检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Wei Cao Luefeng Chen Min Wu Witold Pedrycz School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Electrical and Computer Engineering University of Alberta

Investigated is the problem of estimating the 3 D shape of an object defined by a set of 3 D landmarks with their 2 D correspondences in a single image. To solve this problem, we use a dictionary of the basic shape with LDD-L1 regularization,which is the construction of the shape space model. Based on the proposed convex optimization method, 3 D human pose reconstruction by shape space model and 3 D variable shape model was carried out on the mocap database. To improve accuracy and reduce the number of iterations, we use PSO algorithm to optimize initial value of the key parameter. The experimental results show that the improved algorithm exhibits less iterations but higher accuracy, which can be much helpful in practical applications.

关键词： LDD-L1 regularization 3D reconstruction PSO

来源：评论

学校读者我要写书评

暂无评论

Visual enhancement by spectral optimization of light sources 8

Visual enhancement by spectral optimization of light sources

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： Jin, Xing Cheng, Xianghui Yang, Xiang Zhang, Jinjin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

The visualization of an object image is directly affected by the spectral power distribution of the illuminated light source. In addition, the quality and the clarity of an object image can be evaluated by the color entropy value. Therefore, in order to obtain higher color entropy value of the target object image, a visual enhancement method is proposed by optimizing the spectral of the illumination. The optimal light source spectrum of the target image is obtained by the maximum color entropy, and the spectral reflectance of the object is obtained by the reconstruction method of the RBF neural network. The images under the optimal illumination source were compared with those of other commercial white light sources (6774K, 5000K, 2700K, 3000K,). The result shows that the optimized light source has a better visual effect and the lines in the image are more apparent. © 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： Light sources

来源：评论

学校读者我要写书评

暂无评论

Attenuation of PMSM Torque-Ripple Based on Combination of Equivalent-Input-Disturbance Approach and Sliding-Mode control

Attenuation of PMSM Torque-Ripple Based on Combination of Eq...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Ruoyu Jiang Jinhua She Zhentao Liu Danyun Li Wangyong He Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Engineering Tokyo University of Technology Tokyo Japan

Torque-ripples in a permanent magnet synchronous motor (PMSM) deteriorate control precision. This paper presents a method of attenuating such a kind of a torque-ripple based on the combination of the equivalent-input-disturbance (EID) and the sliding-mode control (SMC). While a low gain of an SMC system avoids chattering phenomenon, the robustness of the system is not satisfied. The EID estimator is incorporated in the system to solve this problem. The effectiveness of the combination of the EID approach and the SMC has been verified by simulations. A comparison with the conventional SMC method demonstrates the priority of the presented method.

关键词： Torque Sliding mode control forging Harmonic analysis Synchronous motors Stators Attenuation

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-based Identification of Influential Spreaders in Online Social Networks

Deep-Learning-based Identification of Influential Spreaders ...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Feng Wang Jinhua She Yasuhiro Ohyama Min Wu School of Engineering Tokyo University of Technology Tokyo Japan Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

Effective influential spreaders prediction in online social networks is critical for a variety of network services such as viral marketing, online recommendation, and many more. The conventional machine learning methods mainly adopted various hand-crafted features in the prediction models. However, their effectiveness relies on the domain knowledge heavily, and thus it is difficult to generalize these models to different domains. In this paper, we propose an Influence Deep Learning (IDL) model to learn users' latent feature representation for predicting influence spread. Our IDL model is fully data-driven, and it takes sampling subnetworks as input to the deep neural networks for learning users' latent vector representation. Moreover, we design a strategy to incorporate user-specific features and network structure into the graph convolutional neural network to overcome the imbalance problem of labeled training data. The experimental results show that our model outperforms other baselines in online social networks, and our model is more practical in large-scale data sets.

关键词： Social network services Machine learning Predictive models Neural networks Integrated circuit modeling Support vector machines Training

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Drilling System Software Framework and Data Architecture Based on MVC Pattern

Design of Intelligent Drilling System Software Framework and...

引用

第三十八届中国控制会议

作者： Peilun Ouyang Weihua Cao Min Wu Chao Gan Fawen Wang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Hubei Institute of Urban Geological Engineering

Drilling system software is crucial for the complex geological drilling process due to its vital role in improving the drilling efficiency and safety. In this paper, a Model-View-controller(MVC) pattern-based software framework and data architecture of an intelligent drilling system are proposed. First, four main functional requirements, namely, data fusion and visualization, safety assessment and efficiency calculation, efficiency and safety optimization, and coordination control have been analyzed. After that, a four-layers is established based on the above analysis and MVC pattern. Finally, a new online data architecture has been presented at the end of this paper. The proposed software framework and data architecture form a basis for the monitoring of the drilling process.

关键词： Model-View-controller intelligent Drilling Software Framework Data Architecture

来源：评论

学校读者我要写书评

暂无评论

Dynamic Security Assessment of Small-Signal Stability for Power systems using Windowed Online Gaussian Process

arXiv

引用

arXiv 2019年

作者： Zhai, Chao School of Automation China University of Geo-sciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Due to the evolving nature of power grids and model uncertainty, the online stability assessment of electrical power systems is always a challenging problem. This paper aims to provide a theoretical framework for estimating the region of attraction for power systems in real time. By analyzing and learning the measurement data in a given time duration, a windowed online Gaussian process (GP) approach is developed to provide the real-time security assessment and quantify the uncertainty caused by measurement errors and dynamic evolution of power systems. In addition, the theoretical analysis is conducted to ensure the conference level of the estimated region of attraction. Finally, numerical simulations are implemented on a microgrid model with 9 buses and 3 generators to validate the proposed approach. The proposed online assessment approach contributes to improving the situational awareness of human operators, thereby taking remedial actions before the emergency. Copyright © 2019, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Design of Deviation Correction control System in Vertical Drilling Process

Design of Deviation Correction Control System in Vertical Dr...

引用

第三十八届中国控制会议

作者： Dian Zhang Luefeng Chen Chengda Lu Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Software and Electrical Engineering Swinburne University of Technology

This paper is concerned with design of a deviation correction control system for vertical drilling process. Notice that only inclination angle is considered by traditional deviation correction systems, which may cause that the drilling trajectory extends around the wellhead's plumb line or gets away from the line. In this paper, focusing on the drilling trajectory itself, a deviation correction control scheme is provided to improve the vertical precision of the vertical drilling while maintaining small inclination angles. A hybrid modeling method for establishing the trajectory extension model and a model predictive control strategy based on the model are integrated in the scheme. It is expected that the phenomenon of spiral-like drilling trajectory can be attenuated by our control system over the traditional ones.

关键词： Geological Exploration Vertical Drilling Deviation Correction control Trajectory Extension Model Model Predictive control

来源：评论

学校读者我要写书评

暂无评论

intelligent control System Design for Electric-drive Rig in complex Geological Drilling Process

Intelligent Control System Design for Electric-drive Rig in ...

引用

第三十八届中国控制会议

作者： Xiao Wu Xuzhi Lai Jianglong Zhu Hongbo Huang Luefeng Chen Sheng Du Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Geological Equipment Group Co. Ltd

The complex geological drilling process is full of uncertain factors because of the invisibility of the bottom hole. The factors cause the problems of trajectory control and condition monitoring. In order to solve these problems, an intelligent control system is designed for complex geological drilling process by taking the XD-35 DB electric-drive rig as a study case. At first,the hardware structure of the rig is described in detail, and the working mechanism is analyzed. Then, based on its working mechanism, an intelligent control system is designed, which includes the basic automation layer and the intelligent control *** intelligent control layer is designed from three aspects: intelligent optimization of drilling trajectory, tracking control of drilling trajectory, and condition monitoring of the drilling process. The intelligent control system provides a feasible solution to improving drilling efficiency and ensuring drilling safety.

关键词： Condition monitoring Drilling process Electric-drive rig intelligent control system intelligent optimization

来源：评论

学校读者我要写书评

暂无评论

A survey of computer vision-based tracking registration technology for augmented reality 8

A survey of computer vision-based tracking registration tech...

引用

作者： Li, Yuqing Hong, Xin Xu, Chi School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China

Augmented reality technology is a research hotspot in the field of computer vision in recent years. Tracking registration technology determines the performance of augmented reality systems. The accuracy of tracking registration directly affects the users experience. Therefore, the research of tracking registration technology is of great significance. In this paper, augmented reality and its core tracking registration technology are introduced firstly. Then, the visual tracking registration method based on marker and natural features are elaborated, and the more advanced visual SLAM-based tracking registration method in recent years is summarized. Finally, the main problems of the current research and possible development directions are analyzed. © 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： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Short-term load forecasting based on GA-BPNN-SVR optimization algorithm 8

Short-term load forecasting based on GA-BPNN-SVR optimizatio...

引用

作者： He, Lianghua Ge, Lai Zhang, Hao Wang, Guowei School of automation China University of Geosciences Wuhan Hubei430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei430074 China

In order to improve the accuracy of short-term power load forecasting, an algorithm that simultaneously optimizes SVR parameters and optimizes the selection of input features is proposed. Firstly, the input features are selected by BP neural network. In order to avoid the influence of the randomness of the initial weights and thresholds on the optimization, the GA algorithm is used to optimize the weights and thresholds. Secondly, using GA algorithm to optimize the parameters of support vector regression, a short-term load forecasting model based on GA-BPNN-SVR optimization algorithm is obtained. Finally, the GA-BPNN-SVR model is applied to practical short-term power load forecasting, and the forecasting effect is compared with that of GA-SVM and BPNN-SVR models. The results show that the average absolute percentage error obtained by this method is only 1.74%, which is 1.64% and 3.11% lower than the average absolute percentage error obtained with GA-SVM model and BPNN-SVR. This algorithm can be effectively used for short-term load forecasting of power systems. © 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：