检索结果-内蒙古大学图书馆

American control conference (ACC)

作者： Gordon, David C. Winkler, Alexander Bedei, Julian Schaber, Patrick Pischinger, Stefan Andert, Jakob Koch, Charles R. Univ Alberta 116 St & 85 Ave Edmonton AB T6G 2R3 Canada Rhein Westfal TH Aachen Teaching & Res Area Mech Mobile Propuls Forckenbeckstr 4 D-52074 Aachen Germany Rhein Westfal TH Aachen Chair Thermodynam Mobile Energy Convers Syst Forckenbeckstr 4 D-52074 Aachen Germany

ISBN: (纸本)9798350382662;9798350382655

Model Predictive control (MPC) provides an optimal control solution based on a cost function while allowing for the implementation of process constraints. As a model-based optimal control technique, the performance of MPC strongly depends on the model used where a trade-off between model computation time and prediction performance exists. One solution is the integration of MPC with a machine learning (ML) based process model which are quick to evaluate online. This work presents the experimental implementation of a deep neural network (DNN) based nonlinear MPC for Homogeneous Charge Compression Ignition (HCCI) combustion control. The DNN model consists of a Long Short-Term Memory (LSTM) network surrounded by fully connected layers which was trained using experimental engine data and showed acceptable prediction performance with under 5% error for all outputs. Using this model, the MPC is designed to track the Indicated Mean Effective Pressure (IMEP) and combustion phasing trajectories, while minimizing several parameters. Using the acados software package to enable the real-time implementation of the MPC on an ARM Cortex A72, the optimization calculations are completed within 1.4 ms. The external A72 processor is integrated with the prototyping engine controller using a UDP connection allowing for rapid experimental deployment of the NMPC. The IMEP trajectory following of the developed controller was excellent, with a root-mean-square error of 0.133 bar, in addition to observing process constraints.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Lithium-Ion Battery SoC Estimation: A Neural network Approach 28

Lithium-Ion Battery SoC Estimation: A Neural Network Approac...

引用

28th International conference on System Theory control and Computing

作者： Mitroi, Daniel-Catalin Stamatescu, Iulia Arghira, Nicoleta Fagarasan, Ioana Natl Univ Sci & Technol POLITEHN Bucharest Automat & Ind Informat Dept Bucharest Romania

ISBN: (纸本)9798350364309;9798350364293

Technologies supporting smart grid vision and renewable energy management are reshaping traditional energy system distribution, transforming modern buildings into active energy agents capable of generating, storing and trading energy. Furthermore, integrating electric vehicles (EVs) into the energy ecosystem presents both challenges and opportunities. Buildings can support EV charging, and optimized energy management systems can ensure energy efficiency, with an important component of forecasting both generation and vehicle charging needs. This paper aims to develop a Lithium-Ion Battery State of Charge estimation method based on a neural network model, capable of dealing with the main difficulties encountered by the usual methods. After a brief introduction in section I, section ii outlines our contribution to the state of the art in electric vehicle state of charge estimation with neural networks. Section iiI presents the conceptualized methods for the stated problem and exemplification of the implemented methods. The main findings are highlighted in Section IV along with parameter estimation. Section V concludes the paper with perspectives on future work.

关键词： artificial neural network electric vehicle state of charge estimation building management system Levenberg-Marquard algorithm

来源：评论

学校读者我要写书评

暂无评论

performance Prediction of Open Rotor Enabled by Neural network 23

Performance Prediction of Open Rotor Enabled by Neural Netwo...

引用

23rd International conference on control, Automation and systems, ICCAS 2023

作者： Wang, Qihang Zhou, Li Wang, Zhanxue School of Power and Energy Northwestern Poly Technical University Shaanxi Xi'an710129 China Collaborative Innovation Center for Advanced Aero-Engine Beijing100191 China

ISBN: (纸本)9788993215274

In this paper, the prediction of the aerodynamic performance of a contra-rotating open rotor is accomplished based on the neural network. To complete the prediction from design parameters to aerodynamic performance, a neural network is established through a limited set of sample points. The results show that the neural network is able to accurately predict the aerodynamic performance of the contra-rotating open rotor. The constructed neural network depends on the selected design parameters and performance parameters. The number of hidden layers and the number of nodes in the hidden layers greatly affects the accuracy of the prediction. © 2023 ICROS.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An east-westbound control architecture for multi-segment deterministic networking 23

An east-westbound control architecture for multi-segment det...

引用

23rd International-Federation-for-Information-Processing (IFIP) networking conference (IFIP networking)

作者： Miserez, Jakob Colle, Didier Pickavet, Mario Tavernier, Wouter Univ Ghent Ghent Belgium Univ Ghent IMEC Ghent Belgium

ISBN: (纸本)9798350390605;9783903176638

Time-Sensitive networking (TSN) and Deterministic networking (DetNet) provide standardized solutions for reliable real-time communication over respectively L2 and L3 networks. Interconnecting heterogeneous TSN segments and L3 DetNet segments is one of the main open challenges to enable wide area DetNet applications. It requires mapping diverse latency guarantee models, as well as adequate interaction between the control systems of different segments. Current state-of-the-art solutions typically focus on a single network segment, or they don't consider the complex interworking between heterogeneous deterministic network segments. This paper proposes an architecture for routing and signaling end-to-end traffic flows in heterogeneous multi-segment deterministic networks. The proposed East-Westbound interaction architecture between the control systems of DetNet network segments enables a divide-and-conquer strategy that significantly reduces the inherent complexity of provisioning end-to-end routes in these networks. The potential of the architecture is validated through a proof-of-concept in an emulated multi-segment network. Notably, interactions contained within a segment retain constant overhead, while the overhead of actions spanning multiple segments tends to increase when the number of involved segments rises.

关键词： Time-Sensitive networking (TSN) Deterministic networking (DetNet) routing Software-Defined networking (SDN) multi-segment deterministic networks east-westbound

来源：评论

学校读者我要写书评

暂无评论

Adaptive Beacon Period Configurator for Scalable LoRaWAN Downlink Applications

引用

IEEE ACCESS 2023年 11卷 83627-83638页

作者： Todoli-Ferrandis, David Silvestre-Blanes, Javier Sempere-Paya, Victor Santonja-Climent, Salvador Inst Tecnol Informat ITI Valencia 46980 Spain Polytech Univ Valencia UPV Dept Informat Sistemas & Comp DISCA ITI Valencia 46022 Spain Polytech Univ Valencia UPV Dept Comunicac DCOM ITI Valencia 46022 Spain

Low-power wide-area networks (LPWAN) are commonly used because they meet the requirements of Internet-of-Things (IoT) networks with a large number of end devices, such as high network scalability, wide area coverage, low data rates, and delay tolerance while consuming very little energy. The LoRa wide-area network (LoRaWAN) is one of the most popular solutions, supporting three types of medium access control (MAC) options to handle distinct application demands. Class B shortens downlink frame transmission latency while maintaining low energy consumption in the end device. This article analyzes the operation of gateways with class B devices to determine the events that influence scalability and performance, presents an analytical model to describe these systems, and proposes an optimization mechanism called Adaptive Beacon Period Configurator (ABPC). ABPC changes the time-related parameters configuration to improve the usability of these networks in dynamic scenarios. The proposed solution is then simulated and tested against the analytical model. The tradeoff between the waiting time between messages, the probability of reception, and the energy consumption of an end device is shown in the results, describing how traffic density increases impacts in these Key performance Indicators (KPI) and how to try to guarantee these requirements in a network deployment.

关键词： LoRaWAN low power wide area network (LPWAN) scalability network optimization

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable network Slicing Orchestration in network Function Virtualization Compatible Operational Technology Environment

Reconfigurable Network Slicing Orchestration in Network Func...

引用

2024 International conference on Communications control and Computing Technologies for Smart Grids

作者： Delgado, Brian G. Kodiles Aguayo, Jared M. Rivera, Abel O. Gomez Tosh, Deepak K. Univ Texas El Paso Dept Comp Sci El Paso TX 79968 USA Johns Hopkins Univ Appl Phys Lab Laurel MD USA Sandia Natl Labs Albuquerque NM USA

ISBN: (纸本)9798350318562;9798350318555

The ongoing transition to Industry 4.0, which is characterized by increased inter-connectivity of cyber-physical systems, requires having time-sensitive, high throughput, and secure transfer of critical data in industrial sites. In this context, network slicing emerges as a critical tool to ensure timely data delivery by provisioning the network resources to cater to specific applications' requirements and mitigating potential cyber attacks. To address these challenges, this paper aims to tackle two key questions essential for the successful implementation of network slicing in industrial environments. First, it investigates architectural considerations for developing a network infrastructure capable of supporting network slicing functionalities effectively. The proposed approach significantly improves deployment efficiency over traditional manual configurations. Second, it delves into the automated orchestration process, elucidating the steps and components involved in transitioning from a static network management approach to dynamically leverage network function virtualization schemes for creating network slices in ad-hoc manner. The system demonstrates high throughput suitable for production-level solutions and maintains exceptionally low latency, making it ideal for ultra-reliable low-latency communications. Even with increased network demands, the system remains stable, with effective Quality of Service (QoS) management, ensuring reliable performance under varying conditions. The proposed architecture outlines the necessary components, services, and communication protocols required for a production-level orchestrator for network segmentation in SCADA environments.

关键词： Cyber-Physical systems network Function Virtualization Operational Technology Software-Defined network

来源：评论

学校读者我要写书评

暂无评论

ANN -PI controller for the Grid -Side Converters in Wind Energy Conversions systems under Voltage Dips 12

ANN -PI Controller for the Grid -Side Converters in Wind Ene...

引用

12th IFAC Symposium on control of Power and Energy systems (CPES)

作者： Rafia, H. Ouadi, H. El Bhiri, B. Mohammed V Univ Natl Sch Arts & Crafts ERERA Rabat Morocco Smartilab EMSI Rabat Morocco

Standard electrical network codes require wind power systems to maintain the supply of active and reactive power, even in the event of operating conditions being disrupted. This paper presents a new controller for the grid side converter (GSC) in a wind power system based on a doubly fed induction generator (DFIG). This controller integrates a neural network, which adjusts the parameters of a PI regulator in real time. This enables the wind system to adapt to varying operating conditions. The control objectives are twofold: (i) regulating the DC bus voltage through the control of the injected grid current quadratic component;and (ii) regulating the reactive power transmitted to the grid, through the control of the injected grid current direct component. The reactive power control allows the wind system power factor (PFC) to be adjusted. To highlight the interest of the proposed controller, these performances are compared to that of a controller based on conventional PI regulators. The simulations presented here were conducted in Matlab/Simulink and demonstrate the enhanced performance of the proposed controller.

关键词： ANN-PI controller,GSC control ANN VDC control gradient descent

来源：评论

学校读者我要写书评

暂无评论

Application of RBF neural network PID control on buck DC-DC converter

Application of RBF neural network PID control on buck DC-DC ...

引用

2024 International conference on Power Electronics and Electrical Engineering, P3E 2024

作者： Pan, Ning Wu, Guitai Li, Renlong School of Electrical Engineering and Automation Jiangxi University of Science and Technology Ganzhou341000 China

A structure to solve low control accuracy and poor tracking performance in traditional PID controlled DC-DC converters when input voltages and load currents fluctuate has been proposed: combining PID control with Radial Basis Function (RBF) neural networks. To optimize the PID controller’s parameters, this approach makes use of the RBF neural network’s approximation capability for nonlinear functions. Under different test conditions, the neural network takes the output voltage and its deviation from the reference value as inputs. The hidden layer employs Gaussian activation and adjusts by gradient descent. The output layer computes the PID controller’s Proportional (Kp), Integral (Ki), and Derivative (Kd) by the linear combination of hidden layer node outputs. Simulation results using MATLAB/Simulink demonstrate that, under different test conditions, the system employing RBF neural network-PID control exhibits a smaller overshoot compared to traditional PID control systems. Furthermore, in steady-state circumstances, the settling time is shortened by around 1/2 and is decreased by roughly 1/4 in the presence of disturbance signals. These results unequivocally demonstrate that, in the presence of fluctuating test conditions, the new structure of this combination greatly improves the control precision and tracking performance of DC-DC converters. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Pipeline Edge Detection Model Based on Heterogeneous Knowledge Distillation

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2024年第12期71卷 5059-5063页

作者： Zhu, Chengyuan Pu, Yanyun Lyu, Zhuoling Wu, Aonan Yang, Kaixiang Yang, Qinmin Zhejiang Univ Coll Control Sci & Engn Hangzhou 310007 Zhejiang Peoples R China Zhejiang Univ Huzhou Inst Huzhou 313000 Zhejiang Peoples R China Zhejiang Univ Coll Engineers Hangzhou 310007 Zhejiang Peoples R China South China Univ Technol Coll Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

The pipeline safety warning system (PSEW) is an important guarantee for the safe transportation of energy pipelines. Given the constraints of deploying detection models at resource-limited pipeline stations, there is a compelling need to develop efficient, lightweight models suitable for edge device applications. This brief introduces an adaptive heterogeneous model knowledge distillation network (AHKDnet) for edge deployment of pipeline network detection models. The global information and long-distance dependency relationships from the ViT-based teacher network are transferred to the CNN-based shallow student network. We introduce the learnable modulation parameters to optimize target information enhancement, reducing the impact of irrelevant information. By embedding the model selection at each stage of knowledge distillation, the performance collapse of student models caused by misleading cross-architecture knowledge is avoided, and model convergence is accelerated. Experiments on three actual scene datasets of pipeline networks show that AHKDnet outperforms the state-of-the-art KD methods and has strong generalization ability. Notably, AHKDnet enhances the recognition performance of shallow student networks by an average of 10%, highlighting its efficacy and potential for practical applications. Our method can provide a new reference for edge deployment of PSEW.

关键词： Pipeline network safety knowledge distillation heterogeneous model lightweight distributed optical fiber

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation of Large-Scale Communication network based on Machine Learning 2

Resource Allocation of Large-Scale Communication Network bas...

引用

2nd IEEE International conference on Integrated Circuits and Communication systems, ICICACS 2024

作者： Zhang, Zhuxin Mo, Ruifeng Hou, Xiaoqi Wei, Xin Guo, Suzhen Research Institute North Automatic Control Technology Taiyuan China

ISBN: (纸本)9798350317558

With the continuous development of mobile Internet technology, its demand for network performance is also increasing. Although the traditional multi-level structure of network resources enhances the scalability and independence of the network, it cannot be used effectively, nor can it intelligently configure network resources. To this end, this paper explores a new network resource allocation method, namely, a machine learning-based large-scale communication network resource allocation method. This paper first explains the concepts of communication network resource allocation and machine learning, and then proposes the principle of communication network resource allocation based on machine learning. Finally, through experiments, this paper analyzes that the bandwidth utilization rate, data delay and packet loss rate of the communication network resource allocation based on the method in this paper are 78%, 5ms and 0.05%, respectively, and the comprehensive performance is better than other communication network resource allocation methods. © 2024 IEEE.

关键词： Communication network Resource Allocation Information Age Machine Learning Optimization Capability

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：