检索结果-内蒙古大学图书馆

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Rana Ashar Burhan Sadiq Hira Mohiuddin Saniya Ashraf Muhammad Imran Anayat Ullah Control Automotive and Robotics Lab National Centre of Robotics and Automation Rawalpindi Pakistan Department of Electronic Engineering Balochistan University of IT Engineering and Management Sciences Quetta Pakistan

Video Stabilization is the basic need for modern-day video capture. Many methods have been proposed throughout the years including 2D and 3D-based models as well as models that use optimization and deep neural networks. This work describes the implementation of cutting-edge Recurrent All-Pairs Field Transforms (RAFT) for optical flow estimation in video stabilization. we use a pipeline that accommodates the large motion. It then passes the results to the optical flow for better accuracy. After that, it satisfies the inaccuracies of the optical flow and makes it robust to occlusion, Parallax, and moving objects. Our approach yields better results (visually and quantitatively) compared to other optimization and deep learning-based visual stabilization techniques.

关键词： Industries Deep learning Visualization Pipelines Neural networks Estimation Transforms

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Solutions for Troubleshooting Autonomous Industrial Mobile Robots

Virtual Reality Solutions for Troubleshooting Autonomous Ind...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Cihat Talat Akpinar Özcan Koşar Akif Durdu Computer Engineering Research and Development Elfatek Elektronik Ltd. Co. Konya Turkey Department of Electrical and Electronics Engineering Robotics Automation Control Laboratory (RAC-LAB) Konya Technical University Konya Turkey

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This study aims to develop a virtual reality (VR) application to improve the fault detection and troubleshooting processes of autonomous industrial mobile robots. The complex systems and operating environments of autonomous robots make fault detection challenging for users, requiring effective and user-friendly solutions to overcome these difficulties. In this context, the Robot Operating System (ROS) was utilized to detect errors in robots and record these errors in a database. Thanks to the modular structure and robust communication infrastructure offered by ROS, faults in the robots were monitored and analyzed through ROS *** study demonstrates the effective use of VR technology in the maintenance and repair processes of autonomous industrial mobile robots. By integrating ROS-based data collection and fault detection into a VR environment for user training, robot operators are enabled to troubleshoot faults more quickly and effectively. In this way, it is aimed to achieve time and cost savings in industrial processes.

关键词： Training Service robots Databases Fault detection Operating systems Virtual reality Maintenance engineering Maintenance Mobile robots Monitoring

来源：评论

学校读者我要写书评

暂无评论

Container Distance Estimation for Automated RTG via Improved SOLOv2 Instance Segmentation

Container Distance Estimation for Automated RTG via Improved...

引用

第43届中国控制会议

作者： Zhengtao Yu Jun Yang Jinya Su School of Automation Southeast University Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University Department of Aeronautical and Automotive Engineering Loughborough University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This study develops a simple real-time algorithm inferring the relative distance between containers stacked in operational yards and spreaders of Rubber Tire Gantry(RTG) in support of fully automated RTG operations in ports. The proposed scheme is based on SOLOv2 instance segmentation network with image captured by camera mounted on RTG driver's ***, distance calculation is achieved by containers' surface recognition via instance segmentation and geometric information pertaining to the containers. To meet the dual demands of accuracy and reduced resource consumption, the original backbone network of SOLOv2, namely resnet18, is replaced by GhostNet. This substitution enables the extraction of multi-level feature maps for fusion, significantly reducing network complexity without sacrificing accuracy. The proposed algorithm is validated by comparative experiments on a self-curated real-life dataset, demonstrating a remarkable reduction of 91.6% in FLOPS and 55.7% in Params for the improved SOLOv2 framework.

关键词： Distance Estimation Instance Segmentation Rubber Tire Gantry Network lightweight

来源：评论

学校读者我要写书评

暂无评论

Robust Flatness-based control for Trajectory Tracking of an Underactuated Surface Ship

Robust Flatness-based Control for Trajectory Tracking of an ...

引用

IEEE International Conference on Automatica (ICA-ACCA)

作者： Matheus T. De Sousa José Oniram De A. Limaverde Filho Eugênio Fortaleza Department of Electrical Engineering University of Brasília Brasília Brazil Automation and Control Group (GRACO) University of Brasília Brasília Brazil

ISBN: (数字)9798350378115

ISBN: (纸本)9798350378122

The control of underactuated mechanical systems represents one of the most active areas of research in robotics and control system engineering, with a strong practical interest. Recently, methods based on differential flatness theory have been found to be useful in nonlinear control design for marine vehicles. However, to the best of the authors’ knowledge, existing works based on differential flatness theory have not addressed the impact of external non-zero mean disturbances or parametric uncertainties in the controller design for non-flat underactuated marine vehicles. Within this context, this work explores a scenario of trajectory tracking for a non-flat and nonlinear model of an underactuated surface ship under the influence of external disturbances and parametric uncertainties. By exploiting the Liouvillian and flat properties of the linearized system, we propose a tracking controller with integral action. Numerical simulation results show the proposed controller’s capability to overcome common problems of real-world systems, which may facilitate its implementation in practical applications.

关键词： Uncertainty Trajectory tracking Numerical simulation Robustness Trajectory Numerical models Proposals Mechanical systems Underactuated surface vessels Robots

来源：评论

学校读者我要写书评

暂无评论

Domain Generalized Solar Cell Defect Segmentation Based on Shape-Aware and Multi-View Meta-Learning 42

Domain Generalized Solar Cell Defect Segmentation Based on S...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Kun Yang, Ying Mao, Jingkun Liu, Weipeng School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300130 China Tianjin University of Technology Department of Automation Tianjin300384 China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789887581543

Various defects are inevitably generated in the manufacturing process of solar cells. Deep learning-based methods for defect segmentation under closed situation have achieved remarkable progress. Due to the difference of imaging condition and camera parameter under different production line, there are large differences in brightness distribution of solar cell images. The model trained under closed situation cannot achieve good performance in opened situation such as multi-production lines. In this paper, a new shape-aware and multi-view meta-learning scheme is proposed to improve the model generalization performance for single-domain solar cell defect segmentation. The scheme roots in gradient-based meta-learning. Multi-brightness view information is yielded from the generated augmented images, and explicitly simulating domain shift with virtual meta-train and meta-test during training to mitigate overfitting in single-source domain train and unstable prediction. Importantly, considering tiny and faint solar cell defects are not easily identified under different image brightness conditions, shape edge constraint loss is proposed to encourage shape compactness and shape smoothness of segmentations. Experimental results show that the proposed method has high segmentation accuracy, which outperforms the state-of-the-art methods. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Solar cells

来源：评论

学校读者我要写书评

暂无评论

Optimization with genetic algorithms of individual pitch control design with and without azimuth offset for wind turbines in the full load region

引用

IFAC-PapersOnLine 2023年第2期56卷 342-347页

作者： Manuel Lara Juan Garrido Jan-Willem van Wingerden Sebastian Paul Mulders Francisco Vázquez Department of Electrical Engineering and Automation University of Cordoba Campus of Rabanales 14071 Cordoba Spain Delft Center for Systems and Control Faculty of Mechanical Engineering Delft University of Technology Mekelweg 2 2628 CD Delft The Netherlands

The reduction of fatigue loadings in wind turbines to increase their lifetime has become of special interest from a control viewpoint. Individual Pitch control (IPC) is a well-known approach used to mainly mitigate periodic blade loads, and it is usually implemented with the assistance of the multi-blade coordinate (MBC) transformation, which transforms and decouples the measured blade load signals from a rotating frame into a non-rotating tilt-axis and yaw-axis. Nevertheless, these axes still show coupling between them in practical scenarios adversely affecting the system performance. Previous studies have demonstrated the benefits of including an extra tuning parameter in the MBC, the azimuth offset, in improving the performance achieved by the IPC. However, the tuning of this parameter and its real improvements that can be obtained compared to the IPC without this offset require more research. Here, two 1P+2P IPC, with and without additional azimuth offset, are designed and applied to the 5 MW reference turbine model developed by NREL using the FAST software as a simulation platform. The controller parameter tuning is formulated as an optimization problem that minimizes the blade fatigue load according to the Dirlik index and that is resolved through genetic algorithms. To fairly analyze the improvement entailed by the addition of the azimuth offset, both optimized IPC schemes, with and without azimuth offset, are compared qualitatively and quantitatively using a classical controller as the baseline case. From the simulation results, it can be stated that the optimal IPC scheme with azimuth offset compared with the IPC scheme without offset achieves improvements of around 11% in load reduction and pitch signal effort.

关键词： control system design control of renewable energy resources wind turbine control individual pitch control genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Simulation Analysis and Model Modification of the LWR Traffic Flow Theory

Simulation Analysis and Model Modification of the LWR Traffi...

引用

IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

作者： Yang Chen Jun Fu Anton Selivanov State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Department of Automatic Control and Systems Engineering University of Sheffield UK

ISBN: (数字)9798350344639

ISBN: (纸本)9798350344646

The surge in urbanization and ensuing traffic congestion underscores the imperative for contemporary traffic flow control models. This paper explores the Lighthill-Whitham-Richards (LWR) theory in the macroscopic domain of traffic flow control. It evaluates the accuracy and mathematical logic of simulation performance of related models, namely Greenshields, Newell-Daganzo, Greenberg, Underwood, and California. This paper employs thorough simulations that utilize a holistic three-dimensional(3D) analysis based on time, location, and density. It provides a comprehensive comparison and discusses specific features of each model. Additionally, a modification to the macroscopic model is proposed. The modified model overcomes the shortcomings of performing well only in some specific short ranges and achieves a full range of application effects. The study offers valuable guidance for real-life scenario selections and applications in the traffic domain.

关键词： Analytical models Accuracy Urban areas Transportation Predictive models Mathematical models Numerical models

来源：评论

学校读者我要写书评

暂无评论

Classification of skin lesions using morpho-granulometry features derived from color clusters

Classification of skin lesions using morpho-granulometry fea...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Gigi Tăbăcaru Simona Moldovanu Marian Barbu Department of Automatic Control and Electrical Engineering Faculty of Automation Computers Electrical Engineering and Electronics "Dunarea de Jos" University of Galati Galati Romania Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics The Modelling & Simulation Laboratory "Dunarea de Jos" University of Galati Galati Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

The skin lesion can be thought of as a biological system, so the morpho-granulometry of significant color clusters found in skin lesions is one of the elements that reproduce in a natural way the structure of the lesion, this novelty is highlighted in this study. Important features of skin lesions can be modulated by fusing neural networks (NN) and machine learning (ML). By choosing the nevus and melanoma classes, the primary goal was accomplished, and three databases were used to test the methodology. The characteristics based on morpho-granulometry allowed for the identification of microstructure within the images, which can be very helpful in characterizing the biological system. Based on random forest (RF) and extreme gradient boosting (XGboost) classifiers, this work aimed to improve the classification performance of important feature selection. The selected features from three free image databases with three NNs were classified. In a binary classification of nevus vs. melanoma, the results showed that the pattern recognition neural network (PRNN), according to the PH2 database, provided an accuracy of 0.923 and an F1-score of 0.876. The classification is interpretable if it is not validated. In our study, the best results were verified with a logistic regression (LR) classifier.

关键词： Accuracy Recurrent neural networks Image color analysis Melanoma Biological systems Artificial neural networks Feature extraction Skin Lesions Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Impulsive Consensus of Two-timescale Multi-agent Systems

Asynchronous Impulsive Consensus of Two-timescale Multi-agen...

引用

Asian control Conference

作者： Yuanyuan Huang Kun Liang Haoxuan Yan Mengshen Chen School of Automation Shanghai University of Electric Power Shanghai Shanghai China Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

This paper investigates the consensus problem of multi-agent systems (MASs) with two-timescales characteristics, which is coped with the singular perturbation technique. The distributed impulsive controller is proposed, where the impulse instants are asynchronous among the agents. A method of average impulsive interval is introduced to regulate the frequency of impulses. By utilizing the singular perturbation parameter-dependent Lyapunov function, some sufficient conditions are obtained to synchronize a two-timescale MAS. Finally, the numerical simulation is verified to confirm the effectiveness of the proposed method.

关键词： Sufficient conditions Perturbation methods Numerical simulation Synchronization Multi-agent systems Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Plate Shape Prediction Based on Data-Driven in Roll Quenching Process

Plate Shape Prediction Based on Data-Driven in Roll Quenchin...

引用

2023 China automation Congress, CAC 2023

作者： Hu, Liu Chen, Luefeng Hu, Jie Wu, Min Pedrycz, Witold Hirota, Kaoru School of Automation Ministry of Education China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2G7 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University The Department of Computer Engineering Istanbul Sariyer34396 Turkey Tokyo Institute of Technology Tokyo Yokohama226-8502 Japan

ISBN: (纸本)9798350303759

In the process of steel plate production, predicting the plate shape is of great significance for producing high-quality and consistently stable plate shapes. This paper presents a model that predicts both the defect types and flatness of the plate, providing theoretical support for setting process parameters in roller quenching production. First, the parameters of the quenching process are analyzed to identify their characteristics. Then, the K-Means clustering algorithm and correlation analysis are employed to process the quenching process parameters. A gradient boosting decision tree (GBDT) model is used to predict the defect types and flatness of the steel plates. Finally, industrial production data is utilized for experimental validation. The obtained experimental results verify the reliability of the proposed method. © 2023 IEEE.

关键词： Decision trees

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：