检索结果-内蒙古大学图书馆

Deep fusion of discrete-time and continuous-time models for long-term prediction of chaotic dynamical systems

Nonlinear Dynamics 2025年第11期113卷 12545-12563页

作者： Cheng, Xinzhuang Liu, Zuolin Fang, Hongbin MOE Engineering Research Center of AI & Robotics Institute of AI and Robotics Fudan University Shanghai200433 China

Time series forecasting plays a crucial role in contemporary production and daily life by analyzing the historical data to predict future trends, patterns, and behaviors across various phenomena. However, forecasting chaotic time series remains a formidable challenge, primarily attributed to the high nonlinearity of chaotic dynamical systems and their extreme sensitivity to noise and initial conditions. In general, predicting through discrete-time models and continuous-time models each have their advantages, but there have been few explorations of their integration. In this paper, we delve into the fusion of these two models by leveraging deep neural networks to achieve a notable improvement in the length and accuracy of chaotic time series prediction. The discrete-time reservoir computing model is utilized to make initial predictions of the chaotic time series, while continuous-time differential equations and Physically Informed Neural Network (PINN) are then adopted to refine the results and mine hidden information from multiple perspectives. The effectiveness of the method is verified by applying it to the Lorenz system. Moreover, we discuss in detail the prediction performance of the method under extreme conditions such as noise, sparse sampling, etc., which reveals satisfactorily results even when a single model fails. By applying the method to an experimental double pendulum system, we further demonstrate the superiority of the method in long-term prediction of real chaotic dynamical systems. Overall, the proposed method represents a new paradigm of multi-method and multi-model fusion, providing innovative ideas for improving the accuracy of chaotic time series prediction. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Tuning of Multi-stability Profile and Transition Sequence of Stacked Miura-Origami Metamaterials

引用

Acta Mechanica Solida Sinica 2023年第4期36卷 554-568页

作者： Haiping Wu Hongbin Fang Institute of AI and Robotics Fudan UniversityShanghai 200433China MOE Engineering Research Center of AI and Robotics Fudan UniversityShanghai 200433China Shanghai Engineering Research Center of AI and Robotics Fudan UniversityShanghai 200433China

Multi-stable origami structures and metamaterials possess unique advantages and could exhibit multiple stable three-dimensional configurations,which have attracted widespread research interest and held promise for applications in many *** a great deal of attention has been paid to the design and application of multi-stable origami structures,less knowledge is available about the transition sequence among different stable configurations,especially in terms of the fundamental mechanism and the tuning *** fill this gap,with the multi-stable dual-cell stacked Miura-ori chain as a platform,this paper explores the rules that govern the configuration transition and proposes effective methods for tuning the transition ***,by correlating the energy evolution,the transition paths,and the associated force-displace-ment profiles,we find that the critical extension/compression forces of the component cells play a critical role in governing the transition ***,we summarize the rules for predicting the transition sequence:the component cell that first reaches the critical force during quasi-static extension or compression will be the first to undergo a configuration *** on these findings,two methods,i.e.,a design method based on crease-stiffness assignment and an online method based on internal pressure regulation,are proposed to tune the stability profile and the transition sequence of the multi-stable origami *** crease-stiffness design approach,although effective,cannot be employed for online tuning once the prototype has been *** pressure-based approach,on the other hand,has been shown experimentally to be effective in adjusting the constitutive force-displacement profiles of the component cells and,in turn,tuning the transition sequence according to the summarized *** results of this study will advance the state of the art of origami mechanics and promote the engineering applications of mu

关键词： Origami metamaterial Bi-stability Origami mechanics Pneumatic origami Snap-through transition

来源：评论

学校读者我要写书评

暂无评论

Towards understanding the surface rippling process by periodic reciprocal nanoscratching

引用

Friction 2023年第10期11卷 1815-1828页

作者： Zihan LI Yongda YAN Jiqiang WANG Chen LI Yanquan GENG State Key Laboratory of Robotics and Systems Robotics InstituteHarbin Institute of TechnologyHarbin 150080China Center for Precision Engineering Harbin Institute of TechnologyHarbin 150001China

The bundle structure formed perpendicular to the scratching direction is a type of wear-induced structure for *** this study,the formation mechanism of bundle structures on polycarbonate(PC)surfaces is investigated by reciprocal scratching *** on the analysis of the morphologies,friction forces,and height signals,the formation of the bundle structure is *** influence of scratching parameters,including the feed value and scratching direction,on the formation of the bundle structure is also *** is found that the bundle structure is accumulated by the continuous stacking of the sample materials plowed by the tip in stick–slip motion,and that the stick–slip behavior is enhanced with increased scratching *** work reproduces the formation process of bundle structure in experiments for the first time and demonstrates that the stick–slip enhancement mechanism exists in the reciprocal scratching process,providing further insight into the friction behavior of polymers.

关键词： atomic force microscopy(AFM) bundle structures stick-slip friction force

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Hemispherical resonator with low subsurface damage machined by small ball-end fine diamond grinding wheel:A novel grinding technique

引用

Chinese Journal of Aeronautics 2024年第5期37卷 570-585页

作者： Biao QIN Henan LIU Jian CHENG Jinchuan TIAN Jiangang SUN Zihan ZHOU Chuanzhen MA Mingjun CHEN State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China Center for Precision Engineering Harbin Institute of TechnologyHarbin 150001China

As for the ultra-precision grinding of the hemispherical fused silica resonator,due to the hard and brittle nature of fused silica,subsurface damage(SSD)is easily generated,which enormously influences the performance of such ***,ultra-precision grinding experiments are carried out to investigate the surface/subsurface quality of the hemispherical resonator machined by the small ball-end fine diamond grinding *** influence of grinding parameters on the surface roughness(SR)and SSD depth of fused silica samples is then *** experimental results indicate that the SR and SSD depth decreased with the increase of grinding speed and the decrease of feed rate and grinding *** addition,based on the material strain rate and the maximum undeformed chip thickness,the effect of grinding parameters on the subsurface damage mechanism of fused silica samples is ***,a multi-step ultra-precision grinding technique of the hemispherical resonator is proposed based on the interaction influence between grinding depth and feed ***,the hemispherical resonator is processed by the proposed grinding technique,and the SR is improved from 454.328 nm to 110.449 nm while the SSD depth is reduced by 94%from 40μm to 2.379μ*** multi-step grinding technique proposed in this paper can guide the fabrication of the hemispherical resonator.

关键词： Fused silica Ultra-precision grinding Hemispherical resonator Subsurface damage Grinding technique

来源：评论

学校读者我要写书评

暂无评论

Path Tracing and Validation of Omni Wheeled Mini Robot Using Visual Feedback 11

Path Tracing and Validation of Omni Wheeled Mini Robot Using...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Ahamed, Aftaab Jayaraj, Karthik Fazil, Shibin Nikitha, S. Sudheer, P.A. National Institute of Technology Calicut Robotics Interest Group Mechatronics Robotics Laboratory India National Institute of Technology Calicut Mechatronics/Robotics Laboratory Mechanical Engineering Department India

ISBN: (纸本)9798350379136

Holonomic drives are gaining popularity in many fields due to their versatility in various industrial applications. The ability of the holonomic drive robots to move in all directions makes it distinct from other drive mechanisms. Open-loop control of omnidirectional bots can be achieved with relative ease whereas automating it is not as easy. When trying to create an automated system with lower cost, off the shelf components and hardware, other problems may arise as a result of the poor performance of the components. Here a three wheeled omnidirectional robot that can trace a predefined path without human intervention has successfully been developed. © 2024 IEEE.

关键词： Open loop control

来源：评论

学校读者我要写书评

暂无评论

OAFuser: Toward Omni-Aperture Fusion for Light Field Semantic Segmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6225-6239页

作者： Teng, Fei Zhang, Jiaming Peng, Kunyu Wang, Yaonan Stiefelhagen, Rainer Yang, Kailun Hunan University School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Changsha410082 China Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics Karlsruhe76131 Germany Institute for Visual Computing ETH Zurich Zurich8092 Switzerland

Light field cameras are capable of capturing intricate angular and spatial details. This allows for acquiring complex light patterns and details from multiple angles, significantly enhancing the precision of image semantic segmentation. However, two significant issues arise: 1) The extensive angular information of light field cameras contains a large amount of redundant data, which is overwhelming for the limited hardware resources of intelligent agents. 2) A relative displacement difference exists in the data collected by different microlenses. To address these issues, we propose an omni-aperture fusion model (OAFuser) that leverages dense context from the central view and extracts the angular information from subaperture images to generate semantically consistent results. To simultaneously streamline the redundant information from the light field cameras and avoid feature loss during network propagation, we present a simple yet very effective subaperture fusion module (SAFM). This module efficiently embeds subaperture images in angular features, allowing the network to process each subaperture image with a minimal computational demand of only (∼1\rm GFlops). Furthermore, to address the mismatched spatial information across viewpoints, we present a center angular rectification module (CARM) to realize feature resorting and prevent feature occlusion caused by misalignment. The proposed OAFuser achieves state-of-the-art performance on four UrbanLF datasets in terms of all evaluation metrics and sets a new record of 84.93% in mIoU on the UrbanLF-Real Extended dataset, with a gain of +3.69%. The source code for OAFuser is available at https://***/FeiBryantkit/OAFuser. © 2020 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Trash Detection in Water Bodies Using Yolo With Explainable AI Insight 6

Trash Detection in Water Bodies Using Yolo With Explainable ...

引用

6th International Conference on robotics and Automation in Industry, ICRAI 2024

作者： Rasheed, Shafaq Mirza, Amal Saeed, Muhammad Saad Yousaf, Muhammad Haroon University of Engineering and Technology Department of Computer Engineering Taxila Pakistan National Center of Robotics and Automation Swarm Robotics Lab Taxila Pakistan

ISBN: (纸本)9798350355703

Waste disposal into water bodies is a serious concern for environmental engineers, often resulting in urban flooding, soil degradation in agricultural areas, and freshwater pollution. Additionally, trash accumulation in water bodies threatens ma-rine life by introducing contaminants through storm drains, rivers, and other channels. Furthermore, the unique character-istics of underwater environments, including high noise levels, low visibility, and color variation, pose challenges for trash detection. Thus, addressing this issue is crucial for environmental sustainability. The work focuses on both floating and submerged trash in water bodies. Typically, the detection of trash on water bodies is impacted by environmental variability, diverse appearance, and background clutter. These conditions also make usual object detection techniques less effective. Deep learning methods have shown promise in handling challenging visual tasks, therefore researchers have turned to them to get over these challenges. In this work, we focus on applying different versions of YOLO to the problem of water trash detection. To assess these models' performance, we use four different datasets: Trash Flow rate Dataset, DeepTrash, FloW, and TrashICRA. Each dataset represents various trash types under different conditions such as underwater trash and floating trash. Our study attempts to identify the best method suitable for the detection of aquatic waste. Our results highlight the effectiveness of YOLO variants in identifying the presence of trash in water ecosystems. By leveraging Grad-CAM we gain insights into the interpretability and transparency of deep learning models thus enabling Explainable AI. This approach will also contribute to the understanding and trustworthiness of artificial systems deployed for trash detection applications by providing a transparent view of decision making process of deep learning models. © 2024 IEEE.

关键词： Storm sewers

来源：评论

学校读者我要写书评

暂无评论

IMPROVING THE LEARNING PROCESS FOR STUDENTS. PERSONALIZING LEARNING THROUGH SOFTWARE APPLICATIONS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer Science 2025年第1期2025卷 157-166页

作者： Drăgoi, Marius-Valentin Puiu, Roxana-Adriana Petrea, Gabriel Burtea, Cătălin Spiridon – Mocioacă, Teodora – Mihaela Puiu, Mihail Suciu, Cosmin Petru Faculty of Industrial Engineering and Robotics National University of Science and Technology POLITEHNICA Bucharest Romania National research and development institute for gas turbines COMOTI Bucharest Romania

Universities often utilize the technique of enhancing educational outcomes by focusing on improving student learning. This technique has seen substantial development via the incorporation of sophisticated software tools, which provide the advantage of not only tackling intricate programming difficulties but also actively assisting students in their educational advancement. These software solutions provide a distinct benefit by facilitating customized learning experiences and enhancing study approaches in a more effective manner. This paper presents an efficient method for comprehending the significance of certain key phrases in a course: to use software that can systematically extract and analyze paragraphs that include those important terms. By prioritizing these essential topics, students may acquire profound perspectives on the subject matter, resulting in a more thorough comprehension. This article introduces a bespoke software program that has been created with the explicit purpose of improving the learning process. The system presented in this article can also deal with Romanian, where this could be a great advantage and a novelty since there is no such advantage of similar systems (to the best of our knowledge). We will showcase the potential influence of this application on student engagement and academic achievement. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Robust control of isopropyl benzene production process using H_(∞) loop shaping control scheme

引用

Journal of Control and Decision 2024年第1期11卷 153-163页

作者： Vinila Mundakkal Lakshmanan Aparna Kallingal Sreepriya Sreekumar Department of Chemical Engineering National Institute of Technology CalicutKozhikodeKeralaIndia Department of Robotics and Automation Adi Shankara Institute of Engineering and TechnologyKaladyIndia

This paper discusses robust control strategy for isopropyl benzene production process using the method of loop shaping H_(∞) *** cumene production process is a part of phenol plant in HOCL,Kochi.H_(∞) control of the propylene concentration is done *** H_(∞) controller is derived from the linearised model of the *** optimal H_(∞) controller is obtained by simplifying two algebraic Riccati *** proposed PID-like H_(∞) controller provides a single tuning parameter which makes the controller design more *** proposed controller has been compared with other robust controllers like H_(2) and *** H_(∞) controller is found to be superior in a wide frequency range and has a feature of low distortion and good regulating *** reactor model has been developed in COMSOL Multiphysics with the parameters obtained from HOCL plant,*** model extracted is reduced using model order reduction for the controller design.

关键词： Cumene reactor H_(∞)loop shaping model order reduction Riccati equation PID control stability robustness

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：