检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Lan-Qin Zhang Zhen-Tao Liu Cheng-Shan Jiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

To achieve effective deployment of the facial expression recognition(FER) system on marginalized devices,we designed a lightweight neural network based on ShufflenetV2,which can balance the relationship between the number of network parameters and the accuracy of *** this paper,a non-parameter SimAM attention module that can extract 3 D features is employed in the ShufflenetV2 network to enhance the spatial features extraction ability of the network,and the shortcut branch is introduced in Bottleneck for information interaction and feature fusion between *** tests were carried out on the RaFD dataset,and the recognition accuracy reaches 98.04%,while the number of model parameters is only 1.4 M.

关键词： Facial expression recognition Shufflenet SimAM Lightweight Neural Network

来源：评论

学校读者我要写书评

暂无评论

Forward and inverse calculation method for shape and depth of seepage channel of embankment 41

Forward and inverse calculation method for shape and depth o...

引用

第41届中国控制会议

作者： Yue-Cheng Zhai Jun-Lei Song Kai-Feng Dong Fang jin Wen-qin Mo Ya-juan Hui School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Seepage diseases in embankments are very common,and if they cannot be treated in time,they will bring serious safety hazards and even cause embankment break *** the location and depth of a seepage channel is the prerequisite and basis for the treatment of seepage *** present,there are several methods are used to detect seepage in embankments,but none of them can accurately calculate or explain the depth of seepage *** magnetic gradient tensor method,which is widely used in the depth calculation of magnetic sources,is only suitable for the magnetic dipole model,and not suitable for the tubular model similar to the seepage *** view of this,this paper draws on the idea of magnetic exploration,and proposes a forward and inverse calculation method for the depth of the seepage *** method first builds a variety of basic seepage channel models based on certain constraints,and calculates the magnetic field value of each model at each measuring point on the ground *** compare the actual measured magnetic field value with the model magnetic field value to find the closest seepage channel ***,by continuously optimizing the closest model,the real seepage channel is gradually *** model calculated by this method can better reflect the depth information of the real seepage channel,and the depth error is less than lm.

关键词： seepage depth magnetic gradient tensor forward and inversion calculation

来源：评论

学校读者我要写书评

暂无评论

Finite-time stabilization for high-order nonholonomic systems with full state constraints 41

Finite-time stabilization for high-order nonholonomic system...

引用

第41届中国控制会议

作者： Liangguang Li Shiqi Zheng Jiachun Sun Tao Song Qing Chang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper studies the finite-time control problem for a class of high-order nonholonomic systems.A new smooth coupling controller is proposed to make the system states converge to zero in *** order to ensure the states constraints of the nonholonomic systems,a new adding a barrier power integrator technique is *** barrier function is integrated into the traditional adding a power integrator ***,the proposed controller is singular-free and can produce smooth control ***,simulations verify the obtained results.

关键词： Finite time nonholonomic system mobile robots constraints

来源：评论

学校读者我要写书评

暂无评论

Latent-Enhanced Variational Adversarial Active Learning Assisted Soft Sensor

引用

IEEE Sensors Journal 2023年第14期23卷 15762-15772页

作者： Dai, Yun Yang, Chao Liu, Yi Yao, Yuan Zhejiang University of Technology Institute of Process Equipment and Control Engineering Hangzhou310023 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China National Tsing Hua University Department of Chemical Engineering Hsinchu300044 Taiwan

As the acquisition of variables that measure quality is typically challenging, labeled samples for building a model for soft sensors are often inadequate. Additionally, owing to the installation of redundant sensors, high-dimensional process data with strong correlations are acquired. Therefore, in this study, a sample selection strategy for active learning (AL), referred to as latent-enhanced variational adversarial AL (LVAAL), is developed to enhance quality prediction performance with limited labeled data. The LVAAL method uses a minimax game to explore the latent representation of the original data. Specifically, a latent-enhanced variational autoencoder (LEVAE) is used to deceive the adversarial network into predicting all samples, both labeled and unlabeled, as labeled. However, the adversarial network attempts to indicate the difference between latent representations. Subsequently, Gaussian process regression (GPR) is adopted as a base model for LVAAL. With the proposed LVAAL selection strategy, informative unlabeled samples are incrementally selected, thereby enhancing the prediction performance. The application results for a numerical case and an industrial example demonstrate the advantages of LVAAL compared with existing AL strategies. © 2001-2012 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Image Semantic Segmentation Scheme based on XGBoost combination with Convolution Feature Extraction 41

Image Semantic Segmentation Scheme based on XGBoost combinat...

引用

第41届中国控制会议

作者： Zichen Dai Xuewen Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Aiming at the problem that the existing image semantic segmentation schemes based on convolutional neural network require a large number of training data sets and high training cost,this paper presents a novel scheme for image semantic segmentation based on extreme gradient boosting(XGBoost),a scalable tree boosting system and the combination of convolution feature extraction(CFE).The scheme consists of three ***,convolution operation is performed on a small amount of RGB pixel information of the image processed by Gaussian filtering to acquire more multi-dimensional image feature ***,some preprocessing techniques of image feature information,including feature normalization and image label pixel number uniformity are performed to match the ***,the preprocessed image feature information and corresponding labels are input into XGBoost to train and predict the data of the test *** simulation and practical tests,compared with other commonly used few data classification algorithms like k-Nearest-Neighbor(kNN) and Support-VectorMachine(SVM),this scheme can achieve high precision pixel-level image semantic segmentation under the condition of lower training cost.

关键词： Image Semantic Segmentation Convolutional Feature Extraction XGBoost Gaussian Filtering Low Training Cost

来源：评论

学校读者我要写书评

暂无评论

Research on Virtual USB Storage in Remote File Transfer 41

Research on Virtual USB Storage in Remote File Transfer

引用

第41届中国控制会议

作者： Jie Li Weihua Cao Zhicheng Zhao Han Peng School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Virtual USB storage technology is an application technology that integrates Universal Serial Bus(USB) virtualization,file system virtualization and reliable file data transfer,which is often applied to virtual file transfer in data *** the current traditional virtual USB storage technology relies on specific software and poor system compatibility,this paper proposes a hardware-based virtual USB storage solution that uses the built-in USB driver of each operating system to map the local USB storage device to the remote controlled server to achieve file reading and *** show that the scheme proposed in this paper has the advantages of simple implementation,good system compatibility,safe and stable *** technology has been successfully applied to the data room management of an enterprise.

关键词： USB storage virtualization file transfer remote mapping

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control for Interval Type-2 T-S Fuzzy systems Under New Dynamic Event-Triggered Mechanism 41

Model Predictive Control for Interval Type-2 T-S Fuzzy Syste...

引用

第41届中国控制会议

作者： Chaoling Zhang Fan Wei Xiongbo Wan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we focus on dynamic event-triggered model predictive control(MPC) problem for interval type-2 Takagi-Sugeno(IT2 T-S) fuzzy systems with hard constraints on the state.A dynamic event-triggered mechanism(DETM) with two adjusting variables is devised to reduce data transmission *** MPC problem is formulated as a "min-max" problem over the infinite *** purpose is to find a series of desired sub-controllers in terms of MPC such that the underlying IT2 T-S fuzzy system is asymptotically *** taking the T-S fuzzy nonlinearities and the DETM into consideration,we give the design method of the controller through an online auxiliary optimization problem with several constraint conditions.A simulation example is used to demonstrate the effectiveness and the validity of the proposed methods.

关键词： Dynamic event-triggered mechanism adjusting variables model predictive control interval type-2 T-S fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Research on Energy Storage control Strategy Considering Economy 41

Research on Energy Storage Control Strategy Considering Econ...

引用

第41届中国控制会议

作者： Zihan Zhang Zhijian Fang Jie Cai Wenhe Peng School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Energy storage system is generally used to ensure the stability and reliability of *** the system generally contains multiple energy storage units,and due to the process,material and other aspects of the limitation,the initial state of charge(SOC) of each energy storage unit cannot be guaranteed to be completely equal,which leads to the shortening of the life of energy storage unit,and affect the economic benefits of energy storage system ***,this paper analyzes the influence conditions between energy storage units according to the calculated formula of energy storage unit *** value of charge between energy storage systems is analyzed through the active power output of the system,and then the difference is obtained by comparing the value of charge of each energy storage unit with the average value of charge of each *** the iterative algorithm is used to update the state of each node,and the balance factor is introduced to gradually reduce the difference on the basis of droop control to optimize and control the output of these energy storage nodes to achieve SOC *** the economic benefits such as maintenance cost of energy storage system are ***,a working model of microgrid is established and the feasibility and economy of this method are verified by simulation.

关键词： Economy Micro grid Energy storage system Droop control SOC balance

来源：评论

学校读者我要写书评

暂无评论

An Improved Exponential Stability Criterion of Generalized Neural Networks With Intermittent Large-Delay Periods 41

An Improved Exponential Stability Criterion of Generalized N...

引用

第41届中国控制会议

作者： Jin-Meng Xu Yong He Wen-Hu Chen Zhe-Li Yuan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper focuses on the exponential stability analysis of generalized neural networks(GNNs) with time-varying delays,where the time delays include several intermittent large-delay periods(LDPs).First,the improved piecewise augmented Lyapunov-Krasovskii functional(LKF) candidate is constructed based on the delay-dependent state ***,some advanced inequalities are adopted to estimate the derivative of LKF *** with switching techniques,an exponential stability criterion with less conservativeness is *** last,a numerical example is used to verify the advantage of the proposed criterion.

关键词： Time-varying delay Switched delay system Large-delay period Exponential stability

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Discrete-Time Delayed Neural Networks via A Cubic Function Negative-Determination Lemma 41

Stability Analysis of Discrete-Time Delayed Neural Networks ...

引用

第41届中国控制会议

作者： Wen-Hu Chen Fei Long Cui Zhu Chuan-Ke Zhang Yong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper is concerned with the stability analysis of discrete-time neural networks with a time-varying ***,an improved augmented Lyapunov-Krasovskii functional(LKF) is established by adding single/double-summation ***,by utilizing summation inequalities,the forward difference of the constructed functional is estimated as a cubic function with respect to the *** applying the cubic function negative-determination lemma,a less conservative stability criterion is obtained,whose advantages are demonstrated via a numerical example.

关键词： Discrete-time neural networks time-varying delay cubic function negative-determination lemma stability analysis

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：