检索结果-内蒙古大学图书馆

Data-Driven Tracking Control of a Cushion Robot with Safe Autonomous Motion Considering Human-Machine Interaction Environment

引用

Journal of Dynamic Systems, Measurement and Control 2025年第4期147卷 041003页

作者： Sun, Ping Shan, Rui Chang, Hongbin Wang, Shuoyu School of Artificial Intelligence Shenyang University of Technology Shenyang110870 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Department of Intelligent Mechanical Systems Engineering Kochi University of Technology Kochi7828502 Japan

This study proposes a data-driven safety controller with velocity constraints for a cushion robot. We constructed a mathematical description of the human-machine interaction environment by decomposing the generalized input force and coefficient matrix in the dynamic model. We established a new equivalent data model, which considered various human-machine interaction environments using a pseudo-Jacobian matrix. A stochastic configuration network (SCN) estimation method for variations in the human-machine interaction environment was proposed, with hidden layer nodes added at random. We designed a safe autonomous navigation path and proposed a data-driven control method that limited the actual velocity while stabilizing the tracking error system. In addition, the desired motion velocity of the robot was designed. This approach has the advantage of ensuring safety at a specified velocity. We also demonstrated and validated the effectiveness of the proposed data-driven algorithm using simulation-based comparative analysis and an experimental study. Copyright © 2024 by ASME.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

GeoRefineNet: A Multistage Framework for Enhanced Cephalometric Landmark Detection in CBCT Images Using 3D Geometric Information 17th

GeoRefineNet: A Multistage Framework for Enhanced Cephalome...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Viriyasaranon, Thanaporn Ma, Serie Choi, Jang-Hwan Department of Computational Medicine Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Department of Artificial Intelligence Ewha Womans University Seoul Korea Republic of

ISBN: (纸本)9789819609000

The precise detection of cephalometric landmarks on two-dimensional (2D) radiographs or three-dimensional (3D) computed tomography (CT) images is a fundamental step in various medical fields, especially in research on orthodontics and maxillofacial surgery. Deep learning-based detectors have demonstrated remarkable accuracy in 2D cephalometric analysis, whereas conventional single-view approaches are limited by their reliance on information from a single perspective. This study proposes GeoRefineNet, a novel multistage framework that leverages information from multiple CT scans acquired at various angles. By incorporating geometric knowledge through a 3D heatmap reconstruction process, GeoRefineNet improves robustness, accuracy, and adaptability to various cephalometric configurations. The proposed framework predicts 3D landmark positions on CT images, effectively addressing challenges associated with high-dimensional input data and limited training examples. GeoRefineNet surpasses the existing state-of-the-art models in the 2D and 3D domains, as demonstrated by its superior performance on numerical and clinical datasets. These findings indicate that GeoRefineNet offers a promising avenue for improving the accuracy and reliability of cephalometric landmark detection fostering further advances in clinical diagnosis and treatment planning. Our code is available at https://***/Thanaporn09/***. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Smart Grid Management for Electric Vehicle Charging and the Integration of Renewable Energy Sources using Pied Kingfisher Optimizer 2

Reconfigurable Smart Grid Management for Electric Vehicle Ch...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sivaramkrishnan, M. Ramkumar, M. Siva Uday, Kaparthi Kanan, Mohammad Raj, C. Mohan Giri, Jayant Karpagam College of Engnieering Dept of EEE India SNS College of Technology Dept of ECE India CVR College of Engineering Ibrahimpatanam EIE Department Hyderabad India College of Engineering University of Business and Technology Department of Industrial Engineering Jeddah21448 Saudi Arabia College of Engineering Zarqa University Department of Mechanical Engineering Zarqa Jordan Centre for Robotics and Industrial Automation Sri Eshwar College of Engineering Department or EEE Coimbatore641202 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India

ISBN: (纸本)9798331505745

Electric Vehicle (EV) charging management under the Smart Grid (SG) framework with incorporated Renewable Energy Sources (RESs) functions to advance Energy Management (EM). The operational cost of EV charging varies because renewable energy availability can change so this affects the financial performance of charging operations. Integration of RESs with the SG becomes challenging for operational system efficiency particularly when renewable energy generation levels are low. To overcome these drawbacks, this manuscript proposes an efficient approach for SG management for EV charging with the integration of RESs. The suggested method is Pied Kingfisher Optimizer (PKO). The main aim of the suggested technique is to minimize the operational expenses of EV charging as well as maximize the efficiency of the SG system. The PKO is used to optimize the scheduling and allocation of energy resources within the SG system. By then, the suggested approach is implemented in MATLAB and contrasted with several other methods that are currently in use. The suggested technique outperforms all existing approaches such as Bald Eagle Search (BES), Red Kite Optimization (RKO), Artificial Neural Network-Particle Swarm Optimization (ANN-PSO), and Coati Optimization Algorithm-Constitutive Artificial Neural Network (COA-CANN). The suggested approach delivers superior performance than conventional methods by reducing operational costs to 638,322$ under coordinated charging and 629,745$ under smart charging without impacting system performance metrics. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Charging Navigation Using Waterwheel Plant Algorithm for Coordinating Smart Grids and Intelligent Transportation Systems 2

Electric Vehicle Charging Navigation Using Waterwheel Plant ...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Siva Ramkumar, M. Sivaramkrishnan, M. Uday, Kaparthi Kanan, Mohammad Mohan Raj, C. Giri, Jayant SNS College of Technology Dept of ECE India Karpagam College of Engnieering Dept of EEE India CVR College of Engineering EIE Department Hyderabad India College of Engineering University of Business and Technology Department of Industrial Engineering Jeddah21448 Saudi Arabia College of Engineering Zarqa University Department of Mechanical Engineering Zarqa Jordan Centre for Robotics and Industrial Automation Sri Eshwar College of Engineering Department or EEE Coimbatore641202 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India

ISBN: (纸本)9798331505745

The efficient charging of electric vehicles (EVs) remains essential to create sustainable mobility while EVs transform into crucial elements of upcoming transportation systems. The present EV charging navigation systems deal with three main issues including grid congestion and inadequate charging station (CS) selection and delays from traffic *** paper proposes a novel Waterwheel Plant Algorithm (WWPA) for optimizing EV charging navigation within the Smart Grid (SG) and Intelligent Transportation Systems (ITS). The suggested method strives to enhance SG-EV coordination through demand balancing in addition to charge price reduction and decreased grid congestion levels. WWPA algorithm serves as the proposed method to optimize EV charging schedules. The MATLAB platform serves as the implementation environment for the proposed method which demonstrates superior performance than Multi-agent Reinforcement Learning (MARL), Deep Reinforcement Learning (DRL), Coati-Northern Goshawk Optimization (Coati-NGO) and Grey Sail Fish Optimization (GSFO). Results demonstrate that the WWPA algorithm reduces average charging expenses by 18.14% throughout diverse charging operations as it produces superior performance than existing algorithms operating in the SG ITS. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of monitoring and control device for biogas production in a pilot scale anaerobic digester 4

Design of monitoring and control device for biogas productio...

引用

4th International Symposium on Advances and Innovation in mechanical engineering, ISAIME 2023

作者： Daud, Muhammad Sabarullah Nurjannah, Siti Setiawan, Adi Hasibuan, Arnawan Faisal Yusuf, Edy Electrical Engineering Department Faculty of Engineering Universitas Malikussaleh Jalan Batam Kampus Bukit Indah Lhokseumawe24352 Indonesia Magister Program in Renewable Energy Engineering Faculty of Engineering Universitas Malikusssaleh Jalan Batam Bukit Indah Lhokseumawe24352 Indonesia Mechanical Engineering Department Faculty of Engineering Universitas Malikussaleh Jalan Batam Kampus Bukit Indah Lhokseumawe24352 Indonesia

Monitoring and control in the biogas production process play important role to optimize the processes occurred inside the digester and help to achieve a stable and safe process. Anaerobic digestion is a complex process involving several groups of microorganisms that are sensitive to many operating factors. Therefore, it is important to monitor and detect the process imbalances at an early stage, thus action can be taken in time to prevent the failure. The purpose of this study is to design an appropriate biodigester to produce biogas from culinary food waste and a smart-based design device which can help in monitoring and controlling the process to enhance the biogas yields and control the process of purifying biogas into biomethane. The research method in this study consists of several stages including designing the reactors and instrumentation, fabrication and installation, testing and calibration of the sensors. Performance of biodigester plants was evaluated based on data gained from the sensors. The efficiency of digesters equipped with control and monitoring instruments is better than ordinary manual digesters. Smart-based digesters can increase the rate of gas production more measurably and be recorded systematically and in real time. It can be concluded that a smart biogester equipped with a microcontroller and monitoring with Web Application can save the time and improve biogas production and safety. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Anaerobic digestion

来源：评论

学校读者我要写书评

暂无评论

SomerBot: A Two-Legged Somersaulting Robotic Climber With Compliant Footpad

引用

Journal of Mechanisms and robotics 2025年第8期17卷 081009页

作者： Mani Sankar, Kadali Thakur, Atul Bio-robotics and ArtificialIntelligence (BRAIn) Laboratory Department of Mechanical Engineering Indian Institute of Technology Patna Patna Bihar 801103 India Bio-robotics and ArtificialIntelligence (BRAIn) Laboratory Department of Mechanical Engineering Indian Institute of Technology Patna Patna Bihar 801106 India

Climbing capability is crucial for expanding the operational range of ground robots in inspection and exploration tasks within confined or hazardous spaces. We introduce SomerBot, a two-legged somersaulting robot designed for climbing flat and curved vertical surfaces. A key contribution is a 3D-printed compliant footpad with passive adhesion and tendon-driven detachment, reducing energy consumption compared to active adhesion techniques. The robot’s simple two-legged design minimizes fabrication complexity, weight, and power needs, which are critical for wall climbing. Optimized joint trajectory design ensures stable climbing by maintaining optimal surface contact. This article addresses several key issues: scaling of speed, payload, power, and weight with increasing motor torque, finding enhanced payload capacity without compromising speed. SomerBot’s structure, made using rapid prototyping techniques such as 3D printing and laser cutting, allows easy replication and customization. Experiments show its ability to transition between planes, overcome obstacles, and carry payloads at an average speed of 1.33 cm/s (0.12 body lengths/s). This work advances wall-climbing robots with energy-efficient adhesion and scalable design for complex climbing tasks.

关键词： legged climbing robots Design Energy consumption trajectory design Robots 3D printing somersaulting robot Adhesion

来源：评论

学校读者我要写书评

暂无评论

A Virtual Characterization of QUAD and DOUBLE-DOUBLE Laminates: Buckling Studies

A Virtual Characterization of QUAD and DOUBLE-DOUBLE Laminat...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Avila, Antonio F. Mapa, Lidianne P.P. Department of Mechanical Engineering Universidade Federal de Minas Gerais Belo Horizonte Minas Gerais31270-901 Brazil Mechanical Engineering Graduate Studies Program Universidade Federal de Minas Gerais Belo Horizonte Minas Gerais31270-901 Brazil

ISBN: (纸本)9781624107238

A new strategy for virtually designing and analyzing double-double laminates to resist buckling under uniaxial compression or in-plane shear conditions has been proposed. This approach combines the off-the-shelf method for carbon/epoxy prepregs with the master-ply concept. The off-the-shelf method utilizes unidirectional prepregs (0° and 90°) and non-crimped fabrics (±30°, ±45°, and 90°). The strength of this non-dimensional design strategy lies in its simplicity, requiring only two parameters: Tsai’s modulus and the number of repetitions. Results were compared with finite element analyses, showing good agreement in all cases. The double-double formulation not only provides higher buckling loads for both uniaxial compression and in-plane shear but also results in distinct buckling modes. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Buckling loads

来源：评论

学校读者我要写书评

暂无评论

Data Entry Errors Detection for Industrial Quality Control Variables Using Data-Driven Models 16th

Data Entry Errors Detection for Industrial Quality Control ...

引用

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

作者： Salles, Rodrigo Leiria, Joana Mendes, Jérôme Institute of Systems and Robotics ARISE University of Coimbra Coimbra Portugal CEMMPRE ARISE Department of Mechanical Engineering University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031817236

In modern industrial environments, quality control is imperative for ensuring product reliability and operational efficiency. Despite advancements in automatic data collection and data-driven models for quality processes, certain critical variables still require manual entry due to the branch of activity from which they originate, leading to potential errors from human involvement. This paper focuses on developing and applying two methodologies, Soft Sensors (SS) and Principal Component Analysis (PCA), to detect data entry errors in quality control variables. The developed methodologies were tested across three industrial datasets and the following error types were studied: blank spaces, duplicates, measurement errors, order errors, and extra number errors. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Soft Robot Kinematic Control Via Manipulability-Aware Redundancy Resolution

引用

Journal of Mechanisms and robotics 2025年第7期17卷 071013页

作者： Azizkhani, Milad Ha, Junhyoung Gunderman, Anthony L. Chen, Yue Department of Mechanical Engineering Georgia Institute of Technology Atlanta GA 30332 Center for Healthcare Robotics Artificial Intelligence and Robotics Institute Korea Institute of Science and Technology Seoul 02792 South Korea Department of Mechanical Engineering University of Arkansas Fayetteville AR 72701 Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA 30332

This article addresses the kinematic control of a redundant soft robotic arm. Full pose kinematic control of soft robots is challenging because direct application of the classical controllers developed based on rigid robots to soft robots could lead to unreliable or infeasible motions. In this study, we explore the manipulability property of a soft robotic arm and develop an advanced resolved-rate controller that prioritizes position over orientation control and switches its modes and gains based on position and orientation manipulabilities, enabling stable motion even when the robot is close to the singular configurations. The simulation and experimental results indicate that our proposed method outperforms previous methods in terms of both accuracy and smoothness during operation.

关键词： Resolution (Optics) Kinematics bio-inspired Simulation Errors Redundancy (engineering) continuum robotics Robots soft robotics Soft robots robotics kinematics Algorithms

来源：评论

学校读者我要写书评

暂无评论

Acceleration-level coordinated control of a dual-arm free-floating space robot under hard joint constraints

引用

Advances in Space Research 2025年第11期75卷 8122-8139页

作者： Xue, Zhihui Liu, Jinguo Zhang, Xin Zhou, Hao Li, Yangmin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Kowloon999077 Hong Kong School of Electrical and Mechanical Engineering University of Portsmouth PortsmouthPO1 3DJ United Kingdom

Dual-arm space robots are becoming increasingly crucial in on-orbit servicing missions. The online motion control of a dual-arm redundant space robot with hard joint constraints presents significant challenges due to its free-floating base. In this article, we proposed an acceleration-level coordinated control framework to solve hard joint constraints and dynamic singularity. The proposed framework combines a task scheduling strategy to achieve saturation in the null space, so that different tasks can achieve trajectory tracking with minimal task scaling under given joint hard constraints. The framework can achieve efficient online control by sequentially abandoning the use of joints that exceed the joint constraint and reintroducing these commands at their saturation level by projecting them into the appropriate null space. Finally, we verify the tracking performance of the algorithm through numerical simulation and experimental research. By comparing the proposed algorithm with the quadratic programming and pseudo-inverse methods, the algorithm has shown excellent online motion control performance, with a computation time of approximately 1 ms within a single sampling period. © 2025 COSPAR

关键词： Quadratic programming

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：