检索结果-内蒙古大学图书馆

Decreasing control signal vibrations in the anti-noise model-free sliding mode control algorithm

International Journal of Systems, control and Communications 2023年第4期14卷 341-356页

作者： Diab, Jomana Mahmoud Wasouf, Hasnaa Faculty of Biomedical Engineering Al Andalus University for Medical Sciences Al-Qadmous Tartous0963-043 Syria Al Baath University Homs0963-031 Syria Department of Automatic Control and Computers Engineering Faculty of Mechanical and Electrical Engineering Al Baath University Homs0963-031 Syria

Thanks to the model-free sliding mode control (MFSMC) algorithm, we were able to overcome errors resulting from the modelling process. When this algorithm was tested in a noise-prone environment, it was observed that the system was not able to track the desired path. In previous research, an anti-noise model-free sliding mode control (AMFSMC) algorithm was proposed. It improved the performance of MFSMC algorithm and made it noise-resistant. The control signal of that AMFSMC algorithm has a lot of chattering, which limits the use of the algorithm in practice. In this research, an improved anti-noise model-free sliding mode control (IAMFSMC) algorithm was proposed to solve the chattering problem. The control law of AMFSMC was modified using three techniques: boundary layer, quasi-sliding mode control, and saturation function. The IAMFSMC algorithm was applied to a second-order linear system. The system performance using the three techniques was compared to that when the AMFSMC algorithm was applied. Simulation results showed that using the saturation function gave good tracking response, despite the presence of noise, with chattering-free and smooth control signal. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Weighted Fuzzy Rough Sets Feature Selection for High Dimensional Classification Problems

Weighted Fuzzy Rough Sets Feature Selection for High Dimensi...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Khabusi, Simon Peter Huang, Yo-Ping Vu, Van Phong National Taipei University of Technology Department of Electrical Engineering Taipei10608 Taiwan National Penghu University of Science and Technology Department of Electrical Engineering Penghu88046 Taiwan Ho Chi Minh City University of Technology and Education Department of Automatic Control Ho Chi Minh City71300 Viet Nam

ISBN: (纸本)9781665410205

Feature selection holds significant importance in knowledge mining as it plays a pivotal role in selecting and preserving the most informative features within a dataset while discarding irrelevant, redundant, or noisy attributes. This process contributes to enhancing model performance, reducing computational complexity, and refining interpretability, thus facilitating more accurate and efficient data analysis. In high-dimensional datasets, the necessity for feature selection becomes more pronounced due to the heightened risk of encountering the curse of dimensionality. Therefore, this study proposes a weighted fuzzy rough quickreduct (FRQR) feature selection approach employing feature weights to handle the equal situation problem inherent in FRQR. The proposed method is evaluated on ten publicly available datasets with feature sizes ranging from 2000 to 15154. The selected features are used to train and test random forest candidate models whose estimates are then combined according to the posterior probabilities by Bayesian Model Averaging (BMA). The performance of the model on the selected features is evaluated on four performance metrics. The essentiality of the selected features is further determined by comparing the model classification performance achieved on the non-selected features and all the dataset features. The results indicate competitiveness in the performance metric values achieved on selected features over the other two feature categories affirming the efficacy of the proposed method. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Improving Workplace Safety in the Cargo Industry through Posture Monitoring using Mediapipe and Machine Learning 17

Improving Workplace Safety in the Cargo Industry through Pos...

引用

17th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2023

作者： Cobb, Buket Sonbas Candan, Fethi Harran University Department of Electrical-Electronics Engineering Sanliurfa63190 Turkey University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom

ISBN: (纸本)9798350338904

This research reveals the potential of Mediapipe with machine learning methods in addressing the critical need for real-time posture monitoring, offering a promising solution for creating secure work environments and improving health and safety conditions not only in the cargo industry but also in other fields, such as healthcare, sports, and industry. The findings indicate that the Random Forest Classifier demonstrates the highest accuracy in classifying untrained movements, indicating its potential for developing a posture correction warning system. Further research is needed to validate the findings and explore real-world applications. Overall, this study contributes to the advancement of workplace safety and sets the foundation for future developments in posture monitoring systems using Mediapipe and machine learning using Python programming. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Modeling and Research of automatic Sun Tracking System On the Bases of Arduino 5

Modeling and Research of Automatic Sun Tracking System On th...

引用

5th IEEE International Conference on Modern electrical and Energy System, MEES 2023

作者： Zachepa, Iurii Kuzmenko, Vitaly Zachepa, Nataliia Antonov, Mykola Antonova, Marina Khrebtova, Oksana Kremenchuk Mykhailo Ostrohradskyi National University Department of Systems of Automatic Control and Electric Drive Kremenchuk Ukraine National University Zaporizhzhya Polytechnic Electrical Engineering Department Zaporizhzhya Ukraine

ISBN: (纸本)9798350359787

The paper presents studies on the effectiveness of the use of solar trackers in mobile platforms of solar panels. It has been proven that the use of solar trackers allows more than doubling the zone of maximum energy generation. The development of a small-sized laboratory stand for the study of mechatronic systems for automatic target tracking and positioning based on solar panels and a tracker that ensures the rotation of the platform along the light source, where experimental studies were carried out, is presented. The solar tracker has a mechanical movement system, a servo drive and an electronic position control unit that work out the hit of sunlight on the panel at an angle of 900 and thereby maximize energy generation. © 2023 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Using Optimal Filters for Plug-in Type Repetitive controllers for Periodic Inputs 28

Using Optimal Filters for Plug-in Type Repetitive Controller...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Diaconu, Larisa Vilanova, Ramon Barbu, Marian Dunǎrea de Jos University of Galaţi Department of Automatic Control and Electrical Engineering Galaţi Romania Universitat Autonoma de Barcelona Department of Telecommunications and Systems Engineering Barcelona Spain

ISBN: (纸本)9798350339918

This paper proposes some solutions to optimize the Butterworth filter from the structure of plug-in type repetitive controllers, as well as the use of the Bessel filter, which offers a simpler way of choosing the anticipatory factor from the repetitive controller structure. The comparative analysis of the two types of filters was made on the basis of three criteria: 1) the standard deviation of the error in the control loop, where the first type of filter proved to be superior;2) ease of obtaining the optimal value of the anticipative parameter, in which case the Bessel filter is preferred;3) sensitivity to changes in the filter parameters and/or process model, where the second filter is also preferred © 2023 IEEE.

关键词： Butterworth filters

来源：评论

学校读者我要写书评

暂无评论

A Review of Manufacturing Technologies of Soft Magnetic Composites for Electric Machines 5

A Review of Manufacturing Technologies of Soft Magnetic Comp...

引用

5th IEEE International Conference on Modern electrical and Energy System, MEES 2023

作者： Manko, Roman Dmytro, Rieznik Vukotic, Mario Rupnik, Urban Miljavec, Damijan Corovic, Selma University of Ljubljana Faculty of Electrical Engineering Ljubljana Slovenia Kremenchuk Mykhailo Ostrohradskyi National University Department of Systems of Automatic Control and Electric Drive Kremenchuk Ukraine

ISBN: (纸本)9798350359787

In this article the review of the existing manufacturing technologies of the soft magnetic materials have been performed. The existing technological protocols for production of the electrically insulated powders and their further treatment towards manufacturing of the soft magnetic materials are provided. The influences of different technological processes on the mechanical, electrical and magnetic properties of the resulting soft magnetic materials have been reviewed and described. Finally, the usage and implementation of the soft magnetic composites in the field of electric motor design have been discussed. © 2023 IEEE.

关键词： Electric motors

来源：评论

学校读者我要写书评

暂无评论

LMI-Based Luenberger Observer Design for Uncertain Nonlinear Systems with External Disturbances and Time-Delays

引用

IEEE Access 2023年 11卷 71823-71839页

作者： Karami, Hamede Nguyen, Ngoc Phi Ghadiri, Hamid Mobayen, Saleh Bayat, Farhad Skruch, Pawel Mostafavi, Fatemeh University of Zanjan Faculty of Engineering Department of Electrical Engineering Zanjan45371-38791 Iran Sejong University Department of Aerospace Engineering Seoul05006 Korea Republic of Islamic Azad University Qazvin Branch Department of Electrical Engineering Qazvin34199-15195 Iran National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliou640301 Taiwan AGH University of Science and Technology Department of Automatic Control and Robotics Kraków30-059 Poland

This paper investigates the simultaneous design of a controller and Luenberger state observer for systems with time-delays, external disturbances, uncertainties, modeling errors, and unknown nonlinear perturbations. The state-feedback control approach and state-observer existence conditions are formulated using the Linear Matrix Inequalities (LMIs). By defining the estimation error, the equations of the closed-loop system are rewritten. External disturbances, uncertainties, unknown nonlinear perturbations, and constant time-delays are considered in system modeling. By using LMI techniques, the estimation error is converged to zero. Therefore, the time-delays, uncertainties, and external disturbance effects on the system output, which have not been considered simultaneously before, are minimized, and the closed-loop system is stabilized. The performance of the proposed approach is verified by simulation of two examples, Flexible-Link Manipulator (FLM) dynamics, and Continuous Stirred Tank Reactor (CSTR) system. These examples illustrate the reliability of the suggested method. © 2013 IEEE.

关键词： Linear matrix inequalities

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 28

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

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

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

ISBN: (纸本)9798350339918

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. © 2023 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Stress Matrix-Based Formation control of Multi-Agent Systems with Discrete-Time Communication 12

Stress Matrix-Based Formation Control of Multi-Agent Systems...

引用

2024 12th International Conference on Systems and control, ICSC 2024

作者： Onuoha, Okechi Ubochi, Brendan Chijioke Kurawa, Suleiman Tang, Zezhi Wu, Changshun Dong, Yi University of Hertfordshire United Kingdom Federal University of Technology The Department of Electrical and Electronic Engineering Akure Nigeria University of Manchester The Department of Electrical Engineering United Kingdom University of Sheffield The Department of Automatic Control and Systems Engineering United Kingdom University Grenoble Alpes Grenoble38000 France The School of Electronics & Computer Science University of Southampton United Kingdom

ISBN: (纸本)9798331531812

This study addresses the affine formation maneuver control of cooperative multi-agent systems (MAS) having periodic inter-agent communication for both static and dynamic leader cases. Here, we focus on the leader-follower MASs. The primary aim of the control system is to steer the entire collection of agents to produce required patterns (geometric) along with any required maneuver through the direct control of only few a selected agents referred to as leaders. Most of the existing works are constrained to either the individual agents communicate with each other in continuous-time or the sample-data scenario where the leaders are stationary or have constant acceleration or velocities. Here, we consider the scenarios where the velocities of the leaders can be time-varying or constant. Here, different cases are addressed and some control laws are proposed. Conditions are established to help guarantee the overall stability of the systems. A simulation study is employed for the illustration of our proposed laws. © 2024 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Fuzzy ASC-GAN: A Fuzzy C-means Audio Similarity CycleGAN on Articulation Disorder Voice Conversion

Fuzzy ASC-GAN: A Fuzzy C-means Audio Similarity CycleGAN on ...

引用

2023 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2023

作者： Huang, Yi-Wei Chang, Sheng-Wen Chin, Chiun-Li Lin, Guang-Tao Chang, Pei-Hsin Lin, Wan-Xuan Chen, Jun-Ren Zheng, Zhong-Ting Wong, Geng-Kai Chung Shan Medical University Department of Medical Informatics Taiwan Taipei Municipal XiSong Senior High School Taipei Taiwan Feng Chia University Automatic Control Engineering Taiwan

ISBN: (纸本)9798350305791

This paper introduces an innovative approach, Fuzzy Audio Similarity CycleGAN (Fuzzy ASC-GAN), turned at addressing articulation disorders and enhancing dysarthric voice conversion (DVC). By integrating Fuzzy C-means clustering and CycleGAN-VC2, the proposed method focuses on refining both training and transformation processes. Notably, Fuzzy ASC-GAN incorporates a unique strategy that leverages the audio similarity of timbres to adjust the training data of CycleGAN-VC2, ensuring accurate and effective voice conversion. Through repeated and rigorous parameter adjustments and comprehensive performance comparisons, Fuzzy ASC-GAN emerges as the standout performer, achieving an average accuracy of 93.35% across diverse S2T models. The method's distinct advantage lies in its ability to tailor voice conversion about specific characteristics of individual with articulation disorders. This highlights the potential of Fuzzy ASC-GAN to significantly enhance communication for individuals with dysarthric voices, marking a significant advancement in the realm of voice conversion techniques. © 2023 IEEE.

关键词： Fuzzy systems

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：