检索结果-南通市图书馆

Convolution-Transformer for Image Feature Extraction

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in engineering & Sciences 2024年第10期141卷 87-106页

作者： lirong Yin Lei Wang Siyu Lu Ruiyang Wang Youshuai Yang Bo Yang Shan liu Ahmed AlSanad Salman A.AlQahtani Zhengtong Yin Xiaolu li Xiaobing Chen Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA school of automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resources and Environmental engineering Key Laboratory of Karst Georesources and Environment(Guizhou University)Ministry of EducationGuiyang550025China school of Geographical Sciences Southwest UniversityChongqing400715China school of electrical and Computer engineering Louisiana State UniversityBaton RougeLA70803USA

This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.

关键词： Transformer E-Attention depth convolution dilated convolution CEFormer

Robust adaptive output feedback control of nonlinearly parameterized systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of electrical and Electronic engineering in china 2007年第3期2卷 282-287页

作者： liu Yusheng li xingyuan school of electrical engineering and Information Science Sichuan UniversityChengdu 610065China

The ideas of adaptive nonlinear damping and changing supply functions were used to counteract the effects of parameter and nonlinear uncertainties,unmodeled dynamics and unknown bounded *** high-gain observer was used to estimate the state of the system.A robust adaptive output feedback control scheme was proposed for nonlinearly parameterized systems represented by input-output *** scheme does not need to estimate the unknown parameters nor add a dynamical signal to dominate the effects of unmodeled *** is proven that the proposed control scheme guarantees that all the variables in the closed-loop system are bounded and the mean-square tracking error can be made arbitrarily small by choosing some design parameters *** results have illustrated the effectiveness of the proposed robust adaptive control scheme.

关键词： nonlinearly parameterized systems adaptive control output feedback unmodeled dynamics robustness stability

Consensus of Multi-Agent Systems with General linear Dynamics and Reduced-Order Protocols

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Consensus of Multi-Agent Systems with General Linear Dynamic...

Finite-time fault-tolerant control of teleoperating cyber physical system against faults

第三十届中国控制会议

作者： li Zhongkui~1,liu Xiangdong~1,liN Peng~2,REN Wei~3 1.school of automation,Beijing Institute of Technology,Beijing 100081,P.R.china 2.Institute of Astronautics and Aeronautics,university of Electronics Science and Technology of china, chengdu 610054,P.R.china 3.Department of electrical and Computer engineering,Utah State university,Logan,UT 84322,USA

＜正＞This paper considers the consensus problems for both continuous- and discrete-time linear multi-agent systems with directed communication *** reduced-order observer-based consensus protocols are proposed,based on the relative outputs of neighboring agents.A multi-step algorithm is presented to construct a reduced-order protocol,under which a continuous-time multi-agent system whose communication topology contains a directed spanning tree can reach *** algorithm has a favorable decoupling *** light of the modified algebraic Riccati equation,an algorithm is then given to construct a reduced-order protocol for the discrete-time case.

关键词： Multi-agent system Consensus Reduced-order protocol

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2023年第2期34卷 469-478页

作者： PAN Chengwei liu Xia CHEN Yong li Meng school of automation engineering University of Electronic Science and Technology of ChinaChengdu 611731China Institute of Electric Vehicle Driving System and Safety Technology University of Electronic Science and Technology of ChinaChengdu 611731China school of electrical engineering and Electronic Information Xihua UniversityChengdu 610039China

This paper studies a finite-time adaptive fractionalorder fault-tolerant control(FTC)scheme for the slave position tracking of the teleoperating cyber physical system(TCPS)with external disturbances and actuator *** on the fractional Lyapunov stability theory and the finite-time stability theory,a fractional-order nonsingular fast terminal sliding mode(FONFTSM)control law is proposed to promote the tracking and fault tolerance performance of the considered ***,the adaptive fractional-order update laws are designed to cope with the unknown upper bounds of the unknown actuator faults and external ***,the finite-time stability of the closed-loop system is ***,comparison simulation results are also provided to show the validity and the advantages of the proposed techniques.

关键词： teleoperating cyber physical system(TCPS) fractional Lyapunov stability fault-tolerant control(FTC) finite-time stability

基于去噪扩散概率模型的水⁃光互补系统随机场景生成方法

在线全文

学校读者我要写书评

暂无评论

电力系统自动化 2024年第19期48卷 171-180页

作者：杨震杨晶显王凯李玉梅刘俊勇张帅西北民族大学电气工程学院甘肃省兰州市730030 西北民族大学双碳创新技术研究院甘肃省兰州市730030 四川大学电气工程学院四川省成都市610065 国网四川省电力公司四川省成都市610041

随着水-光互补系统应用越来越广泛,准确地描述水-光出力的不确定性对电网的运行和规划具有重要影响。现有多源融合特性建模方法不仅存在考虑可再生能源出力时空相关性不充分的问题,而且在实际复杂应用环境下要进行先验假设,进而导致生... 详细信息

随着水-光互补系统应用越来越广泛,准确地描述水-光出力的不确定性对电网的运行和规划具有重要影响。现有多源融合特性建模方法不仅存在考虑可再生能源出力时空相关性不充分的问题,而且在实际复杂应用环境下要进行先验假设,进而导致生成质量降低。基于此,文中提出了基于去噪扩散概率模型的水-光互补系统随机场景生成方法。首先,将结合欧氏距离和L2正则化的损失函数作为衡量生成噪声与原始噪声分布差异的标准,并设计适应水-光-荷随机场景生成的UNet网络结构;然后,通过对前向过程不断加噪和逆向过程不断去噪训练,捕捉水-光-荷多维变量相关性变化及波动特征,拟合其概率分布规律;最后,对多源数据协同建模,高效生成水-光互补系统随机场景。文中算例基于某地区电网实际采集数据进行测试,通过综合评估指标验证了所提方法的有效性。

关键词：场景生成去噪扩散概率模型水-光互补系统多源

直流闭锁引起的暂态过电压计算方法及其影响因素分析

在线全文

学校读者我要写书评

暂无评论

电网技术 2016年第10期40卷 3059-3065页

作者：王峰刘天琪丁媛媛曾琦李兴源四川大学电气信息学院四川省成都市610065

高压直流系统闭锁引起的暂态过电压对输电设备及系统稳定性均产生巨大冲击,目前,相关研究缺乏定量的分析方法。针对该问题,首先提出了一种计及系统稳态传输功率的交流系统等值方法,从而得到交流系统的2个重要参数(即等值电抗和等值电势... 详细信息

高压直流系统闭锁引起的暂态过电压对输电设备及系统稳定性均产生巨大冲击,目前,相关研究缺乏定量的分析方法。针对该问题,首先提出了一种计及系统稳态传输功率的交流系统等值方法,从而得到交流系统的2个重要参数(即等值电抗和等值电势)。在此基础上,考虑暂态过程中换流站剩余无功容量及其补偿容量随电压升高的特性,推导了换流母线暂态电压的解析表达式,从而得到了暂态过电压的定量计算方法,并分析了其影响因素。研究表明,系统强度越弱,暂态电压越高,而且随着闭锁容量的增加,暂态过电压呈非线性上升趋势,而闭锁容量和等值电势与暂态过电压呈负相关关系。基于BPA的南方电网2030年规划数据仿真分析验证了所提方法的正确性和有效性。

关键词：高压直流暂态过电压短路比影响因素故障分析机理分析

风火打捆外送系统次同步振荡的改进自抗扰直流附加阻尼控制

在线全文

学校读者我要写书评

暂无评论

电力自动化设备 2018年第11期38卷 174-180页

作者：毕悦刘天琪赵磊李兴源顾雨嘉四川大学电气信息学院四川成都610065 国网江苏电力公司电力科学研究院江苏南京210000 国网宁夏电力公司电力科学研究院宁夏银川750011

针对送端电网大规模风电接入可能加剧火电机组次同步振荡的问题,提出一种基于改进遗传算法的自抗扰附加阻尼控制方法。利用基于总体最小二乘法-旋转不变技术的信号参数估计(TLS-ESPRIT)算法对系统进行次同步振荡特性辨识,根据主模比指... 详细信息

针对送端电网大规模风电接入可能加剧火电机组次同步振荡的问题,提出一种基于改进遗传算法的自抗扰附加阻尼控制方法。利用基于总体最小二乘法-旋转不变技术的信号参数估计(TLS-ESPRIT)算法对系统进行次同步振荡特性辨识,根据主模比指标选择合适的控制反馈信号,得到系统在次同步频段内各振荡模式对应的低阶传递函数;结合时间乘绝对误差积分准则(ITAE)指标与极大极小值原理确定被控系统控制目标,并利用改进遗传算法寻优确定多通道自抗扰控制器参数。在PSCAD上搭建含大规模风电的测试系统模型,仿真结果表明基于改进自抗扰控制的附加次同步阻尼控制器在送端电网多种运行方式和不同故障情况下都能有效抑制汽轮发电机组的次同步振荡,鲁棒性较强,同时低阶自抗扰控制器也具有令人满意的控制效果。

关键词：风火打捆次同步振荡自抗扰控制改进遗传算法附加次同步阻尼控制器

Systematic protective scheme for mega‐city power systems against stray currents caused by metro systems

在线全文

学校读者我要写书评

暂无评论

High Voltage 2023年第5期8卷 943-953页

作者： Yujun Guo Qing Du Yijie liu Feng Yang Lu Chen Xueqin Zhang Song Xiao Chunmao li Guangning Wu The school of electrical engineering Southwest Jiaotong UniversityChengduChina The State Grid Shanghai Electric Power Research Institute ShanghaiChina

In modern megacities,stray currents from metro systems intrude into multiple transformers'neutral points becoming a potential threat to the high‐capacity *** current anomalies are exacerbated in unprotected substations when we instal guards at single *** paper presents a system protection strategy for multiple substations affected by stray currents in modern *** model,taking Shanghai as an example,includes the spatial distribution information of the urban electrical energy transmission structure,the power system,and the metro system.A Particle swarm algorithm is used to calculate the resistance values of the devices for each *** stability tests are performed to select the optimal protection *** results show that when protection is considered as a system,the protection runs well and the neutral current level remains below the unprotected level when the protection fails at a single station or multiple stations.

关键词： protected neutral protective

Study of degradation of fuel cell stack based on the collected high-dimensional data and clustering algorithms calculations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

能源与人工智能(英文) 2022年第4期10卷 29-40页

作者： Tong Niu Weifeng Huang Caizhi Zhang Tao Zeng Jiawei Chen Yu li Yang liu College of mechanical and vehicle engineering The State Key Laboratory of Mechanical TransmissionsChongqing Automotive Collaborative Innovation CentreChongqing UniversityChongqing 400044China school of electrical engineering Chongqing UniversityChongqing 400044China Propulsion Research Institute of Chongqing Changan New Energy Vehicle Technology Co. LtdChongqingChina school of automation Chongqing UniversityChongqing 400044China Institute of Sustainable Energy/College of Sciences Shanghai universityShanghai 200444China sichuan Energy Internet Research Institute Tsinghua UniversityChengduSichuan 610213China Shaoxing Institute of Technology Shanghai UniversityShaoxingZhejiang 312000China

Accurate perception of the performance degradation of fuel cell is very important to detect its health ***,inconsistent operating conditions of fuel cell vehicles in the test result in errors in the *** order to obtain a more credible degradation rate,this study proposes a novel method to classify the experimental data collected under different working conditions into similar operating conditions by using dimensionality reduction and clustering ***,the experimental data collected from fuel cell vehicles belong to high-dimensional *** projecting high-dimensional data into three-dimensional feature vector space via principal component analysis(PCA).The dimension-reduced three-dimensional feature vectors are input into the clustering algorithm,such as K-means and density-based noise application spatial clustering(DBSCAN).According to the clustering results,the fuel cell voltage data with similar operating conditions can be ***,the selected voltage data can be used to precisely represent the true performance degradation of an on-board fuel cell *** results show that the voltage using the K-means algorithm declines the fastest,followed by the DBSCAN algorithm, finally the original data, which indicates that the performance of the fuel cell actually declines faste. Early intervention can prolong its life to the greatest extent.

关键词： Fuel cell vehicle Principal component analysis Clustering algorithms Degradation of fuel cell