Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models

By O. Nelles. 2000

1,581 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d81b3d13ec1e30ebc2238c2e03fa06367b72c053

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Data-driven discovery of Koopman eigenfunctions for control (2017, background): “This lack of simple equations motivates data-driven control methodologies, which include system identification for model discovery [73, 9, 86, 16, 22].”
Review of soft sensor methods for regression applications (2016, background): “possesses a non-linear behavior, then a non-linear model should be the best choice [31].”
Mathematical modelling of wave energy converters: A review of nonlinear approaches (2017, methodology): “Kolmogorov-Gabor polynomial model The Kolmogorov-Gabor Polynomial (KGP) model is a black-box model that uses polynomial nonlinearities to describe the input/output relationship of the data [193].”
Decomposed Vector Rotation-Based Behavioral Modeling for Digital Predistortion of RF Power Amplifiers (2015, background): “A. Zhu is with the School of Electrical, Electronic and Communications Engineering, University College Dublin, Dublin 4, Ireland (e-mail: anding.zhu@ucd.ie). considered as a “black” box, modeling the PA can be simply treated as a general nonlinear system identification issue.”
Identification of pre-sliding and sliding friction dynamics: Grey box and black-box models (2007, methodology): “The first (initial optimisation) phase utilizes a Genetic Algorithm (GA) [18] in order to explore large areas of the parameter space and locate regions where global or local minima may exist.”
SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics (2020, background): “, system identification) is a rapidly developing field [1], with a range of techniques including classic linear approaches [2, 3], dynamic mode decomposition (DMD) [4, 5] and Koopman theory [6–9], nonlinear autoregressive models [10, 11], neural networks [12–20], Gaussian process regression [21, 22]”
Using ant colony optimization to optimize long short-term memory recurrent neural networks (2018, background): “Traditionally in the NARX model the weights for recurrent connects are fixed constants [16], and therefore their corresponding inputs are not considered in the gradient calculations and these weights are not updated in the training epochs.”
Sparse identification of nonlinear dynamics for model predictive control in the low-data limit (2017, methodology): “We refer the reader to an extensive review on nonlinear system identiﬁcation methods [39] and a recent review in the context of machine learning [40].”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “Both optimization-based and learning-based techniques for system identification exist (21).”
Sensitivity analysis and assessment of prior model probabilities in MLBMA with application to unsaturated fractured tuff (2005, background): “If the analyst has a prior perception about how plausible each alternative model (or a group of models) is relative to others, he or she may be able to formulate this perception as a nonlinear constrained optimization problem [Nelles, 2001]:”
Forecasting Stock Exchange Movements Using Neural Networks: A Case Study (2011, methodology): “Gradient Descent method is used for learning of parameters of NN and Toolbox of Matlab software is utilized to study different learning methods and to reach less error and more optimized structure.”