检索结果-内蒙古大学图书馆

IEEE Instrumentation and Measurement technology Conference

作者： Qimin Zhang Qiang Wang Ningyuan Wang Jiulong Xie Department of Control Science and Engineering Harbin Institute of Technology Harbin PR China

The vision system often plays a vital auxiliary role in the high-precision grinding process of the robot. This paper presents an eye-in-hand vision system which incorporates a depth camera on the six-axis robotics and scans from multiple angles to extract the information of workpieces to be ground. Contour and centroid extraction were applied for locating workpiece and planning path of fine scanning. After obtaining the multi-angle point cloud images, we reconstructed the point cloud of the workpiece surface through point cloud registration and segmentation. Harris corner detection was used to recognize bumps on the surface. Then grinding information was uniformly converted to the robot coordinate system through coordinate transformation. The experimental results show that this system can obtain comprehensive and precise grinding information, ensuring the smooth execution of robotic grinding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation 3

SAGPCN: Self-Attention Graph Pooling Convolutional Network f...

引用

3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

作者： Zhang, Jiusi Tian, Jilun Jiang, Yuchen Luo, Hao Huang, Cong-Sheng Chow, Mo-Yuen Yin, Shen Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan North Carolina State University Department of Electrical and Computer Engineering RaleighNC27606 United States Norwegian University of Science and Technology Faculty of Engineering Trondheim7034 Norway

ISBN: (纸本)9798350324754

Lithium-ion batteries are widely applied in sustainable energy conversion system. Consequently, it is of great research significance to accurately estimate the state of health (SOH) of batteries. To effectively model the input features at the spatial level, this article proposes a self-attention graph pooling convolutional network (SAGPCN) to estimate the SOH. The advantages of SAGPCN proposed in this paper can be reflected as follows: (1) The SAGPCN can consider node characteristics and graph topology, which focuses the attention on key parts of the graph. (2) The SAGPCN designs a self-attention mechanism to reserve significant nodes and delete secondary nodes, so as to optimize the network structure. A real-world dataset is adopted to evaluate the proposed battery SOH estimation approach in this paper. Experimental results represent that the estimation performance of the proposed SAGPCN is better than some data-driven SOH prediction approaches. © 2023 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

High-order Fully Actuated Approach for Output Position control of Two Mass Systems based on Extended State Observer

High-order Fully Actuated Approach for Output Position Contr...

引用

Fully Actuated System theory and Applications (CFASTA), Conference on

作者： Ping Li Guang-Ren Duan Bi Zhang Yuzhong Wang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper proposes a high-order fully actuated (HOFA) control approach for the output position control of two-mass systems (TMSs) based on extended state observer (ESO). TMSs belongs to a class of underactuated mechanical systems, which can be converted into an HOFA model using variable elimination. Based on the feature of HOFA model, it is extremely simple to solve the position control law such that a desired tracking error system can be achieved. To handle the control issues of high-order derivatives and unknown disturbances, a linear ESO is employed for state estimation and active disturbance rejection control, where the lumped disturbance is treated as an extended system state. The theoretical stability of control system is analyzed with the help of sliding manifold. Comparative simulations are performed to demonstrate the effectiveness of the proposed approach.

关键词： Robust control Uncertain systems Simulation Position control Observers control systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic Soft Sensor Development Based on Hierarchical Spatiotemporal Extreme Learning Machine for Anaerobic Digestion Process

Dynamic Soft Sensor Development Based on Hierarchical Spatio...

引用

Chinese control and Decision Conference, CCDC

作者： Ning Zhang Yuhong Wang Minghui Gai Pengfei Yan Department of Control Science and Engineering China University of Petroleum (East China) Qingdao China Department of Control Science and Engineering Harbin Institute of Technology China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The effective approach for dealing with kitchen waste is anaerobic digestion (AD) technology. The concentration of volatile fatty acid (VFA) determines whether anaerobic digestion process can proceed smoothly. This paper introduces a novel approach, the Hierarchical Spatiotemporal Extreme Learning Machine (HSTELM), for real-time quality variables monitoring. The proposed model utilizes the adjacency matrix and positional encoding to obtain the spatial and dynamic characteristics of the process data, respectively. Additionally, deep features of the process data are extracted by stacking Spatiotemporal Extreme Learning Machine Autoencoder (STELM-AE). Finally, an AD process in kitchen waste plants is introduced as a case study. The actual industrial data of the plant verify the suggested model.

关键词： Extreme learning machines Soft sensors Process control Predictive models Feature extraction Encoding Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Adversarial Training with Maximal Coding Rate Reduction

Adversarial Training with Maximal Coding Rate Reduction

引用

Asilomar Conference on Signals, Systems & Computers

作者： Hsiang-Yu Chu Hongbo Zhao Markus Flierl Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. Adversarial training is one commonly used strategy to improve the robustness of deep learning models against adversarial examples, which is performed by incorporating adversarial examples into the training process. Traditionally, during this process, cross-entropy loss is used as the loss function. In order to improve the robustness of deep learning models against adversarial examples, we propose in this paper two new methods of adversarial training by applying the principle of Maximal Coding Rate Reduction (MCR 2 ). We evaluate the performance of different adversarial training methods by comparing the clean accuracy and adversarial accuracy. It is shown that adversarial training with the MCR 2 loss function yields a more robust network than the traditional adversarial training method. In our experiments, adversarial accuracies are improved by up to 10%. The two loss functions are discussed by using a model.

关键词： Training Deep learning Hands Accuracy Image coding Computational modeling Robustness Data models Encoding Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning-based predefined-time optimal tracking control for rigid spacecraft with actuator faults

引用

Acta Astronautica 2025年 235卷 195-214页

作者： Zhao, Zhoujia Zhang, Jierui Wang, Aixue Wang, Guan Ma, Guangcheng Xia, Hongwei Space Control and Inertial Technology Research Center Harbin Institute of Technology Harbin150001 China Department of Aeronautics and Astronautics School of Mechanics and Aerospace Engineering Dalian University of Technology Dalian116081 China

In this paper, we propose an optimal learning tracking controller for six-degree-of-freedom (6-DOF) rigid spacecraft, proficient in addressing nonlinear and non-affine actuator faults. A predefined-time fault observer is first devised to expeditiously diagnose actuator faults, followed by the utilization of neural networks for online compensation of estimation errors and external disturbances. Following this, a novel predefined-time optimal learning controller is formulated, capable of meticulously tracking the target spacecraft trajectory with observational data while attaining near-optimal control cost. Notably, we implement a predefined-time-based online weight update mechanism that extracts feature information from storage stacks, thereby augmenting the learning performance of neural networks. The stability of the proposed strategy is rigorously established using the Lyapunov method. Numerical simulations and experiments conducted on 6-DOF air-bearing testbeds substantiate the effectiveness and superiority of the theoretical findings. © 2025

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Improved Event-Triggered Sequential Fusion Filter for Cluster Sensor Networks with Deceptive Attacks

SSRN

引用

SSRN 2024年

作者： Liu, Weicheng Cheng, Guorui Ma, Xiaolei Wang, Shengli Song, Shenmin College of Marine Science and Engineering Shandong University of Science and Technology Qingdao266000 China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin150001 China

This paper investigates cluster sensor networks that are subjected to deceptive attacks in multi-sensor systems, and proposes an improved event-triggered (IET) mechanism to reduce their impact. The threshold of the upper bound in the IET mechanism is set to intercept the attacked information to improve the accuracy of estimation of the filter, while the lower bound is set to reduce the rate of communication to reduce the loss of unnecessary energy. Sequential fusion is used in the cluster sensor network to detect the attacked information, and the Kalman sequence fusion filter (KSFF) is applied to fuse the measurements in the cluster. Once the measurements fusion filter has been applied, the states of the clusters are exchanged and fused by using the Kalman consensus fusion filter (KCFF). We then derive the optimal IET-KSFF-KCFF under the criterion of minimum linear covariance based on event-triggered conditions and perform integral calculation. It is proved by mathematical induction that the covariance of the algorithm has an upper bound. Finally, the effectiveness of the algorithm is verified through simulations. © 2024, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Study on Target Detection and Tracking Method of UAV Based on LiDAR 12

Study on Target Detection and Tracking Method of UAV Based o...

引用

12th IEEE Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021

作者： Wang, Hong Peng, Yu Liu, Liansheng Liang, Jun Harbin Institute Of Technology Department Of Test And Control Engineering Harbin China

ISBN: (纸本)9781665401302

Unmanned aerial vehicle (UAV) may bring potential danger such as hurting people falling accidents, Therefore the surveillance of trajectory of UAV is subjected to extensive attention for avoiding irreversible damage. This paper presents a target detection and tracking method based on LiDAR, in which target detection uses Euclidean distance clustering and particle filter are utilized to achieve target detection and tracking, respectively. Once UAV is detected by the clustering method, the particle filter algorithm is used to track the target. In the experiment, the Livox Mid 40 LiDAR developed by the Livox company is used as the front-end sensor to detect the UAV. Experimental results show that the proposed method could realize the detection and tracking of UAV. © 2021 IEEE.

关键词： Object detection

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

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

引用

第43届中国控制会议

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

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

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 Li DAR images for information switching and modality fusing. Multiple experiments are conducted on two widely used hyperspectral and Li DAR 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.

关键词： Intrinsic Image Decomposition Hyperspectral Image LiDAR Image Cross-modal Strategy Object Classification

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Distributed Kalman Consensus Filter with Measurement Delay and Noise Correlation for Sensor Networks

SSRN

引用

SSRN 2024年

作者： Liu, Weicheng Yang, Yuhang Wang, Shengli Song, Shenmin College of Marine Science and Engineering Shandong University of Science and Technology Qingdao266000 China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin150001 China

This paper reports the design of a nonlinear distributed Kalman consensus filter (NDKCF) with one-step random measurement delay and noise correlation for sensor networks. Because of the correlation between system noise and observed noise in multi-sensor systems, the state cannot be predicted directly in one-step, so the correlated noise is first decoupled. When there is a delay in the transmission of local observations from a sensor node, its predictor is used as compensation. The NDKCF with measurement delay and noise correlation under the unbiased minimum covariance criterion is derived for the first time, and the numerical integration form is designed in a Bayesian framework under the assumption that the conditional density is Gaussian. A numerical implementation of the proposed algorithm is given based on the third-degree spherical-radial rule cubature Kalman filter (CKF). It is proved that the covariance of the algorithm has an upper bound by linearization approximation, which shows the stability of the algorithm. Finally, a simulation experiment verifies the effectiveness of the algorithm. © 2024, The Authors. All rights reserved.

关键词： Sensor nodes

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：