检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Mengran Chen, Junzhou Jiang, Guanying Li, Fuliang Zhang, Ronghui Gong, Siyuan Lv, Zhihan Guangdong Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Guangzhou510275 China Baidu Inc Beijing100085 China Department of Electrical Engineering The Hong Kong Polytechnic University Hong Kong School of Information and Engineering Chang’an University Shanxi Xi’an710064 China Department of Game Design Faculty of Arts Uppsala University Uppsala75236 Sweden

Accurately estimating time of arrival (ETA) for trucks is crucial for optimizing transportation efficiency in logistics. GPS trajectory data offers valuable information for ETA, but challenges arise due to temporal sparsity, variable sequence lengths, and the interdependencies among multiple trucks. To address these issues, we propose the Temporal-Attribute-Spatial Tri-space Coordination (TAS-TsC) framework, which leverages three feature spaces—temporal, attribute, and spatial—to enhance ETA. Our framework consists of a Temporal Learning Module (TLM) using state space models to capture temporal dependencies, an Attribute Extraction Module (AEM) that transforms sequential features into structured attribute embeddings, and a Spatial Fusion Module (SFM) that models the interactions among multiple trajectories using graph representation learning. These modules collaboratively learn trajectory embeddings, which are then used by a Downstream Prediction Module (DPM) to estimate arrival times. We validate TAS-TsC on real truck trajectory datasets collected from Shenzhen, China, demonstrating its superior performance compared to existing methods. © 2024, CC BY.

关键词： Truck transportation

来源：评论

学校读者我要写书评

暂无评论

Study on Mechanical Properties of Dual-Channel Cryogenic 3d Printing Scaffold for Mandibular Defect Repair

SSRN

引用

SSRN 2023年

作者： Gao, Lilan Sun, Mengchao Liu, Jie Meng, Lulu Liu, Han Zheng, Xiongfei Liu, Hao Li, Ruixin Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300382 China Tianjin300382 China Beijing Friendship Hospital Capital Medical University 100050 China State Key Laboratory of Robotics Institutes for Robotics and Intelligent Manufacturing Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110017 China Tianjin Key Laboratory of Oral and Maxillofacial Function Reconstruction Tianjin Stomatological Hospital The Affiliated Stomatological Hospital of Nankai University Tianjin300041 China

Mandibular defect repair has always been a clinical challenge, facing technical bottleneck. The new materials directly affect technological breakthroughs in mandibular defect repair field. Our aim is to fabricate a scaffold for mandibular defect repairing with advanced biomaterials. Therefore, a novel dual-channel printed scaffold consisting of silk fibroin/collagen type I /hydroxyapatite (SCH) and polycaprolactone/hydroxyapatite (PCL/HA) was fabricated by 3D printing technology with double nozzles. The mechanical properties and behaviors of dual-channel printed scaffold were investigated by performing uniaxial compression, creep, stress relaxation and ratcheting experiments respectively. The experiments indicated the Young modulus of dual-channel printed scaffold was 60.1 kPa and dual-channel printed scaffold was typical nolinear viscoelastic consistent with bone tissue. Finite Element Analysis (FEA) was employed performing a numerical simulation to evaluate the implantation effect in mandible. The stress distribution of the contact area between scaffold and defect was uniform, the maximum Mises stress of cortical bone and cancellous bone in defect area were 54.52MPa and 3.196MPa, and the maximum displacement of cortical bone and cancellous bone in defect area were 0.1575mm and 0.1555mm, which were distributed in the incisor region. The peak value of the maximum Mises stress for the scaffold implanted was 3.128× MPa and the maximum displacement was 6.453×mm distributed near incisor area. The displacement distribution of the scaffold was consistent with that of cortical and cancellous bone. The scaffold recovered well when the force applied on it disappeared. Above all, dual-channel printed scaffold had excellent bio-mechanical properties in implanting mandible, which provides a new idea for the reconstruction of irregular bone defects in the mandible and has good clinical development prospects. © 2023, The Authors. All rights reserved.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Modeling, simulation and experiment of an origami robot with a coupled bar-hinge mechanism

Modeling, simulation and experiment of an origami robot with...

引用

Fully Actuated system Theory and Applications (CFASTA), Conference on

作者： Junpeng Mai Hanzhao Shao Shaojie Liu Yuanzhuo Zhang Liangming Chen Huijuan Feng School of System Design and Intelligent Manufacturing and Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology Shenzhen P. R. China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen P. R. China Department of Mechnical and Energy Engineering Southern University of Science and Technology Shenzhen P. R. China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper aims to analyze the motion behavior of an origami robot with a coupled bar-hinge mechanism. By disassembling the planar six-hinge mechanism into two planar four-hinge mechanisms with coupled motion, this paper derives the kinematics of the planar six-hinge mechanism based on the algebraic differential kinematics of the planar four-hinge motions. The rotational angle change and the moving step length of the origami robot are further calculated. Finally, the theoretical motion model is verified with the motion simulation data of the planar six-hinge mechanism origami robot in SolidWorks and the experimental data of the physical model. This verification proves the feasibility of the theoretical analysis, simulation model, and physical model.

关键词： Solid modeling Analytical models Prototypes Kinematics Three-dimensional printing Mathematical models Data models

来源：评论

学校读者我要写书评

暂无评论

The relationship between orthopedic clinical imaging and bone strength prediction

引用

Medicine in Novel Technology and Devices 2021年第1期9卷 9-17页

作者： He Gong Meng Zhang Shaowei Jia Linwei Lv Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education Beijing Advanced Innovation Center for Biomedical EngineeringSchool of Biological Science and Medical EngineeringBeihang UniversityBeijingChina Department of Engineering Mechanics Nanling CampusJilin UniversityChangchun130025China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin300384China

Pathologic fracture is caused by bone diseases,which is common in middle-aged and elderly *** bone strength is the leading contributor to this type of ***,accurately quantifying bone strength could help clinicians assess individualized fracture risk and develop therapeutic *** clinical imaging including dual X-ray absorptiometry(DXA),computed tomography(CT),and magnetic resonance imaging(MRI)has been an important tool to obtain radiology images of bone,which could be further used for noninvasive assessment of bone strength and related fracture *** the development of biomechanics and computer technology,the combination of finite element analysis with orthopedic imaging is the most advanced method for noninvasive prediction of bone strength in *** this review,an overview is provided for the commonly noninvasive methods based on the radiology images(i.e.,DXA,CT,and MRI)to predict bone strength,which may improve the understanding of the relationship between orthopedic clinical imaging and biomechanics.

关键词： Orthopedic clinical imaging Biomechanics Bone strength Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality and Quick Response Code Technology in Engineering Drawing Course 17

Augmented Reality and Quick Response Code Technology in Engi...

引用

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

作者： Wang, Xiaofei Chen, Chenfei Li, Zhaotong Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China

ISBN: (纸本)9781728164151

Augmented reality (AR) technology is a cutting technology. It can enhance the perception of reality and provide more information of the real world. AR technology is used in many fields, like medical, industry, and education. In this paper, AR is introduced into engineering drawing course. Engineering drawing course is difficult to learn as it is a knowledge that students rarely contact with. To have a close contact with the models and the views, a convenient AR application (AR app) is proposed in the paper. With the help of the AR app, virtual models and real views are combined well. The models can be moved and rotated by touching the screen. Some videos of model assembly and disassembly can be obtained when scanning the quick response code (QR code). Thus, it is convenient for students to use mobile phone to study engineering drawing effectively. The interactive teaching environment enhances students' spatial thinking and cultivates their sense of innovation. © 2020 IEEE.

关键词： Augmented reality

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 17

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

引用

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

作者： Liu, Shujian Zhou, Haibo Li, Chenming Wang, Shuo Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China

ISBN: (纸本)9781728164151

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. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

design of Programmable Droplet Manipulation Platform Based on Magnetic Control 12

Design of Programmable Droplet Manipulation Platform Based o...

引用

12th International Conference on CYBER Technology in Automation, Control, and intelligent systems, CYBER 2022

作者： Zhang, Xianmiao Liu, Jie Liu, Jiying Wang, Yuzhe Zhang, Mian Xiang, Hongbiao School of Mechanical Engineering Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Hong Kong Baptist University United International College Division of Culture and Creativity Beijing Normal University Guangdong Zhuhai519087 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Droplet actuation simplifies the handling of various reagents or samples and can be applied to a wide range of fields, including chemistry, biology, biomedical, and others. This paper presents a programmable droplet control system based on a magnetoelastic membrane and electromagnetic pillar array. Different magnetic blocks with different magnetization directions were designed on the silicone rubber membrane, and the magnetoelastic membrane deformed under the magnetic field generated by the array of electromagnetic pillars. By combining the gravitational forces of the droplet and the deformation of the magnetic membranes, the motion of the droplet can be controlled. Furthermore, the surface of membranes was ablated with a laser machine to impart superhydrophobic properties. The simulation results show that with the different magnetic fields, the droplet can move lengthwise, widthwise, and diagonally in the horizontal plane, and multiple droplets can be merged and mixed. In contrast to the traditional droplet control method, the droplet programmable movement control system utilizing superhydrophobic magnetoelastic membranes and an electromagnetic pillar array has better stationarity, flexibility and does not affect the basic properties of the droplets. © 2022 IEEE.

关键词： Silicones

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization and Control Method Based on Multistage Nonlinear Model Predictive Control

Trajectory Optimization and Control Method Based on Multista...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Qingchun Zheng Zhi Peng Peihao Zhu Ran Zhai Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China 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

To improve the trajectory optimization efficiency of robot manipulators, this paper proposes a novel approach for trajectory optimization and control of manipulators based on multistage nonlinear model predictive control (msNLMPC). This approach is realized by using a neural state space model as the prediction model of nonlinear model predictive control (NLMPC). The simulation results show that the actual trajectory of the manipulator in our proposed scheme coincides with the desired trajectory. The manipulator achieves the control task of following the optimal trajectory. Our proposed method improves the trajectory optimization efficiency of the robot manipulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Surgical Gesture Recognition in Open Surgery Based on 3DCNN and SlowFast

Surgical Gesture Recognition in Open Surgery Based on 3DCNN ...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Yutao Men Jian Luo Zixian Zhao Hang Wu Feng Luo Guang Zhang Ming Yu 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 Systems Engineering Institute Academy of Military Sciences People's Liberation Army Tianjin China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

In the field of computer-aided medicine, automated surgical gesture recognition is an important research direction. Its main applications include automated skills assessment, intraoperative guidance, and education and training systems. Current research has focused on robotic surgery, and there is less research on surgical gestures for open surgery. Therefore, in this study, a new simulated open surgery dataset was developed, and a series of surgical gestures for open surgery were defined for closure the abdomen surgery with the cooperation of professional doctors. In addition, this paper uses the classical algorithm 3DCNN and SlowFast model in the field of action recognition to perform offline recognition of surgical gestures for open surgery on the dataset. 3DCNN uses R3D and R(2+1)D models. The experimental results show that on the self-built open surgical dataset, the R3D model has the best surgical gesture recognition results, with an accuracy rate of 90.4%, a precision rate of 90.5%, and a recall rate of 90.0%.

关键词： Training Automation Accuracy Surgery Gesture recognition Medical services Information technology Robots Abdomen

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent Temperature Control Method of Closed-Loop Cooling system Based on Deep Q-Network

SSRN

引用

SSRN 2024年

作者： Liu, Yongchao Wang, Bo Zheng, Wei Wang, Zibo Li, Tong Cheng, Jiahao Niu, Zhenfeng Ke, Zhiwu Tan, Sichao Li, Jiangkuan Gao, Puzhen Tian, Ruifeng Zhu, Qidan Heilongjiang Provincial Key Laboratory of Nuclear Power System & Equipment Harbin Engineering University Harbin150001 China Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology Ministry of Industry and Information Technology Harbin Engineering University Harbin150001 China Science and Technology Thermal Energy and Power Laboratory Wuhan430205 China Wuhan Second Ship Design and Research Institute Wuhan430205 China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China

As one of the most important subsystem types in the nuclear power system, the closed-loop cooling system is used for the heat transfer of the system. The control quality of its operating temperature is important for the safe operation of the entire nuclear power system. This paper proposes an intelligent temperature control method based on deep reinforcement learning (DRL). First, the closed-loop cooling system simulator is built and expanded to provide an experimental platform for the implementation of DRL. Secondly, a DRL interaction system is designed based on prior knowledge such as system thermal control characteristics and temperature control targets. Finally, the improved deep Q-network (DQN) algorithm is used to train the deep neural network agent, and the optimal temperature control strategy is approached and saved through self-learning interaction. The experimental results demonstrate that the DRL controller can realize automatic control operation and has good target tracking ability and robustness. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

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：