检索结果-内蒙古大学图书馆

data-driven model identification near a supercritical Hopf bifurcation using phase-based approaches

PHYSICA D-NONLINEAR PHENOMENA 2025年 476卷

作者： Wilson, Dan Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

A data-driven model identification strategy is developed for dynamical systems near a supercritical Hopf bifurcation with nonautonomous inputs. This strategy draws on phase-amplitude reduction techniques, analytically relating the phase and amplitude response curves to the terms of the controlled Hopf normal form. Fitting can be performed by recording the system output during the relaxation to the stable limit cycle after applying as few as two carefully timed pulse inputs. Unlike standard phase-based model identification strategies, the resulting model is valid in the neighborhood of the Hopf bifurcation, rather than just in a close vicinity of the unperturbed limit cycle. This strategy is illustrated in two examples with relevance to circadian oscillations. In each example, the proposed model identification strategy allows for the formulation, solution, and implementation of a closed loop nonlinear optimal control problem.

关键词： Nonlinear oscillations Coupled oscillators Phase-amplitude reduction data-driven model identification

来源：评论

学校读者我要写书评

暂无评论

data-driven model identification using forcing-induced limit cycles

引用

PHYSICA D-NONLINEAR PHENOMENA 2024年 459卷

作者： Wilson, Dan Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

This paper presents a data-driven model identification strategy that characterizes the behavior of a general dynamical system relative to a set of limit cycles that emerge in response to periodic forcing. Using time series data to infer the phase-amplitude dynamics associated with the underlying forced limit cycles, a low-order model can be obtained that accurately captures the dynamical behavior in response to arbitrary external inputs. The proposed strategy can be readily implemented in situations where full state measurements are unavailable and does not require any prior knowledge of the underlying model equations. This technique is applied to a model of coupled planar oscillators and to a model that considers the spike rate in a population of coupled conductance-based neurons where it outperforms two other commonly used data-driven model identification techniques.

关键词： data-driven model identification Phase model Phase-amplitude reduction model reduction Neuroscience Koopman analysis

来源：评论

学校读者我要写书评

暂无评论

data-driven model identification and Control of the Inertial Systems

引用

Intelligent Control and Automation 2023年第1期14卷 1-18页

作者： Irina Cojuhari Department of Software Engineering and Automatics Technical University of Moldova Chisinau Republic of Moldova

In the synthesis of the control algorithm for complex systems, we are often faced with imprecise or unknown mathematical models of the dynamical systems, or even with problems in finding a mathematical model of the system in the open loop. To tackle these difficulties, an approach of data-driven model identification and control algorithm design based on the maximum stability degree criterion is proposed in this paper. The data-driven model identification procedure supposes the finding of the mathematical model of the system based on the undamped transient response of the closed-loop system. The system is approximated with the inertial model, where the coefficients are calculated based on the values of the critical transfer coefficient, oscillation amplitude and period of the underdamped response of the closed-loop system. The data driven control design supposes that the tuning parameters of the controller are calculated based on the parameters obtained from the previous step of system identification and there are presented the expressions for the calculation of the tuning parameters. The obtained results of data-driven model identification and algorithm for synthesis the controller were verified by computer simulation.

关键词： data-driven model identification Controller Tuning Undamped Transient Response Closed-Loop System identification PID Controller

来源：评论

学校读者我要写书评

暂无评论

data-driven model identification of boiler-turbine coupled process in 1000 MW ultra-supercritical unit by improved bird swarm algorithm

引用

ENERGY 2020年 205卷 118009-118009页

作者： Huang, Congzhi Sheng, Xinxin North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China North China Elect Power Univ Key Lab Power Stn Energy Transfer Convers & Syst Beijing Peoples R China

Ultra-supercritical units with high steam temperature and pressure have been widely employed in thermal power plants due to their high efficiency and environmental friendliness. To ensure efficient unit operation, it is necessary to develop a model for the boiler-turbine coupled process of the unit. The present models may be complicated or non-transparent, preventing their practical application. In this work, the model structure is a transfer function matrix by dynamic analysis, and the model parameters are obtained by the proposed data-driven multivariable model parameters intelligent identification scheme with the cloud adaptive chaotic bird swarm algorithm combining sheep optimization and lion swarm optimization. By employing operational data from 1000 MW ultra-supercritical unit, extensive experimental results were given to show that the model identified was reasonable and accurate by comparison tests between identification outputs and process outputs around 800 MW operation condition. The developed model can provide reference for further control strategy synthesis and performance optimization. (C) 2020 Published by Elsevier Ltd.

关键词： Ultra-supercritical unit Boiler-turbine coupled process data-driven model identification Cloud adaptive chaotic bird swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

data-driven flutter suppression of noised airfoil models: model identification and robust sliding mode control designed with multi-level control surfaces

引用

NONLINEAR DYNAMICS 2025年第5期113卷 4235-4252页

作者： Mao, Yicheng Liu, Xianbin Nanjing Univ Aeronaut & Astronaut Nanjing Jiangsu Peoples R China

The robust control of complex systems poses a persistent challenge in modern control theory. While several model-free robust control strategies have been developed, they often falter in the face of large perturbations. To address this issue, this paper introduces an integrated approach that combines data-driven model identification with robust control law design paradigm. The resulting control law demonstrates robustness against both large noise perturbations and model identification errors. Furthermore, it offers advantages such as strong interference resistance, smaller control energy requirement, and enhanced stability of controlled states when compared to traditional PID control strategies. Notably, our method yields valuable insights for tackling complex control issues in general multi-degree-of-freedom Lagrangian mechanical systems, particularly those characterized by uncertain governing equations and large discontinuous perturbations.

关键词： Flutter suppression of airfoil systems data-driven model identification Nonlinear robust control L & eacute vy noise

来源：评论

学校读者我要写书评

暂无评论

Noise aware parameter estimation in bioprocesses: Using neural network surrogate models with nonuniform data sampling

引用

AICHE JOURNAL 2025年第2期71卷

作者： Weir, Lauren Mathias, Nigel Corbett, Brandon Mhaskar, Prashant McMaster Univ Dept Chem Engn Hamilton ON Canada Sartorius Canada Inc Oakville ON Canada

This article demonstrates a parameter estimation technique for bioprocesses that utilizes measurement noise in experimental data to determine credible intervals on parameter estimates, with this information of potential use in prediction, robust control, and optimization. To determine these estimates, the work implements Bayesian inference using nested sampling, presenting an approach to develop neural network- (NN) based surrogate models. To address challenges associated with nonuniform sampling of experimental measurements, an NN structure is proposed. The resultant surrogate model is utilized within a Nested Sampling Algorithm that samples possible parameter values from the parameter space and uses the NN to calculate model output for use in the likelihood function based on the joint probability distribution of the noise of output variables. This method is illustrated against simulated data, then with experimental data from a Sartorius fed-batch bioprocess. Results demonstrate the feasibility of the proposed technique to enable rapid parameter estimation for bioprocesses.

关键词： Bayesian inference data-driven model identification machine learning nested sampling nonuniform sampling frequency parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Extracting parametric dynamics from time-series data

引用

NONLINEAR DYNAMICS 2023年第16期111卷 15177-15199页

作者： Ma, Huimei Lu, Xiaofan Zhang, Linan Ningbo Univ Sch Math & Stat 818 Fenghua Rd Ningbo 315211 Zhejiang Peoples R China

In this paper, we present a data-driven regression approach to identify parametric governing equations from time-series data. Iterative computations are performed for each time stamp to first determine if the governing equations to be recovered are time dependent. The results are then used as input data to extract the parametric equations. A combination of the constrained l(1) and l(0)+ l(2) optimization problems are used to ensure parsimonious representation of the learned dynamics in the form of parametric differential equations. The method is demonstrated on three canonical dynamics. We show that the proposed method outperforms other sparse-promoting algorithms in identifying parametric differential equations in the low-noise regime in the aspect of accuracy and computation time.

关键词： data-driven model identification Nonlinear dynamics Sparse recovery Parametric models

来源：评论

学校读者我要写书评

暂无评论

Learning the Dynamics of Future Marine Microgrids Using Temporal Convolutional Neural Network

Learning the Dynamics of Future Marine Microgrids Using Temp...

引用

IEEE Conference on Evolving and Adaptive Intelligent Systems (IEEE EAIS)

作者： Ge, Xiaoyu Hosseinipour, Ali Putri, Saskia Moazeni, Faegheh Khazaei, Javad Lehigh Univ Dept Elect & Comp Engn Bethlehem PA 18015 USA Lehigh Univ Dept Civil & Environm Engn Bethlehem PA 18015 USA

ISBN: (纸本)9798350366235;9798350366242

Medium-voltage direct-current (MVDC) shipboard microgrids (SMGs) are the state-of-the-art architecture for onboard power distribution in navy. These systems are considered to be highly dynamic due to high penetration of power electronic converters and volatile load patterns such as pulsed-power load (PPL) and propulsion motors demand variation. Obtaining the dynamic model of an MVDC SMG is a challenging task due to the confidentiality of system components models and uncertainty in the dynamic models through time. In this paper, a dynamic identification framework based on a temporal convolutional neural network (TCN) is developed to learn the system dynamics from measurement data. Different kinds of testing scenarios are implemented, and the testing results show that this approach achieves an exceptional performance and high generalization ability, thus holding substantial promise for development of advanced data-driven control strategies and stability prediction of the system.

关键词： Temporal Convolutional Network Smart Grid and Energy Marine Microgrids data-driven model identification

来源：评论

学校读者我要写书评

暂无评论

Machine learning prediction of mechanical properties in metal additive manufacturing

引用

ADDITIVE MANUFACTURING 2024年 91卷

作者： Akbari, Parand Zamani, Masoud Mostafaei, Amir Carnegie Mellon Univ Dept Mech Engn Pittsburgh PA 15213 USA Univ Pittsburgh Dept Mech Engn & Mat Sci Pittsburgh PA 15261 USA IIT Dept Mech Mat & Aerosp Engn W 32nd St Chicago IL 60616 USA

Predicting mechanical properties in metal additive manufacturing (MAM) is essential for ensuring the performance and reliability of printed parts, as well as their suitability for specific applications. However, conducting experiments to estimate mechanical properties in MAM processes can be laborious and expensive, and they are often limited to specific materials and processes. Machine learning (ML) methods offer a more flexible and cost-effective approach to predicting mechanical properties based on processing parameters and material properties. In this study, we introduce a comprehensive framework for benchmarking ML models for predicting mechanical properties. We compiled an extensive experimental dataset from over 90 MAM articles and data sheets from a diverse range of sources, encompassing 140 different MAM data sheets. This dataset includes information on MAM processing conditions, machines, materials, and resulting mechanical properties such as yield strength, ultimate tensile strength, elastic modulus, elongation, hardness, and surface roughness. Our framework incorporates physics-aware featurization specific to MAM, adjustable ML models, and tailored evaluation metrics to construct a comprehensive learning framework for predicting mechanical properties. Additionally, we explore the Explainable AI method, specifically SHAP analysis, to elucidate and interpret the predicted values of ML models for mechanical properties. Furthermore, data-driven explicit models were developed to estimate mechanical properties based on processing parameters and material properties, offering enhanced interpretability compared to conventional ML models.

关键词： Additive manufacturing Machine learning Mechanical properties Explainable AI data-driven model identification

来源：评论

学校读者我要写书评

暂无评论

Are Neural Networks the Right Tool for Process modeling and Control of Batch and Batch-like Processes?

引用

PROCESSES 2023年第3期11卷 686页

作者： Rashid, Mustafa Mhaskar, Prashant McMaster Univ Dept Chem Engn Hamilton ON L8S 4L8 Canada

The prevalence of batch and batch-like operations, in conjunction with the continued resurgence of artificial intelligence techniques for clustering and classification applications, has increasingly motivated the exploration of the applicability of deep learning for modeling and feedback control of batch and batch-like processes. To this end, the present study seeks to evaluate the viability of artificial intelligence in general, and neural networks in particular, toward process modeling and control via a case study. Nonlinear autoregressive with exogeneous input (NARX) networks are evaluated in comparison with subspace models within the framework of model-based control. A batch polymethyl methacrylate (PMMA) polymerization process is chosen as a simulation test-bed. Subspace-based state-space models and NARX networks identified for the process are first compared for their predictive power. The identified models are then implemented in model predictive control (MPC) to compare the control performance for both modeling approaches. The comparative analysis reveals that the state-space models performed better than NARX networks in predictive power and control performance. Moreover, the NARX networks were found to be less versatile than state-space models in adapting to new process operation. The results of the study indicate that further research is needed before neural networks may become readily applicable for the feedback control of batch processes.

关键词： subspace identification neural networks data-driven model identification

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：