检索结果-内蒙古大学图书馆

On Designing Control Systems for Electron-Beam Processing Plants

Russian Electrical engineering 2024年第7期95卷 579-584页

作者： Kozhechenko, A.S. Sliva, A.P. Maslov, A.N. Shcherbakov, A.V. Goncharov, A.L. Rodyakina, R.V. Dragunov, V.K. Department of Power Supply of Industrial Enterprises and Electric Technologies National Research University "Moscow Power Engineering Institute" Moscow111250 Russia Department of Metal Technologies National Research University "Moscow Power Engineering Institute" Moscow111250 Russia Department of Robotics Mechatronics Dynamics and Machine Strength National Research University "Moscow Power Engineering Institute" Moscow111250 Russia

This study shows the need for a common structured approach to designing control systems for electron-beam welding, surfacing, and additive shaping plants. The main controlled parameters of the process are highlighted. The three-level hierarchical structure of the control system is described. The control processes are differentiated taking into account the process requirements for electron-beam treatment processes and the features of the vacuum system, the electron gun, and the positioning system, as well as the system of taking images of the treated area according to the signal of backscattered electrons. The types and quantitative characteristics of the parameters of the signals necessary for running the system are given. It is shown that it is effective to divide the control processes in three groups, depending on the requirements on the rapid response of the actuators, as well as on the need for synchronizing some processes with others over time. The presented differentiation is used to propose a method for selecting technical facilities for each of the mentioned groups. An example is provided of constructing a control system for an electron-beam process plant using hardware components available for purchase. © Allerton Press, Inc. 2024.

关键词： Numerical control systems

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulation of soft bio-mimetic fingers with a novel soft thumb design for bionic hand applications using ANN

Biotechnology Notes

引用

Biotechnology Notes 2025年 6卷 164-176页

作者： Soliman, Eman R.A. Nada, Ayman Ishii, Hiroyuki Fathelbeb, Ahmed M.R. Mechatronics and Robotics Engineering Egypt Japan University of Science and Technology Alexandria Egypt School of Creative Science and Engineering Waseda University Tokyo Japan

The paper presents a novel design for a soft bio-mimetic finger and soft thumb structure for bionic hand applications. It introduces an anthropomorphic pneumatic flexible finger system using a PneuNets framework to enhance flexibility and maneuverability. The research investigates the influence of geometric variations (wall thickness, chamber number, and spacing) on finger deformation, demonstrating that reduced wall thickness and augmented chambers substantially improve flexibility. A key innovation is the soft thumb design that accurately replicates the complex movements of the Carpometacarpal (CMC) joint, enabling natural opposition and dexterity. Eight models were developed for four fingers and two models for the thumb. Simulation results indicate that models with thinner walls (2 mm) achieve bending angles exceeding 80° at 120 KPa, whereas 3 mm models remain below 50°. Moreover, increasing the number of chambers enhances deformation, with each added chamber contributing approximately 41 % more flexibility. For the thumb models, we successfully mapped the motion ranges and accurately mimicked the base joint, enabling natural opposition and dexterity. Furthermore, the paper also integrates Artificial Neural Networks (ANNs) to model forward kinematics, improving the estimation of bending angles and end-tip positions, which enhances the overall adaptability and control of the system. © 2025 The Authors

关键词： Anthropomorphic Artificial neural network (ANN) Bionic hands Neural network PneuNets Soft robotics Soft robotics finger Soft thumb

来源：评论

学校读者我要写书评

暂无评论

Improving Road Safety With Enhanced Vehicle Detection for Night-time Traffic in Mirpur 6

Improving Road Safety With Enhanced Vehicle Detection for Ni...

引用

6th International Conference on robotics and Automation in Industry, ICRAI 2024

作者： Younis, Usama Riaz, Faisal Raza, Umar Atali, Gokhan Rabnawaz, Hamid HEC Control Automotive and Robotics Lab Islamabad Pakistan Manchester Metropolitan University Department of Engineering Manchester United Kingdom Mechatronics Engineering Sakarya University of Applied Sciences Sakarya54050 Turkey Selftech Pvt Ltd Pakistan

ISBN: (纸本)9798350355703

This paper presents a study on improving night-time vehicle detection in the Mirpur region through a modified neural network model. Given the challenges of low visibility at night, the research focused on optimizing a deep learning algorithm to enhance detection accuracy. A dataset of 10,000 images covering various vehicle types was collected and annotated to train and test the model. The study found a 7% increase in detection performance compared to the standard model, highlighting the potential for tailored algorithms in specific environmental conditions. The findings suggest significant implications for road safety and autonomous driving systems, particularly in regions with similar night-time driving challenges. The research contributes to the broader field of computer vision by showing the effectiveness of model optimization in real-world conditions. © 2024 IEEE.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Implicit Grasp Diffusion: Bridging the Gap between Dense Prediction and Sampling-based Grasping 8

Implicit Grasp Diffusion: Bridging the Gap between Dense Pre...

引用

8th Conference on Robot Learning, CoRL 2024

作者： Song, Pinhao Li, Pengteng Detry, Renaud KU Leuven Dept. Mechanical Engineering Research Unit Robotics Automation and Mechatronics Belgium KU Leuven Dept. Electrical Engineering Research Unit Processing Speech and Images Belgium AI Thrust Hong Kong

There are two dominant approaches in modern robot grasp planning: dense prediction and sampling-based methods. Dense prediction calculates viable grasps across the robot's view but is limited to predicting a fixed number of grasps per voxel. Sampling-based methods, on the other hand, encode multi-modal grasp distributions, allowing for different grasp approaches at a point. However, these methods rely on a global latent representation, which struggles to represent the entire field of view, resulting in coarse grasps. To address this, we introduce Implicit Grasp Diffusion (IGD), which combines the strengths of both methods by using implicit neural representations to extract detailed local features and sampling grasps from diffusion models conditioned on these features. Evaluations on clutter removal tasks in both simulated and real-world environments show that IGD delivers high accuracy, noise resilience, and multi-modal grasp pose capabilities. Our code is freely available at https://***/detry-lab/public/***. © 2024 Proceedings of Machine Learning Research.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

CO2 Laser Fabrication of a Passive continuous-flow T-shaped Polymethyl Methacrylate (PMMA) Micromixer

引用

Lasers in Manufacturing and Materials Processing 2023年第3期10卷 373-388页

作者： Okello, Job Lazarus El-Bab, Ahmed M. Fath Yoshino, Masahiko El-Hofy, Hassan A. Industrial and Manufacturing Engineering Department University of Science and Technology New Borg El-Arab City Egypt Mechatronics and Robotics Engineering Department University of Science and Technology New Borg El-Arab City Egypt Department of Mechanical Engineering Tokyo Institute of Technology Tokyo Japan On leave from Department of Production Engineering Faculty of Engineering Alexandria University Alexandria Egypt

Since the emergence of microfluidics, the demand for microfluidic devices is ever increasing. Polymethyl methacrylate (PMMA) is extensively used to manufacture microfluidic devices because it is cheap, disposable, and biocompatible. CO2 laser micromachining of PMMA is cheap, fast, and efficient. However, thermal defects affect the process. In this work, a passive continuous-flow T-shaped micromixer was fabricated using a low-power CO2 laser. Microchannels were fabricated on PMMA substrates coated with a 1-µm layer of 99.95% pure aluminium. The power and speed of the laser varied from 1.5 to 7.5 W and 5 to 17.5 mm/s respectively. The effects of the deposited energy on surface roughness, heat-affected zone, and volumetric removal rate were examined. The microchannels were characterized to get the suitable dimensions for the micromixer’s microchannel which was fabricated at 3.0 W and 17.5 mm/s. The micromixer was bonded using the microwave welding technique and tested for leakage using purple dye by varying the flow pressure at intervals of 100 kPa for 20 min. Up to 1.5 MPa, no leakage occurred. Beyond 1.5 MPa, any increase in pressure resulted in leakage from the inlet tubes. Coating PMMA substrates with 99.95% pure aluminium before fabrication reduces thermal defects and improves efficiency. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Carbon dioxide lasers

来源：评论

学校读者我要写书评

暂无评论

Data Collection, Heat Map Generation for Crack Detection Using Robotic Dog Fused with FLIR Sensor

Data Collection, Heat Map Generation for Crack Detection Usi...

引用

IEEE Southeastcon

作者： Jose Chagoya Shrey Patel Charles Koduru Aiden Kovarovics M. Hassan Tanveer Razvan C. Voicu Department of Robotics and Mechatronics Engineering Kennesaw State University Marietta GA USA

The imperative need to monitor critical infrastructure, encompassing power plant transformers and essential civil structures, is paramount for ensuring their sustained longevity and safety. A notable progression in this domain arises from the widespread availability of Forward-Looking Infrared (FLIR) cameras, made possible by reductions in manufacturing costs. These FLIR cameras, distinguished by their remarkable precision in temperature data collection and visualization, hold significant potential across diverse fields. This paper underscores the pioneering application of FLIR cameras in infrastructure monitoring, with a specific focus on power transformers and aging civil structures like bridges. In the realm of transformers, the FLIR camera exhibits the capability to delve into and record internal temperatures, facilitating the early identification of deviations from standard operational temperature ranges. Detection of such anomalies serves as a trigger for preemptive measures, thereby minimizing operational disruptions. Similarly, for structures such as bridges, routine FLIR analyses prove instrumental in discerning temperature variations that may indicate potential wear or fractures. This timely identification allows for proactive maintenance, ensuring structural integrity and averting potential hazards. To augment the safety and efficiency of data collection, this research advocates for the integration of FLIR cameras with mobile robots, exemplified by the Unitree GoAirl. This strategic amalgamation enables precise yet remote surveillance, mitigating risks to operators while maximizing the accuracy of infrastructure health assessments. The proposed approach not only advances the capabilities of FLIR technology but also her-alds a paradigm shift in the realm of infrastructure monitoring, promising enhanced reliability and safety standards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ChildACT: Child Action Recognition Dataset in RGB Data 25

ChildACT: Child Action Recognition Dataset in RGB Data

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Anara Sandygulova Andrey Yershov Aida Zhanatkyzy Zhansaule Telisheva Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Human action recognition is concerned with analysing, understanding and synthesizing kinematic and kinetic data. Data-driven computer vision solutions have advanced the progress in the field of action recognition while it would not be possible without large and publicly available datasets. While there are numerous datasets available for adult action recognition, child-centered action recognition efforts are still scarce. This paper presents a dataset that consists of video recordings of 200 children of different age and gender groups performing seven actions (boxing, waving, clapping, running, jogging, walking towards the camera, and walking from side to side). Two camera perspectives are provided, with a top view and a frontal view in RGB format. The dataset provides an opportunity for kinematic analysis of children motion while it also aims to bridge the performance gap between activity recognition systems for adults and children.

关键词： Training Legged locomotion Transfer learning Human-robot interaction Estimation Kinematics Cameras Human activity recognition Video recording Testing

来源：评论

学校读者我要写书评

暂无评论

AI-Driven 3D Printing: Generative Gcode for Quality and Efficiency

AI-Driven 3D Printing: Generative Gcode for Quality and Effi...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Haque, Sean Tanveer, Muhammad Hassan Voicu, Razvan Cristian Kennesaw State University Department of Robotics & Mechatronics Engineering MariettaGA United States

ISBN: (纸本)9798331504847

Artificial Intelligence (AI) is transforming the landscape of three-dimensional (3D) printing by enabling generative approaches that extend beyond conventional, parameter-tuning strategies. Rather than merely adjusting nozzle temperatures or speeds, modern AI models can create or refine Gcode paths themselves, seeking to balance objectives such as print strength, dimensional accuracy, and defect minimization. This paper introduces a holistic AI-driven workflow for automated Gcode generation. We demonstrate that generative Large Language Models (LLMs) can parse, synthesize, and optimize printing instructions, thus offering an alternative to human-engineered slicing parameters. Our approach incorporates a continuous feedback loop in which a predictive model evaluates each generated Gcode script for potential print outcomes. Experimental results illustrate strong correlations between the number of lines in generated Gcode and key performance metrics (tensile strength, defect rate, and dimensional accuracy). Notably, some scripts with fewer lines reduced material defects yet slightly degraded dimensional accuracy, while more complex scripts improved measurement fidelity but also introduced minor flaws. These findings illuminate the trade-offs in AI-driven 3D printing and highlight the method's capacity for ongoing improvement. By exploring future expansions, such as continuous-function printing trajectories and multi-material prints, this study shows that AI-based Gcode generation can significantly advance 3D printing quality and customization across diverse applications. © 2025 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

ChildACT: Child Action Recognition Dataset in RGB Data 20

ChildACT: Child Action Recognition Dataset in RGB Data

引用

20th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2025

作者： Sandygulova, Anara Yershov, Andrey Zhanatkyzy, Aida Telisheva, Zhansaule School of Engineering and Digital Sciences Nazarbayev University Department of Robotics and Mechatronics Astana Kazakhstan

ISBN: (纸本)9798350378931

关键词： Pattern recognition systems

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Humanoid Robot for Sign Language Interpretation

引用

SN Computer Science 2021年第3期2卷 1-17页

作者： Nihal, Ragib Amin Broti, Nawara Mahmood Deowan, Shamim Ahmed Rahman, Sejuti Department of Robotics and Mechatronics Engineering University of Dhaka Dhaka Bangladesh

Purpose: With an indisputable complexity of communication for hearing and speaking impaired people, most sign language recognition systems utilize virtual reality or onscreen robots. This paper presents the design and development of a special and low-cost humanoid robot that can perform as a sign language interpreter. To the best of our knowledge, this is the first endeavor to fabricate a humanoid robot for Bangla sign language (BdSL) and Medical signs interpretation. Methods: Considering the plethora of design criteria and balancing between rigidity and flexibility 3D models of the robotics parts are designed and 3D printed ensuring cost efficiency. With the help of modern fabrication technology, the robot is developed and assembled with proper actuators and circuitry. An image dataset is built comprising 950 images for BdSL recognition and made publicly available. We utilized the Recurrent neural network (RNN) and Convolutional neural network (CNN) for deep learning model establishment and feature extraction from video and image data. Results: The developed humanoid robot has 43 Degrees of freedom (DoF) which includes two 15 DoF hands. It can imitate 16 BdSL alphabets in sign language, can capture a video or image input in real-time from the user, and recognize 10 medical signs and 38 alphabets of BdSL. The learning model for video-based medical sign recognition achieved 87.5% test accuracy. Image-based Bangla sign language recognition achieved an overall test accuracy of 98.19% in our dataset and 93.8% in another available dataset. Conclusion: Compared to the state-of-the-art robotic systems for sign language interpretation, our approach has achieved higher kinematic characteristics, remarkable results in sign recognition, and impressive competency in sign imitation;all at almost 10 times lower cost than the state-of-the-art systems. The results are evidence that our approach is efficient and suitable in helping hearing and speaking impaired people. Moreover, thi

关键词： Convolutional neural network Humanoid robot Recognition Recurrent neural network Sign language

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：