检索结果-内蒙古大学图书馆

Identification of Linear Parameter Varying Systems with Missing Output Data Using Generalized Expectation-Maximization Algorithm

引用

IFAC Proceedings Volumes 2014年第3期47卷 9364-9369页

作者： X. Yang W. Xiong B. Huang H. Gao Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin Heilongjiang 150080 China Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Jiangnan University Wuxi Jiangsu 214122 China Department of Chemical and Materials Engineering University of Alberta Edmonton Alberta T6G 2G6 Canada Research Institute of Mechatronics and Automation Bohai University Jinzhou 121013 China and Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin Heilongjiang 150080 China

This paper is concerned with the identification problems of linear parameter varying (LPV) systems with randomly missing output data. Since one local linearized model cannot capture the global dynamics of the nonlinear industrial process, the multiple-model LPV model in which the global model is constructed by smoothly weighted combination of multiple local models is considered here. The problem of missing output variables data is commonly encountered in practice. In order to handle the multiple-model identification problems of LPV systems with incomplete data, the local model is taken to have a finite impulse response (FIR) model structure and the generalized expectation-maximization (EM) algorithm is adopted to estimate the unknown parameters of the global LPV model. To avoid the problems of ill-conditioned matrices and high sensitivity of parameters to noise, the prior information on the coefficients of each local FIR model is employed to construct the prior probability of unknown parameters. Then the maximum a posteriori (MAP) estimates of the global model parameters are derived via the generalized EM algorithm. The numerical example is presented to demonstrate the effectiveness of the proposed method.

关键词： Linear parameter varying systems Generalized EM algorithm Missing output data Maximum a posteriori estimates

来源：评论

学校读者我要写书评

暂无评论

Continuous use of ERP-based BCIs with different visual angles in ALS patients

arXiv

引用

arXiv 2017年

作者： Jin, Jing Allison, Brendan Z. Zhang, Yu Chen, Yan Zhou, Sijie Dong, Yi Wang, Xingyu Chchocki, Andrzej Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai China Department of Neurology Huashan hospital Fudan University Shanghai China Department of Cognitive Science University of California at San Diego San DiegoCA United States Laboratory for Advanced Brain Signal Processing Brain Science Institute RIKEN Wako-shi Japan Systems Research Institute PAS Warsaw Poland Torun Poland

Objective: Amyotrophic lateral sclerosis (ALS) is a rare disease, but is also one of the most common motor neuron diseases, and people of all races and ethnic backgrounds are affected. There is currently no cure. Brain computer interfaces (BCIs) can establish a communication channel directly between the brain and an external device by recognizing brain activities that reflect user intent. Therefore, this technology could help ALS patients in promoting functional independence through BCI-based speller systems and motor assistive devices. Methods: In this paper, two kinds of ERP-based speller systems were tested on 18 ALS patients to: (1) assess performance when they spelled 42 characters online continuously, without a break;and (2) to compare performance between a matrix-based speller paradigm (MS-P, mean visual angle 6◦) and a new speller paradigm that used a larger visual angle called the large visual angle speller paradigm (LS-P, mean visual angle 8◦). Results: Although results showed that there were no significant differences between the two paradigms in accuracy trend over continuous use (p>0.05), the fatigue during the LS-P condition was significantly lower than that of MS-P (p Copyright © 2017, The Authors. All rights reserved.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Large Scale and High-Precision Crop Recognition Using Satellite Remote Sensing Images

Large Scale and High-Precision Crop Recognition Using Satell...

引用

Chinese Automation Congress (CAC)

作者： Xuanting Tao Jinglu Tan Jianguo Zhang Suleyman I. Allakhverdiev Zhenyu Xu Ya Guo Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China Department of Chemical & Biomedical Engineering University of Missouri Columbia Missouri USA Wuxi Agricultural Equipment Technology Extension Center Wuxi China Timiryazev Institute of Plant Physiology RAS Moscow Russia Longcom Internet of Things Co. Ltd Hefei China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Precise large-scale crop recognition is crucial for estimating crop yield and carbon assimilation. Current research on crop type recognition based on deep learning is often limited to a single crop and small areas, with poor model transferability. When performing multi-crop recognition over large areas, the accuracy significantly decreases. Therefore, it is necessary to establish a high-precision crop type recognition model with strong generalization capability. A deep learning model (LSTM-Transformer Parallel, LTP) based on the combination of LSTM (Long Short-Term Memory) network and Transformer self-attention mechanism architecture is proposed in this paper. The model captures the dependencies among crop NDVI time series data to achieve high-precision recognition of large-scale crop types. Experimental results show that in crop recognition experiments using small-scale agricultural area data, the recognition results of the LTP, TSMixer, and SegRNN models all performed excellently, with average accuracies of 94.55%, 94.41%, and 94.79%, respectively. In contrast, in crop recognition experiments using large-scale agricultural area data, the average accuracy of the LTP model reaches 93.77%, while the accuracies of the TSMixer and SegRNN models are 82.30% and 84.13%, respectively. This indicates that the LTP model not only performs well on small-scale agricultural area datasets but also significantly outperforms models in the literature on large-scale agricultural area datasets, demonstrating strong generalization capability. It provides a reliable method for large-scale multi-crop recognition, contributing to global food security and carbon cycle assessment.

关键词： Deep learning Analytical models Accuracy Satellites Time series analysis Crops Transformers Data models Long short term memory Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Intelligent imaging algorithm of blast furnace radar array based on threshold synergism and data interaction

引用

Gongcheng Kexue Xuebao/Chinese Journal of Engineering 2015年 37卷 66-72页

作者： He, Shu-Rui Chen, Xian-Zhong Hou, Qing-Wen School of Automation University of Science and Technology Beijing Beijing100083 China Key Laboratory of the Ministry of Education of China for Advanced Control of Iron and Steel Process Beijing100083 China

A series of optimized signal processing algorithm was proposed for the radar system based on two-dimensional imaging of the burden surface. Firstly, a self-correlation algorithm was proposed to restrain background noises based on signal superposition. Secondly, the intelligent synergism adopting time-varying threshold on the basis of the prior knowledge of metallurgy and statistical characteristics of echo for multi-radar was accomplished. Finally, the interaction and synergism of data combined the parameters of industrial field with principal component analysis were proposed, as well as "outlier-removed α-β filter", and a suitable model of burden surface with outliers α-β filter algorithm was optimized. After practical verification, those improved signal processing methods were proved to enhance the stability of imaging and decrease the values of image fluctuation and abnormal proportion. The detecting probability and accuracy for the burden surface of the blast furnace radar were increased by 21.57% and 10.42%, respectively, which meet the requirements of real-time detection for the burden surface better. © All right reserved.

关键词： Blast furnaces

来源：评论

学校读者我要写书评

暂无评论

Hexapod Robot Gait Switching Based on Different Wild Terrains

Hexapod Robot Gait Switching Based on Different Wild Terrain...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Shijie Fei Yiyang Chen Hongfeng Tao Hongtian Chen School of Mechanical and Electrical Engineering Soochow University Suzhou P. R. China Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Jiangnan University Wuxi P. R. China Department of Automation Shanghai Jiao Tong University Shanghai China

Hexapod robots have become an indispensable part of legged robots due to their excellent stability and traversability, and have recently become a hot research topic. In complex outdoor environments, the ability of the hexapod robot to switch its motion strategy according to the terrain is crucial for improving its mobility. This paper presents a terrain recognition network that enables our hexapod robot to switch its forward gait based on the different types of outdoor terrain. This method provides better stability for the hexapod robot than traditional single-gait walking through different terrains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Image Annotation Method Based on SVM and Semi-supervised EM

引用

Acta Automatica Sinica 2010年第7期36卷 960-967页

作者： Yan-Yu Gao Yi-Xin YIN Takashi UOZUMI School of Information Engineering University of Science and Technology Beijing Beijing 100083 P. R. China Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education) University of Science and Technology Beijing Beijing 100083 P. R. China Department of Computer Science and Systems Engineering Muroran Institute of Technology Muroran 050-8585 Japan

Automatic image annotation, which aims at automatically identifying and then assigning semantic keywords to the meaningful objects in a digital image, is not a very difficult task for human but has been regarded as a difficult and challenging problem to machines. In this paper, we present a hierarchical annotation scheme considering that generally human s visual identification to a scenery object is a rough-to-fine hierarchical process. First, the input image is segmented into multiple regions and each segmented region is roughly labeled with a general keyword using the multi-classification support vector machine. Since the results of rough annotation affect fine annotation directly, we construct the statistical contextual relationship to revise the improper labels and improve the accuracy of rough annotation. To obtain reasonable fine annotation for those roughly classified regions, we propose an active semi-supervised expectation-maximization algorithm, which can not only find the representative pattern of each fine class but also classify the roughly labeled regions into corresponded fine classes. Finally, the contextual relationship is applied again to revise the improper fine labels. To illustrate the effectiveness of the presented approaches, a prototype image annotation system is developed, the preliminary results of which showed that the hierarchical annotation scheme is effective.

关键词： Hierarchical image annotation support vector machine (SVM) semi-supervised expectation-maximization coexistence relative location relationship

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Optimal Infinite-Horizon control of Probabilistic Boolean control Networks

arXiv

引用

arXiv 2023年

作者： Ni, Jingjie Li, Fangfei Wu, Zheng-Guang The School of Mathematics East China University of Science and Technology Shanghai200237 China The Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China The Institute of Cyber-Systems & Control Zhejiang University Zhejiang Hangzhou310027 China

In this paper, a deep reinforcement learning based method is proposed to obtain optimal policies for optimal infinite-horizon control of probabilistic Boolean control networks (PBCNs). Compared with the existing literatures, the proposed method is model-free, namely, the system model and the initial states needn’t to be known. Meanwhile, it is suitable for large-scale PBCNs. First, we establish the connection between deep reinforcement learning and optimal infinite-horizon control, and structure the problem into the framework of the Markov decision process. Then, PBCNs are defined as large-scale or small-scale, depending on whether the memory of the action-values exceeds the RAM of the computer. Based on the newly introduced definition, Q-learning (QL) and double deep Q-network (DDQN) are applied to the optimal infinite-horizon control of small-scale and large-scale PBCNs, respectively. Meanwhile, the optimal state feedback controllers are designed. Finally, two examples are presented, which are a small-scale PBCN with 3 nodes, and a large-scale one with 28 nodes. To verify the convergence of QL and DDQN, the optimal control policy and the optimal action-values, which are obtained from both the algorithms, are compared with the ones based on a model-based method named policy iteration. Meanwhile, the performance of QL is compared with DDQN in the small-scale PBCN. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Zwitterionic Liquid Hydrogel Sustained-Release Strategy for High-Performance Nanofiltration Membrane

SSRN

引用

SSRN 2022年

作者： Xiao, Luqi Bai, Ju Lai, Wei Jiao, Yang Wu, Qi Liu, Hongyan Zhang, Yizhou Shan, Linglong Luo, Shuangjiang School of Rare Earths University of Science and Technology of China Hefei230026 China CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex Systems Beijing Key Laboratory of Ionic Liquids Clean Process Institute of Process Engineering Chinese Academy of Sciences Beijing100190 China Ganjiang Innovation Academy Chinese Academy of Sciences Ganzhou341000 China Key Laboratory of Organic Compound Pollution Control Engineering Ministry of Education School of Environmental and Chemical Engineering Shanghai University Shanghai200444 China Langfang Green Industrial Technology Center Langfang065000 China

controlling amine monomer diffusion behavior plays a crucial role in fabricating well-defined architecture and high-performance nanofiltration (NF) membranes through interfacial polymerization. Herein, a zwitterionic liquid hydrogel transition layer was introduced to the sustained-release amine monomer to the regulated interfacial polymerization process to fabricate a high-performance NF membrane. The hydrogel (Gel) was fabricated via in-situ one-step UV photo-initiated free-radical polymerization between 1-vinyl-3-ethylimidazolium chloride ([VEIm][Cl]) and 3-sulfopropyl methacrylate potassium salt (SMP) on PES substrate membrane surface. Then polyamide layer formed on the Gel layer surface under the regulation of mitigating the amine diffusion behavior. Low-field time-domain NMR (LF-NMR) analysis and water-absorbing demonstrated that the Gel-PA membrane showed high water-membrane interaction. Positron annihilation lifetime spectroscopy (PALS) also confirmed the Gel-PA composite membrane possessed enlarged free volume . Membrane surface and cross-sectional SEM morphologies also showed the Gel-PA membrane with a less ridge-and-valley loose structure and thinner thickness. Combined with the uptake ability of the Gel layer, the obtained Gel-PA composite membrane displayed a high permeance of 13.22 L m -2 h -1 bar -1 , a high Na 2 SO 4 rejection of 98.23%, a favorable NaCl/Na 2 SO 4 selectivity of 49.75, and excellent long-term operational stability . This sustained-release strategy provides a facial and feasible approach to controlling the IP process and obtaining high-performance nanofiltration membranes. © 2022, The Authors. All rights reserved.

关键词： Nanofiltration

来源：评论

学校读者我要写书评

暂无评论

Repetitive T-S Fuzzy Model-Based Iterative Learning control Law Design

Repetitive T-S Fuzzy Model-Based Iterative Learning Control ...

引用

IEEE Conference on Decision and control

作者： Robert Maniarski Wojciech Paszke Hongfeng Tao Eric Rogers Institute of Automation Electronic and Electrical Engineering University of Zielona Góra ul. Szafrana 2 Zielona Góra Poland Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Jiangnan University Wuxi China School of Electronics and Computer Science University of Southampton Southampton UK

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper develops an iterative learning control law for a class of nonlinear systems. The approach used to represent the nonlinear system dynamics is a Takagi-Sugeno fuzzy repetitive process that considers the two directions of information propagation. Then, the control action investigated is a state feedback control law combined with a PD-type feed-forward learning control law. Consequently, linear matrix inequality techniques can be used for control design. Furthermore, this approach allows the design of control action to satisfy the requirements on both the error convergence and the transient dynamics. Finally, an example demonstrates the properties of the new design.

关键词： State feedback control design Takagi-Sugeno model Nonlinear dynamical systems Linear matrix inequalities Transient analysis Iterative learning control Convergence

来源：评论

学校读者我要写书评

暂无评论

Visualization of layer distribution of furnace burden based on array radar of blast furnace

引用

Gongcheng Kexue Xuebao/Chinese Journal of Engineering 2015年 37卷 173-178页

作者： Hou, Qing-Wen Li, Xu Chen, Xian-Zhong Lu, Yi-Fang School of Automation & Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Advanced Control of Iron and Steel Process Ministry of Education Beijing100083 China

The visualization of layer distribution of furnace burden in the time-radial-height dimension was presented based on array radar measured data. Abnormal data mining and data sampling method were adopted to obtain valid data. According to the burden falling model, the layer distribution of furnace burden was calculated. The cubic spline interpolation algorithm was used in the radial dimension and the improved least square method was proposed in the time dimension, which were used for conducting piecewise fitting of burden surface. The visualization system achieves multi-view visualization of burden surface and burden layer in the time-radial-height dimensions, which shows the change course of burden surface and provides an intuitive way to the blast furnace operation and control. © All right reserved.

关键词： Visualization

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：