检索结果-内蒙古大学图书馆

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Xie, Tao Gao, Jinghan Wang, Ke Li, Ruifeng Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350331820

Optical flow seeks to estimate the per-pixel 2D motion between two frames by identifying corresponding pixels. Current flow estimators typically involve per-pixel feature extraction, multi-scale 4D correlation volume construction, and iterative flow field updates through a Conv-GRU module. However, the locality of convolutional features in these methods renders the calculated correlations vulnerable to different noises. In addition, the Conv-GRU module of these methods is only executed with a convolution layer, which is incapable of exploiting context clues from larger window sizes even inside the image being queried itself, thus raising it more difficult for the model to process images with challenging regions, e.g., textureless areas. To this end, we introduce GCA-Net, a global context aggregation network for credible yet effective optical flow estimation. More specifically, we propose a highly efficient multi-scale transformer (MSFormer) layer which enables the per-pixel feature to aggregate long-range information from other features, hence building more accurate 4D correlation volumes. Besides, we develop an attention-enhanced Conv-GRU block (AttGRU) that can incorporate information alongside a larger context window even within itself empowering our network to estimate optical flow in even the most challenging regions. Experimentally, we demonstrate that GCA-Net outperforms previous state-of-the-art methods by large margins on Sintel (Final) and KITTI 2015 (background and foreground) benchmarks. © 2023 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Watt Linkage–Based Legged Deployable Landing Mechanism for Reusable Launch Vehicle: Principle, Prototype Design, and Experimental Validation

引用

Engineering 2023年第1期20卷 120-133页

作者： Haitao Yu Baolin Tian Zhen Yan Haibo Gao Hongjian Zhang Huiqiang Wu Yingchao Wang Yuhong Shi Zongquan Deng State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150080China Beijing Institute of Aerospace Systems Engineering Beijing 100076China

The reusable launch vehicle (RLV) presents a new avenue for reducing cost of space transportation. The landing mechanism, which provides landing support and impact absorption, is a vital component of the RLV at final stage of recovery. This study proposes a novel legged deployable landing mechanism (LDLM) for RLV. The Watt-II six-bar mechanism is adopted to obtain the preferred configuration via the application of the linkage variation approach. To endow the proposed LDLM with advantages of large landing support region, lightweight, and reasonable linkage internal forces, a multi-objective optimization paradigm is developed. Furthermore, the optimal scale parameters for guiding the LDLM prototype design is obtained numerically using the non-dominated sorting genetic algorithm-II (NSGA-II) evolutionary algorithm. A fully-functional scaled RLV prototype is developed by integrating the gravity-governed deploying scheme to facilitate unfolding action to avoid full-range actuation, a dual-backup locking mechanism to enhance reliability of structure stiffening as fully deployed, and a shock absorber (SA) with multistage honeycomb to offer reliable shock absorbing performance. The experimental results demonstrate that the proposed LDLM is capable of providing rapid and smooth deployment (duration less than 1.5 s) with mild posture disturbance to the cabin (yaw and pitch fluctuations less than 6°). In addition, it provides satisfactory impact attenuation (acceleration peak less than 10g (g is the gravitational acceleration)) in the 0.2 m freefall test, which makes the proposed LDLM a potential alternative for developing future RLV archetype.

关键词： Reusable launch vehicle(RLV) Deployable mechanism Optimization desi gn

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Improving CNNs in Medical Image Classification 8

Data Augmentation for Improving CNNs in Medical Image Classi...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Ren, Yi He, Zengmin Deng, Yang Huang, Bo Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350302455

Medical image is essential for physicians to diagnose diseases. And convolutional neural networks (CNNs) have gained momentum for computer-aided diagnosis (CAD) medical image. However, there are still challenges in CNNs related to a lack of data and class-imbalanced datasets. Data augmentation is utilized to address the issues mentioned above. In this study, the Pseudo-color enhancement algorithm (OCEAN and TWILIGHT), common linear transform, CLAHE enhancement, and K-means clustering algorithm were applied to pneumonia X-ray images for data augmentation. Thus, five processed datasets were finally obtained. The results indicated that five data-augmentation methods effectively improved the performance of CNNs for the pneumonia X-ray images binary classification detection, in which the CLAHE enhancement and OCEAN enhancement methods had the accuracy and F1 Score with 97.42%, 97.19%, and 97.42%, 98.36%, respectively. DenseNet121 showed the best classification performance of four CNNs utilized in this study, as evidenced by the area under the receiver operating characteristic (ROC) curves (AUC). To verify the generalizability of the two enhancement methods, CLAHE and OCEAN enhancement methods were applied to the Magnetic Resonance Imaging (MRI) dataset of Alzheimer's disease, which had the accuracy and F1 Score with 98.15% , 98.15%, and 97.22%, 97.68%, respectively. Therefore, these simple and efficient data-augmentation methods effectively improve the performance of CNNs for diagnosing medical image, which can provide theoretical reference for physicians to diagnose the above two diseases, and advance the application of clinical medicine. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Dual-Arm Dynamic Planning with Considering Arm Reachability Constraint in Task Space 16th

Dual-Arm Dynamic Planning with Considering Arm Reachability ...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Shu, Xin Fan, Xinyang Min, Kang Ji, Zhu Ni, Fenglei Liu, Hong State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819964888

This paper aims to address the issue of planning dual-arm motions in scenarios involving tracking dynamic desired pose and obstacle avoidance. In situations where dual-arm motion requires synchronous behavior, inflexible planning, encountering obstacles, and beyond-the-arm motion capability may lead to task failure. To overcome these issues, we propose a dynamic-system-based method for dual-arm collaborative planning. The method can coordinate the motions of dual arms while keeping synchronous behavior in tracking the moving target and avoiding obstacles. Meanwhile, we incorporate the reachability by modeling the motion boundary to ensure that the arms moving within the reachable space. The experiment successfully verified the above scenarios, showcasing its adaptability in dual-arm planning and its potential applicability in dual-arm applications such as transportation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

An Effective Rotor-Shape Optimization Method for IPM Motor with 1/2 Slot per Phase per Pole

An Effective Rotor-Shape Optimization Method for IPM Motor w...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Yu, Guodong Sun, Shuqi Li, Junlong Xiao, Lijun Xu, Yongxiang Zou, Jibin Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350301571

Although IPM motor with 1/2 slot per phase per pole has a relatively less rotor loss in comparison with other fractional slot concentrated winding (FSCW), the problems of THD of back-EMF and cogging torque are worse, which limits its application in electric vehicles and other industry fields. This paper proposes an effective rotor-shape optimization method to suppress both THD of back-EMF and cogging torque for improving torque ripple problem. Different from the prevalent rotor optimization methods, the proposed rotor-shape optimization method associates both shape function optimization of rotor surface with PM shaping, which can effectively decrease optimization parameters, and enhance optimization efficiency. To clarify the optimization strategy, the back-EMF and cogging torque for this PM motor with 1/2 slot per phase per pole are analyzed firstly. Then, the proposed optimization method is presented in detail. Finally, the optimized IPM motor is prototyped and its experimental results verifies the effectiveness of the proposed optimization method. © 2023 IEEE.

关键词： back-EMF cogging torque IPM motor optimization method

来源：评论

学校读者我要写书评

暂无评论

Flight control of a large-scale flapping-wing flying robotic bird:system development and flight experiment

引用

Chinese Journal of Aeronautics 2022年第2期35卷 235-249页

作者： Wenfu XU Erzhen PAN Juntao LIU Yihong LI Han YUAN School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Large-scale flapping-wing flying robotic birds have huge application potential in outdoor tasks,such as military reconnaissance,environment exploring,disaster rescue and so *** this paper,a multiple modes flight control method and system are proposed for a large-scale robotic bird which has 2.3 m wingspan and 650 g *** from small flapping wing aerial vehicle,the mass of its wings cannot be neglected and the flapping frequency are much ***,the influence of transient aerodynamics instead of only mean value are considered in attitude estimation and controller ***,flight attitude and trajectory are highly coupled,and the robot has only three actuators----one for wings flapping and two for tail adjustment,it is very difficult to simultaneously control the attitude and ***,a fuzzy control strategy is addressed to determine the command of each actuator by considering the priority of attitude stabilization,trajectory tracking and the flight ***,the on-board controller is designed based on *** not only satisfies the strict restrictions on mass,size,power and space but also meets the autonomous,semi-autonomous and manual flight control ***,the developed control system was integrated to the robotic prototype,*** experiments under different environment conditions such as sunny and windy weather were completed to verify the control method and system.

关键词： Autonomous flight control Flapping-wing Free RTOS HIT-Phoenix Robotic bird

来源：评论

学校读者我要写书评

暂无评论

Thermal analysis of lubricated three-dimensional contact bodies considering interface roughness

引用

Frontiers of Mechanical Engineering 2022年第2期17卷 177-191页

作者： Jiqiang WU Liqin WANG Zhen LI Peng LIU Chuanwei ZHANG MIIT Key Laboratory of Aerospace Bearing Technology and Equipment Harbin Institute of TechnologyHarbin 150001China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080China

Surface roughness and thermal action are of remarkable importance in the lubrication performance of mechanical components,especially in extreme ***,available studies mainly focus on the full-film lubrication conditions without considering temperature rise and real 3D surface roughness due to the complexity of surface topography and temperature ***,studies on the interfacial thermal behaviors of 3D rough surface lubricated contact in an extended range of working conditions remain *** this paper,a deterministic mixed thermal elastohydrodynamic lubrication model considering real 3D surface roughness and thermal effects is *** this model,pressure and temperature are coupled with each other,the computation of elastic deformation is accelerated through the discrete convolution and fast Fourier transform method,the temperature field is calculated with the column sweeping technique,and the semi-system method is introduced to improve convergence and numerical stability under severe *** model is validated by comparing its results with available published numerical and experimental *** thermal behaviors of the contact interface are studied in a wide range of working *** influences of surface roughness and thermal effect on lubrication performance are *** results show that the proposed model can be used as a powerful analysis tool for lubrication performance and temperature prediction in various heavy-load,high-speed lubricated components over a wide range of lubrication conditions.

关键词： thermal elastohydrodynamic lubrication surface roughness effect thermal effect temperature characteristics severe conditions

来源：评论

学校读者我要写书评

暂无评论

Research on Multisensor Fusion state Estimation of Automatic Navigation Vehicle Based on RNN Model 13th

Research on Multisensor Fusion State Estimation of Automatic...

引用

13th International Conference on Frontier Computing, FC 2023

作者： Zhang, Liyuan Cui, Zhiquan Wang, Honggang Harbin Institute of Technology Shandong Weihai264209 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9789819992980

Multi sensor fusion state estimation of autonomous navigation vehicle based on RNN model. Multi sensor fusion is a process of combining information from different sensors to estimate a single value. In this paper, we propose a recursive neural network (RNN) model to estimate the state of multiple sensors. This method uses RNN architecture with two hidden layers and one output layer to combine sensor data. The input data is first divided into a sequence and then input into the RNN model to predict the output. We use three types of sensors: IMU, LIDAR and GPS. First, the RNN model is trained using three sensors for the navigation system. Then, we use this trained model to estimate the current position using only one sensor data. Finally, we combine the data of all three sensors to obtain the final estimated position of the vehicle at any given time step. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Research on Size Calibration Algorithm of Dark-field Flaw on Optics Surface Based on Convolutional Neural Network

Research on Size Calibration Algorithm of Dark-field Flaw on...

引用

2024 Applied Optics and Photonics China: Optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Wang, Bei Yin, Zhaoyang Zhou, Shicheng Zhao, Linjie Chen, Mingjun Cheng, Jian School of Mechatronics Engineering Harbin Institute of Technology Harbin China State Key Laboratory of Robotics and System Harbin Institute of Technology 150001 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

Optics in high-power solid-state laser devices will be damaged and adhere to contaminates on the surface during manufacturing and operation, which reduces the service life. To facilitate the positioning and recognition of the flaw (damage and contaminates) in the process of automatic repair, the dark-field flaw size calibration algorithm was studied. In this paper, a flaw size calibration model based on convolutional neural network was established. The size, exposure time, and loss function of damage and contaminate were optimized respectively. The training parameter of the damage regression model is determined to be size of less than 500μm, 30ms of exposure time and SmoothL1 loss function, and the parameter of contaminate is 0-100μm, 20ms of exposure and SmoothL1 loss function. After data balancing, the calibration precision was improved. To improve the calibration consistency of the full-size segment, a comprehensive size calibration strategy is proposed. The CNN regression algorithm is used for small size, and the pixel-level calibration algorithm is used for large size. Compared with the single regression calibration algorithm, the relative error and absolute error of the calibration results of small damage ( © 2024 SPIE.

关键词： Solid state lasers

来源：评论

学校读者我要写书评

暂无评论

Autonomous Formation Flight Control of Large-Sized Flapping-Wing Flying Robots Based on Leader–Follower Strategy

引用

Journal of Bionic Engineering 2023年第6期20卷 2542-2558页

作者： Hui Xu Yuanpeng Wang Erzhen Pan Wenfu Xu Dong Xue School of Mechanical Engineering and Automation Harbin Instwitute of TechnologyShenzhen518055China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150000China School of Aeronautics Northwestern Polytechnical UniversityXi’an710072China

Birds in nature exhibit excellent long-distance flight capabilities through formation flight,which could reduce energy consumption and improve flight *** by the biological habits of birds,this paper proposes an autonomous formation flight control method for Large-sized Flapping-Wing Flying Robots(LFWFRs),which can enhance their search range and flight ***,the kinematics model for LFWFRs is ***,an autonomous flight controller based on this model is designed,which has multiple flight control modes,including attitude stabilization,course keeping,hovering,and so ***,a formation flight control method is proposed based on the leader–follower strategy and periodic characteristics of flapping-wing *** up and down fluctuation of the fuselage of each LFWFR during wing flapping is considered in the control algorithm to keep the relative distance,which overcomes the trajectory divergence caused by sensor delay and fuselage ***,typical formation flight modes are realized,including straight formation,circular formation,and switching ***,the outdoor formation flight experiment is carried out,and the proposed autonomous formation flight control method is verified in real environment.

关键词： Bionic Large-sized flapping-wing flying robot HIT-Phoenix Periodic flight characteristics Formation flight Leader follower strategy

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：