检索结果-内蒙古大学图书馆

13th International Conference on Computer Vision Systems, ICVS 2021

作者： Patten, Timothy Alempijevic, Alen Fitch, Robert Robotics Institute Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia Automation and Control Institute Faculty of Electrical Engineering and Information Technology TU Wien Vienna1040 Austria

ISBN: (纸本)9783030871550

This paper addresses the problem of detecting natural contaminants in freshly shorn wool fleece in RGB images using deep learning-based semantic segmentation. The challenge of inconsistent annotation is overcome by learning the probability of contamination as opposed to a discrete class. From the continuous value predictions, contaminated regions can be extracted by selectively thresholding on the probability of contamination. Furthermore, the imbalance of the class distributions is accounted for by adaptively weighting each pixel’s contribution to the loss function. Results show that the adaptive weight improves the prediction accuracy and overall outperforms learning an approximated representation by quantising the distributions. © 2021, Springer Nature Switzerland AG.

关键词： Wool

来源：评论

学校读者我要写书评

暂无评论

Individual pitch controller with static inverted decoupling for periodic blade load reduction on monopile offshore wind turbines

引用

Ocean engineering 2025年 334卷

作者： Lara, Manuel Ruz, Mario L. Mulders, Sebastiaan Paul Vázquez, Francisco Garrido, Juan Department of Electrical Engineering and Automation University of Cordoba Campus of Rabanales Cordoba14071 Spain Department of Mechanics University of Cordoba Campus of Rabanales Cordoba14071 Spain Delft Center for Systems and Control Faculty of Mechanical Engineering Delft University of Technology Mekelweg 2 Delft2628 CD Netherlands

Individual pitch control (IPC) is a technique used to reduce periodic blade loads in wind turbines. It generally uses the multiblade coordinate transformation to convert blade load measurements from a rotating frame into a two-axes non-rotating frame. Although these non-rotating axes are assumed to be decoupled, studies reveal persistent interactions. Reducing this coupling, such as by introducing an azimuth offset, enhances IPC performance. This study explores the impact of static inverted decoupling, which decouples the process in the steady state, on IPC performance. The proposed IPCs are adaptive, scheduling controller and decoupling gains based on operational conditions. In such IPC designs, the integral gains of the diagonal controllers and the decoupling elements can either be the same or different. These methods were validated on a simulated 15 MW wind turbine. controller parameter optimization was accomplished through genetic algorithms to minimize blade fatigue loads, measured via the damage equivalent load (DEL). Results indicate that incorporating static inverted decoupling into IPC improves blade load reduction without increasing pitch actuator effort. IPCs with similar integral gains and matching absolute values in decoupling elements achieved the best balance between DEL reduction and complexity with minimal actuator effort, while additional optimization parameters provided negligible improvements. © 2025 Elsevier Ltd

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Pain Level Assessment in Post-Surgery Patients Using Artificial Intelligence Algorithms

Enhancing Pain Level Assessment in Post-Surgery Patients Usi...

引用

European control Conference (ECC)

作者： G. Ben Othman E. Yumuk D. Copot A. R. Ynineb H. Farbakhsh I. R. Birs C. I. Muresan R. De Keyser I. Chihi C. M. Ionescu M. Neckebroek Department of Electromechanics Systems and Metal Engineering Research Group on Dynamical Systems and Control Ghent University Gent Belgium Department of Control and Automation Engineering Istanbul Technical University Maslak Istanbul Turkey Department of Automation Technical University of Cluj-Napoca Cluj-Napoca Romania Department Of Engineering Faculty of Science Technology and Medicine University of Luxembourg Kirchberg Luxembourg Department of Anesthesia Ghent University Hospital Ghent Belgium

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

control performance decreases significantly in the presence of uncertainty in variable availability, measurement noise, or instrumentation failure. In cluttered environments such as the Post Anesthesia Care Unit (PACU), clinical measures are often influenced by noise and artifacts. An important component in post-operative treatment is the assessment and management of pain levels. However, reliable information is critical for clinically relevant results and improved patient outcomes. From a control engineering point of view, variables are often estimated and interpolated to allow a suitable flow of feedback information to control loops for the optimization of drug dosages. In this context, Artificial Intelligence (AI) stands as a promising tool to augment pain level assessment. This study introduces and compares two AI-based approaches for predicting continuous Numerical Rating Scales (NRS) based on heart rate (HR) data. The first approach uses polynomial regression, lasso regression, and ridge regression, while the second employs an LSTM model. Notably, the AI prediction model, independent of traditional interpolation techniques, outperforms the approach relying on interpolation. The proposed AI-based method holds promise for continuous estimation and can serve as an estimator for model-based control. This proof of concept study underscores the potential of AI tools to enhance pain level assessment.

关键词： Heart rate Interpolation Uncertainty Pain Noise Numerical models Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Speed Profile Optimization for Autonomous Electric Bus in Urban Area: Based on Service Route Parameter in Thailand

Speed Profile Optimization for Autonomous Electric Bus in Ur...

引用

Conference on Power, Energy and Innovations (ICPEI)

作者： Guntinan Sakulphaisan Sirirat Son-In Nitikorn Junhuathon Theerapol Muankhaw Industrial technology and innovation management Faculty of science and technology Pathumwan institute of technology Bangkok Thailand Electrical Engineering and Automation Control Systems Faculty of engineering and industrial technology Bansomdejchaopraya Rajabhat University Bangkok Thailand Department of Electrical Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathumthani Thailand

This study conducts a comprehensive analysis of optimizing the speed profile of an AE-bus, a critical step in enhancing its operational efficiency. It encompasses three distinct case studies, each targeting specific objectives. The first case emphasizes energy consumption reduction, contributing to overall resource efficiency. The second focuses on eco-conscious speed profiles within predefined travel durations, balancing environmental sustainability and timeliness. The third case prioritizes travel time minimization for streamlined efficiency. Detailed insights into speed adjustments, bus positions, and energy consumption patterns are provided for each case. The findings reveal tailored approaches for energy conservation, speed, and travel time optimization. Additionally, emissions analysis demonstrates that electric buses significantly reduce CO 2 emissions compared to conventional NGV buses, showcasing their potential for environmental benefits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online B-Spline Based Trajectory Planning for Swarm of Agents Using Distributed Model Predictive control

Online B-Spline Based Trajectory Planning for Swarm of Agent...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Cong Khanh Dinh Ionela Prodan Florin Stoican Univ. Grenoble Alpes Grenoble INP† LCIS Valence France The Faculty of Automation Control and Computer Science Institute of Engineering and Management Univ. Grenoble Alpes University Politehnica of Bucharest Romania

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

This paper deals with the motion planing in real-time for swarm of agents using distributed Model Predictive control (DMPC). Optimization-based control helps both to stabilize the motion dynamics of the robots and to enforce the system's constraints. However, the price is a significant increase in complexity as the scale of the system surges. To improve the scalability for a large formation, we propose a DMPC framework that considers B-spline parameterizations for the agents' trajectories. The proposed approach has great promise for multi-drones system, as illustrated with simulation examples using a state of the art quadcopter model.

关键词： Trajectory planning Scalability Prediction algorithms Real-time systems Trajectory Splines (mathematics) Surges

来源：评论

学校读者我要写书评

暂无评论

Analysis of Equilibrium Point and Genetic Algorithm Design of Observer-Based PID controller for Membrane Bioreactor

Analysis of Equilibrium Point and Genetic Algorithm Design o...

引用

2021 International Automatic control Conference, CACS 2021

作者： Changsila, Yanita Banjerdpongchai, David Intelligent Control Automation of Process Systems Research Unit Dept. of Electrical Engineering Faculty of Engineering Chulalongkorn University 254 Phayathai Road Pathumwan Bangkok10330 Thailand

ISBN: (纸本)9781665444125

The operation of most wastewater treatment systems is an open-loop system. There is limited feedback control of membrane bioreactors (MBR) which makes it impossible to regulate the quality of the treated water. The objectives of this paper are twofold. First, we analyze the equilibrium point of the MBR nonlinear model. Second, we utilize output feedback control with state observer and design optimal PID controllers. We determine the optimum equilibrium point and derive a linearized model of MBR. Then, we design the state observer to estimate the non-measurable state using the pole placement method. Both the measurable output and estimated state are fed back through PID controller. The objectives of PID control consist of stabilization and performance improvement. Genetic Algorithm is applied to find the optimal PID parameters that minimize the integral of absolute error and satisfy the specified time-domain criteria. We apply the observer-based PID controller to the linearized model of MBR. Numerical results demonstrate the design of PID controller and the improvement of the closed-loop response and quality of the treated water. © 2021 IEEE

关键词： Bioreactors

来源：评论

学校读者我要写书评

暂无评论

Remote Monitoring of Patient's Breathing Process in Complex Chronomagnetotherapy 10

Remote Monitoring of Patient's Breathing Process in Complex ...

引用

10th Mediterranean Conference on Embedded Computing, MECO 2021

作者： Gurzhin, Sergey G. Zhulev, Vladimir I. Kaplan, Michail B. Nguyen, Viet Linh Proshin, Evgeniy M. Shulyakov, Andrey V. Ryazan State Radio Engineering University Named after V.F. Utkin RSREU Faculty of Automation and Information Technologies in Control Ryazan Russia

ISBN: (纸本)9780738133614

The article considers remote monitoring system of patient's breathing process in complex chronomagnetotherapy. Hardware and software computer-based system implementation featuring contactless position sensitive detector, standard data acquisition module and original virtual devices that provide high level of automation and extensive functionality is shown. © 2021 IEEE.

关键词： Computer hardware

来源：评论

学校读者我要写书评

暂无评论

Towards Energy Efficient control for Commercial Heavy-Duty Mobile Cranes: Modeling Hydraulic Pressures using Machine Learning

arXiv

引用

arXiv 2023年

作者： Taheri, Abdolreza Pettersson, Robert Gustafsson, Pelle Pajarinen, Joni Ghabcheloo, Reza Control Systems R&D HIAB Hudiksvall Sweden Faculty of Engineering and Natural Sciences Tampere University Tampere Finland Department of Electrical Engineering and Automation Aalto University Espoo Finland

A sizable part of the fleet of heavy-duty machinery in the construction equipment industry uses the conventional valve-controlled load-sensing hydraulics. Rigorous climate actions towards reducing CO2 emissions has sparked the development of solutions to lower the energy consumption and increase the productivity of the machines. One promising solution to having a better balance between energy and performance is to build accurate models (digital twins) of the real systems using data together with recent advances in machine learning/model-based optimization to improve the control systems. With a particular focus on real-world machines with multiple flow-controlled actuators and shared variable-displacement pumps, this paper presents a generalized machine learning approach to modeling the working pressure of the actuators and the overall pump pressures. The procedures for deriving reaction forces and flow rates as important input variables to the surrogate models are described in detail. Using data from a real loader crane testbed, we demonstrate training and validation of individual models, and showcase the accuracy of pressure predictions in five different experiments under various utilizations and pressure levels. © 2023, CC BY.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Exchange Strategies for Multi-Colony Ant Algorithms in Dynamic Environments

Exchange Strategies for Multi-Colony Ant Algorithms in Dynam...

引用

Congress on Evolutionary Computation

作者： Michalis Mavrovouniotis Changhe Li Danial Yazdani Diofantos Handjimitsis ERATOSTHENES Centre of Excellence Limassol Cyprus Department of Civil Engineering and Geomatics Cyprus University of Technology Limassol Cyprus Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Wuhan China Faculty of Engineering & Information Technology University of Technology Sydney Sydney Australia

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

In dynamic optimization problems where optimal solutions change over time, traditional ant colony optimization (ACO) algorithms face limitations. This study explores the adaptation of multi-colony ACO algorithms, known for their enhanced search capabilities in stationary problems, to tackle optimization problems in dynamic environments. Various strategies for exchanging information between colonies, which is a critical factor influencing algorithm performance, are investigated. Using the dynamic traveling salesman problem as a foundation, we generate test cases to reflect real-world complexities. Our results on a set of problem instances reveal that the choice of communication strategy between colonies significantly impacts the adaptability and efficiency of multi-colony ACO algorithms in tracking moving optimum.

关键词： Schedules Satellites Processor scheduling Heuristic algorithms Evolutionary computation Traveling salesman problems Search problems

来源：评论

学校读者我要写书评

暂无评论

A dynamic event-triggered transmission strategy for distributed convex optimization

A dynamic event-triggered transmission strategy for distribu...

引用

第42届中国控制会议

作者： Pengfei Liu Kun-Zhi Liu Dianfeng Zhang Shengli Du Academy of Control Science and Engineering Dalian University of Technology School of Mathematics and Informational Science Yantai University College of Automation Faculty of Information TechnologyBeijing University of Technology

A dynamic event-triggered transmission strategy is considered for the continuous-time distributed convex optimization algorithm over a strongly connected and weight-balanced directed *** auxiliary variable is introduced in the dynamic event-triggered control(DETC) that is free of Zeno *** model the DETC system into a hybrid *** Lyapunov stability theory,we give a detailed proof for convergence of the continuous-time distributed convex optimization ***,a numerical simulation shows that the DETC can effectively save network communication resources compared with a static event-triggered control(SETC).

关键词：

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：