检索结果-内蒙古大学图书馆

Semi-supervised feature contrast incremental learning framework for bearing fault diagnosis with limited lab.led samples

引用

Applied Soft Computing 2025年 176卷

作者： Tao, Xuyang Shen, Changqing Li, Lin Wang, Dong Shi, Juanjuan Zhu, Zhongkui School of Rail Transportation Soochow University Suzhou215131 China Space Optoelectronic Measurement and Perception Lab. Beijing Institute of Control Engineering Beijing100190 China The State Key Laboratory of Mechanical Systems and Vibration Shanghai Jiao Tong University Shanghai200240 China

In real-world scenarios, rotating machinery consistently introduces new fault classes, but intelligent fault diagnosis methods mostly rely on the closed-world assumption, expecting only known fault classes during testing. Moreover, obtaining a sufficient number of lab.led samples is often challenging. These challenges constrain the application and reliability of intelligent diagnosis models in real-world scenarios. Semi-supervised incremental learning enables continuous learning of new fault classes in an open environment, relying on a small number of lab.led samples and a certain number of unlab.led samples. To address the semi-supervised incremental learning problem of fault classes, semi-supervised feature contrast (SSFC) is proposed, a new approach for bearing fault diagnosis with limited lab.led samples. Specifically, a feature contrastive loss incorporating enhancement strategies is designed, independent of lab.led sample information. This approach enables the model to retain knowledge of old classes while learning about new ones. A lab.l reconstruction mechanism based on class centroids is utilized, effectively leveraging the structural information inherent in the samples to support supervised training. A dynamic class prototype cosine classifier initialized by class centroids is devised to mitigate interference between knowledge of fault classes. Finally, two incremental fault diagnosis case studies are designed to evaluate the effectiveness of the proposed method. The fault diagnosis results indicate that SSFC can continuously learn knowledge of new fault classes with limited lab.led samples and effectively alleviate catastrophic forgetting. © 2025 Elsevier B.V.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Track Correlation Based on the Quasi-consistent Extended Kalman Filter 34

Track Correlation Based on the Quasi-consistent Extended Kal...

引用

第三十四届中国控制会议

作者： HE Xingkang JIANG Yanguang XUE Wenchao FANG Haitao HUANG Yi Key Lab. of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of Sciences

ISBN: (纸本)9781467374439

This paper considers the problem of track correlation for the targets obeying general nonlinear dynamics. Based on the quasi-consistent extended Kalman filter(QCEKF), a novel track correlation algorithm is proposed. With the filtering error evaluated by the QCEKF, the proposed track correlation algorithm is proven to ensure that the probability of acceptable fault is lower than the desired value. In the simulation for several typical scenarios, the feasibility and effectiveness of the algorithm are validated.

关键词： track correlation,quasi-consistent extended Kalman filter(QCEKF)

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Detection Based on Features Level Selection for CNN-SVM Combination

Alzheimer's Disease Detection Based on Features Level Select...

引用

2023 IEEE International Conference on Artificial Intelligence and Green Energy, ICAIGE 2023

作者： Zayene, Mohamed Amine Basly, Hend Sayadi, Fatma Ezahra National School of Engineering School of Sousse Lab. Networked Objects Control and Communication Systems Sousse Tunisia

ISBN: (纸本)9798350325539

Neurodegenerative disease especially dementia are reported as disease that leads to death, Alzheimer's Disease (AD) is kind dementia that cause progressive and irreversible brain disorder loss which leads to death. AD shows no symptoms in its early stages which makes diagnosing it its beginning a challenge and helpful for doctors as they can slow down its progress in its early stages. Computer-aided approaches such as machine learning which come up with several techniques to detect AD by extracting features from the given image data and use them to build a classifier. Recently, a subcategory of machine learning called deep learning has widely been employed to enhance the medical diagnosis by attempting notable performance. In fact, these approaches avoid the tricky manual feature extraction using Convolutional Neural Network (CNN) considered as a reference in the field of computer vision. This paper proposes a combination of machine-deep learning technics for early diagnosis of AD from positron emission tomography (PET). We first train our CNN on PET images to extract the most relevant features, then we select the most appropriate CNN's level from where the features will be extracted, which will be feed in a second step as input to a Support Vector Machine based classifier (SVM). The proposed approach achieves notable results that exceeded the performance obtained by various existing approaches. © 2023 IEEE.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

Discrete manufacturing ontology development

Discrete manufacturing ontology development

引用

2017 IEEE International Conference on Industrial Technology, ICIT 2017

作者： Cheng, Haibo Xue, Lingling Wang, Peng Zeng, Peng Yu, Haibin Lab. of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China

ISBN: (纸本)9781509053209

The manufacturing enterprises are currently under great pressures to shorten innovation cycles, grow importance of high-efficiency manufacturing and accommodate new products by building more factories. Discrete manufacturing sectors face a huge array of problems because of its specificity. Knowledge representation is one of the most highlighted troubles. In this case, ontology is a significant knowledge model for representing discrete manufacturing knowledge in a human and machine interpretable way. This knowledge can also be used for automatic design-making to reconfigure the control software that supervises and coordinates the production process of discrete manufacturing. This paper addresses the important issues in developing specific ontology for discrete manufacturing. A generic ontology named DeMO is developed considering all the aspects about product from customized order to resulting production. © 2017 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A prognostics and health management based method for refurbishment decision making for electromechanical systems

引用

IFAC-PapersOnLine 2015年第3期28卷 454-459页

作者： Wang, Kai Tian, Jing Pecht, Michael Xu, Aidong Lab. of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Liaoning110016 China University of Maryland College ParkMD20742 United States

Refurbishing end of life electromechanical products is a value-added operation that provides both economic and environmental benefits. To maximize the benefits from refurbishing, decision making is critical, where the optimized time and the right component for manufacturing are determined. However, there has not been any satisfactory refurbishing decision-making strategy developed. In this paper, a prognostics and health management-based method is developed for refurbishment decision making. First, components are selected for in-situ monitoring using failure modes, mechanisms and effects analysis, then the remaining useful life for the system is estimated by analyzing the in-situ monitoring data so that the optimized refurbishing time can be determined. Finally, near the end of the system life, certain degraded components are selected via diagnosis, and refurbishment is carried out. The procedure of the method is evaluated by an analysis of the refurbishment of instruments in industrial process control. Using this method, the remaining useful life of electromechanical products can be optimally used, and the cost of refurbishment can be minimized. © 2015, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Decision making Health Manufacture Plant life extension systems engineering Decision making strategies Economic and environmental benefits Electro mechanical products Electromechanical systems End of life electromechanical products Industrial process control Prognostics and health managements Refurbishment

来源：评论

学校读者我要写书评

暂无评论

Fusion performance analysis with the correlation

Fusion performance analysis with the correlation

引用

作者： Yuan, Xianghui Han, Chongzhao Lian, Feng MOE Key Lab. for Intelligent and Networked Systems State Key Lab. for Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an Shaanxi China

ISBN: (纸本)9780982443811

Estimation fusion performance with the effect of correlation is analyzed. First, the correlation type is classified into two categories: same source correlation and different source correlation. Second, with the best linear unbiased estimation (BLUE) criteria, the scalar case is analyzed with the effect of correlation. For the same source correlation, with the same absolute value, the fusion result for negative correlation is better than positive correlation. For the different source correlation, with independent extra information, stronger correlation can lead to better fusion result. Finally, the conclusions are supported by some examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing web page classification via local co-training

Enhancing web page classification via local co-training

引用

International Conference on Pattern Recognition

作者： Du, Youtian Guan, Xiaohong Cai, Zhongmin MOE Key Lab. for Intelligent Networks and Network Security State Key Lab. for Manufacturing Systems Engineering Xi'an Jiaotong University 710049 China Center for Intelligent and Networked Systems TNLIST Lab. Tsinghua University China

ISBN: (纸本)9780769541099

In this paper we propose a new multi-view semi-supervised learning algorithm called Local Co-Training (LCT). The proposed algorithm employs a set of local models with vector outputs to model the relations among examples in a local region on each view, and iteratively refines the dominant local models (i.e. the local models related to the unlab.led examples chosen for enriching the training set) using unlab.led examples by the co-training process. Compared with previous co-training style algorithms, local co-training has two advantages: firstly, it has higher classification precision by introducing local learning;secondly, only the dominant local models need to be updated, which significantly decreases the computational load. Experiments on WebKB and Cora datasets demonstrate that LCT algorithm can effectively exploit unlab.led data to improve the performance of web page classification. © 2010 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fully distributed consensus of second-order multi-agent systems using adaptive event-based control

引用

Science China(Information Sciences) 2018年第12期61卷 199-201页

作者： Wei ZHU Qianghui ZHOU DANDan WANG Gang FENG Key Lab of Intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications Key Lab of Industrial Internet of Things & Networked Control Ministry of EducationChongqing University of Posts and Telecommunications Department of Mechanical and Biomedical Engineering City University of Hong Kong

Dear editor,In recent years, the distributed consensus of multiagent systems (MASs) has attracted compelling attention because of its potential applications in many fields such as sensor networks, unmanned aerial vehicle (UAV) formation flying, and multiple signals tracking. The central task in the distributed consensus of MASs is to design distributed control protocols to achieve the consensus

关键词： In MAS Fully distributed consensus of second-order multi-agent systems using adaptive event-based control

来源：评论

学校读者我要写书评

暂无评论

Ranging-aided relative navigation of multi-platforms

引用

control Theory and Technology 2018年第2期16卷 122-132页

作者： Hai-Long PEI Ruican XIA Key Lab of Autonomous Systems and Networked Control Ministry of Education China Unmanned System Engineering Center of Guangdong Province Guangzhou Guangdong 510640 China School of Automation South China University of Technology Guangzhou Guangdong 510640 China

This paper proposes a relative attitude and distance estimation algorithm based on pairwise range measurements between vehicles as well as inertial measurement of each platform. The solution of Wahba＇s Problem is introduced to compute the relative attitude between multi-platforms with the sampled pairwise ranges, in which the relative distance estimation is derived and the estimation error distributions are analyzed. An extended Kalman filter is designed to fuse the estimated attitude and distance with the inertial measurement of each platform. The relative poses between platforms are determined without any external aided measurement. To show this novelty, a real testbed is constructed by our research lab. And the experiment results are positive.

关键词： Multi-vehicles relative navigation Wahba's Problem pose estimation extended Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Scenario-based stochastic programming strategy for microgrid energy scheduling considering uncertainties 2

Scenario-based stochastic programming strategy for microgrid...

引用

2nd International Conference on Renewable Energy and Environmental Technology, REET 2014

作者： Li, He Peng Zang, Chuan Zhi Zeng, Peng Yu, Hai Bin Li, Zhong Wen Lab. of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783038352860

The inherent random and intermittence of the renewable energy resources pose a huge challenge to the Microgrid (MG) energy management systems (EMS). In order to mitigate the effects of uncertainties, we propose a novel two-stage stochastic programming model for the energy scheduling optimization by considering the uncertainties in solar and wind generation, and the plug-in electric vehicles (EV). The random nature of uncertainty is characterized by a scenarios generation approach based on autoregressive moving average (ARMA) model according to probability density function of each random variable. By use of the strategy of scenarios simulation, the stochastic problem is decomposed into the deterministic equivalent problem. The firefly algorithm (FA) is used to solve the equivalent model. The effectiveness and robust of proposed stochastic energy scheduling optimization strategy for MG is valid by comparison with the simulation results of deterministic method. © (2014) Trans Tech Publications, Switzerland.

关键词： Stochastic programming

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：