检索结果-内蒙古大学图书馆

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Cui, Zhigang Yao, Wenlong Chi, Ronghu Chen, Xianghao The College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao266100 China

ISBN: (纸本)9798350361674

A multi-motor speed synchronization control method is proposed for the prefabricated vegetable vortex cleaning line in this paper. The focus of this method is to enhance the system's synchronization performance, disturbance rejection capability, dynamic response, and stability of the motors. This method is based on Model-Free Sliding Mode control (MFSMC) combined with an enhanced deviation coupling control structure. Its objective is to tackle the challenges arising from significant variations in motor speed tracking errors, notable differences in speed and acceleration, and the complex system structure that results in unstable cleaning effects. Initially, Permanent Magnet Synchronous Motors (PMSM) are selected as the controlled objects. An improved sliding mode manifold function is introduced to minimize the rate of change in motor speed tracking errors. Utilizing this, a data-driven model-free control technique is employed to design a model-free adaptive sliding mode controller for the motors. Additionally, the deviation coupling structure is enhanced to mitigate the negative effects caused by notable differences in speed and acceleration, along with the complex system structure on the synchronization performance. Finally, a simulation analysis is performed employing three motors to evaluate the effectiveness of the offered control method. The results obtained demonstrate the superior performance of motors controlled by the proposed control method exhibit enhanced response speed, reduced overshoot, improved disturbance rejection capability, and superior speed synchronization performance. © 2024 ieee.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty Involved Two-Stage Energy Optimization Framework Based on Deep Reinforcement learning for Steel Enterprise

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年

作者： Wang, Zhiyuan Han, Zhongyang Zhao, Jun Wang, Wei Dalian Univ Technol Sch Control Sci & Engn Dalian 116023 Peoples R China

The optimization of energy systems within the steel industry faces challenges due to the complexity of nonconvex models as well as supply and demand uncertainty. To address these issues, a novel two-stage data-driven deep reinforcement learning (DRL) framework is proposed in this study. The first stage is focused on offline learning, where probability distribution of energy media is incorporated into Augmented Lagrangian based Alternating Direction Inexact Newton method (ALADIN) for solving nonconvex problems. Some key physics-related constraints, such as gas transmission and steam heat conduction, are comprehensively integrated. Then in order to ensure the independence of various energy media and to reduce the dimensionality of the solution process, the iterative process of updating consensus variables in ALADIN is regarded as a Markov Decision Process (MDP). An optimal decision-making method based on Soft Actor-Critic (SAC) algorithm is established for the energy system. The second stage is targeted at online guidance, where a fuzzy c-means clustering based algorithm is designed for real-time energy optimization. Through the continuous interaction and collaboration between the two-stage framework, the potential disruptions caused by uncertain factors in energy supply and demand on the stable control and operation of steel plants have been effectively hedged. Experiments using data from a steel enterprise in China are conducted, where the proposed framework is compared with both commonly deployed and state-of-the-art methods. The results demonstrate the significant advantages in terms of scheduling efficiency, cost-effectiveness, as well as the adaptability to the uncertainties of the industrial environment, compared with other existing state-of-the-art methods.

关键词： Optimization Mathematical models Uncertainty Steel Biological system modeling Pipelines Media Costs Job shop scheduling Heuristic algorithms Deep reinforcement learning (DRL) energy system steel industry uncertainty

来源：评论

学校读者我要写书评

暂无评论

Identification of the Hammerstein Nonlinear systems Utilizing Correlation Analysis and Maximum Likelihood Methods 13

Identification of the Hammerstein Nonlinear Systems Utilizin...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Dai, Guangqiang Li, Feng Zhu, Yanzong Zhou, Zhou School of Electrical and Information Engineering Jiangsu University of Technology Changzhou213001 China

ISBN: (纸本)9798350361674

In this paper, a parameter identification method for the Hammerstein nonlinear systems is proposed, which is derived by exploiting the correlation analysis and maximum likelihood methods. The Hammerstein system proposed in this study consists of two modules, one of which is approximated by a neural fuzzy model, and a dynamical linear block that is represented by an autoregressive moving average model with additional input. The separation of parameters identification in the Hammerstein system is accomplished by employing a combination of signals encompassing both binary signals and random signals. First of all, based on the correlation function relationship of separable signals in nonlinear systems, the parameters of the dynamic linear block are established through a correlation analysis method, which the issue with colored noise interference is solved. To improve recognition accuracy, a maximum likelihood recursive least squares method was obtained by using the maximum likelihood principle to identify the nonlinear block and colored noise model based on random signals. Simulation results confirm the effectiveness of the proposed approach in accurately identifying Hammerstein nonlinear systems. © 2024 ieee.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

A General Framework for learning-Based Distributionally Robust MPC of Markov Jump systems

引用

ieee TRANSACTIONS ON AUTOMATIC control 2023年第5期68卷 2950-2965页

作者： Schuurmans, Mathijs Patrinos, Panagiotis Katholieke Univ Leuven Dept Elect Engn ESAT STADIUS B-3001 Leuven Belgium

In this article, we present a data-driven learning model predictive control (MPC) scheme for chance-constrained Markov jump systems with unknown switching probabilities. Using samples of the underlying Markov chain, ambiguity sets of transition probabilities are estimated, which include the true conditional probability distributions with high probability. These sets are updated online and used to formulate a time-varying, risk-averse optimal control problem. We prove recursive feasibility of the resulting MPC scheme and show that the original chance constraints remain satisfied at every time step. Furthermore, we show that under sufficient decrease of the confidence levels, the resulting MPC scheme renders the closed-loop system mean-square stable with respect to the true-but-unknown distributions, while remaining less conservative than a fully robust approach. Finally, we show that the data-driven value function of the learning MPC converges from above to its nominal counterpart as the sample size grows to infinity. We illustrate our approach on a numerical example.

关键词： Markov processes Optimization control systems Stability analysis Optimal control learning systems Safety Predictive control robustness statistical learning

来源：评论

学校读者我要写书评

暂无评论

Software Modeling Assistance with Large Language Models 24

Software Modeling Assistance with Large Language Models

引用

ACM/ieee 27th International conference on Model driven Engineering Languages and systems: Companion Proceedings (MODELS)

作者： Ben Chaaben, Meriem Univ Montreal Montreal PQ Canada

ISBN: (纸本)9798400706226

Software modeling requires a challenging combination of expertise in both domain knowledge and modeling formalisms. Existing methods often fail to provide effective, general modeling assistance. This research introduces a novel approach using large language models (LLMs) to enhance software modeling. Utilizing few-shot prompt learning, our method supports various modeling activities without extensive training data. Initially focusing on static and behavioral formalisms like UML diagrams, we aim to extend this to other paradigms and integrate it into the Model-driven Engineering (MDE) pipeline. Additionally, we aim to assess productivity, model quality, and accuracy when receiving real-time, context-aware suggestions during modeling tasks.

关键词： Modeling formalisms generative AI large language models modeldriven engineering prompt learning user study

来源：评论

学校读者我要写书评

暂无评论

Subsynchronous Oscillation Suppression Strategy for Grid-Connected Photovoltaic systems Based on data-driven Predictive control

Subsynchronous Oscillation Suppression Strategy for Grid-Con...

引用

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

作者： Wang, Zihan Cao, Junqi Wang, Yenning Zhang, Xiaonan Li, Gengyin Xn, Yardmi Zhang, Le Xia, Shiwei North China Elect Power Univ Slate Key Lab Alternate Elect Power Syst Renewa Beijing Peoples R China

ISBN: (纸本)9798350318562;9798350318555

With the increasing installed capacity of photovoltaic (PV) in China, there is a risk of subsynchronous oscillations (SSOs) in grid-connected PV systems. As for the grid-connected PV systems, the high complexity of the dynamic behavior and the difficulty of obtaining mathematical models have brought new challenges to the stability control of power systems. To enhance the stability of the modern power systems, this paper proposes a data-driven SSO suppression strategy for grid-connected PV systems. This strategy leverages data-driven predictive control to mitigate SSOs by constructing suitable objective functions and constraints. Furthermore, it employs the rolling optimization and feedback correction in the predictive control to determine the optimal input sequences for grid-connected PV systems, ensuring that the system's state converges to the desired steady state. The data-driven strategy proposed in this paper can be used as a bridge between the measurement data and the dynamic characteristics of the complex power system, which greatly enhances the stability and robustness of the SSO suppression. Finally, the effectiveness and robustness of the suppression strategy are verified in various conditions through MATLAB/Simulink simulation.

关键词： Subsynchronous oscillation suppression data-driven predictive control grid-connected photovoltaic system

来源：评论

学校读者我要写书评

暂无评论

Online Residual learning using Interpretable Reservoir Computing for Quadrotor control

Online Residual Learning using Interpretable Reservoir Compu...

引用

International conference on Unmanned Aircraft systems (ICUAS)

作者： Gu, Weibin Rizzo, Alessandro Politecn Torino Dept Elect & Telecommun Turin Italy

ISBN: (纸本)9798350357899;9798350357882

Quadrotors, valued for their mobility and cost-effectiveness, have found widespread use in applications such as aerial photography and infrastructure inspection. However, their complex and nonlinear dynamics make them sensitive to uncertainties. In dynamic scenarios with online data but little-to-no prior knowledge of these unknowns, data-driven approaches show promise in both system identification and controller design. Nonetheless, the black-box nature of deep learning poses challenges for trust and generalizability. In this paper, we introduce a novel tracking controller featuring an online learning module for quadrotor residual dynamics. This module, implemented using deep Echo State Network (ESN), enhances adaptability to unforeseen scenarios, thereby extending the applicability of the controller to a broader range of situations. Furthermore, we employ post-hoc interpretation techniques tailored for the ESN to improve trustworthiness. This is achieved through dynamic system analysis and visualization of network predictions. Simulation results demonstrate the effective tracking of a figure-8 trajectory with online learning compensating for various non-parametric uncertainties, which showcases the potential of the proposed approach and establishes a foundation for the real-world testing in future.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Coatings Intelligence: data-driven Automation for Chemistry 4.0 7

Coatings Intelligence: Data-driven Automation for Chemistry ...

引用

ieee 7th International conference on Industrial Cyber-Physical systems (ICPS)

作者： Hoseini, Sayed Zhang, Gaoyuan Polke, Dominik Surjana, Alvin Wagner, Lasse Schmitz, Christian Quix, Christoph HSNR Inst Coatings & Surface Chem Krefeld Germany HSNR Dept Elect Engn & Comp Sci Krefeld Germany Fraunhofer Inst Appl Informat Technol FIT St Augustin Germany

ISBN: (纸本)9798350363029;9798350363012

Organic coatings and paints play a vital role in safeguarding surfaces, but improving their properties typically requires a large number of carefully planned experiments. High-throughput screening (HTS), employing industrial robots, allows automated preparation and testing, thus speeding up research and development on materials. Challenges remain in hardware interfaces, data management, and plant control system adaptation. Machine learning (ML) is increasingly applied to various applications in chemistry for experiment suggestions and analysis;thereby paving the way for a higher degree of automation in HTS. This work presents an integrated system composed of an automation platform to perform HTS, a characterization module to evaluate the material, and a DL model to accelerate the development of new coatings by evaluating their scratch resistance using sensor data independent of images. The model is trained on data managed by a data lake. This integration showcases the interplay between chemistry, automation, and data science as a basis for smart manufacturing.

关键词： High-Throughput Screening Chemistry 4.0 Plant control System

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability of Network Intrusion Detection in a Federated learning Setup 1

Improving Transferability of Network Intrusion Detection in ...

引用

1st ieee International conference on Machine learning for Communication and Networking (ieee ICMLCN)

作者： Ghosh, Shreya Jameel, Abu Shafin Mohammad Mahdee El Gamal, Aly Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

ISBN: (纸本)9798350343205;9798350343199

Network Intrusion Detection systems (IDS) aim to detect the presence of an intruder by analyzing network packets arriving at an internet connected device. data-driven deep learning systems, popular due to their superior performance compared to traditional IDS, depend on availability of high quality training data for diverse intrusion classes. A way to overcome this limitation is through transferable learning, where training for one intrusion class can lead to detection of unseen intrusion classes after deployment. In this paper, we provide a detailed study on the transferability of intrusion detection. We investigate practical federated learning configurations to enhance the transferability of intrusion detection. We propose two techniques to significantly improve the transferability of a federated intrusion detection system. The code for this work can be found at https://***/ghosh64/transferability.

关键词： Network intrusion detection Transferability Federated learning

来源：评论

学校读者我要写书评

暂无评论

data-driven Rate control for RDMA Networks: A Lightweight Online learning Approach 43

Data-Driven Rate Control for RDMA Networks: A Lightweight On...

引用

43rd ieee International conference on Distributed Computing systems (ICDCS)

作者： Ye, Jiancheng Lin, Dong Cai, Kechao Zhou, Chao He, Jianfei Lui, John C. S. Huawei Technol Co Ltd Network Technol Lab Shenzhen Peoples R China Huawei Technol Co Ltd Hong Kong Res Ctr Hong Kong Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Guangzhou Peoples R China Huawei Technol Co Ltd Comp Prod Line Shenyang Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China

ISBN: (纸本)9798350339864

Link speed in datacenter networks (DCNs) keeps growing rapidly, inducing an increasingly large portion of network flows to become short flows which can be finished within one round-trip time (RTT). This phenomenon makes many existing congestion control schemes ineffective because they iteratively adjust the sending rate based on the latest congestion feedback in multiple rounds. We find that the representative DCQCN scheme for RDMA exhibits substantial performance degradation when there are many short flows, and this is specially true in High Performance Computing (HPC) scenarios where most of Message Passing Interface (MPI) messages are small. In this paper, we propose a data-driven rate control framework which can learn from long-term online data about past rate control decisions via a lightweight online learning technique named Multi-Armed Bandit (MAB) which has a provable performance guarantee. Utilizing the framework, we devise a rate control scheme named Dolce-RC, which dynamically controls the rate increase and reduction by learning from online data. We implement Dolce-RC in commodity smart NICs, and show via testbed experiments and large-scale simulations that compared to DCQCN, Dolce-RC reduces average completion time of MPI messages by up to 68%, while not requiring any modification to switches.

关键词： Message passing

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：