检索结果-内蒙古大学图书馆

Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review

引用

Operations Research Forum 2024年第3期5卷 58页

作者： Wei, Li Solihin, Mahmud Iwan Saruchi, Sarah ‘Atifah Astuti, Winda Hong, Lim Wei Kit, Ang Chun School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Guangxi 545006 China Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur 56000 Malaysia Faculty of Manufacturing and Mechatronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Computer Engineering Department Automotive and Robotics Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

High-precision cylindrical parts are critical components across various industries including aerospace, automotive, and manufacturing. Since these parts play a pivotal role in the performance and safety of the systems they are integrated into, they are often subject to stringent quality control measures. Defects on the interior and exterior wall surfaces of these cylindrical parts can severely undermine their function, leading to degraded performance, increased wear, and even catastrophic failures in extreme cases. This article aims to comprehensively summarize the task definition, challenges, mainstream methods, public datasets, evaluation metrics, and other aspects of surface defect detection for high-precision cylindrical parts, in order to help researchers quickly grasp this field. Specifically, the background and characteristics of industrial defect detection are first introduced. Owing to the unique geometric features of cylindrical part surfaces, algorithms and equipment for image data acquisition used in surface defect detection are elaborated in detail. This article presents an extensive overview of state-of-the-art surface defect detection techniques designed for high-precision cylindrical components, all rooted in deep learning. The methods are systematically classified into three main categories: fully supervised, unsupervised, and alternative approaches, based on their data labeling strategies. Additionally, the paper conducts a comprehensive analysis within each category, shedding light on their unique strengths, limitations, and practical use cases. Concluding the discussion, the paper provides insights into future development trends and potential research directions in this field that will lead to manufacturing innovation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection Computer vision Deep learning Defect detection High-precision cylindrical parts Image processing Optical illumination

来源：评论

学校读者我要写书评

暂无评论

Exploring Robot-Assisted Optical Coherence Elastography for Surgical Palpation

Exploring Robot-Assisted Optical Coherence Elastography for ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yeonhee Chang Elan Z. Ahronovich Nabil Simaan Cheol Song Department of Robotics and Mechatronics Engineering DGIST Daegu South Korea Department of Mechanical Engineering Vanderbilt University Nashville TN USA

Optical Coherence Elastography (OCE) is a method that discerns local tissue stiffness using optical information. This method has recently been explored for laryngeal cancer tumor margin detection but has not been widely deployed clinically. Part of the challenge hindering such clinical deployment is the need for controlled high-precision mechanical probing of the tissue. This paper explores the concept of robot-assisted optical coherence elastography(OCE) and presents a preliminary system integration used to demonstrate the approach for stiffness mapping and discerning tumor margins. The approach is demonstrated on a custom Cartesian stage robot, and a custom-built OCE system comprised of an 830 nm broad-band laser with a vector-analysis method for phase gradient estimation and strain imaging. The paper illustrates one of the advantages of robot-controlled probing in terms of increasing the accuracy of the OCE system in a large range of displacement and strain. By leveraging motion information from the robot, online re-calibration of the OCE strain map may be achieved, thereby reducing OCE errors. After calibration, it is shown that the error in estimating the local Young's modulus is 0.485% in the silicon phantom and 0.531% in the agar phantom. These results suggest that future integration of optical coherence tomography(OCT) in clinically deployable robots may offer advantages in enabling local stiffness map estimation using OCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Multi-bending Flexible Manipulator for Gastrointestinal Surgery

Design of a Multi-bending Flexible Manipulator for Gastroint...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Hyojae Park Minho Hwang Department of Robotics and Mechatronics Engineering DGIST Daegu Korea

Unlike the existing rigid surgical robots, flexible endoscopic robotic platforms have been actively researched owing to the advantages of high lesion accessibility and scar-free. However, there still exists difficult-to-access areas such as cardia and fundus in the gastrointestinal tract due to the limited Degrees of Freedom (DoFs) of the manipulator. In this study, we propose a multi-bending endoscopic manipulator to improve accessibility to the gastric region in any position and orientation. We perform mechanism design, kinematics, and cable-control analysis of the proposed manipulator. Finally, we verify the multi-bending motion in the simulated flexible pathway.

关键词： Medical robotics Automation Surgery Kinematics Manipulators Control systems Gastrointestinal tract

来源：评论

学校读者我要写书评

暂无评论

PROSPECTS ON APPLICATION OF ELASTIC METAMATERIALS IN ACOUSTIC EMISSION SENSING

e-Journal of Nondestructive Testing

引用

e-Journal of Nondestructive Testing 2023年第1期28卷

作者： Klimek, Zbigniew Paćko, Pawel Cracow branch Warsaw Poland AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Robotics and Mechatronics Krakow Poland

This paper discusses challenges, limitations and problems arising in currently employed acoustic emission testing systems, sensors and signal processing algorithms. Main factors influencing and compromising accuracy and reliability of the classically used methods are briefly analyzed. Next, metamaterials and their dynamic properties are outlined with the aim and focus on their potential in manipulating energy flow. Several applications of metamaterials in acoustic emission are presented that indicate their potential in acoustic emission. Finally, possibilities of designing a new type of sensor for acoustic emission using metamaterials is discussed. As a consequence, it is expected to increase sensitivity and accuracy of source localization with smaller number of sensors used during measurements. © 2023 The Authors.

关键词： Metamaterials

来源：评论

学校读者我要写书评

暂无评论

Modelling of Machining Time and its Uncertainty in Micro Electrical Discharge Machining Process Using RSM

Modelling of Machining Time and its Uncertainty in Micro Ele...

引用

International Conference on mechatronics (ICOM)

作者： Mohammad Mainul Hasan Tanveer Saleh Ali Sophian Autonomous Systems and Robotics Research Unit (ASSRU) Department of Mechatronics Engineering International Islamic University Malaysia Kuala Lumpur Malaysia

ISBN: (数字)9798350349788

ISBN: (纸本)9798350349795

In modern manufacturing processes, precision and efficiency are paramount, particularly in a stochastic method such as Micro Electrical Discharge Machining (μEDM). With its ability to fabricate intricate geometries in hard and difficult-to-machine materials, μEDM has become indispensable in various industries. However, optimising machining time while ensuring reliability and accuracy remains a significant challenge that often relies on the intuition and experience of machinists. In response, this paper presents a comprehensive study on the modelling of machining time (MT) and also its associated uncertainty characterised by the standard deviation (SD) in the μEDM process using Response Surface Methodology (RSM). The study utilises experimental data generated through the I -optimal design of experiment technique (DOE) to develop quadratic equations for the MT Mean and SD MT models. The input factors for the models include capacitance, voltage, feed rate, tool speed, tool diameter, workpiece thickness, and workpiece materials defined by thermal conductivity, melting point, and electrical resistivity. The adequacy of both models was assessed based on ANOV A and fit statistics, demonstrating their effectiveness. Additionally, the mean percentage accuracies of the MT Mean and SD MT models are evaluated as 74.5% and 58% for the train set and 86.8% and 82.1 % for the test set, respectively. By leveraging RSM techniques, this research aims to provide insights into the complex relationships between machining parameters and the resulting machining time and uncertainty, facilitating enhanced process μEDM control and performance optimisatio n.

关键词： Training Adaptation models Uncertainty Accuracy Estimation Machining Predictive models

来源：评论

学校读者我要写书评

暂无评论

Human Hand Gesture Recognition System Using Body Sensor Network 4

Human Hand Gesture Recognition System Using Body Sensor Netw...

引用

4th International Conference on robotics and Automation in Industry, ICRAI 2021

作者： Maheen, Asra Bin Shahzad, Moosa Asif, M. Usama Ahmad, Syed Fasih Zafar, Saqib Maqbool, H. Farhan Usman, Muhammad Arshad, Hira Department of Mechanical Mechatronics And Manufacturing Engineering Faisalabad Pakistan Human-Centered Robotics Lab National Center of Robotics And Automation Lahore Pakistan Pakistan Engineering Council Islamabad Pakistan Department of Mechanical Mechatronics And Manufacturing Engineering Faisalabad Pakistan

ISBN: (纸本)9781665423434

Wearable technology has gained massive popularity for applications in healthcare in recent years. Body sensor network (BSN) includes wearable sensors such as Myoware muscle sensor that can capture electromyography (EMG) signal from human muscles during a movement. This study involves the control of a 3d prosthetic hand using EMG data of basic hand gestures from healthy subjects and operating the prosthetic hand with this classified data. Artificial Neural Networks (ANN) are biologically inspired computational networks which help to build predictive models from large databases. Backpropagation combined with feedforward ANN is used to classify data here. Classification results showed an accuracy of about 91% for four-hand gestures - hand closed, hand open, pointing index finger, and pinch motion. The BSN-based prosthetic hand can facilitate rehabilitation of amputees, perform surgery using recorded EMG data from a surgeon's hands and reduce industrial manpower in the future. © 2021 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved Efficiency of Weakly Coupled Wireless High-Power Transfer Systems by Loss-Separation Strategy

引用

International Journal of Circuit Theory and Applications 2025年

作者： The Nguyen, Hoach Al-Sumaiti, Ameena Saad Alhassan, Ahmad Bala Do, Ton Duc Smart OR Lab Advanced Power and Energy Center Department of Electrical Engineering Khalifa University Abu Dhabi United Arab Emirates Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan

In the equivalent T-model of the loosely coupled transformers, the small mutual inductance can lead to higher conducting currents, which cause high losses in the primary circuit and significantly reduce the overall transfer efficiency under weak-coupling states. To overcome this challenge, this paper proposes a strategy to separate the primary loss components from the weak-coupling stage. In the proposed strategy, a gyrator in the form of a double-resonance T-block is added just before the weak-coupling stage to improve the overall efficiency. Then, the strategy is realized by various topologies such as compensating circuits, added coils, isolated transformers, and integrated-/split- inductors/coils. Also, the optimized designs and component selection for resonance and the mathematical derivation for optimal load resistances were investigated. ANSYS comparative analyses of the topologies are presented by considering practical aspects, including component designs, power flows, transfer efficiency, resonance frequency shifting, and optimal loads. Finally, the analyses were validated using the fabricated experimental setups and demonstrated an efficiency improvement of about 5% for a case with a coupling factor of 0.1. The proposed strategy offers suggestions for industrial designs of high-power wireless battery charging systems using resonant inductive coils. © 2025 John Wiley & Sons Ltd.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Shape-adaptive stiffness variable soft gripper using porous structure

引用

Journal of Institute of Control, robotics and Systems 2021年第3期27卷 238-246页

作者： Lee, Jae-Young Cho, Seong J. Seo, Yong-Sin Park, Chan-Hun Park, Dong-Il Kim, Byeung-In Kim, Hwi-Su Song, Sung-Hyuk Department of Robotics & Mechatronics Korea Institute of Machinery & Materials Daejeon Korea Republic of School of Mechanical Engineering Chungnam National University Daejeon Korea Republic of

Robotic grippers are essential components used in robots to perform certain tasks. Effective gripping capabilities are important for industrial and service robots. However, the parallel-type gripper, which is one of the most widely used robotic grippers, has limitations in terms of the objects that it can handle as well as applying the correct handling force, especially when handling fragile objects. Hence, a soft gripper fabricated using soft materials is proposed as a new alternative, with the advantage of preventing injuries when human-robot interaction is required. However, the limited holding force and uncontrollable movement of a soft gripper, due to its softness, could limit its use in real-life conditions. Therefore, in this article, we propose a shape-adaptive tip using a variable stiffness mechanism. To decrease the initial stiffness of the gripper tip, the reticulated polyurethane foam structure was embedded in the tip as the soft supporting layer to support the external force. The flexible mesh structure was applied as the jamming layer to change the stiffness of the tip. The prototype of the gripping system was tested, and the gripper could transfer the grape effectively without damage using the jamming mechanism. © ICROS 2021.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Compositional Construction of Barrier Functions for Switched Impulsive Systems 63

Compositional Construction of Barrier Functions for Switched...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Bieker, Katharina Kussaba, Hugo Scholl, Philipp Jung, Jaesug Swikir, Abdalla Haddadin, Sami Kutyniok, Gitta Ludwig-Maximilians-Universität Department of Mathematics München Germany Department of Electrical and Electronic Engineering Albaida Libya Aalto University Finland Mbuzai Abu Dhabi United Arab Emirates Germany Germany University of Tromso Department of Physics and Technology Norway Institute of Robotics and Mechatronics DLR-German Aerospace Center Germany

ISBN: (纸本)9798350316339

Many systems occurring in real-world applications, such as controlling the motions of robots or modeling the spread of diseases, are switched impulsive systems. To ensure that the system state stays in a safe region (e.g., to avoid collisions with obstacles), barrier functions are widely utilized. As the system dimension increases, deriving suitable barrier functions becomes extremely complex. Fortunately, many systems consist of multiple subsystems, such as different areas where the disease occurs. In this work, we present sufficient conditions for interconnected switched impulsive systems to maintain safety by constructing local barrier functions for the individual subsystems instead of a global one, allowing for much easier and more efficient derivation. To validate our results, we numerically demonstrate its effectiveness using an epidemiological model. © 2024 IEEE.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Static Characteristics of Zero-Current-Switching Quasi-Resonant Boost Converter under Variation of Resonant Circuit and Load Parameters 8

Static Characteristics of Zero-Current-Switching Quasi-Reson...

引用

8th IEEE International Conference on Energy Smart Systems, ESS 2022

作者： Dymerets, Andrii V. Gorodny, Alexey N. Yershov, Roman D. Revko, Anatoliy S. Stepenko, Serhii A. Chernihiv Polytechnic National University Electronics Automation Robotics and Mechatronics Department Chernihiv Ukraine Chernihiv Polytechnic National University Electrical Engineering Information and Measurement Technologies Department Chernihiv Ukraine

ISBN: (数字)9798350334418

ISBN: (纸本)9798350399202

The impact of resonant circuit parameters on static characteristics of a half-wave boost quasi-resonant converter is investigated. The dependences of the converter voltage maximum conversion ratio under variation of resonant circuit time constant and characteristic impedance with different load impedance values are obtained by dint of multi-factor numeric simulation. The dependences of the ratio between the transistor current peak value and input current rms value under variation of resonant circuit time constant and characteristic impedance with different load impedance values are also obtained. Approximated laws described above dependencies are fitted. Results allow determining the allowable values for resonant inductance and capacitance, as well as the load impedance to keep within a zero-current-switching mode. © 2022 IEEE.

关键词： Resonant circuits

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：