检索结果-内蒙古大学图书馆

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Wang, Zhiao Luo, Zhong Zhu, Yunpeng Zhou, Guangze Yang, Mingyang Northeastern University School of Mechanical Engineering and Automation Shenyang110819 China Northeastern University Foshan Graduate Innovation College Foshan528312 China Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion Systems Ministry of Education of China Shenyang110819 China Queen Mary University of London School of Engineering and Material Science LondonE1 4NS United Kingdom

ISBN: (纸本)9798350325294

Rotor systems can be affected by environmental and operational factors, which often cause faults in their operations. Therefore, fault detection of rotor systems, which involves fault diagnosis and classification, is of great importance in engineering practice. Traditional fault detection methods often rely on experienced experts and are highly subjective. To address these issues, a novel automatic fault detection method is presented, using the time-frequency images of rotating machinery and the Orthogonal Matching Pursuit (OMP) algorithm. Firstly, the fault vibration signals generated by the rotor systems are transformed into time-frequency images using the wavelet transform. Secondly, a sparse image classification method using the OMP is introduced. Finally, a sparse image classification method, combined with a time-frequency image, is used to detect faults in the rotor system. The effectiveness of the proposed method is verified by detecting the misalignment and unbalance faults of rotor systems. The results show that the method is with high efficiency, and is more accurate than the traditional KNN method for rotor fault detections. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Markovian lifting and asymptotic log-Harnack inequality for stochastic Volterra integral equations

arXiv

引用

arXiv 2023年

作者： Hamaguchi, Yushi Graduate School of Engineering Science Department of Systems Innovation Osaka University 1-3 Machikaneyama Osaka Toyonaka Japan

We introduce a new framework of Markovian lifts of stochastic Volterra integral equations (SVIEs for short) with completely monotone kernels. We define the state space of the Markovian lift as a separable Hilbert space which incorporates the singularity or regularity of the kernel into the definition. We show that the solution of an SVIE is represented by the solution of a lifted stochastic evolution equation (SEE for short) defined on the Hilbert space and prove the existence, uniqueness and Markov property of the solution of the lifted SEE. Furthermore, we establish an asymptotic log-Harnack inequality and some consequent properties for the Markov semigroup associated with the Markovian lift via the asymptotic coupling *** Codes 60H20, 60H15, 60G22, 37A25 © 2023, CC BY.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Development of an Autonomous Navigation System for Small Vessels Using Remote control

Development of an Autonomous Navigation System for Small Ves...

引用

Electrical, Computer and Energy Technologies (ICECET), International Conference on

作者： Ayoung Yang Atushi Ishibashi Ryota Imai Tadasuke Furuya Graduate School of Marine Science and Technology Tokyo University of Marine Science and Technology Tokyo Japan Department of Maritime Systems Engineering Tokyo University of Marine Science and Technology Tokyo Japan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

Research on autonomous ships is being vigorously pursued globally. The International Maritime Organization (IMO) is leading a phased approach to the development of unmanned large ships. In contrast, the development of small ships is progressing independently in countries with a robust recreational maritime culture, focusing on innovative hull designs and systems. The small ship market is distinguished by high rates of used vessel purchases, a preference for cost-effectiveness, and a general lack of navigational aids compared to larger vessels. Furthermore, small ships are often operated by amateurs rather than professional navigators. These market characteristics suggest that the adoption of small autonomous ships will likely lag behind that of larger vessels. In response, our research aims to develop an economical program that enables autonomous operations in existing small ships or provides navigational assistance to inexperienced operators. Initially, we identified the necessary technology and economical equipment required to retrofit existing small ships for autonomous functionality. Subsequently, we analyzed the vessel's motion model to determine suitable control parameters. A straightforward control method was selected to facilitate user comprehension of the ship's status and interaction with the autonomous program. Our goal is to allow users to grasp the ship's motion dynamics through devices designed for autonomous navigation and to effectively implement navigational programs.

关键词： Navigation Dynamics Organizations Sensor systems Recycling Marine vehicles Autonomous vehicles Remote control Autonomous robots Logistics

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE Transactions on Instrumentation and Measurement 2024年 1-1页

作者： Wu, Jin Wang, Chaoqun Li, Chong Jiang, Yi Zhang, Chengxi Huang, Yulong Qi, Yuhua Xue, Bohuan Jiao, Jianhao Fan, Rui Zhang, Wei Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China School of Control Science and Engineering Shandong University Jinan China Department of Automation and Measurement Ocean University of China Qingdao China Department of Electrical Engineering City University of Hong Kong Hong Kong China School of Internet of Things Jiangnan University Wuxi China Department of Automation Harbin Engineering University Harbin China School of Systems Science and Engineering Sun Yat-Sen University China College of Electronics and Information Engineering Tongji University Shanghai China

Similarity transformation problems are important in robotic instrumentation and computer vision based measurements since in many cases the information of visually observed scene scale is unknown and must be restored for accurate 3-dimensional reconstruction. In existing solvers, the scale is often considered as a scalar, i.e., isotropic, which may be invalid for anisotropic-scale setups. This paper exploits some mathematical coincidences that will lead to efficient solution to these problems. Possible further applications also include hand-eye calibration and structure-from-motion. We revisit pose estimation problems within the framework of similarity transformation, the one that considers scale-stretching, rotation and translation simultaneously. Two major problems are taken into account, i.e., the scale-stretching point-cloud registration and perspective-n-points (PnP). It has been found out that these two problems are quite similar. Moreover, we solve the anisotropic-scale registration problem that is important and is a remaining unsolved one in previous literatures. To compute the globally optimal solution of these non-convex problems, algebraic solution is obtained to compute all local minima using computationally efficient methods. The designed algorithm is deployed for robotic-arm pose estimation. We also extend the algorithm for solving the problem of robust magnetometer calibration. Visual pose experiments verify the superiority of the proposed method compared with representatives, including P3P, Lambda-Twist P3P and EPnP, which can be reproduced by repository in https://***/zarathustr/APnP. IEEE

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

One-Piece 3D-Printed Legs Using Compliant Mechanisms That Produce Effective Propulsive Force for Hexapod Robot Locomotion

One-Piece 3D-Printed Legs Using Compliant Mechanisms That Pr...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Atsushi Kaneko Dai Owaki Masahiro Shimizu Takuya Umedachi Faculty of Textile Science and Technology Shinshu University Ueda Nagano Japan Department of Robotics Graduate School of Engineering Tohoku University Sendai Japan Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan

Bio-inspired soft robotic legs can be designed by utilizing continuous deformation to perform desired functions such as increasing propulsion force. Previous studies of legged robots have improved locomotion performance by simplifying animal legs as a single spring and mimicking the function of its elasticity during locomotion. This study proposes a one-piece 3D-printed leg that can kick the ground backward strongly by increasing the horizontal component of the elastic force (i.e., by designing two-dimensional elasticity). The geometry and stiffness of the leg were optimized via a combination of physical simulation and a genetic algorithm to achieve the function. Experiments using a prototype hexapod robot were conducted to compare a leg designed using the proposed method and two additional deteriorated types of legs by measuring locomotion speed. Angle of attack (angle at which the legs touch the ground) was also changed in this experiment. The experimental results indicate that designing the two-dimensional elasticity of legs can contribute to increasing propulsion force, resulting in higher locomotion speed. This study suggests that soft robotic parts with various functions, such as hands and arms, can be designed using continuous deformation and one-piece 3D-printed parts.

关键词： Legged locomotion Manufacturing processes Deformation Force Prototypes Soft robotics Elasticity

来源：评论

学校读者我要写书评

暂无评论

Comparison with Detection of Bacteria from Gram Stained Smears Images by Various Object Detectors

Comparison with Detection of Bacteria from Gram Stained Smea...

引用

IIAI International Conference on advanced Applied Informatics (IIAIAAI)

作者： Tsubasa Tanaka Kouichi Hirata Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Department of Artificial Intelligence Kyushu Institute of Technology Iizuka Japan

ISBN: (数字)9798350377903

ISBN: (纸本)9798350377910

In this paper, we detect bacteria from Gram stained smears images by the object detectors of SSD, M2Det, RT-DETR and YOLOv8. Then, we show that SSD and M2Det are not appropriate for detecting bacteria. Also we show that RT-DETR with pre-training and the variation of YOLOv8 shifting convolution layers are more appropriate to detect bacteria than standard YOLOv8.

关键词： Convolution Detectors Bacteria Informatics Standards

来源：评论

学校读者我要写书评

暂无评论

Unknown-input-proportional-differential Observer-based Event-triggered Intrusion-tolerant control for Human-in-the-loop Multi-agent systems against Unconstrained Actuator and Sensor FDIAs

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 15701-15712页

作者： Wang, Bo-Qun Guo, Xiang-Gui Wang, Jian-Liang Coutinho, Daniel Park, Ju H. University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China Harbin Institute of Technology School of Astronautics Harbin China Shunde Graduate School of University of Science and Technology Beijing Foshan528000 China University of Science and Technology Beijing School of Beijing Engineering Research Center of Industrial Spectrum Imaging School of Automation and Electrical Engineering Beijing100083 China Hangzhou Innovation Institute of Beihang University Autonomous Intelligent Systems Department Hangzhou310051 China Universidade Federal de Santa Catarina Department of Automation and Systems Florianópolis88040-900 Brazil Yeungnam University Department of Electrical Engineering Kyongsan38541 Korea Republic of

This paper investigates an intrusion-tolerant control problem for human-in-the-loop multi-agent systems (HILMASs) subjected to external disturbances and unconstrained actuator and sensor false data injection attacks (FDIAs) under directed graph. It is critical to emphasize that once a hacker gets to the control loop of the HILMAS, he can do whatever damage he wants, which means that the attack signal should be free of any constraints. Two main unconstrained attacks, i.e., unbounded FDIAs and variable-frequency FDIAs, are hard to accurately estimate and defend since the widely adopted constraints on the existing FDIAs such as the bounded or/and the bounded first-order derivative have been removed. To tackle this challenging obstacle, a novel unknown-input-proportional-differential observer (UIPDO) is developed to not only reconstruct the follower agents’ states as well as unconstrained actuator and sensor FDIAs simultaneously, but also avoid the decrease of estimation accuracy caused by measurement deviation. It should be noted that this measurement deviation may be extremely large as it is caused by unconstrained sensor FDIAs, which renders the traditional observer ineffective in providing reliable and accurate estimates of the system states and unconstrained actuator and sensor FDIAs. Then, a novel UIPDO-based intrusion-tolerant control strategy without requiring boundedness of the first-order derivatives of the FDIAs as in existing literature is proposed. Furthermore, an adaptive Zeno-free event-triggered mechanism (ETM) solely relying local state information is developed to reduce the communication burden. Finally, the numerical simulation is provided to verify the merits and effectiveness of the developed methodology. © 2004-2012 IEEE.

关键词： Signal flow graphs

来源：评论

学校读者我要写书评

暂无评论

Detecting Infectious Disease-Causing Bacteria from Gram Stained Smears Images 14

Detecting Infectious Disease-Causing Bacteria from Gram Stai...

引用

14th IIAI International Congress on advanced Applied Informatics, IIAI-AAI 2023

作者： Kashino, Ukyo Terada, Syoma Hirata, Kouichi Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Kawazu 680-4 Iizuka820-8502 Japan Bold Inc Japan Kyushu Institute of Technology Department of Artificial Intelligence Kawazu 680-4 Iizuka820-8502 Japan

ISBN: (纸本)9798350324228

In this paper, we detect 13 kinds of infectious disease-causing bacteria from Gram stained smears images. As detectors, we adopt YOLOv5 and YOLOv7, and their improvements to changing an activation function from Swish to Mish and to add a 'Squeeze-and-Excitation' block in front of the output layer. Then, we give experimental results of detecting them in Gram stained smears images and evaluate the results. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SCATTERING BELOW GROUND STATES FOR A CLASS OF systems OF NONLINEAR SCHRODINGER EQUATIONS

arXiv

引用

arXiv 2023年

作者： Masaki, Satoshi Tsukuda, Ryusei Division of Mathematical Science Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka560-8531 Japan

In this paper, we consider the scattering problem for a class of N-coupled systems of the cubic nonlinear Schrödinger equations in three space dimensions. We prove the scattering of solutions which have a mass-energy quantity less than that for the ground states. This result is previously obtained by Duyckaerts-Holmer-Roudenko for the single cubic nonlinear Schrödinger equation in three space dimensions. It turns out that the result can be extended to a wide class of N-coupled *** Codes 35Q55, 35B40 © 2023, CC BY.

关键词： Ground state

来源：评论

学校读者我要写书评

暂无评论

Learning Soft Robot Dynamics Using Differentiable Kalman Filters and Spatio-Temporal Embeddings

Learning Soft Robot Dynamics Using Differentiable Kalman Fil...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Xiao Liu Shuhei Ikemoto Yuhei Yoshimitsu Heni Ben Amor School of Computing and Augmented Intelligence Arizona State University Department of Human Intelligence Systems Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology

This paper introduces a novel approach for modeling the dynamics of soft robots, utilizing a differentiable filter architecture. The proposed approach enables end-to-end training to learn system dynamics, noise characteristics, and temporal behavior of the robot. A novel spatio-temporal embedding process is discussed to handle observations with varying sensor placements and sampling frequencies. The efficacy of this approach is demonstrated on a tensegrity robot arm by learning end-effector dynamics from demonstrations with complex bending motions. The model is proven to be robust against missing modalities, diverse sensor placement, and varying sampling rates. Additionally, the proposed framework is shown to identify physical interactions with humans during motion. The utilization of a differentiable filter presents a novel solution to the difficulties of modeling soft robot dynamics. Our approach shows substantial improvement in accuracy compared to state-of-the-art filtering methods, with at least a 24% reduction in mean absolute error (MAE) observed. Furthermore, the predicted end-effector positions show an average MAE of 25.77mm from the ground truth, highlighting the advantage of our approach. The code is available at https://***/ir-lab/soft_robot_DEnKF.

关键词：

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：