检索结果-内蒙古大学图书馆

A machine learning-based motion training approach applied to multilegged and bipedal robots

Control engineering Practice 2024年 147卷

作者： Kuo, Ping-Huan Huang, Chiou-Jye Yang, Wei-Cyuan Hsu, Po-Wei Chang, Wei-Hsin Chen, Xin-Yu Department of Mechanical Engineering National Chung Cheng University Chiayi62102 Taiwan National Chung Cheng University Chiayi62102 Taiwan Department of Intelligent Automation Engineering National Chin-Yi University of Technology Taichung411030 Taiwan Department of Intelligent Robotics National Pingtung University Pingtung 90004 Taiwan

To promptly gain an understanding of disasters as they occur and to draft plans for search and rescue operations, various types of robots are used. Robots not only increase rescue efficiency but also reduce firefighter casualties. Therefore, this study investigated how bionic robots can be utilized to search destroyed and chaotic disaster sites as quickly as possible. However, manually adjusting the motion parameters of robots performing robot motions is extremely inefficient. To resolve this problem, this study used machine learning algorithms to allow robots to train themselves in the environment and autonomously determine their optimal motion parameters. However, many types of machine learning algorithms exist, each with their own strengths and weaknesses. Therefore, this study designed a series of experiments to investigate the features of each algorithm in optimizing the robots’ motions;subsequently, this study compared the strengths and weaknesses of each algorithm based on their performance. The results indicated that for both multipedal and bipedal robots, the use of machine learning to find the optimal motion parameters is both feasible and practical. © 2024 Elsevier Ltd

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Localized Bearing Defects using Texture Analysis of Vibration Envelope Signals and Machine Learning

Diagnosis of Localized Bearing Defects using Texture Analysi...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Cong Dai Nguyen Fazal E Nasir Shahbaz Khan Sheraz Ali Khan Jong-Myon Kim Faculty of Radio-Electronic Engineering Le Quy Don Technical University Hanoi Vietnam Advanced Robotics and Automation Lab National Center for Robotics and Automation Peshawar Pakistan Institute of Manufacturing University of Engineering and Applied Sciences Swat Pakistan Department of Mechatronics Engineering University of Engineering and Technology Peshawar Pakistan Department of IT Convergence University of Ulsan Ulsan South Korea PD Technology Ulsan South Korea

Bearings are important because they play a critical role in the operation of many machines and devices by reducing friction and enabling smooth motion between two moving parts. They are commonly used in rotating machinery, such as electric motors, turbines, pumps, and gearboxes, where they support and guide the rotating shafts. The primary cause of failure in wind turbines and induction motors is bearing faults, resulting in significant downtime and economic losses. Detecting these faults accurately and promptly is crucial to preventing unexpected shutdowns. Most of the existing methods for bearing fault detection rely on envelope analysis, which involves filtering and demodulating the raw signal, and Fourier analysis of the envelope signal to identify defect frequencies. Recent research has focused on improving the visibility of these frequencies by selecting an optimal band for filtering, using sub-band analysis and spectral kurtosis, which is a complex process and can be time-consuming. This paper presents a new approach to envelope signal analysis using texture analysis of the envelope signals that are projected as 2D grayscale images where each fault generates a unique texture. These textures are encoded using the local binary pattern operator and then used for fault classification. The method is tested on a publicly available seeded fault dataset.

关键词： Vibrations Fault diagnosis Shafts Time-frequency analysis Filtering Pumps Machine learning

来源：评论

学校读者我要写书评

暂无评论

Analyze the mitigation effect of FWM for SD-WDM system

引用

Journal of Optical Communications 2025年

作者： Kumar, Ghanendra Kumar, Chakresh Sahu, Deepak Parashuram University School of Automation and Robotics New Delhi India University School of Information Communication & Technology Guru Gobind Singh Indraprastha University New Delhi110078 India Department of Electronics and Communication Engineering Bharati Vidyapeeth's College of Engineering Delhi110 063 India

Four-wave mixing (FWM) is the most dominating feature for 440 × 14Gbps super dense wavelength division multiplexing system, which almost spoil the performance of super dense communication signals. So, the effect of FWM has mitigated with the implementation of optical phase conjugation with combination of dispersion modified fiber and fiber grating compensator. Further, power level of the transmitting signals has also enhanced with the arrangement of RAMAN-SOA hybrid optical amplifier. Furthermore, final analysis has recommended that proposed techniques are the acceptable approach for the proposed super dense communication system. © 2025 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Four wave mixing

来源：评论

学校读者我要写书评

暂无评论

Machine learning-supported CFD optimization of heat transfer in a pipe with a corrugated wall shape 26

Machine learning-supported CFD optimization of heat transfer...

引用

26th Fluid Mechanics Conference, FMC 2024

作者： Kamiński, P. Li, Y. Wawrzak, K. Tyliszczak, A. Noack, B.R. Department of Thermal Machinery Czȩstochowa University of Technology al. Armii Krajowej 21 Czȩstochowa42-201 Poland Artificial Intelligence and Aerodynamics School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology Shenzhen518055 China

The paper focuses on using machine learning to optimize the corrugation of a heated pipe wall to improve the uniformity of temperature distribution while minimizing pressure losses. The corrugation is characterized by a five-parameter function, allowing for extensive variations in wall shape. The machine learning process employs the Bayesian optimization method, iteratively working alongside the ANSYS Fluent code to perform RANS computations. A two-parameter cost function, which includes temperature variation and pressure drop, is used to define the optimization goal. The study demonstrates that substantial variations in flow patterns occur depending on the type of corrugation. An optimal set of corrugation parameters, ensuring the most uniform temperature distribution with minimal pressure losses, is determined within an optimization loop consisting of 1200 RANS simulations. The optimal configuration is characterized by a smooth waviness oriented outside the original wall location in a straight pipe. It ensures more than three times smaller temperature variation at only minor increase in the pressure drop. © Published under licence by IOP Publishing Ltd.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Design, Modeling, and Control of a Coaxially Aligned Steerable (COAST) Guidewire Robot” [Jul 20 4947-4954]

引用

IEEE robotics and automation Letters 2023年第11期8卷 7823-7824页

作者： Seokhwan Jeong Yash Chitalia Jaydev P. Desai Medical Robotics and Automation (RoboMed) Laboratory Georgia Institute of Technology Atlanta GA USA Department of Mechanical Engineering Sogang University Seoul South Korea Healthcare Robotics and Telesurgery (HeaRT) Laboratory Department of Mechanical Engineering University of Louisville Louisville KY USA RoboMed Laboratory Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA USA

Presents corrections to the article “Design, Modeling, and Control of a Coaxially Aligned Steerable (COAST) Guidewire Robot”.

关键词： Medical robotics Catheters Position control Blood vessels Wires

来源：评论

学校读者我要写书评

暂无评论

Robotic Single-Micropipette Enucleation Method for Zona-free Oocytes 42

Robotic Single-Micropipette Enucleation Method for Zona-free...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zhang, Yidi Liu, Yaowei Li, Minghui Sun, Dong Zhao, Xin Tianjin300350 China City University of Hong Kong Department of Biomedical Engineering Hong Kong Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China Shenzhen Research Institute City University of Hong Kong Centre for Robotics and Automation Shenzhen518057 China

ISBN: (纸本)9789887581543

Somatic cell nuclear transfer is a mammalian cloning method that involves replacing the oocyte nucleus with a somatic cell nucleus. One of the most critical steps in this process is the efficient production of large numbers of enucleated oocytes. While a single-micropipette-based manual enucleation method has been widely used in manual cloning, it is still a manual operation that requires exceptional technical skills and experience. Additionally, it is difficult to accurately control the amount of enucleation and to meet the demand for high-throughput enucleation. Therefore, we propose a robotic enucleation method using a single micropipette for zona-free oocytes, which allows for the detection and control of the amount of enucleation, as well as continuous enucleation on a large scale. A single oocyte enucleation can be completed in less than 13 seconds. This robotic enucleation method provides a solution for enhancing the operational efficiency of robotic somatic cell nuclear transfer. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Faults in Edge-PLC using Optimized Deep Learning models in Industrial IoT

Diagnosis of Faults in Edge-PLC using Optimized Deep Learnin...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： A. Kishore Kumar T Rajesh Kumar R. Balamanigandan A. Sasi Kumar Mahaveerakannan R Department of Robotics and Automation Sri Ramakrishna Engineering College Coimbatore Tamilnadu Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu Department Of Cloud Technology & Data Science Institute Of Engineering & Technology Srinivas University Surathkal

Industrial Internet of Things (IIoT) may allow for the state of equipment to be monitored and defects to be detected before they become serious, helping smart factories keep up with the rising demands for safety and efficiency brought on by worldwide competition. In the case of Cloud Computing, data-driven approaches implemented in the cloud are used to first train the model using a vast quantity of raw data, and then end-machines send their real-time readings for processing at the cloud data centre. It is possible, however, that this will impose a significant delay and a high computational cost. In this study, we take into account a hierarchical structure in which edge-PLCs are used to collect sensed data locally and lessen the burden on long-distance connections. Due to the fact that a single responsibility may be associated with multiple swaying topographies, we aim to first reduce the sum of features required to identify a fault, and then identify the smallest possible set of edge-PLCs that still accounts for all of the most important ones, all while keeping deployment costs to a minimum. To address this, we present an Enhanced Harris Hawkins Optimization (EHHO) approach to tackling the features selection issue, followed by the assortment of edge-PLCs through the set coverage problematic. The model named Residual Attention Neural Network (RANN) is proposed the in this study to forecast the fault detection procedure. Residual Neural Network (ResNet) is used by RANN to help diagnose problems, alongside the knowledge of experts. We evaluate the performance of our technique in comparison to existing AI-based approaches, such as the lregression model and its expansions, by simulating on a real data trail. The findings confirm competence and presentation of the suggested approach, which meets or even surpasses the correctness of approaches employing the entire collection of data.

关键词： Fault diagnosis Deep learning Solid modeling Cloud computing Image edge detection Computational modeling Fault detection

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity in Healthcare: Safeguarding Patient Data

Cybersecurity in Healthcare: Safeguarding Patient Data

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： P Divya Prabha N Suresh Kumar N Nandhine Shree R. Sundaram H Nishanthi D Pranesh Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India Department of Information Technology Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India Department of Computer Science and Engineering Ganesh College of Engineering Salem Tamil Nadu India Department of Robotics and Automation Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

The Study indicates the need for adequate cybersecurity safeguards in healthcare to protect patient data. The importance derives from the vulnerabilities of redundant systems, which are prone to cyber-attacks, highlighting the need for updated security standards. To strengthen the hospital’s IT infrastructure, the proposed system employs a complex technique that combines advanced encryption, strong authentication, and ongoing audits. The comprehensive technique consists of evaluating the security architecture, installing encryption, strengthening authentication, integrating intrusion detection systems, and using real-time monitoring tools. According to the results and analysis, the proposed system outperforms existing systems in terms of data security (90), cyberattack risk (85), and system integrity (90). Notable developments include 256-bit encryption, multifactor authentication, continuous vulnerability scans, and improved intrusion detection, demonstrating the proposed system’s effectiveness in dealing with cybersecurity challenges and ensuring the long-term stability of the healthcare IT infrastructure. The Study demonstrates the essential requirement for improved cybersecurity methods to provide an adequate healthcare IT infrastructure in the face of improving cyber threats.

关键词： Data security Stability criteria Authentication Intrusion detection Medical services Encryption Computer security

来源：评论

学校读者我要写书评

暂无评论

Optimizing Route Efficiency in Formula One (F1) Vehicles Using Reinforcement Learning Algorithms

Optimizing Route Efficiency in Formula One (F1) Vehicles Usi...

引用

AI in Cybersecurity (ICAIC), International Conference on

作者： Sanam Narejo Muhammad Taimoor Khan Muhammad Zakir Shaikh Lubna Luxmi Dhirani Bhawani Shankar Chowdhery Department of Computer Systems Mehran Univerity of Engineering and Technology Jamshoro Pakistan National Centre for Robotics Automation and Artificial Intelligence Mehran Univerity of Engineering and Technology Jamshoro Pakistan Mechanical Engineering and energy efficiency School of Industrial Engineering University of Malaga Malaga Spain Department of Electronic and Computer Engineering University of Limerick Limerick Ireland

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

This research explores the application of reinforcement learning (RL) to enhance route efficiency and performance of a Formula One (F1) car within a simulation environment. The simulation is implemented using Python, NEAT (NeuroEvolution of Augmenting Topologies), and PyGame to create a dynamic system where neural networks control the car’s navigation. RL enables the F1 car, acting as an agent, to learn optimal decisions through a fitness-based reward mechanism by interacting with its environment. Equipped with radar sensors to detect obstacles and measure distances, the virtual car adjusts its speed and steering to avoid collisions and optimize movement. Over successive generations, the RL algorithm refines the car’s driving ability, improving speed and directional control to maximize distance covered and minimize lap times. A fitness-based evaluation system tracks progress, providing metrics such as best and average fitness scores, which highlight the car’s evolving performance. Results demonstrate the effectiveness of RL in enhancing autonomous driving capabilities, enabling the car to navigate complex environments and improve decision-making across generations.

关键词： Navigation Tracking Neural networks Decision making Reinforcement learning Radar tracking Topology Sensors Automobiles Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement of Voltage Regulator and Capacitor for Distribution System

Optimal Placement of Voltage Regulator and Capacitor for Dis...

引用

2021 International Conference on System, Computation, automation and Networking, ICSCAN 2021

作者： Rajalakshmi, M. Addisu, Molla Jeyakkannan, N. Renuka Devi, G. Karthik, C. Jyothi Engineering College Department of Mechatronics Thrissur India Woldia University Department of Electrical and Computer Engineering Ethiopia Manakula Vinayagar Institute of Technology Deprtment of Robotics and Automation Puduchery India

ISBN: (纸本)9781665439862

The radial distribution system (RDS) is the ultimate link between the high-voltage transmission system (HVT) and the user in most electrical systems in Ethiopia. The Distribution System (DS) is divided into different areas for proper operation and supply of electricity demand. The study in this paper applies specifically to the Gondar feeder, which consists of 60 nodes with 3,413 MW of total capacity, in power distribution lines. For the modulation of voltages and DS node power loss indices, the fuzzy membership functions are used. A fluid expert system (FES) with a collection of heuristic legislation will determine the voltage regulator and the capacitor suitability index. The proposed method discusses and compares the effectiveness and results obtained from the voltage control system and the optimal placement of capacitors. © 2021 IEEE.

关键词： Voltage regulators

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：