检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Yi-Juan Ning Hai-Peng Ren Jie Li Shaanxi Key Laboratory of CoTplex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China Department of Electrical Engineering Xi’an University of Technology Xi’an China

Power electronic converters play an important role in the energy conversion. Power electronic converters, exhibiting different system dynamical characteristics according to the onoff state of the switch, are typical switching (nonlinear) systems. The traditional model of power electronic converter is the small signal average model and the converter controller is designed using the linear system theory. This kind of method is effective only within the vicinity of the predefined operating point. When the system parameter varies in a large scale, the converter control performance will degrade. The hybrid system model reflects the essential switching characteristics of the converter, and the controllers designed based on the hybrid model are suitable for converter control when the system states or parameters vary in a large scale. However, the parameter uncertainty is still a problem in conventional switching control method. In this paper, the inductor current compensation control is proposed to deal with the uncertainties of the circuit parameters and working point variation. The effectiveness of the proposed method is verified by both simulation and experiment.

关键词： Switches Voltage control Resistance Inductance Matrix converters

来源：评论

学校读者我要写书评

暂无评论

control-oriented fault detection of solid oxide fuel cell system unknown input on fuel supply

Control-oriented fault detection of solid oxide fuel cell sy...

引用

作者： Wu, Xiao-long Xu, Yuan-wu Xue, Tao Shuai, Junchao Jiang, Jianhua Deng, Zhonghua Fu, Xiaowei Li, Xi School of Automation Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science & Technology Wuhan China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Wuhan Industrial Economic Development Research Center Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China

As the solid oxide fuel cell (SOFC) system work environment is a high-temperature environment for a long time, it is difficult to obtain the SOFC stack internal state change directly. When the fault occurs, it is difficult to determine where the fault occurs. Moreover, the existing literature ignores the impact of faults, which creates many problems for SOFC system control. Therefore, a state observer-based fault detection method, which is used to detect the input flow sensor fault and the fuel input fault, is proposed. Their advantage is that they do not need data processing. To realize the fault detection, the observer is used to track the changes of SOFC stack chamber temperature. To obtain the observer estimation parameter, an approach from the actual stack structure parameters is employed to approximate the observer parameters. The results show the proposed fault detect method can judge fuel input fault type quickly and shield the disturbances signals from the sensor effectively. The proposed method also can be used to other operating points or air input fault. © 2018 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A registration-aided domain adaptation network for 3D Point cloud based place recognition

arXiv

引用

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Learning of long-horizon sparse-reward robotic manipulator tasks with base controllers

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Xin, Minjian Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering University of California San Diego La Jolla CA92093 United States Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Assessment and prediction of leakage degree of expansion joints in underground network heating pipe network based on LS-SVM and ARIMA model 13

Assessment and prediction of leakage degree of expansion joi...

引用

13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

作者： Shang-Bin, Jiao Le, Fan Peng-Yue, Wu Lei, Qiao Yong-Ze, Jin Qian-Kun, Shen Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China Xi'an Thermal Power Research Institute Co. Ltd Xi'an710054 China

ISBN: (纸本)9781538637579

The study shows that the leakage of the expansion joints in the underground heating primary pipe network will lead to the fluctuation of soil temperature and conductivity around the leakage point. Based on the online monitoring of changes of physical quantities around the expansion joint, this paper established the assessment model of temperature and conductivity as the input parameters and the degree of expansion joints leakage as the output parameters, which took the radial basis function as kernel function and made use of PSO algorithm to achieve the optimization of the kernel function parameters. Then, the temperature and conductivity were predicted based on the ARIMA model, and the LS-SVM assessment of expansion joint leakage was realized according to the prediction results. Both simulation and field experiments show that the prediction model based on ARIMA has higher accuracy, which has identified the foundation for on-line prediction and accurate assessment of the expansion joint leakage in the underground heating primary pipe network. © 2018 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Model Identification and Internal Model control for 3D Printer

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期740卷

作者： Ruidong Xie Yingmin Yi Haichuan Yang Key Lab of Manufacturing Equipment of Shaanxi Province Xi'an University of Technology Xi'an 710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an 710048 China

A 3D printer system for selective laser sintering technology is used to establish a mathematical model of the relationship between laser power and temperature by using the recursive least squares method. Based on this model, the internal model control method is used to design the controller to realize the actual 3D printer. Temperature control, simulation analysis of internal model control and traditional PID control effects. The experimental results show that the feasibility, accuracy and internal model control of the recursive least squares identification model are fast, easy to implement, robust, and only one adjustable parameter, easy to adjust.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Detection and Identification Method Based on CNN for Laser Point Thermal Radiation

引用

Journal of Physics: Conference Series 2020年第1期1654卷

作者： Haichuan Yang Ruidong Xie Yingmin Yi Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an 710048 China Key Lab of Manufacturing Equipment of Shaanxi Province Xi'an University of Technology Xi'an 710048 China

Aiming at the high demands of temperature and precision in the aspect of additive manufacturing, a method based on CNN was proposed for estimating measurement. The network was trained through the collected laser thermal radiation images for image recognition and isotherm estimation after modeling a CNN. The experimental conclusion verifies that the isotherm detection and temperature estimation of the laser point can be efficiently implemented in proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The estimation of the laser point temperature based on CNN (Convolutional Neural Network)

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期740卷

作者： Yingmin Yi Ruidong Xie Haichuan Yang Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an 710048 China Key Lab of Manufacturing Equipment of Shaanxi Province Xi'an University of Technology Xi'an 710048 China

For the requirements of the laser temperature in additive manufacturing, there is a high precision and high heat need in the industry. The method is proposed to estimate the temperature of laser point, which is based on CNN. In this method, a model of CNN is carried out. The collected laser thermal radiation images are used to train the model. Image recognition and isotherm estimation can be obtained by the trained model. The conclusion can be verified by the experiment. The isotherm and temperature of the laser can be measured efficiently in this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Power Optimization control Method Based on IMC for 3D Printer

引用

Journal of Physics: Conference Series 2020年第1期1654卷

作者： Ruidong Xie Haichuan Yang Yingmin Yi Key Lab of Manufacturing Equipment of Shaanxi Province Xi'an University of Technology Xi'an 710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an 710048 China

Aiming at the effect of selective laser sintering technology used in 3D printing, the recursive least squares method was applied to fitting a control system model for quantification the relationship between laser power and corresponding temperature in this paper. The internal model control method is considered based on the establishing model. The controller is put into the actual 3D printing power control system for controlling the laser power. In the experiment, both internal model controller and the PID controller for the 3D printer are researched and deployed for comparing the their effects in the paper. The experimental result illustrates that the IMC based on the recursive least squares method is of effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

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：