期刊文献+
共找到2,483篇文章
< 1 2 125 >
每页显示 20 50 100
Development of a Medium Voltage, High Power, High Frequency Four-Port Solid State Transformer 被引量:4
1
作者 Ahmad El Shafei Saban Ozdemir +2 位作者 Necmi Altin Garry Jean-Pierre Adel Nasiri 《CES Transactions on Electrical Machines and Systems》 CSCD 2022年第1期95-104,共10页
The power and voltage levels of renewable energy resources is growing with the evolution of the power electronics and switching module technologies.For that,the need for the development of a compact and highly efficie... The power and voltage levels of renewable energy resources is growing with the evolution of the power electronics and switching module technologies.For that,the need for the development of a compact and highly efficient solid-state transformer is becoming a critical task in-order to integrate the current AC grid with the new renewable energy systems.The objective of this paper is to present the design,implementation,and testing of a compact multi-port solid-state transformer for microgrid integration applications.The proposed system has a four-port transformer and four converters connected to the ports.The transformer has four windings integrated on a single common core.Thus,it can integrate different renewable energy resources and energy storage systems.Each port has a rated power of 25 kW,and the switching frequency is pushed to 50 k Hz.The ports are chosen to represent a realistic industrial microgrid model consisting of grid,energy storage system,photovoltaic system,and load.The grid port is designed to operate at 4.16 k VAC corresponding to 7.2 kV DC bus voltage,while the other three ports operate at 500 VDC.Moreover,the grid,energy storage and photovoltaic ports are active ports with dual active bridge topologies,while the load port is a passive port with full bridge rectifier one.The proposed design is first validated with simulation results,and then the proposed transformer is implemented and tested.Experimental results show that the designed system is suitable for 4.16 k VAC medium voltage grid integration. 展开更多
关键词 CO-SIMULATION high frequency high power medium voltage MICROGRID MULTI-PORT solid state transformer
在线阅读 下载PDF
Modeling and Control of the Modular Multilevel Converter (MMC) based Solid State Transformer (SST) with Magnetic Integration 被引量:1
2
作者 Gengzhe Zheng Yu Chen Yong Kang 《CES Transactions on Electrical Machines and Systems》 CSCD 2020年第4期309-318,共10页
Solid state transformer(SST)can provide more advanced functionalities compared with conventional transformer,and has great potential in smart grid application.Recently,the SST with medium frequency(MF)isolation link a... Solid state transformer(SST)can provide more advanced functionalities compared with conventional transformer,and has great potential in smart grid application.Recently,the SST with medium frequency(MF)isolation link and magnetic integration feature has been proposed,which can reduce the system volume and thus increase the power density.However,the magnetic integration also introduces strong coupling between the line frequency(LF)and MF variables,which poses a great challenge on modeling and control issues.This paper proposes a modeling and control method for an SST with magnetic integration and mixed-frequency modulation.A mathematical model based on dual d-q references is deduced,and then a cascaded control system is designed according to the model.Parameters of the controller for the variables at one frequency are properly designed to avoid disturbance from the variables at the other frequency.The simulation and experimental results show good decoupling effect and satisfactory dynamics performance of the proposed control system. 展开更多
关键词 solid state transformer(SST) modular multilevel converter(MMC) control system mathematical model
在线阅读 下载PDF
Sliding mode control of solid state transformer using a three-level hysteresis function
3
作者 刘宝龙 査亚兵 张涛 《Journal of Central South University》 SCIE EI CAS CSCD 2016年第8期2063-2074,共12页
The solid state transformer(SST) can be viewed as an energy router in energy internet. This work presents sliding mode control(SMC) to improve dynamic state and steady state performance of a three-stage(rectifier stag... The solid state transformer(SST) can be viewed as an energy router in energy internet. This work presents sliding mode control(SMC) to improve dynamic state and steady state performance of a three-stage(rectifier stage, isolated stage and inverter stage) SST for energy internet. SMC with three-level hysteresis sliding functions is presented to control the input current of rectifier stage and output voltage of inverter stage to improve the robustness under external disturbance and parametric uncertainties and reduce the switching frequency. A modified feedback linearization technique using isolated stage simplified model is presented to achieve satisfactory regulation of output voltage of the isolated stage. The system is tested for steady state operation, reactive power control, dynamic load change and voltage sag simulations, respectively. The switching model of SST is implemented in Matlab/ Simulink to verify the SST control algorithms. 展开更多
关键词 solid state transformer(SST) energy internet sliding mode control(SMC) feedback linearization three-level hysteresis
在线阅读 下载PDF
STATE TRANSFORMATION PROCESSES FOR FREE-FLOATING THREE-LINK PLANAR ROBOTS 被引量:1
4
作者 XuMingtao XuYangsheng JamesK.Mills 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2004年第2期166-169,共4页
The transformation process of an m-DOF free-floating robot from one staticstate to a different static state has m degrees of freedom. The proposed approach of thesetransformations utilizes a series of single-DOF trans... The transformation process of an m-DOF free-floating robot from one staticstate to a different static state has m degrees of freedom. The proposed approach of thesetransformations utilizes a series of single-DOF transformation processes as an alternative to them-DOF transformation process. Two static state transformation processes are studied in detail.First, a single-DOF transformation process is established using a newly defined concept, referred toas transformation planning, and the definite integral of conservation of angular momentum. Second,the governing equation of the single-DOF transformation process is established using the dynamicequations of motion of the robot. This allows the joint torques to be computed to effect the statetransformation. Finally, an extension of the single-DOF transformation process is proposed to extendthe application of this proposed transformation methodology to create a transformation net whichallows the reconfiguration of a robot from one state to many other possible states. 展开更多
关键词 Planar robot Static state Single-DOF transformation process n-elementtransformation net
在线阅读 下载PDF
Experimental Evidence of Reversible Crystalline State Transformation of 2,2':6',2"-Terpyridine: Visualization and Seed Effect
5
作者 Masaaki Yokota Atsushi Ito Norihito Doki 《Advances in Chemical Engineering and Science》 2015年第4期484-489,共6页
We have succeeded in causing reversible polymorphic transformation of 2,2':6',2"-terpyridine (terpy). By contacting a template terpy crystal with the target crystal, reversible orthorhombic-to-monoclinic ... We have succeeded in causing reversible polymorphic transformation of 2,2':6',2"-terpyridine (terpy). By contacting a template terpy crystal with the target crystal, reversible orthorhombic-to-monoclinic transformation occurred directly without via melting state. The transformation process is successfully visualized and it is found that the template crystal influences the transition temperature itself. 展开更多
关键词 CRYSTALLIZATION POLYMORPHISM SOLID-state transformation TERPYRIDINE
在线阅读 下载PDF
Development of medium voltage single-phase solid-state transformer for high-speed railway vehicles:Reduced scale verification results
6
作者 Dong-Uk Kim Jin-Hyuk Park +1 位作者 Seung-Hwan Lee Sungmin Kim 《High Voltage》 2025年第3期555-569,共15页
This paper presents a high-power-density solid-state transformer(SST)designed for 25 kV alternative current railway applications,delivering a 3 kV direct current output to traction inverters.The SST is composed of sub... This paper presents a high-power-density solid-state transformer(SST)designed for 25 kV alternative current railway applications,delivering a 3 kV direct current output to traction inverters.The SST is composed of sub-modules with the adoption of 1.7 kV insulated gate bipolar transistor and SiC metal oxide field effect transistor(MOSFET)in an input-series-output-series structure,providing higher power density than conventional topologies that rely on high-voltage switches(>1.7 kV).Because these high-voltage SiC MOSFETs are still expensive and not fully commercialised,the proposed approach offers a more cost-effective alternative.A total of 42 converter cells ensure a highly modular and scalable design,with precise synchronisation and high-speed control achieved through an EtherCAT-based communication network.Additionally,a distributed control algorithm is introduced,mitigating excessive dependence on the communication link for module-level operations.The effectiveness of the entire system-including the design and control schemes-has been experimentally verified,ranging from individual converter cells to a reduced SST prototype of up to three sub-modules.These results confirm the feasibility and advantages of the proposed SST in terms of power density,cost efficiency and reliability for railway traction applications. 展开更多
关键词 gate bipolar transistor kv igbt distributed control sic metal oxide field effect transistor mosfet ETHERCAT solid state transformer high power density sic mosfet
在线阅读 下载PDF
基于KPCA与NRBO-Transformer的锂电池健康状态评估方法
7
作者 刘富强 刘为国 +2 位作者 朱洪波 胡凯 马旭东 《重庆理工大学学报(自然科学)》 北大核心 2026年第2期35-44,共10页
锂电池健康状态(state of health, SOH)可表征锂电池的老化状态。为准确评估SOH,首先,提取充电阶段的电流、电压、IC曲线中的6个特征,为了提高输入特征的质量,采用核主成分分析(kernel principal component analysis, KPCA)结合Spearma... 锂电池健康状态(state of health, SOH)可表征锂电池的老化状态。为准确评估SOH,首先,提取充电阶段的电流、电压、IC曲线中的6个特征,为了提高输入特征的质量,采用核主成分分析(kernel principal component analysis, KPCA)结合Spearman相关性分析,消除多维特征的冗余性获取输入特征的关键信息。其次,为了降低模型复杂度,将全连接层代替Transformer解码器,并利用牛顿-拉夫逊优化算法(Newton-Raphson-based optimization algorithm, NRBO)对模型的超参数寻优,提高预测精度。最后,利用公开数据集不同训练比例划分验证方法的有效性,并采用不同电池交叉验证与灰狼优化算法(gray wolf optimization algorithm, GWO)和鲸鱼优化算法(whale optimization algorithm, WOA)进行比较,结果表明:所提方法在精度和计算耗时方面均优于其他2种算法。 展开更多
关键词 核主成分分析 牛顿-拉夫逊 transformer模型 锂电池 健康状态
在线阅读 下载PDF
基于Transformer-XGBoost框架的轨交车辆电池多视角数据健康诊断研究
8
作者 王健 毛建 +4 位作者 唐超伟 孙小康 候晓双 王春生 廖垠钦 《电源技术》 北大核心 2026年第1期129-142,共14页
锂离子电池凭借其高能量密度和长寿命,在轨道交通与储能系统中得到了广泛应用,但随着充放电循环次数的增加,其健康状态(SOH)逐步衰退,给电池管理带来安全风险与维护挑战。传统的SOH预测方法主要依赖单一视角的增量容量分析(ICA)及常规... 锂离子电池凭借其高能量密度和长寿命,在轨道交通与储能系统中得到了广泛应用,但随着充放电循环次数的增加,其健康状态(SOH)逐步衰退,给电池管理带来安全风险与维护挑战。传统的SOH预测方法主要依赖单一视角的增量容量分析(ICA)及常规数据驱动模型,难以全面捕捉电池退化过程中电化学特性与时序动态的多尺度变化,导致预测精度和鲁棒性均受限。提出了一种基于多视角数据分析的SOH预测方法,通过融合电压视图与时间视图下的增量容量(IC)曲线信息构建多视图健康因子(HI),并设计了结合Transformer与极限梯度提升(XGBoost)的预测框架。其中,Transformer采用动态时间窗调整和双尺度注意力机制,以适应不同退化阶段下的时序特征提取。而XGBoost则通过引入物理信息约束,进一步提升了预测的稳定性与鲁棒性。在马里兰大学的PL13电池训练集中,该方法实现的均方根误差(RMSE)仅为3.13×10^(−3),决定系数R^(2)高达0.997;而在PL11电池测试集中,RMSE仅为4.57×10^(−3),R^(2)达到0.994,充分验证了该方法在多视角特征融合和动态时序建模方面的卓越性能。 展开更多
关键词 健康状态 多视角数据分析 transformER XGBoost 电池管理系统
在线阅读 下载PDF
MTSR:Mamba-Transformer协同增强的轻量化图像超分辨率模型
9
作者 庞梦鑫 董智红 +2 位作者 曹鹏 洪京平 张鸣赟 《计算机系统应用》 2026年第3期80-92,共13页
为解决现有轻量化图像超分辨率模型在平衡全局感受野、局部特征提取能力与计算效率方面的不足,并针对Mamba架构在上下文建模中存在的跨token交互能力不足问题,提出一种名为MTSR的高效Mamba-Transformer协同网络.首先,构建一种混合协同架... 为解决现有轻量化图像超分辨率模型在平衡全局感受野、局部特征提取能力与计算效率方面的不足,并针对Mamba架构在上下文建模中存在的跨token交互能力不足问题,提出一种名为MTSR的高效Mamba-Transformer协同网络.首先,构建一种混合协同架构,通过合理配比Mamba与Transformer模块,利用Transformer卓越的跨token交互能力弥补纯Mamba模型在上下文建模方面的缺陷,实现了长程依赖建模与计算效率的有效平衡.其次,设计一种深度卷积注意力前馈网络,用以替代传统的多层感知机.此网络能够显著增强局部细节特征的提取能力和通道间的信息交互,从而减少重建过程中的像素级信息损失,从而更充分地发挥Mamba模块的性能潜力.最后,提出一个三重深度可分离浅层细化模块.该模块专注于高效捕获并增强图像的浅层特征,为后续的非线性映射提供更丰富的原始纹理信息.在5个公开基准数据集上的大量实验结果表明,所提MTSR模型相较于当前的轻量化SOTA模型SRFormer-light和MambaIR-light,峰值信噪比(PSNR)分别获得了高达0.31 dB和0.38 dB的性能增益,同时保持了Mamba高效推理速度的优势.实验结果表明,该方法为轻量化图像超分辨率领域提供了一种兼具高性能与高效率的有效解决方案. 展开更多
关键词 超分辨率 轻量化 状态空间模型 自注意力 Mamba transformER
在线阅读 下载PDF
Analyzing and Designing Business Processes Management System Based on Transformation of Instantiated Ontology’s State
10
作者 YAO Qing WANG Haiyang 《Wuhan University Journal of Natural Sciences》 CAS 2006年第5期1126-1131,共6页
The paper discusses efforts of finding a simple and transparent method to analyze business processes and developing its management system architecture. By introducing ontology and its state, the approach tried to find... The paper discusses efforts of finding a simple and transparent method to analyze business processes and developing its management system architecture. By introducing ontology and its state, the approach tried to find a unified representation and a flexible choreography of business processes. The main idea of the paper is the transformation of ontology's states, which are the most important scenarios of enterprises. The business activity composition, that is, case composition based on an AI technique, Case Based Reason (CBR), which is to solve new problems by retrieving solutions to previous problems, and then store the modified solution. The main interest in CBR relies on that it allows a system to avoid past failures and exploit past successes. 展开更多
关键词 ontology business process management (BPM) case based reason(CBR) state transform
在线阅读 下载PDF
多物理场下基于TCN-Transformer网络的变压器异常状态辨识
11
作者 冯俊杰 降国俊 +1 位作者 张广勇 刘雨飞 《山西电力》 2026年第1期20-26,共7页
变压器是电力系统中的关键设备,其状态稳定性对于保障电网的安全可靠具有决定性作用。为应对变压器在实际运行中易受负载和环境影响难以准确评估其健康状态的问题,在分析变压器电-热-振动特征的基础上,采用k-means++算法对所提取的变压... 变压器是电力系统中的关键设备,其状态稳定性对于保障电网的安全可靠具有决定性作用。为应对变压器在实际运行中易受负载和环境影响难以准确评估其健康状态的问题,在分析变压器电-热-振动特征的基础上,采用k-means++算法对所提取的变压器负载电流、环境温度和运行电压3个关键参数进行工况划分,提出了一种基于TCN-Transformer的融合模型,实现了对变压器工况的异常状态辨识。以500 kV变压器进行试验,结果表明,所提出的TCN-Transformer模型在预测精度方面明显优于对比算法,可以更全面地捕捉数据中的重要信息,较好地实现了变压器多变量特征序列预测。 展开更多
关键词 变压器 多物理场 TCN-transformer 时序预测 工况聚类 异常状态辨识
在线阅读 下载PDF
基于BiLSTM-Transformer的铅酸电池剩余容量预测
12
作者 唐丽 魏冰凌 +1 位作者 王蕴敏 高鑫哲 《电池》 北大核心 2026年第1期142-148,共7页
通过超声波检测技术与深度学习模型的结合,实现对铅酸电池剩余容量的精确预测。选取变电站主要使用的4种铅酸电池作为研究对象,提出一种双向长短期记忆网络(BiLSTM)-Transformer混合深度学习模型。首先,利用超声波检测技术获取代表电池... 通过超声波检测技术与深度学习模型的结合,实现对铅酸电池剩余容量的精确预测。选取变电站主要使用的4种铅酸电池作为研究对象,提出一种双向长短期记忆网络(BiLSTM)-Transformer混合深度学习模型。首先,利用超声波检测技术获取代表电池容量的超声波信号特征,结合BiLSTM网络处理时间序列数据,捕捉电池状态数据的长期依赖关系,并通过Transformer模型的多头注意力机制提取全局特征,增强预测的准确性。实验结果显示,BiLSTM-Transformer模型的健康状态(SOH)预测误差均控制在0.3%内,相较于传统方法,该混合模型在预测精度和泛化能力上均有显著提升。 展开更多
关键词 铅酸电池 健康状态(SOH) 特征提取 超声波无损检测 BiLSTM-transformer模型
在线阅读 下载PDF
基于多源掘进参数与LSTM-Transformer的复杂地层盾构姿态预测方法
13
作者 邹道恒 《国防交通工程与技术》 2026年第1期6-12,共7页
针对深大城际黄麻布—石岩中心盾构区间的复杂地层及纵坡变化问题,提出一种基于多源数据融合与深度神经网络的盾构姿态实时预测方法。方法整合掘进参数、地质信息、渣样分析等数据,经特征筛选和规范化处理后,构建LSTM-Transformer混合... 针对深大城际黄麻布—石岩中心盾构区间的复杂地层及纵坡变化问题,提出一种基于多源数据融合与深度神经网络的盾构姿态实时预测方法。方法整合掘进参数、地质信息、渣样分析等数据,经特征筛选和规范化处理后,构建LSTM-Transformer混合神经网络模型,结合两者优势动态学习姿态变化规律,并在复杂地层转换处引入状态残差校正机制。以区间实测数据验证,该方法姿态预测均方误差较传统方法降低36%以上、提前预警时间达2环,能有效辅助掘进参数调控与风险预警、减少管片破损等事故,提升施工效率与安全性。 展开更多
关键词 多源数据融合 LSTM-transformer混合模型 盾构姿态预测 复杂地层 状态残差校正
在线阅读 下载PDF
Dynamic quantum secret sharing protocol based on two-particle transform of Bell states 被引量:5
14
作者 Yu-Tao Du Wan-Su Bao 《Chinese Physics B》 SCIE EI CAS CSCD 2018年第8期118-123,共6页
To solve the problems of updating sub-secrets or secrets as well as adding or deleting agents in the quantum secret sharing protocol, we propose a two-particle transform of Bell states, and consequently present a nove... To solve the problems of updating sub-secrets or secrets as well as adding or deleting agents in the quantum secret sharing protocol, we propose a two-particle transform of Bell states, and consequently present a novel dynamic quantum secret sharing protocol. The new protocol can not only resist some typical attacks, but also be more efficient than the existing protocols. Furthermore, we take advantage of the protocol to establish the dynamic secret sharing of a quantum state protocol for two-particle maximum entangled states. 展开更多
关键词 quantum secret sharing two-particle transform of Bell states ATTACK DYNAMIC
原文传递
Effects of high-pressure heat treatment on the solid-state phase transformation and microstructures of Cu_(61.13)Zn_(33.94)Al_(4.93) alloys 被引量:8
15
作者 王海燕 刘建华 +1 位作者 彭桂荣 王文魁 《Chinese Physics B》 SCIE EI CAS CSCD 2010年第9期469-474,共6页
The phase transformation activation energy of the Cu61.13Zn33.94A14.93 alloys, which were treated at 4 GPa and 700 ℃ for 15 minutes, was calculated by means of differential scanning calorimetry curves obtained at var... The phase transformation activation energy of the Cu61.13Zn33.94A14.93 alloys, which were treated at 4 GPa and 700 ℃ for 15 minutes, was calculated by means of differential scanning calorimetry curves obtained at various heating and cooling rates. Then, the effects of high-pressure heat treatments on the solid-state phase transformation and the microstructures of Cu61.13Zn33.94A14.93 alloys were investigated. The results show that high-pressure heat treatments can refine the grains and can change the preferred orientation from (111) to (200) of α phase. Compared with the as-cast alloy, the sample with high-pressure heat treatment has finer grains, lower β'→β and/β→β' transformation temperature and activation energy. Furthermore, we found that high cooling rate favours the formation of fine needle-like α phase in the range of 5-20℃/min. 展开更多
关键词 Cu61.13Zn33.94A14.93 alloy high-pressure heat treatment solid-state phase transformation MICROSTRUCTURES
原文传递
基于转置Transformer模型的电化学储能自适应SOH估计方法 被引量:2
16
作者 李鹏 葛儒哲 +3 位作者 董存 孙树敏 张元欣 王士柏 《高电压技术》 北大核心 2025年第6期2945-2953,I0015,共10页
为了保障锂离子电池运行的可靠性和安全性,及时监测其健康状况,在Autoformer模型和iTransformer模型的基础上,结合线性回归模型,提出了一种基于转置Transformer的自适应特征感知电池健康状态融合估计模型。首先,从充电曲线中提取健康因... 为了保障锂离子电池运行的可靠性和安全性,及时监测其健康状况,在Autoformer模型和iTransformer模型的基础上,结合线性回归模型,提出了一种基于转置Transformer的自适应特征感知电池健康状态融合估计模型。首先,从充电曲线中提取健康因子。其次,将容量退化分解为退化趋势部分和容量再生部分,利用线性回归模型预测电池容量的退化趋势,利用转置Transformer模型估计电池容量再生部分,两部分组合以获得电池容量退化的估计结果。最后,利用注意力权重对模型赋予可解释性。研究结果表明:此方法在NASA锂电池老化数据集上的仿真实验中,预测误差明显小于其他时序预测模型,验证了所提方法的预测精确性与可靠性。论文为电池健康状态精确估计的进一步深入研究提供了参考。 展开更多
关键词 锂离子电池 健康状态 深度学习 注意力机制 转置transformer模型 可解释性
原文传递
结合状态空间模型和Transformer的时空增强视频字幕生成 被引量:3
17
作者 孙昊英 李树一 +1 位作者 习泽宇 毋立芳 《信号处理》 北大核心 2025年第2期279-289,共11页
视频字幕生成(Video Captioning)旨在用自然语言描述视频中的内容,在人机交互、辅助视障人士、体育视频解说等领域具有广泛的应用前景。然而视频中复杂的时空内容变化增加了视频字幕生成的难度,之前的方法通过提取时空特征、先验信息等... 视频字幕生成(Video Captioning)旨在用自然语言描述视频中的内容,在人机交互、辅助视障人士、体育视频解说等领域具有广泛的应用前景。然而视频中复杂的时空内容变化增加了视频字幕生成的难度,之前的方法通过提取时空特征、先验信息等方式提高生成字幕的质量,但在时空联合建模方面仍存在不足,可能导致视觉信息提取不充分,影响字幕生成结果。为了解决这个问题,本文提出一种新颖的时空增强的状态空间模型和Transformer(SpatioTemporal-enhanced State space model and Transformer,ST2)模型,通过引入最近流行的具有全局感受野和线性的计算复杂度的Mamba(一种状态空间模型),增强时空联合建模能力。首先,通过将Mamba与Transformer并行结合,提出空间增强的状态空间模型(State Space Model,SSM)和Transformer(Spatial enHanced State space model and Transformer module,SH-ST),克服了卷积的感受野问题并降低计算复杂度,同时增强模型提取空间信息的能力。然后为了增强时间建模,我们利用Mamba的时间扫描特性,并结合Transformer的全局建模能力,提出时间增强的SSM和Transformer(Temporal enHanced State space model and Transformer module,TH-ST)。具体地,我们对SH-ST产生的特征进行重排序,从而使Mamba以交叉扫描的方式增强重排序后特征的时间关系,最后用Transformer进一步增强时间建模能力。实验结果表明,我们ST2模型中SH-ST和TH-ST结构设计的有效性,且在广泛使用的视频字幕生成数据集MSVD和MSR-VTT上取得了具有竞争力的结果。具体的,我们的方法分别在MSVD和MSR-VTT数据集上的绝对CIDEr分数超过最先进的结果6.9%和2.6%,在MSVD上的绝对CIDEr分数超过了基线结果4.9%。 展开更多
关键词 视频字幕生成 视频理解 状态空间模型 transformER
在线阅读 下载PDF
基于VGAE与Transformer的机器人自主导航优化算法 被引量:1
18
作者 唐敏 朱耀东 +2 位作者 胡蝶 朱永梁 樊紫岩 《微电子学与计算机》 2025年第2期59-67,共9页
在复杂的动态环境中实现智能体的无碰撞自主导航是一项人工智能的重要课题,然而在移动机器人面对多人环境下时,现有的基于深度强化学习方法导航容易出现碰撞、机器人冻结等问题。为实现机器人稳定的自主导航,文章提出利用变分图自编码器... 在复杂的动态环境中实现智能体的无碰撞自主导航是一项人工智能的重要课题,然而在移动机器人面对多人环境下时,现有的基于深度强化学习方法导航容易出现碰撞、机器人冻结等问题。为实现机器人稳定的自主导航,文章提出利用变分图自编码器(Variational Graph Auto-Encoder,VGAE)学习每个代理之间状态的潜在特征,再将潜在特征输入Transformer建模更加全局的空间交互,同时利用强化学习找到最优导航策略。该算法能够计算生成关系图,更好地对人类未来运动能力和随时间演变的动态位置变换进行建模。实验结果表明,算法在连续导航测试中,与开源仿真场景CrowdNav导航成功率与碰撞率相当,导航时间和平均累积奖励皆有所提升,相比现有的导航算法,该算法应用于机器人在人群拥挤环境下的自主导航更加有效。 展开更多
关键词 机器人 导航 深度强化学习 状态预测 transformER
在线阅读 下载PDF
Assessing Strategy of Power Transformers Insulation State Based on Part-division and Entropy Method 被引量:1
19
作者 LIAO Ruijin LIU Bin ZHANG Yiyi YANG Lijun ZHENG Hanbo 《高电压技术》 EI CAS CSCD 北大核心 2013年第8期1830-1836,共7页
Failure mechanisms of power transformers are complex and uncertain; it is difficult to determine index weights of insulation state. Therefore, it is a challenge to acquire an accurate assessment of insulation state of... Failure mechanisms of power transformers are complex and uncertain; it is difficult to determine index weights of insulation state. Therefore, it is a challenge to acquire an accurate assessment of insulation state of power transformers. In this paper, an assessing strategy for transformer insulation is proposed base on part-division of transformer and a comprehensive weight determination method. An index system of transformer is established on the basis of part-division of transformer. Each index’s weight is consisted of two parts, the constant weight and the variable weight, which are determined by improved analytic hierarchy process (AHP) and entropy method respectively. Af- ter categorizing insulation state into four levels and standardizing assessing indexes, a Cauchy membership function is forged, and a fuzzy algorithm is employed to simulate the uncertainty of the insulation state. Finally, a confidence criterion is employed to perform part-division based condition assessment of transformer. Case studies reveal that the proposed assessing strategy method is effective, convenient, and practical; with the new strategy, potential failures of transformers can be forecasted and insulation state of transformer parts can also be as- sessed. Furthermore, the assessing results can be used to guide condition-based maintenance. 展开更多
关键词 电力变压器 绝缘状态 评估策略 熵值法 国家战略 分划 改进层次分析法 指标权重
原文传递
Quantum state transformation and general design scheme on teleportation protocols
20
作者 JIANG Min HUANG Xu +1 位作者 ZHOU LiuLieZHOU YiMing ZENG Jia 《Chinese Science Bulletin》 SCIE EI CAS 2012年第18期2247-2251,共5页
We present a scheme for probabilistic transformation of special quantum states assisted by auxiliary qubits.In our scheme,if quantum states can be rewritten in a particular form,it is possible to transform such states... We present a scheme for probabilistic transformation of special quantum states assisted by auxiliary qubits.In our scheme,if quantum states can be rewritten in a particular form,it is possible to transform such states into other states using lowerdimensional unitary operations that can be more easily realized in physical experiments.Furthermore,as an important application,we propose a generalized scheme that helps construct faithful quantum channels via various probabilistic channels when considering the existence of nonmaximally-entangled states. 展开更多
关键词 量子比特 通用设计方案 状态转换 传输协议 隐形 非最大纠缠态 物理实验 量子通道
在线阅读 下载PDF
上一页 1 2 125 下一页 到第
使用帮助 返回顶部