检索结果-内蒙古大学图书馆

14th IEEE International Conference on Cyber Technology in automation, Control, and Intelligent Systems, CYBER 2024

作者： Zhuo, Fanbo Tang, Fengzhen Shenyang Institute of Automation The State Key Laboratory of Robotics Shenyang China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China The University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331506056

This paper presents an approach for optimizing frequency bands in motor imagery (MI) classification using Particle Swarm Optimization (PSO) combined with the Generalized learning Riemannian space quantization (GLRSQ) classifier. The proposed method leverages the class distance metric to assess the distribution of EEG signals in the Symmetric Positive Definite (SPD) manifold. Experimental results on the BCI IIa dataset demonstrate improved classification accuracy and Kappa values compared to baseline method. The study highlights the effectiveness of opti-mizing frequency bands on the Riemannian manifold for enhancing MI classification performance. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

FluidFM for single-cell biophysics

引用

Nano Research 2022年第2期15卷 773-786页

作者： Mi Li Lianqing Liu Tomaso Zambelli Laboratory of Biosensors and Bioelectronics Institute for Biomedical EngineeringETH ZurichZurich 8092Switzerland State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China

Fluidic force microscopy(FluidFM),which combines atomic force microscopy(AFM)with microchanneled cantilevers connected to a pressure controller,Is a technique allowing the realization of force-sensitive nanopipette under aqueous *** has unique advantages in simultaneous three-dimensional manipulations and mechanical measurements of biological specimens at the micro-/*** the past decade,FluidFM has shown its potential in biophysical assays particularly in the investigations at single-cell level,offering novel possibilities for discovering the underlying mechanisms guiding life ***,we review the utilization of FluidFM to address biomechanical and biophysical issues in the life ***,the fundamentals of FluidFM are ***,the applications of FluidFM for biophysics at single-cell level are surveyed from several facets,including single-cell manipulations,single-cell force spectroscopy,and single-cell ***,the challenges and perspectives for future progressions are provided.

关键词： atomic force microscopy fluidic force microscopy single-cell manipulation single-cell force spectroscopy single-cell electrophysiology

来源：评论

学校读者我要写书评

暂无评论

Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network

引用

Petroleum Science 2023年第2期20卷 1142-1154页

作者： Yun-Peng He Chuan-Zhi Zang Peng Zeng Ming-Xin Wang Qing-Wei Dong Guang-Xi Wan Xiao-Ting Dong State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyangLiaoning 110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyangLiaoning 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyangLiaoning 110169China University of Chinese Academy of Sciences Beijing100049China Shenyang University of Technology ShenyangLiaoning 110870China School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyangLiaoning 110159China

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

关键词： Few-shot learning Indicator diagram Meta-learning Soft thresholding Sucker-rod pumping system Time–frequency signature Working condition recognition

来源：评论

学校读者我要写书评

暂无评论

A policy gradient algorithm integrating long and short-term rewards for soft continuum arm control

引用

Science China(Technological Sciences) 2022年第10期65卷 2409-2419页

作者： DONG Xiang ZHANG Jing CHENG Long XU WenJun SU Hang MEI Tao School of Electrical Engineering and Automation Anhui UniversityHefei 230601China State Key Laboratory for Control and Management of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Robotics Research Center Peng Cheng LaboratoryShenzhen 518055China

The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous control problems, which can learn an effective control policy with an unknown system model. However, it is often affected by the high sample complexity and requires huge amounts of data to train, which limits its effectiveness in soft arm control. An improved policy gradient method, policy gradient integrating long and short-term rewards denoted as PGLS, is proposed in this paper to overcome this issue. The shortterm rewards provide more dynamic-aware exploration directions for policy learning and improve the exploration efficiency of the algorithm. PGLS can be integrated into current policy gradient algorithms, such as deep deterministic policy gradient(DDPG). The overall control framework is realized and demonstrated in a dynamics simulation environment. Simulation results show that this approach can effectively control the soft arm to reach and track the targets. Compared with DDPG and other model-free reinforcement learning algorithms, the proposed PGLS algorithm has a great improvement in convergence speed and performance. In addition, a fluid-driven soft manipulator is designed and fabricated in this paper, which can verify the proposed PGLS algorithm in real experiments in the future.

关键词： soft arm control Cosserat rod deep reinforcement learning policy gradient algorithm high sample complexity

来源：评论

学校读者我要写书评

暂无评论

The System of Coordinated Operation of Two Underwater Vehicles in a Complex Environment

The System of Coordinated Operation of Two Underwater Vehicl...

引用

2023 International Conference on Ocean Studies, ICOS 2023

作者： Filaretov, Vladimir Katsurin, Alexey Institute of Automation and Control Processes Feb Ras Vladivostok State University Laboratory of Robotic Systems Laboratory of Automation and Robotics Vladivostok Russia Far Eastern Federal University M.D. Ageev Institute for Marine Technology Problems Feb Ras Laboratory of Intelligent Information Systems for Marine Robots Department of Automation and Robotics Vladivostok Russia

ISBN: (纸本)9798350382457

The paper discusses methods of coordinated operation of two autonomous underwater vehicles, one of which is equipped with a multi-link manipulator and a vision system, and the second - auxiliary - only a vision system. These methods ensure the joint operation of two autonomous underwater vehicles both in the mode of semi-automatic positional remote control, and in the mode of automatic execution of operations with various objects. At the same time, work is considered in situations when the vision system of the main underwater vehicle does not allow observing the object of work, which is nevertheless located in the working area of the manipulator. In this case, the auxiliary inspection underwater vehicle with its own vision system is used to monitor the object. In the semi-automatic remote control mode, the manipulator automatically takes into account the current spatial orientation of the optical axis of the vision system of the inspection underwater vehicle, as well as the spatial orientations of both underwater vehicles at yaw angles in the absolute coordinate system. And in automatic mode, an accurate transfer of the spatial location and orientation of the object, which are determined using the vision system of the inspection underwater vehicle, is additionally provided to the associated coordinate system of the main underwater vehicle. It is possible to identify and eliminate errors that occur during the operation of the vision system and navigation systems of both underwater vehicles. The results of experimental studies have confirmed the operability of the proposed methods. © 2023 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

An adaptive Kalman filter for physiological tremor suppression in robot-assisted minimally invasive surgery

An adaptive Kalman filter for physiological tremor suppressi...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Yang, Daolong Jiang, Li Xu, Kun Robotics Institute of School of Mechanical Engineering and Automation Beijing100191 China Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin150008 China

ISBN: (纸本)9798350325706

Physiological tremors of surgeons' hands bring vibration to the tip of surgical instruments, which may severely damage the accuracy of surgical procedures and even put patients' lives at risk. Thus robot-assisted surgery using a teleoperation system was introduced to solve this problem. Many filter algorithms were implemented into the robot-assisted surgery system to suppress the inevitable tremors, but always overlooking the traits of hand motion. An innovation/residual-based floating forgetting-factor adaptive Kalman filter (IFFAKF) is proposed to address this problem. A floating forgetting-factor is brought into the innovation/residual-based adaptive estimation algorithm to adjust the process noise covariance (Q) and measurement noise covariance (R) of the system, thus generating estimation of voluntary hand movement and suppressing the vibration at the tip of the surgical instrument caused by the physiological tremor during surgeries. The proposed filter has been contrasted with various filters in simulations and experiments. The results confirm that the proposed filter has obvious advantages in terms of time delay, estimation error, and tremor suppression performance. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Model Retrieval Technology Based on Audio Recognition 1

引用

13th International Workshop of Advanced Manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Wu, Junyang Chen, Kunpeng School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

At present, the number of 3D models in machinery industry is increasing, and the commonly used keyword retrieval methods need a lot of manual labeling work, and many complex 3D models are difficult to describe accurately in words. This paper proposes a 3D model retrieval algorithm based on audio recognition, which can quickly and effectively find 3D models in massive models. This paper takes the 3D model of STL file format as the research object, and its main work is as follows: Firstly, a new rotation normalization algorithm for 3D models is proposed. Then a point density control scheme of STL file based on unit volume is proposed. After that, an audio fingerprint extraction algorithm for 3D model is proposed. Finally,the original speed matching method and the neighborhood matching method are proposed to calculate the similarity between models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Wind Turbine Maintenance Based on Data-Physical Fusion Modeling 4

Research on Wind Turbine Maintenance Based on Data-Physical ...

引用

4th International Conference on Green Energy, Environment and Sustainable Development, GEESD 2023

作者： Wang, Weilong Cai, Hongxia Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai China

ISBN: (纸本)9781643684260

With the large-scale application of wind power generation technology, its maintenance and repair have received extensive attention. Since wind turbines are complex equipment coupled with multiple fields, the faults are sudden and diverse, and the fault samples are scattered. At the same time, wind turbine operation data has non-linear and unstable time-series characteristics. Single data-driven and physics-driven methods can no longer well meet the current wind turbine maintenance needs. This paper proposes a wind turbine maintenance method with data-mechanism fusion modeling. A data-driven algorithm considering the timeseries characteristics of wind turbine operation data is designed. The fusion strategy for updating the boundary parameters of the machine physical model is proposed. Simulation calculations are completed using a fluid-solid coupling model. Simulation results optimize the wind turbine maintenance strategy to guide wind farm maintenance activities. © 2023 IOS Press BV. All rights reserved.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Research on Structural Topology Optimization Based on SIMP-BESO Coupling Algorithm 1

引用

13th International Workshop of Advanced Manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Sun, Yi Tan, Youquan School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

Structure topology optimization technology plays an increasingly important role in mechanical engineering, as it allows high quality structures to be obtained while meeting the demands for lightweight structures. Using topology optimization makes it possible to distribute the material in a given area appropriately to minimize the weight of the structure while meeting the performance requirements. And it reduces the structural design cycle and gives engineers more structural options. This paper takes the SIMP algorithm as the object of study and proposes a SIMP-BESO coupling algorithm for solving the grayscale problem in the algorithm. This algorithm is based on the concept of the termination factor for SIMP, linking the optimization process to the number of iterations. Dynamic movement factor makes the iterative process "fast then slow" to achieve the phenomenon of removing the grayscale elements in structure, and structures with smaller flexibility and larger stiffness can be obtained. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Shape optimization

来源：评论

学校读者我要写书评

暂无评论

An Improved Plant Disease Detection Method Based on YOLOv5 15

An Improved Plant Disease Detection Method Based on YOLOv5

引用

15th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2023

作者： Cai, Hongxia Jiang, Jiaying School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai China

ISBN: (纸本)9798350326178

To overcome the challenges of weak generalization, high false detections, and missed targets in multi-scale plant disease detection under complex scenarios, this paper proposes an enhanced method based on YOLOv5. The method improves YOLOv5 by incorporating a multi-scale feature fusion module, an attention mechanism, and optimizing the loss function to accurately locate and classify plant disease targets. Experimental results show significant improvements over the original YOLOv5 model in terms of mAP, precision, and recall, with enhancements of 3.99%, 1.56%, and 1.27% respectively. Additionally, the proposed method outperforms other commonly used models. This study provides an efficient and accurate approach for plant disease detection, enabling real-time monitoring of plant health and precise disease control in plant factories. © 2023 IEEE.

关键词： Object detection

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：