检索结果-内蒙古大学图书馆

IEEE Instrumentation and Measurement technology Conference

作者： Yushuo Hu Qiang Wang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Compared to other techniques, mechanical weeding has many benefits that support more accurate weeding operations without polluting the environment. The primary challenge is precisely locating target crops in complex surroundings, and deep learning methods are suitable for this kind of work. In this paper, in order to apply object detection approaches to agricultural weeding, we build two object detection models, YOLOv5 and YOLOv8, which are based on a total of 838 labeled images of corn seedlings in farmland. The two models were then implemented on different embedded systems, and their performance was compared. Model compression is also used to optimize network performance and enhance model deployment on embedded devices. Finally, we applied it to the actual project, and the results demonstrated that the object detection model could accurately identify target corn seedlings while significantly reducing computation and parameters.

关键词： YOLO Performance evaluation Deep learning Accuracy Embedded systems Image coding Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Subspace-Aided SIR Approach with Application to Indicator Diagram Estimation of BPUs

Subspace-Aided SIR Approach with Application to Indicator Di...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Xinyu Qiao Jilun Tian Xiaoyi Xu Jiusi Zhang Hao Luo Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

Aiming at the difficulty in the estimation of indicator diagrams for electrical parameters of beam pumping units (BPUs), a subspace-aided stable image representation (SIR) approach is proposed for the search of the mapping relationship among electrical and force parameters and the implementation of accurate estimation of indicator diagrams. The advantage of the proposed method is a data-driven implementation, which does not require analyzing the dynamic relationship and model knowledge of the BPUs. Further, through collecting data from the BPUs, the Hankle matrix is constructed to form signal spaces. Then, the SIR can be calculated by performing LQ decomposition, namely, finding the mapping relationship among electrical and force parameters, which is helpful for using the electrical parameter estimation indicator diagram. Eventually, the effectiveness and applicability of the proposed method are verified through the actual data of BPUs.

关键词： Industrial electronics Analytical models Parameter estimation Accuracy Force Dynamics Estimation

来源：评论

学校读者我要写书评

暂无评论

Fast Terminal Quasi-Sliding Mode control for Spacecraft Formation Flying Systems via RBFNN

Fast Terminal Quasi-Sliding Mode Control for Spacecraft Form...

引用

2023 China Automation Congress, CAC 2023

作者： Xiang, Zhihua Li, Yufei Zhong, Xiaoqing Lei, Wenxiao Tang, Feilong Ju, Yinhao Harbin Institute of Technology Department of Control Science and Engineering Harbin China Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing China Institute of Telecommunication Satellite China Academy of Space Technology Beijing China

ISBN: (纸本)9798350303759

This paper investigates the problem of relative control for spacecraft formation flying systems. With elliptical orbit, the model is built by relative position vector. To improve the tracking performance, a controller is designed and proven stable as a fast terminal quasi-sliding mode controller with feedback control based on radial basis function neural network (RBFNN). The performance of the proposed method is validated with numerical simulation. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning and Disturbance Observer Based Optimal control for Uncertain Systems

Reinforcement Learning and Disturbance Observer Based Optima...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Yucheng Zhu, Yupeng Wang, Shaohai Yin, Liyuan Zhu, Hongming Sun, Xingjian Wu, Chengwei Harbin Institute of Technology Department of Control Science and Engineering Harbin China Tianjin Zero-One Intelligent Technology Co. Ltd Tianjin China Nantong University Department of Electrical Engineering Nantong China

ISBN: (纸本)9798350303759

This paper investigates the robust adaptive optimal control problem for linear systems in the presence of matching uncertainties. A nominal controller utilizing Q-Iearning algorithm is designed for the nominal linear system without uncertainties. Introducing a disturbance observer serves the purpose of actively estimating uncertainties, enabling proactive compensation for matching uncertainties. The analysis of the closed-loop system's stability under the robust adaptive optimal controller is conducted, presenting sufficient conditions to ensure its stability. Finally, the control algorithm is validated using a two-wheeled mobile robot as the experimental platform. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Parameter Identification Based on Generalized Orthonormal Basis Function Without Persistent Excitation: A Learning-Based Paradigm

Parameter Identification Based on Generalized Orthonormal Ba...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Kuan Li Weijie Su Xingyong Li Yang He Minchang Huang Hao Luo Shanghai Aerospace Control Technology Institute Shanghai China Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

This paper presents the parameter identification based on generalized orthonormal basis function (GOBF) without persistent excitation via two learning-based paradigms. The problem is formulated as a two-stage identification of poles and weight coefficients of GOBFs. The GOBF is designed based on the two-parameter Kautz basis function for the compatiblity with complex poles. The two learning-based paradigms are established on the nature-inspired meta-heuristic optimization and deep reinforcement learning, respectively. The ability of identification without strict persistent excitation is discussed as well. The effectiveness of the two paradigms are verified through a simulation study on a 4-order transfer function model.

关键词： Parameter estimation Metaheuristics Transfer functions Optimization methods Deep reinforcement learning Informatics Convergence

来源：评论

学校读者我要写书评

暂无评论

Input saturation control of manipulator based on fully actuated system approach

Input saturation control of manipulator based on fully actua...

引用

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

作者： Yongqiang Xiao Guangbin Cai Mingzhe Hou Department of Missile Engineering Rocket Force University of Engineering Xi’an China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

A control strategy based on fully actuated system approach is proposed for the manipulator system with input saturation. By introducing a smooth hyperbolic tangent function to approximate the saturation function, the original system is transformed into a smooth system. The complex differential operation is converted into algebraic operation by introducing a first-order low-pass filter. By designing an adaptive law, the uncertainty of the system model is effectively estimated. Based on fully actuated system approach, the controller for the manipulator system is directly designed, which eliminates the step of converting the original second-order strict feedback system into a first-order strict feedback system, reduces the steps of controller design, lowers the complexity of algorithm design, and effectively avoids the "differential explosion" problem. The Lyapunov stability theory is used to prove that all signals in the closed-loop system are uniformly ultimately bounded. Finally, numerical simulations of the manipulator system are performed to verify the effectiveness of the proposed method.

关键词： Adaptation models Uncertainty Adaptive systems Low-pass filters Manipulators Numerical simulation Explosions

来源：评论

学校读者我要写书评

暂无评论

An Automotive Headlight Leveling control Strategy with Rough Road Identification 42

An Automotive Headlight Leveling Control Strategy with Rough...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhao, Xinyi Zhao, Linhui Deng, Zhichong Ji, Guohuang Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China Intelligent Power System Co. Ltd. Wuhan430056 China

ISBN: (纸本)9789887581543

The Automotive Headlamp Leveling System (ALS), aims to ensure the stability of the illumination range of the headlamp by vertically rotate the headlamp using motors when the body attitude changes. This paper proposes an ALS scheme which obtains the body attitude from body height sensors and accordingly calculates the output angles of left headlamp and right headlamp respectively based on Euler transformation. Different from existing ALS, this scheme uses several strategies to improve the performance of ALS, including anti-shake function, working mode division and rough road identification. The purpose of rough road identification is to avoid unexpected vibration of headlamp caused by ALS on rough road and decision tree model is chosen for identification to improve the accuracy. Moreover, several field tests are performed to verify the validity and stability of the system. © 2023 Technical Committee on control theory, Chinese Association of Automation.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Sampling-efficient path planning and improved actor-critic-based obstacle avoidance for autonomous robots

引用

Science China(Information Sciences) 2024年第5期67卷 197-214页

作者： Yefeng YANG Tao HUANG Tianqi WANG Wenyu YANG Han CHEN Boyang LI Chih-yung WEN Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Center for Control Theory and Guidance Technology Harbin Institute of Technology School of Engineering The University of Newcastle Research Center for Unmanned Autonomous Systems The Hong Kong Polytechnic University

Autonomous robots have garnered extensive utilization in diverse fields. Among the critical concerns for autonomous systems, path planning holds paramount importance. Notwithstanding considerable efforts in its development over the years, path planning for autonomous systems continues to grapple with challenges related to low planning efficiency and inadequate obstacle avoidance response in a timely *** study proposes a novel and systematic solution to the path planning problem within intricate office buildings. The solution consists of a global planner and a local planner. To handle the global planning aspect, an adaptive clustering-based dynamic programming rapidly exploring random tree(ACDP-RRT) algorithm is proposed. ACDP-RRT effectively identifies obstacles on the map by leveraging geometric *** obstacles are then represented as a collection of sequentially arranged convex polygons, optimizing the sampling region and significantly enhancing sampling efficiency. For local planning, a network decoupling actor-critic(ND-AC) algorithm is employed. The proposed ND-AC simplifies the local planner design process by integrating planning and control loops into a neural network(NN) trained via an end-to-end model-free deep reinforcement learning(DRL) framework. Moreover, the adoption of network decoupling(ND) techniques leads to an improved obstacle avoidance success rate when compared to conventional actor-critic(AC)-based methods. Extensive simulations and experiments are conducted to demonstrate the effectiveness and robustness of the proposed approach.

关键词： rapidly exploring random tree (RRT) adaptive clustering network decoupling actor critic (AC) path planning

来源：评论

学校读者我要写书评

暂无评论

External blast load factors for dome structures based on reliability

引用

Defence technology（防务技术） 2022年第2期18卷 170-182页

作者： Shao-bo Qi Guang-yan Huang Xu-dong Zhi Feng Fan Richard GJFlay State Key Laboratory of Explosion Science and Technology Beijing Institute of TechnologyBeijing100081PR China Key Lab of Structure Dynamic Behaviour and Control of the Ministry of Education Harbin Institute of TechnologyHarbin150090China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin150090China Department of Mechanical Engineering University of AucklandPrivate Bag 92019Auckland1142New Zealand

Dome structures have been used extensively for industrial,residential,and military ***,it is necessary to understand the damage risk potential for such structures for blast-resistant design *** paper investigates the effect of blast load variability on the design value and the structural dynamic ***,the sources of uncertainty in the external blast load on dome structures were discussed *** based on the probabilistic blast load model for the dome,the rationality of a deterministic mass-increase safety method was *** was found that previous deterministic design method cannot provide a consistent and sound assurance factor or reliability index on the entire dome *** addition,it was also proved that the assurance-based load method fails to ensure compliance with structural safety design standards on the dome roof when compared with the reliability-based blast method.A sensitivity analysis on the probabilistic blast load was conducted,and the results indicate that stand-off distance and explosive mass both act as dominant sources to influence the mean and variability of blast ***,based on the Latin hypercube sampling method,a reliability-based external blast load factor technique was *** technique was further used to estimate structural damage levels of a single-layer reticulated dome under different reliability requirements,associated with a low,medium,and high level of protection grades for a specific explosion scenario,and it indicated that this technique can be useful in the building design to achieve a higher structural anti-explosion *** study herein can serve as a reference for the calculation method of designed blast load.

关键词： Dome structure Airblast variability Deterministic design Assurance factor Reliability-based blast load factor Structural damage levels

来源：评论

学校读者我要写书评

暂无评论

Data-driven Based PEMFC EIS Modeling with Nyquist Plot 48

Data-driven Based PEMFC EIS Modeling with Nyquist Plot

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Zhang, Haochuan Lv, Jianfeng Kuang, Jiyuan Wang, Zhenhuan Matraji, Imad Muhl, Patrick Liu, Jianxing Harbin Institute of Technology Department of Control Science and Engineering Harbin China Harbin Institute of Technology Space Control and Inertial Technology Research Center Harbin China Ftxt Energy Technology Co. Ltd Baoding071000 China

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Electrochemical impedance spectroscopy (EIS) Nyquist plot modeling has been attached great importance to fault diagnosis of proton exchange membrane fuel cell (PEMFC) system. This paper applies Gaussian process regression (GPR) and Bayesian optimization (BO) to the problem of building an adaptive EIS Nyquist plot model of PEMFC. The experimental results show that GPR performs better than multivariate polynomial regression and equivalent circuit model (ECM) method for this task when a small number of training samples are available. Therefore, this method can be a suitable approach for online adaption of EIS Nyquist plot model for fault diagnosis application. © 2022 IEEE.

关键词： Gaussian noise (electronic)

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：