检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Jiang, Shengqin Lu, Xiaobo Lei, Yinjie Liu, Lingqiao School of Computer Science University of Adelaide AdelaideSA5005 Australia Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China School of Automatic Southeast University Nanjing210096 China Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China College of Electronics and Information Engineering Sichuan University Chengdu610064 China School of Computer Science University of Adelaide AdelaideSA5005 Australia

Crowd counting problem aims to count the number of objects within an image or a frame in the videos and is usually solved by estimating the density map generated from the object location annotations. The values in the density map, by nature, take two possible states: zero indicating no object around, a non-zero value indicating the existence of objects and the value denoting the local object density. In contrast to traditional methods which do not differentiate the density prediction of these two states, we propose to use a dedicated network branch to predict the object/non-object mask and then combine its prediction with the input image to produce the density map. Our rationale is that the mask prediction could be better modeled as a binary segmentation problem and the difficulty of estimating the density could be reduced if the mask is known. A key to the proposed scheme is the strategy of incorporating the mask prediction into the density map estimator. To this end, we study five possible solutions, and via analysis and experimental validation we identify the most effective one. Through extensive experiments on five public datasets, we demonstrate the superior performance of the proposed approach over the baselines and show that our network could achieve the state-of-the-art performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design of an Optimization and control System for Carbon Efficiency in the Green Manufacturing of Sinter Ore 36

Design of an Optimization and Control System for Carbon Effi...

引用

第36届中国控制会议

作者： Sheng Du Min Wu Xin Chen Weihua Cao Jinhua She School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Engineering Tokyo University of Technology

ISBN: (纸本)9781538629185

Sinter ore is the raw material of the iron and steel production.A sintering production process is with high energy consumption and large CO *** is important to achieve the green manufacturing of the sinter *** this paper,an optimization and control system for the carbon efficiency(OCSCE) in the green manufacturing of the sinter ore is designed from the point of view of the maximum utilization of the carbon and the best protection of environment in the sintering *** OCSCE has three parts:the optimization for the carbon efficiency,the coordinated optimization and control for the production phases and the comprehensive performance evaluation for the carbon *** optimization for the carbon efficiency is used to optimize the state *** coordinated optimization and control for the production phases is applied to optimize and control the operation *** comprehensive performance evaluation for the carbon efficiency assesses whether the carbon efficiency of the whole sintering process is consistent with green ***,an implementation scheme of the OCSCE is put forward for the industrial *** results of preliminary tests show that the OCSCE is in line with the needs of the industrial site,and it will have a significant performance after the OCSCE is put into the industrial site.

关键词： Carbon Efficiency Sintering Process Optimization Evaluation Hierarchical Structure

来源：评论

学校读者我要写书评

暂无评论

Efficient Deployment of Patrols to Catch Arsonists

Efficient Deployment of Patrols to Catch Arsonists

引用

Chinese Automation Congress (CAC)

作者： Jinpeng Han Fei-Yue Wang Yisheng Lv Fenghua Zhu Yilun Lin Xingyuan Dai Li Li School of Software Engineering Xian Jiaotong University Xian China The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing Qingdao Academy of Intelligent Industries Qingdao Shandong The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China Department of Automation Tsinghua University Beijing China

Forest fires are serious disasters that endanger the safety and property of residents. To deal with the arson-caused forest fires, we use security game theory to generate optimal patrol strategy under limited patrolling resources. The existing security game algorithms focus on a single behavior model to prevent attacks, while our work is to incorporate the secondary damage caused by the attack behavior into the optimization object. For forest fires, the security game algorithm only expects to catch arsonists in the forest, which is unreasonable in our opinion. Our algorithm incorporates the spread of fires into patrolling path planning so that defenders avoid being swallowed by fire via capturing the spread of it.

关键词： Games Forestry Security Game theory Mathematical model Automation control systems

来源：评论

学校读者我要写书评

暂无评论

State Estimation and Fault Detection for Nonlinear Dynamic systems

State Estimation and Fault Detection for Nonlinear Dynamic S...

引用

Chinese control Conference (CCC)

作者： Baohua Lu Liping Yan Hongxue Chen Yuanqing Xia Mengyin Fu Bo Xiao Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

In practical problems, the dynamic systems are usually nonlinear. In this case, the traditional Kalman filter cannot be used for state estimation or fault detection. The two typical extension based on Kalman filtering framework is the Extended Kalman Filter (EKF) and the Unscented Kalman Filter (UKF). Theoretically speaking, UKF is better than EKF when estimation accuracy is concerned, especially for high degree nonlinear cases. This paper is concerned with the state estimation and fault detection problem for a class of nonlinear dynamic systems. A novel fault detection and analyse method is presented based on the period residual of EKF and UKF. For different kind of faults, mainly, the system parameter error, the sensor/data error, EKF and UKF are used and the estimation and fault detection effects are compared and analyzed.

关键词： Fault detection Mathematical model State estimation Kalman filters Nonlinear systems Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Multi objective optimization based on SPEA for the microgrid energy dispatch

Multi objective optimization based on SPEA for the microgrid...

引用

第37届中国控制会议

作者： Xiaomin Wu Weihua Cao Dianhong Wang Min Ding School of Automation China University of Geosciences Hubei KEY Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Mechanical Engineering and Electronic Information China University of Geosciences

Microgrid provides an effective technical approach for distributed generation system connected to the power *** are renewable sources such as wind power, photovoltaic in the microgrid, which the power volatility of distributed generation limits the effective scheduling and real-time performance of microgrid. Energy storage device is used to stabilize the volatility of distributed generation, make sure the feasibility of distributed generation optimal scheduling. Microgrid optimizes scheduling the energy allocation od various types of distributed generation in technology, economy, environment and other aspects. In order to solutio the multi objective optimization of microgrid energy allocation, a Strength Pareto Evolutionary Algorithm based optimal method was proposed. Finally, the correctness and feasibility of the proposed method were verified through the simulation.

关键词： Microgrid Distributed generation Multi objective optimization Strength Pareto Evolutionary Algorithm

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Data-driven Model for Predicting Strip Temperature in Continuous Annealing Line Heating Process

A Dynamic Data-driven Model for Predicting Strip Temperature...

引用

Chinese control Conference (CCC)

作者： Yongyue Zhang Yali Jin Weihua Cao Zezhong Li Yan Yuan School of Information Science and Engineering Central South University Changsha Hunan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei China

In the continuous annealing line heating process, it is hard to get an accurate predict result only by a steady state model as it is a complex, strongly time-delayed and confounding process. This study provides a method for building a dynamic model. First analyzes the mechanism of the annealing line to get the main parameters, and then use the data-driven modeling method to get a steady state model, finally combines with dynamic algorithm to establish a dynamic model. This modeling method improves the accuracy of predict result to guarantee the efficiency of enterprises.

关键词： Heating systems Strips Mathematical model Predictive models Furnaces Process control Data models

来源：评论

学校读者我要写书评

暂无评论

ADP-Based Model Reference Adaptive control Design for Unknown Discrete-Time Nonlinear systems

ADP-Based Model Reference Adaptive Control Design for Unknow...

引用

第37届中国控制会议

作者： Wei Wang Xin Chen Fang Wang Hao Fu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Electrical and Information Engineering Zhengzhou University of Light Industry

In engineering applications, it is very useful to make a nonlinear system behave like a linear stable system. However,how to design a model reference adaptive control（MRAC） as the nonlinear dynamics is unknown is the key problem. In this study,an MRAC with adaptive dynamic programming（ADP） algorithm is presented for discrete-time nonlinear unknown dynamic systems, in which a multi-layer neural network（NN） model is utilized to describe the nonlinear system’s dynamics. Then based on this approximate model, a feedforward neuro-controller is developed as the desired control corresponding to the reference input. Third, the iterative ADP algorithm, in the form of actor-critic framework, employs two NNs to estimate the action value function, and generates the feedback control which, together with the feedforward neuro-controller, makes the state of the system track the reference model. Finally the feasibility of the new approach is verified by two numerical experiments.

关键词： Model reference adaptive control Adaptive dynamic programming Nonlinear system Q-function

来源：评论

学校读者我要写书评

暂无评论

Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control

arXiv

引用

arXiv 2018年

作者： Li, Wenqing Zhao, Chunhui Huang, Biao State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Chemical and Materials Engineering University of Alberta EdmontonABT6G-2V4 Canada

For large-scale industrial processes under closed-loop control, process dynamics directly resulting from control action are typical characteristics and may show different behaviors between real faults and normal changes of operating conditions. However, conventional distributed monitoring approaches do not consider the closed-loop control mechanism and only explore static characteristics, which thus are incapable of distinguishing between real process faults and nominal changes of operating conditions, leading to unnecessary alarms. In this regard, this paper proposes a distributed monitoring method for closed-loop industrial processes by concurrently exploring static and dynamic characteristics. First, the large-scale closed-loop process is decomposed into several subsystems by developing a sparse slow feature analysis (SSFA) algorithm which capture changes of both static and dynamic information. Second, distributed models are developed to separately capture static and dynamic characteristics from the local and global aspects. Based on the distributed monitoring system, a two-level monitoring strategy is proposed to check different influences on process characteristics resulting from changes of the operating conditions and control action, and thus the two changes can be well distinguished from each other. Case studies are conducted based on both benchmark data and real industrial process data to illustrate the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Inverse control of multi-dimensional Taylor network for permanent magnet synchronous motor

引用

Compel 2017年第6期36卷 1676-1689页

作者： Zhang, Chao Hong-Sen, Yan Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education and School of Automation Southeast University Nanjing China and Department of Automatic Control Henan Institute of Technology Xinxiang China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education and School of Automation Southeast University Nanjing China

PurposeThe purpose of this paper is to propose a new control strategy based on adaptive inverse control aiming at high performance control of permanent magnet synchronous motor (PMSM).Design/methodology/approachThis scheme adopts the vector control with double closed-loop structure and introduces a multi-dimensional Taylor network (MTN) inverse control method into velocity-loop. First, the invertibility of PMSM's mathematical model is proved. Second, a novel dynamic network (MTN) is presented, which has simple structure and faster computing speed. Besides, to realize the high-precision speed control, three MTNs are applied to achieve system modeling, inverse modeling and noise disturbance elimination which correspond to the function of the adaptive identifier, adaptive feed-forward controller and nonlinear adaptive filter, *** scheme is designed with the full consideration of the PMSM's particularity. For the PMSM's unknown dynamics and time-varying characteristics, the variable forgetting factor recursive least squares algorithm is adopted to improve identification ability, and the weight-elimination algorithm is used to remove redundant regression items in the MTN identifier and inverse controller. In addition, to reduce the influence arose from measurement noise and other stochastic factors, adaptive MTN filter is introduced to eliminate noise disturbance. The computational results show that the proposed scheme possesses excellent control performance and better robustness against the load ***/valueThe paper presents a new inverse control scheme with MTN which is practical and flexible, and the MTN-based control system is very promising for real-time applications.

关键词： Adaptive inverse control Multi-dimensional Taylor network Nonlinear adaptive filter System identification

来源：评论

学校读者我要写书评

暂无评论

Recommendation with the cold-start problem in evolving user-movie network

引用

Journal of Computers (Taiwan) 2019年第5期30卷 18-30页

作者： Zhang, Shu-Juan Zhang, Juan Jin, Zhen School of Mechatronic Engineering North University of China Shanxi Taiyuan030051 China School of Data Science and Technology North University of China Shanxi Taiyuan030051 China Complex Systems Research Center Shanxi University Shanxi Taiyuan030006 China Shanxi Key Laboratory of Mathematical Techniques and Big Data Analysis on Disease Control and Prevention Shanxi University Shanxi Taiyuan030006 China

Faced with the problem of information overload on the Internet, recommender systems have been paid more and more attention. At present, many recommendation algorithms have been proposed. However, there are two problems in these recommendation methods which must be solved. Most of them are studied in a single round of recommendation, but lots of complex systems in reality are evolving with time. Besides, the cold-start problem has always been intractable in the recommender system. Therefore, in this paper, we propose two recommendation methods (i.e., Method I and Method II) to solve the movie cold-start problem for the evolving user-movie network which is comprised of users and movies, and then examine the recommendation performance and long-term effects of these two methods in evolving networks, and evaluate influence factors through the numerical simulation. The experiment results show that the network structure, the movie attributes and the length of the recommendation list affect the recommendation accuracy and its novelty. The effects of Method I and Method II are better than those of other recommendation methods in previous works. Moreover, in Method Iwe should lay more emphasis on the relation between nodes, while in Method II we should focus on node attributes. © 2019 Computer Society of the Republic of China. All rights reserved.

关键词： Recommender systems

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：