检索结果-内蒙古大学图书馆

data-driven modeling and control of oscillatory instabilities in Kolmogorov-like flow

THEORETICAL AND COMPUTATIONAL FLUID DYNAMICS 2025年第2期39卷 1-15页

作者： Conlin, Nicholas Tithof, Jeffrey Hemati, Maziar S. Univ Minnesota Aerosp Engn & Mech Minneapolis MN 55455 USA Princeton Univ Mech & Aerosp Engn Princeton NJ 08544 USA Univ Minnesota Mech Engn Minneapolis MN 55455 USA

We apply data-driven techniques to construct a nonlinear 3-mode model of a Kolmogorov-like flow transitioning from steady to periodic. data from direct numerical simulation that include features of experimental realizations of Kolmogorov-like flow are used to build the model. Our low-order modeling methodology does not require knowledge of the underlying governing equations. The 3-mode basis for the model is determined solely from data and the sparse identification of nonlinear dynamics framework (SINDy) is used to fit a dynamical system describing modal interactions. We impose constraints within the SINDy framework to ensure the resulting model will possess energy-preserving nonlinear terms that are consistent with the underlying flow physics. We use the low-order model to determine an appropriate equilibrium solution to stabilize, thereby avoiding searching for equilibrium solutions in the full-order system. The model is linearized about the identified equilibrium solution and subsequently used to design feedback controllers that successfully suppress an oscillatory instability when applied in direct numerical simulations-a testament to the model's ability to capture the underlying dynamics that are most relevant for flow control. Our results confirm that low-order models obtained in a purely data-driven framework can be implemented for flow control in experimentally-realizable Kolmogorov-like flow.

关键词： Kolmogorov flow Oscillatory instabilities Flow control data-driven modeling

来源：评论

学校读者我要写书评

暂无评论

data-driven modeling of bifurcation systems by learning the bifurcation parameter generalization

引用

NONLINEAR DYNAMICS 2025年第2期113卷 1163-1174页

作者： Li, Shanwu Yang, Yongchao Michigan Technol Univ Dept Mech Engn Engn Mech Houghton MI 49931 USA

Nonlinear dynamical systems in such applications as design and control often depend on a set of parameters, resulting in parameterized dynamical systems. Establishing mathematical models of such parameterized systems is essential for numerical simulations, where first-principle models are often not affordable although they are desired whenever possible. data-driven modeling is an important alternative with a trade-off among modeling difficulty, model complexity, and computational efficiency. However, data-driven modeling of such parameterized systems is challenging because not only nonlinear dynamics but also their parametric dependence need to be identified from data;especially for bifurcation systems where small changes in the parameters may cause drastic, qualitative changes of dynamical behaviors. Thus, data-driven modeling of bifurcation systems can be intractable. This work presents a novel method for data-driven modeling of bifurcation systems by transforming the intractable modeling problem into two tractable steps: first, learning an intermediate meta-model that is general for a wide range of bifurcation parameter values;subsequently, using this meta-model to perform efficient adaptation to target/new bifurcation values. Particularly, we leverage the meta-learning to guide the intermediate model to learn to generalize over the bifurcation parameter values, yielding a meta-model which allows a fast and data-efficient adaptation (generalization) to any new bifurcation parameter values. We conduct numerical experiments to validate the presented method on three classic bifurcation systems. It is observed that the adaptation (generalization) to new parameter values enabled by the obtained meta-model is faster than the direct modeling for the new parameter values from scratch. Furthermore, the meta-model-based adaptation yields more accurate models that allow long-term future-state prediction. Finally, we discuss the limitations of this work and potential future

关键词： Parameterized nonlinear systems Bifurcation data-driven modeling Meta-learning Deep neural network

来源：评论

学校读者我要写书评

暂无评论

data-driven modeling for electro-active liquid crystal polymer networks

引用

DISCOVER APPLIED SCIENCES 2025年第1期7卷 1-15页

作者： Amiri, Anahita Shakib, Mohammad Fahim Arteaga, Ines Lopez van de Wouw, Nathan Eindhoven Univ Technol Dept Mech Engn NL-5600 MB Eindhoven Netherlands Imperial Coll London Dept Elect & Elect Engn London England Eindhoven Univ Technol Inst Complex Mol Syst NL-5600 MB Eindhoven Netherlands KTH Royal Inst Technol Dept Engn Mech Marcus Wallenberg Lab Sound & Vibrat MWL S-10044 Stockholm Sweden

In this paper, we propose a data-driven nonlinear modeling approach to describe the dynamics of smart surfaces composed of electroactive liquid crystal networks (LCNs). LCNs are among the top candidates for materials to be employed in smart surfaces such as haptic displays. To realize such applications, the ability to predict an accurate LCN surface response as a function of the input signal is crucial. In this paper, we propose a data-driven modeling approach to identify the parameters of a dynamic model based on experimental data. The resulting model is used for feedforward control to compute the appropriate excitation parameters that ensure a certain desired surface deformation. This feedforward control approach is validated in a simulation study.

关键词： Liquid Crystal Networks (LCNs) Nonlinear system identification data-driven modeling Dynamic models Nonlinear feedforward control Electro-active coatings

来源：评论

学校读者我要写书评

暂无评论

data-driven modeling and integrated optimization of machining quality and energy consumption for internal gear power honing process

引用

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 2025年 93卷

作者： Zhang, You Li, Congbo Tang, Ying Cao, Huajun Tao, Guibao Chongqing Univ State Key Lab Mech Transmiss Adv Equipment Chongqing 400044 Peoples R China Rowan Univ Dept Elect & Comp Engn Glassboro NJ 08028 USA

The internal gear power honing process is increasingly used in the gear machining of electric vehicles due to superior tooth surface quality. Most of the existing work only investigates the quality improvement of gear machining processes, and focuses little attention on energy saving. However, the total rated power of multi-axis motion for gear honing process reaches 60 kW, which has great energy-saving potential. To this end, this article proposes a data-driven modeling and integrated optimization method of machining quality and energy consumption for internal gear power honing process. The machining quality formation mechanism and energy consumption characteristics of gear honing process are first analyzed. A gradient-enhanced Kriging (GEK) method is then used to establish data-driven tooth profile form deviation model and energy consumption model. Furthermore, an integrated honing process optimization model considering tooth profile form deviation and energy consumption is constructed. An improved multi-objective coati optimization algorithm (IMOCOA) is used to solve the optimization problem. The experimental results show that the R-square of the GEK model reaches 0.99, which has superior modeling accuracy compared with other methods. The optimization results demonstrate that compared with the empirical scheme, the proposed integrated optimization model reduces the tooth profile form deviation and energy consumption by 38.46 % and 10.26 %, respectively. Moreover, the developed IMOCOA also presents competitive algorithm performance. The proposed integrated optimization scheme significantly balances honing machining quality and energy consumption.

关键词： Machining quality Energy consumption data-driven modeling Integrated optimization Internal gear power honing

来源：评论

学校读者我要写书评

暂无评论

Observation and transition point detection in transient two-body abrasive wear process using machine vision system and data-driven modeling

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2025年第10期136卷 4511-4523页

作者： Fujisawa, Kei Yokohama Natl Univ Fac Engn Div Syst Res 79-5 TokiwadaiHodogaya Ku Yokohama Kanagawa 2408501 Japan

The evolution of transient two-body abrasive wear was investigated using a machine vision system. In the early stages, abrasives with sharp tips produced abrasive wear patterns characterized by isolated elongated grooves. As the abrasive wear progressed, these grooves disintegrated into shorter grooves owing to the overlap of existing and newly formed abrasive wear patterns. This increased the optical image features that correlated with both roughness and mass loss. The relationship between optical image features and mass loss was analyzed from the perspective of abrasive wear theory, and the transition points in the relationship was detected by Kalman filtering. Furthermore, a data-driven framework was developed to predict spatiotemporal variations in surface conditions and the associated optical image features.

关键词： Digital image processing Machine vision Regression analysis Gray-level intensity Abrasive wear Grinding data-driven modeling Kalman filter Deep learning

来源：评论

学校读者我要写书评

暂无评论

Novel dynamic data-driven modeling based on feature enhancement with derivative memory LSTM for complex industrial process

引用

NEUROCOMPUTING 2025年 626卷

作者： Zhu, Xiuli Xu, Jiajun Fu, Zixuan Damarla, Seshu Kumar Wang, Peng Hao, Kuangrong Univ Shanghai Sci & Technol Dept Opt Elect & Comp Engn Shanghai 200093 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Univ Alberta Dept Chem & Mat Engn Edmonton AB T6G2V4 Canada Shanghai Jiao Tong Univ Dept Automat Shanghai 200241 Peoples R China Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China

Effective feature extraction is important for accurate data-driven soft sensor modeling in large-scale dynamic industrial processes. However, due to the temporal, nonlinear, and high-dimensional nature of the data collected from large-scale industrial processes, traditional data-driven modeling methods often suffer from imperfect feature extraction. To overcome this challenge, this paper proposes a novel feature enhancement framework based on derivative memory long short-term memory (FEDM-LSTM) algorithm for soft sensor modeling. First, inspired by the proportional-integral-derivative control theory, the LSTM is equipped with a derivative gate that dynamically predicts future information. Combined with inherent gates that resemble the proportional and integral parts in traditional LSTM, the derivative memory LSTM (DM-LSTM) captures the dynamic information of the past, the present, and the future. Then, to adapt to multiple phases in complex industrial systems, a feature enhancement framework is designed for DM-LSTM in which features representing important dynamic information from previous phases are fed to the DM-LSTM as additional input in the current phase. Finally, the effectiveness of the proposed method is evaluated through two real industrial datasets, showcasing its ability to achieve high prediction accuracy.

关键词： data-driven modeling Soft sensor Long short-term memory network Feature extraction Industrial process

来源：评论

学校读者我要写书评

暂无评论

On the Solution Uniqueness of data-driven modeling of Flexible Loads

引用

IEEE TRANSACTIONS ON SMART GRID 2025年第2期16卷 1993-1996页

作者： Lu, Shuai Ding, Jiayi Chen, Mingji Gu, Wei Zhu, Junpeng Xu, Yijun Dong, Zhaoyang Sun, Zezheng Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China Hohai Univ Sch Elect & Power Engn Nanjing 211100 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China Univ New South Wales UNSW Business Sch Sydney NSW 2033 Australia

This letter first explores the solution uniqueness of the data-driven modeling of price-responsive flexible loads (PFL). The PFL on the demand side is critical in modern power systems. An accurate PFL model is fundamental for system operations. However, whether the PFL model can be uniquely and correctly identified from operational data remains unclear. To address this, we analyze the structural and practical identifiability of the PFL model, deriving the dataset condition that guarantees the solution uniqueness. Besides, we point out the practical implications of the results. Numerical tests validate this work.

关键词： Load modeling Optimization Numerical models data-driven modeling Upper bound Indexes Electricity Safety Reliability Batteries Flexible loads data-driven modeling identifiability inverse optimization solution uniqueness

来源：评论

学校读者我要写书评

暂无评论

Adaptive Regulated Sparsity Promoting Approach for data-driven modeling and Control of Grid-Connected Solar Photovoltaic Generation

引用

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY 2025年第1期16卷 560-572页

作者： Zhang, Zhongtian Khazaei, Javad Blum, Rick S. Lehigh Univ Dept Elect & Comp Engn Bethlehem PA 18015 USA

This paper introduces a new statistical learning technique based on sparsity promotion for data-driven modeling and control of solar photovoltaic (PV) systems. Compared with conventional sparse regression techniques that might introduce computational complexities when the number of candidate functions increases, an innovative algorithm, named adaptive regulated sparse regression (ARSR) is proposed. The ARSR adaptively regulates the hyperparameter weights of candidate functions to best represent the dynamics of PV systems. This method allows for the application of different sparsity-promoting hyperparameters for each state variable, whereas the conventional approach uses the same hyperparameter for all state variables, which may result in not excluding all the unrelated terms from the dynamics. Consequently, the proposed method can identify more complex dynamics with greater accuracy. Utilizing this algorithm, open-loop and closed-loop models of single-stage and two-stage PV systems are obtained from measurements and are utilized for control design purposes. Moreover, it is demonstrated that the proposed data-driven approach can be successfully employed for fault analysis studies, which distinguishes its capabilities from other data-driven techniques. Finally, the proposed approach is validated through real-time simulations.

关键词： Power system dynamics Adaptation models Nonlinear dynamical systems Voltage control Mathematical models Analytical models Heuristic algorithms data-driven modeling Photovoltaic systems Adaptive systems Adaptive regulated sparse regression (ARSR) closed-loop data-driven modeling photovoltaic (PV) systems single-stage PV two-stage PV

来源：评论

学校读者我要写书评

暂无评论

Compressive strength prediction of ultra lightweight cement using data-driven modeling techniques

引用

MULTISCALE AND MULTIDISCIPLINARY modeling EXPERIMENTS AND DESIGN 2025年第6期8卷 1-18页

作者： Hussain, Athar Addo-Yobo, Andrew Emadi, Hossein Qureshi, Sarah Abdelkerim, Omar Watson, Marshall Texas Tech Univ Lubbock TX 79409 USA Occidental Petr Corp Houston TX USA Conoco Phillips Houston TX USA Bosque Syst Cleburne TX USA

The advancement of predictive modeling techniques using machine learning (ML) has emerged as a pivotal component in optimizing the performance of materials in the oil and gas industry. This paper presents an in-depth analysis of employing four distinct ML algorithms-Artificial Neural Networks (ANN), Gradient Boosting Regressor (GBR), Random Forest (RF), and Support Vector Regression (SVR)-to accurately estimate the Unconfined Compressive Strength (UCS) of lightweight cement formulations. This study tested 516 different cement samples, and the models were trained and validated using a portion of the dataset. The ANN and the GBR ensemble approach produced highly accurate and consistent results when tested on unseen data, supported by Root Mean Squared Error (RMSE) scores of 140 psi and 130 psi and Mean Absolute Percentage Error (MAPE) of approximately 10% and 9%, respectively. All models had computed coefficient of determination (R2) values exceeding 0.9 for all dataset splits, indicating good model fits. By leveraging a dataset comprising various cement samples enhanced with strength-improving additives, the study explores the effectiveness of each algorithm in predicting UCS under different wellbore conditions. Through meticulous hyperparameter tuning and validation processes, the research assesses the performance metrics of each algorithm, thereby providing valuable insights into their applicability for real-time cementing operations in the oil and gas sector. The findings illustrate the potential of these advanced modeling techniques to enhance decision-making processes, reduce costs, and improve the reliability of cementing practices in challenging environments.

关键词： Machine learning Lightweight cement Unconfined compressive strength prediction data-driven modeling Well integrity

来源：评论

学校读者我要写书评

暂无评论

Robust SCN for data-driven modeling Based on Heavy-Tailed Noise Distribution

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Xin Liu, Xiaoqing Dai, Wei China Univ Min & Technol Artificial Intelligence Res Inst Xuzhou 221116 Peoples R China

This article focuses on discussing the extensive application of data-driven models in industry and the challenges it faces, particularly in dealing with interference and outliers in process data. To this end, the basic stochastic configuration network (SCN) is expanded with the heavy-tailed Laplace distribution in order to effectively address the outliers in industrial data, and a novel robust data-driven modeling method (renamed as Lap-RSC) is proposed. First, the prototype of the SCN learner model is constructed with the stochastic configuration algorithm, which means the hidden nodes number, the input weights, and biases of the SCN learner model are all determined in this step. Second, as the output data are contaminated with the outliers, the expectation-maximization (EM) algorithm is combined with the Laplace distribution to estimate the output weights of the SCN learner model robustly. Furthermore, the mathematical decomposition of the Laplace distribution is introduced in this work, which brings three major advantages: 1) it largely improves the computational efficiency of the Lap-RSC;2) it allows a more clearly and evident explanation of the robustness of the Lap-RSC;and 3) it facilitates the mathematical proof of the convergence property of the Lap-RSC. Finally, the verification results demonstrate the effectiveness of the proposed Lap-RSC.

关键词： Training Stochastic processes Robustness Mathematical models Heavily-tailed distribution Predictive models data-driven modeling Probability density function Gaussian distribution data mining expectation-maximization (EM) algorithm Laplace distribution robust parameter estimation stochastic configuration networks (SCNs)

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：