检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Feng, Guoliang Lu, Wei Pedrycz, Witold Yang, Jianhua Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116023 China School of Automation Engineering Northeast Electric Power University Jilin132012 China School of Control Science and Engineering Dalian University of Technology Dalian116023 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2V4 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

Numerous learning methods for fuzzy cognitive maps (FCMs), such as the Hebbian-based and the population-based learning methods, have been developed for modeling and simulating dynamic systems. However, these methods are faced with several obvious limitations. Most of these models are extremely time consuming when learning the large-scale FCMs with hundreds of nodes. Furthermore, the FCMs learned by those algorithms lack robustness when the experimental data contain noise. In addition, reasonable distribution of the weights is rarely considered in these algorithms, which could result in the reduction of the performance of the resulting FCM. In this article, a straightforward, rapid, and robust learning method is proposed to learn FCMs from noisy data, especially, to learn large-scale FCMs. The crux of the proposed algorithm is to equivalently transform the learning problem of FCMs to a classic-constrained convex optimization problem in which the least-squares term ensures the robustness of the well-learned FCM and the maximum entropy term regularizes the distribution of the weights of the well-learned FCM. A series of experiments covering two frequently used activation functions (the sigmoid and hyperbolic tangent functions) are performed on both synthetic datasets with noise and real-world datasets. The experimental results show that the proposed method is rapid and robust against data containing noise and that the well-learned weights have better distribution. In addition, the FCMs learned by the proposed method also exhibit superior performance in comparison with the existing methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

Target tracking based on neural network depth feature and texture fusion

引用

IOP Conference Series: Earth and Environmental Science 2020年第1期461卷

作者： Yongzhan Cao Meiju Liu Shanykui Yang Guodong Yang Peng Chen Shuyun Zhu Zhuang Ge Yuwang Liu Information and Control Engineering Faculty Shenyang Jianzhu University Shenyang Liaoning 110168 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China School of Mechanical Engineering and Automation Northeastern University 3 Wenhua Street Shenyang 110819 China

This paper presents a method of target tracking based on convolution neural network and texture feature fusion. The lower layer of the convolutional neural network can extract some spatial structure, shape and other features of the target. High-level level can extract relatively abstract semantic information. In this paper, vgg-m convolutional neural network is adopted to realize tracking by adaptive fusion of the extracted depth features of Conv2 and Conv5 with the texture features extracted by two-dimensional Gabor filtering. In this paper, the experimental analysis of this method is carried out on the OTB2013 data set, and the results show that this method can achieve more accurate positioning of the target and has a strong timeliness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Deep Learning for 3D Printing of Tooth Model

3D Deep Learning for 3D Printing of Tooth Model

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Yiwen Liu Xiuqin Shang Zhen Shen Bin Hu Zhihai Wang Gang Xiong Faculty of Information The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing University of Technology Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China Faculty of Information Beijing University of Technology Beijing China

Recently, with the development of both 3D sensors and 3D virtual network that bring the needs of interaction with the real world, many 3D applications burst out. However, it is difficult to understanding these three-dimensional scenes with a fixed program. Then, a data-driven method is required to process these 3D data, which brings a strong demand of 3D Deep Learning in 3D data. Towards this goal, with an end-to-end deep learning, the experiment is based on PointNet++, a well proposed method for feature extraction. The experiment optimizes the network structure and parameters to improve the classification results. Finally, the network is applied to tooth model for classification and identification so that the dental model can be found from different perspectives.

关键词： Three-dimensional displays Deep learning Transforms Cameras Object segmentation Image segmentation Sensors

来源：评论

学校读者我要写书评

暂无评论

Bat Algorithm for Flexible Flow Shop Scheduling with Variable Processing Time

Bat Algorithm for Flexible Flow Shop Scheduling with Variabl...

引用

International Conference on Mechatronics and Intelligent Robotics, ICMIR 2017

作者： Zhonghua, Han Boqiu, Zhu Hao, Lin Wei, Gong Faculty of Information and Control Engineering Shenyang Jianzhu University Shenyang China Department of Digital Factory Shenyang Institute of Automation CAS Shenyang China School of Foreign Languages Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9783319659770

In order to solve the flexible flow shop scheduling problem with variable processing time (FFSP-VPT), it is analyzed, the paper analyzes the selection mode of processing time, jobs detection mode as well as rework mode, sets up FFSP-VPT mathematical model and puts forward a two-step encode mode for FFSP-VPT. By means of simulation experiment, the results are compared to mature genetic algorithm and differential evolution algorithm so that effectiveness of bat algorithm will be verified to solve practical production of FFSP-VPT. © 2018, Springer International Publishing AG.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Sizing of a sustainable condensation system for the production of sweet water through the use of photovoltaic panels in La Mesa de los Santos, Santander, Colombia

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1154卷

作者： B E Tarazona-Romero A-J Rodriguez Nieves C L Sandoval-Rodriguez J G Ascanio-Villabona M-A Duran-Sarmiento A-D Rincon-Quintero Automation and Control Energy Systems Research Group (GISEAC) Faculty of Natural Sciences and Engineering Electromechanical engineering Unidades Tecnologicas de Santander (UTS) Student Street No 9-82 680005 Bucaramanga Colombia Energy in Building research group (ENEDI) Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV / EHU) Engineer Torres Quevedo Square 1 48013 Bilbao BI Spain Doctoral Program in Electronic and Communications Department of Communications Engineering University of the Basque Country UPV/EHU 48013 Bilbao Spain

The objective of the project is to carry out the dimensioning of a photovoltaic system that allows its integration with a condensation system for the production of fresh water in isolated areas (Rural), in such a way that a sustainable condensation application capable of producing water is generated. sweet to supply small groups of inhabitants in areas where the basic supply of liquid is deficient. The study area is the Department of Santander, Colombia, specifically in the Municipality of los Santos and the area known as Mesa de los Santos, in which difficult geographical conditions are presented such as: altitude of 1650 meters above sea level and deficiency in aquifers. The methodological development proposes the analysis of the meteorological conditions of the area, the identification, selection and dimensioning of the condensing system and the photovoltaic system through the amp-hour method and the software system advisor model (SAM). Additionally, a CAD model is developed to obtain the complete schematization of the model and carry out a simulation process to analyze the behavior of the integration of the aforementioned systems. Finally, a techno-economic analysis of the proposed system is carried out.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of a prototype water electrolysis system as an alternative to produce hydrogen

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1154卷

作者： B E Tarazona-Romero C L Sandoval-Rodriguez J G Ascanio-Villabona A Quintero-Ruiz R E Páez-Castro O A Acosta-Cárdenas Automation and Control Energy Systems Research Group (GISEAC) Faculty of Natural Sciences and Engineering Electromechanical engineering Unidades Tecnologicas de Santander (UTS) Student Street No 9-82 680005 Bucaramanga Colombia Energy in Building research group (ENEDI) Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV / EHU) Engineer Torres Quevedo Square 1 48013 Bilbao BI Spain Doctoral Program in Electronic and Communications Department of Communications Engineering University of the Basque Country UPV/EHU 48013 Bilbao Spain

The objective of the development of the prototype or scale model of production of hydrogen and oxygen through the electrolysis process of water is to generate an alternative with a sustainable approach, which proposes the supply or source of energy initially with a direct current power source. replaceable in the future by a photovoltaic solar system. For the development of the prototype, it began with the academic compilation of information, then the model was made in CAD, followed by the need to integrate an electronic control system and a mechanical system to obtain the final model, materials were selected and used premises for the development of the two systems, the electronic and physical schematization was carried out, chaired by the assembly and field experimentation. It is important to highlight that the constructed scale model generates hydrogen and oxygen with a low current consumption and a constant voltage, the maximum point of gas generation is the maximum point of energy consumption and its relationship is almost linear.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AISI SAE 1045 steel tenacity variation evaluation subjected to corrosion process by chloride using the Charpy pendulum machine

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1154卷

作者： C G Cárdenas-Arias A D Rincón-Quintero C L Sandoval-Rodriguez B E Tarazona-Romero J S Muñoz-Gutierrez J L Jímenez-Rueda O A Acosta-Cárdenas Design and materials research group (DIMAT) Energy Systems Automation and Control Research Group (GISEAC) Electromechanical Engineering Faculty of Natural Sciences and Engineering Unidades Tecnológicas de Santander (UTS) Bucaramanga Colombia Doctoral Program in Engineering of Materials and Sustainable Processes University of the Basque Country UPV/EHU Bilbao Spain Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV / EHU) Engineer Torres Quevedo Square 1 Bilbao BI Spain Doctoral Program in Electronic and Communications Department of Communications Engineering University of the Basque Country UPV/EHU Bilbao Spain

The steel corrosion affecting study is important for industries and companies as well as for manufacturers of these material types. AISI SAE 1045 steel was used in this study, due to its frequent use. A specimen's series were prepared which were induced in an aggressive environment with the aim of degenerative process accelerating by increasing the material corrosion impact by altering the material mechanical properties. 15 specimens were exposed to the fog bank chamber, likewise 15 specimens in saline immersion chamber all with different exposure times 15. 30, and 45 days, subsequently the specimens are the impact test subjected to by the method of Charpy obtaining the tenacity value. To determine these values, the ASTM E23, ASTM A673 and ASTM E739 standards were used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Processing and monitoring algorithm for solar-powered smart home in DC-environment system based on RF-radio node 11th

Processing and monitoring algorithm for solar-powered smart ...

引用

11th Multi-disciplinary International Workshop on Artificial Intelligence, MIWAI 2017

作者： Sabry, A.H. Hasan, W.Z.W. Kadir, Mza Ab. Radzi, M.A.M. Shafie, S. Control and Automation Faculty of Engineering UPM Serdang Malaysia Faculty of Engineering UPM Serdang Malaysia

ISBN: (纸本)9783319694559

The success of a design of an effective premises area network requires appropriate algorithm and communication strategy. The primary objective of this paper is to present an effective algorithm for low cost process and monitoring system integrated with energy management of a solar-powered home system. The proposed algorithm designed to serve a system of a low power consumption and recognized by a lower number of electronic components, the system includes only a pair of XBee RF modules to process signals of current, voltage and temperature sensors and to monitor the power consumption data rate variations. The proposed control algorithm able to manage the Xbee on-board micro-controller with the associated sensors to act as a remote integrated wireless sensor node. The processed information sent to base node attached to PC for monitoring the attained data and displaying over an appropriate GUI. The approach suits the XBee RF environment, but, based on a direct sensor link concept, can open horizon to other wireless sensor networking applications such as WiFi. The results have been validated by a real case study conducted in solar powered home appliances in the DC - environment system. A (11–123) Hz sampling frequency has been achieved to capture the possible surge power. This work serves as an essential stepping stone towards more efficient wireless circuit design for the smart home energy system. © Springer International Publishing AG 2017.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Finite Element Modeling and Motion Planning of an Adaptive Elastic Wingsail

引用

IFAC-PapersOnLine 2017年第1期50卷 6768-6773页

作者： Kater A. Wriedt J.-P. Meurer T. Chair of Automatic Control Faculty of Engineering Kiel University Kiel 24143 Germany

A systematic motion planning methodology for elastomechanic structures is introduced using a combination of flatness based feedforward control and state feedback control. The concept is applied to a so-called wingsail for yachts, this structure can be described as a complex flexible structure based on two curved carbon sail areas with embedded actuators allowing to generate deflections to accomplish an adaptive sail structure. Due to the complexity of the structure the finite element method (FEM) is applied to determine the equations of motion (EOMs) in terms of a high dimensional system of ordinary differential equations (ODEs). The usage of model order reduction by means of modal truncation leads to a design system of feasible dimension and also directly represents a suitable form for the determination of the flatness-based state and input parametrization. This yields an efficient approach for motion planning and feedforward control, which is amended by a state feedback controller to address model uncertainties or disturbances. Simulation results illustrate the performance of the presented two-degrees-of-freedom control approach. © 2017

关键词： adaptive structure distributed parameter system feedforward control finite element method motion planning Smart structures wingsail

来源：评论

学校读者我要写书评

暂无评论

Backstepping-based extended Luenberger observer design for a Burgers-type PDE for multi-agent deployment

引用

IFAC-PapersOnLine 2017年第1期50卷 6780-6785页

作者： Freudenthaler G. Göttsch F. Meurer T. Chair of Automatic Control Faculty of Engineering Kiel University Kiel 24143 Germany

An extended Luenberger state observer is presented for a Burgers-type PDE. For this, pointwise boundary and an additional in-domain measurement are considered, which allows to split the observer setup into two subsystems. The observer gains are determined by utilizing the backstepping technique, which enables to stabilize the distributed parameter observer error dynamics. The concept is integrated into a motion planning and feedback control strategy and is applied to achieve the deployment of multi-agent continuum into desired spatial-temporal formation profiles. For the evaluation of the observer strategy the transfer to a finite-dimensional discrete multi-agent system in leader-follower configuration is obtained by means of a finite difference discretization. This in addition imposes the required communication topology for the interconnected agents. © 2017

关键词： backstepping Burger's equation deployment extended Luenberger observer formation control multi-agent system observer design Partial differential equation

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：