检索结果-内蒙古大学图书馆

2022 Chinese Automation Congress, CAC 2022

作者： Zhang, Kunpeng Liu, Zhuang Xu, Ruiqi Yu, Dongling Kong, Deshan Guan, Qichao Zhao, Yue State Grid Heilongjiang Electric Power Company Limited Yichun Power Supply Company Yichun China Harbin Institute of Technology Department of Control Science and Engineering Harbin China Southampton Ocean Engineering Joint Instituteg Harbin Engineering University Harbin China

ISBN: (纸本)9781665465335

In this paper, a controller which can achieve fixed-time convergence is studied for manipulator systems. Firstly, an adaptive neural network (ANN) is used to estimate the unknown parts and external disturbances of the system. Secondly, a piecewise sliding mode variable is used to realize the nonsingular control of the terminal sliding mode. Then, in order to improve the tracking speed of the manipulator system, a faster fixed-time control algorithm is designed, and the tracking error can converge within a faster fixed-time. Finally, the practicability of the proposed algorithm is verified by simulation. © 2022 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Comfort-Oriented control for Half-Car Semi-active Suspension Using a Model Predictive Approach 7

Comfort-Oriented Control for Half-Car Semi-active Suspension...

引用

7th CAA International Conference on Vehicular control and Intelligence, CVCI 2023

作者： Zhao, Huichao Yuan, Qing Miao, Weiwei Zhou, Hongliang Chen, Songlin Yu, Zhen Cao, Zhenqian New Energy Development Institude China FAW Group Co. Ltd ChangChun China Control Science and Engineering Harbin Institute of Technology Harbin China Chassis Development Department Institude China FAW Group Co. Ltd ChangChun China

ISBN: (纸本)9798350340488

This paper presents a controller design for magnetorheological (MR) semi-active vehicle suspensions, with the main objective of optimizing suspension performance while ensuring that the desired damping coefficients of the front and rear suspension dampers generated by the control law satisfies the physical constraints of the MR damper. To tackle these control objectives, a constrained quadratic programming problem is formulated within the framework of model predictive control (MPC). Integrated Analytic Hierarchy Process (IAHP) and Particle Swarm Optimization (PSO) algorithm are then utilized to optimize the performance of the controller. The optimal control law is determined using the GRAMPC toolbox. Simulation results based on CarSim-MATLAB cosimulations are presented to validate the effectiveness and superiority of the proposed controller compared to conventional control methods. © 2023 IEEE.

关键词： GRAMPC Model predictive control pitch motion PSO semi-active suspension

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Human-Machine Safety System Based on Visual Perception

Design and Implementation of Human-Machine Safety System Bas...

引用

2021 China Automation Congress, CAC 2021

作者： Zhao, Liu Jin, Jing Lin, Weiyang Guo, Shan Ma, Yixiang Gao, Ying Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China Research Institute of Intelligent Control Systems Harbin Institute of Technology Harbin150001 China Space Contral and Interial Technology Research Center Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781665426473

A human-machine safety system based on multi-target detection and tracking is proposed for the safety problems in the human-machine coexistence environment. For the motion state of pedestrians, the YOLOv5 detection algorithm and Deep SORT tracking algorithm are used to compare and study the effects of different activation functions and loss functions on the performance of neural networks, and the detection accuracy is improved by using Mish activation functions, and the motion trajectory and motion speed of pedestrians are obtained. To address the human-machine safety issue, the human-machine safety system model is proposed to establish the information feedback from vision processing to robot decision making and control robot motion decision. It is verified on the actual system and the goal of human-machine safety is achieved. © 2021 IEEE

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Random Forest Regression for Battery State-of-Health Estimation Based on Unsupervised Transfer Component Analysis Domain Adaptation

Random Forest Regression for Battery State-of-Health Estimat...

引用

2022 IEEE International Conference on Industrial technology, ICIT 2022

作者： Tian, Jilun Zhang, Jiusi Huangy, Congsheng Chowz, Mo-Yuen Luo, Hao 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

ISBN: (纸本)9781728119489

Machine learning is an useful approach estimating the state-of-health (SOH) of the lithium-ion batteries and had been successfully implemented on battery management systems (BMS). However, the SOH estimation accuracy of the machine learning relies highly on the similarity of training dataset and battery data of estimation. In other words, the machine learning approach may fail if the battery of estimation is operated in a different condition from the condition set for collecting the training dataset. This paper aims on solving such a problem by proposing a transfer component analysis-random forest regression (TCA-RF) approach. The robustness of this proposed approach is ensured by the random forest regression, which is an ensemble learning approach. The generalization of this proposed approach is enhanced by transfer component analysis since it achieves the domain adaption with well transformation of features between two datasets. Two battery ageing datasets collected in different operating conditions are selected in this paper to validate the success of the proposed work, where these two datasets are collected by the Center for Advanced Life Cycle engineering (CALCE) and the National Aeronautics and Space Administration (NASA) Prognostics Center of Excellence (PCoE). The proposed work is further compared with multiple commonly adopted intelligent algorithms to showcase the high performance of the proposed work. The experimental results shows that the proposed TCA-RF approach has a better accurate SOH estimation comparing to other estimation algorithms by 2% to more 50%. © 2022 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Sequential Fusion Filters for Nonlinear Multi-Sensor System with Random Packet Dropout and Composite Correlated Noise

SSRN

引用

SSRN 2023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 study investigates event-triggered (ET) mechanism-based sequential fusion filtering for nonlinear multi-sensor systems with composite correlated noise and random packet dropout. Composite correlated noise means that the observation noise at the same time is correlated, while the observation noise is also correlated with the process noise at the previous and the same instants. To minimize the energy loss within the system, the ET mechanism is used to reduce the communication rate of the sensors. The equation for the local filtering process is derived based on whether the ET mechanism has been triggered. To improve the accuracy of the filter, a noise estimator for local observations is developed using the ET mechanism. A two-step prediction method is used to calculate the estimate state vector of the main filter for time updating. In this paper, the sequential fusion filtering algorithm under the Bayesian framework is derived to solve the nonlinear systems with above problems, and the numerical implementation of the algorithm is given by the cubature Kalman filter (CKF). Finally, simulation experiments demonstrate that the developed algorithm enables a reduced communication rate of the sensor system while maintaining powerful filter estimation performance. © 2023, The Authors. All rights reserved.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

A data-driven disturbance estimation algorithm based on adaptive observer for MIMO linear systems

A data-driven disturbance estimation algorithm based on adap...

引用

第34届中国过程控制会议

作者： Xiaoyi Xu Hao Luo Xiao Zhang Department of Control Science and Engineering Harbin Institute of Technology Department of Automation Science and Electrical Engineering Beihang University

The adaptive observer is a well-developed datadriven algorithm for co-estimation of system parameters and ***,inevitable disturbances can affect the systems and lead to deterioration of the algorithm *** disturbance estimation methods require prior knowledge about model parameters and disturbance *** paper presents a robust adaptive observer method for multiple-inputmultiple-output linear systems subject to *** proposed method can perform joint estimation of unknown parameters,states and disturbances without any prior information about the model parameters and *** stability and convergence of the algorithm are rigorously proved to ensure that the estimation errors converge exponentially to *** results of a numerical example demonstrate the effectiveness of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Finite Time Prescribed Performance Fault Tolerant control for Spacecraft Attitude Maneuver

Adaptive Finite Time Prescribed Performance Fault Tolerant C...

引用

IEEE Conference on Decision and control

作者： Ze Yang Baoqing Yang Ruihang Ji Jie Ma Department of Control Science and Engineering Harbin Institute of Technology Harbin China Department of Electrical and Computer Engineering National University of Singapore Singapore

In this paper, an active fault tolerant control method for spacecraft against actuator faults, uncertainties and disturbances is investigated. First, an adaptive iterative learning observer with improved adaptive law is proposed, which greatly improves the accuracy and speed of fault estimation. Then, a novel adaptive finite time prescribed performance fault tolerant controller is proposed, which has flexible performance constraints according to faults and control references, with better robustness and lower conservatism, breaking the limitation of fixed performance constraint. Next, an online optimal control allocation strategy is designed to achieve high-performance actuator allocation under saturation and fault constraints. Finally, through numerical simulation, the effectiveness and robustness of the proposed scheme are illustrated by comparing with existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stacked Dual-stream LSTM based Feature Extraction Network for Hyperspectral Image Classification

Stacked Dual-stream LSTM based Feature Extraction Network fo...

引用

第42届中国控制会议

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

Remote sensing technology plays a significant role in classifying and detecting on-ground objects accurately. Specifically, hyperspectral imagery outperforms other remote sensing tools in terms of its abundant spatial and spectral ***, analyzing hyperspectral images is always hampered by their redundant spectral dimensionality. In this paper, we proposed a novel stacked dual-stream long short-term memory(LSTM) based feature extraction network(SDLSTMnet) for hyperspectral image classification. The whole network consists of two streams for spatial and spectral information, respectively. In this network, convolutional layers are absolutely removed because of their time-consuming calculating and optimizing *** a substitute, stacked LSTM layers are utilized to capture the spatial information within sample neighbourhoods. Notably, the latent sequential features are captured to simulate the neighbouring regions of samples. Furthermore, the sequential features along the spectral dimension are also extracted by stacked LSTM layers because these bands are continuous locally. Finally, the presented fusion module is capable to fuse and align these extracted features for classification. Multiple experiments are conducted to prove the effectiveness of the proposed SDLSTMnet. Compared with other state-of-the-art techniques, SDLSTMnet is capable to reduce the spectral dimension and increase the classification accuracies simultaneously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Transferability via Information Bottleneck Constraints

arXiv

引用

arXiv 2024年

作者： Qi, Biqing Gao, Junqi Liu, Jianxing Wu, Ligang Zhou, Bowen Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China Tshinghua University Bejing China Frontis.AI Beijing China School of Mathematics Harbin Institute of Technology Harbin150001 China

From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitively, diminishing the reliance of adversarial perturbations on the original data, under equivalent attack performance constraints, encourages a greater reliance on invariant features that contributes most to classification, thereby enhancing the transferability of adversarial attacks. Building on this motivation, we redefine the optimization of transferable attacks using a novel theoretical framework that centers around IB. Specifically, to overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation. Moreover, to quantitatively evaluate mutual information, we utilize the Mutual Information Neural Estimator (MINE) to perform a thorough analysis. Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB. Our code is available at ***/IBTA. Copyright © 2024, The Authors. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Improvement of the Predictive control Method for the High-Level controller 17

Improvement of the Predictive Control Method for the High-Le...

引用

17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer engineering, TCSET 2024

作者： Budashko, Vitalii Sandler, Albert Glazeva, Oksana Educational and Scientific Institute of Automation and Electrical Engineering National University 'Odessa Maritime Academy' NUOMA Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of the theory of automatic control and computer technology Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of electrical engineering and electronics Odesa Ukraine

ISBN: (纸本)9798331520564

Automation of ship maneuvering in limited sailing conditions usually requires 100% redundancy of thrusters (THRs) of various modifications and their locations in accordance with the matrix. The hierarchy of the motion control system is branched by levels using high-level motion controllers and THRs control distribution algorithms, which allows for a modular design with software, where the high-level controller (HLC) can be designed without comprehensive information about the thruster motors, and the input signal branching and speed limits are handled by the motion controller. But, for certain THRs configurations, this branching leads to the decrease in control efficiency due to the limitation of data on the physical characteristics of the ships and the operation of the motion controller. This research examines different approaches to improving control efficiency using methods of nonlinear predictive control models as a basis for developing motion controllers with decision optimization based on relevant constraints. The implemented branched system is the result of solving two simple problems of ship's motion, which highlight the related problems. The use of different approaches to eliminate the identified shortcomings made it possible to develop the nonlinear controller that combines the motion controller with distributed control of the THRs and ensuring the certain level of system reliability. The modularity of the control system is provided by the expansion of the closed system, which made it possible to achieve an increase in efficiency during the combined mode of operation. The obtained solution of nonlinear control with time-varying constraints made it possible to increase the accuracy of the control with a decrease in the duration of the pause in response to the change of the disturbance within 10% © 2024 IEEE.

关键词： Predictive control systems

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：