检索结果-内蒙古大学图书馆

1st International Conference of Adisutjipto on Aerospace Electrical Engineering and Informatics, ICAAEEI 2024

作者： Sumari, Arwin Datumava Wahvudi Aryandika, Ahnaf Bagus Purnami, Ndaru Atmi Dermawan, Denny Syamsiana, Ika Noer State Polytechnic of Malang Cognitive Artificial Intelligence Research Group Department of Electrical Engineering Malang Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Aerosp. Digit. Syst. Microprocessor Microcontroller and Programmable Logic Devices Research Group Yogyakarta Indonesia

ISBN: (纸本)9798331507930

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Constrained Trajectory Optimization for Coordinated Maneuver Planning of Spacecraft with Dual Manipulators

SSRN

引用

SSRN 2025年

作者： Zhu, Zhe Xu, Rui Li, Zhaoyu Zhu, Shengying Long, Jiateng Zhang, Shengyu Institute of Deep Space Exploration Technology Beijing Institute of Technology Beijing100081 China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration Beijing Institute of Technology Ministry of Industry and Information Technology Beijing100081 China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai201203 China

Application of spacecraft with movable mechanisms is more effective in attitude maneuver missions than rigid three-axis spacecraft owning to extra degrees of freedom, but also raises challenges on attitude trajectory planning. This paper investigates the application of a hierarchical mixed-strategy optimization method to coordinated attitude trajectory planning of the spacecraft with dual manipulators. In order to overcome the computation complexity issue, decoupled strategy is employed to split demanded pointing into the body quaternion and manipulator joint angles. Having the pointing path compliant with pointing constraints, objectives of energy consumption and joint angle change are designed. The secondary rotation of quaternion sequence is utilized as design variables in conjunction with a hierarchical swarm optimization algorithm using mixed search strategy for attitude trajectory optimization. The optimal solutions of body attitude and joint angle path are parametrized with cubic splines to solve complete trajectories of system states using inverse dynamics while imposed constraints are satisfied. Simulation results are presented for coordinated attitude trajectory planning of spacecraft with two manipulators and demonstrate the effectiveness of the proposed optimization method. © 2025, The Authors. All rights reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Unsupervised learning on particle image velocimetry with embedded cross‐correlation and divergence‐free constraint

引用

IET Cyber-Systems and Robotics 2022年第3期4卷 200-211页

作者： Yiwei Chong Jiaming Liang Tehuan Chen Chao Xu Changchun Pan College of Control Science and Engineering Zhejiang UniversityHangzhouZhejiangChina School of Mechanical Engineering and Mechanics Ningbo UniversityNingboZhejiangChina Ningbo Artificial Intelligence Institute Shanghai Jiao Tong UniversityNingboZhejiangChina The State Key Laboratory of Industrial Control Technology Institute of Cyber‐Systems and ControlZhejiang UniversityHangzhouZhejiangChina School of Electronic Information and Electrical Engineering Key Laboratory of Shanghai Navigation and Location Based ServicesShanghai Jiao Tong UniversityShanghaiZhejiangChina

Particle image velocimetry(PIV)is an essential method in experimental fluid *** recent years,the development of deep learning‐based methods has inspired new ap-proaches to tackle the PIV problem,which considerably improves the accuracy of ***,the supervised learning of PIV is driven by large volumes of data with ground truth ***,the authors consider unsupervised PIV *** has been some work on unsupervised PIV,but they are not nearly as effective as supervised learning *** authors try to improve the effectiveness and accuracy of unsupervised PIV by adding classical PIV methods and physical *** this paper,the authors propose an unsupervised PIV method combined with the cross‐correlation method and divergence‐free constraint,which obtains better performance than other unsupervised PIV *** authors compare some classical PIV methods and some deep learning methods,such as LiteFlowNet,LiteFlowNet‐en,and UnLiteFlowNet with the authors’model on the synthetic ***,the authors contrast the results of LiteFlowNet,UnLiteFlowNet and the authors’model on experimental particle *** a result,the authors’model shows comparable performance with classical PIV methods as well as supervised PIV methods and outperforms the previous unsupervised PIV method in most flow cases.

关键词： neural network particle image velocimetry unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Modeling the optimal compensation capacitance of a giant magnetostrictive ultrasonic transducer with a loosely-coupled contactless power transfer system

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2022年第10期23卷 757-770页

作者： Tian LAN Ping-fa FENG Jian-jian WANG Jian-fu ZHANG Hui-lin ZHOU State Key Laboratory of Tribology Department of Mechanical EngineeringTsinghua UniversityBejing 100084China'China China Ordnance Industry Navigation and Control Technology Research Institute Beijing 10089China

The giant magnetostrictive rotary ultrasonic processing system(GMUPS)with a loosely-coupled contactless power transfer(LCCPT)has emerged as a high-performance technique for the processing of hard and brittle materials,owing to its high power density.A capacitive compensation is required to achieve the highest energy efficiency of GMUPS to provide sufficient vibration amplitude when it works in the resonance *** this study,an accurate model of the optimal compensation capacitance is derived from a new electromechanical equivalent circuit model of the GMUPS with LCCPT,which consists of an equivalent mechanical circuit and an electrical *** phase lag angle between the mechanical and electrical circuits is established,taking into account the non-negligible loss in energy conversion of giant magnetostrictive material at ultrasonic *** change of system impedance characteristics and the effectiveness of the system compensation method under load are *** idle vibration experiments and machining tests are conducted to verify the developed *** results show that the GMUPS with optimal compensation capacitance can achieve the maximum idle vibration amplitude and smallest cutting *** addition,the effects of magnetic conductive material and driving voltages on the phase lag angle are also evaluated.

关键词： Rotary ultrasonic machining Giant magnetostrictive transducer(GMT) Loosely-coupled contactless power transfer(LCCPT) Electromechanical equivalent circuit Optimal compensation capacitance

来源：评论

学校读者我要写书评

暂无评论

Distributed Consensus Kalman Filtering Over Time-Varying Graphs

引用

IFAC-PapersOnLine 2023年第2期56卷 10228-10233页

作者： Aviv Priel Daniel Zelazo Department of Guidance Navigation and Control Lulav Space Ltd. Haatzmaut 43 Haifa 3303322 Israel Faculty of Aerospace Engineering Technion-Israel Institute of Technology Haifa 32000 Israel

This paper proposes an improved method for distributed consensus Kalman filtering (DCKF). We introduce a minor modification to the consensus kalman filter proposed in (Olfati-Saber (2009)). Namely an extra averaging term is introduced into the filter update equations. In this direction, we propose a decentralized consensus gain that can be computed by each agent in the sensor network, and depends only on local properties of the network, i.e., the number of neighbors of each sensor. Moreover we prove that this scheme is stable for networks with time varying communication regime. Our results are compared to other existing solutions in the literature with a numerical example.

关键词： Sensor networks Estimation and filtering Distributed control and estimation Cooperative systems distributed Kalman filtering

来源：评论

学校读者我要写书评

暂无评论

Safe reinforcement learning task planning with uncertain duration and resource consumption in limited daytime for lunar rovers

Safe reinforcement learning task planning with uncertain dur...

引用

2024 IAF Space Operations Symposium at the 75th International Astronautical Congress, IAC 2024

作者： Lu, Siyao Xu, Rui Gao, Ai Li, Zhaoyu Liu, Jiamou Zhang, Libo Zhao, Zhijun Zhu, Shengying Li, Yuqiong School of Aerospace Engineering Beijing Institute of Technology 5th Zhongguancun South Street Haidian Distinct Beijing Beijing100081 China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration Beijing Institute of Technology Ministry of Industry and Information Technology Beijing100081 China School of Computer Science University of Auckland 34 Princes Street Auckland1010 New Zealand Beijing Institute of Spacecraft Engineering Beijing Beijing100094 China Institute of Mechanics Chinese Academy of Sciences 15th North Fourth Ring West Road Haidian District Beijing100190 China

ISBN: (纸本)9798331312183

The International Lunar Research Station will be established near the south pole through advanced unmanned rovers at the beginning period. The south pole of the moon has short daytime, so the efficiency of remote control is inadequate. However, the duration and power resource usage of the lunar rover moving on the lunar surface remains uncertain because of different loading weight of collection and changes of terrain in moving. What’s more, a lunar rover needs to move back to the base before nighttime without sunlight to provide energy, while the whole time of working on the moon also needs optimization. We select to solve the planning problem with reinforcement learning (RL) due to its capability in tackling uncertainty and optimization. However, traditional reinforcement learning cannot guarantee safety with time uncertainty, resource uncertainty, and constraints due to the soft constraints in optimization. Therefore, we propose a new way through safe reinforcement learning of task planning and resource collection optimization among tasks with uncertain duration and resource collection. We consider a scenario of in-situ material utilization for the lunar base, where there are tasks of moving, charging, collecting, material delivering, and material receiving, all of which have uncertain duration in execution and every task must be done during the daytime except the charging. Resource collection is related to power consumption in moving so it will be decided according to the remaining power. We further propose an architecture on reinforcement learning to let rovers decide the next step instantaneously according to the expected task duration, the remaining time, and the remaining power. Maximizing the amount of material delivered is an optimization target in training while keeping the rovers safe to work only in the daytime without an empty battery. In our experiment, we intend that our way works well in the uncertainties, and it will lead the rover to finish tasks w

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving Formation Maneuvering of Unmanned Surface Vehicles: A Finite-Time Distributed Approach with Velocity Constraints

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Wang, Ping Yu, Chengpu Lv, Maolong Park, Ju H. School of Automation Beijing Institute of Technology Beijing China College of Air Traffic Control and Navigation Air Force Engineering University Xi'an China Department of Electrical Engineering Yeungnam University Kyongsan Republic of Korea

This paper presents a novel approach for addressing the finite-time distributed formation maneuvering (FTDFM) of multiple unmanned surface vehicles (USVs), which takes into account the challenges posed by velocity and error constraints. Each USV is subject to parameter uncertainty, ocean disturbance, actuator fault, and input saturation, making the task of achieving reliable and accurate formation particularly challenging. To overcome these challenges and meet practical requirements, a finite-time (FT) performance function is selected as the constraint function, which ensures that the velocity and error of each USV stay within a given bounded set within a known time. Using FT stability theory, a new framework is proposed that integrates a tangent-type barrier function and an improved backstepping approach to handle uncertainties and constraints. In this approach, a tracking differentiator (TD) is introduced to replace the virtual controller's derivative, and a smooth function is used to address the input saturation, effectively reducing the complexity and dynamic order of the algorithm. The proposed controller is capable of ensuring the realization of the desired formation within a finite time while maintaining the constraints without deviation. Additionally, by using the auxiliary variable technique, the proposed control method can also be applied to USVs with underactuated models. Simulation examples are provided to demonstrate the efficacy of the proposed control algorithm in achieving accurate and reliable formation maneuvering of multiple USVs under various constraints. IEEE

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

Multi-Yolov8: An Infrared Motion Object Detection Model Based on Yolov8 for Air Vehicle

SSRN

引用

SSRN 2023年

作者： Sun, Shizun Mo, Bo Xu, Junwei Li, Dawei Zhaoa, Jie Han, Shuo School of Aerospace engineering Beijing Institude of Technology Beijing China Southwest Institute of Technical Physics Chengdu China North Navigation Control Technology Company Beijing China

The detection of infrared motion objects faces significant challenges in object detection for air vehicles. These objects typically occupy a relatively small number of pixels within the infrared system, resulting in limited feature information, significant feature loss, reduced recognition accuracy, and difficulties in single-frame detection. To tackle these challenges, this paper proposes an efficient multi-input method called Multi-YOLOv8, built upon the YOLOv8s model. Firstly, this method uses current frames as the primary input and incorporates optical flow processing images and background suppression images as auxiliary inputs to enhance detection performance. An improved method for optical flow computations is proposed, referred to as the pyramidal Weight-Momentum Horn-Schunck (PWMHS) method, which is used to perform optical flow processing efficiently and accurately. Secondly, an enhanced version of Wise-IoU (WIoU) v3, referred to as α*-WIoU v3, is proposed as the bounding box regression loss to optimize the network. Thirdly, BiFormer module is introduced to improve the focus on critical information in the model. This paper introduces a new module called GSC2f, which utilizes the lightweight convolution GSConv to replace Conv layers in C2f module, aiming at balancing computational load and improving detection performance. Lastly, a small object detection layer is added to boost the capacity for small object detection. After assessment on an open-access dataset, the comprehensive experiments reveal that our model outperforms other mainstream models in overall performance. The method significantly enhances the detection ability of infrared small motion objects. © 2023, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

含有不确定参数结构的数据驱动载荷识别方法

引用

Acta Mechanica Sinica 2024年第2期40卷 199-213页

作者：崔文旭姜金辉孙慧玉杨泓基王旭王立辉李鸿秋 State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and AstronauticsNanjing210016China College of Mechanical and Electronic Engineering Nanjing Forestry UniversityNanjing210037China Key Laboratory of Micro-Inertial Instrument and Advanced Navigation Technology Ministry of EducationSoutheast UniversityNanjing210016China Mechatronic Engineering College Jinling Institute of TechnologyNanjing211169China

动载荷识别在结构设计和优化中起着至关重要的作用目前的大多数研究都集中在确定性结构上.然而,实际工程结构中的结构参数是未知的.不确定参数的存在会导致载荷识别结果与实际载荷值之间的误差,因此研究不确定结构的动载荷识别问题至关... 详细信息

动载荷识别在结构设计和优化中起着至关重要的作用目前的大多数研究都集中在确定性结构上.然而,实际工程结构中的结构参数是未知的.不确定参数的存在会导致载荷识别结果与实际载荷值之间的误差,因此研究不确定结构的动载荷识别问题至关重要的.本文针对含有不确定参数的结构,提出了一种数据驱动的动载荷识别方法.首先,将不确定参数由一组闭区间向量表征.然后引入卷积神经网络(CNN)对未知载荷区间进行重构.将区间分析理论与泰勒展开相结合,得到了监督载荷的上下边界,并将其用作训练样本.最后,训练后的CNN模型直接识别未知载荷区间的边界.仿真结果表明,该方法具有较高的载荷识别精度和对噪声的鲁棒性.我们构造了一个简支梁结构进行实验,以进一步验证所提出方法在工程中的可行性.此外,我们还讨论了测量点分布和样本数量对识别精度的影响,这有利于在工程实践中的应用。

关键词：数据驱动载荷识别不确定结构不确定参数样本数量泰勒展开测量点分布闭区间

来源：评论

学校读者我要写书评

暂无评论

Dynamic Data Processing Method of Gravity Gradiometer Based on Equivalent Source

Dynamic Data Processing Method of Gravity Gradiometer Based ...

引用

2022 DGON Inertial Sensors and Systems, ISS 2022

作者： Da, Li Lin, Zhao Haina, Weng Chengsuo, Li Zhi, Pei Jia, Chen College of Intelligent Systems Science and Engineering Harbin Engineer University Nangang District Harbin150001 China Tianjin Navigation Instrument Research Institute Xianyang Hongqiao District Tianjin300131 China State Shipbuilding Corporation Xianyang Laboratory of Science and Technology on Marine Navigation and Control of China Hongqiao District Tianjin300131 China

ISBN: (数字)9781665490214

ISBN: (纸本)9781665490214

The gravity gradiometer is an instrument that continuously measures the small gravity gradient changes on the earth's surface. The actual output signal of the system contains a lot of noise, and the signal-to-noise ratio is extremely low due to the limitations of the process and performance level of the core sensitive element accelerometer, and the installation errors of multiple links. In order to effectively extract the real gravity gradient signal from the strong noise, a gravity gradient noise reduction method based on the equivalent source model is proposed by using the basic principle that the earth's gravity field is a conservative force field. First, according to the relationship between the rectangular prism and the gravity gradient, the analytical model of the equivalent source is derived, and the regression equation of the equivalent source is established. Aiming at the ill conditioned problem of regression operators, Tikhonov regularization method is proposed, and the optimal regularization parameters are determined by L-curve method, which can reduce the noise of gravity gradient measurement by an order of magnitude in simulation. Using this method to process the measured data of the shipborne test, the results show that this method has an obvious effect on suppressing the dynamic measurement noise of the gravity gradiometer, and can reduce the internal coincidence mean square error of the horizontal tensor gravity gradient measurement signal by 58%, which is of engineering significance. © 2022 IEEE.

关键词： Mean square error

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：