检索结果-内蒙古大学图书馆

Study on the Shock Resistance of Double-Layer Vibration Isolation system for Ship Power Equipment

学校读者我要写书评

暂无评论

Study on the Shock Resistance of Double-Layer Vibration Isol...

China Instrument and Control Society (ACCIS), Academic Conference of

作者： Zhongyi Cheng Junning Cui Xinbin Zhang Yizhong Zhuang Bo Kang Yamin Zhao Center of Ultra-precision Optoelectronic Instrument Engineering Harbin Institute of Technology Harbin China Key Lab of Ultra-precision Intelligent Instrumentation Harbin Institute of Technology (Harbin Institute of Technology) Ministry of Industry and Information Technology Harbin China Laboratory for Space Environment and Physical Sciences Harbin Institute of Technology Harbin China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (数字)9798350350326

ISBN: (纸本)9798350350333

Given the problem that the influences of different vibration isolation parameters on the dynamic characteristics of isolated equipment in the double-layer vibration isolation system of ship power equipment is still unclear, a double-layer vibration isolation model for ship power equipment is established to study the time-domain response characteristics of the isolated equipment under the action of a half-sine wave shock. The dimensionless differential equations of system motion are derived using dimensional analysis, and the numerical simulation based on the fourth-order Runge-Kutta method is used to analyze the influences of vibration isolation parameters on shock resistance performance of the system, which provides a theoretical basis for the shock resistance design of the double-layer vibration isolation system of ship power equipment and is of significant instruction to the practice.

关键词： Vibrations Resistance Damping Isolators Electric shock Numerical simulation Shock absorbers Numerical models Marine vehicles Time-domain analysis

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

Operational Concept and Design of Multiple AUVs for Rapid Underwater Investigation in Case of Maritime Accidents

学校读者我要写书评

暂无评论

Operational Concept and Design of Multiple AUVs for Rapid Un...

OCEANS

作者： Sea-Moon Kim Hyuk Baek Pan-Mook Lee Byeong-Woong Choi Ho-Seong Kim Jin-Ho Kim Min-Sik No Hyeong-Moon Park Seong-Hee Hong Ji-Hong Li Hyeong-Joo Kang Seong-Yong Moon Bo-Hyeong Jo Myeong-Cheol Jung Ocean and Maritime Digital Technology Research Division Korea Research Institute of Ships and Ocean Engineering Korea Hanwha System Cooperation Korea Kyeongin Technology Co. Korea BNSoft Co. Korea Korea Institute of Robotics and Technology Convergence Korea Sonartech Co. Korea Giga RF Korea

ISBN: (数字)9798331540081

ISBN: (纸本)9798331540098

After a helicopter crash off Dokdo Island in 2019, Korea Coast Guard (KCG) decided to develop an unmanned vehicle system capable of underwater survey even in harsh marine environments. The whole system consists of four small-sized AUVs equipped with side scan sonars (SSS AUVs), a mid-sized AUV with synthetic aperture sonar (SAS AUV), an integrated mission control system (MCS), and sensor data post-processing module (DPP). An unmanned surface vehicle (USV) and a robot buoy (RBB) are also included for real-time monitoring or data transmission with underwater acoustic modems and RF communication systems. Each system design has been completed and manufactured, and performance tests and demonstrations based on scenarios by KCG will be conducted from this year.

关键词： Surveys Radio frequency Sea surface Robot sensing systems Real-time systems Synthetic aperture sonar Underwater acoustics Autonomous vehicles system analysis and design Accidents

Rediscovering BCE Loss for Uniform Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Computer Vision Institute Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China

This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model’s performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classification datasets and three feature extraction models show that, compared to the SoftMax loss, the models trained with the BCE loss not only exhibit higher uniform classification accuracy but also higher sample-wise classification accuracy. In addition, the learned bias from BCE loss is very close to the unified threshold used in the uniform classification. The features extracted by the models trained with BCE loss not only possess uniformity but also demonstrate better intra-class compactness and inter-class distinctiveness, yielding superior performance on open-set tasks such as face recognition. © 2024, CC BY.

关键词： Classification (of information)

Active Virtual Mass Micro-Vibration Isolation Control Method based on Two-Parameter Acceleration Feedback 15

学校读者我要写书评

暂无评论

Active Virtual Mass Micro-Vibration Isolation Control Method...

15th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2021

作者： Wang, Jing Wang, Lei Li, Junzhong Yang, Yuanyuan Bian, Yujian Zhou, Bin School of instrumentation science and engineering Harbin Institute of Technology Harbin China Chinese Academy of Sciences Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen China Heilongjiang Research Institute of Territory's Spatial Planning Harbin China

ISBN: (纸本)9781665444910

External interference is an important factor affecting the accuracy and stability of precision equipment. An active micro-vibration isolation control method is proposed and used in active vibration control to suppress external interference in this paper. This method is based on two-parameter acceleration feedback, which splits the acceleration feedback gain into two parameters, one on the front path and one on the feedback path. Compared with the traditional acceleration feedback, the proposed method not only increases the virtual mass of the system to reduce the natural frequency, but also suppresses the excessive motor output in the vibration isolation system simultaneously. Simulation results proved the effectiveness of the proposed two-parameter acceleration feedback control method in preventing excessive motor output, and experimental results confirm its capacity to reduce the natural frequency of the system. © 2021 IEEE.

关键词： Natural frequencies

Multi-kernel Correntropy Regression: Robustness, Optimality, and Application on Magnetometer Calibration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Shilei Chen, Yihan Lou, Yunjiang Shi, Dawei Li, Lijing Shi, Ling The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen518055 China The School of Automation Beijing Institute of Technology China The School of Information and Control Engineering China University of Mining and Technology China

This paper investigates the robustness and optimality of the multi-kernel correntropy (MKC) on linear regression. We first derive an upper error bound for a scalar regression problem in the presence of arbitrarily large outliers and state that the kernel bandwidth plays an important role in minimizing the lowest upper error bound. Then, we find that the proposed MKC is related to a specific heavy-tail distribution, where its head shape is consistent with the Gaussian distribution but its tail shape is heavy-tailed, and the extent of heavy-tail is controlled by the kernel bandwidth. It becomes a Gaussian distribution when the bandwidth is infinite, which allows one to tackle both Gaussian and non-Gaussian problems without explicitly investigating the noise distributions. To explore the optimal underlying distribution parameters, an expectation-maximization-like (EM) algorithm is developed to estimate the parameter vectors and the distribution parameters in an alternating manner. The results show that our algorithm can achieve equivalent performance compared with the traditional linear regression under Gaussian noise, and it significantly outperforms the conventional method under heavy-tailed noise. Both numerical simulations and experiments on a magnetometer calibration application verify the effectiveness of the proposed method. Note to Practitioners-The goal of this paper is to enhance the accuracy of conventional linear regression in handling outliers while maintaining its optimality under Gaussian assumptions. Our algorithm is formulated under the maximum likelihood estimation (MLE) framework, assuming the regression residuals follow a type of heavy-tailed noise distribution with an extreme case of Gaussian. The degree of the heavy tail is explored alternatingly using an Expectation-Maximization (EM) algorithm which converges very quickly. The robustness and optimality of the proposed approach are investigated and compared with the traditional approaches. Both th

关键词： Linear regression

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and Simulation for Children with Cerebral Palsy

学校读者我要写书评

暂无评论

Exoskeleton-Based Lower Limb Rehabilitation Robot Design and...

World Rehabilitation Robot Convention (WRRC)

作者： Wujing Cao Shuo Zhang Yupeng Zou Xinqiang Guo Changyu Li Jingxin Wang Worawarit Kobsiriphat Xinyu Wu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China and SIAT-CUHK Joint Laboratory of Robotics and Intelligent Systems. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Mechanical Engineering China University of Petroleum East China Jining Zhongke Intelligent Technology Co. Ltd. Department of Rehabilitation Medicine Zhengzhou Central Hospital Affiliated Zhengzhou University Zhengzhou China National Metal and Materials Technology Center Thailand

ISBN: (数字)9798350355123

ISBN: (纸本)9798350355130

Squat gait is the most common abnormal gait in children with cerebral palsy. Gait training with lower limb rehabilitation robots can improve rehabilitation efficiency and reduce manual labor for them. A novel exoskeleton-based lower limb rehabilitation robot for children with cerebral palsy is proposed, considering the squat gait characteristics of children with cerebral palsy. The structure of the lower limb rehabilitation robot, which combines hip and knee with 4 active degrees of freedom exoskeleton and mobile walker, is designed and optimized. Static analysis of the key mechanical structure of the exoskeleton is conducted using ANSYS Workbench, and local structures are optimized to ensure the safety factor of the mechanical structure is greater than 1, guaranteeing reasonable structural strength and stiffness design. Dynamic simulation analysis based on the ADAMS model validates the reliability and dynamic walking effect of the lower limb exoskeleton rehabilitation robot, obtaining the curve relationship between joint angles and motion cycles, thus verifying the effectiveness of the mechanical system motion.

关键词： Knee Training Cerebral palsy Exoskeletons Dynamics Static analysis Assistive robots Safety Finite element analysis Hip

A Triboelectric Multifunctional Sensor Based on the Controlled Buckling Structure for Motion Monitoring and Bionic Tactile of Soft Robots

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Xu, Jinsui Xie, Zhijie Yue, Honghao Lu, Yifan Yang, Fei State Key Laboratory of Robotics and System School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China College of mechanical and electrical engineering Northeast Forestry University Harbin150042 China

Soft robots have unlimited degrees of freedom, which limits the application of traditional sensors in the field of soft robots. Therefore, continuous motion monitoring and tactile feedback for soft robots have been challenging. To address this challenge, this paper proposes a multifunctional sensor by combining controlled buckling structure with triboelectric nanogenerator for the first time to detect and control grasping, realize two-dimensional (2D) planar motion, and achieve adaptive obstacle avoidance in soft robots. A 2D kirigami electrode is compressed and buckled into a stretchable three-dimensional (3D) structure by pre-stretching the substrate. The proposed soft grasping system sensor can detect the bending angle of a soft gripper to identify the size of a grasped object, achieving a detection accuracy of 91.67%. By alternately arranging the buckling electrodes to form a 2D spatial decoupling structure, the 2D motion sensor (2DMS) can detect the movement direction and real-time position of a robot with an accuracy rate of 83.33%. Using the compressible properties of the buckling 3D structure, the inchworm-like soft robot (I-LSR) tactile sensor can sense the surrounding environment, thereby realizing dynamic obstacle avoidance. The proposed novel multifunctional triboelectric sensor by combining the properties of controlled buckling structure provides a theoretical and experimental basis for high-precision motion detection and intelligent obstacle avoidance for soft robots. © 2022, The Authors. All rights reserved.

关键词： Buckling

Adjacency-hopping de Bruijn Sequences for Non-repetitive Coding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Bin Liang, Zhenglin Wu, Shiqian The Institute of Robotics and Intelligent Systems School of Information Science and Engineering Wuhan University of Science and Technology Wuhan430081 China The Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan430072 China

A special type of cyclic sequences named adjacency-hopping de Bruijn sequences is introduced in this paper. It is theoretically proved the existence of such sequences, and the number of such sequences is derived. These sequences guarantee that all neighboring codes are different while retaining the uniqueness of subsequences, which is a significant characteristic of original de Bruijn sequences in coding and matching. At last, the adjacency-hopping de Bruijn sequences are applied to structured light coding, and a color fringe pattern coded by such a sequence is presented. In summary, the proposed sequences demonstrate significant advantages in structured light coding by virtue of the uniqueness of subsequences and the adjacency-hopping characteristic, and show potential for extension to other fields with similar requirements of non-repetitive coding and efficient matching. Copyright © 2023, The Authors. All rights reserved.

关键词：