检索结果-内蒙古大学图书馆

Advanced Algorithms and control Engineering (ICAACE), international conference on

作者： Yuntian Hou Di Zhang Department of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Suzhou China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

This study introduces Starformer, a hybrid model combining Graph Neural Networks (GNNs) with a novel Series-Core Fusion (SC-Fusion) mechanism for urban traffic prediction. By leveraging GNNs for spatial modeling and SC-Fusion for efficient temporal dependency capture, the model effectively addresses complex spatio-temporal dynamics in traffic systems. Evaluated on six widely used traffic datasets-METR-LA, PEMS-BAY, PEMS03, PEMS04, PEMS07, and PEMS08-Starformer demonstrates consistent and robust performance across diverse traffic conditions and regions. The results highlight its ability to model both short-term and long-term dependencies, making it well-suited for real-world applications. These findings emphasize the potential of integrating advanced neural network architectures for intelligent traffic management, contributing to smarter, more sustainable urban transportation systems.

关键词： control engineering Accuracy Scalability Time series analysis Transportation Predictive models Prediction algorithms Graph neural networks Forecasting

来源：评论

学校读者我要写书评

暂无评论

Digital Twin of Npps: Simulation systems and Verification

Digital Twin of Npps: Simulation Systems and Verification

引用

2021 international Russian Automation conference, RusAutoCon 2021

作者： Jharko, Elena V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Laboratory of Distributed Information and Control Systems Moscow Russia

ISBN: (纸本)9780738131566

The article discusses the approach conformity with which the flexible software package (FMSP) is the kernel of the digital twin of an NPP power unit. The models that are part of the FMSP cover the main and a number of auxiliary technological systems of the power unit, automatic control systems. The developed flexible modeling software package is designed to simulate dynamic processes occurring in NPP power units with VVER-1000 reactors. The FMSP allows considering various types of violations in the operation of safety systems and energy imbalances in the reactor core. The results of verification of a flexible modeling complex based on stationary neutron-physical calculations of the VVER-1000 reactor core using the BIPR-7 program and NPP operational data are presented. © 2021 IEEE.

关键词： Verification

来源：评论

学校读者我要写书评

暂无评论

On the Fixed-Interval Smoothing for Jump Markov Nonlinear systems 25

On the Fixed-Interval Smoothing for Jump Markov Nonlinear Sy...

引用

25th international conference of Information Fusion (FUSION)

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Xue, Yanbo Univ Canterbury Dept Elect & Comp Engn Christchurch New Zealand Natl Univ Def Technol State Key Lab Complex Electromagnet Environm Effe Changsha Peoples R China Univ Sheffield Dept Automat Control & Syst Engn Sheffield S Yorkshire England Career Sci Lab Beijing Peoples R China

ISBN: (数字)9781737749721

ISBN: (纸本)9781665489416

This paper considers the fixed-interval smoothing for jump Markov systems. An optimal backward-time recursive equation for computing the joint posterior of the state vector and model index is established first. A suboptimal algorithm is then developed to approximate the new Bayesian smoother under nonlinear state-space models with additive Gaussian noise. The proposed method utilizes the well-known assumed density filtering with Gaussian assumption and the expression for the quotient of two Gaussian densities to compute the smoothing posterior. It eliminates the need for finding the inverse of the state dynamics and can handle singular process noise covariance, compared with several existing multiple model smoothers. Promising results are obtained in simulations using a maneuvering target tracking task.

关键词： Smoothing methods Target tracking Computational modeling Gaussian noise Markov processes Approximation algorithms Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Optimization of the Technological Process of Deironing Groundwater in Critical Water Supply Infrastructure of Settlements 17

Optimization of the Technological Process of Deironing Groun...

引用

IEEE 17th international conference on Computer Sciences and Information Technologies (CSIT)

作者： Martynov, Sergiy Kunytskyi, Sergiy Shatnyi, Serhii Ivanchuk, Nataliia Galkina, Olena Natl Univ Water & Environm Engn Dept Water Supply Water Dispousal & Drilling Rivne Ukraine Natl Univ Water & Environm Engn Res Dept Rivne Ukraine Natl Univ Water & Environm Engn Dept Comp Engn Rivne Ukraine Natl Univ Water & Environm Engn Dept Appl Math & Comp Sci Rivne Ukraine Beketov Natl Univ Urban Econ Kharkiv Dept Water Supply Water Dispousal & Water Treatme Kharkiv Ukraine

ISBN: (纸本)9798350334319

The article examines tower-columns for the drinking water supply of the rural population, proposes methods of their automation, which consists in automatically regulating the performance of pumps by applying the principles of controlling electric drives. The existing automated systems were analyzed and the one proposed in the form of a structural diagram was synthesized, where the main control circuit for regulation is the pressure in the pipeline. The main parameters and transfer functions of the components of the automatic system were mathematically calculated. Based on the above calculations, a simulation model was designed and built in a specialized software complex. By means of modeling and simulation of the process, the transient characteristics are determined and the main quality indicators are determined.

关键词： iron removal filtering expanded polystyrene column tower automated control system structural diagram mathematical model regulator transition process

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks-based Model Predictive control for Automated Surface Vessels

Physics-Informed Neural Networks-based Model Predictive Cont...

引用

international conference on control, Automation and systems ( ICCAS)

作者： Jiahang Liu Yuxiang Zhang Yunze Leng Shuzhi Sam Ge Bernard Voon Ee How Department of Electrical and Computer Engineering National University of Singapore Singapore Enigneering Cluster Singapore Institute of Technology Singapore

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Ensuring accurate and efficient operation of automated surface vessels under uncertainties and environmental disturbances remains technically complex and practically challenging for the safety and reliability of intelligent maritime systems. For such safety-critical operations, this paper proposes the physical-informed neural network (PINN)-based method for automated surface vessel control that integrates deep learning neural networks into the nonlinear model predictive control (NMPC) framework. Compared with the pure neural networks method, PINN integrates the physics information into the loss function and adds control actions and initial conditions to the input of the prediction model. By adopting the PINN as the prediction model of NMPC during the optimization process, better control accuracy has been achieved, and the forward prediction time and computational complexity have been reduced. In conclusion, the proposed method is proven to be efficient through comparison studies with pure deep learning networks and experiments with higher accuracy of prediction and control.

关键词： Deep learning Accuracy Uncertainty Computational modeling Neural networks Predictive models Safety Reliability Physics Predictive control

来源：评论

学校读者我要写书评

暂无评论

Representing control Software Functionality as Part of a Modular, Mechatronic Construction Kit

Representing Control Software Functionality as Part of a Mod...

引用

IEEE international conference on Industrial Engineering and Engineering Management (IEEM)

作者： Neumann, E. M. Vogel-Heuser, B. Bayar, I Tech Univ Munich TUM Sch Engn & Design Inst Automat & Informat Syst Dept Mech Engn Munich Germany MDSI Munich Germany MIRMI Munich Germany

ISBN: (纸本)9781665437714

automated Production systems (aPS) are highly complex mechatronic systems with lifetimes of up to 50 years. The lack of advanced software engineering methods in industrial automation often causes historically grown legacy code with low quality. modeling and refactoring of legacy control software are considered as inevitable to manage ever-increasing software complexity and face upcoming challenges in the context of Industry 4.0. However, promising goals such as mechatronic modularization, product line engineering, or variability management have up to now hardly made their way to control software in aPS. To address this gap, the main contribution of this paper is a concept of function-oriented software modeling for aPS. The approach provides three models to map control software in aPS to the implemented system functionalities on code level, by also considering extra-functional software tasks that cannot be directly mapped to the physical modules. The models are implemented using ME-TUS software, i.e., a renowned tool for modeling and optimizing mechatronic system architectures based on a function-oriented construction kit principle. The modeling approach is evaluated with industrial and academic experts with promising results.

关键词： automated Production systems control software IEC 61131-3. software architecture function-oriented modularization mechatronic construction kit

来源：评论

学校读者我要写书评

暂无评论

Failure control Scheme of Network Automatic Transfer Switching Unit in Ring Network

Failure Control Scheme of Network Automatic Transfer Switchi...

引用

international conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Igor Fomin Vadim Chernyshov Maxim Borodin Roman Belikov Vadim Bolshev Alexander Alexandrovich Lansberg Department of Power Supply Orel State Agrarian University Orel Russia Department of "Electrical Equipment and Energy Saving" Orel State University Orel Russia Laboratory of Power and Heat Supply Federal Scientific Agroengineering Center VIM Moscow Russia

Reliability of power transmission lines ensures the reliability of power supply to consumers. The accident rate and the number of power supply outages depend on the condition and quality of operation of power lines. At the same time, agricultural networks are characterized by the greatest length and low reliability. Consumers of all reliability categories are connected to distribution networks. Low reliability and high deterioration of agricultural distribution networks adversely affect the reliability of power supply to consumers. Improving power supply reliability for consumers of the agro-industrial complex will reduce interruptions in power supply, reduce direct economic and technological damage as well as the losses of power supply organizations as a result of decreasing the undersupply of electricity. From the foregoing, it follows that consumers and producers of electricity are interested parties in improving the reliability of power supply to consumers of the agro-industrial complex. The proposed circuit for monitoring failures of right triggering the automatic transfer switch unit will reduce the damage from undersupply of electric energy and increase the reliability of power supply to consumers of the agro-industrial complex. The implementation of the developed scheme will reduce the economic and technological damage to agricultural consumers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAN: Attention-based social aggregation neural networks for recommendation system

引用

international JOURNAL OF INTELLIGENT systems 2022年第6期37卷 3373-3393页

作者： Jiang, Nan Gao, Li Duan, Fuxian Wen, Jie Wan, Tao Chen, Honglong East China Jiaotong Univ Coll Informat Engn Nanchang 330013 Jiangxi Peoples R China China Univ Petr Coll Control Sci & Engn Qingdao Peoples R China

The recommender system is of great significance to alleviate information overload. The rise of online social networks leads to a promising direction-social recommendation. By injecting the interaction influence among social users, recommendation performance has been further improved. Successful as they are, we argue that most social recommendation methods are still not sufficient to make full use of social network information. Existing solutions typically either considered only the local neighbors or treat neighbors' information equally, even or both. However, few studies have attempted to solve these social recommendation problems jointly from both the perspective of social depth and social strength. Recently, graph convolutional neural networks have shown great potential in learning graph data by modeling the information propagation and aggregation process. Thus, we propose an attention-based social aggregation neural networks (abbreviated as SAN) model to build a recommendation system. Different from previous work, our proposed SAN model simulates the recursive social aggregation process to spread the global social influence, and simultaneously introduces social attention mechanism to incorporate the heterogeneous influences for better model user embedding. Instead of a shallow linear interaction function, we adopt multi-layer perception to model the complex user-item interaction. Extensive experiments on two real-world datasets show the effectiveness of our proposed model SAN, and further analysis verifies the generalization and flexibility of the model.

关键词： attention graph convolutional networks social influence social interaction social recommendation

来源：评论

学校读者我要写书评

暂无评论

Theoretics of Zhang Neurodynamics Models for Position-Orientation control of Soft Continuum Robots from Kinematic modeling to Noise Suppression

Theoretics of Zhang Neurodynamics Models for Position-Orient...

引用

complex systems and Intelligent Science (CSIS-IAC), international Annual conference on

作者： Jiawei Chen Min Yang Haifeng Hu Yunong Zhang Ning Tan School of Computer Science and Engineering Sun Yat-sen University Guangzhou P. R. China School of Electronics and Information Technology Sun Yat-sen University Guangzhou P. R. China

Compared with conventional redundant robots, soft continuum robots (simply termed soft robots or continuum robots) are more flexible, so they have broad application prospects in the future. Although there are a few studies focused on the position-orientation tracking control of soft continuum robots, most of those studies are based on continuous mod-els/algorithms and may have poor effectiveness in noisy environments. Generally, discrete models/algorithms are more friendly to the digital computer, chip, and so on. Hence, developing a discrete, effective, and robust model for the position-orientation tracking control of soft continuum robots is meaningful and significant. In this paper, we first introduce the kinematic modeling process about a three-section soft robot. Then, we use Zhang neurodynamics (ZN) method and develop a continuous ZN (CZN) model. By applying three time-discretization formulas to discretize the CZN model, three discrete ZN (DZN) algorithms are developed for convenient control purposes. We also consider noise situations. Through formulas and detailed theoretical analyses, we prove that three DZN algorithms have great abilities under noise situations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trajectory control of Midcourse Guidance for Air-to-Air Missile Based on Feedback Linearization and Sliding Mode control

Trajectory Control of Midcourse Guidance for Air-to-Air Miss...

引用

IEEE international conference on Unmanned systems (ICUS)

作者： Chencheng Zhang Zhiqiang Tong Hongquan Liu Weijian Pang College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Air force Research Institute Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

To guarantee the accuracy and energy efficiency of long-distance midcourse guidance for air-to-air missile, a robust trajectory control method based on feedback linearization and sliding mode control is proposed. In guidance loop, the framework of offline trajectory optimization and online tracking control is introduced and the nominal optimal trajectory is obtained by Gauss pseudo-spectral method. In control loop, based on the fact that the velocity profile of tactical missile is untracked, the model is reduced to only depending on flight path angle and height. Furthermore, the reduced complex nonlinear dynamics are accurately linearized by feedback linearization. To overcome the multiple disturbances and parameter perturbation, sliding mode control is introduced to improve the robustness. The global asymptotic stability of the resulting control law is proved. The efficiency and robustness are verified by multiple simulations under the conditions of initial errors, random wind disturbance model, and parameter perturbation.

关键词： Missiles Tracking loops Trajectory planning Perturbation methods Atmospheric modeling Robustness Feedback linearization Nonlinear dynamical systems Sliding mode control Trajectory optimization

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：