检索结果-南通市图书馆

Ensemble successor representations for task generalization in offline-to-online reinforcement learning

Science China(Information Sciences) 2024年第7期67卷 240-255页

作者： changhong wang Xudong YU Chenjia BAI Qiaosheng ZHANG Zhen wang Space Control and Inertial Technology Research Center Harbin Institute of Technology Shanghai Artificial Intelligence Laboratory Shenzhen Research Institute of Northwestern Polytechnical University School of Cybersecurity Northwestern Polytechnical University

In reinforcement learning(RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline policy, which can be refined through online interactions. However, existing approaches primarily perform offline and online learning in the same task, without considering the task generalization problem in offline-to-online adaptation. In real-world applications, it is common that we only have an offline dataset from a specific task while aiming for fast online-adaptation for several tasks. To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning. We demonstrate that the conventional paradigm using successor features cannot effectively utilize offline data and improve the performance for the new task by online fine-tuning. To mitigate this, we introduce a novel methodology that leverages offline data to acquire an ensemble of successor representations and subsequently constructs ensemble Q functions. This approach enables robust representation learning from datasets with different coverage and facilitates fast adaption of Q functions towards new tasks during the online fine-tuning phase.Extensive empirical evaluations provide compelling evidence showcasing the superior performance of our method in generalizing to diverse or even unseen tasks.

关键词： offline reinforcement learning online fine-tuning task generalization successor representations ensembles

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Numerical Study of Water Transport and Operating Strategy for Fuel Cells with Segmented Water Management Flow Fields

引用

Journal of Thermal Science 2024年第4期33卷 1577-1589页

作者： CHEN Chengdai wang changhong ZHENG Zijun School of Materials and Energy Guangdong University of Technology

The effective cathode flow field design can realize the internal water balance and higher current density output of proton exchange membrane fuel cells(PEMFC).Therefore,a segmented water management flow field is proposed in this study,i.e.a half separated-half coupled cathode(HSHC) flow field which has two inlets but just one outlet.A 3D numerical PEMFC model is applied to study the effect of the HSHC flow field on PEMFC performance and its operating strategy in terms of operating conditions.The study results are shown as follows:Compared with the two conventional cathode flow fields,the HSHC flow field improves the water balance along the channel and increases the current density by 17.1% at a cathode stoichiometry of 3.25.It is because the HSHC flow field can overcome the water loss at channels upstream and the water accumulation at channels downstream.The draw water phenomenon(DWP) in the HSHC flow field is observed,which is mainly affected by the water vapor pressure of channel.Based on the DWP,cooling channel inlet flow rates can be used to adjust water balance,but severe water loss should be avoided.In addition,the inlet temperature control in HSHC flow field should be that cell temperature>cathode channel inlet temperature>cooling channel inlet temperature> ambient temperatures for better water balance.

关键词： proton exchange membrane fuel cells channel design segmented water management water balance operating strategy

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Deterministic and Robust Volt-var Control Methods of Power System Based on Convex Deep Learning

引用

Journal of Modern Power Systems and Clean Energy 2024年第3期12卷 719-729页

作者： Qing Ma changhong Deng IEEE the School of Electrical Engineering and Automation Wuhan University

Volt-var control(VVC) is essentially a non-convex optimization problem due to the non-convexity of power flow(PF) constraints, resulting in the difficulty in obtaining the optimum without convexity conversion. The existing second-order cone method for the convexity conversion often leads to a sharp increase in PF constraints and optimization variables, which in turn increases the optimization difficulty or even leads to optimization failure. This paper first proposes a deterministic VVC method based on convex deep learning power flow(DLPF). This method uses the input convex neural network(ICNN) to establish a single convex mapping between state parameters and node voltage to complete the convexity conversion while the optimization variables only correspond to reactive power equipment, which can ensure the global optimum with extremely fast computation speed. To cope with the impact brought by the uncertainty of distributed energy and omit the additional worst scenario search of traditional robust VVC, this paper proposes robust VVC method based on convex deep learning interval power flow(DLIPF), which continues to adopt ICNN to establish another convex mapping between state parameters and node voltage interval. Combining DLIPF with DLPF, this method decreases the modeling and optimization difficulty of robust VVC significantly. Test results on 30-bus, 118-bus, and 200-bus systems prove the correctness and rapidity of the proposed methods.

关键词： Optimization Reactive power Mathematical models Deep learning Uncertainty Load flow Programming

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Calibration method of quartz accelerometer on dynamic centrifuge

引用

Chinese Journal of Aeronautics 2022年第6期35卷 262-272页

作者： Yingbo SUN Shunqing REN changhong wang School of Astronautics Harbin Institute of TechnologyHarbin 150001China

This paper proposes a novel method for calibrating error coefficients of the quartz accelerometer faster on the dynamic centrifuge,which can generate a continuous dynamic acceleration excitation.Firstly,working principle and structure of the dynamic centrifuge are analyzed,the error sources and the uncertainty of the dynamic centrifuge are expounded,and relevant coordinate systems are established.Then,according to the characteristics of the input specific forces and the propagating methods of the error sources,the accurate input specific forces acted on the input reference axes of accelerometer are obtained.Based on the calibration error model of the accelerometer,the corresponding dynamic calibration method is proposed.Finally,the second-order and high-order coefficients of the acceleration error model are calibrated,and the calibration precision of the coefficients is analyzed.Compared with traditional calibration methods,the method proposed in this paper not only greatly enhances the calibration efficiency by reducing the installing positions of the accelerometer,but also separates the centrifuge errors from the outputs of the accelerometer,which improves the accuracy and efficiency of the calibration method simultaneously.

关键词： Accelerometer Calibration Dynamic centrifuge Dynamic excitation stimulus Error model Homogeneous transformation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Neurotrophins and neural stem cells in posttraumatic brain injury repair

引用

Animal Models and Experimental Medicine 2024年第1期7卷 12-23页

作者： Wenwen Guo Ke Liu Yinghua wang Xu Ge Yifan Ma Jing Qin Caiqin Zhang Ya Zhao changhong Shi Laboratory Animal Center Fourth Military Medical UniversityXi'anP.R.China Gansu University of Traditional Chinese Medicine LanzhouP.R.China Medical College of Yan'an University Yan'anP.R.China

Traumatic brain injury(TBI)is the main cause of disability,mental health disorder,and even death,with its incidence and social costs rising steadily.Although different treatment strategies have been developed and tested to mitigate neurological decline,a definitive cure for these conditions remains elusive.Studies have revealed that vari-ous neurotrophins represented by the brain-derived neurotrophic factor are the key regulators of neuroinflammation,apoptosis,blood-brain barrier permeability,neurite regeneration,and memory function.These factors are instrumental in alleviating neu-roinflammation and promoting neuroregeneration.In addition,neural stem cells(NSC)contribute to nerve repair through inherent neuroprotective and immunomodulatory properties,the release of neurotrophins,the activation of endogenous NSCs,and in-tercellular signaling.Notably,innovative research proposals are emerging to combine BDNF and NSCs,enabling them to synergistically complement and promote each other in facilitating injury repair and improving neuron differentiation after TBI.In this review,we summarize the mechanism of neurotrophins in promoting neurogen-esis and restoring neural function after TBI,comprehensively explore the potential therapeutic effects of various neurotrophins in basic research on TBI,and investigate their interaction with NSCs.This endeavor aims to provide a valuable insight into the clinical treatment and transformation of neurotrophins in TBI,thereby promoting the progress of TBI therapeutics.

关键词： mutual effect neural stem cells neurological function neurotrophins traumatic brain injury

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Surface-mediated iron on porous cobalt oxide with high energy state for efficient water oxidation electrocatalysis

引用

Green Energy & Environment 2022年第4期7卷 662-671页

作者： Jingsha Li Tao Hu changhong wang Chunxian Guo Institute of Materials Science and Devices Suzhou University of Science and TechnologySuzhou215011China

Surface engineering of active materials to generate desired energy state is critical to fabricate high-performance heterogeneous catalysts.However, its realization in a controllable level remains challenging. Using oxygen evolution reaction(OER) as a model reaction, we report a surface-mediated Fe deposition strategy to electronically tailor surface energy states of porous Co_(3)O_(4)(Fe-pCo_(3)O_(4)) for enhanced activity towards OER. The Fe-pCo_(3)O_(4) exhibits a low overpotential of 280 mV to reach an OER current density of 100 mA cm^(-2), and a fast-kinetic behavior with a low Tafel slop of 58.2 mV dec^(-1), outperforming Co_(3)O_(4)-based OER catalysts recently reported and also the noble IrO_(2). The engineered material retains 100% of its original activity after operating at an overpotential of 350 m V for 100 h. A combination of theoretical calculations and experimental results finds out that the surface doped Fe promotes a high energy state and desired coordination environment in the near surface region, which enables optimized OER intermediates binding and favorably changes the rate-determining step.

关键词： Surficial Fe doping Cobalt oxides High energy state Water oxidation Oxygen evolution reactions

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Posture Control of Legged Locomotion Based on Virtual Pivot Point Concept

引用

Journal of Bionic Engineering 2023年第6期20卷 2683-2702页

作者： Hao Sun Junjie Yang Yinghao Jia changhong wang Space Control and Inertial Technology Research Center Harbin Institute of TechnologyHarbin150001China

This paper presents a novel control approach for achieving robust posture control in legged locomotion,specifically for SLIP-like bipedal running and quadrupedal bounding with trunk stabilization.The approach is based on the virtual pendulum concept observed in human and animal locomotion experiments,which redirects ground reaction forces to a virtual support point called the Virtual Pivot Point(VPP)during the stance phase.Using the hybrid averaging theorem,we prove the upright posture stability of bipedal running with a fixed VPP position and propose a VPP angle feedback controller for online VPP adjustment to improve performance and convergence speed.Additionally,we present the first application of the VPP concept to quadrupedal posture control and design a VPP position feedback control law to enhance robustness in quadrupedal bounding.We evaluate the effectiveness of the proposed VPP-based controllers through various simulations,demonstrating their effectiveness in posture control of both bipedal running and quadrupedal bounding.The performance of the VPP-based control approach is further validated through experimental validation on a quadruped robot,SCIT Dog,for stable bounding motion generation at different forward speeds.

关键词： Legged robots Bionic control Virtual pivot point Posture stability Dynamic locomotion

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Multi-Source Adaptive Selection and Fusion for Pedestrian Dead Reckoning

引用

IEEE/CAA Journal of Automatica Sinica 2022年第12期9卷 2174-2185页

作者： Yuanxun Zheng Qinghua Li changhong wang Xiaoguang wang Lifeng Hu NORINCO GROUP Air Ammunition Research Institute Harbin 150030China the Research Center of Space Control and Inertial Technology Harbin Institute of TechnologyHarbin 150001China Research Center of Space Control and Inertial Technology Harbin Institute of TechnologyHarbin 150001China

Accurate multi-source fusion is based on the reliability, quantity, and fusion mode of the sources. The problem of selecting the optimal set for participating in the fusion process is nondeterministic-polynomial-time-hard and is neither sub-modular nor super-modular. Furthermore, in the case of the Kalman filter(KF) fusion algorithm, accurate statistical characteristics of noise are difficult to obtain, and this leads to an unsatisfactory fusion result. To settle the referred cases, a distributed and adaptive weighted fusion algorithm based on KF has been proposed in this paper. In this method, on the basis of the pseudo prior probability of the estimated state of each source, the reliability of the sources is evaluated and the optimal set is selected on a certain threshold. Experiments were performed on multi-source pedestrian dead reckoning for verifying the proposed algorithm. The results obtained from these experiments indicate that the optimal set can be selected accurately with minimal computation, and the fusion error is reduced by 16.6% as compared to the corresponding value resulting from the algorithm without improvements.The proposed adaptive source reliability and fusion weight evaluation is effective against the varied-noise multi-source fusion system, and the fusion error caused by inaccurate statistical characteristics of the noise is reduced by the adaptive weight evaluation.The proposed algorithm exhibits good robustness, adaptability,and value on applications.

关键词： Adaptive reliability evaluation adaptive weight evaluation Kalman filter(KF) multi-source fusion optimal set selection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Data-driven Static Equivalence with Physics-informed Koopman Operators

引用

CSEE Journal of Power and Energy Systems 2024年第1期10卷 432-438页

作者： Wei Lin changhong Zhao Maosheng Gao C.Y.Chung Department of Electrical Engineering The Hong Kong Polytechnic UniversityHong Kong SARChina Department of Information Engineering The Chinese University of Hong KongHong Kong SARChina School of Electrical Engineering Chongqing UniversityChongqing 400044China

With deployment of measurement units,fitting static equivalent models of distribution networks(DNs)by linear regression has been recognized as an effective method in power flow analysis of a transmission network.Increasing volatility of measurements caused by variable distributed renewable energy sources makes it more difficult to accurately fit such equivalent models.To tackle this challenge,this letter proposes a novel data-driven method to improve equivalency accuracy of DNs with distributed energy resources.This letter provides a new perspective that an equivalent model can be regarded as a mapping from internal conditions and border voltages to border power injections.Such mapping can be established through 1)Koopman operator theory,and 2)physical features of power flow equations at the root node of a DN.Performance of the proposed method is demonstrated on the IEEE 33-bus and IEEE 136-bus test systems connected to a 661-bus utility system.

关键词： Data-driven distribution network Koopman operator theory static equivalent model

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Standing wave drift of hemispherical resonator with quality factor non-uniformity under a ring electrode excitation

引用

Chinese Journal of Aeronautics 2022年第1期35卷 160-172页

作者： Yan HUO Zeyu wang Shunqing REN Zhennan WEI Guoxing YI changhong wang Space Cotrol and Inertial Technology Research Centre Harbin Institute of TechnologyHarbin 150080China HIT(Anshan)Institute of Industrial Technology Anshan 114000China

Hemispherical Resonator Gyroscope(HRG)is a classical high precision Coriolis Vibration Gyroscope(CVG),which performs attitude estimation of carrier by detecting the precession of standing wave of resonator,thus,the drift of standing wave of resonator has a great influence on the output accuracy of gyroscope,where the quality factor non-uniformity of resonator is one of main error sources.Ring electrode is a classical excitation structure of HRG because the standing wave can precess freely under its excitation,which makes the gyroscope have more accurate scale factor,larger measurement range and better dynamic characteristics.In this paper,the equations of motion of an ideal resonator excited by a ring electrode are derived by the elastic thin shell theory and Lagrange mechanical principle,then the corresponding equivalent mechanical model is established.According to the“average method”,it can be seen that the ideal resonator excited by the ring electrode works in integral mode,and any position in the circumferential direction of resonator can be a working point,which means that the quality factor non-uniformity has a great effect on the drift of standing wave.Therefore,the equations of motion of resonator with quality factor non-uniformity under the ring electrode excitation are deduced by the equivalent mechanical model,and the drift model of standing wave is established by the“average method”,it can be found that both the amplitude of quality factor non-uniformity and angle between the“inherent damping axis”and antinode axis of standing wave can affect the drift rate of standing wave.Moreover,the drift model indicates that if the input angular rate does not reach the threshold,the precession angular rate of standing wave will appear“self-locking”phenomenon,that is,the gyroscope will lose the integral effect.

关键词： Hemispherical resonator Theory of elastic thin shell Motion equations Average method Quality factor non-uniformity “Self-locking”phenomenon

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：