检索结果-内蒙古大学图书馆

13th IEEE International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Zeng, Sheng Sun, Xiao Chen, Kang Huang, Weibing Chen, Yi Chen, Dan Xu, Zhezhuang College of Electrical Engineering and Automation Key Laboratory of Industrial Automation Control Technology and Information Processing Fuzhou University Education Department of Fujian Province Fuzhou350000 China Evomotion Co. Ltd. Guangdong Shenzhen518000 China

ISBN: (纸本)9798350315196

High cost of environmental interaction and low data efficiency limit the development of reinforcement learning in robotic grasping. This paper proposes an end-to-end robotic grasping method based on offline reinforcement learning via sequence modeling. It considers the most recent n-step history to assist the agent in making decisions, where a predictive model learns to directly predict actions from raw image inputs. The experimental results show that our method can achieve higher grasping success rate with less training data than traditional reinforcement learning algorithms in offline setting. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Robust control of Feeding Speed in Coal Seam Drilling Process Considering Borehole Friction

Robust Control of Feeding Speed in Coal Seam Drilling Proces...

引用

2024 China automation Congress, CAC 2024

作者： Liu, Xiao Chen, Luefeng Lu, Chengda Fan, Haipeng Wu, Min Pedrycz, Witold School of Automation The Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Wuhan430074 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Department of Computer Engineering Istinye University Sariyer Istanbul34396 Turkey

ISBN: (纸本)9798350368604

During the coal seam drilling process, the drill string is subject to compressive deformation, compounded by unpredictable variations in formation hardness and borehole wall friction, leading to challenges in maintaining a stable feeding speed. This paper presents a novel approach by introducing uncertain parameters to describe the effects of formation hardness and borehole wall friction. Drill string axial movement model is modeled as a polyhedral system based on a lumped parameter representation. To meet industrial performance requirements, we design a robust H∞ controller to achieve consistent feeding speed control. Our simulation results demonstrate the controller’s effectiveness in ensuring system stability despite fluctuations in formation hardness and drill string friction. © 2024 IEEE.

关键词： Coal deposits

来源：评论

学校读者我要写书评

暂无评论

Model-Based Reinforcement Learning for Robotic Arm control with Limited Environment Interaction 13

Model-Based Reinforcement Learning for Robotic Arm Control w...

引用

13th IEEE International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Chen, Yi Sun, Xiao Zheng, Song Huang, Weibing Zeng, Sheng Chen, Dan Xu, Zhezhuang College of Electrical Engineering and Automation Key Laboratory of Industrial Automation Control Technology and Information Processing Fuzhou University Education Department of Fujian Province Fuzhou350000 China Evomotion Co. Ltd. Shenzhen Guangdong518000 China

ISBN: (纸本)9798350315196

Reinforcement Learning (RL) has been applied to robotic arm control, which enables the agent to learn an effective policy to solve complex tasks. However, it requires constant interaction with the environment leading to low sample efficiency. In this paper, we propose a robotic arm control approach based on planning via lookahead search, which is a model-based RL algorithm to improve the sample efficiency. The approach builds an environment model in order to obtain the dynamics of the environment. Thus the model can be used to plan future actions by a tree-based search. The experiments show that our approach can solve the task of robotic arm control with less environmental samples. © 2023 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Predicting the State of Crane Spreader for Steel Bar Delivery Based on Machine Learning 13

Predicting the State of Crane Spreader for Steel Bar Deliver...

引用

13th IEEE International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Liu, Zibin Xu, Zhezhuang Chen, Jian Cui, Chen Chen, Boyu Zhang, Qingdong College of Electrical Engineering and Automation Key Laboratory of Industrial Automation Control Technology and Information Processing Education Fuzhou University Department of Fujian Province Fuzhou350000 China Sansteel Minguang Co. Ltd Fujian Sanming353000 China

ISBN: (纸本)9798350315196

Deducing the twisting pattern of spreader is very important for crane operators in steel warehouse, since crane spreaders have to be rotated repeatedly at steel bar transport sites. To improve the efficiency of the steel bar delivery, the state prediction for crane spreaders is necessary. In order to fulfill this requirement, the HTSK-LN-ReLU model prediction method based on Optuna optimization is applied in this paper. We deploy the IMU on the spreader surface, and then obtain the state data during the operation of the crane spreader by wireless transmission. The data are first denoised through fourier filtering, and then the Optuna framework is used to optimize the HTSK-LN-ReLU model's hyperparameters. The evaluation index of mean square error is used for model evaluation, and finally the optimal hyperparameter combination of the model is selected from 200 comparison experiments. Experimental results demonstrate superior performance of the HTSK-LN-ReLU model in predicting the state of crane spreader for steel bar delivery. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive control of an Inverted Pendulum by a Reinforcement Learning-based LQR Method

arXiv

引用

arXiv 2023年

作者： Yıldıran, Uğur Yildiz Technical University Control and Automation Engineering Department İstanbul Turkey

Inverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model. However, deriving a mathematical model using physical parameters or system identification techniques requires manual effort. Moreover, the designed controllers may perform poorly if system parameters change. To mitigate these problems, recently, some studies used Reinforcement Learning (RL) based approaches for the control of inverted pendulum systems. Unfortunately, these methods suffer from slow convergence and local minimum problems. Moreover, they may require hyperparameter tuning which complicates the design process significantly. To alleviate these problems, the present study proposes an LQR-based RL method for adaptive balancing control of an inverted pendulum. As shown by numerical experiments, the algorithm stabilizes the system very fast without requiring a mathematical model or extensive hyperparameter tuning. In addition, it can adapt to parametric changes online. © 2023, CC BY-NC-ND.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

An Experimental Research on Temperature Accuracy Algorithm in Fan Coil Thermostat 6

An Experimental Research on Temperature Accuracy Algorithm i...

引用

6th IEEE International Electrical and Energy Conference, CIEEC 2023

作者： Ari, Yunus Cücük, Ergün Karateke, Seda Institute of Graduate Studies Istanbul University - Cerrahpaşa Electric and Electronic Engineering Istanbul34320 Turkey Control and Automation Systems Industry and Trade Inc. Department of Research and Development Ges Teknik Air Conditioning Istanbul34852 Turkey Istanbul Topkapi University Faculty of Engineering Department of Computer Engineering Istanbul34087 Turkey

ISBN: (纸本)9798350346671

The efficient operation of HVAC&R systems are based on keeping indoor temperature and air quality at an optimum level without disturbing comfort. Starting from this point, in this experimental research, the factors affecting the measurement accuracy during the room temperature detection of a wall mount fan coil thermostat were examined. Among the external effects, the effect of the device components on the measurement was focused and the solution of the measurement deviations occurred in this extent was investigated. Based on the experiments, the algorithm that must be applied to reach the optimum temperature measurement of a room thermostat developed for Fan Coil systems was proposed. © 2023 IEEE.

关键词： Thermostats

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

Advancing Orchard Fruit Detection: An Innovative Agricultural Foundation Model Approach

Advancing Orchard Fruit Detection: An Innovative Agricultura...

引用

2024 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2024

作者： Li, Jiajia Lammers, Kyle Yin, Xunyuan Yin, Xiang He, Long Lu, Renfu Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University MI United States School of Chemical and Biomedical Engineering Nanyang Technological University Singapore Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Department of Agricultural and Biological Engineering Pennsylvania State University United States United States Department of Agriculture Agricultural Research Service East LansingMI United States Department of Mechanical Engineering Michigan State University East LansingMI United States

ISBN: (纸本)9798331302214

Fruit harvesting poses a significant labor and financial burden on the fruit industry, which underscore the urgent need for advancements in robotic harvesting solutions. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced Vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated across several metrics, outperforming existing state-of-the-art algorithms in our MetaFruit, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset (https://***/datasets/jiajiali/metafruit) and detection framework (https://***/JiajiaLi04/FMFruit) are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector. © 2024 ASABE Annual International Meeting. All rights reserved.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Levitation control of Maglev Systems Based on Cascade control

Levitation Control of Maglev Systems Based on Cascade Contro...

引用

2022 Chinese automation Congress, CAC 2022

作者： Wen, Jie Wu, Jikuo Tian, Yukai North University of China Department of Automation Taiyuan China North University of China School of Electrical and Control Engineering Taiyuan China

ISBN: (纸本)9781665465335

We address the levitation control of the single-point levitation system for maglev train by using the cascade control strategy in this paper. The levitation system is divided into two subsystems, i.e., electromagnetic system and motion system. In order to stabilize the levitation system more faster and roust, we design the sliding mode controller and fuzzy Proportional Integral Derivative (PID) controller, which constitute the cascade control, to control the electromagnetic system and motion system, respectively. The effectiveness and robustness of the cascade control are also verified in the numerical simulations. © 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

Combined Nonlinear control System for Non-Affine Multi-Loop Plant with control and State Delays 4

Combined Nonlinear Control System for Non-Affine Multi-Loop ...

引用

4th International Conference on control Systems, Mathematical Modeling, automation and Energy Efficiency, SUMMA 2022

作者： Eremin, Eugenie L. Nikiforova, Larisa V. Shelenok, Evgeniy A. Amur State University Information and Control Systems Department Blagoveshchensk Russia Pacific National University Automation and System Engineering Department Khabarovsk Russia

ISBN: (数字)9781665456593

ISBN: (纸本)9781665456593

The paper considers the synthesis of a combined nonlinear controller of the control multiply-connected system for an input-non-affine plant with delay at the input signal and state. Dynamics of the plant changes in stages. The plant under consideration operates in conditions of a parametric, functional and structural uncertainties, in the presence of a permanent external noise and measurement only the controlled variable (output signal). The structure of a multiply connected control system includes an implicit reference model, predictor-compensator and correction filters. The authors use the hyperstability criterion and method for constructing L-dissipative dynamic systems to synthesize the nonlinear algorithms for combined control system. The structural synthesis is performed by defining the special estimates which guarantee the validity of the V.M. Popov's integral inequality. Operability of the developed hyperstable control system with structural perturbation is ensured with the help of the special L-dissipativity conditions. At the final section of the article with the help of simulation the authors show the quality of the obtained nonlinear control system. The results of the system simulation show the fulfillment of the control goal with a sufficiently high quality. The obtained results may be useful for construction the control systems for technical plants which dynamics can be described as non-affine MIMO-system. For example, the robot-manipulators and some plants of heat power engineering has the mathematical description like multi-connected systems. © 2022 IEEE.

关键词： MIMO 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：