检索结果-内蒙古大学图书馆

Developments in smart wall-climbing robots for corrosion inspection through IoT integration, deep learning and advanced control strategies

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Acar, Özgür Yaşar, Claudia Fernanda Department of Control and Automation Engineering Yildiz Technical University Davutpaşa Campus Esenler Istanbul34320 Turkey

This study provides insights into a smart and autonomous robotic design with a Node-RED as a low code and Internet of Things architecture, advancing the wall-climbing robot design and construction field. The robot makes use of a special palletized mechanism that adheres magnetically. This includes an anti-slip design and powerful magnetic forces that enable the robot to be attached to the wall. It is overcoming locomotion challenges such as magnetic adhesion, slippery issues, gravity forces, and Coulomb friction. The work focuses on manufacturing a robot equipped with essential hardware and software, actuators, and sensors, enabling reliable control algorithms for locomotion and inspection. The robot can interact in resource-intensive and hazardous environments thanks to the Internet of Things, which also enhances the system's visualization and monitoring functions. A visual corrosion diagnostic display and deep learning-based corrosion inspection algorithms training and testing enhance visual inspection. This work validates a control strategy against high gravitational, magnetic, and Coulomb friction forces. A robot based on differential driving with direct current motors is built. Its features include autonomous trajectory tracking on vertical surfaces in the presence of high disturbances and the capacity to produce references and adjust positioning utilizing a fusion of sensors and a Kalman filter to enhance autonomous driving while minimizing noise. This study provides insights into a smart and autonomous robotic design with a Node-RED as a low code and Internet of Things architecture, advancing the wall-climbing robot design and construction field. The robot makes use of a special palletized mechanism that adheres magnetically. This includes an anti-slip design and powerful magnetic forces that enable the robot to be attached to the wall. It is overcoming locomotion challenges such as magnetic adhesion, slippery issues, gravity forces, and Coulomb friction. The

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Robust controller Design for Longitudinal and Lateral Model of High-Performance Fixed-Wing UAVs 11

Robust Controller Design for Longitudinal and Lateral Model ...

引用

11th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Isci, Burak Ucun, Levent Yildiz Technical University Department of Control and Automation Engineering Istanbul Turkey

ISBN: (纸本)9798350362541

This study focuses on designing and analyzing H∞ and H2 control algorithms for fixed-wing unmanned aerial vehicles (UAVs) with reference tracking control objective under disturbances. Two different robust control strategies, developed based on the linearized UAV mathematical model, are implemented in the inner loop defined as the angular velocity control loop in the nonlinear mathematical model to enhance the performance of attitude angular velocity by improving the robustness against disturbances. This papaer also includes disturbance effects on UAVs such as gust model and time-dependent change of the centre of gravity model. The results of the two different control algorithms are compared and presented in terms of time-domain specifications. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Size Matters: Exploring the Impact of Scaling on Quadruped Robot Dynamics 25th

Size Matters: Exploring the Impact of Scaling on Quadruped R...

引用

25th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2024

作者： Rahvar, Faraz Yilmaz, Abdurrahman Department of Mechatronics Engineering Istanbul Technical University Istanbul Turkey Department of Control and Automation Engineering Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9783031720611

Quadruped robots are indispensable for specialized tasks, particularly in disaster scenarios like earthquakes, where their mobility surpasses that of fixed robots. However, altering their dimensions significantly impacts their mechanical requirements and control systems. This study investigates and compares the principal mechanical parameters affecting the control systems of quadruped robots during scaling, aiming to understand how scalability influences their design across different sizes. Using a standard quasi-direct driven commercial quadruped robot1(Unitree A 1) model featuring dual coaxial motor design and serial link architecture actuators, simulations are conducted at four different sizes, each expanding the robot size by 30%. These simulations analyze static and dynamic forces as the robot walks on a flat surface at a constant speed. To fortify our findings, simulations employ three trajectory scenarios, in each scenario, four robots are scaled in length, increasing by a coefficient of 0.3 from robot 1 to robot 4. The first and second scenarios feature different trajectory lengths, while the third scenario increases the trajectory height while maintaining the length of the second scenario. Specifically, we examine the required torque, energy consumption of the robot motors, reaction forces between the robot feet and terrain, and the mechanical cost of transport. These outcomes encompass critical components of the robot from a mechanical analysis perspective, including joints, providing valuable references for various actuator architecture designs. Our findings reveal a logical pattern in the increase of torques, power consumptions, and reaction forces as the robot scales. These insights lay the groundwork for developing a scalable control architecture for legged robots. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Extended Kalman Filter Based Nonlinear Probabilistic Model Predictive control of an Autonomous Motorcycle 11

Extended Kalman Filter Based Nonlinear Probabilistic Model P...

引用

11th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Çerçi, Nurettin Yalçin, Yaprak Istanbul Technical University Mechatronics Engineering Department Istanbul Turkey Istanbul Technical University Control and Automation Engineering Department Istanbul Turkey

ISBN: (纸本)9798350362541

This work focuses on the control of a nonlinear autonomous motorcycle model using Probabilistic Model Predictive control (MPC). The main purpose of this work is to control the speed, yaw angle and roll angle of the motorcycle while keeping its balance during a maneuver. The Probabilistic MPC takes into account the probabilistic disturbances acting on the control inputs or the state variables. The cost function of the optimization of this proposed nonlinear probabilistic MPC is different than the cost of traditional deterministic MPC, such that, it contains terms that represent the mean of the state variable which is calculated with the help of an Extended Kalman Filter (EKF) and also the terms as the functions of covariances of the state variables and control inputs. The optimization algorithm is fed with these mean and covariance values every time instant, then the controller calculates the optimal control sequence to apply it to the system model. The speed of the motorcycle, the yaw angle and, the roll angle of the motorcycle are controlled with good efficiency. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Proton Exchange Membrane Fuel Cell Thermal System Modeling and control 10

Proton Exchange Membrane Fuel Cell Thermal System Modeling a...

引用

10th International Conference on Electrical and Electronics engineering, ICEEE 2023

作者： Özdemir, Tuna Han Yasar, Claudia Fernanda Yildiz Technical University Avl Research and Engineering Department of Control and Automation Engineering Istanbul Turkey Yildiz Technical University Department of Control and Automation Engineering Istanbul Turkey

ISBN: (纸本)9798350304299

The urgent issue of global warming and its adverse effects, including wildfires, water scarcity, and the spread of diseases, calls for concerted efforts to mitigate emissions and curb climate change. Among the effective strategies is the reduction of carbon emissions, for which hydrogen-powered proton exchange membrane fuel cell systems are vital. These systems generate electricity through chemical reactions involving hydrogen, with only water and heat as byproducts, hence their environmentally friendly nature. Fuel cell efficiency is higher than conventional systems depending on the type and the operating temperature. Proper thermal control is essential for maintaining high efficiency. This research paper aims to examine standard models of proton exchange membrane fuel cell thermal systems and suggest an efficient control approach. The system dynamics are derived from fundamental models, and an adaptive PID controller is simulated with MATLAB/Simulink. The paper also presents a comparative analysis between traditional PID control and adaptive PID, an advanced control technique. © 2023 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming vs Q-learning for Feedback Motion Planning of Manipulators 5

Dynamic Programming vs Q-learning for Feedback Motion Planni...

引用

5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023

作者： Yildiran, Ugur Yildiz Technical University Control and Automation Engineering Department İstanbul Turkey

ISBN: (纸本)9798350337525

Reinforcement Learning (RL) based methods have became popular for control and motion planning of robots, recently. Unlike sampling based motion planners, optimal policies computed by them provide feedback motion plans which eliminates the need for re-computing (optimal) trajectories when a robot starts from a different initial configuration each time. In related studies, an optimal policy (actor) and the associated value function (critic) are usually calculated preforming training in a simulation environment. During training, RL allows learning by interactions with the environment in a physically realistic manner. However, in a simulation system, it is possible to make physically unimplementable moves. Thus, instead of RL, one can make use of Dynamic Programming approaches such as Value Iteration for computing optimal policies, which does not require an exploration component and known to have better convergence properties. In addition, dimension of a value function is smaller than that of a Q-fuction, thereby lessening the severity of the curse of dimensionality. Motivated by these facts, the aim of this paper is to employ Value Iteration algorithm for motion planning of robot manipulators and elaborate its effectiveness compared to a popular RL method, Q-learning. © 2023 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Local Planner Algorithms for a ROS-based Omnidirectional Mobile Robot 8

A Comparison of Local Planner Algorithms for a ROS-based Omn...

引用

8th International Conference on Robotics and automation engineering, ICRAE 2023

作者： Imamoglu, Mehmed Rafi Sumer, Ecem Temeltas, Hakan Istanbul Technical University Department of Control and Automation Engineering Istanbul Turkey

ISBN: (纸本)9798350327656

The topic of local planner algorithms applicable to omnidirectional mobile robots is yet to thoroughly investigated. This study investigates the performance of the most commonly implemented local planner algorithms for omnidirectional mobile robots by conducting a comparative analysis between the Dynamic Window Approach (DWA) and the Timed Elastic Band (TEB) algorithms. The evaluation was conducted within real-world settings, specifically targeting the challenges of parking maneuvers, dynamic obstacle avoidance and turning maneuvers. Performance metrics, tailored to each scenario, were employed to assess the algorithms. The results demonstrate that the TEB method outperforms the DWA in the tested conditions. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Generating High-Quality Prediction Intervals for Regression Tasks via Fuzzy C-Means Clustering-Based Conformal Prediction

Generating High-Quality Prediction Intervals for Regression...

引用

Intelligent and Fuzzy Systems - Intelligence and Sustainable Future Proceedings of the INFUS 2023 Conference

作者： Msaddi, Saleh Kumbasar, Tufan Control and Automation Engineering Department Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9783031397769

Accurately assessing uncertainty and prediction of a regression model is essential for making informed decisions, especially in high-risk tasks. Conformal Prediction (CP) is a powerful distribution-free uncertainty quantification framework for building such models as it is capable to transform a single-point prediction of any machine learning model into a Prediction Interval (PI) with a guarantee of encompassing the true value for specified levels of confidence. On the other hand, to generate high-quality PIs, the PIs should be as narrow as possible while enveloping a certain amount of uncertainty (i.e. confidence level). The generated width of the PIs mainly depends on the nonconformity measure used within the CP. In this study, we propose two novel Fuzzy c-Means Clustering (FCM) based nonconformity measures for CP with nearest neighbors to learn distribution-free and high-quality PIs for regression. The proposed approach generates tight PIs by evaluating the degree of nonconformity of a new data point compared to the so-called calibration points via Fuzzy Sets (FSs). From the calibration dataset, we extract representative FSs via FCM and assign every test point alongside the nearest neighbors within the calibration dataset with membership grades to adapt the nonconformity measure. To evaluate the performance, we present statistical comparisons and demonstrate that the proposed FCM-based nonconformity measures result in high-quality PIs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Empowering Lab Education: Integrating a Vision-Based Monitoring System with Small-Scale Self-Driving Experiment Platforms

Empowering Lab Education: Integrating a Vision-Based Monitor...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Ren, Junru Fisker-Bodker, Nis Guldenring, Ronja Chang, Jin Hyun Vegge, Tejs Ravn, Ole Nalpantidis, Lazaros Technical University of Denmark Automation and Control Group Department of Electrical and Photonics Engineering Denmark Technical University of Denmark Department of Energy Conversion and Storage Denmark

ISBN: (纸本)9798331531614

The rise of self-driving laboratories has seen significant growth across various research domains, particularly in chemistry, materials science and life science. However, a major challenge persists - the majority of self-driving systems are costly due to the use of highly precise lab equipment, robotic platforms, and case-specific algorithms, rendering these systems less accessible for educational purposes. This paper takes a multidisciplinary approach;we first introduce a small-scale self-driving experiment platform tailored for educational use, focusing on liquid materials mixing tasks commonly seen in chemistry and life sciences. To understand the operational status in real-time while maintaining self-driving capability and efficiency, we propose a novel system concept: employing a mobile robot as the lab supervisor to monitor the experiment process across multiple identical self-driving platforms. Specifically, this paper focuses on implementing a vision-based monitoring system. A deep learning architecture with a new training strategy is presented to jointly address two tasks: (a) vessel and content material segmentation and (b) volume estimation. The two tasks can be trained independently but can be inferred end-to-end by integrating them into the Mask R-CNN framework. Through evaluating the monitoring module on a real dataset, the results showcase promising detection capabilities, good real-time performance, and compatibility with the self-driving platform, indicating the feasibility of our proposed system. © 2025 IEEE.

关键词： Crystalline materials

来源：评论

学校读者我要写书评

暂无评论

Switching Multi-regulator control of Electro-Hydraulic Servo System

Switching Multi-regulator Control of Electro-Hydraulic Servo...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Mihalev, Georgi Yordanov, Stanimir Ormandzhiev, Krasimir Technical University of Gabrovo Information and Control Systems Department of Automation Gabrovo Bulgaria Technical University of Gabrovo Department of Power Engineering Gabrovo Bulgaria

ISBN: (纸本)9798350353907

The paper proposes a switching multi-regulator control for an electro-hydraulic servo system with throttle regulation. The architecture of the multi-regulator control, composed of three conventional regulators (PID1, PI2, PI3) for different regions of the setpoint signal variation and switching logic, is discussed. The main issues arising from the use of such control are considered, and an analysis of the stability of the closed-loop system is conducted. Some mathematical formulas and descriptions are presented. Using a universal measurement and control module, graphical results for the quality of the designed control are obtained. The advantages of this type of control and the emergence of additional robust qualities of the system are experimentally proven. © 2024 IEEE.

关键词： Hydraulic servomechanisms

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：