检索结果-内蒙古大学图书馆

第29届中国控制与决策会议

作者： Hairong Yin Qingling Wang Changyin Sun School of Automation Southeast University Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University

ISBN: (纸本)9781509046584

To deal with the position and attitude tracking control problem of a quadrotor unmanned aerial vehicle(UAV),the proportional-derivative(PD) and integral sliding mode techniques are adapted to design a double-loop controller in this ***,the system model of quadrotor is established according to the Lagrange ***,a PD control method is put forward in the outer-loop to achieve the position ***,an integral sliding mode control method is adapted in the inner-loop to ensure the quadrotor track the desired attitude angles in the presence of external ***,a double-loop controller is ***,simulation results are presented to verify the effectiveness and robustness of the proposed control laws.

关键词： quadrotor PD control integral sliding mode control double-loop controller tracking

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Depth Completion with Adaptive Online Adaptation 23

Self-supervised Depth Completion with Adaptive Online Adapta...

引用

7th International Conference on Machine Learning and Soft Computing, ICMLSC 2023

作者： Chen, Yang Tan, Yang Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781450398633

Although depth completion has achieved remarkable performance relying on deep learning in recent years, these models tend to suffer a performance degradation when exposed to new environments. Online adaptation, where the model is trained in a self-supervised manner during testing, seems a promising technique to alleviate the drop. However, continuous online adaptation may cause the model to over-adapt and miss the optimal parameters, resulting in oscillation or even degradation of the model performance, in addition to wasting computational resources. Therefore, this paper proposes an adaptive online adaptation framework to make model adaptively trigger online adaptation when encountering novel environments and stop adaptation when model has adapted to the current environment. In detail, we design a trigger to detect the familiarity of model to the current scenario based on image similarity and then launch online adaptation when the scenario is novel. Besides, we elaborate a stopper to monitor the error between prediction and depth input and convert online adaptation to inference when online adaptation does not bring improvement for model. Experimental results demonstrate that our method improves the accuracy of model prediction and increases average running speed of the model on each frame in online adaptation. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-Time Cooperative Tracking for Delayed Disturbed Multi-Agent systems Under Dynamic Event-Triggered control

引用

IEEE/CAA Journal of Automatica Sinica 2022年第5期9卷 930-933页

作者： Jian Liu Yongbao Wu Mengwei Sun Changyin Sun School of Automation Southeast UniversityNanjing 210096 Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of EducationSoutheast UniversityNanjing 210096China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601China IEEE

Dear editor,Recently,researchers have obtained many new results about the multi-agent systems(MASs)[1]-[3].In[1],the fixed-time cooperative control(FTCC)algorithm of linear MASs with matched disturbances was *** nonholonomic chained-form dynamics case was considered in[2].In[3],the output tracking problem with data packet dropout was solved for high-order ***,delay frequently occurs because of the non-ideal data transmission[4],and the corresponding FTCC algorithm of MASs with delay was given in[5].

关键词： editor Dynamic Trigger Event

来源：评论

学校读者我要写书评

暂无评论

Interval analysis for neural networks with application to fault detection

引用

Science China(Information Sciences) 2024年第11期67卷 222-237页

作者： Zhenhua WANG Youdao MA Song ZHU Thach Ngoc DINH Yi SHEN Department of Control Science and Engineering Harbin Institute of Technology National Key Laboratory of Complex System Control and Intelligent Agent Cooperation School of Mathematics China University of Mining and Technology The CEDRIC-Lab Conservatoire National des Arts et Métiers (CNAM)

This paper investigates an interval analysis method for neural networks and applies it to fault detection for systems with unknown but bounded measurement noise. First, a novel interval analysis method is presented, which can compute the bounds of the output of a feedforward neural network subject to a bounded input. By applying the proposed interval analysis method to a network trained with fault-free system data, adaptive thresholds for fault detection are computed. Finally, one can acquire fault detection results via a fault detection strategy. The proposed method can achieve tight bounds of the network output and employ simple operations, which leads to accurate fault detection results and a low computational burden.A numerical simulation and an experiment on an AC servo motor are given to illustrate the effectiveness and superiority of the proposed method.

关键词： interval analysis feedforward neural network fault detection adaptive thresholds

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Frequency Regulation Method for Multi-Terminal HVDC Grids 38

Data-Driven Frequency Regulation Method for Multi-Terminal H...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Yong, Panxiao Jia, Yubin Guo, Jun Zhou, Jun Liu, Zhimin Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9798350303636

High voltage direct current (HVDC) lines allow low-loss transmission over long distances. The multi-terminal HVDC network consists of multiple terminals connected by HVDC lines, and each area shares the frequency reserve. Through secondary frequency control, the frequency of AC and DC areas can be regulated back to the set point when the system frequency has deviated. In this paper, a data-driven model predictive control (MPC) strategy is proposed. The Kooman operator is used to obtain the high-dimensional linear model of a nonlinear system, and the Deep Learning method is used to approximate the infinite-dimensional Koopman operator. The nominal MPC is used for optimization and control, and the optimal problem is solved for the Koopman linearized system. The optimal control is applied to the original nonlinear system. Simulation results show the effectiveness of the proposed method. © 2023 IEEE.

关键词： data-driven Koopman operator model predictive control Multi-terminal HVDC

来源：评论

学校读者我要写书评

暂无评论

Non-convex Optimization Based On Deep Koopman Operator 38

Non-convex Optimization Based On Deep Koopman Operator

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Guo, Jun Jia, Yubin Yong, Panxiao Zhou, Jun Liu, Zhimin Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9798350303636

Non-convex optimization problems are prevalent in various fields, and finding the global optimal solution for such problems remains challenging. This paper proposes an optimization method based on deep Koopman operator, which leverages the power of deep neural networks to provide a data-driven architecture for the Koopman function. The Koopman operator is used to linearly represent non-convex problems, and the proposed method utilizes model predictive control to optimize the resulting linear systems. Simulation results show that this method can solve the non-convex optimization problem effectively, quickly and accurately, while obtaining the global optimal solution. © 2023 IEEE.

关键词： Koopman operator model predictive control Non-convex

来源：评论

学校读者我要写书评

暂无评论

Development and application of a portable 3-axis transient magnetic field measuring system based on AMR sensor

Development and application of a portable 3-axis transient m...

引用

2013 IEEE International Conference on Smart Instrumentation, measurement and Applications, ICSIMA 2013

作者： Wang, Xiaohua Huang, Qi Lu, Youliang Du, Mo Sichuan Provincial Key Lab of Power System Wide-area Measurement and Control School of Energy Science and Engineering UESTC Chengdu China

ISBN: (纸本)9781479908431

With the development of smart substations, much attention has been focused on the transient magnetic field (TMF) generated during switching operation in substations. In order to study the TMF, a portable integrated system based on Anisotropic Magneto-resistive (AMR) sensor has been developed. The system mainly consists of magnetic probe, sampling card, and industrial computer. A GPS has also been brought in to stamp the TMF events time. This system can record TMF across a bandwidth from DC to 5MHz and a dynamic range from 20mGs to 6Gs for at least 50ms continuously. laboratory tests show that the system linearity is greater than 97%, the measuring error is less than 3% and the verified rising time of input magnetic field reaches 6.4μs. Field applications are presented at last, they show that the TMF is very complex but regular to some extent, and the stable magnetic fields are in conformity with operation theory. In conclusion, the proposed system is high sensitivity, wide dynamic and relatively wide bandwidth, and it is qualified to most applications in substations. © 2013 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Consensus-based Distributed Augmented Lagrangian Method for Nonconvex Optimization with Coupled Constraints

Consensus-based Distributed Augmented Lagrangian Method for ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Su, Yanxu Anhui University School of Artificial Intelligence Hefei230601 China Ministry of Education Southeast University Key Laboratory of Measurement and Control of Complex System of Engineering Nanjing210096 China

ISBN: (纸本)9781665465335

In this paper, we study the nonconvex optimization problems with consideration of globally coupled constraints. The constrained optimization problem is converted into an augmented Lagrangian function, and a distributed primal-dual algorithm is exploited in the context of finite-time consensus for solving such a problem. Particularly, we do not require the globally coupled constraints to be separable. Instead, we introduce some local variables for estimating the constraint violations. Under some mild assumptions in the research of nonconvex optimization, we prove the convergence of the presented algorithm to a KKT point of the problem. The numerical experiment verifies the correctness and the effectiveness of the theoretical results. © 2022 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A multi-channel projection haar features method for face detection 32

A multi-channel projection haar features method for face det...

引用

32nd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2017

作者： Li, Tianhuang Jian, Dong Yang, Wankou School of Automation Southeast University Nanjing210096 China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9781538629017

The face detection algorithm based on multi-channel map discriminant projection Haar feature is proposed in this paper. The multi-channel map is extracted from the face image, which can reduce the influence of the illumination and the noise in the image. Based on the positive and negative training samples, the enhanced Haar feature are obtained by the linear discriminant projection, which can improve the distinguishing ability of the feature. The response in multi-channel map of the augmented Haar feature in the training samples is calculated based on the two steps mentioned previously. After that, the non-symmetric quick boosting method is used to generate a set of weak classifiers. The weight and threshold of the strong classifier are adjusted by the linear non symmetric classifier. This method not only improves the distinguishing ability of the feature, but also realizes the reasonable division of the non-balanced positive and negative sample space. The experiment indicates that the detection rate using the proposed method increases compared to the original method, which shows more competitiveness than conventional algorithms on FDDB dataset. © 2017 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Experimental study of Tunnel and Anisotropic Magnetoresistive sensor for power system magnetic field measurement applications 3

Experimental study of Tunnel and Anisotropic Magnetoresistiv...

引用

3rd IEEE International Conference on Smart Instrumentation, measurement and Applications, ICSIMA 2015

作者： Khawaja, Arsalan Habib Huang, Qi Lian, Libo Sichuan Key Lab of Power System Wide-area Measurement and Control School of Energy Science and Engineering University of Electronic Science and Technology Chengdu China

ISBN: (纸本)9781467372558

This experimental investigation is focused to assess a Tunnel Magneto-Resistive (TMR) and Anisotropic Magneto-Resistive (AMR) sensor for power system magnetic field measurement applications as in current sensing, transmission line monitoring, detection and classification of Transient Magnetic Field (TMF) interference in substations. For measurement applications, AMR sensors have the limitations of low field range up to ±6 Gauss impractical for high magnetic field measurements, disorientation in sensitivity at exposure to field over ±20 Gauss recurrent in outdoor applications and high power consumption not appealing for portable devices. Thus, a complete testing system is established to identify if TMR sensors are a superior candidate for our application domain. For this, both of the sensors were exposed to uniform and transient magnetic field. Experimentation with identical conditioning circuitry confirms the superior performance of TMR sensor over AMR sensor in terms of twice the sensitivity, 200 times reduced power consumption and 5 times more field range. Additionally, in a TMF event, AMR sensor response depicts a time lag of 15 microseconds whereas TMR sensor only lags by 10 nanoseconds. Magnetic fields above field range of AMR sensor disorient the sensor until recalibrated;to cater for this a practical recalibration pulse blinds the sensor for 4 milliseconds once initiated. © 2015 IEEE.

关键词： Anisotropy

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：