检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Shuaiyu Jin Lei Sun School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology

ISBN: (纸本)9781665431293

Ship detection is very important in improving navigation *** recent years,YOLO series object detection algorithm has achieved remarkable *** the representative work of the YOLO series,version 5（YOLOv5） is widely used in target recognition tasks for its high recognition accuracy and lightweight model. However,the sea scene background is complex and variable,which is greatly affected by extreme weather such as light,rain and *** this reason,an improved YOLOv5s algorithm with attention mechanism is proposed to enhance the feature fusion ***,the feature map extracted from different layers was aligned on the number of ***,different weight coefficients were added to the corresponding feature ***,the experimental results demonstrate that the improved algorithm obtain 3.1% higher mAP.5 than YOLOv5s on MS-COCO *** the meanwhile,the performance on BOAT data is also competitive in terms of quality.

关键词： Ship Detection Convolution Neural Network Attention Mechanism YOLOv5

来源：评论

学校读者我要写书评

暂无评论

Grade quantification of Parkinson's disease based on principal component analysis

Grade quantification of Parkinson's disease based on princip...

引用

2021 China Automation Congress, CAC 2021

作者： Zhou, Long Tong, Jigang Dong, Enzeng Zhu, Lin Zhang, Jiachen Tianjin Key Laboratory For Control Theory and Applications in Complicated Systems Tianjin University of Technology Tianjin300384 China China North Industries Group 210 Reseasrch Institute Beijing China

ISBN: (纸本)9781665426473

Parkinson's disease is a common neurodegenerative disease, which seriously affects the life of patients. Whether there is an objective and reliable method to classify and identify the disease grade is of great significance in the clinical diagnosis of Parkinson's disease. In this paper, principal component analysis was used to comprehensively evaluate the degree of Parkinson's disease of 28 randomly selected subjects, establish a comprehensive scoring model of Parkinson's disease degree, and fit it according to HY grade, so as to realize the quantification of Parkinson's disease grade. Based on the data of vertical ground reaction force, 12 gait features with strong correlation are calculated as the main features to establish the scoring model. The validity of the model is verified by predicting the HY grade of another 12 subjects in the randomly selected data set. The results show that the prediction accuracy is 83.3%, which can effectively predict the Parkinson's disease level of subjects. © 2021 IEEE

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

PID control for Aeroengine Based on Sparrow Search Algorithm

PID Control for Aeroengine Based on Sparrow Search Algorithm

引用

2021 China Automation Congress, CAC 2021

作者： Xu, Liang Wang, Hao Liu, Ying Xue, Wei Li, Ningning Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China National Key Laboratory for Complex Systems Simulation Beijing China BeijingAerospace Propulsion Institute Beijing China

ISBN: (纸本)9781665426473

To address the problem of aeroengine PID parameter optimization and tuning, this work employs the excellent performance of the sparrow search algorithm (SSA) with high convergence accuracy and fast convergence speed to propose a self-tuning PID control method (SSA-PID) for aeroengine parameters. Considering that the oil supply output by the actuator may have a substantial overshoot, the proposed technique adds a penalty mechanism for the overshoot at the output, designs and improves the fitness function weighted by performance indicators, and effectively avoids the possible excessive overshoot and sharp oil supply phenomenon of the engine oil supply. The SSA-PID simulates and verifies the mathematical models of the turbofan engine ' s steady-state operating points on the ground and at high altitudes. The results show that the SSA-PID control method has better parameter tuning and optimization effects, a faster speed step response, and generates a fuel supply that does not have a large overshoot, thereby proving its effectiveness and feasibility. © 2021 IEEE

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Research on Measuring Method of Self-Mixing Interference Magnetic Field Based on Faraday Effect

SSRN

引用

SSRN 2024年

作者： Zhao, Yan Sun, Wenqiang Wang, Haipeng Ma, Shihui School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China Institute of Functional Crystals and Tianjin Key Laboratory of Functional Crystal Materials Tianjin University of Technology Tianjin300384 China

In this paper, the magnetic field measurement method of laser self-mixing interference based on the Faraday effect is proposed. The polarization plane of the linearly polarized light is changed by the terbium gallium garnet crystal with the influence of the magnetic field. The light modulated by the magnetic field reentered into the laser cavity through the Brewster window and formed the self-mixing effect. The theoretical analysis of the self-mixing interference model based on the Faraday effect is conducted, which explains essential features of the experimental results. The magnetic field is measured by the peak-to-peak value of self-mixing interference signal. The experimental results show that the relative error of the magnetic field measurement is within ±1.6%. The measurement method has the advantage of simple and compact structure with strong anti-interference ability. © 2024, The Authors. All rights reserved.

关键词： Faraday effect

来源：评论

学校读者我要写书评

暂无评论

Study on a Two-layer Path Planning Method of Spherical Multi-robot 20

Study on a Two-layer Path Planning Method of Spherical Multi...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Li, Chenqi Guo, Jian Guo, Shuxiang Fu, Qiang Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory BinshuiXidao Extension 391 Tianjin300384 China Shenzhen Institute of Advanced Biomedical Robot Co. Ltd. No.12 Ganli Sixth Road Jihua Street Longgang District Shenzhen518100 China Key Laboratory of Convergence Medical Engineering Systems and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science Beijing Institute of Technology No.5 Zhongguancun South Street Beijing100081 China

ISBN: (纸本)9798350320831

A path planning method based on a two-layer coordination system is proposed for the compatibility requirement of path planning global optimum and local coordination in a spherical multi-robot system. In the first layer of the algorithm, the global path quality is improved by proposing a nonlinear sine factor and a sparrow search algorithm with improved levy flight strategy to plan the global collision-free optimal path for each robot. In the second layer, a rolling window method is used to determine the possible collision positions of each robot in the system, and a priority-based conflict resolution strategy is proposed to complete the local coordination of the path near the corresponding position. The experimental results show that the path planning method enables the robots to drive along the global optimal path, but still can carry out flexible and orderly local path coordination, which effectively improves the path planning performance of the system. © 2023 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

FGNet: Faster Robotic Grasp Detection Network

FGNet: Faster Robotic Grasp Detection Network

引用

IEEE International Conference on Mechatronics and Automation

作者： Bangqiang Cheng Lei Sun School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In unstructured environments, achieving fast and accurate object detection and successful grasping presents a significant challenge. Current grasping detection networks primarily focus on reducing the network's floating point operations (FLOPs) to improve network speed. However, we found that the effectiveness of this method is not particularly significant. To address this issue, we employed partial convolution (PConv) in place of regular convolutions to significantly enhance the network's detection speed. Additionally, we implemented a parallel structure for the network to fuse low-level and high-level features, reducing the loss of detail information during the decoding process. Our proposed faster grasp detection network (FGNet) achieved a performance of 96.74% (ow) and 98.66% (iw) on the Cornell dataset, with a detection speed of only 11ms. The grasping success rate was 96.5% in single-object scenarios and 92% in cluttered grasping scenarios.

关键词： Training Accuracy Mechatronics Convolution Fuses Grasping Object detection

来源：评论

学校读者我要写书评

暂无评论

Time parameter measurement system for alternating current filament relay of railway signal lamp 4

Time parameter measurement system for alternating current fi...

引用

4th International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2021

作者： Zhang, Baofeng Pang, Tao Li, Zhiwei Zhu, Junchao Tianjin University of Technology Tianjin Key Lab. for Control Theory Application Complicated Systems and Biomedical Robot Laboratory Tianjin China

ISBN: (纸本)9781665415965

Aiming at the tedious maintenance work of ac filament conversion relay of railway signal lamp unit, this paper designs a new online detection device for relay working state. By switching relay paths and relying on the collected data, contact voltage image fitting is performed during the conversion process, and time parameters are extracted by different method to obtain the conversion time. Compared with the traditional detection device, the operation and detection time of the device is short, flexible and convenient. © 2021 IEEE.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Path Optimization Method for the Spherical Underwater Robot in Unknown Environment

引用

Journal of Bionic Engineering 2020年第5期17卷 944-958页

作者： Jian Guo Chunying Li Shuxiang Guo Tianjin Key Laboratory for Control Theory&Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of TechnologyTianjin 300384China Department of Intelligent Mechanical Systems Engineering Faculty of EngineeringKagawa UniversityTakamatsu 761-0396Japan

One of the major respects of the autonomous capability of underwater robots in unknown environment is to be capable of global path planning and obstacles avoiding when encountering abrupt *** the Spherical Underwater Robot(SUR)to fulfill autonomous task execution,this paper proposed a novel fuzzy control method that incorporates multi-sensor technology to guide underwater robots in unknown *** attain the objective,a SUR we designed is used to design the *** to its kinematic model,the safety distance was calculated and sensors(US1000-21 A)were *** novel fuzzy control method was then explored for robot's path planning in an unknown environment through *** simulation results demonstrate the capability of the proposed method to guide the robot,and to generate a safe and smooth trajectory in an unknown *** effectiveness of the proposed method was further verified through experiments with a SUR in a real *** real environment experiments by using the novel fuzzy control method were compared with the basic control *** experimental results show that in unknown environments,the proposed method improves the execution efficiency and flexibility of the SUR.

关键词： path planning fuzzy control spherical underwater robot unknown environment

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Laser SLAM Algorithm Based on RBPF improved resampling technology 17

Optimal Design of Laser SLAM Algorithm Based on RBPF improve...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Wang, Hainan Ni, Jianyun Qi, Yong Zhao, Mingyang Tianjin University of Technology Tianjin Key Laboratory for Control Theory Applications in Complicated Systems China

ISBN: (纸本)9781728164151

Simultaneous Localization and Mapping (SLAM) has always been a fundamental and central issue for mobile robots. At present, Rao-Blackwellized particle filter (RBPF) is a practical method to solve the Simultaneous Localization and Mapping of robots. In order to improve the problem of lack of particles and lack of diversity in the traditional RBPF algorithm, an optimized laser SLAM algorithm is proposed. Minimum sampling-variance(MSV) resampling is used to improve the original resampling method, and improve the proposal distribution to make it closer to the target distribution. In this paper, simulation experiments are carried out on Matlab and ROS platforms, and the experimental results prove that the improved algorithm can effectively improve the positioning effect and the quality of mapping. © 2020 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification of Riemannian Tangent Spaces Based on MI-BCI

Machine Learning Classification of Riemannian Tangent Spaces...

引用

IEEE International Conference on Mechatronics and Automation

作者： Chunli Zhao Enzeng Dong Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology 391 Binshui West Road Tianjin China Department of Electrical Engineering Tshwane University of Technology Pretoria South Africa

Motor imagery brain-computer interfaces (BCIs) have been extensively used in stroke rehabilitation, particularly in China where stroke incidence is high. The application of BCI to control prostheses and robotic arms has shown promising results in improving the quality of life for stroke patients. However, a major challenge in this field is improving the accuracy of motor imagery (MI) classification. Several previous studies have reported that stroke patients exhibit atypical patterns of even-trelated desynchronization (ERD) and event-related synchronization (ERS) activation during motor imagery (MI) tasks. It has been suggested that the brain regions affected by stroke may show reduced excitability and relative insensitivity to external interference compared to those of healthy individuals. Therefore, this study proposes that the classification accuracy of stroke patients in the same MI task would be higher compared to that of healthy volunteers. In this study, we employed a feature extraction algorithm that combines the Filter Bank Common Spatial Pattern (FBCSP) and Riemann geometric mean distance methods to compare the classification accuracy of five different classifiers, with the objective of identifying the most suitable classifier for our analysis. The obtained results revealed that the K-Nearest Neighbors (KNN) classifier yielded the highest accuracy, reaching 87.5% for stroke patients and 85% for healthy volunteers, respectively. In addition to accuracy, we also utilized Kappa values as evaluation metrics, which yielded Kappa results of 0.619 and 0.613 for stroke patients and healthy volunteers, respectively.

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：