检索结果-南通市图书馆

Reinforcement Learning-Based MAS Interception in Antagonistic Environments

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 270-272页

作者： Siqing Sun Defu Cai Hai-Tao Zhang ning Xing the School of Artificial Intelligence and Automation the MOE Engineering Research Center of Autonomous Intelligent Unmanned Systemsthe Guangdong Engineering Technology Research Center of Fully Autonomous Unmanned Surface VehiclesHuazhong University of Science and TechnologyWuhan 430074China the State Grid Hubei Electric Power Research Institute Wuhan 430074China IEEE

Dear Editor, As a promising multi-agent systems(MASs) operation, autonomous interception has attracted more and more attentions in these years, where defenders prevent intruders from reaching *** far, most of the relevant methods are applied in ideal environments without agent damages. As a remedy, this letter proposes a more realistic interception method for MASs suffered by damages.

关键词： agent MAS destination

A Novel Tuning Method for Predictive Control of VAV Air Conditioning System Based on Machine Learning and Improved PSO

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2022年第4期31卷 350-361页

作者： ning He Kun Xi Mengrui Zhang Shang Li School of Mechanical and Electrical Engineering Xi’an University of Architecture and TechnologyXi’an 710055China

The variable air volume(VAV)air conditioning system is with strong coupling and large time delay,for which model predictive control(MPC)is normally used to pursue performance *** at the difficulty of the parameter selection of VAV MPC controller which is difficult to make the system have a desired response,a novel tuning method based on machine learning and improved particle swarm optimization(PSO)is *** this method,the relationship between MPC controller parameters and time domain performance indices is established via machine *** the PSO is used to optimize MPC controller parameters to get better performance in terms of time domain *** addition,the PSO algorithm is further modified under the principle of population attenuation and event triggering to tune parameters of MPC and reduce the computation time of tuning ***,the effectiveness of the proposed method is validated via a hardware-in-the-loop VAV system.

关键词： model predictive control(MPC) parameter tuning machine learning improved particle swarm optimization(PSO)

Application of the sulphide capacity theory on refining slags during LF treatment

在线全文

学校读者我要写书评

暂无评论

Journal of University of Science and Technology Beijing 2006年第2期13卷 112-116页

作者： ning Hao Hong Li Haitao Wang Xinhua Wang Wanjun Wang Metallurgical and Ecological Engineering School University of Science and Technology Beijing Beijing 100083 China

Sulphur has been reduced from 0.02wt% to 0.002wt% in 38 min average during 200 t ladle treatment in 2^# steel plant of Capital Steel. The sulphide capacity and equilibrium sulphur distribution of slags are calculated and compared with the measured values. The results show that the KTH model is a useful tool for the prediction of sulphide capacity and sulphur distribution during ladle treatment; the desulphurization reactions are completed nearly in thermo-equilibrium.

关键词： desulphurization ladle furnace sulphide capacity sulphur distribution

Image Captioning with multi-level similarity-guided semantic matching

在线全文

学校读者我要写书评

暂无评论

Visual Informatics 2021年第4期5卷 41-48页

作者： Jiesi Li ning Xu Weizhi Nie Shenyuan Zhang The School of Electrical and Information Engineering Tianjin UniversityChina People’s Daily China

Image Captioning is a cross-modal task that needs to automatically generate coherent natural sentences to describe the image *** to the large gap between vision and language modalities,most of the existing methods have the problem of inaccurate semantic matching between images and generated *** solve the problem,this paper proposes a novel multi-level similarity-guided semantic matching method for image captioning,which can fuse local and global semantic similarities to learn the latent semantic correlation between images and generated ***,we extract the semantic units containing fine-grained semantic information of images and generated captions,*** on the comparison of the semantic units,we design a local semantic similarity evaluation ***,we employ the CIDEr score to characterize the global semantic *** local and global two-level similarities are finally fused using the reinforcement learning theory,to guide the model optimization to obtain better semantic *** quantitative and qualitative experiments on large-scale MSCOCO dataset illustrate the superiority of the proposed method,which can achieve fine-grained semantic matching of images and generated captions.

关键词： Image Captioning Cross-modal semantic matching Reinforcement learning

The Path Planning Study of Autonomous Greeting Robot based on Ant Colony Algorithm 32

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

The Path Planning Study of Autonomous Greeting Robot based o...

Modelling the performance of EPB shield tunnelling using machine and deep learning algorithms

第32届中国控制与决策会议

作者： Cui Qingquan ning Jing Yin Xunhe School of Innovation and entrepreneurship Yunnan Land and Resources Vocational College School of Economics and Management Yunnan Agricultural University Kunming School of Electronics and Information Engineering Beijing Jiaotong University

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

In order to realize the autonomous greeting and greeting of the field guests,the autonomous greeting robot needs to collect and analyze the environmental *** the optimization algorithm,an optimal autonomous moving path from the starting point of greeting to a certain guest is *** this paper,aiming at the autonomous greeting robot,the path planning problem of the autonomous greeting robot based on ant colony algorithm is proposed,and the related design scheme is *** simulation example shows that the greeting robot can visit specific guests in the shortest path and *** can effectively ensure that the robot avoids obstacles and other guests in the process of *** verifies the feasibility and validity of the path planning proposed in this paper,and lays a theoretical foundation for the further application of the autonomous greeting robot in non-specific environment.

关键词： Autonomous Greeting Robot Path planning Ant colony algorithm Environment map Coordinate

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

Geoscience Frontiers 2021年第5期12卷 81-92页

作者： Song-Shun Lin Shui-Long Shen ning Zhang Annan Zhou Department of Civil Engineering School of Naval ArchitectureOceanand Civil EngineeringShanghai Jiao Tong UniversityShanghai 200240China MOE Key Laboratory of Intelligent Manufacturing Technology College of EngineeringShantou UniversityShantouGuangdong 515063China Discipline of Civil and Infrastructure School of EngineeringRoyal Melbourne Institute of Technology(RMIT)Victoria 3001Australia Shanghai Key Laboratory for Digital Maintenance of Buildings and Infrastructure Shanghai Jiao Tong UniversityShanghai 200240China

This paper introduces an intelligent framework for predicting the advancing speed during earth pressure balance(EPB)shield *** artificial intelligence(AI)models based on machine and deep learning techniques-back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),long-short term memory(LSTM),and gated recurrent unit(GRU)-are *** geological and nine operational parameters that influence the advancing speed are considered.A field case of shield tunnelling in Shenzhen City,China is analyzed using the developed models.A total of 1000 field datasets are adopted to establish intelligent *** prediction performance of the five models is ranked as GRU>LSTM>SVM>ELM>***,the Pearson correlation coefficient(PCC)is adopted for sensitivity *** results reveal that the main thrust(MT),penetration(P),foam volume(FV),and grouting volume(GV)have strong correlations with advancing speed(AS).An empirical formula is constructed based on the high-correlation influential factors and their corresponding field ***,the prediction performances of the intelligent models and the empirical method are *** results reveal that all the intelligent models perform better than the empirical method.

关键词： EPB shield machine Advancing speed prediction Intelligent models Empirical analysis Tunnel excavation

A constrained parameter evolutionary learning algorithm for Bayesian network under incomplete and small data 36

在线全文

学校读者我要写书评

暂无评论

A constrained parameter evolutionary learning algorithm for ...

A survey on multi-agent reinforcement learning and its application

第36届中国控制会议

作者： Yao You Jie Li ning Xu College of Mechatronic Engineering and Automation National University of Defense Technology

ISBN: (纸本)9781538629185

Lack of relevant data is a major challenge for Bayesian network（BN） parameters learning. For the issue, this paper proposes a constrained parameter evolutionary learning algorithm（CPEL） which is based on the qualitative knowledge and evolutionary strategy. In detail, firstly qualitative knowledge is employed into BN parameters learning process to reduce the parameter search space where two types of qualitative knowledge with experts’ confidence are presented;and then evolutionary strategy is introduced into the process to avoid the problem that classical learning technique falls into local optimum easily in which the special encoding for the BN parameters is presented and some evolutionary strategies are discussed. So combining their advantages will have an important significance for BN parameters learning under incomplete and small data. Comparative experiments show that the CPEL algorithm is better than classical EM algorithm in accuracy and timeliness performance, which verify the feasibility and superiority of the algorithm proposed. Additionally, the CPEL algorithm has been applied to UAV threat assessment under complex dynamic environment.

关键词： Bayesian network parameters learning CPEL algorithm qualitative knowledge evolutionary strategy

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 Automation and Intelligence 2024年第2期3卷 73-91页

作者： Zepeng ning Lihua Xie School of Electrical and Electronic Engineering Nanyang Technological UniversityNanyang Avenue639798Singapore

Multi-agent reinforcement learning(MARL)has been a rapidly evolving *** paper presents a comprehensive survey of MARL and its *** trace the historical evolution of MARL,highlight its progress,and discuss related survey ***,we review the existing works addressing inherent challenges and those focusing on diverse *** representative stochastic games,MARL means,spatial forms of MARL,and task classification are *** then conduct an in-depth exploration of a variety of challenges encountered in MARL *** also address critical operational aspects,such as hyperparameter tuning and computational complexity,which are pivotal in practical implementations of ***,we make a thorough overview of the applications of MARL to intelligent machines and devices,chemical engineering,biotechnology,healthcare,and societal issues,which highlights the extensive potential and relevance of MARL within both current and future technological *** survey also encompasses a detailed examination of benchmark environments used in MARL research,which are instrumental in evaluating MARL algorithms and demonstrate the adaptability of MARL to diverse application *** the end,we give our prospect for MARL and discuss their related techniques and potential future applications.

关键词： Benchmark environments Multi-agent reinforcement learning Multi-agent systems Stochastic games

CeO_(2)-supported Fe,Co and Ni toward CO_(2) hydrogenation:Tuning catalytic performance via metal-support interaction

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

Journal of Rare Earths 2023年第6期41卷 926-932,I0005页

作者： Bolang Li Fei Wang Kai Li Ping ning Min Chen Changbin Zhang Faculty of Environmental Science and Engineering Kunming University of Science and TechnologyKunming 650500China National-Regional Engineering Center for Recovery of Waste Gases from Metallurgical and Chemical Industries Kunming University of Science and TechnologyKunming 650500China State Key Joint Laboratory of Environment Simulation and Pollution Control Research Center for Eco-Environment SciencesChinese Academy of SciencesBeijing 100085China University of Chinese Academy of Sciences Beijing 100049China

The chemical transformation of CO_(2) produces carbon compounds that can be used as precursors for the production of chemicals and ***,we investigated the activity and selectivity of the transition metals(Fe,Co,and Ni)supported on CeO_(2) catalyst for CO_(2) hydrogenation at atmospheric *** found that Ni/CeO_(2) shows the highest CO_(2)conversion compared with Fe/CeO_(2) and Co/CeO_(2).Besides,Co/CeO_(2)and Ni/CeO_(2) exhibit nearly 100%CH_(4)selectivity while Fe/CeO_(2) inclines to produce *** characterization results show that the metal-support interaction order is Fe/CeO_(2)>Co/CeO_(2)>Ni/CeO_(2),the weak metal-support inte raction over Ni/CeO_(2)benefits the activation of H_(2) and then promotes the activity of CO_(2) ***,in situ DRIFTS results demonstrate that monodentate formate species rather than bidentate formate are the active *** main route of CO_(2) hydrogenation to CH_(4) is that CO_(2) is firstly transformed to m-HCOO*and then direct hydrogenation of the m-HCOO*to CH_(4).This study provides insights into the understanding of the mechanisms of CO_(2) hydrogenation on CeO_(2)based catalysts.

关键词： Ni CeO_(2) Metal-support interaction CO_(2)hydrogenation Rare earths