检索结果-内蒙古大学图书馆

engineering Research Express 2025年第2期7卷 025423-025423页

作者： Ma, Bao Ma, Jun Guo, Kai Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming University of Science and Technology Yunnan Kunming China

This study proposes an innovative diagnostic approach for coupling misalignment faults by integrating dynamic modeling with transfer learning. It tackles the challenge of limited fault samples in real-world diagnostic scenarios, a common obstacle to developing robust diagnostic models. A dynamic model of coupling misalignment is first established, generating diverse misalignment fault signals that are experimentally validated. Time- and frequency-domain features are then extracted from both simulated and experimental vibration signals. The Laplace Score (LS) method is utilized to select sensitive features, with simulated signal features serving as training samples and experimental signal features as testing samples. Transfer Component Analysis (TCA) is employed to reduce distributional differences between the two datasets. Subsequently, the Cuckoo Search (CS) algorithm optimizes a Support Vector Machine (SVM), yielding a robust model that effectively detects coupling misalignment faults. Experimental validation achieves 98.43% fault recognition accuracy, surpassing the baseline TCA-CS-SVM approach (90.31% without feature selection), thereby providing a novel solution for detecting coupling misalignment faults. © 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Lightweight CNN Models for Drone Collision Avoidance Dataset

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

引用

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

Designing of A Plastic Garbage Robot With Vision-Based Deep Learning Applications

Designing of A Plastic Garbage Robot With Vision-Based Deep ...

引用

2023 International Conference on System Science and engineering, ICSSE 2023

作者： Thanh, Le Tien Lam, Le Hoang Nguyen, Thanh Nha Tran, Duc Thien Ho Chi Minh City University of Technology and Education Automation Control Department Ho Chi Minh City70000 Viet Nam Ho Chi Minh City University of Technology and Education Faculty of Electrical and Electronics Engineering Ho Chi Minh City70000 Viet Nam

ISBN: (纸本)9798350322941

To address the issue of plastic waste, a robot using deep learning technology for visual recognition to classify plastic waste has been developed. This system includes a 3DOF robot arm, a conveyor, a camera, an electrical cabinet, and a computer. The object detection component of the system is designed using transfer learning with a pre-trained YOLOv5 model to ensure the system operates in real time. Selecting the best model by evaluating and comparing the results of models trained using labeling by bounding box and polygon methods. Then, the real-world coordinates for the origin of the robot arm are determined by utilizing matrices obtained from MATLAB through chessboard images. The computer processes the data and transmits commands to the robot arm system and conveyor, which is controlled by a PLC and 3 different Servo Drivers, for object sorting on the conveyor. The best-performing model has a Precision of 92.1% and a Recall of 87.3%, and the success rate of picking up an object is 91.5%. While the experimental results indicate complete stability in inter-device connectivity, implementing it would necessitate hardware improvements to leverage its potential. © 2023 IEEE.

关键词： Deep learning

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

Event-triggered learning of Euler-Lagrange systems: A Koopman operator framework

Event-triggered learning of Euler-Lagrange systems: A Koopma...

引用

IEEE Conference on Decision and control

作者： Kaikai Zheng Dawei Shi Shilei Li Yang Shi MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing Institute of Technology Beijing China Department of Mechanical Engineering Faculty of Engineering University of Victoria Victoria BC Canada

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Euler-Lagrange (EL) systems represent a crucial and large class of dynamical systems, and a precise model of the true system would be beneficial in planning and tracking problems. This work aims to learn an unknown EL system using noisy measurement data to achieve improved data utilization efficiency. Specifically, for the considered EL system, a linear representation of the system is constructed using the Koopman operator, which is further characterized by sample data using Willems’ fundamental lemma. Moreover, an event-triggered learning mechanism is proposed to improve data utilization efficiency, and it is designed based on the analysis of the learning error bounds. The effectiveness of the proposed event-triggered learning approach is validated through a manipulator example.

关键词： Learning systems Event detection Manipulators Safety Planning Noise measurement Dynamical systems

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

A Parallel and Asynchronous Blob Shape Descriptor Implemented in CMOS Technology 33

A Parallel and Asynchronous Blob Shape Descriptor Implemente...

引用

33rd IEEE International Conference on Microelectronics, MIEL 2023

作者： Bogacki, P. Dlugosz, M. Talaska, T. Dlugosz, R. Aptiv Services Poland Kraków30-399 Poland Agh University of Science and Technology Institute of Telecommunications Faculty of Computer Science Electronics and Telecommunications Kraków30-059 Poland Poznan University of Technology Faculty of Control Robotics and Electrical Engineering Institute of Automation and Robotics Division of Signal Processing and Electronic Systems Poznan60-965 Poland Bydgoszcz University of Science and Technology Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz85-796 Poland

ISBN: (纸本)9798350347760

The paper presents a family of novel light blob shape descriptors for use in selected active safety algorithms used in Advanced Driver Assistance Systems (ADAS). One of the motivations was to obtain a descriptor that would ensure low computational complexity. This makes it easy to implement both in software and hardware. One assumption is that the location of the center of a given light spot is approximately known. The principle of its operation is then to count white pixels in selected directions, starting from this central point. A key issue here is an efficient way of determining indexes of particular pixels belonging to the image patch, as well as the location of points representing places where the white area turns into black. In the case of a hardware implementation, this can be done using a parallel circuit operating in asynchronous mode, without the need for a control clock. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Towards Intelligent and Trustworthy Crowdsourcing Systems with Cyber-physical Social Intelligence via Retrieval-augmented Generation

Towards Intelligent and Trustworthy Crowdsourcing Systems wi...

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Yang, Jing Wang, Xingxia Ni, Qinghua Liu, Yuhang Wang, Jing Wang, Fei-Yue Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Macau University of Science and Technology Faculty of Innovation Engineering 999078 China Macau University of Science and Technology 999078 China Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing100190 China

ISBN: (纸本)9798350376739

In recent years, crowdsourcing systems that tackle complex tasks through the collective efforts of many individuals have garnered substantial attention. However, the existing crowd-sourcing systems face some challenges such as overreliance on human experience and effort, information overload, and risks of privacy breaches. To overcome these challenges, this paper proposes an intelligent and trustworthy crowdsourcing frame-work based on blockchain and retrieval-augmented generation. The framework centers around foundational models to integrate the three distinct and sequentially interdependent phases: task decomposition, task allocation or recommendation, and task execution, enabling the automatic provision of a personalized, comfortable, and efficient user experience. Blockchain and smart contracts are utilized to protect user privacy and interests without leaning on any third trusted authority. Additionally, the operational process of the framework is explained and validated by taking printed circuit board design and manufacturing as a case study and ChatGPT as its generator. © 2024 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Power Loss Analysis of Energy Management System with Model Predictive control in Mae Hong Son Microgrid

Power Loss Analysis of Energy Management System with Model P...

引用

IEEE International Conference on Power Electronics, Intelligent control and Energy Systems (ICPEICES)

作者： Nattakit Prapanwattana Donlapat Dechawatanapaisal David Banjerdpongchai Abhishek Rajan Dept. of Electrical Engineering Faculty of Engineering Center of Excellence in Intelligent Control Automation for Process Systems Chulalongkorn University Bangkok Thailand Dept. of Electrical Engineering National Institute of Technology Sikkim South Sikkim India

ISBN: (数字)9798350387193

ISBN: (纸本)9798350387209

Energy management system (EMS) is an important tool for energy efficiency and reliability of the power system. The optimal power dispatch of energy resources can be obtained using the nonlinear model predictive control (NMPC). It is formulated as an optimization problem subject to linear and nonlinear constraints. Although the existing system works well under the current conditions, power loss has not been considered. Power loss in transmission lines occurs due to their resistance and a high amount of power flow to loads connecting to the system. The power loss leads to decreased efficiency in the electrical system and reduces the lifespan of equipment because of the high temperature from loss. This paper aims to analyze the power loss in the Mae Hong Son (MHS) microgrid. To achieve the research objectives, we employ the EMS of MHS with NMPC and calculate power loss in transmission lines for a period of 7 days. EMS considers three objective functions, namely, total operating cost, total carbon dioxide emission, and combined economic and emission dispatch and take into account of three seasons consisting of rainy, winter, and summer.

关键词： Resistance Power transmission lines Microgrids Propagation losses Power system reliability Reliability Energy management systems Power generation Load flow Predictive control

来源：评论

学校读者我要写书评

暂无评论

Comparison Performance on SOTA Deep Learning Models for Coffee Beans Grading Inspection

Comparison Performance on SOTA Deep Learning Models for Coff...

引用

Asian control Conference

作者： Achmad Norman Firdaus Amalia Rakhmawati Vebi Nadhira Suprijanto Endang Juliastuti Gema Nuran Utomo Ayu Gareta Risangtuni Master Program on Instrumentation and Control Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia Graduate Program on Engineering Physics Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia Instrumentation Control and Automation Research Group Faculty of Industrial Technology Bandung Institute of Technology Bandung Indonesia

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Several coffee producers rely on manual inspection for quality control, which is prone to inconsistencies and time consumption. Recent studies have proposed Comparison performance on State-of-The-Art (SOTA). Deep learning models were investigated as part of the proposed intelligent computer vision for faster and more reliable coffee bean grading. Performance Deep learning models, i.e., MobileNetV3Small, ResNet50, EfficientNetV2L, and DenseNet201, were evaluated to grade the quality of coffee beans that followed a grading procedure based on Indonesian National Standard (SNI) 01-2907-2008. A specific tray was designed to position coffee beans evenly without overlap for sample preparation, which consist of about 500–600 coffee beans. The process of capturing images is conducted systematically, focusing on each type of coffee bean defect individually. For comparison of SOTA models, five classes of coffee bean defects, With 1053 beans per class, the total dataset comprises 5265 beans. This dataset was divided into 10% for testing and 90% for training. Within the training data, 12% was reserved for validation. The result from this paper shows that MobileNetV3Small achieves the highest accuracy (99.43%) with minimal memory and parameters. Its efficient design allows for robust feature extraction, crucial for distinguishing subtle defect features. While larger models like ResNet50 and EfficientNetV2L also perform well, they exhibit higher memory and parameters.

关键词： Deep learning Training Accuracy Computational modeling Training data Inspection Feature extraction

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：