检索结果-内蒙古大学图书馆

Performance Comparison of Lightweight CNN Models for Drone Collision Avoidance Dataset

Performance Comparison of Lightweight CNN Models for Drone C...

International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Rifqi Nabila Zufar David Banjerdpongchai Department of Electrical Engineering Faculty of Engineering Center of Excellence in Intelligent Control Automation of Process Systems Chulalongkorn University254 Phayathai Road Pathumwan Bangkok Thailand

Collision Avoidance System (CAS) is important for drone safety. CAS consists of three steps e.g., obstacle sensing, collision prediction, and collision avoidance. Collision prediction enables drones to gain information, process information, and estimate whether the object has a risk of collision. Convolution Neural Network (CNN) is one of the methods that can be employed for collision prediction. However, CNN is a method that needs a large data in the training. Dario Pedro et al. provided a dataset called the CoLANet dataset that consists of VDOs of collision drones. Subsequently, they proposed a new algorithm called Neural Network Pipeline which has a Convolution Neural Network (CNN) part to extract the feature from a couple of images. CNN extracts images by using MobileNetV2 as a pre-trained model. They chose MobileNetV2 due to training performance from another dataset. This paper aims to assess the performance of lightweight CNN models using the CoLANet dataset. The models will be trained on the Keras library with parameters of fewer than ten million. The models will be validated by Confusion Matrix and Receiver Operating Characteristics. In conclusion, we examine which pre-trained CNN model has the best performance and suggest ongoing work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Time-Delay System Optimization with Auto-Configured Metaheuristics

Efficient Time-Delay System Optimization with Auto-Configure...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Senkerik, Roman Byrski, Aleksander Guzowski, Hubert Janku, Peter Kadavy, Tomas Oplatkova, Zuzana Kominkova Matusu, Radek Pluhacek, Michal Pekar, Libor Smolka, MacIej Viktorin, Adam Tomas Bata University A.I. Lab Faculty of Applied Informatics Department of Informatics and Artificial Intelligence Zlin Czech Republic Tomas Bata University Faculty of Applied Informatics Department of Automation and Control Engineering Zlin Czech Republic Institute of Computer Science Agh University of Science and Technology Krakow Poland

ISBN: (纸本)9798350337020

This paper presents an experimental study that compares the performance of four selected metaheuristic algorithms for optimizing a time delay system model. Time delay system models are complex and challenging to optimize due to their inherent characteristics, such as non-linearity, multi-modality, and constraints. The study includes an explanation of the choice and core functionality of the selected algorithms, which are both baseline and state-of-the-art variants of self-organizing migrating algorithm (SOMA), state-of-the-art variant from the Success-History-based Adaptive Differential Evolution family of algorithms, with emphasis on diverse search (DISH algorithm), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm. The hyperparameters of the metaheuristic algorithms were set using the iRace automatic algorithm configuration framework. The paper emphasizes the importance of metaheuristic algorithms in control engineering for time-delay systems to develop more effective and efficient control strategies and precise model identifications. The experimental results highlight the effectiveness of the state-of-the-art algorithms with specific adaptive mechanisms like population organization process, diverse search and adaptation mechanisms ensuring a gradual transition from exploration to exploitation. Overall, this study contributes to understanding the challenges and advantages of using metaheuristic algorithms in control engineering for time delay systems. The results provide valuable insights into the performance of modern metaheuristic algorithms and can help guide the selection of appropriate adaptive mechanisms of metaheuristics. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding

arXiv

引用

arXiv 2025年

作者： Lin, Fei Tian, Yonglin Zhang, Tengchao Huang, Jun Guan, Sangtian Wang, Fei-Yue Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology 999078 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Unmanned Aerial Vehicles (UAVs) are increasingly important in dynamic environments such as logistics transportation and disaster response. However, current tasks often rely on human operators to monitor aerial videos and make operational decisions. This mode of human-machine collaboration suffers from significant limitations in efficiency and adaptability. In this paper, we present AirVista-II—an end-to-end agentic system for embodied UAVs, designed to enable general-purpose semantic understanding and reasoning in dynamic scenes. The system integrates agent-based task identification and scheduling, multimodal perception mechanisms, and differentiated keyframe extraction strategies tailored for various temporal scenarios, enabling the efficient capture of critical scene information. Experimental results demonstrate that the proposed system achieves high-quality semantic understanding across diverse UAV-based dynamic scenarios under a zero-shot setting. Copyright © 2025, The Authors. All rights reserved.

关键词： Drones

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

Investigation of a Simulated Robot Model when it is Trained to Set Trajectories in the Task of controlling Assembly Parameters at Remote Visualization

Investigation of a Simulated Robot Model when it is Trained ...

引用

2022 International Russian automation Conference, RusAutoCon 2022

作者： Malkarov, A.Yu. Arkhipov, M.V. Kocherevskaya, L.B. Moscow Polytechnic University Faculty of Mechanical Engineering Department of Automation and Control Moscow Russia Moscow Aviation Institute National Research University Foreign Language Department for Aerospase Specialities Moscow Russia

ISBN: (数字)9781665466554

ISBN: (纸本)9781665466554

The science of robotics is becoming more and more relevant for industrial production. Visualization of the production system involves the exact modeling of its components as accurately as possible. For a robotic technological complex, such a main component is an industrial robot. The robot model should most accurately reflect what is happening in real production, since the robot is the basis of robotic production. Modeling allows you to perform a comprehensive analysis of the production system without direct design and start-up and, if possible, easily redesign it. An application was developed for building a virtual model of the robot and the workspace. An analysis of the behavior of the manipulator makes it possible to consistently improve the accuracy of modeling and the efficiency of designing a robotic technological complex. © 2022 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Context-Aware control for Quality Improvement in Liquid Steel Manufacturing

Context-Aware Control for Quality Improvement in Liquid Stee...

引用

2023 IEEE Conference on control Technology and Applications, CCTA 2023

作者： Birs, Isabela R. Muresan, Cristina I. Susca, Mircea Mihaly, Vlad Mihai Ghita, Mihaela Ghita, Maria De Keyser, Robin Ionescu, Clara Eedt Decision & Control Flanders Make Consortium Tech Lane Science Park 125 and 131 GhentB-9052 Belgium Ghent University Research Group of Dynamical Systems and Control Faculty of Engineering and Architecture Belgium Technical University of Cluj Napoca Department of Automation Memorandumului nr 28 Cluj-Napoca400114 Romania

ISBN: (纸本)9798350335446

This paper presents an original theoretical and implementation framework of fractional order event-based control with the purpose of quality improvement at the end production line of a continuous casting process. A real-life steel manufacturing plant is taken into consideration in the study. A prior fractional order model is considered to tune a fractional order Proportional Integral controller that ensures an ideal flow velocity of liquid steel. A novel event-based fractional order methodology is proposed that uses internal and external process events in order to improve quality. The implementation strategy takes into consideration available software and hardware components at the plant site, offering a realistic and implementable solution, highly suitable for the current steel industry setting. Numeric simulations successfully validate the proposed methodology. © 2023 IEEE.

关键词： Steelmaking

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach For Faults Recognition of Dissolved Oxygen Sensor in Wastewater Treatment Plants

A Deep Learning Approach For Faults Recognition of Dissolved...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Liliana Maria Ghinea Mihaela Miron Harsha Ratnaweera Department of Automatic Control and Electrical Engineering Department Faculty of Automation Computers Electrical Engineering and Electronics Galați Romania Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Galați Romania Faculty of Science and Technology Norwegian University of Life Sciences Oslo Norway

Fault diagnosis in wastewater treatment plants (WWTPs) is important to protect communities and ecosystems from toxic elements discharged into water. In this sense, fault identification of sensors plays an important role as they are the key components of the water plants control, especially because environmental legislation is very strict when referring to failures or anomalies in WWTPs. This paper analyzes the performances of two Deep Learning models, a Feedforward Neural Network (FFNN) and a 1D Convolution Neural Network (1DCNN) for identifying five operating states of the dissolved oxygen (DO) sensor: normal and faulty (bias, stuck, spike and precision degradation faults). The experiments were conducted on the Benchmark Simulator Model No 2 (BSM2) developed by the IWA Task Group. The performance of the Deep Learning (DL) classifiers was evaluated via accuracy, precision, recall, and F1-score metrics. The best overall classification accuracy was obtained by FFNN, 98.32% for training and 98.30% for testing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Fault-Tolerant control of Wave Equation Without Estimations of Plant and Failure Parameters

引用

IFAC-PapersOnLine 2022年第26期55卷 143-148页

作者： Zhiji Han Zhijie Liu Thomas Meurer Wei He School of Intelligence Science and Technology and Institute of Artificial Intelligence University of Science and Technology Beijing Beijing 100083 China Chair of Automation and Control Faculty of Engineering Kiel University 24143 Kiel Germany

This paper describes a novel robust fault-tolerant control for a vibrating string (captured by a wave partial differential equation) with constraint to be clamped at the left end and free at the right one. The control input is a force at the right hand, which might be affected by an actuator failure modelled by a general multiplicative type with unknown values. Except for the actuator failure, some physical parameters of the plant are also unavailable. We propose a pure output feedback control law without any estimation terms to guarantee the prescribed performance constraint of the state on the boundary of the closed-loop system and the uniform boundedness of the state in the whole domain. By applying the backstepping technique to the boundary of the system, together with a barrier Lyapunov function, we develop a non-adaptive control method capable of dealing with the underlying problem. Effective control performance in the wave equation with the designed control strategy is verified via Lyapunov analysis and numerical simulation.

关键词： Wave equation Boundary control Fault-tolerant control Prescribed performance constraint Non-adaptive method

来源：评论

学校读者我要写书评

暂无评论

Heat transfer of copper mesh-powder composite-based sintered-wick vapor chamber

Heat transfer of copper mesh-powder composite-based sintered...

引用

作者： Zhao, Zhengang Li, Lei Wang, Yuyuan Wang, Yaxin Hui, Yueyao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Green Energy Electric Power Measurement Digitalization Control and Protection Kunming650500 China Yunnan Institute of Measuring and Testing Technology Kunming650228 China

With the rapid spread of high-power density equipment, the vapor chamber must adapt to more applicable environments and exhibit a better heat transfer performance. The copper mesh and powder are sintered in this work to make a composite wick vapor chamber (CW-VC). Six sections of copper wire are cut and sintered together with the wick as the inner support column of the CW-VC. The effects of filling ratio and inclination on the heat transfer performance of the vapor chamber are investigated. The experimental results showed that the maximum thermal power of the CW-VC is 23.29 W at the optimal liquid filling ratio of 80% and the lowest thermal resistance is 0.33 °C/W. Below the liquid filling ratio of 60%, when the inclination angle of the CW-VC increases, its thermal resistance increases. At filling ratios of 70%, 80%, and 90%, the inclination angle of 30° can reduce the thermal resistance of the CW-VC. It implies that the inclination angle of the CW-VC can be increased appropriately to reduce the thermal resistance when the filling ratio is high. However, when the liquid filling ratio is low, increasing the inclination angle of the CW-VC will make the liquid film of the evaporator thinner and dry out earlier and its thermal resistance will increase. © 2023 Author(s).

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Informer-LSTM-EWMA for Panax Notoginseng with Prediction of Early Intervention Time

Informer-LSTM-EWMA for Panax Notoginseng with Prediction of ...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Jiahui Ye Chunxi Yang Xiufeng Zhang Jin Zhang Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Panax notoginseng is one of economic crop with significant medicinal value in southwest China. However, traditional extensive fertilization and irrigation method usually damages the soil, making it difficult to achieve sustainable cultivation of Panax notoginseng. In order to assess the growth status of Panax notoginseng and take timely action, this paper proposed an Informer-LSTM-EWMA model to predict the growth trend of Panax notoginseng in cultivation fields. In the experimental greenhouse, we set up two experimental fields A and B to verify the feasibility of the proposed method. Firstly, wavelet denoising is utilized on the date collected by the sensor. Then, Informer and Long short-term Memory (LSTM) are used to train the denoised data to obtain data prediction. Further process the predicted data through Exponential Weighted Moving Average (EWMA) for trend prediction. Finally, the early intervention time is obtained by searching for the maximum value. The results indicate that the model can predict early intervention time and its predictive performance is far better than that of a single model.

关键词： Learning systems Economics Irrigation Noise reduction Crops Predictive models Soil

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：