检索结果-内蒙古大学图书馆

Deep reinforcement learning-based adaptive fuzzy control for electro-hydraulic servo system

Neural Computing and Applications 2025年 1-18页

作者： Khater, A. Aziz Fekry, Mohamed El-Bardini, Mohammad El-Nagar, Ahmad M. Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32852 Egypt

In this paper, a novel adaptive fuzzy controller based on deep reinforcement learning (DRL) is introduced for electro-hydraulic servo systems. The controller combines the strengths of fuzzy proportional–integral (PI) control and deep Q-learning network (DQLN) to achieve real-time adaptation and improve the control performance. The purpose of this paper is to address the challenges of controlling electro-hydraulic servo systems by developing an adaptive controller that can dynamically adjust its control parameters based on the system’s state. The traditional fuzzy PI controller is enhanced with DRL techniques to enable automatic adaptation and compensation for changing online conditions. The proposed adaptive controller utilizes a DQLN to dynamically adjust the scaling factors of the input/output membership functions. By using the DQLN algorithm, the controller learns from a variety of system data to determine the optimal control parameters. The update equation of the weights for the Q-network is derived using the Lyapunov stability (LS) theorem, which overcomes the limitations of gradient descent (GD) methods such as instability and local minima trapping. To evaluate the effectiveness of the proposed controller, it is practically implemented to regulate an electro-hydraulic servo system. The controller’s performance is compared against other existing controllers, and its enhancements are demonstrated through experimental evaluation. © The Author(s) 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Development of sliding mode control based on diagonal recurrent neural network for coupled tank system

引用

Neural Computing and Applications 2024年第25期36卷 15279-15293页

作者： El-Nagar, Ahmad M. Abdo, Mohamed I. Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menof32852 Egypt

This study presents the development of sliding mode control (SMC) using the diagonal recurrent neural network (DRNN) for nonlinear systems. Firstly, the SMC for linear systems is developed for nonlinear coupled tank system. Second, the DRNN is used to design the equivalent part of the SMC law, which is performed to approximate the dynamics of a controlled process. Third, the sliding surface for the switching control is developed using the DRNN. The DRNN parameters are tuned using Lyapunov function to achieve the controlled process stability. For the developed scheme, discontinuous signum function is used to compensate the chattering phenomenon. The developed scheme is applied for controlling the uncertain nonlinear coupled tank system. The simulation results indicate that the developed scheme can respond to the effects of system uncertainties compared to other existing schemes. © The Author(s) 2024.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Multi-agent Systems Using Deep Q-Networks Reinforcement Learning 25th

Path Planning for Multi-agent Systems Using Deep Q-Networks...

引用

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

作者： Alispahić, Ibrahim Tahirović, Adnan Faculty of Electrical Engineering Department of Automatic Control and Electronics Sarajevo Bosnia and Herzegovina

ISBN: (纸本)9783031720611

This work presents a comprehensive study of the application of multi-agent reinforcement learning (MARL) based on deep Q-networks (DQN), aiming to enhance the cooperation and coordination of multiple agents in complex environments. The core problem addressed is the multi-agent traveling salesman problem, i.e. the effective collaboration and target-reaching by multiple agents. This challenge is inherently present in a variety of applications, including inspection and maintenance tasks based on autonomous aerial robotic systems. The research delves into the intricacies of multi-agent systems, emphasizing the dynamic interaction between agents and the environment. Although the proposed algorithm is developed and trained in a planar space, its principles and methodologies are easily extendable to any operational environment. The proposed approach is capable of training on a number of different scenarios, using various numbers of agents and targets, regardless of their initial positions, making it highly adaptable to scenarios like aerial inspections, where the number of agents, the number of inspection sites and their locations are unknown a priori. Furthermore, the work outlines how the enhanced DQN algorithm can be tailored for scenarios with numerous autonomous agents and targets, ensuring efficient path planning and target acquisition in constrained and unstructured spaces. This work also provides a solid foundation for future research in integrating advanced reinforcement learning techniques into the design and operational strategies for solving tasks, which can be described by the multi-agent traveling salesman problem, including inspection and maintenance with an autonomous multi-agent system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

A deep learning LSTM-based approach for AMD classification using OCT images

引用

Neural Computing and Applications 2024年第31期36卷 19531-19547页

作者： Hamid, Laila Elnokrashy, Amgad Abdelhay, Ehab H. Abdelsalam, Mohamed M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Mansoura Ophthalmic Center Faculty of Medicine Mansoura University Mansoura Egypt Electronics and Communications Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Faculty of Engineering Mansoura National University Mansoura Egypt

Age-related macular degeneration (AMD) is an age-related, persistent, painless eye disease that impairs central vision. The central area (macula) of the retina, located at the back of the eye, sustains damage that is the cause of loss of vision. The early detection of AMD can increase the probability of treatment and prevent vision loss. The AMD can be classified into dry and wet AMD based on the absence of neovascularization. This study introduces a new methodology for the classification of AMD using optical coherence tomography (OCT) retinal images. The proposed methodology is based on three stages. The first stage is the data preparation stage for resizing and normalizing the used images. The second stage is the image processing stage for enhancing the image quality as contrast and resolution these enhancements have been checked by the weighted peak signal-to-noise ratio (WPSNR) methodology. The third stage is the deep feature extraction and classification stage, which consists of two sub-models. The first model is MobileNet V1 which has been used as a deep feature extractor. The second model is LSTM (long short-term memory), fed with deep features to classify the AMD stages. A multi-classification with six separate trials has been employed with the proposed methodology, and compared with other models like DenseNet201 and InceptionV3. The proposed model has been tested on a sample of benchmark data with 4005 grayscale images labeled into three classes. The proposed methodology has achieved an accuracy of 98.85%, a sensitivity of 99.09%, and a specificity of 99.1%. To ensure the effectiveness of the proposed methodology, a comparative analysis has been established with previous approaches in the related field, and the results demonstrated the superiority of the proposed system in AMD multi-classification. © The Author(s) 2024.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Fault Detection of Partial Shading Faults in Solar Photovoltaic Energy Systems 3

Fault Detection of Partial Shading Faults in Solar Photovolt...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Shaheen, Eslam Sobaih, Abdul-Azim Nabil, Essam Menoufia University Faculty of Electronic Engineering Industrial Electronics and Control Engineering Department Menouf Egypt Menoufia University Faculty of Electronic Engineering Industrial Electronics and Control Engineering Department Egypt

ISBN: (纸本)9798350323511

This paper addresses a developed viable fault-detection scheme based on power evaluation and observation against partial shading degradation faults in solar photovoltaic (PV) system. To extract maximum power from photovoltaic systems and increase their efficiency and performance under atmospheric circumstances changes that leads to PV system failures, like solar irradiance and ambient temperature. An explicit fault detection algorithm is derived to detect the effectiveness factor as well as the threshold indicator relating the partial shading faults in PV array. Simulation result on PV array is demonstrated to justify the validation of the proposed design scheme. The faulty part of the array is detected with a short and acceptable time period and a computation load reduction for large number of PV modules. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Fault detection and diagnosis strategy for wind turbine system using partial least square technique 3

Fault detection and diagnosis strategy for wind turbine syst...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Elshenawy, Lamiaa M. Gafar, Ahmed A. Awad, Hamdi Menoufia University Faculty of Electronic Engineering Industrial Electronics and Control Engineering Department Egypt

ISBN: (纸本)9798350323511

Process monitoring has been used in industry for detecting and diagnosing abnormal behaviour of processes which abundantly improves the overall efficiency of such processes. Recently, the wind turbines' installed power generation capacity is rising worldwide, so, it is important to achieve reliability and safety on such systems. The major task behind this study is to provide an inclusive framework for the fault detection and diagnosis of the wind turbine system. According to the proposed methodology, the faults are first detected by two fault detection indices using the partial least squares (PLS) approach. Then, the diagonal contribution plot (DC) method based on PLS approach (DC-PLS) is used for fault diagnosis. Data collected from a benchmark of a wind turbine system is utilized to confirm the execution of the proposed methodology. The results proved the efficacy of the proposed methodology from the point of view the fault detection and diagnosis. © 2023 IEEE.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Soft Sensors Based on Support Vector Regression and Gray Wolf Optimizer 3

Data-Driven Soft Sensors Based on Support Vector Regression ...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Abouomar, Mahmoud S. Badawy, Ahmed Elshenawy, Lamiaa M. Menoufia University Faculty of Electronic Engineering Industrial Electronics and Control Engineering Department Egypt

ISBN: (纸本)9798350323511

Data-driven soft sensors offer a reliable means of estimating hard-to-measure variables using easily measurable process variables, so they play a crucial role in implementing closed-loop control in industrial processes. These soft sensors enable real-time process control, act as backup measurement systems, facilitate what-if analysis, support sensor validation, and contribute to fault diagnosis. Additionally, they allow for a reduction in the number of required hardware sensors, thereby enhancing system reliability while decreasing costs associated with sensor acquisition and maintenance. The proposed method for soft sensor design involves utilizing the Support Vector Regression (SVR) technique which effectively addressing nonlinear regression problems. To optimize the SVR parameters, the Gray Wolf Optimization algorithm (GWO) is employed. The GWO-SVR model is then used for predicting system variables. To validate the effectiveness of this approach, case studies are conducted in the benchmark Tennessee Eastman process. The results demonstrate the successful application of the proposed method. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Attacks Detection in Industrial Cyber-Physical Systems Using Convolutional Neural Networks 3

Attacks Detection in Industrial Cyber-Physical Systems Using...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Salah, Mohamed Elshenawy, Lamiaa M. Menoufia University Faculty of Electronic Engineering Industrial Electronics and Control Engineering Department Egypt

ISBN: (纸本)9798350323511

Cyber-physical systems (CPSs) are widely used and extremely important due to their promise for substantial and long-term benefits to society, economy, environment, and human life. Moreover, the development in communication, computing, and storage technologies has resulted in a revolution in information communication technologies (ICT). The utilization of CPSs in industrial control systems are well known as industrial CPSs (ICPSs). Consequently, these systems have become a popular target for cyber-attacks and malicious threats which can disable the system's functioning and have serious safety-related consequences. This paper presents an attack detection method based on simple neural networks, 1D convolutional neural networks. The presented method is verified using a popular public dataset, the Secure Water Treatment testbed (SWaT), which is a small-scale representation of a real-world industrial water treatment plant. The results have demonstrated the effectiveness of the presented method for attack detection in ICPSs. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Fault Detection of Photovoltaic Systems using Pre-Train CNN-VGG16 9

Fault Detection of Photovoltaic Systems using Pre-Train CNN-...

引用

9th International Conference on control, Instrumentation and Automation, ICCIA 2023

作者： Azimi, Samaneh Manthouri, Mohammad Shahed University Faculty of Engineering Department of Power Electronics Tehran Iran Shahed University Faculty of Engineering Department of Control Electronics Tehran Iran

ISBN: (纸本)9798350366013

Fault detection in photovoltaic systems is crucial for boosting the output power and extending the lifespan of a PV system. However, conditions such as partial shading, high impedance faults, and the presence of Maximum Power Point Tracking make fault detection challenging in weather conditions. Most research in this area has only identified and classified faults in a few scenarios. This study identifies and classifies faults in the PV system using two-dimensional Deep Convolutional Neural Networks (2-D CNN) and features extracted from two-dimensional scalograms generated from PV system data. Unlike previous methods for fault classification, our study considers different faults by combining MPPT. This study shows that the proposed method, including a pre-trained CNN, performs better than existing methods and achieves 98.76 fault detection accuracy. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Breast Tumor Model Based on Magnetoacoustic Concentration Tomography of Magnetic Nanoparticles with Magnetic Induction

引用

Progress In Electromagnetics Research C 2024年 139卷 197-209页

作者： Yan, Xiaoheng Liu, Fangtian Smolik, Waldemar T. Dan, Xinxian Hou, Xiaohan Faculty of Electrical and Control Engineering Liaoning Technology University Huludao125000 China The Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China Faculty of Electronics and Information Technology Warsaw University of Technology Warsaw Poland

Magnetic nanoparticles (MNPs) have been widely investigated as effective drug carriers for targeted tumor therapy. However, the successful application of this technology in the human body requires reliable imaging support. Magnetoacoustic Concentration Tomography of Magnetic Nanoparticles with Magnetic Induction (MACT-MI) is an electromagnetic-ultrasonic coupling imaging technique that holds great promise in improving imaging resolution and providing unique advantages for tumor monitoring and treatment. To evaluate the imaging feasibility of MACT-MI technology for targeted therapy of breast tumors, this study establishes a realistic breast model and takes into account the distribution of magnetic particles within the actual breast tissue environment. A concentration gradient model is introduced, and the finite element method is employed to solve the electromagnetic and sound fields. In addressing the research objective, the forward problem is investigated by analyzing the magnetic force and sound pressure distribution for various tumor sizes and locations, different breast tissues, and both benign and malignant tumors. The results obtained indicate that the magnetoacoustic signal emitted by magnetic particles facilitates accurate mapping of the size and location information of magnetic particles enveloping breast tumors, as well as distinguishing between benign and malignant tumors. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Tomography

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：