检索结果-内蒙古大学图书馆

Understanding the Machining Process of Hierarchical Micro/Nanograting Structures Used for Optical Variable Device

Chinese Journal of Mechanical engineering 2025年第1期38卷 161-185页

作者： Yanquan Geng Wenhan Zhu Xiaosong Zhang Aoxiang Zhang Yongda Yan Hailong Cui Bo Xue Jiqiang Wang TState Key Laboratory of Robotics and Systems Robotics InstituteHarbin Institute of TechnologyHarbin 150080China Sichuan Precision and Ultra-Precision Machining Engineering Technology Center Chengdu 610200China College of Mechanical and Electrical Engineering Northeast Forestry UniversityHarbin 150040China

Hierarchical micro/nanograting structures have attracted increasing attention owing to their significant applications in the fields of structural coloring,anti-counterfeiting,and ***,the fabrication of hierarchical micro/nanograting structures is important for these *** this study,a strategy for machining hierarchical micro/nanograting structures is developed by controlling the tool movement trajectory.A coupling Euler-Lagrange finite element model is established to simulate the machining *** effect of the machining methods on the nanograting formation is demonstrated,and a suitable machining method for reducing the cutting force is *** height of the nanograting decreases with an increase in the tool edge ***,optical variable devices(OVDs)are machined using an array overlap machining *** schemes for the parallel column unit crossover and column unit in the groove crossover are designed to achieve high-quality machining of *** coloring of the logo of the Harbin institute of Technology and the logo of the centennial anniversary of the Harbin institute of Technology on the surface of metal samples,such as aluminum alloys,is *** findings of this study provide a method for the fabrication of hierarchical micro/nanograting structures that can be used to prepare OVDs.

关键词： Hierarchical micro/nanograting structures Optical variable devices Finite element simulation Tool trajectory controlling

来源：评论

学校读者我要写书评

暂无评论

引用

43rd Chinese Control Conference, CCC 2024

作者： Chen, Zhen-Peng Li, Hong-Yue Song, Tian-Shu Hou, Hui-Rang Meng, Qing-Hao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin300072 China

ISBN: (纸本)9789887581581

Detecting ignitable liquids (ILs) at the fire scene is essential for fire investigation. Electronic nose (e-nose) plays a crucial role in the detection of ILs due to its low cost and rapid response. However, when we used different e-noses with the same sensor array (i.e., identical model and number of gas sensors) and running the same algorithm to identify the same ILs, we found that the identification results were different because of the poor consistency of the gas sensors used in the e-noses. To address the issue of ILs identification across e-noses, we built a platform for sensor similarity detection, which is used to reject sensors with large differences. Based on this platform, we constructed a similarity dataset using eight types of gas sensors (each containing eight sensors) to collect samples of four ILs (ethanol, gasoline, diesel and thinner). Moreover, a multi-branch residual convolutional neural network for evaluating sensor similarity was proposed. Comparative experiments on the dataset show that compared with the two-dimensional convolutional neural network (2D-CNN) and multilayer perceptron (MLP), the average accuracy of similarity evaluation of our method is improved by 13.1 % and 3.23 %, respectively. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Renewable Energy Forecasting Using CNN-LSTM Hybrid Model 25

Multi-Source Renewable Energy Forecasting Using CNN-LSTM Hyb...

引用

25th International Middle East Power System Conference, MEPCON 2024

作者： El-Saieed, Asmaa Mohamed Mosallam, Hanan A. Mansoura High Institute of Engineering and Technology Dept. of Computers and Systems Mansoura Egypt Mansoura Higher Institute of Engineering and Technology Department of Electrical Engineering Mansoura Egypt

ISBN: (纸本)9798350379648

Accurate forecasting of renewable energy output is vital for enhancing the efficiency and stability of integrated power systems. This study introduces a novel deep learning approach that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks to predict energy production from solar, wind and hydropower sources. The hybrid CNN-LSTM model utilizes historical meteorological data, including solar irradiance, cloud cover, temperature, wind speed, and precipitation, to forecast future energy generation with high precision. The CNN component extracts spatial features from the weather data, while the LSTM component captures temporal dependencies and long-term trends. For solar energy forecasting, the model estimates solar radiation based on factors like temperature and humidity, while wind energy predictions rely on wind speed variations, and hydropower output is forecasted using rainfall and watershed information. This comprehensive approach enables accurate and reliable predictions of renewable energy production. The model's performance is evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R-squared (R2), etc. Results demonstrate that the hybrid model significantly improves the accuracy and reliability of renewable energy forecasts. This advanced tool provides valuable insights for energy managers, utility companies, and policymakers, aiding in optimizing resource allocation and enhancing the sustainability and resilience of energy grids. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Two-Rated-Power, Dual-Winding, Three-Phase Induction Motor

Two-Rated-Power, Dual-Winding, Three-Phase Induction Motor

引用

2024 International Conference on electrical Machines, ICEM 2024

作者： Ferreira, Fernando J. T. E. Institute of Systems and Robotics University of Coimbra Dep. of Electrical and Computer Engineering Coimbra3030-250 Portugal

ISBN: (纸本)9798350370607

This paper proposes using star-delta and star-series connection modes in three-phase dual-winding squirrelcage induction motors to have available 100% and 55% of the original rated power for a given supply line-to-line voltage. The connection mode can be changed on a nine-terminal block. The experimental results obtained with a commercial 4-kW, 400-V, 50-Hz, 4-pole induction motor whose stator windings were redesigned to provide 4-kW and 2.2-kW output powers are presented and validate the proposed solution. Two-rated-power motors with the proposed output power ratio could be used as spare motors to replace faulty/damaged motors with the same frame size. The proposed solution allows fine-tuning the motor power to the actual maximum power required by the driven application/load and can be considered cost-effective as it may lead to significant gains in the motor efficiency and power factor when the low-power mode is adopted. In many cases, it may avoid the underloaded operation of induction motors, while keeping their original rated power available. © 2024 IEEE.

关键词： Microelectronics

来源：评论

学校读者我要写书评

暂无评论

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5575-5588页

作者： Jiang, Zihan Ma, Yiqun Shi, Bingyu Lu, Xin Xing, Jian Goncalves, Nuno Jin, Bo Suzhou215000 China Northeast Forestry University College of Computer and Control Engineering Harbin150000 China University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction. © 2024 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

MuSe4ASD - An Interactive Music Station for Children with ASD 6

MuSe4ASD - An Interactive Music Station for Children with AS...

引用

6th Experiment at International Conference, exp.at 2023

作者： Lagos, Beatriz Menezes, Paulo University of Coimbra Institute of Systems and Robotics Electrical and Computer Engineering Department Coimbra Portugal

ISBN: (纸本)9798350314403

This article explores the topic involving children with autism, referencing what this condition is about, as well as the hypotheses for approaching the problem based on the literature reviewed. The proposed approach involves the creation of an adequate space with an immersive interactive system based on musical stimuli, and physical exercise to improve their communication, memory, visual and motor capabilities, and eventually potentiate the development of artistic skills. The development of this interactive system includes the development of an avatar that will be animated using Motion Capture technology, so it can interact with the child and accompany him/her while doing the exercises with fluid movements. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Exploring Player's Body as a Game Controller for Fitness Activity Promotion 6

Exploring Player's Body as a Game Controller for Fitness Act...

引用

6th Experiment at International Conference, exp.at 2023

作者： Simoes, Diogo Menezes, Paulo University of Coimbra Institute of Systems and Robotics Electrical and Computer Engineering Department Coimbra Portugal

ISBN: (纸本)9798350314403

In recent years, there has been a tendency for people to resort to a more sedentary lifestyle, which has only been aggravated by the COVID-19 pandemic and the evermore common remote work policies. This lack of physical activity brings negative health outcomes and can generally be difficult to overcome due to how challenging it can be for a person to find the motivation to adopt a more physically active routine. To address this issue, we propose the use of serious games as an engaging, fun, and highly motivational tool that can aid people in their quest for a healthier lifestyle. We focus on three problem areas: motor control improvement and rehabilitation, post-stroke rehabilitation, and physical activity for general health. There exist multiple solutions for these problems which often require specific equipment that may not be available to the common user. Therefore, we propose a different approach requiring solely a laptop equipped with a camera, thus making it more practical and accessible to the wider public. © 2023 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

引用

computers, Materials & Continua 2023年第5期75卷 3713-3728页

作者： Qiqi Li Longfei Ma Zheng Jiang Mingyong Li Bo Jin College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Institute of Systems and Robotics(ISR) Department of Electrical and Computer Engineering(DEEC)University of CoimbraCoimbraPortugal

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low ***-modal retrieval technology can be applied to search engines,crossmodalmedical processing,*** existing main method is to use amulti-label matching paradigm to finish the retrieval ***,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal *** avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal ***,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for ***,this method uses the inference capabilities of the transformer encoder to generate global fine-grained ***,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching *** article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous *** experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

关键词： Deep learning cross-modal retrieval hash learning transformer

来源：评论

学校读者我要写书评

暂无评论

MM-LINS: a Multi-Map LiDAR-Inertial System for Over-Degenerate Environments

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-11页

作者： Ma, Yongxin Xu, Jie Yuan, Shenghai Zhi, Tian Yu, Wenlu Zhou, Jun Xie, Lihua school of Mechanical Engineering Shandong University Jinan China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China

SLAM plays a crucial role in automation tasks, such as warehouse logistics, healthcare robotics, and restaurant delivery. These scenes come with various challenges, including navigating around crowds of people, dealing with flying plastic bags that can temporarily blind sensors, and addressing reduced LiDAR density caused by cooking smoke. Such scenarios can result in over-degeneracy, causing the map to drift. To address this issue, this paper presents a multi-map LiDAR-inertial system (MM-LINS) for the first time. The front-end employs an iterated error state Kalman filter for state estimation and introduces a reliable evaluation strategy for degeneracy detection. If over-degeneracy is detected, the active map will be stored into sleeping maps. Subsequently, the system continuously attempts to construct new maps using a dynamic initialization method to ensure successful initialization upon leaving the over-degeneracy. Regarding the back-end, the Scan Context descriptor is utilized to detect inter-map similarity. Upon successful recognition of a sleeping map that shares a common region with the active map, the overlapping trajectory region is utilized to constrain the positional transformation near the edge of the prior map. In response to this, a constraint-enhanced map fusion strategy is proposed to achieve high-precision positional and mapping results. Experiments have been conducted separately on both public datasets that exhibited over-degenerate conditions and in real-world environments. These tests demonstrated the effectiveness of MM-LINS in over-degeneracy environment. Our codes are open-sourced on Github. IEEE

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

LPL-VIO: monocular visual-inertial odometry with deep learning-based point and line features

引用

Neural Computing and Applications 2024年第36期36卷 23061-23075页

作者： Liu, Changxiang Yang, Qinhan Yu, Hongshan Fu, Qiang Akhtar, Naveed College of Electrical and Information Engineering School of Robotics Quanzhou Institute of Industrial Design and Machine Intelligence Innovation Hunan University Changsha China School of Computing and Information Systems The University of Melbourne VIC Australia

Visual-inertial SLAM (VINS) has garnered substantial interest in the field of mobile robotics due to its robustness and cost-effectiveness. The incorporation of both point and line features in visual SLAM has shown significant performance improvements compared to relying solely on point features. Furthermore, learning-based features consistently outperform traditional hand-crafted features across a diverse range of tasks. Leveraging all these observations, we propose a novel deep learning technique, termed learning-based point and line visual-inertial odometry (LPL-VIO), which is aimed to enhance robustness and performance of traditional systems. LPL-VIO takes a 2-stage approach, including a deep learning front-end and a traditional nonlinear optimization back-end. In the first stage (front-end), we employ proposed networks for points and lines to extract and track deep learning-based point and line features in visual images, while implementing IMU preintegration. In the second stage (back-end), we adopt a sliding window strategy to tightly couple point and line re-projection errors with IMU preintegration residuals. These residuals are optimized using bundle adjustment for precise global pose estimation. Extensive experiments are conducted on both public EuRoC datasets and our own real-world dataset collected in challenging outdoor environments. Qualitative and quantitative results show that our method exhibits strong competitiveness compared with the existing point–line techniques, and outperforms the popular VINS-Mono. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： SLAM robotics

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：