检索结果-内蒙古大学图书馆

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： P. Sathish Kumar Ramesh Singh Rawat Manish Shrimali Swapnil Parikh Harshal Patil Ramya Maranan Department of Robotics & Automation United Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and IT Janardan Rai Nagar Rajasthan Vidyapeeth (Deemed to be University) Udaipur Rajasthan India Department of Computer Science and Engineering Parul Institute of Engineering and Technology Parul University Gujarat India Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Ensuring the safety of individuals should be a top priority. Everyone wants to return home safely. Many riders continue to disregard safety constraints, increasing the chance of accidents that result in death. It is critical to incorporate the latest technology into road monitoring systems to make cities smarter and to ensure rider safety. For this research, Deep Learning (DL) and the Internet of Things (IoT) were chosen for effective road surveillance and alert systems. The primary goal of the study is to detect and inform riders about accidents that occur along their path and to provide details about the location of the detected accident. Additionally, the system provides the vehicle's speed. To identify automobile accidents in the footage, a hybrid DL model that includes Convolutional Neural Network - Bidirectional Long Short-Term Memory (CNN-Bi-LSTM) is suggested. For the model's training, both accident and non-accident data were collected. The model is evaluated using three metrics: accuracy, loss, and execution time. The next step is to upload the recommended model to the ThingSpeak cloud. A Graphical User Interface (GUI) is being created in the ThingSpeak cloud. The GUI displays the vehicle's speed, accident images, and the precise location of the accident scene using the Raspberry Pi, speed sensor, Pi-camera, and Global Positioning System (GPS) module. An LED is also integrated into the GUI to alert the user. A real-world test is conducted on the designed system. The proposed solution has many advantages and will ensure driver safety.

关键词： Deep learning Training Cloud computing Accuracy Roads Surveillance Feature extraction Safety Accidents Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Prediction and Modeling of Tool Wear with Cutting Force and Fine Gaussian Support Vector Machine in Drilling

Prediction and Modeling of Tool Wear with Cutting Force and ...

引用

International Virtual Conference on Emerging Trends in Design, Manufacturing, Materials and Thermal Sciences, ETDMMT 2020

作者： Mahendran, G. Sai Balaji, M.A. Susai Mary, J. Dinakaran, D. Department of Mechanical Engineering B S Abdur Rahman Crescent Institute of Science and Technology Chennai India Department of Electronics and Instrumentation Engineering B S Abdur Rahman Crescent Institute of Science and Technology Chennai India Center for Automation and Robotics Hindustan Institute of Technology and Science Chennai India

ISBN: (纸本)9789813364271

The tool wear is a vital problem in machining which affects the accuracy, geometry of the workpiece and also productivity. This paper presents a cutting-force-based monitoring method with a Gaussian Support Vector Machine for tool wear prediction in a drilling process. The experimental results show that the tool wear has a significant effect on the cutting forces. Statistical features in time and frequency domains are extracted from the measured force signals and are used as inputs to the Support Vector Machine (SVM). The machining parameters speed and feed are also taken as inputs for tool wear prediction as they greatly influence the cutting force. The fine Gaussian SVM algorithm is able to model the tool wear with a prediction accuracy of 88% and can be used for online diagnosis of tool wear. The results of the Gaussian SVM algorithm are compared with standard algorithms like ANN to prove its efficiency. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Condition monitoring Fine Gaussian SVM drilling Force Tool wear

来源：评论

学校读者我要写书评

暂无评论

Trustworthy Bayesian Perceptrons

Trustworthy Bayesian Perceptrons

引用

International Conference on Information Fusion

作者： Markus Walker Hayk Amirkhanian Marco F. Huber Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology (KIT) Germany Department Cyber Cognitive Intelligence (CCI) Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Institute of Industrial Manufacturing and Management IFF University of Stuttgart Germany

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

Bayesian Neural Networks (BNNs) offer a sophisticated framework for extending classical neural network point estimates to encompass predictive distributions. Despite the high potential of BNNs, established BNN training methods such as Variational Inference (VI) and Markov Chain Monte Carlo (MCMC) grapple with issues such as scalability and hyperparameter dependence. In addressing these issues, our research focuses on the fundamental elements of BNNs, in particular perceptrons and their predictive capabilities. We introduce a new perspective on the closed-form solution for backward-pass computation for the Bayesian perceptron and prove that the state-of-the-art solution is equivalent to statistical linearization. To assess the efficacy of Bayesian perceptrons and provide insights into their performance in distinct input space regions, a novel methodology utilizing k-d trees as a space partitioning method is introduced to evaluate prediction quality within specific input space regions.

关键词： Training Systematics Monte Carlo methods Scalability Neural networks Estimation Predictive models Nonhomogeneous media Bayes methods Testing

来源：评论

学校读者我要写书评

暂无评论

Determination of the Characteristics of Gears of Robot-Like Systems by Analytical Description of their Structure

Determination of the Characteristics of Gears of Robot-Like ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Stefan Landler Raúl Molina Blanco Michael Otto Birgit Vogel-Heuser Markus Zimmermann Karsten Stahl Technical University of Munich Germany TUM School of Engineering and Design Department of Mechanical Engineering Munich Institute of Robotics and Machine Intelligence (MIRMI) Institute of Machine Elements Gear Research Center (FZG) Institute of Automation and Information Systems (AIS) Laboratory for Product Development and Lightweight Design (LPL)

The axes of robots and robot-like systems (RLS) usually include e-motor-gearbox-arrangements for optimal connection of the elements. The characteristics of the drive system and thus also of the robot depend strongly on the gears. Different gearbox designs are available which differ in stiffness, efficiency and further properties. For an application-optimal design of RLS a uniform documentation and a comparability of gearbox concepts is a decisive factor. The application-optimal design is supported by an interdisciplinary approach between mechanical engineering and software design, guided by adequate product development methodology. The quite heterogeneous characterization of gearboxes for RLS which is currently the state of the art is a relevant obstacle in the flexible and optimal design of RLS. The paper shows the analysis of the gear structure with unified symbols for specific machine elements and contact types. The introduced method gives insight into the mechanical structure of the gearboxes. Similarities between gear types can thus be revealed. This also enables the classification of new developments in the state of the art. Moreover, the developed method for analyzing the gear structure can be used to determine the characteristics of gears. Examples for these characteristics are backlash, efficiency or stiffness. Specifically, the stiffness of gears can be synthesized by the force action of individual contacts and the individual phenomena that occur with them. The representation by individual phenomena also makes it possible to extend the calculation to include influencing parameters such as temperature that have not been sufficiently taken into account so far.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnostic Opportunities for Electromagnetic Coils of Active Magnetic Bearings using Physics-of-Failure Analysis

Fault Diagnostic Opportunities for Electromagnetic Coils of ...

引用

System Reliability and Safety engineering (SRSE), International Conference on

作者： Ruiqi Li Kai Wang Peng Zeng Jiwei Cao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Department of Electrical Engineering Harbin Institute of Technology China

Active magnetic bearings (AMBs) have many advantages over traditional oil bearings due to their non-contact characteristics. They are environmentally friendly solution and have been proven to be highly reliable and available. Electromagnetic coils are vital components of AMB and they are failure prone. In this paper, the failure mode of magnetic bearing coil and its corresponding failure mechanism are reviewed by FMMEA method, and the existing coil fault diagnosis methods are introduced. Future directions for coil insulation health monitoring aiming at the application characteristics of AMBs are also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Predicting River Water Height Based on GRU-RNN Method

An Intelligent Method for Predicting River Water Height Base...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： K. Kavitha Kavita Singh Priyanka Shakya Vatsal Kumar Parasar Deepak Kaushal Gourav Kalra Department of Information Technology Aditya Institute of Technology And Management Tekkali India Department of Civil Engineering Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Department of Atmospheric and Ocean Science Studies University of Allahabad India Robotics & Automation Noida Department of Management Studies Graphic Era Deemed to be University Dehradun Uttarakhand India Department of mechanical engineering Maharishi Markandeshwar (Deemed to be University) Mullana Ambala India

It is vital in hydrology to be able to predict the magnitude of a flood, and this is often done using a number of conceptual and deterministic models. Such models may require highly specialized data that is not always easily accessible, such as soil moisture, soil type, evaporation rate, characteristic and slope of the land use, soil surface, and management issues in the catchment region, etc. It's crucial to be able to predict when and how much rain will fall. Additional constraints on the effectiveness of such models include the necessity to make simplifying assumptions and a required response time. Preprocessing, feature extraction, and model training are the first three steps of the proposed strategy. Preprocessing makes use of a time and frequency representation obtained by wavelet analysis. The recursive feature elimination approach was employed for the feature extraction. After using information gain to choose useful features, the models are trained with GRU-RNN. The proposed method outperforms the two most popular alternatives, GRU and RNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis

arXiv

引用

arXiv 2024年

作者： Liu, Shuhong Deng, Tianchen Zhou, Heng Li, Liuzhuozheng Wang, Hongyu Wang, Danwei Li, Mingrui Department of Information Science and Technology Department of Complexity Science and Engineering The University of Tokyo Tokyo113-8654 Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Department of Mechanical Engineering Columbia University New York10027 United States School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Computer Science Dalian University of Technology Dalian116024 China

Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems. © 2024, CC BY.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Design and preliminary testing of a piezoelectric-based sole energy harvester

Design and preliminary testing of a piezoelectric-based sole...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Wang, Yidi Zhao, Xuan Shi, Qiuyu Liao, Haisu Wu, Xinyu Gao, Fei Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin999077 Hong Kong

ISBN: (纸本)9781665481090

Harvesting energy from the human body to replenish existing energy sources is receiving substantial attention. Recently scientists have been focusing on harvesting biomechanical energy from human feet during walking. This paper develops a piezoelectric-based sole energy harvester that is designed to be worn on the bottom of shoes to harvest energy, thus powering wearable electronic devices. Specifically, a cam with piezoelectric(PZT) stacks is mounted on the heel to scavenge energy during the heel strike. The cam can change the input's direction from the vertical direction to the horizontal direction. In addition, the output power of this part can be optimized or improved by generating a specified cam profile. A bimorph piezoelectric plate is installed on the forefoot to convert the toes' bending deformation into electricity. Herein, piezoelectric Macro Fiber Composites (MFC) are employed to capture the large deformation. Preliminary testing on a healthy subject is conducted to validate this design. The average power output of the harvester is 8.83 m W. © 2022 IEEE.

关键词： Cams

来源：评论

学校读者我要写书评

暂无评论

Distilled Visual and Robot Kinematics Embeddings for Metric Depth Estimation in Monocular Scene Reconstruction

arXiv

引用

arXiv 2022年

作者： Wei, Ruofeng Li, Bin Mo, Hangjie Zhong, Fangxun Long, Yonghao Dou, Qi Liu, Yun-Hui Sun, Dong The Department of Biomedical Engineering City University of Hong Kong Hong Kong The Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong The Department of Computer Science and Engineering T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong

Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth information, which is difficult to transfer to the soft robotics-based surgical systems due to the use of monocular endoscopy. In this paper, we present a novel framework that combines robot kinematics and monocular endoscope images with deep unsupervised learning into a single network for metric depth estimation and then achieve 3D reconstruction of complex anatomy. Specifically, we first obtain the relative depth maps of surgical scenes by leveraging a brightness-aware monocular depth estimation method. Then, the corresponding endoscope poses are computed based on non-linear optimization of geometric and photometric reprojection residuals. Afterwards, we develop a Depth-driven Sliding Optimization (DDSO) algorithm to extract the scaling coefficient from kinematics and calculated poses offline. By coupling the metric scale and relative depth data, we form a robust ensemble that represents the metric and consistent depth. Next, we treat the ensemble as supervisory labels to train a metric depth estimation network for surgeries (i.e., MetricDepthS-Net) that distills the embeddings from the robot kinematics, endoscopic videos, and poses. With accurate metric depth estimation, we utilize a dense visual reconstruction method to recover the 3D structure of the whole surgical site. We have extensively evaluated the proposed framework on public SCARED and achieved comparable performance with stereo-based depth estimation methods. Our results demonstrate the feasibility of the proposed approach to recover the metric depth and 3D structure with monocular inputs. Copyright © 2022, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Practical Structural Design Approach of Multicon guration Planar Single-Loop Metamorphic Mechanism with a Single Actuator

引用

Chinese Journal of Mechanical engineering 2020年第5期 29-43页

作者： Qiang Yang Guangbo Hao Shujun Li Hongguang Wang Haiyang Li College of Mechanical Engineering and Automation Northeastern University Department of Electrical and Electronic Engineering University College Cork State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences

As a type of multiconfiguration mechanism that can operate in an under-actuated state, metamorphic mechanisms were proposed more than two decades ago and attracted significant interest. Studies on structural synthesis of metamorphic mechanisms tend to focus more on metamorphic techniques and the structural synthesis of source mechanisms for metamorphic mechanisms. By designing di erent constraint architectures of metamorphic joints, multistructures can be obtained from the same source metamorphic mechanism. To determine the constraint architectures of metamorphic joints and their di erent assembly combinations, a kinematic status matrix and a corresponding constraint status matrix are constructed based on the metamorphic cyclogram of a source mechanism. According to the equivalent resistance gradient model and the constraint status matrix, an equivalent resistance matrix for the metamorphic joints is proposed. A structural synthesis matrix of the metamorphic mechanism is then obtained from the equivalent resistance matrix by deducing the constraint form vectors of the metamorphic joints. Furthermore, a kinematic diagram synthesis of the source metamorphic mechanism of a planar single-loop metamorphic mechanism is proposed, which is based on only the 14 one-or zero-degrees-of-freedom linkage groups. The entire structural design method of a metamorphic mechanism is based on the structural synthesis matrix and is presented as a systematic process. Finally, the proposed structural design approach is illustrated by two examples to verify its feasibility and practicality. This study provides an effective method for designing a practical multi-mobility and multiconfiguration planar single-loop metamorphic mechanism with a single actuator.

关键词：

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：