检索结果-内蒙古大学图书馆

control valve simulation method integrable into the global gradient algorithm

ISH Journal of Hydraulic Engineering 2025年第1期31卷 1-7页

作者： Sivakumar, P. Gorev, N.B. Gorev, V.N. Kodzhespirova, I.F. Shedlovsky, I.A. Itanagar India Department for Functional Elements of Control Systems Institute of Technical Mechanics Dnipro Ukraine Department of Physics Dnipro University of Technology Dnipro Ukraine Department of Automation and Computer Systems Dnipro University of Technology Dnipro Ukraine

This paper presents a refinement of a method that simulates flow- and pressure-regulating valves by replacing them with pipes and adjusting the resistances (diameters) of those pipes to meet the valve settings. The method, referred to as the replacing pipe method (RPM), is readily integrable into the global gradient algorithm, which is the heart of the commonly used EPANET 2 water distribution system modeling software. The RPM proved to be more robust, yet slower than the EPANET 2 valve handling heuristics. In this work, the RPM was modified to increase its computational speed. The modification involved the RPM check valve handling algorithm and condition for updating the diameters of the valve-replacing pipes. The modified RPM was tested as part of a hybrid simulator, which switches from the EPANET 2 valve handling heuristics to the RPM when the former fails. The test networks included a large network with thousands of nodes, pipes, and valves, and a case of an ill-posed problem. As the testing showed, the modified RPM offers a significant reduction in the number of iterations compared to its previous version. © 2024 Indian Society for Hydraulics.

关键词： Safety valves

来源：评论

学校读者我要写书评

暂无评论

Tactical Conflict Avoidance of Manned Traffic - Display Concepts for UAV Pilots

引用

CEAS Aeronautical Journal 2024年第2期15卷 315-324页

作者： Peukert, Markus Santel, Christoph G. Institute of Flight Systems and Automatic Control Technical University of Darmstadt Otto-Berndt-Str. 2 Darmstadt64287 Germany Garrecht Avionik GmbH Wieslocher Str. 38 Walldorf69190 Germany

The number of collisions between manned and unmanned aerial vehicles (UAVs) has risen due to the increased use of UAVs. Pilots of manned aircraft can visually detect the usually much smaller UAVs only very late or not at all, which is why UAVs are required to avoid manned aircraft in lower airspace by most regulations. For the task of collision avoidance, the UAV pilot needs appropriate traffic awareness. While operating UAVs within the visual line of sight (VLOS), the UAV pilot can monitor the surrounding traffic himself, but operation beyond the visual line of sight (BVLOS) requires an additional airspace observer or a supporting detect-and-avoid system. In this work, a traffic display concept supporting UAV pilots is derived and proposed using the human-centered design process. Commonly used collision avoidance displays of manned and unmanned aviation are reviewed and the user context for the proposed traffic display is introduced. An online survey is conducted to gather user preferences for several 2D graphical elements of the traffic display. 25 experienced UAV pilots participated in the survey. The data is analyzed using Gwet’s AC1 agreement coefficient. Overall, fair agreement can be observed with individual coefficients for different 2D graphical elements ranging from poor to almost perfect agreement. With a developed heuristic, preferred 2D graphical elements are extracted and combinations reviewed to derive a complete traffic display design. The proposed traffic display design, based on user preferences, will be implemented for further evaluation in human-in-the-loop experiments. © The Author(s) 2024.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Instance-Wise MRI Reconstruction Based on Self-Supervised Implicit Neural Representation 46

Instance-Wise MRI Reconstruction Based on Self-Supervised Im...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Yang, Song-Xiao Li, Yi-Zhou Okutomi, Masatoshi Tokyo Institute of Technology School of Engineering Department of Systems and Control Engineering Tokyo Japan

ISBN: (纸本)9798350371499

Accelerated MRI involves a trade-off between sampling sufficiency and acquisition time. Supervised deep learning methods have shown great success in MRI reconstruction from under-sampled measurements, but they typically require a large set of fully-sampled MR images for training, which can be difficult to obtain. In this paper, we present a novel fully self-supervised method based on implicit neural representation, which requires only a single under-sampled MRI instance for training. To effectively guide the self-supervised learning process, we introduced multiple novel supervisory signals in both the image and frequency domains. Experimental results indicate that the proposed method outperforms existing self-supervised methods and even a supervised method, demonstrating its strong reliability and flexibility. Our code is publicly available at https://***/YSongxiao/*** relevance - The proposed method can significantly enhance the image quality of under-sampled MR images without the need of ground-truth fully-sampled MR images for supervision and additional prior images for guidance. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

automatic control of Wall-following Mobile Robots Based on Machine Learning

Automatic Control of Wall-following Mobile Robots Based on M...

引用

2024 Conference of Young Researchers in Electrical and Electronic Engineering, ElCon 2024

作者： Hammoud, Moahmmed Lupin, Sergey National Research University of Electronic Technology Institute of Microdevices and Control Systems Moscow Russia

ISBN: (纸本)9798350360646

Mobile robots have become increasingly popular in various industries and applications due to their versatility and ability to perform tasks safely, effectively, and independently. They can operate in hazardous or inaccessible areas, thus reducing the risk of injury to human workers. Mobile robots can also work continuously without breaks, thus increasing productivity and reducing labor costs. Wall-following mobile robots (WMRs) use sensors and algorithms to detect and avoid obstacles while maintaining a constant distance from them. They are instrumental in environments with narrow passages or limited visibility, such as underground tunnels or mines. This study used a benchmark dataset collected by the SCITOS G5 robot to evaluate various Machine Learning (ML) algorithms. This research guides on selecting an ML algorithm to achieve a balance between accuracy and memory consumption. The experiments showed that eXtreme Gradient Boosting (XGB) performed the best with a macro F1-score of 0.9934 on 24 sensor readings. © 2024 IEEE.

关键词： machine learning Mobile robot Multi-category classification SCITOS G5 wall-following robot

来源：评论

学校读者我要写书评

暂无评论

Network Generating Network for Multi-scale Image Classification 2

Network Generating Network for Multi-scale Image Classificat...

引用

2nd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum, AIBDF 2022

作者： Dong, Hang Xiao, Liping Cong, Longjian Zhou, Bin National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9781510663107

Features extracted by the neural network do not have scale invariance, which makes multi-scale image recognition and classification a difficult problem. Recent studies have proposed many new ways to solve this problem, such as feature fusion, sensor field transformation, etc. However, none of them essentially solve the problem that the neural network does not have scale invariance. In this paper, we propose a network generating network (NGN) architecture and design the NGNResNet network, which is an improved version of the ResNet network. The network can identify images at three scales simultaneously and has scale invariance. The experimental results show that the NGN structure helps us to improve the classification accuracy of small-scale images by about 10 percentage points, and helps to improve the performance of the network in the face of small targets. © 2023 SPIE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Path Planning Algorithms for Warehouse Mobile Robot Based on Reinforcement Learning

Experimental Study on Path Planning Algorithms for Warehouse...

引用

2024 Conference of Young Researchers in Electrical and Electronic Engineering, ElCon 2024

作者： Hammoud, Moahmmed Haydar, Ola Lupin, Sergey Institute of Microdevices and Control Systems National Research University of Electronic Technology Moscow Russia

ISBN: (纸本)9798350360646

Planning in mobile robots is an essential task because it helps to achieve efficient movement in terms of time, computational resources, and safety. Warehouse robots, for example, are equipped with sensors and cameras to avoid obstacles and to move products around the warehouse pick and pack orders. In this project, we have used path-planning algorithms based on Reinforcement Learning (RL), which include Q-learning (QL), State-Action-Reward-State-Action (SARSA), and Expected SARSA (ESARSA). We evaluated these algorithms on a benchmark dataset with different sizes and obstacle densities. Our findings show that QL produces a more optimal path, but the path is risky since it is close to obstacles. On the other hand, SARSA produces a safer path. However, in terms of convergence speed, SARSA is slow, while ESARSA is faster and more stable but with extra computations. © 2024 IEEE.

关键词： machine learning Mobile robot Multi-category classification SCITOS G5 wall-following robot

来源：评论

学校读者我要写书评

暂无评论

Efficient News Synopsis Generation with T5 Transformers 12

Efficient News Synopsis Generation with T5 Transformers

引用

12th IEEE International Conference on Intelligent systems, IS 2024

作者： António, João Mihaylova, Lyudmila Georgieva, Petia Aveiro Portugal University of Sheffield Dep. of Automatic Control and Systems Engineering Sheffield United Kingdom Institute of Telecommunications Aveiro Portugal

ISBN: (纸本)9798350350982

In this paper we propose a Text-To-Text Transfer Transformer-based (T5) model to generate concise, human-like synopses of Merger and Acquisition (M&A) economic news. Leveraging recent advancements in artificial intelligence and natural language processing, we have focused our resources on the creation of a specific summarizer, opting for a translation of all news into English to ensure consistency and mitigate complexity. The implementation of Graphics processing unit (GPU) resources for model training played a crucial role in optimizing the learning process, allowing us to effectively utilize the time window provided by platforms such as Google Colab Pro and Free. Through iterative fine-tuning, our model was trained to generate high-quality, human-like synopses of M&A events. Our findings underscore the enhanced transparency and interpretability of the proposed generative AI-driven text summariser, suggesting promising avenues for future exploration and development in this field. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Distributed multiple model filtering for markov jump systems with communication delays

引用

Journal of the Franklin institute 2023年第4期360卷 3407-3435页

作者： Li, Hui Yan, Liping Xia, Yuanqing Zhang, Jinhui the Key Laboratory of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

In this paper, we study a distributed state estimation problem for Markov jump systems (MJS) over sensor networks, in which each sensor node connects with each other through wireless networks with communication delays. We assume that each sensor node maintains a buffer to store delayed data transmitted from neighbor nodes. A distributed multiple model filter is designed by using the interacting multiple model methods (IMM) and a recursive delays compensation method. In order to ensure the stability, two stability conditions are derived for boundedness of estimation errors and boundedness of error covariance. Finally, the effectiveness of the proposed methods is illustrated by simulations and experiments of maneuvering target tracking. © 2022 The Franklin institute

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant control of Hypersonic Flight Vehicle Attitude Tracking Based on Adaptive Dynamic Programming

Fault-Tolerant Control of Hypersonic Flight Vehicle Attitude...

引用

2024 International Annual Conference on Complex systems and Intelligent Science, CSIS-IAC 2024

作者： Liu, Hao Zhou, Chuan Guo, Jian Lu, Dong Cao, Xiaolei Jia, Zhiqiang Nanjing University of Science and Technology School of Automation Nanjing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9798331504755

The attitude control problem of hypersonic flight vehicles (HFV) in the presence of bias faults is addressed in this paper, and an intelligent fault-tolerant control strategy using Adaptive Dynamic Programming (ADP) is proposed. A new performance index function is adopted for the fault-tolerant controller design to deal with bias faults. The fault-tolerant control problem is transformed as an optimized control problem based on the improved performance index function. Utilizing policy iteration, a critic neural network is constructed to solve the Hamilton-Jacobi-Bellman equation and the approximate optimal controller is obtained. The uniform ultimate boundedness of the closed-loop system is proved by the Lyapunov stability theorem. Theoretical derivation and simulation verification demonstrate the effectiveness of the proposed fault-tolerant control strategy. © 2024 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Simulation of an Adaptive Model Based on AIC and BIC ARIMA Predictions

Simulation of an Adaptive Model Based on AIC and BIC ARIMA P...

引用

2022 International Conference on Applied Mathematics and Digital Simulation, AMDS 2022

作者： Zhang, Ying Meng, Gong National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ARIMA model forecasting algorithm is a commonly used time series forecasting algorithm, this paper first obtains a stable sequence through differential operation, and then obtains a stable sequence from the AR model, as the MA model, and even the ARIMA model. Select the appropriate model for prediction and use it for adaptive mode model design. In the field of machine learning, the complexity of the model is likely to increase, while the accuracy of the model improves, and the models with a complex structure usually cause the following overfitting problem. In order to balance the complexity and the accuracy of the model reasonably, using appropriate indicators AIC (Akaike Information Criterion), as well as BIC (Bayesian information criterion), to make the judgments, which is achieved by eliciting penalty terms in the paper, and the established ARIMA (1,1,2) model meets the requirements. © Published under licence by IOP Publishing Ltd.

关键词： Forecasting

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：