检索结果-内蒙古大学图书馆

Global control for a class of feedforward nonlinear systems with uncertain measurement functions ⁎

IFAC-PapersOnLine 2020年第2期53卷 6262-6267页

作者： Wenting Zha Junyong Zhai Yingyu Liang School of Mechanical Electronic & Information Engineering China University of Mining & Technology (Beijing) Beijing 100083 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China 210096 China

Based on the nested-saturation technique, this paper investigates the global stabilization problem for a class of upper-triangular nonlinear systems with uncertain measurement functions. By imposing certain assumptions on the uncertain powers, a state-feedback controller, only involving the known parameters, is designed to locally stabilize the nonlinear system. Then, a saturated controller is constructed by combining the nested function and the local stabilizer. With appropriate saturation level, it can be proved that the saturated controller is able to make the closed-loop system globally asymptotically stable. Finally, a simulation example is presented to demonstrate the effectiveness and robustness of the proposed control scheme.

关键词： Nonlinear system upper-triangular system uncertain measurement function nested saturation approach robustness global stabilization

来源：评论

学校读者我要写书评

暂无评论

GPI observer-based composite current-constrained control approach for DC–DC buck converters

GPI observer-based composite current-constrained control app...

引用

2019 Jiangsu Annual Conference on Automation, JACA 2019

作者： Wang, Zuo Guo, Tianliang Wang, Xiangyu Li, Shihua School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

In this study, overcurrent protection technique is investigated for the voltage regulation problem of the DC–DC buck converter system with time-varying disturbances and uncertainties. Normally, fast dynamics during the start-up phase generates large transient current. The overlarge transient current may lead to risks of hardware damage. By selecting conservative control parameters, the current constrained performance can be realised. However, the transient performance and disturbance rejection ability are sacrificed. It is of significant importance to design a controller which keeps a good balance between dynamic performance and overcurrent protection. Moreover, the control accuracy is inevitable affected by the time-varying disturbances effects, including load variations, input voltage fluctuations and circuit parameter perturbations. In this paper, the control design is divided into two parts. Firstly, by inserting a dynamic penalty term into the state feedback controller, a baseline current-constrained scheme is developed. Rigorous stability analysis and current constraint performance are given under the presented baseline controller. Secondly, taking the time-varying disturbances into account, a novel GPI observer-based composite current-constrained controller can be developed by combining disturbance estimations and the baseline controller. Experimental results are provide to demonstrate the effectiveness of the presented control strategy. © 2019 Institution of engineering and *** rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

GPIO-based rail pressure control for diesel high pressure common rail injection system

GPIO-based rail pressure control for diesel high pressure co...

引用

2019 Jiangsu Annual Conference on Automation, JACA 2019

作者： Wang, Jiapeng Sun, Hao Dai, Chen Li, Shihua Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Jiangsu210096 China

The rail pressure control in diesel high-pressure common rail (HPCR) system is considered as one of the key issues for precise control of fuel injection. This study investigates the application of generalised proportional integral observer (GPIO)based control in diesel HPCR system. Firstly, a non-linear mathematical model of HPCR system which uses the metering unit as the actuator is established based on hydromechanics under some proper simplifications. Secondly, a GPIO is developed to estimate the mismatched disturbance caused by the injection process. Then a composite controller combining GPIO and backstepping control method is designed. By introducing the disturbance estimations into the control design process, the disturbance rejection capability of the system is promisingly enhanced. The effectiveness of the proposed control method is validated by the simulation results. © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Differential evolution algorithm based on PCA to determine the objective function to optimize the configuration of microgrid

引用

Journal of Physics: Conference Series 2021年第1期2003卷

作者： Wang, Yunhu Xu, Ruobing Duan, Qing Zhang, Guobao Huang, Yongming Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Nanjing210096 China State Grid Jiangsu Electric Power Co. Ltd. Nanjing Power Supply Branch Nanjing210019 China China Electric Power Research Institute Co. Ltd. Beijing100192 China

Recently, microgrids are increasingly used in our lives. The purpose of this paper is to solve the uncertainties of multi-objective decision-making and the instability of algorithms in the optimal configuration of traditional microgrids. This paper proposed a differential evolution algorithm based on PCA to determine the objective function. Firstly, a multi-objective optimization model of the micro-grid was established on the basis of fully considering the economy, environmental protection and stability of the micro-grid. Next, the first principal component of the multi-objective was extracted based on PCA combining innovatively the Pareto optimal solution set, and the multi-objective optimization problem was transformed into a single-objective optimization problem. Finally, the experimental simulation result shows that the algorithm proposed in this paper can comprehensively consider the economy, environmental protection and stability of the microgrid on the basis of ensuring the efficiency and stability of the algorithm to realize the optimized configuration of the microgrid. © Published under licence by IOP Publishing Ltd.

关键词： differential evolution algorithm microgrid Pareto optimal solution set PCA

来源：评论

学校读者我要写书评

暂无评论

A Driver Fatigue Recognition Algorithm Based on Spatio-Temporal Feature Sequence

arXiv

引用

arXiv 2020年

作者： Zhang, Chen Lu, Xiaobo Huang, Zhiliang School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

—Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety. In recent years, with the development of deep learning, the field of pattern recognition has made great development. This paper designs a real-time fatigue state recognition algorithm based on spatio-temporal feature sequence, which can be mainly applied to the scene of fatigue driving recognition. The algorithm is divided into three task networks: face detection network, facial landmark detection and head pose estimation network, fatigue recognition network. Experiments show that the algorithm has the advantages of small volume, high speed and high accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Driving behaviour recognition from still images by using multi-stream fusion CNN

Driving behaviour recognition from still images by using mul...

引用

作者： Hu, Yaocong Lu, Mingqi Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Abnormal driving behaviour is a leading cause of serious traffic accidents threatening human life and public property globally. In this paper, we investigate the use of a deep learning approach to automatically recognize driving behaviour (such as normal driving, driving with hands off the wheel, calling, playing mobile phone, smoking and talking with passengers) in a single image. The task of driving behaviour recognition can be regarded as a multi-class classification problem, and we resolve this problem from two aspects in our study: (1) Employ multi-stream CNN to extract multi-scale features by filtering images with receptive fields of different kernel sizes and (2) investigate different fusion strategies to combine the multi-scale information and generate the final decision for driving behaviour recognition. The effectiveness of our proposed method is validated by extensive experiments carried out on our self-created simulated driving behaviour dataset, as well as a real driving behaviour dataset, and the experiment results demonstrate that the proposed multi-stream CNN-based method achieves the significant performance improvements compared to the state of the art. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Smoky vehicle detection algorithm based on improved transfer learning 6

Smoky vehicle detection algorithm based on improved transfer...

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Guangming Zhang, Dexiong Lu, Xiaobo Cao, Yichao School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

With the demand for pollution prevention has increased. Establishing a smoky vehicle inspection and evidence collection system will help to supervise the problem of excessive emissions of vehicles. Because the sample in the training data set is insufficient and unbalanced, the existing methods cannot obtain sufficient classification accuracy in the classification task of the smoky vehicle. This paper uses the transfer learning method to compare the effects of smoky car classification tasks on the five basic networks of DenseNet, NasNet, Inception, VGG19, MobileNet. In addition, for the classification task of the smoke vehicle, it is necessary to consider both the global information of the tail of the vehicle and the detailed information of the smoke area. In this paper, the global average pooling layer is changed to the spatial pyramid pooling layer, and it has achieved better results. Finally, the classification Precision nearly 0.1, Recall 0.3 are obtained, which is much better than the traditional classification method and the shallow non-transfer deep learning method. © 2019 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

arXiv

引用

arXiv 2021年

作者： Zhang, Yang Yu, Xin Lu, Xiaobo Liu, Ping The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Australian Institute of Artificial Intelligence University of Technology Sydney UltimoNSW2007 Australia The School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Singapore138634 Singapore

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8×) the occluded and tiny faces (16×16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network upsamples and inpaints occluded LR faces via a coarse-to-fine fashion, significantly reducing undesirable artifacts and blurriness. Specifically, we design a novel cross-modal attention module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutually beneficial manner. Extensive experiments show that our Pro-UIGAN attains visually pleasing completed HR faces, thus facilitating downstream tasks, i.e., face alignment, face parsing, face recognition as well as expression classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An attention convolutional neural network for forest fire smoke recognition 6

An attention convolutional neural network for forest fire sm...

引用

6th International Conference on systems and Informatics, ICSAI 2019

作者： Zhang, Dexiong Cao, Yichao Zhang, Guangming Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9781728152561

In order to find forest fire in time and accurately, the identification of forest fire smoke based on computer vision has become an important research direction. In this paper, a convolutional neural network model based on the attention mechanism is designed for forest fire smoke recognition. By focusing on the regions with obvious discrimination in the image, more precise local features are extracted for fire smoke identification with the auxiliary of backbone network. The performance of network on the unbalanced forest fire dataset is improved by optimizing the cross-entropy loss function with weights. The experimental results show that attention convolutional neural network improves the accuracy of the model which reached 89.3% while reducing false positives and false negatives. © 2019 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Correction to: Global finite-time set stabilization of spacecraft attitude with disturbances using second-order sliding mode control

引用

Nonlinear Dynamics 2022年第2期108卷 1847-1847页

作者： Guo, Zeyu Wang, Zuo Li, Shihua School of Automation Southeast University Nanjing People’s Republic of China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing People’s Republic of China

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：