检索结果-内蒙古大学图书馆

COMPARATIVE ANALYSIS OF FIVE NH3/AIR OXIDATION MECHANISMS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rabbani, Shahid Manias, Dimitris M. Kyritsis, Dimitrios C. Goussis, Dimitris A. Department of Mechanical Engineering Khalifa University of Science and Technology Abu Dhabi127788 United Arab Emirates Department of Electrical Engineering and Computer Science Khalifa University of Science and Technology Abu Dhabi127788 United Arab Emirates Research and Innovation Center on CO2 and H2 Department of Mechanical Engineering Khalifa University of Science and Technology Abu Dhabi127788 United Arab Emirates

Five recently developed chemical kinetics mechanisms for ammonia oxidation are analysed and compared, in the context of homogeneous adiabatic autoignition. The analysis focuses on the ignition delay and is based on the explosive mode that is shown to drive the process. Using algorithmic tools based on the Computational Singular Perturbation algorithm, the reactions responsible for the generation of the explosive mode are identified, along with the variables (species mass fractions and temperature) that associate the most to this mode. Comparison of these sets of reactions and variables, obtained for each mechanism, allows to correlate the differences in the predictive outcomes from the mechanisms with specific reactions. The major differences identified, which lead to different ignition delay times, relate to (i) the relative duration of chemical and thermal runaways (a sizeable chemical runaway develops only in some mechanisms) and (ii) the dominant chemistry during the chemical runaway (chemistry involving species with two nitrogen atoms is active only in some mechanisms). The major similarities identified refer to the thermal runaway and in particular to (i) the chemical activity, which is supported mainly by OH-producing reactions and by reactions producing their reactants and (ii) the thermal activity, which is dominated by strongly exothermic OH-consuming reactions. © 2023, CC BY.

关键词： Ammonia

Data-Driven Nonlinear Deformation Design of 3D-Printable Shells

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Silverman, Samuel Snapp, Kelsey L. Brown, Keith A. Whiting, Emily Department of Computer Science Boston University BostonMA United States Department of Mechanical Engineering Boston University BostonMA United States Division of Materials Science & Engineering Boston University BostonMA United States Physics Department Boston University BostonMA United States

Designing and fabricating structures with specific mechanical properties requires understanding the intricate relationship between design parameters and performance. Understanding the design-performance relationship becomes increasingly complicated for nonlinear deformations. Though successful at modeling elastic deformations, simulation-based techniques struggle to model large elastoplastic deformations exhibiting plasticity and densification. We propose a neural network trained on experimental data to learn the design-performance relationship between 3D-printable shells and their compressive force-displacement behavior. Trained on thousands of physical experiments, our network aids in both forward and inverse design to generate shells exhibiting desired elastoplastic and hyperelastic deformations. We validate a subset of generated designs through fabrication and testing. Furthermore, we demonstrate the network’s inverse design efficacy in generating custom shells for several applications. © 2024, CC BY.

关键词： Shells (structures)

Advanced Tracking Algorithm for Multiple Dynamic Vehicles using Attention Mechanisms and Kinematic Models

学校读者我要写书评

暂无评论

Advanced Tracking Algorithm for Multiple Dynamic Vehicles us...

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Kishore Ravikumar Kamal Sutaria Ganesh Pandit Pathak Shailesh Rastogi Department of Mechanical Engineering Chennai Institute of Technology Kundrathur India Deparment of Computer Science and Engineering Faculty of Engineering and Technology Parul University Vadodara India Balaji Institute of Modern Management Pune India Symbiosis Institute of Business Management Nagpur Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Efficient vehicle tracking in urban environments is crucial for intelligent transportation systems but faces challenges such as nonlinear motion, dynamic backgrounds, and frequent occlusions. To address these complexities, we propose the AM-Vehicle-Track system, designed under the tracking-by-detection paradigm. This system integrates the Lightweight Convolutional Block Attention Module (LCBAM), which enhances detection accuracy by refining feature maps through channel-wise and spatial attention, and the Noise-Adaptive Extended Kalman Filter (NSA-EKF), which dynamically adjusts observation noise based on detection confidence to handle nonlinear vehicle motion. Additionally, the Byte data association technique is employed to mitigate issues with low-confidence detections and reduce identity switches. Tested on the challenging VisDrone-MOT dataset, AM-Vehicle-Track achieves a mean object tracking accuracy (MOTA) of 42.2%, an identity F1 score (IDF1) of 51.2%, and processes at 72 frames per second (FPS), outperforming existing state-of-the-art systems. These results highlight its robustness and efficiency in real-time scenarios, making it suitable for intelligent transportation applications. By significantly improving detection accuracy, tracking precision, and scalability, AM-Vehicle-Track establishes a new benchmark in multi-object tracking technologies and demonstrates its potential to enhance the reliability and efficiency of vehicle tracking in complex urban environments.

关键词： Accuracy Attention mechanisms Tracking Heuristic algorithms Urban areas Refining Real-time systems Kalman filters Vehicle dynamics Integrated circuit modeling

Human Preferences and Robot Constraints Aware Shared Control for Smooth Follower Motion Execution

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Qibin Zhu, Yaonan Hansel, Kay Aoyama, Tadayoshi Hasegawa, Yasuhisa Department of Micro-Nano Mechanical Science and Engineering Nagoya University Aichi Nagoya464-8603 Japan Department of Computer Science Technical University of Darmstadt Hochschulstr. 10 Darmstadt64289 Germany

With the continuous advancement of robot teleoperation technology, shared control is used to reduce the physical and mental load of the operator in teleoperation system. This paper proposes an alternating shared control framework for object grasping that considers both operator’s preferences through their manual manipulation and the constraints of the follower robot. The switching between manual mode and automatic mode enables the operator to intervene the task according to their wishes. The generation of the grasping pose takes into account the current state of the operator’s hand pose, as well as the manipulability of the robot. The object grasping experiment indicates that the use of the proposed grasping pose selection strategy leads to smoother follower movements when switching from manual mode to automatic mode. © 2023, CC BY.

关键词： Robots

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yuan, Puzhen Ma, Angyuan Yao, Yunchao Yao, Huaxiu Tomizuka, Masayoshi Ding, Mingyu Xingjian College Tsinghua University China Robotics Institute Carnegie Mellon University United States Department of Computer Science UNC Chapel Hill United States Department of Mechanical Engineering UC Berkeley United States

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC’s effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC’s superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline without any task-specific prompting or finetuning. Copyright © 2025, The Authors. All rights r

关键词： Robot programming

Optimized Human Drowsiness Detection using Spatial and Temporal features of Eye and Mouth

学校读者我要写书评

暂无评论

Optimized Human Drowsiness Detection using Spatial and Tempo...

International Conference on Signal Processing and Integrated Networks (SPIN)

作者： Anushka Gupta Vinod Maan Kuldip Singh Sangwan Dhiraj Department of Electronics and Instrumentation Birla Institute of Technology and Science Pilani Rajasthan Department of Computer Science & Engineering Mody Unversity Rajasthan Department of Mechanical Engineering Birla Institute of Technology and Science Pilani Rajasthan Integrated Circuits & Systems Group CSIR-CEERI Pilani Rajasthan

Drowsy drivers can cause casualties, grave injuries, and fimancial waste; thus, it is essential to have a mechanism that detects drowsiness among drivers. This paper presents a compressed non-intrusive drowsiness monitoring system in three phases. In phase 1, we target the detection of human drowsiness using a set of state-of-the-art machine learning architectures and a custom architecture by using the state of eye and mouth regions from a combination of the MRL Eye and YawDD datasets. Out of VGG-16 (97% test accuracy), Xception (98%), MobileNet (97%), InceptionV3 (98%), and custom architecture (98%), the custom architecture is selected to get carried forward to the subsequent phases because it gives comparable results to deeper models with 100 times fewer parameters. The satisfactory performance of this model was also verified on a selective subset of the NTHU-DDD video dataset. In phase 2, the custom architecture is employed to extract appearance-related features from a set of frames used by an LSTM network to learn motion-related characteristics. The CNN+LSTM model gives 98% test accuracy on the mouth test dataset. In phase 3, to target an embedded board implementation, we used the knowledge distillation technique where the thinned-out version of custom architecture (student network) to get trained under the guidance of Xception (teacher network). Under this experimental phase, the accuracy of the student network got increased from 92% to 96.4% on eye detection and from 97% to 98% on mouth detection.

关键词： Knowledge engineering Convolution Mouth Deep architecture Machine learning Feature extraction Monitoring

Design and Implementation of a LoRa-Based Remote Health Monitoring System with Emergency Alert Capabilities

学校读者我要写书评

暂无评论

Design and Implementation of a LoRa-Based Remote Health Moni...

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Rajesh K P Vinu Kumar S M Parameshwari V Divyaa N Manikanda Prabu Nallasivam Padma Suresh L Electronics & Communication Engineering Sri Krishna College of Technology Coimbatore India Mechanical Engineering Sri Krishna College of Technology Coimbatore India Electronics & Communication Engineering Nandha Engineering College Erode India Electronics & Communication Engineering Velalar College of Engineering and Technology Erode India Computer Science and Engineering Baselios Mathews II College of Engineering Sasthamcotta Kerala India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Saving human lives is essential in the field of medical science. engineering technologies support to achieve this goal. This article explores the integration of Internet of Things and LoRa technology in hospital wristbands to enhance patient care and streamline healthcare operations. The proposed system employs Arduino Pro Mini microcontrollers and LoRa1276 in the LoRa enabled Patient Wrist Band Module (LPWM) to facilitate real-time monitoring of patient vital signs, such as temperature and pulse. The acquired data is transmitted wirelessly to a central nursing station. In the nursing station, a Raspberry Pi equipped with a LoRa receiver device consolidates and displays the data. Grey Wolf Optimization algorithm is used in Raspberry Pi to prioritize patient care based on predefined parameters. The integration of Explainable AI in the receiver module enhances the transparency and trustworthiness of AI-driven recommendations. This supports personalized patient care. This comprehensive approach aims to bridge the healthcare gap in ensuring efficient resource allocation and improved patient outcomes through advanced technological solutions.

关键词： Wrist Microcontrollers Explainable AI Medical services Receivers Real-time systems Resource management

DrivAerNet++: a large-scale multimodal car dataset with computational fluid dynamics simulations and deep learning benchmarks 24

学校读者我要写书评

暂无评论

DrivAerNet++: a large-scale multimodal car dataset with comp...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Mohamed Elrefaie Florin Morar Angela Dai Faez Ahmed Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA Morphing and Optimization Solutions BETA CAE SYSTEMS USA Inc Farmington Hills MI Department of Computer Science Technical University of Munich Garching Germany

ISBN: (纸本)9798331314385

We present DrivAerNet++, the largest and most comprehensive multimodal dataset for aerodynamic car design. DrivAerNet++ comprises 8,000 diverse car designs modeled with high-fidelity computational fluid dynamics (CFD) simulations. The dataset includes diverse car configurations such as fastback, notchback, and estateback, with different underbody and wheel designs to represent both internal combustion engines and electric vehicles. Each entry in the dataset features detailed 3D meshes, parametric models, aerodynamic coefficients, and extensive flow and surface field data, along with segmented parts for car classification and point cloud data. This dataset supports a wide array of machine learning applications including data-driven design optimization, generative modeling, surrogate model training, CFD simulation acceleration, and geometric classification. With more than 39 TB of publicly available engineering data, DrivAerNet++ fills a significant gap in available resources, providing high-quality, diverse data to enhance model training, promote generalization, and accelerate automotive design processes. Along with rigorous dataset validation, we also provide ML benchmarking results on the task of aerodynamic drag prediction, showcasing the breadth of applications supported by our dataset. This dataset is set to significantly impact automotive design and broader engineering disciplines by fostering innovation and improving the fidelity of aerodynamic evaluations. Dataset and code available at: https://***/Mohamedelrefaie/DrivAerNet

关键词：

Advancements in Repetitive Action Counting: Joint-Based PoseRAC Model With Improved Performance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Haodong Zendehdel, Niloofar Leu, Ming C. Moniruzzaman, Md Yin, Zhaozheng Hajmohammadi, Solmaz Department of Mechanical and Aerospace Engineering Missouri University of Science and Technology United States Department of Biomedical Informatics Department of Computer Science Stony Brook University United States Peloton Interactive United States

Repetitive counting (RepCount) is critical in various applications, such as fitness tracking and rehabilitation. Previous methods have relied on the estimation of red-green- and-blue (RGB) frames and body pose landmarks to identify the number of action repetitions, but these methods suffer from a number of issues, including the inability to stably handle changes in camera viewpoints, over-counting, under-counting, difficulty in distinguishing between sub-actions, inaccuracy in recognizing salient poses, etc. In this paper, based on the work done by [1], we integrate joint angles with body pose landmarks to address these challenges and achieve better results than the state-of-the-art RepCount methods, with a Mean Absolute Error (MAE) of 0.211 and an Off-By-One (OBO) counting accuracy of 0.599 on the RepCount data set [2]. Comprehensive experimental results demonstrate the effectiveness and robustness of our method. © 2023, CC BY.

关键词：