检索结果-内蒙古大学图书馆

Mechanical Analysis and Performance Optimization for the Lunar Rover’s Vane-Telescopic Walking Wheel

Engineering 2020年第8期6卷 936-943页

作者： Lu Yang Bowen Cai Ronghui Zhang Kening Li Zixian Zhang Jiehao Lei Baichao Chen Rongben Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin 300384China Guangdong Key Laboratory of Intelligent Transportation System School of Intelligent Systems EngineeringSun Yat-sen UniversityGuangzhou 510275China College of Transportation Jilin UniversityChangchun 130025China Department of Mechanical Science and Engineering Tokyo Institute of TechnologyTokyo 152-8550Japan Armour College of Engineering Illinois Institute of TechnologyChicagoIL 60616USA China Academy of Space Technology Beijing 100029China

It is well-known that optimizing the wheel system of lunar rovers is ***,this is a difficult task due to the complex terrain of the moon and limited resources onboard lunar *** this study,an experimental prototype was set up to analyze the existing mechanical design of a lunar rover and improve its ***,a new vane-telescopic walking wheel was proposed for the lunar rover with a positive and negative quadrangle suspension,considering the complex terrain of the ***,the performance was optimized under the limitations of preserving the slope passage and minimizing power *** was achieved via analysis of the wheel force during ***,the effectiveness of the proposed method was demonstrated by several simulation *** newly designed wheel can protrude on demand and reduce energy consumption;it can be used as a reference for lunar rover development engineering in China.

关键词： intelligent vehicle Vane-telescopic walking wheel Performance optimization Vane spring Lunar rover

来源：评论

学校读者我要写书评

暂无评论

LED Visible Light Localization Based on Illuminance Analysis

LED Visible Light Localization Based on Illuminance Analysis

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Chenting Gu Xiaofeng Liu Yongsheng Ou Chao Liu Hao Tao Tianyun Shi HoHai University Nanjing China Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen China Key Laboratory of Special Robots Changzhou China Changzhou Key Laboratory of Robots and Intelligent Technology Changzhou China College of IoT Engineering Hohai University Changzhou China Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China China Ship Development and Design Center Wuhan Tian-yun Shi China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

LED based positioning technology has recently become a popular choice due to the low cost, convenience for maintenance and strong adaptability to the environment. In this paper, we introduce an illuminance-distance analysis method with a rolling shutter camera, for a low-cost indoor positioning system to improve robustness in the case of insufficient LEDs. Firstly, the binary threshold method is used to decode the light signals. Then the gray value information of image is extracted to analyze the depth of LEDs, using the illuminance attenuation theorem. It provides potential solution to the position of devices with the camera by combining depth information, image and camera intrinsic. Our proposed method reduced the minimum number of LEDs observed by the camera from three to two, using only the camera. We evaluated the proposed method with real scene data and demonstrated the effectiveness of illumination-distance model based localization.

关键词： Light emitting diodes Cameras Receivers Light sources Robots Mathematical model Image sensors

来源：评论

学校读者我要写书评

暂无评论

DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge

arXiv

引用

arXiv 2020年

作者： Luo, Chunlong Yu, Tianqi Luo, Yufan Wang, Manqing Yu, Fuhai Li, Yinhao Tian, Chan Qiao, Jie Xiao, Li Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Peking University Third Hospital Beijing China School of Computer and Control Engineering University of Chinese Academy of China

Chromosome classification is an important but difficult and tedious task in karyotyping. Previous methods only classify manually segmented single chromosome, which is far from clinical practice. In this work, we propose a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image. We firstly introduce the Additive Angular Margin Loss to enhance the discriminative power of model. To alleviate batch effects, we transform decision boundary of each class case-by-case through a siamese network which make full use of prior knowledges that chromosomes usually appear in pairs. Furthermore, we take the clinically seven group criterion as a prior knowledge and design an additional Group Inner-Adjacency Loss to further reduce inter-class similarities. 3390 metaphase images from clinical laboratory are collected and labelled to evaluate the performance. Results show that the new design brings encouraging performance gains comparing to the state-of-the-art baselines. Copyright © 2020, The Authors. All rights reserved.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

Analysis of Anchor-Based and Anchor-Free Object Detection Methods Based on Deep Learning

Analysis of Anchor-Based and Anchor-Free Object Detection Me...

引用

IEEE International Conference on Mechatronics and Automation

作者： Shujian Liu Haibo Zhou Chenming Li Shuo Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

As one of the core mission of computer vision, object detection has been widely applied with the rapid development of computer technology, especially in the fields of face detection, behavior detection, auto driving, and intelligent monitoring. Aiming at the shortcomings of the traditional object detection, such as low detection accuracy, low efficiency and poor robustness, this article summarizes deep learning-based detectors of two kinds of modules: Anchor-Based and Anchor-Free. The performance of each detector is compared and analyzed in this paper as well. In addition, we summarize the development of object detection's key technologies from the aspect of improvement of Backbone, the optimization of NMS, imbalance of positive and negative samples' solution etc. Finally, the development trend of object detection is discussed from the prospect of lightweight detection model, weakly supervision detection and small object detection etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Micro-texture Parameters on Bone Drilling Force and Torque: A Finite Element Model 4

Influence of Micro-texture Parameters on Bone Drilling Force...

引用

2018 4th International Conference on Mechanical Engineering and Automation Science, ICMEAS 2018

作者： Hu, Yahui Li, Xiangjun Chen, Chuncheng Su, Lili Zheng, Qingchun Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin University of Technology 391 Binshui West Road Tianjin Xiqing District300384 China

The micro-texture on the tool surface is an effective way to improve the quality of the drilling. While high-performance micro-texture plays an important role in improving the quality of working surface and prolonging the life of tool. In this study, a three-dimensional finite element model was established to study the relationship between drilling thrust, torque and microstructure parameters (micro-pit depth, micro-pit diameter and micro-pit spacing) during drilling of cortical bone. The model was validated by cortical bone drilling using a micro-structured tool. On basis of this, the thrust and torque prediction models of the micro-texture parameters were obtained. The results indicate that the thrust and torque increased with the increase of micro-pit diameter;while the increase of the micro-pit spacing caused the thrust and torque to decrease. When the depth of the micro-pit increased, the thrust and torque decreased first and then increased, and we found that the effect of micro-pit spacing and micro-pit depth on force and torque is insignificant. © Published under licence by IOP Publishing Ltd.

关键词： Torque

来源：评论

学校读者我要写书评

暂无评论

Visual Servoing of Magnetic Swimming Robot Based on Mean Shift and Fast Template Matching Algorithm

Visual Servoing of Magnetic Swimming Robot Based on Mean Shi...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Hongbiao Xiang Tilei Zhang Mengwei Li Shoujun Wang Xiuping Yang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China

The actuation and control of mini-scale swimming robots have exhibit promising potential in limited and constrained environments, such as biomedical, micro-assembly and microfluidic applications. However, closed-loop control is still a challenging for the precision and repeatability in those applications. In this paper, a new type of soft-micro swimming robot based on magnetoelastic composite material is designed, and the swimmer can move freely on the water surface controlled by a rotating magnetic field with visual servoing. The visual feedback control strategy is proposed based on Mean Shift Algorithm and Fast Template Matching. The algorithm includes three parts: prediction, template matching, target positioning and template updating. To understand the characteristics of the swimmer, the relationship between swimming speed and magnetic field strength and frequency is verified by the algorithm in experiments. Furthermore, the proposed path following method with visual servoing applied in this control system. The experimental results show that the algorithm runs fast, has high accuracy and good real-time performance, and can provide great potential in mini-scale robot applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer-LSTM-KOA: A novel approach for prediction of chlorophyll in the South China Sea

引用

Environmental Modelling & Software 2025年 192卷

作者： Gang Chen Zhenzhong Liu Runfeng Zhang Guobin Zhang Jutao Wang Tongrui Zhang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin 300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin China School of Environmental Science and Safety Engineering Tianjin University of Technology Tianjin 300384 China Tianjin Hanhailanfan Marine Technology Co. Ltd. Tianjin 300457 China

Chlorophyll is a critical indicator of marine primary productivity and is essential in assessing aquatic ecosystem health. To address the limitations of current prediction models regarding accuracy, mobility, and reliability, this study proposes a novel Transformer-LSTM-KOA model for Chlorophyll prediction. Leveraging remote sensing data from the South China Sea, the model synergistically integrates Transformer's global analytical capabilities via self-attention and multi-head attention mechanisms with LSTM's proficiency in capturing long-term dependencies through gated mechanisms. The Kepler Optimization Algorithm (KOA) is subsequently employed to systematically optimize both global and local model parameters, thereby enhancing adaptability and robustness across diverse prediction datasets. Experimental results demonstrate superior performance with MSE and MAE values of 0.00011 and 0.00685, respectively, outperforming benchmark models. This enhanced modeling framework provides crucial technical support for marine ecological forecasting and early warning systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Methodology for optimization of preload in a bolted-flange connection based on Markov theory

引用

Journal of Physics: Conference Series 2022年第1期2174卷 012072页

作者： Yuezhen Wang Zhifeng Liu Ying Li Congbin Yang Institute of Advanced Manufacturing and Intelligent Technology Beijing University of Technology Beijing Beijing 100124 China Mechanical Industry Key Laboratory of Heavy Machine Tool Digital Design and Testing Beijing University of Technology Beijing Beijing 100124 China Key Laboratory of CNC Equipment Reliability Ministry of Education Jilin University Changchun Jilin 130012 China

The bolted-flange connection is one of the most popular detachable mechanical joints in mechanical flange connection. It is well known that bolted-flange joints need to be tightened to meet the assembly performance in practical engineering applications. However, the dispersion of the pre-tightening force caused by the elastic interaction between the bolts has a serious impact on the sealing and safety of the product, and therefore the optimization of bolt preload has always been a hot spot in the assembly research field. Combining mathematical theory and experimental data, this paper proposes an optimization model for uniformly distributed preload based on the Markov theory. The torque method was utilized to fasten the bolt-flange joint. The bolt pre-tightening force in the final state was collected and used as sample data. A state transition model was constructed to determine the state transition matrix. Ultimately, an iterative model of the preload was deduced, and the rationality of the model was verified through experimentation. The proposed optimization method of bolt preload can be applied to determine the initial preload of each bolt. This method improves the assembly efficiency and accuracy, which provides a theoretical approach to effectively guide the tightening work of bolted-flange connections.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constraining ultralight vector dark matter with the Parkes Pulsar Timing Array second data release

arXiv

引用

arXiv 2022年

作者： Wu, Yu-Mei Chen, Zu-Cheng Huang, Qing-Guo Zhu, Xingjiang Bhat, N.D. Ramesh Feng, Yi Hobbs, George Manchester, Richard N. Russell, Christopher J. Shannon, R.M. School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced Study UCAS Hangzhou310024 China School of Physical Sciences University of Chinese Academy of Sciences No. 19A Yuquan Road Beijing100049 China CAS Key Laboratory of Theoretical Physics Institute of Theoretical Physics Chinese Academy of Sciences Beijing100190 China Department of Astronomy Beijing Normal University Beijing100875 China Advanced Institute of Natural Sciences Beijing Normal University Zhuhai519087 China International Centre for Radio Astronomy Research Curtin University BentleyWA6102 Australia Research Center for Intelligent Computing Platforms Zhejiang Laboratory Hangzhou311100 China Australia Telescope National Facility CSIRO Astronomy and Space Science P.O. Box 76 EppingNSW1710 Australia CSIRO Scientific Computing Australian Technology Park Locked Bag 9013 AlexandriaNSW1435 Australia Centre for Astrophysics and Supercomputing Swinburne University of Technology HawthornVIC3122 Australia Australia

Composed of ultralight bosons, fuzzy dark matter provides an intriguing solution to challenges that the standard cold dark matter model encounters on sub-galactic scales. The ultralight dark matter with mass m ∼ 10−23eV will induce a periodic oscillation in gravitational potentials with a frequency in the nanohertz band, leading to observable effects in the arrival times of radio pulses from pulsars. Unlike scalar dark matter, pulsar timing signals induced by the vector dark matter are dependent on the oscillation direction of the vector fields. In this work, we search for ultralight vector dark matter in the mass range of [2 × 10−24, 2 × 10−22 ]eV through its gravitational effect in the Parkes Pulsar Timing Array (PPTA) second data release. Since no statistically significant detection is made, we place 95% upper limits on the local dark matter density as ρVF . 5 GeV/cm3 for m . 10−23 eV. As no preferred direction is found for the vector dark matter, these constraints are comparable to those given by the scalar dark matter search with an earlier 12-year data set of PPTA. Copyright © 2022, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Knowledge-routed visual question reasoning: Challenges for deep representation embedding

arXiv

引用

arXiv 2020年

作者： Cao, Qingxing Li, Bailin Liang, Xiaodan Wang, Keze Lin, Liang School of Intelligent Systems Engineering Sun Yat-sen University China DarkMatter AI Research China Department of statistics University of California Los AngelesCA90095 United States School of Computer Science and Engineering Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education China

Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly annotated in a crowdsource way, e.g., collecting questions and external reasons from different users via the internet. In addition to the challenge of knowledge reasoning, how to deal with the annotator bias also remains unsolved, which often leads to superficial over-fitted correlations between questions and answers. To address this issue, we propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning. Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases. The programs can select one or two triplets from the scene graph or knowledge base to push multi-step reasoning, avoid answer ambiguity, and balanced the answer distribution. In contrast to the existing VQA datasets, we further imply the following two major constraints on the programs to incorporate knowledge reasoning: i) multiple knowledge triplets can be related to the question, but only one knowledge relates to the image object. This can enforce the VQA model to correctly perceive the image instead of guessing the knowledge based on the given question solely;ii) all questions are based on different knowledge, but the candidate answers are the same for both the training and test sets. We make the testing knowledge unused during training to evaluate whether a model can unde

关键词： Knowledge based systems

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：