检索结果-南通市图书馆

Heterogeneous Image Knowledge Driven Visual Perception

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 255-257页

作者： Lan Yan Wenbo Zheng fei-Yue Wang IEEE the College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China the School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan 430070China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Dear Editor,This letter is concerned with visual perception closely related to heterogeneous *** the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.

关键词： Visual visual knowledge

DBN-GABP model for estimation of aircraft wake vortex parameters using Lidar data

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第9期37卷 347-368页

作者： Zhiqiang WEI Tong LU Runping GU fei LIU College of Air Traffic Management Civil Aviation University of ChinaTianjin 300300China

Aircraft wake turbulence is an inherent outcome of aircraft flight,presenting a substan-tial challenge to air traffic control,aviation safety and operational *** upon data obtained from coherent Doppler Lidar detection,and combining Dynamic Bayesian Networks(DBN)with Genetic Algorithm-optimized Backpropagation Neural Networks(GA-BPNN),this paper proposes a model for the inversion of wake vortex *** the wake vortex flow field simulation analysis,the wind and turbulent environment were initially superimposed onto the simulated wake velocity ***,Lidar-detected echoes of the velocity field are simulated to obtain a data set similar to the actual situation for model *** the case study validation,real measured data underwent preprocessing and were then input into the established *** allowed us to construct the wake vortex characteristic parameter inversion *** final results demonstrated that our model achieved parameter inversion with only minor *** a practical example,our model in this paper significantly reduced the mean square error of the inverted velocity field when compared to the traditional *** study holds significant promise for real-time monitoring of wake vortices at airports,and is proved a crucial step in developing wake vortex interval standards.

关键词： Air traffic control Wake vortex flow field simulation Lidar echo simulation DBNmodel GA-BP model Wakevortex characteristic parameter inversion model

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

HTR-PM主氦风机电机冷却性能分析

清华大学学报（自然科学版） 2018年第2期58卷 188-191页

作者：莫非张佑杰王宏张勤昭清华大学核能与新能源技术研究院先进核能技术协同创新中心先进反应堆工程与安全教育部重点实验室

HTR-PM（high temperature reactor-pebblebed modules）主氦风机是高温气冷堆的重要部件,使用氦气作为工作介质。由于空间结构限制,主氦风机采用了自带风冷的一体化结构,通过专设冷却装置将电机热量带出。为了能针对性地设计辅助叶轮,... 详细信息

HTR-PM（high temperature reactor-pebblebed modules）主氦风机是高温气冷堆的重要部件,使用氦气作为工作介质。由于空间结构限制,主氦风机采用了自带风冷的一体化结构,通过专设冷却装置将电机热量带出。为了能针对性地设计辅助叶轮,需要得到电机冷却流道的流动特性和传热特性等热工参数。该文针对主氦风机特殊的冷却流道进行了实验研究,通过对氮气工质下的实验获得了HTRPM的特殊风冷系统的流动特性和传热特性,并向氦气工质下的特性进行类推。根据实验分析和理论计算,给出了冷却系统的优化方案。该方案将为下一步HTR-PM主氦风机辅助叶轮的设计和优化提供重要基础。

关键词：气冷堆主氦风机冷却系统热工特性

Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第3期37卷 237-257页

作者： fei WANG Xiaoping ZHU Zhou ZHOU Yang TANG School of Astronautics Northwestern Polytechnical UniversityXi’an 710072China School of Aeronautics Northwestern Polytechnical UniversityXi’an 710072China

In some military application scenarios,Unmanned Aerial Vehicles(UAVs)need to perform missions with the assistance of on-board cameras when radar is not available and communication is interrupted,which brings challenges for UAV autonomous navigation and collision *** this paper,an improved deep-reinforcement-learning algorithm,Deep Q-Network with a Faster R-CNN model and a Data Deposit Mechanism(FRDDM-DQN),is proposed.A Faster R-CNN model(FR)is introduced and optimized to obtain the ability to extract obstacle information from images,and a new replay memory Data Deposit Mechanism(DDM)is designed to train an agent with a better *** training,a two-part training approach is used to reduce the time spent on training as well as retraining when the scenario *** order to verify the performance of the proposed method,a series of experiments,including training experiments,test experiments,and typical episodes experiments,is conducted in a 3D simulation *** results show that the agent trained by the proposed FRDDM-DQN has the ability to navigate autonomously and avoid collisions,and performs better compared to the FRDQN,FR-DDQN,FR-Dueling DQN,YOLO-based YDDM-DQN,and original FR outputbased FR-ODQN.

关键词： Faster R-CNN model Replay memory Data Deposit Mechanism(DDM) Two-part training approach Image-based Autonomous Navigation and Collision Avoidance(ANCA) Unmanned Aerial Vehicle(UAV)

Review on synergistic damage effect of irradiation and corrosion on reactor structural alloys

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第3期35卷 109-141页

作者： Hui Liu Guan-Hong Lei He-fei Huang Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China School of Nuclear Science and Technology University of Chinese Academy of SciencesBeijing 100049China

The synergistic damage effect of irradiation and corrosion of reactor structural materials has been a prominent research *** paper provides a comprehensive review of the synergistic effects on the third-and fourth-generation fission nuclear energy structural materials used in pressurized water reactors and molten salt *** competitive mechanisms of multiple influencing factors,such as the irradiation dose,corrosion type,and environmental temperature,are summarized in this *** approaches are proposed to alleviate the synergistic damage caused by irradiation and corrosion,thereby promoting in-depth research in the future and solving this key challenge for the structural materials used in reactors.

关键词： Irradiation and corrosion Synergistic effect Austenitic stainless steels Nickel-based alloys Reactors

Bayesian Filtering for High-Dimensional State-Space models With State Partition and Error Compensation

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1239-1249页

作者： Ke Li Shunyi Zhao Biao Huang fei Liu Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) Institute of AutomationJiangnan UniversityWuxi 214122China Department of Chemical and Materials Engineering University of AlbertaEdmonton AB T6G 2G6Canada

In the era of exponential growth of data availability,the architecture of systems has a trend toward high dimensionality,and directly exploiting holistic information for state inference is not always computationally *** paper proposes a novel Bayesian filtering algorithm that considers algorithmic computational cost and estimation accuracy for high-dimensional linear *** high-dimensional state vector is divided into several blocks to save computation resources by avoiding the calculation of error covariance with immense *** that,two sequential states are estimated simultaneously by introducing an auxiliary variable in the new probability space,mitigating the performance degradation caused by state ***,the computational cost and error covariance of the proposed algorithm are analyzed analytically to show its distinct features compared with several existing *** results illustrate that the proposed Bayesian filtering can maintain a higher estimation accuracy with reasonable computational cost when applied to high-dimensional linear systems.

关键词： filtering estimation error

在线全文

学校读者我要写书评

暂无评论

基于条件随机场的模型特征线提取方法

电子学报 2014年第3期42卷 498-504页

作者：张尧烨孙正兴刘凯宋沫飞章菲倩南京大学计算机软件新技术国家重点实验室江苏南京210046

本文提出了一种草图指导的三维模型特征线提取方法,该方法特点在于:一方面,建立了笔画采样点与模型特征线点间的条件随机场匹配模型,将模型几何特征与形状相似性结合匹配,实现了草图信息与模型特征线提取的有效融合;另一方面,提出了基... 详细信息

本文提出了一种草图指导的三维模型特征线提取方法,该方法特点在于:一方面,建立了笔画采样点与模型特征线点间的条件随机场匹配模型,将模型几何特征与形状相似性结合匹配,实现了草图信息与模型特征线提取的有效融合;另一方面,提出了基于结构相似性的模型特征线度量机制,并采用迭代优化方法实现了全局最优模型特征线的提取.实验结果表明:本文提出的方法能有效获取与草图结构形状相对应的模型特征线绘图.

关键词：非真实感绘制特征线提取条件随机场迭代优化指导草图

Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 919-931页

作者： fei Ming Wenyin Gong Ling Wang Yaochu Jin the School of Computer Science China University of GeosciencesWuhan 430074China the Department of Automation Tsinghua UniversityBeijing 100084China the Faculty of Technology Bielefeld UniversityNorth Rhine-Westphalia33619 BielefeldGermany

Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable *** constrained multi-objective optimization evolutionary algorithms(CmoEAs)have been developed with the use of different algorithmic strategies,evolutionary operators,and constraint-handling *** performance of CmoEAs may be heavily dependent on the operators used,however,it is usually difficult to select suitable operators for the problem at ***,improving operator selection is promising and necessary for *** work proposes an online operator selection framework assisted by Deep Reinforcement *** dynamics of the population,including convergence,diversity,and feasibility,are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the *** using a Q-network to learn a policy to estimate the Q-values of all actions,the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic *** framework is embedded into four popular CmoEAs and assessed on 42 benchmark *** experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CmoEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CmoEAs.

关键词： Constrained multi-objective optimization deep Qlearning deep reinforcement learning(DRL) evolutionary algorithms evolutionary operator selection

Reduction of unactivated alkyl chlorides enabled by light-induced single electron transfer

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2024年第2期67卷 471-481页

作者： Lei Dai Zhao-fei Zhang Xiang-Yu Chen School of Chemical Sciences University of the Chinese Academy of SciencesBeijing100049China Institute of Chemistry Chinese Academy of SciencesBeijing100190China Binzhou Institute of Technology Weiqiao-UCAS Science and Technology ParkBinzhou256606China

Alkyl chlorides are abundant and easily accessible starting ***,due to the high reduction potentials associated with unactivated alkyl chlorides,achieving their single electron reduction remains a persistent *** challenge has spurred the exploration of efficient activation methods to overcome this *** recent years,photocatalysis has emerged as a mild and potent tool for the single electron reduction of unactivated alkyl chlorides,opening up new possibilities in this *** the rapid advancements in this area,a comprehensive review that provides a conceptual understanding of this emerging field,with a specific focus on reaction design and catalytic mechanisms,would be timely and highly ***,we present an overview of various synthetic techniques for photoinduced single electron reduction of unactivated alkyl ***,we also discuss the limitations of the present methods and future directions that lie ahead in this field.

关键词： photocatalysis unactivated alkyl chlorides single electron transfer radical reactions