检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Xueying Lu Huazhou Hou Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

The balance control problem of disturbed inverted pendulum systems is *** of the existing advanced control methods for disturbed inverted pendulum systems are developed only to suppress constant or bounded *** results in a degradation of system performance when meeting severe *** this end,a finite-time disturbance observer is developed to estimate time-varying ***,an integral terminal sliding mode controller is designed for the inverted pendulum *** on the finite-time disturbance observer and the integral terminal sliding mode technique,a composite controller with finite-time convergence is proposed,which rejects the time-varying disturbances and alleviates the *** simulation results on the inverted pendulum system are presented to demonstrate the advantage and effectiveness of the proposed method.

关键词： Anti-disturbance Finite-time Disturbance Observer Integral Terminal Sliding Mode control

来源：评论

学校读者我要写书评

暂无评论

Subgroup State Prediction under Different Noise Levels Using MODWT and XGBoost

引用

Journal of Healthcare engineering 2023年第1期2023卷

作者： Zhao, Xin Nie, Xiaokai School of Mathematics Southeast University Nanjing211189 China 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 Shenzhen Research Institute Southeast University Shenzhen518057 China

In medical states prediction, the observations of different individuals are generally assumed to follow an identical distribution, whereas precision medicine has a rigorous requirement for accurate subgroup analysis. In this research, an aggregated method is proposed by means of combining the results generated from different subgroup models and is compared with the original method for different denoising levels as well as the prediction gaps. The results using real data demonstrate the effectiveness of the aggregated method exhibiting superior performance such as 0.95 in AUC, 0.87 in F1, and 0.82 in sensitivity, particularly for the denoising level that is set to be 2. With respect to the variable importance, it is shown that some variables such as heart rate and lactate arterial become more important when the denoising level increases. © 2023 Xin Zhao and Xiaokai Nie.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fault Detection Method of Photovoltaic System Based on Power Change of Array

Fault Detection Method of Photovoltaic System Based on Power...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Chao Tan Chenxi Li Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

The fault detection of photovoltaic power generation system is of great significance in photovoltaic plant management. The conventional fault detection method of photovoltaic power system requires additional sensors, and the fault detection scheme needs to be redesigned if the parameters of the photovoltaic plant ***, for large photovoltaic plants, it is necessary to develop a method that does not require the use of external sensors or the detailed parameters of the photovoltaic plant. This paper proposes a photovoltaic system fault detection method based on photovoltaic array current and voltage data. This method does not require additional sensor data such as irradiance and temperature. The failure of photovoltaic system can be detected through the change of power,and the abnormal situation of photovoltaic power station can still be detected under cloudy and shaded conditions. The advantages of this method are that there is no need for complex and diverse sensor equipment, the calculation is simple and the fault detection ability is accurate. The experimental data of Padang Poverty Power Station of State Grid has been verified.

关键词： Photovoltaic System(PVS) Fault detection algorithm Electrical data Sensorless Power characteristics

来源：评论

学校读者我要写书评

暂无评论

An Improved Faster R-CNN for Railway Fastening System Detection 21

An Improved Faster R-CNN for Railway Fastening System Detect...

引用

5th International Conference on Computer Science and Application engineering, CSAE 2021

作者： Peng, Xinfeng Tong, Shuzhen Lu, Xiaobo Wei, Yun School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Beijing Mass Transit Railway Operation Corporation Limited Beijing100044 China

ISBN: (纸本)9781450389853

In the automatic railway anomaly inspection technology based on image processing and deep learning, an effective algorithm used for high-precision detection of the fastening system is very important, especially in turnout sections. It is challenging because the background of the turnout sections is complicated with various types of targets. This paper improved the Faster R-CNN model, used multi-scale feature map fusion for small targets. And modified predefined anchor to generate region proposals, added attention module to make the network focus on meaningful feature. Besides, this paper used cross-entropy function and SmoothL1 loss function for training and labeled 1200 image samples as dataset. Compared with the original Faster R-CNN model, the experimental results (AP) of the improved model in this paper increased from 96.3% to 98.9%, which effectively reduced the fault detection and missed detection and improved the accuracy of location.. © 2021 Association for Computing Machinery. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distilling Object Detectors with Efficient Logit Mimicking and Mask-Guided Feature Imitation

SSRN

引用

SSRN 2023年

作者： Lu, Xin Cao, Yichao Chen, Shikun Li, Weixuan Zhou, Xin 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 Nanjing Enbo Technology Co. Ltd. Nanjing210007 China

Knowledge distillation (KD) is a promising approach to learning compact models for object detection with information inherited from intricate teacher networks. In this paper, we raise some shortcomings of existing KD methods for object detectors, e.g., ignoring knowledge selection, coarse feature imitation mask, etc. To address these issues, we present a novel KD framework to train efficient object detectors via Logit Mimicking and Feature Imitation (LMFI). First, we put forward a novel logit mimicking method for classification and localization heads. On the one hand, it first proposes to mimic the classification logits of one-category object detectors. On the other hand, we exploit the localization knowledge from teacher predictions and ground truths, which dynamically guides the learning of student's regression outputs by stages. Second, an adaptive positive teacher selection (APTS) strategy is designed to obtain high-quality teacher samples during distillation, which reduces the transmission of inferior knowledge. Moreover, we heuristically introduce a soft metric and fine-grained mask to reconcile the discrepancy between teacher and student features in a position-wise manner. Extensive experiments show that LMFI outperforms the state-of-the-art KD frameworks for object detection. It can significantly boost the performance of various detectors on different benchmarks, e.g., 2.83% and 2.58% MR-2 reduction of Cascade R-CNN on the S and All sets of CityPersons, and an improvement of ResNet-50 based ATSS from 36.7% to 40.5% mAP on the COCO benchmark. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Robust Clock Synchronization Scheme for Wireless Sensor Networks against DoS Attacks

A Robust Clock Synchronization Scheme for Wireless Sensor Ne...

引用

第40届中国控制会议

作者： Xuxin Zhang Shiyu Chen Bingya Zhao Ya Zhang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

This paper investigates the clock synchronization problem of wireless sensor networks with time-varying noises and malicious denial of service（Do S） attacks. A robust and secure clock synchronization scheme based on filter is proposed in intermittent Do S attack case, which is composed of three steps: relative skew estimation, clock skew compensation and software clock reading compensation. Through the clock skew compensation, the synchronization error of the clock skew can be constrained into a bounded range. Through the software clock reading compensation, the possible error of the software clock reading can be compensated and the clock synchronization can be achieved completely. In addition, extensive simulations are conducted which validate that the proposed scheme outperforms the existing ones.

关键词： clock synchronization wireless sensor networks DoS attacks bounded noises filter

来源：评论

学校读者我要写书评

暂无评论

An Improved Frequency Hopping Algorithm Based on Transmission Scheduling against Jamming Attacks 36

An Improved Frequency Hopping Algorithm Based on Transmissio...

引用

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Wang, Chenyuan Kong, Xiangying Chen, Xuebing Cao, Xianghui Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Jiangsu Automation Research Institute Jiangsu China Southeast University School of Cyber Science and Engineering Nanjing China

ISBN: (纸本)9781665437127

In wireless networked systems, jamming attacks are destructive and easy to be launched. To mitigate the jamming attack impact, frequency hopping is an effective way, in which a defender side can switch channels to avoid using the ones under jamming attack. However, the resilient ability of anti-jamming of traditional frequency hopping algorithm can't meet the requirement of communication without channel strategy and jamming detection under the circumstance of various forms of jamming attacks. In this paper, an improved frequency hopping algorithm with higher transmit success rate (TSR) has been proposed based on channel selection and adjustment of transmission time to defend different kinds of attacks such as reactive jamming, static jamming and scanning jamming. Our algorithm judges whether to adjust data transmission time according to the result of transmit success rate and use channel selection strategy to avoid most of interfered channels. Finally, our proposed algorithm is evaluated as a resilient scheme under different forms of jamming attacks through simulations. © 2021 IEEE.

关键词： Frequency hopping

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking control of unknown state target for CPSs subjected to cyberattacks

Adaptive tracking control of unknown state target for CPSs s...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Yizhou Sun Ya Zhang School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Automation Southeast University Nanjing China

ISBN: (纸本)9781665476881

In this study, an adaptive controller for Cyber-Physical systems(CPSs) subjected to cyberattacks is proposed to track a class of target system with unknown inputs and states. Firstly, an estimation strategy is proposed to adaptively estimate the unknown inputs and states of target on the basis of finite impulse response (FIR) filter. Secondly, due to the existence of cyberattacks in CPSs, an adaptive tracking control scheme with designed compensation signal is constructed to stabilize the system performance which might be damaged by attacks, where Lyapunov function related to adaptive estimated factor is adopted to prove that the CPSs are able to track the target under attacks. In the last part, a numerical experiment is implemented to demonstrate the validity of the theoretical results.

关键词： Target tracking Adaptive systems Finite impulse response filters System performance Estimation Lead control systems

来源：评论

学校读者我要写书评

暂无评论

Hot Spot Detection of Photovoltaic Module Infrared Near-field Image based on Convolutional Neural Network 4

Hot Spot Detection of Photovoltaic Module Infrared Near-fiel...

引用

2022 4th International Conference on Energy systems and Electrical Power, ICESEP 2022

作者： Fan, Fu Na, ZhiXiong Zhang, ChangZhi Li, HaoRan Tong, ChaoLiu School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China State Grid e-commerce Co. Ltd Beijing100053 China State Grid Tianjin Electric Power Company Tianjin300010 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

With the installation and use of large-scale photovoltaic systems around the world, the detection of photovoltaic system operation and maintenance has become increasingly important. This research uses a convolutional neural network training model to detect and classify the infrared near-field images of photovoltaic modules from small-scale photovoltaic plants in the laboratory. This model classifies the images into two categories: with and without hot spots, with a classification accuracy of 96.58%. The experimental results show that the convolutional neural network training model has a good classification result. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CrossNet: Computing-Friendly Lightweight Anchor-Free Detector 4

CrossNet: Computing-Friendly Lightweight Anchor-Free Detecto...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Yao, Yuncong Wang, Qiang Mai, Jiren Yang, Wankou Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjin210096 China School of Automation Southeast University Nanjin210096 China Jiangsu Automation Research Institute Lianyungang221116 China

ISBN: (纸本)9780738131702

Many scenarios such as edge and mobile scenarios are very sensitive to computing complexity and parameter size. Most object detection models cannot be directly deployed without specific modifications. In this paper, we introduce CrossNet, a compute-friendly lightweight anchor-free detector based on CenterNet. We abandon DCN module and design the network structure according to lightweight design principles. A new sample matching strategy based on neighbor points is adopted for improving its performance greatly. Weighted Focal Loss and Balanced L1 Loss further reduce the performance gap between CrossNet and CenterNet. CrossNet possesses a model size of 4.3MB (12.8× smaller than original CenterNet, respectively) and requires 1.51B operations for inference (11.7× smaller than original CenterNet, respectively) while still achieving mAP of 74.2% on VOC dataset. We hope our work could provide some inspiration for lightweight detector design. © 2021 IEEE.

关键词： Object detection

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：