检索结果-内蒙古大学图书馆

作者： Tao Zhang Hongyu Yan Danping Jia Hualiang Zhang Bingjie Zhao Xu Lu Yang Liu Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Electrical Engineering Dalian University of Technology School of Artificial Intelligence Shenyang University of Technology School of Information Science and Engineering Shenyang University of Technology

X-Y precision plane motion stage is widely used in precision motion control fields such as lithography machine workpiece stage,CNC machine tool,Laser measuring system,etc.,which requires high accuracy of the position *** X-Y precision plane motion stage uses two permanent magnet linear synchronous motors(PMLSM) as drivers to drive the motion table to perform XY two-degree-of-freedom *** open-closedloop PD-type iterative learning controller(ILC) approach based on accelerated convergence was proposed to improve trajectory tracking performance of *** interval was changed by real-time correction of the exponential gain matrix in the interval to accelerate the convergence *** to the λ norm,the monotone convergence of the proportion differentiation(PD) was developed for the *** controller consists of two terms:a PID controller which enhances robustness to disturbances and system parameter variability and an ILC which generally improves the performance in the repetitive tasks by using the information from previous *** experimental results show that tracking precision and convergence speed of PMLSM can be effectively improved by the scheme.

关键词： X-Y precision plane motion stage Iterative learning control tracking precision convergence rate

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industrial Process

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industria...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Shaojie Yang Peng Li Shuai Li Xiaofeng Zhou Shanghong Jiang Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Information Center of Ansteel Mining Limited Company Anshan China

ISBN: (纸本)9781665401166

Aiming at the characteristics of multi-scale, time series and nonlinear of the complex industrial process data, in order to extract process information more efficiently for improving the diagnosibility, a novel fault diagnosis method based on multi-scale long short term memory- fully convolutional networks (LSTM-FCNs) for industrial process is proposed. Firstly, variational mode decomposition (VMD) is used to obtain the multi-scale components of the process data. Then a parallel LSTM and FCNs optimized by batch normalization and random inactivation is built to extract features for each component. Finally, based on the fusion of multi-scale features, a fully connected layer is used for diagnosis. The LSTM-FCNs method is evaluated by the Tennessee Eastman (TE) benchmark industrial process, and compared with other methods, its effectiveness and superiority are verified.

关键词： Fault diagnosis Fault detection Time series analysis Benchmark testing Feature extraction Safety Data mining

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Based on RseNet-LSTM for Industrial Process

Fault Diagnosis Based on RseNet-LSTM for Industrial Process

引用

IEEE Advanced Information Technology, Electronic and automation Control Conference (IAEAC)

作者： Peifu Yao Shaojie Yang Peng Li China Copper Co.LTD Kunming China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Aiming at the problems that conventional data-driven diagnosis methods are difficult to adaptively extract effective features from industrial process data, and do not make full use of the time series characteristics of process data, in this paper, a fault diagnosis method based on residual convolutional neural networks and long short-term memory networks (ResNet-LSTM) is developed. Firstly, the local spatial features of process data are captured by the deep residual convolution network. Then, the time series characteristics of process data are extracted by LSTM. Finally, the output of the fault category is performed through the softmax classifier. This method can extract features adaptively, more fully extract features in time series fault data, and effectively reduce the difficulty of deep neural network training. The benchmark Tennessee-Eastman (TE) process is used to validate performance of the proposed method. The ResNet-LSTM model is compared with the CNN, LSTM, ResNets, CNN-LSTM models, and the experiment results show that the ResNet-LSTM method achieves better performance.

关键词： Fault diagnosis Training Time series analysis Neural networks Process control Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Power IOT against Attack Based on General Framework

On the Robustness of Power IOT against Attack Based on Gener...

引用

Power and Energy Engineering (ICPEE), International Conference on

作者： Tianyu Wang Weiwei Miao Jianming Zhao Bowen Zhang Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China State Grid Jiangsu Electric Power Co. Ltd Information & Telecommunication Branch Nanjing China

ISBN: (纸本)9781665420471

Power Internet of Things (IOT) is the application of Internet of things in smart grid and the result of the development of information and communication technology to a certain stage. It will effectively integrate communication infrastructure resources and power system infrastructure resources, and improve the informationize level of power system. However, real-world complex systems are often vulnerable under disruptions. Power IOT is facing with different types of attack, which contains natural disasters and human intentional attacks. Motivated by this point, we propose a general framework of Power IOT robustness with different structures against diverse attacks. Evaluation on example IOT networks shows the effectiveness of our framework, and the characteristics of different structure against attacks. Our study contributes to a better understanding of Power IOT robustness, and reveals the designation of the Power IOT network improves the robustness of the network.

关键词： Robustness Power systems Smart grids Information and communication technology Internet of Things Complex systems

来源：评论

学校读者我要写书评

暂无评论

Self-Interference Cancellation Based Hybrid Beamforming Design for Full-Duplex mmWave Communication with Partially-Connected Structures

Self-Interference Cancellation Based Hybrid Beamforming Desi...

引用

International Conference on Communication Technology (ICCT)

作者： Gengshan Wang Zhijia Yang Tierui Gong Chuang Xie State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang China Key Laboratory of Networked Control Systems Shenyang China Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Institute of Computing Technology Beijing China

ISBN: (数字)9781728181417

ISBN: (纸本)9781728181424

The ever increasing demand for throughputs in next-generation wireless communication systems has been put forward for satisfying the exponentially incremental data transmissions. Millimeter wave (mmWave), massive multipleinput multiple-output (MIMO) and full-duplex (FD) are three disruptive technologies to meet the throughputs requirement, which can supply abundant spectral resources, provide multiplexing gain in space, as well as allow simultaneous transmissions, respectively. In this paper, we consider combining these three enablers to form a FD mmWave massive MIMO communication system. Due to the high costs and power consumption of the massive amount of radio-frequency chains components, especially when working on mmWave frequencies, as well as the strong self-interference (SI) that significantly degrades the performance, we focus on the SI cancellation based hybrid beamforming design for the FD mmWave system with partially-connected structures. Resorting to null space projection, we propose our hybrid beamforming design to cancel the SI as well as consider the spectral efficiency (SE) performance. Numerical results verify that our proposed hybrid beamforming design can indeed improve the SE performance when the signal-to-noise ratio (SNR) and the number of RF chains are large enough.

关键词： Radio frequency Interference cancellation Array signal processing Massive MIMO Throughput Millimeter wave communication Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Novel Text Personalized Analysis Model Based on BP Neural Network 6th

A Novel Text Personalized Analysis Model Based on BP Neural ...

引用

6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on intelligent Computing for Sustainable Energy and Environment, ICSEE 2020

作者： Wang, Zhongfeng Wang, Chu Li, Ligang Pan, Zhudong Zou, Yunfeng Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China DongFang Eleceronics CO. LTD Yantai264001 China State Grid Jiangsu Marketing Service Nanjing210019 China

ISBN: (纸本)9789813363779

In online interactive platform, text analysis has greatly changed people's communication, thinking, and promoted the explosive growth of user-generated information. A large number of texts generated by users have become one of the most representative data sources of big data in recent years. Mining and analyzing user-generated information has become essential part on research of social development. The sentiment analysis on social media text as an information processing technology for analyzing, processing, summarizing and reasoning subjective texts with emotions has received extensive attention in academia and industry in recent years, and has been used among many areas of social media and many applications. The traditional text sentiment analysis research work mainly focuses on analyzing emotions from texts, but ignores the individualized differences of users in emotional expression, thus affecting the quality of analysis results. To solve the problems, this paper is about solving the problem of personalized sentiment analysis of social media texts. Considering the wide application of BP neural network technology in social media was proposed to solve the possible challenges of social media text personalized sentiment analysis. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Extracting Semantic Knowledge from GANs with Unsupervised Learning

arXiv

引用

arXiv 2022年

作者： Xu, Jianjin Zhang, Zhaoxiang Hu, Xiaolin The School of Mathematics and Computer Science Panzhihua University The Department of Computer Science and Technology Tsinghua University China The Insitute of Automation Chinese Academy of Sciences The Centre for Artificial Intelligence and Robotics Hong Kong Innovation and Science Insitute Chinese Academy of Sciences Hong Kong The Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems THU-Bosch JCML Center THBI IDG/McGovern Institute for Brain Research BNRist Tsinghua University Beijing China Beijing China

Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations learned by generative models and in particular, Generative Adversarial Networks (GANs). Previous works on the interpretation of GANs reveal that GANs encode semantics in feature maps in a linearly separable form. In this work, we further find that GAN’s features can be well clustered with the linear separability assumption. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN’s features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects, e.g., car, portrait, animals, and so on. With KLiSH, we can sample images from GANs along with their segmentation masks and synthesize paired image-segmentation datasets. Using the synthesized datasets, we enable two downstream applications. First, we train semantic segmentation networks on these datasets and test them on real images, realizing unsupervised semantic segmentation. Second, we train image-to-image translation networks on the synthesized datasets, enabling semantic-conditional image synthesis without human annotations. © 2022, CC BY-SA.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Upper Bound on the Maximum Eigenvalue of Exponential Model Based Spatial Correlation Matrices in Massive MIMO systems 19

An Improved Upper Bound on the Maximum Eigenvalue of Exponen...

引用

19th IEEE International Conference on Communication Technology, ICCT 2019

作者： Gong, Tierui Yang, Guang Mu, Ke Zhao, Chun Yang, Zhijia Shenyang Institute of Automation Chinese Academy of Sciences Key Laboratory of Networked Control Systems State Key Laboratory of Robotics Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781728105352

Massive Multiple-Input, Multiple-Output (MIMO) communications are considered as one of the most promising directions for the next generation communications and have attracted extensive research interests. The using of exponential model is recognized as an effective manner to describe the spatial correlation matrix in a spatially correlated MIMO channel for its simple form and accurate fitting on the experimental measurements. Based on this useful exponential model, an improved upper bound on the maximum eigenvalue of the spatial correlation matrix is given in this paper. Complying with the existing results, the proposed upper bound is also a function of the number of antennas and the absolute value of correlation coefficient. However, the proposed upper bound is obtained using a trace-based derivation, which is tighter than existing results in high spatial correlation massive MIMO systems. Simulations show that the proposed upper bound is closer to the true maximum eigenvalues for both uniform linear array and uniform planar array scenarios, which is expected to be widely used in massive MIMO systems. © 2019 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Antenna Cross-correlation based Compressive Subspace Learning for Wideband Spectrum Sensing 19

Antenna Cross-correlation based Compressive Subspace Learnin...

引用

19th IEEE International Conference on Communication Technology, ICCT 2019

作者： Gong, Tierui Liu, Zhifeng Yang, Zhijia Wang, Gengshan Key Laboratory of Networked Control Systems State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781728105352

To address the performance degradation of wide-band spectrum sensing by sub-Nyquist sampling (SNS) in wireless fading channels, two compressive subspace learning (CSL) algorithms are proposed for signal subspace learning based on antenna cross-correlations for further improving the sensing performance. Both algorithms are developed based on different organizations of SNS samples, and both exploit space diversity and noise uncorrelations between antennas. We further establish the expressions for statistical covariance matrices (SCMs) obtained by SNS samples in the multi-antenna SNS cognitive radio system. Based on the derived SCM expressions, conditions to ensure SCMs without noise contamination are given. Simulations validate the derived conditions and show the improvement on sensing performance over related works. © 2019 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Implementation of CAPI and Traditional PCIe and Delay of Comparison

Implementation of CAPI and Traditional PCIe and Delay of Com...

引用

IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)

作者： Fudong Wang Tao Zhang Bingjie Zhao Fan Yang Qingxin Li Ziyang Li Key Laboratory of Networked Control Systemsm Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang China Chinese Academy of Sciences Dalian University of Technology Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Liaoning Shenyang China

ISBN: (数字)9781728160245

ISBN: (纸本)9781728160252

With the development of artificial intelligence technology and heterogeneous computing, heterogeneous communication speed is becoming more and more important. The latency of transmitting data determines whether a heterogeneous computing architecture is available. Current acceleration cards usually use PCIe interface. IBM developed the CAPI communication architecture for heterogeneous computing. This paper compares the technical principles and delays of the Power CAPI architecture and a high speed PCIe communication method.

关键词： Field programmable gate arrays Kernel Computer architecture Acceleration Linux Hardware

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：