检索结果-内蒙古大学图书馆

第36届中国控制会议

作者： ZHAO Liang Zhu Yanxing ZHANG Jianyu Ye Zhencheng Key Laboratory of Advanced Control and Optimization for Chemical Process(Ministry of Education) East China University of Science and Technology Ethylene Plant of Jilin Petrochemical Company Ltd.PetroChina

ISBN: (纸本)9781538629185

Coevolutionary particle swarm optimization（CPSO） algorithm has been investigated and applied in the real world *** tackling the large-scale and complex real time optimization problems,the running time of CPSO algorithm is a *** this paper,Graphics Processing Unit（GPU） is introduced to provide speedup in order to meet the real time *** CPSO algorithm has been implemented on GPU concurrently using the CUDA *** performance and run time of CPU-based and GPU-based CPSO algorithms are compared in *** experiment result shows that the GPU-based parallel computation mode can shorten the run time of CPSO algorithm apparently.

关键词： GPU CUDA Particle swarm optimization Coevolutionary particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Label-Smooth Learning for Fine-Grained Visual Categorization 5th

Label-Smooth Learning for Fine-Grained Visual Categorization

引用

5th Asian Conference on Pattern Recognition, ACPR 2019

作者： Mo, Xianjie Wei, Tingting Zhang, Hengmin Huang, Qiong Luo, Wei College of Mathematics and Informatics South China Agricultural University GuangzhouGD510642 China Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai200237 China

ISBN: (纸本)9783030414030

Fine-Grained Visual Categorization (FGVC) is challenging due to the superior similarity among categories and the large within-category variance. Existing work tackles this problem by designing self-localization modules in an end-to-end DCNN to learn semantic part features. However the model efficiency of this strategy decreases significantly with the increasing of the number of categories, because more parts are needed to offset the impact of the increasing of categories. In this paper, we propose a label-smooth learning method that improves models applicability to large categories by maximizing its prediction diversity. Based on the similarity among fine-grained categories, a KL divergence between uniform and prediction distributions is established to reduce model’s confidence on the ground-truth category, while raising its confidence on similar categories. By minimizing it, information from similar categories are exploited for model learning, thus diminishing the effects caused by the increasing of categories. Experiments on five benchmark datasets of mid-scale (CUB-200-2011, Stanford Dogs, Stanford Cars, and FGVC-Aircraft) and large-scale (NABirds) categories show a clear advantage of the proposed label-smooth learning and demonstrate its comparable or state-of-the-art performance. Code is available at https://***/Cedric-Mo/LS-for-FGVC. © Springer Nature Switzerland AG 2020.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive neural output feedback control for stochastic nonlinear systems with unknown control directions

Adaptive neural output feedback control for stochastic nonli...

引用

第三十二届中国控制会议

作者： Yu Zhaoxu Li Shugang Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology Department of Industrial Engineering and Logistics Shanghai Jiao Tong University

ISBN: (纸本)9781479900305

This paper focuses on the problem of adaptive output feedback stabilization for a class of stochastic nonlinear system with unknown control *** using a linear state transformation,the unknown control coefficients are lumped together, such that the original system is transformed to a new system for which control design becomes *** employing the inputdriven observer,a novel adaptive neural network(NN) output-feedback controller which only contains one adaptive parameter is developed for such systems by using backstepping technique and NNs' *** proposed control design guarantees that all the signals in the closed-loop systems are 4-moment semi-globally uniformly ultimately bounded.

关键词： stochastic systems output-feedback neural network(NN) Nussbaum function backstepping

来源：评论

学校读者我要写书评

暂无评论

Outlet Temperature Correlation and Prediction of Transfer Line Exchanger in an Industrial Steam Ethylene Cracking Process

引用

Chinese Journal of chemical Engineering 2013年第4期21卷 388-394页

作者：金阳坤李进龙杜文莉王振雷钱锋 Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai 200237 China Institute of Automation East China University of Science and Technology Shanghai 200237 China

Predicting the best shutdown time of a steam ethylene cracking furnace in industrial practice remains a challenge due to the complex coking process. As well known, the shutdown time of a furnace is mainly determined by coking condition of the transfer line exchangers （TLE） when naphtha or other heavy hydrocarbon feedstocks are cracked. In practice, it is difficult to measure the coke thickness in TLE through experimental method in the complex industrial situation. However, the outlet temperature of TLE （TLEOT） can indirectly characterize the coking situation in TLE since the coke accumulation in TLE has great influence on TLEOT. Thus, the TLEOT could be a critical factor in deciding when to shut down the furnace to decoke. To predict the TLEOT, a paramewic model was proposed in this work, based on theoretical analysis, mathematic reduction, and parameters estimation. The feasibility of the proposed model was further checked through industrial data and good agreements between model prediction and industrial data with maximum deviation 2% were observed.

关键词： transfer line exchanger outlet temperature parametric model steam ethylene cracking

来源：评论

学校读者我要写书评

暂无评论

Physical Safety and Cyber Security Analysis of Multi-Agent Systems:A Survey of Recent Advances

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 319-333页

作者： Dan Zhang Gang Feng Yang Shi Dipti Srinivasan the Research Center of Automation and Artificial Intelligence Zhejiang University of TechnologyHangzhou310023 Key Laboratory of Advanced Control and Optimization for Chemical Processes(East China University of Science and Technology) Ministry of EducationShanghai 200237China the Department of Biomedical Engineering City University of Hong KongHong KongChina the Department of Mechanical Engineering University of VictoriaCanada the Department of Electrical and Computer Engineering National University of SingaporeSingapore

Multi-agent systems(MASs)are typically composed of multiple smart entities with independent sensing,communication,computing,and decision-making ***,MASs have a wide range of applications in smart grids,smart manufacturing,sensor networks,and intelligent transportation *** of the MASs are often coordinated through information interaction among agents,which is one of the most important factors affecting coordination and cooperation ***,unexpected physical faults and cyber attacks on a single agent may spread to other agents via information interaction very quickly,and thus could lead to severe degradation of the whole system performance and even destruction of *** paper is concerned with the safety/security analysis and synthesis of MASs arising from physical faults and cyber attacks,and our goal is to present a comprehensive survey on recent results on fault estimation,detection,diagnosis and fault-tolerant control of MASs,and cyber attack detection and secure control of MASs subject to two typical cyber ***,the paper concludes with some potential future research topics on the security issues of MASs.

关键词： Consensus deception attack deny-of-service(DoS)attack fault detection fault estimation fault tolerant control multiagent systems

来源：评论

学校读者我要写书评

暂无评论

An energy efficient clustering and relay node selection algorithm in wireless sensor networks 35

An energy efficient clustering and relay node selection algo...

引用

第35届中国控制会议

作者： HU Yuan JIA Tinggang NIU Yugang Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education (East China University of Science and Technology) Automation Division of Shanghai Electric Group Co. Ltd.

ISBN: (纸本)9781509009107

Wireless sensor networks utilize large numbers of sensors to perform sensing and forwarding tasks in the monitoring *** to the resources constraints of sensors and the energy efficiency QoS requirement,prolonging the network lifetime is a major concern in *** is an efficient approach to reduce energy consumption since it can reduce data transmission of the *** most traditional clustering protocols,the cluster heads（CHs） aggregate the coming data from their cluster members（CMs） and send the aggregated data to the remote sink node directly or visa other ***,assigning a node to serve as CHs and relay nodes simultaneously may result in unbalanced energy *** energy efficient overlapping clustering and relay node selection algorithm is proposed,which selects different nodes as CHs and relay node to attain the balancing of energy consumption of the network.A direction fitness metric is designed to select the proper boundary nodes in the overlapping area to serve as relay *** results show that the proposed algorithm significantly prolongs the network lifetime.

关键词： Wireless sensor networks energy efficiency clustering relay nodes multi-hop

来源：评论

学校读者我要写书评

暂无评论

Real-time Online UAV Images Mosaic with Robustness to Cumulative Errors 20

Real-time Online UAV Images Mosaic with Robustness to Cumula...

引用

2020 International Conference on Computing, Networks and Internet of Things, CNIOT 2020

作者： Xia, Xing Wang, Bei Li, Jing Song, Li Gong, Yi Hang Deng, Bao Song Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai China National Innovation Institute of Defense Technology Academy of Military Science Tianjin Artificial Intelligence Innovation Center Tianjing China

ISBN: (纸本)9781450377713

In this paper, a novel real-time online UAV image mosaic algorithm is proposed to meet the real-time, robustness and accuracy requirements of practical application. First, the algorithm adopts GPS and track planning information to locate the adjacent images. Instead of the 8-DOF (degrees of freedom) homography transformation, the 4-DOF similarity transformation is estimated to more robustly register the UAV images and reduce their perspective errors. Second, a new method of local registration is developed to reduce the cumulative errors and calculation costs. Meanwhile, the real-time mosaic process is used to register images and update the panoramic image. Finally, the effectiveness of the proposed approach is evaluated by a group of experiments on 4K images taken by quadrotor drones. According to the comparison of experiments, the proposed algorithm is robust to cumulative errors and obtains high-quality panorama. Additionally, through the analysis on stitching time and practical application, frame-by-frame mosaic synthesis is online updated in real-time. © 2020 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Path planning for mobile anchor node in localization based on ad-hoc localization algorithm 3

Path planning for mobile anchor node in localization based o...

引用

3rd International Workshop on advanced Computational Intelligence and Intelligent Informatics, IWACIII 2013

作者： Pu, Shi Qi, Rong-Bin Jin, Wen-Hao Qian, Feng East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education Shanghai200237 China Shanghai Consulting and Academic Activeties Center for Academicians Chinese Academy of Engineering Shanghai200020 China

For mobile anchor node static path planning cannot accord the actual distribution of node for dynamic adjustment which result in incomplete coverage and lack of flexibility. We take advantage of the high localization accuracy and low computational complexity of AHLos algorithm. This article introduces mobile anchor nodes instead of the traditional fixed anchor nodes to improve the algorithm. Firstly, the high connectivity nodes are chosen in the network as AHLos algorithm initial anchor nodes. The initial anchor nodes are located through the method of approximate location. The mobile anchor nodes traverse all the initial nodes. The residual nodes in the network will be located by AHLos location algorithm. In addition, not every two initial anchor nodes are neighbor nodes in the process of traverse. The minimum hop path from one initial anchor node to the next one is defined as the transition path. The mobile anchor node use the transition path between two non-neighboring initial nodes to induction the next initial node. At the same time, the GPS can be shut down along the transition path. The mobile anchor nodes adjust its direction as soon as possible, once the signal of the next node is perceived. This method could both avoid the energy consumption of GPS and greatly reduce the actual distance of the mobile anchor node. The result shows that, through introduce the mobile anchor node, we can configure the information of initial anchor nodes more flexible. Meanwhile, with the use of the approximate location and the transition path, the distance and energy consumption of the mobile anchor node is greatly reduced.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Modified Self-adaptive Immune Genetic Algorithm for optimization in the Combustion Side Reaction of p-Xylene Oxidation

Modified Self-adaptive Immune Genetic Algorithm for Optimiza...

引用

第23届过程控制会议

作者： Lili Tao Xiangdong Kong Weimin Zhong Feng Qian Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education E Automation Institute East China University of Science and Technology Shanghai 200237 China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education E

In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution of non-linear optimization problems encountered in many engineering applications. In IGA, the mutation factor values are either fixed or change together according to a function of the individual’s current generation number during all the search process. However, IGA with deterministic mutation factor suffers from the problem of premature convergence. A modified self-adaptive immune genetic algorithm (MSIGA) with two memory bases, in which immune concepts are applied to determine the mutation parameters, is proposed to strengthen the searching ability of the algorithm and maintain population diversity. Performance comparisons with other well-known population-based iterative algorithms show that the proposed method can quickly converge to the global optimum and overcome premature problem. Then, this algorithm is applied to optimize a feed forward neural network to measure the content of products in the combust ion side reaction of p-xylene oxidation, and satisfactory results are obtained.

关键词： Self-adaptive immune genetic algorithm Artificial neural network Measurement p-Xylene oxidation process

来源：评论

学校读者我要写书评

暂无评论

Thermal Decomposition Behavior of Terephthalate in Inert Gas

引用

China Petroleum Processing & Petrochemical Technology 2017年第3期19卷 1-8页

作者： Yu Jing Wang Jiming Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237 DuPont China Holding Co. LtdShanghai 201203 School of Chemical Engineering East China University of Science and TechnologyShanghai 200237

Several metal terephthalates were synthesized by hydrothermal solvent method. Firstly, the coordination type of metal ions and carboxylates in terephthalate was studied by FTIR spectroscopy. The results showed that the binding type of zinc terephthalate and aluminum terephthalate are mainly bridged coordination, while the chelating coordination mode dominated in the magnesium terephthalate and cerium terephthalate. Secondly, the thermal decomposition mechanism of zinc terephthalate in nitrogen atmosphere was studied by TG and Py-GC/MS techniques. Finally, the activation energy of the thermal decomposition process was obtained by the Friedman method and the Flynn-Wall-Ozawa(FWO) method, and the most probabilistic function was obtained by multiple linear fitting. The results showed that the decomposition process of zinc terephthalate was an one-step reaction and the activation energy was equal to 187.38 kJ/mol.

关键词： terephthalate TG/DTG thermal decomposition mechanism kinetics

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：