检索结果-内蒙古大学图书馆

第37届中国控制会议

作者： Gong Chen Yonghua Xiong Wei Chen Hao Zhou School of Automation China University of Geoscience Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

The evaluation and decision support system are widely used in agriculture with the development of information technology. In this paper, a Web-based comprehensive evaluation and decision support system（WCEDSS） is designed for flue-cured tobacco cultivation process. Using the artificial neural networks and some image processing methods, WCEDSS can predict various indicators of tobacco such as yield and flue-cured score, or give decisions at different stages of tobacco cultivation. As the system is developed by the Browser/Server（B/S） architecture, it is possible to make full use of the Internet resources and to facilitate users at any place with access to the Internet. Test results indicates that WCEDSS can achieve good performance. With other auxiliary functions, the system shows potential and extensive practicality in agricultural information management and guidance.

关键词： tobacco Browser/Server architecture evaluate decision support

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Prediction Model Based on BP Neural Network for Predicting CO/CO_2 in Iron Ore Sintering Process

Hierarchical Prediction Model Based on BP Neural Network for...

引用

Chinese control Conference

作者： Ben Xu Xin Chen Yang Zhou School of Automation China University of Geosciences Wuhan China Intelligent Automation for Complex Systems Hubei key Laboratory of Advanced Control Wuhan China

The sintering process is one of the most energy-consuming processes in steelmaking, its carbon fuel consumption accounts for 8% to 10% in the steel production process. To find ways of reducing the energy consumption, it is necessary to predict the carbon efficiency. The value of CO/CO_2 in the carbon emission can reflect the utilization of carbon combustion in sintering process. In this study, the CO/CO_2 is taken to be a measure of carbon efficiency and a hierarchical model is built to predict it. Firstly, the physical and chemical reactions and the carbon flow mechanism in the sintering process are analyzed, and the process parameters that affect the CO/CO_2 are determined. Then, the gray relational analysis method is used to analyze the influence factors to determine the relationship between the parameters, and a hierarchical predictive model for CO/CO_2 is established based on the relationship between the parameters. The hierarchical predictive model is divided into two parts: the predictive models for the thermal state parameters and the predictive model for CO/CO_2. The inputs of the predictive models for the thermal state parameters are the raw material parameters and the operating parameters, and the inputs of the predictive model for CO/CO_2 are the predicted values of the predictive models for the thermal state parameters. Finally, the simulation results verify the effectiveness of the proposed modeling method. This method can provide a theoretical basis for the optimization and control of carbon efficiency in the sintering process.

关键词： Predictive models Combustion Correlation Mathematical model Carbon dioxide Chemicals Raw materials

来源：评论

学校读者我要写书评

暂无评论

Modeling and Maximizing Angle Coverage in Visual Sensor Networks

Modeling and Maximizing Angle Coverage in Visual Sensor Netw...

引用

第37届中国控制会议

作者： Yonghua Xiong Manjie Lu Wei Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

Maintaining the quality of network coverage is a major concern in visual sensor networks. In this paper, we study the angle coverage problem in visual sensor networks, considering the target is very large, and each camera node can only monitor a portion of its perimeter. The goal of the proposed work is to schedule camera nodes to achieve maximum angle coverage in different period. Firstly, we establish a novel coverage model and formally prove that the problem is NP-hard in ***, we present a scheduling scheme based on greedy algorithm, to schedule camera nodes into disjoint cover sets working in ***, we conclude that the approximate ratio of the proposed algorithm is k, theoretically, and the time complexity of the algorithm is O（n）. Finally, extensive simulations have been conducted to evaluate the performance of the proposed algorithm.

关键词： Visual sensor network angle coverage camera node scheduling greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on a Thermostatic Heating control System for Optically Pumped Cesium Magnetometer

Research on a Thermostatic Heating Control System for Optica...

引用

第37届中国控制会议

作者： Shuting Hu Jian Ge Haobin Dong Liyue Xue Zhiwen Yuan Jun Zhu HaiYang Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System

Since the operating temperature of absorption chamber affects the sensitivity of the optically pumped cesium magnetometer（OPCM） directly, it is necessary to control the temperature precisely. In this paper, by using the positive temperature coefficient（PTC） and the integral separation proportional-integral-derivative（PID） algorithm, a high-precision thermostatic heating system is designed for OPCM. Firstly, the PTC heating device and the TSic506 temperature sensor are used to form a closed loop control system. Then, the three parameters of P, I and D are adjusted for different temperature, and the temperature control system is realized by STM32 microcontroller. Finally, the integral separation PID algorithm is used to eliminate overshoot. Experiments show that the effective temperature control ranges are 45?C5?C, the accuracy is less than ±0.2?C, and the system stability time is 300 s. It is obviously that the designed system has reference value and guidance significance for OPCM.

关键词： Thermostatic heating control system Integral separation PID algorithm Optically pumped cesium magnetometer

来源：评论

学校读者我要写书评

暂无评论

Street Object Detection Based on Faster R-CNN

Street Object Detection Based on Faster R-CNN

引用

第37届中国控制会议

作者： Wendi Cai Jiadie Li Zhongzhao Xie Tao Zhao Kang Lu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Library of Wuhan University of Technology

With the increased number of traffic accidents, the research and development of smart cars have been *** detection of street objects has become one of the important research topics. Generic Model detection algorithm based on Convolution Neural Network(CNN) need to design the training model, while the training and testing of the model will take a lot of time. Transfer Learning is used to fine-tune the pre-trained models, using the Image task datasets of COCO, transferring a generic deep learning model to specific one with different weights and outputs. Furthermore, the CNN structure is adjusted to improve overall performance, and the street environment is trained to the special scene. We compare the results of experiments,and the results showed that the network which is fine-tuned is effective.

关键词： Transfer Learning Faster R-CNN Inception-ResNet-v2 Object Detection

来源：评论

学校读者我要写书评

暂无评论

Differential-Evolution-Based Generative Adversarial Networks for Edge Detection

Differential-Evolution-Based Generative Adversarial Networks...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Wenbo Zheng Chao Gou Lan Yan Fei-Yue Wang School of Software Engineering Xi'an Jiaotong University The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Intelligent Systems Engineering Sun Yat-sen University School of Artificial Intelligence University of Chinese Academy of Sciences

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Since objects in natural scenarios possess various scales and aspect ratios, learning the rich edge information is very critical for vision-based tasks. Conventional generative adversarial networks (GANs) based methods for edge detection don't perform so well due to model collapse. In order to capture rich edge information and avoid model collapse as much as possible, we consider the learning of GANs as an evolutionary optimization and propose a novel method termed as differential-evolution-based generative adversarial networks (DEGAN) for richer edge detection. In particular, built upon GANs structure, we introduce an improved differential evolutionary algorithm to refine the input of generator, with fitness function evaluated by the discriminator. Experimental results on the well-known BSDS500 and NYUD benchmarks indicate our proposed DEGAN can achieve state-of-the-art performance while retaining a fast speed and validate its simplicity, effectiveness, and efficiency. The high quality of our results on edge detection with proposed DEGAN may promise to make other vision-based tasks work better.

关键词： Image edge detection Generators Gallium nitride Training Generative adversarial networks Evolutionary computation Evolution (biology)

来源：评论

学校读者我要写书评

暂无评论

Multi-Convolution Neural Networks-Based Deep Learning Model for Emotion Understanding

Multi-Convolution Neural Networks-Based Deep Learning Model ...

引用

Chinese control Conference

作者： Luefeng Chen Min Wu Wanjuan Su Kaoru Hirota Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Tokyo Institute of Technology Yokohama Japan

Multi-convolution neural networks-based deep learning model in combination with multimodal data for emotion understanding is proposed, in which facial expression and body gesture are used to achieve emotional states recognition for emotion understanding. It aims to understand coexistence multimodal information in human-robot interaction by using multi-convolution neural networks, where multilayer convolutions are connected in series and multiple networks are executed in parallel. Moreover, when optimizing the weights of deep neural network by traditional method, it is easy to fall into poor local optimal. To address this problem, a hybrid genetic algorithm with stochastic gradient descent is developed, which has the capacity of inherent implicit parallelism and better global optimization of genetic algorithm so that it can adaptively find the better weights of the network. And in order to speed up the convergence of the proposal, the weights optimized by stochastic gradient descent will be taken as a chromosome of genetic algorithms initial population, and it also can be used as a priori knowledge. To verify the effectiveness of the proposal, experiments on benchmark database of spontaneous emotion expressions are developed, and experimental results show that the proposal outperforms the state-of-the-art methods. Meanwhile, the preliminary application experiments are also carried out and the results indicate that the proposal can be extended to human-robot interaction.

关键词： Feature extraction Genetic algorithms Biological cells Machine learning Sociology Statistics Neural networks

来源：评论

学校读者我要写书评

暂无评论

Development of electric cart for improving walking ability — application of control theory to assistive technology

引用

Science China(Information Sciences) 2017年第12期60卷 262-270页

作者： Jinhua SHE Yasuhiro OHYAMA Min WU Hiroshi HASHIMOTO School of Engineering Tokyo University of Technology School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Master Program of Innovation for Design & Engineering Advanced Institute of Industrial Technology

This paper explains the development of an electric cart that helps the elderly maintain or improve their physical strength. Unlike commercially available ones, it has a pedal unit that provides some exercise for a user in training his lower limbs. An impedance model describes the feeling of pushing the pedals. The largest pedal load is determined based on a pedaling experiment. An H∞ controller is designed for each of the largest pedal load and virtually no load. A control law, which is based on the concept of dynamic parallel distributed compensation, is designed using the rating of perceived exertion of a driver as a criterion to choose a pedal load between the largest and almost zero. Five university students and twelve elderly people participated experiments to verify the system design and the validity of the system.

关键词： aging Borg’s scale dynamic parallel distributed compensation electrical cart H_∞ control Karvonen formula lower limbs pedaling rating of perceived exertion

来源：评论

学校读者我要写书评

暂无评论

Optimal Consensus control of Unknown Nonlinear Multi-Agent systems Using Adaptive Dynamic Programming via MRAC

Optimal Consensus Control of Unknown Nonlinear Multi-Agent S...

引用

第37届中国控制会议

作者： Hao Fu Xin Chen Wei Wang Jinbin Li Yaodong Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems State Grid Hubei Electric Power Research Institute

This paper introduces an optimal consensus control scheme for nonlinear multi-agent systems with completely unknown dynamics. In general, it is difficult to solve the coupled Hamilton-Jacobi-Bellman（HJB） equations, which the optimal consensus control relies on in multi-agent systems, especially unknown nonlinear systems. For the purpose of solving the problem, we propose an optimal consensus control approach based on the model reference adaptive control（MRAC） and adaptive dynamic programming（ADP）. Using the structure of the diagonal recurrent neural network, the identifier and controller are devised to achieve MRAC for every plant of the unknown nonlinear systems, i.e. the reference model serves as a dynamic model of each individual agent. Then, according to reference models of distributed agents, an adaptive dynamic programming（ADP）is introduced to approximate the solution of the coupled HJB equations.

关键词： Multi-agent systems optimal consensus model reference adaptive control adaptive dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Peak and valley time-of-use price optimization strategy with distributed power supply 8

Peak and valley time-of-use price optimization strategy with...

引用

8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Applications, ISCIIA and ITCA 2018

作者： Hu, Bo Zhang, Yu Han, Xin-Yang Jiao, Yu-Qiao Ding, Min School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Wuhan430074 China State Grid Energy Research Institute Co. LTD. Beijing102200 China

This paper proposes a peak-to-valley time-based electricity price optimization method based on NSGA-II with distributed power supply. First, the curve-fitting method is used to obtain the comprehensive electricity price response curve of users in the whole society. Secondly, based on the use of time-sharing electricity price, the peak-to-valley time-sharing optimization model is established. Then, based on the NSGA-II optimization method, the optimal model is solved, and the optimal electricity price is obtained at different time periods to change the peak-to-valley load and the valley load. Finally, the simulation results verify the effectiveness of the proposed method. © ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Application.

关键词： Genetic algorithms

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：