检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Hao Hao Aimin Zhou Hu Zhang Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University Shanghai China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-mechanical Engineering Institute Beijing China

Preselection is an important strategy to improve evolutionary algorithms’ performance by filtering out unpromising solutions before fitness evaluations. This paper introduces a pre-selection strategy based on an approximated Pareto domination relationship for multiobjective evolutionary optimization. For each objective, a binary relation between each pair of solutions is constructed based on the current population, and a binary classifier is built based on the binary relation pairs. In this way, an approximated Pareto domination relationship can be defined. When new trial solutions are generated, the approximated Pareto domination is used to select promising solutions, which shall be evaluated by the real objective functions. The new preselection is integrated into two algorithms. The experimental results on two benchmark test suites suggest that the algorithms with preselection outperform their original ones.

关键词： Filtering Computational modeling Sociology Training data Evolutionary computation Approximation algorithms Linear programming

来源：评论

学校读者我要写书评

暂无评论

Impulse control of chaos in the exible shaft rotating-lifting system of the mono-silicon crystal puller

arXiv

引用

arXiv 2020年

作者： Zhou, Zi-Xuan Grebogi, Celso Ren, Hai-Peng Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an Shaanxi710048 China North Minzu University Library Yinchuan Ningxia750021 China Institute for Complex System and Mathematical Biology University of Aberdeen AB24 3UE United Kingdom

Chaos is shown to occur in the flexible shaft rotating-lifting (FSRL) system of the mono-silicon crystal puller. Chaos is, however, harmful for the quality of mono-silicon crystal production. Therefore, it should be suppressed. Many chaos control methods have been proposed theoretically and some have even been used in applications. For a practical plant displaying harmful chaos, engineers from a specified area usually face with the challenge to identifying chaos and to suppressing it by using a proper method. However, despite of the existing methods, chaos control method selection in the FSRL system is not a trivial task. For example, for the OGY method, if one cannot find a practical adjustable parameter, then the OGY method cannot be applied. An impulsive control method is being proposed which is efficiently able to suppress chaos in the FSRL system. The selection of the control parameters is obtained by using the Melnikov method. Simulation results show the correctness of our theoretical analysis and the effectiveness of the proposed chaos control method. Copyright © 2020, The Authors. All rights reserved.

关键词： Silicon

来源：评论

学校读者我要写书评

暂无评论

Temperature prediction of generator carbon brush based on LSTM neural network

Temperature prediction of generator carbon brush based on LS...

引用

Chinese Automation Congress (CAC)

作者： Qing Zhang Tingyang Jiao Yinxing Ma Youmin Zhang Xiaohui Wu Pengyue Wu Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China The Faculty of Computing Science The University of Alberta Edmonton Alberta Canada Concordia University Montreal Canada Huaneng Weihai Power Generation Co. Ltd Wei’hai China Xi’an Thermal Power Research Institute Co. Ltd Xi’an China

ISBN: (纸本)9781665426480

In order to improve the prediction accuracy of the carbon brush temperature trend of the generator, analyzing the operating state of the generator more accurately, and reduce other accidents like the unplanned outage caused by carbon brush failure of the generator in the power plant. A multi-step temperature prediction model based on the LSTM (Long Short-Term Memory) neural network is proposed. The data comes from real operating carbon brush temperature of Weihai Power Plant in ten days. Then the temperature prediction model is established to achieve an accurate prediction of the carbon brush temperature in the future day. The prediction error is stable within 0.4 °C. By comparing the predicted results of the BP model and Elman model, the error between the predicted results of each model and the actual temperature data is analyzed. By comparing the indicators and analyzing the actual curves, the results show that LSTM neural network has higher accuracy in predicting the temperature of generator carbon brush. This method is of reference significance for the accurate analysis of the operation state of the generator and the load analysis of the excitation system.

关键词： Analytical models Temperature distribution Brushes Neural networks Predictive models Market research Generators

来源：评论

学校读者我要写书评

暂无评论

Research method of identifying transformer inrush current and fault current based on VMD-HHT

Research method of identifying transformer inrush current an...

引用

第三十八届中国控制会议

作者： Shangbin Jiao Yuan Chang Qing Zhang Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing(Xi'an University of Technology)

To settle the problem that identifying inrush current and fault current of large transformer is difficult,a new identification method which is a combination of variational mode decomposition(VMD)and Hilbert-Huang transform(HHT)is come up ***,the inrush current and fault current signals are decomposed into multi-band intrinsic mode function(IMF)by using ***,the instantaneous frequencies of each intrinsic mode function(IMF)of inrush current and fault current are calculated respectively by Hilbert-Huang transform,so that the corresponding Hilbert spectrum is ***,the Hilbert spectra of inrush current and fault current are filtered by band-pass filter to remove the similar main lobes and some *** is concluded that the Hilbert spectra of inrush current and fault current are significantly different from each *** order to facilitate engineering application,the energy values of the first 16 sites in the Hilbert spectra of the two are taken to identify the inrush current and fault current,and the protection criteria are obtained.

关键词： inrush current fault current variational mode decomposition Hilbert-Huang transform

来源：评论

学校读者我要写书评

暂无评论

A novel single-phase-to-earth fault line method in small current grounding systems

A novel single-phase-to-earth fault line method in small cur...

引用

第三十八届中国控制会议

作者： Jiao Shangbin Guo Jingwen Li Yunjun Xiao Ting Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing(Xi'an University of Technology)

Aiming at the problem that the fault characteristics of single-phase-to-ground fault in small current grounding system are not obvious,the fault situation is complex,and the single fault criterion is difficult to accurately select the *** this paper,a new method for small current single-phase ground fault line selection is proposed based on improved Empirical Wavelet Transform(EWT)and D-S evidence *** method firstly smoothes the transient zero-sequence current spectrum of each feeder,and then performs EWT decomposition to extract the natural modal function that best characterizes the original signal,and obtains the energy peak and the intrinsic modal energy value to determine the probability of each line fault,***,the results of the two methods are fused by D-S evidence theory,and the final line selection results are obtained.

关键词： Small current Single-phase grounding Fault line selection EWT D-S evidence theory

来源：评论

学校读者我要写书评

暂无评论

Learning Latent Semantic Attributes for Zero-Shot Object Detection

Learning Latent Semantic Attributes for Zero-Shot Object Det...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Kang Wang Lu Zhang Yifan Tan Jiajia Zhao Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineer Institute Beijing China

ISBN: (数字)9781728192284

ISBN: (纸本)9781728185361

Zero-shot Object Detection (ZSD) aims to locate and classify instances of unseen categories. Existing methods focus on learning the mapping from visual space to semantic space, while the learning of discriminative representations for ZSD has not gained enough attention. In this paper, we demonstrate the necessity to learn discriminative semantic representations for ZSD, and propose a new end-to-end framework for this task. Our framework is able to learn discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes, and refine the user-defined attributes with the help of unseen and external classes. The proposed method is extensively evaluated on two challenging ZSD datasets, and the experimental results show that our method significantly outperforms several existing methods.

关键词： Visualization Conferences Semantics Object detection Tools Boosting Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Learning Convolutional Neural Network Approach for Network Robustness Prediction

arXiv

引用

arXiv 2022年

作者： Lou, Yang Wu, Ruizi Li, Junli Wang, Lin Li, Xiang Chen, Guanrong The Department of Computing and Decision Sciences Lingnan University Hong Kong The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The College of Computer Science Sichuan Normal University Chengdu610066 China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201210 China The Department of Control Science and Engineering Tongji University Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

Network robustness is critical for various societal and industrial networks again malicious attacks. In particular, connectivity robustness and controllability robustness reflect how well a networked system can maintain its connectedness and controllability against destructive attacks, which can be quantified by a sequence of values that record the remaining connectivity and controllability of the network after a sequence of node- or edge-removal attacks. Traditionally, robustness is determined by attack simulations, which are computationally very time-consuming or even practically infeasible. In this paper, an improved method for network robustness prediction is developed based on learning feature representation using convolutional neural network (LFR-CNN). In this scheme, higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction. Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors;2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability;3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations;4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures. © 2022, CC BY.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Distributed Observer Design for Achieving Asymptotical Omniscience over Time-variant Disconnected Networks ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 3565-3570页

作者： Haotian Xu Jingcheng Wang Hongyuan Wang Shangwei Zhao Hai Lin Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Autonomous Systems and Intelligent Control International Joint Research Center Xi’an Technological University Xi’an Shaanxi 710021 China

This paper investigates the distributed observer design for linear system under time-variant disconnected communication network. By constructing basic eigenvectors of 0-eigensubspace of disconnected Laplacian Matrix and using LMIs method, we prove the distributed observer cannot achieve omniscience asymptotically under switching topology without constraining the system matrix or alternative topologies set. To deal with this problem, this paper investigates three kinds of constraints and the system matrix only needs to satisfy any one of them. Then a group of sufficient conditions corresponding to the asymptotic omniscience of distributed observer under switching topology are proved by Lyapunov analysis. Finally, a numerical simulation shows the validity of our method.

关键词： Distributed observer Continuous time system estimation Consensus Sensor networks Switching topology

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM Image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

An adaptive fault detection strategy for Cz crystal growth process

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Mu, Lingxia Feng, Nan Zhang, Zhenhua Zhang, Youmin Zhang, Jian Xian University of Technology Crystal Growth Equipment and Systems Integration National Engineering Research Center Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xian710048 China University of Science and Technology Beijing School of Intelligence Science and Technology Beijing100083 China Concordia University Department of Mechanical Industrial and Aerospace Engineering MontrealQCH3G 1M8 Canada

The monitoring and fault detection for the Czochralski (Cz) crystal growth process is important to ensure the quality of the produced mono-crystalline silicon. The Cz process is a typical multi-modes industrial process, which makes the detection difficult in distinguish the change caused by the fault or mode switching. In this paper, an adaptive fault detection strategy for Cz crystal growth process is proposed. Firstly, quality-related variables are selected from numerous process variables, based on which the training dataset is constructed. Then, a fault detection model is built based on slowly-varying feature and statics indicator. A model switching strategy and updating algorithm are designed to handle the abnormal situation caused by the mode switching or fault occurrence. Three representative experiments are conducted to verify the performance of the proposed strategy, including numerical cases, a publicly available dataset, and Cz crystal growth process from our laboratory. © 1963-2012 IEEE.

关键词： Crystal growth from melt

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：