检索结果-内蒙古大学图书馆

Interval analysis for neural networks with application to fault detection

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

Attack prevention and detection for cyber-physical systems based on coprime factorization technique 32

Attack prevention and detection for cyber-physical systems b...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Wu, Shimeng Luo, Hao Jiang, Yuchen Li, Kuan Harbin Institute of Technology Department of Control Science and Engineering Harbin China Shanghai Aerospace Control Technology Institute Shanghai China

ISBN: (纸本)9798350399714

While cyber-physical systems (CPSs) bring convenience to industrial production and human life, they are, in the mean time, exposed to the threat of cyber-physical attacks, which have the characteristics of concealment and vital destruction. Recent reports on several horrible attack events aroused people's attention to the security of CPSs. Motivated by this, this paper proposes a defense scheme based on co-prime factorization technology, consisting of attack prevention and detection. This scheme utilizes residual signals that are commonly used in fault diagnosis to realize secure transmission because these residual signals do not contain essential system knowledge. At the same time, a filter module is added, which makes use of noise signals to cover and protect the reference signals and the operation status of the system. By this means, the secure transmission method reduces the leakage of system information and interferes with the design of stealthy attacks, which need sufficient system knowledge. Furthermore, it realizes the detection of non-stealthy attacks under the same framework. Simulation results on a linear system with random parameters demonstrate the effectiveness of the proposed scheme. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Resilient Event-Triggered Model Predictive control for Adaptive Cruise control Under Sensor Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 807-809页

作者： Zhijian Hu Rong Su Kai Zhang Zeyuan Xu Renjie Ma School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore Key Laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technologyand the Center of Ultra-Precision Optoelectronic Instrument EngineeringHarbin Institute of TechnologyHarbin 150001China Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemical and Biomolecular Engineering National University of SingaporeSingapore 117585Singapore State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150001China IEEE

Dear Editor,This letter addresses the resilient model predictive control(MPC)problems for adaptive cruise control(ACC)systems under sensor *** the light of vulnerabilities of ACC systems to sensor attacks,an intrusion detection mechanism is proposed at the controller side to distinguish abnormal ***,the robust control gains are derived to design the terminal region constraint for MPC.

关键词： Trigger Event constraint

来源：评论

学校读者我要写书评

暂无评论

Class Incremental Learning Method for Hyperspectral Images Based on Real Data Playback Mechanism and Classification Network Optimization 15th

Class Incremental Learning Method for Hyperspectral Images B...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Liu, Xiaodong Wang, Siqi Liu, Huanyu Li, Junbao Department of Automatic Test and Control School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China School of Computer Science and Technology Information Countermeasure Technique Institute Harbin Institute of Technology Harbin150080 China

ISBN: (纸本)9789819700677

In recent years, the hyperspectral image (HSI) classification has attracted great attention in the field of earth observation. With the expansion of application scenarios and the continuous improvement of application requirements, new classes of HSI continue to emerge. In the face of open and dynamic application scenarios, the model is required to be able to continuously learn new categories based on maintaining existing category knowledge. Class incremental learning algorithms have received extensive attention as key solutions to the problem above. In this paper, we use a regularization-based incremental learning algorithm, elastic weight consolidation (EWC) for class incremental learning for HSI classification. After data preprocessing to reduce data dimensions, we select new classes for research on class incremental learning. We combine 3D-2D convolutional structures and residual blocks as the classification network and use real data playback mechanism to improve class recognition accuracy and realize class incremental recognition of HSI data. We demonstrate the feasibility of the algorithm with extensive experiments based on three widely used hyperspectral datasets. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Contact-Aided Model for Soft Continuum Robots Moving in Unstructured Environment

A Contact-Aided Model for Soft Continuum Robots Moving in Un...

引用

2024 China Automation Congress, CAC 2024

作者： Jingyu, Zhang Qin, Fang Mingjian, Sun Rong, Xiong Wang, Yue Haojian, Lu School of Information Science and Engineering Harbin Institute of Technology Weihai China Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Control Science and Engineering Harbin Institute of Technology Heilongjiang China

ISBN: (纸本)9798350368604

Due to their inherent flexibility and high human-computer interaction potential, soft continuum robots have been developed and popularized in industrial and medical scenarios. However, when moving in an unstructured environment, the contact with environment will change the configuration parameters of the robot, which brings problems to the control. Aiming at improving the control performance of soft continuum robots in an unstructured environment, a contact-aided model is proposed to estimate the varying configurations of the robot. Besides, a model-based controller is proposed to control the robot in an unstructured environment. To verify the performance of the proposed method, a small-scale soft continuum robot is designed and fabricated. Through the characterization experiment, the robot shows a large workspace by changing the contact position, and the kinematic model is verified. Through the trajectory tracking experiment, the robot showed good accuracy, with an average error of 1.2mm. Through an exploration experiment in the unstructured environment, the robot showed good control effect, with an average error of 1.9mm. This work enhances the application capability of the soft continuum robots in unstructured environments. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered H∞ Consensus Secondary Voltage control of AC Microgrids With Sampling Data 5

Event-Triggered H∞ Consensus Secondary Voltage Control of A...

引用

5th International Conference on Power and Energy technology, ICPET 2023

作者： Liu, Chuang Wang, Xinsheng Zhang, Huaqiang Deng, Jingchuan Harbin Institute of Technology Department of Control Science and Engineering Weihai China Harbin Institute of Technology Department of Electrical Engineering Weihai China

ISBN: (纸本)9798350339673

In this article, a distributed event-triggered H∞ consensus control strategy is proposed for secondary voltage control of microgrids (MGs) to reduce communication and computational burden. The event-triggered is implemented based on periodic sampling. By using the Lyapunov method to design the triggering conditions and sampling period of the distributed generators (DGs), DGs only communicate with their neighbors under certain specific event conditions, and the event triggering conditions are only calculated at the sampling time. Therefore, it avoids continuous communication and the calculation of continuous event-triggered conditions, thereby reducing the communication and computational burden. The simulation results demonstrate the effectiveness of the control strategy. © 2023 IEEE.

关键词： distributed control event-triggered H∞ consensus islanded microgrids time-varying delay

来源：评论

学校读者我要写书评

暂无评论

Multi-perspective regional continuity alignment network for hyperspectral and LiDAR image fusion and classification 43

Multi-perspective regional continuity alignment network for ...

引用

43rd Chinese control Conference, CCC 2024

作者： Yu, Wenbo Zhang, Miao Soochow University School of Electronics and Information Engineering Suzhou215021 China Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China

ISBN: (纸本)9789887581581

In these decades, remote sensing (RS) techniques have been widely used when facing diverse real-world tasks. These unique RS theories tend to observe on-ground objects and materials by several techniques from different perspectives. Generally, several works have verified that land cover classification tasks are always hampered when using one single RS modality owing to the lack of diverse information. In this paper, we propose a multi-perspective regional continuity aligning network (MPRCAnet) for hyperspectral and light detection and ranging (LiDAR) image fusion and classification. Our motivation is to capture and align the regional spatial-spectral continuities from different perspectives for better performance. Specifically, the whole network consists of three parallel streams, including 1) the HS spatial stream, 2) the HS spectral stream and 3) the LiDAR spatial stream. This network aims to discuss the potential of the continuous information extraction strategy in related tasks. Multiple experiments are conducted on two publicly available hyperspectral and LiDAR datasets to prove the effectiveness and feasibility of the proposed MP-RCAnet. Compared with several state-of-the-art techniques, MP-RCAnet is capable of generating fusion and classification results with higher evaluation accuracies. Its classification map has less scattered noise than other techniques. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Cross-modal three-dimensional intrinsic image decomposition for hyperspectral and LiDAR image joint classification 43

Cross-modal three-dimensional intrinsic image decomposition ...

引用

43rd Chinese control Conference, CCC 2024

ISBN: (纸本)9789887581581

Existing remote sensing technologies capture discriminant information of on-ground objects and materials from a distance for accurate land-cover identification. Specifically, hyperspectral and light detection and ranging (LiDAR) images record spectral and spatial information and elevation information, respectively. Aligning and fusing both RS modalities comprehensively is beneficial to improving classification performance. However, this alignment and fusion are always challenged by the enormous RS modality gap. In this paper, a cross-modal three-dimensional intrinsic image decomposition (CM3DIID) is presented for hyperspectral and LiDAR image joint classification. Intrinsic image decomposition contributes to enhancing semantic information and making RS modalities clear. Our motivation is to construct a unique cross-modal intrinsic image decomposition for three-dimensional data cubes specifically, facilitating robust discriminant information extraction. Specifically, the hyperspectral image contributes to restricting the decomposed reflectance component, making the samples with similar spectral curves very close. The LiDAR image is considered to search samples with similar elevations, which should be closed in the shading component. The whole optimization process is clearly analyzed and achieved by constructing a deep learning network. The proposed CM3DIID constructs a connection bridge between hyperspectral and LiDAR images for information switching and modality fusing. Multiple experiments are conducted on two widely used hyperspectral and LiDAR datasets to verify the effectiveness and feasibility of the proposed CM3DIID. The final results clearly prove that the proposed CM3DIID is capable of generating better classification performance than other state-of-the-art comparison techniques. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Spacecraft Chase and Escape Game Based on PPO Algorithm 7th

Spacecraft Chase and Escape Game Based on PPO Algorithm

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Ye, Ruiqing Deng, Wudong Guo, Yanning Li, Chuanjiang Department of Control Science and Engineering School of Astronautics Harbin Institute of Technology Harbin150001 China Shanghai Institute of Satellite Engineering Shanghai201109 China

ISBN: (纸本)9789819733231

This paper addresses the pursuit-evasion game problem for spacecraft using pulse propulsion, uses Particle Swarm Optimization (PSO) and Proximal Policy Optimization (PPO) algorithms as pursuit and evasion strategies for the spacecraft. The distance between the spacecraft is employed as the optimization objective for the PSO algorithm, aiming to minimize the distance between them. Similarly, the distance between the spacecraft is used as the reward function for the PPO algorithm, aiming to maximize the distance between them. Additionally, the paper takes into account that the spacecraft use pulse propulsion with a maximum velocity increment constraint. Through simulation examples, the effectiveness of using the PPO algorithm as a spacecraft strategy-solving method is validated. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Spacecraft

来源：评论

学校读者我要写书评

暂无评论

Local–global transformer-based point cloud segmentation network for workpiece surface defect grinding

引用

Machine Vision and Applications 2025年第4期36卷 1-17页

作者： Zhang, Qimin Wang, Qiang Wang, Ningyuan Liu, Jiaxuan Qu, Delin Department of Control Science and Engineering Harbin Institute of Technology Harbin China

Point cloud is extremely useful in high-precision intelligent robotic grinding due to their abundant spatial information. Accurate point cloud segmentation can extract surface defects of workpieces to provide 3D data for robotic grinding. Recently, with the development of computer vision, Transformer-based methods have been widely applied in point cloud segmentation, while most of them only capture features based on global or local attention, resulting in a lack of comprehensive information. In this paper, we propose a novel segmentation network, Local and Global Feature Transformer Network (LGFT-Net), to combine local features and global features based on Transformer module. Specifically, a local feature extraction block with feature embedding module and Local Transformer module is designed to embed features into a higher space and learn feature correlations in local regions, and a global feature extraction block with Global Transformer module is used to obtain global contextual information. We perform extensive experiments on ShapeNet dataset and workpiece point cloud dataset. The results show that: (1) the LGFT-Net achieves segmentation performance comparable to state-of-the-art methods in part segmentation and (2) this model is feasible to segment surface bump defects of workpieces to provide 3D data for robotic grinding.

关键词：

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：