检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Zhang, Zhiwei Zhuang, Yan Liang, Zhida Kong, Shuai Zhu, Shengyi School of Control Science and Engineering Dalian University of Technology Dalian China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Special Equipment Safety Testing Technology of Zhejiang Province Zhejiang Academy of Special Equipment Science Hangzhou China

ISBN: (纸本)9798331516147

High-current out-of-phase closed bus is an essential link in the transmission of electric energy and is widely used in thermal power stations, hydropower stations and nuclear power plants. Although these busbars have the advantages of excellent dustproof effect and strong magnetic shielding, they are susceptible to insulator aging and damage in long-term operation, posing a potential safety risk to the power grid. Due to the enclosed space inside the bus and the complexity of external maintenance tasks, manual inspection has problems such as inefficiency and low safety. In order to solve these problems, this paper proposes an improved detection algorithm based on Yolov7 for insulator defect detection in hydropower station scenarios. Because of the particularity of Yolov7 network structure and application scenarios, this paper proposes a Channel Feature Enhancement module to enhance the channel representation ability of the network. In addition, an Edge Feature Enhancement module is introduced to improve the boundary detection of insulators by enhancing the contrast between the target and the background. Considering the limitations of existing studies in specific scenarios and the scarcity of dataset, this paper constructs and accurately annotates an insulator defect detection dataset applied to hydropower station scenarios. Experimental results show that the improved-Yolov7-tiny algorithm in this paper achieves a balance between accuracy and inference speed. © 2025 IEEE.

关键词： Magnetic shielding

来源：评论

学校读者我要写书评

暂无评论

A Flexible Piezoelectric-based Tactile Sensor for Dynamic Force Measurement 4

A Flexible Piezoelectric-based Tactile Sensor for Dynamic Fo...

引用

4th International Conference on High Performance Big Data and Intelligent Systems, HDIS 2022

作者： Xiang, Guiyao Wang, Xiaoxin Cheng, Nengyuan Hu, Liang Zhang, Hongwei Liu, Honghai School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China Harbin Institute of Technology Shenzhen State Key Laboratory of Robotics and System Shenzhen China

ISBN: (数字)9781665491440

ISBN: (纸本)9781665491440

Force measurement is important in the robotic manipulation tasks, and it is an essential property of specific tactile sensor. An increasing number of studies demonstrated the capacity of tactile sensor in force measurement. However, most of the works focus on the static force measurement, the precise track of dynamic force is hard to be accomplished. Compared with traditional piezoresistive sensors, piezoelectric-based tactile sensors have advantages in low energy consumption and high sensitivity. This paper developed a flexible multi-layer piezoelectric-based tactile sensor inspired by the structure of skin. The size of sensor with a 3×3 sensing element array was designed to match that of a finger. The signal processors and logical algorithms were integrated to sense and distinguish the size, location and pattern of different external force stimuli in real time, including pressure intensity and vibration frequency. Two experiments about pressure sensing and vibration sensing show that the proposed tactile sensor with finger-like force range, high sensitivity and fast response time. The range of measured force amplitude and frequency were 0.1N-2N and 0.1Hz-100Hz. Another characteristic, the response time, was less than 50ms. In addition, the sensor array has a spatial resolution of 4 mm. This work has driven the development of tactile sensor for dynamic force measurement in real-Time robotic grasping. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Nanosecond pulsed laser-assisted modified copper surface structure:Enhanced surface microhardness and microbial corrosion resistance

引用

Journal of Materials Science & Technology 2022年第12期107卷 111-123页

作者： Boxin Wei Jin Xu Liqun Gao Hui Feng Jiajun Wu Cheng Sun Zhenyao Wang Wei Ke School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China Liaoning Shenyang Soil and Atmosphere Material Corrosion National Observation and Research Station Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110169China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China

Microbiologically influenced corrosion(MIC) is an unavoidable problem in several industries. Copper(Cu)and its alloys are widely used engineering materials. However, MIC of Cu remains a persistent challenge to their performance and functional lifetime under aggressive environments. This study investigated nanosecond pulsed laser processing(LP), which may enhance the corrosion resistance of Cu. The microstructural evolution and corrosion behavior of LP-Cu in the presence of sulfate-reducing bacteria(SRB) were evaluated. Typical deformation-induced microstructural features of high-density dislocations were analyzed on the top surface of LP-Cu coupon. Electrochemical measurements suggested that LP-Cu coupons exhibited better corrosion resistance in SRB-inoculated solution compared with their original counterpart. The enhanced corrosion resistance by LP primarily resulted from the combined influences of compressive residual stress and work hardening in the surface. However, overlap percentage played a key role in improving corrosion resistance. LP produced optimal corrosion resistance at 50% overlap. Therefore, this study introduces a unique and an option for anticorrosion control in manufacturing processes and potentially implements it onto other materials to improve its microbial corrosion resistance through LP.

关键词： Pure copper Laser processing Microbiologically influenced corrosion Pitting Severe plastic deformation

来源：评论

学校读者我要写书评

暂无评论

An Environmental-Complexity-Based Navigation Method Based on Hierarchical Deep Reinforcement Learning

An Environmental-Complexity-Based Navigation Method Based on...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Pengbin Chen Qi Liu Yanjie Li Shuaikang Ma Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation The Harbin Institute of Technology Shenzhen China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Navigation methods based on deep reinforcement learning (RL) have recently exhibited superior performance, particularly for navigation in dynamic environments. However, most existing methods solely rely on deep neural network feature encoders to extract features from raw LiDAR data, lacking an explicit representation of environmental structure. This limitation hinders effective environmental representation and interpretability, constraining navigation performance improvement. To solve this problem, we propose two quantitative metrics based on laser scans, which explicitly represent environmental complexity and show great interpretability. Furthermore, we propose an environmental-complexity-based navigation method based on hierarchical deep RL with the proposed metrics. Experimental results show that the proposed method achieves better navigation performance than baselines, especially in challenging scenarios with corners and dynamic obstacles.

关键词： Measurement Laser radar Navigation Lasers Artificial neural networks Feature extraction Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Teleoperation of Multi-functional Neurosurgical Tool∗ 5

Teleoperation of Multi-functional Neurosurgical Tool∗

引用

5th World Robot Conference Symposium on Advanced robotics and automation, WRC SARA 2023

作者： Ma, Xudong Yao, Lechen Chen, Anqi Wang, Junchen Li, Changsheng Liu, Wenyong Hu, Yida David Su, Bai-Quan Beijing University of Posts and Tele-communications Medical Robotics Laboratory School of Automation Beijing100876 China Affiliated High School of Peking University Beijing100190 China Beihang University School of Mechanical Engineering and Automation Beijing100083 China School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Beihang University Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beijing100083 China Brigham and Women's Hospital Harvard Medical School BostonMA02115 United States

ISBN: (纸本)9798350307320

Fluid removal and electrotome coagulation are routine procedures in neurosurgery operations, and the doctor's remote control can reduce physical fatigue. In this paper, an integrated multi-functional surgical tool which can realize electrocoagulation and liquid aspiration is designed. At the same time, the multi-functional integrated surgical device is combined with the remote operation method to realize the remote operation of the instrument. This multifunctional instrument includes CCD-imaging, suction and electrical coagulation. The system can complete the remote operation function of the special design tool, and can isolate the doctor from the operation. The teleoperation of this instrument is integrated with the teleoperation of other functional instruments to realize the teleoperation of the complete surgical process. © 2023 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Implementation of data transmission mechanism in a Bi-directional optical fiber network

引用

Journal of Optical Communications 2025年

作者： Gummadi, Dinesh Venkat Karanam, Harish Naidu Samudrala, Sivanaga Akshaya Nampally, Harshavardhan Prasanna Preethi Priya Darshini, Sagabala Sindhwani, Manoj Sachdeva, Shippu Shukla, Manoj Kumar School of Electronics and Electrical Engineering Lovely Professional University Punjab Phagwara India Department of Robotics and Automation Symbiosis Institute of Technology Symbiosis International Deemed University Pune India

Passive optical network (PON) has become the leader in delivering broadband high-speed connectivity. The paper introduces a detailed description of PON, its working principle, key features, and their potential applications. In addition, we discuss the types of PON architectures including GPON, EPON, and XG-PON with merits and demerits. Finally, we discuss the technical considerations of PONs in data transmission mechanisms, network design, and component selection. This paper further demonstrates the use of PON technology via a case study on the design and implementation of a bidirectional optical fiber network. Within this project, we went ahead to demonstrate the use of PON components including optical splitters, transmitters, receivers, and power controllers towards the development of an efficient and functional network structure. It mainly covered the results of the project since the PONs appeared to be a promising solution for obtaining high-performing and reliable broadband services. © 2025 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery 38

Happy: A Debiased Learning Framework for Continual Generaliz...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Shijie Zhu, Fei Zhong, Zhun Liu, Wenzhuo Zhang, Xu-Yao Liu, Cheng-Lin MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. Although several settings are proposed to study the C-GCD task, they have limitations that do not reflect real-world scenarios. We thus study a more practical C-GCD setting, which includes more new classes to be discovered over a longer period, without storing samples of past classes. In C-GCD, the model is initially trained on labeled data of known classes, followed by multiple incremental stages where the model is fed with unlabeled data containing both old and new classes. The core challenge involves two conflicting objectives: discover new classes and prevent forgetting old ones. We delve into the conflicts and identify that models are susceptible to prediction bias and hardness bias. To address these issues, we introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization. For the prediction bias, we first introduce clustering-guided initialization to provide robust features. In addition, we propose soft entropy regularization to assign appropriate probabilities to new classes, which can significantly enhance the clustering performance of new classes. For the harness bias, we present the hardness-aware prototype sampling, which can effectively reduce the forgetting issue for previously seen classes, especially for difficult classes. Experimental results demonstrate our method proficiently manages the conflicts of C-GCD and achieves remarkable performance across various datasets, e.g., 7.5% overall gains on ImageNet-100. Our code is publicly available at https://***/mashijie1028/Happy-CGCD. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Locomotion Control of Biped Robot with Foot Described on SE(3)*

Locomotion Control of Biped Robot with Foot Described on SE(...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Kun Xu Minghao Xu Yuanyang Cui Gang Liu Wei Lou Jiawei Chen Qikai Li Cheng Chen Long Li Xilun Ding School of Mechanical Engineering and Automation Beihang University Beijing China Aubo (Beijing) Robotics Technology CO. LTD Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

The unique challenge of the humanoid biped robot is the locomotion control of humanoid feet which is not a simple point-contact model. A new dynamics control based on model predictive control and whole-body control of a humanoid biped robot is proposed to achieve stable locomotion of the body and feet. To control the position and orientation of feet with no singularity, the locomotion of the foot is described on $S E(3)$ using exponential mapping. Firstly, the velocity screw is used as the swing and supporting foot constraint in the model predictive control to achieve the trajectory optimization of feet. Then, the task of the supporting foot which should be no relative motion with the ground uses the velocity screw as the description. To achieve the following orientation between the body and swing feet, the acceleration task of the swing foot utilizes the rigid model. Finally, the proposed method for a humanoid biped robot is verified and effectively controls the orientation of robot feet to achieve stability walking in the simulation.

关键词： Legged locomotion Mechatronics Robot kinematics Simulation Humanoid robots Fasteners Stability analysis Trajectory optimization Foot Predictive control

来源：评论

学校读者我要写书评

暂无评论

Modular design automation of the morphologies, controllers, and vision systems for intelligent robots: a survey

引用

Visual Intelligence 2023年第1期1卷 1-28页

作者： Li, Wenji Wang, Zhaojun Mai, Ruitao Ren, Pengxiang Zhang, Qinchang Zhou, Yutao Xu, Ning Zhuang, JiaFan Xin, Bin Gao, Liang Hao, Zhifeng Fan, Zhun International Cooperation Base of Evolutionary Intelligence and Robotics Guangdong Shantou China Department of Electronic Information Engineering Shantou University Shantou 515063 China School of Automation Beijing Institute of Technology Beijing 100081 China School of Mechanical Science & Engineering HUST Huazhong University of Science and Technology Wuhan 430074 China College of Science Shantou University Shantou 515063 China

Design automation is a core technology in industrial design software and an important branch of knowledge-worker automation. For example, electronic design automation (EDA) has played an important role in both academia and industry. Design automation for intelligent robots refers to the construction of unified modular graph models for the morphologies (body), controllers (brain), and vision systems (eye) of intelligent robots under digital twin architectures, which effectively supports the automation of the morphology, controller, and vision system design processes of intelligent robots by taking advantage of the powerful capabilities of genetic programming, evolutionary computation, deep learning, reinforcement learning, and causal reasoning in model representation, optimization, perception, decision making, and reasoning. Compared with traditional design methods, MOdular DEsigN automation (MODENA) methods can significantly improve the design efficiency and performance of robots, effectively avoiding the repetitive trial-and-error processes of traditional design methods, and promoting automatic discovery of innovative designs. Thus, it is of considerable research significance to study MODENA methods for intelligent robots. To this end, this paper provides a systematic and comprehensive overview of applying MODENA in intelligent robots, analyzes the current problems and challenges in the field, and provides an outlook for future research. First, the design automation for the robot morphologies and controllers is reviewed, individually, with automated design of control strategies for swarm robots also discussed, which has emerged as a prominent research focus recently. Next, the integrated design automation of both the morphologies and controllers for robotic systems is presented. Then, the design automation of the vision systems of intelligent robots is summarized when vision systems have become one of the most important modules for intelligent robotic systems. Then

关键词： Bond graph Evolutionary computation Intelligent robots Modular design automation Neural architecture search

来源：评论

学校读者我要写书评

暂无评论

A Risk-sensitive Automatic Stock Trading Strategy Based on Deep Reinforcement Learning and Transformer

A Risk-sensitive Automatic Stock Trading Strategy Based on D...

引用

IEEE International Conference on automation Science and engineering (CASE)

作者： Linyu Li Qi Liu Yanjie Li Yongjin Mu Zheng Zhang Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation the Harbin Institute of Technology Shenzhen China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Navigating the world of stock trading can be a daunting task, with its high risk, high reward potential, and intricate market dynamics. For investors and financial researchers, making informed investment decisions is essential. To our knowledge, limited by insufficient feature representation in highly dynamic trading scenarios, existing rule-based and machine learning-based methods struggle to extract complex intrinsic information from the stock market. Thus, with the huge success of reinforcement learning (RL) in sequential decision-making tasks and the powerful feature extraction capabilities of Transformer, this paper proposes an automatic stock trading method based on RL and Transformer. First, data from multiple stocks are collected into Transformer to extract the correlations among stocks. Then, the output of Transformer is used as the state input for deep RL, and the trading action is obtained. Furthermore, we propose a risk-sensitive reward function by adding the turbulence index to avoid risk. Experimental results on Dow Jones 30 constituent stocks show that the proposed method outperforms baselines regarding profit, risk, and comprehensive indicators.

关键词： Measurement Learning systems Navigation Transformers Feature extraction Solids Indexes Data mining Stock markets Investment

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：