. Firstly, we identify the main factor of glass weathering through chi-squared test and Fisher's exact test, then conduct a significance test on the basis of preprocessing various data of glass cultural relics. Secondly, the glass samples are classified into high potassium glass and lead barium glass by spectral clustering method, and further sub-classified into eight classes. The sub-classes are named based on feature extraction, and the clustering quality is tested by contour coefficient. Finally, we analyze the chemical composition affecting the glass types by combining the non-parametric tests to identify the types of glass cultural relics by multiple linear regression with significance testing. In addition, correlation test, spectral clustering and multiple linear regression are used to study the sub-classification and type identification of weathered silicate glasses, which provides a reference for further study of ancient glass making process and weathering process. © Published under licence by IOP Publishing Ltd.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Design of Upper Limb Posture Detection and Trajectory Matching Based on Motion Capture 8

Design of Upper Limb Posture Detection and Trajectory Matchi...

引用

8th International Conference on Electromechanical Control technology and Transportation, ICECTT 2023

作者： Wang, Linlin Li, Siyi Liu, Hao Xie, Kunshuo College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China College of Mechanical and Electrical Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9781510668331

As biomechanics research evolves, the significance of motion capture technology in domains like film and television, gaming, and motion training is progressively gaining prominence, with an expanding repertoire of applications. Optical motion capture, employing optical dynamic capture equipment founded on a 3D imaging analysis system within a specified setting, stands as the most mature technique. However, its high cost and constraints pertaining to venue and environmental factors limit its usage. Conversely, inertial motion capture devices, functional under non-optical conditions, can cater to the needs of the broader public. To further enhance affordability, portability, and simplification of the device, this study proposes an embedded system design grounded on a nine-axis inertial sensor. It captures the posture of each joint in the human upper limb and wirelessly transmits the data to the Unreal Engine 3D arm model for action replication and motion trajectory delineation. Thus, it generates feedback results facilitating remote motion control. © 2023 SPIE.

关键词： Engines

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：