Identification of unknown nonlinear systems based on multilayer neural networks and Lyapunov theory

Vargas, José A. R.; Grzeidak, Emerson; Alfaro, Sadek Crisóstomo Absi

doi:10.1109/ssci.2016.7849877

Cited by 5 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While Lopez et al used convolutional neural networks to deal with nonlinear system modeling and identification, by which the identification process falling into local optimum can be avoided and the system robustness can also be improved [11]. Based on Lyapunov theory, Vargas et al designed a simple three-layer neural network to identify nonlinear systems, where the weight matrix is transformed into a nonlinear parametric matrix and the robust adaptive method is used to optimize the trained results [12]. However, the literature reviewed and references published generally speak that it is still a challenge to accurately model and identify complicated nonlinear systems by conventional methods such as machine learning.…”

Section: Introductionmentioning

confidence: 99%

Complex Nonlinear System Modelling and Parameters Identification by Deep Neural Networks

Lin¹,

Luo²,

Cao³

et al. 2019

dtcse

View full text Add to dashboard Cite

As most systems are inherently nonlinear in nature, many efforts have been made to improve the understanding of complicated nonlinear models. However, current research has indicated that it is still a challenge to accurately model and identify nonlinear systems by conventional methods such as machine learning. This paper investigates a complex nonlinear system with three parameters identification by training a Deep Neural Network (DNN) to model the system based on Fourier series theory. The DNN with 10 layers is constructed such that it can model any nonlinear system, and the parameters identification is performed by the trained neural networks. The proposed method has been evaluated by applying to a nonlinear system for multiple parameters measurement by interferometric fiber sensors. Experimental results demonstrate that the DNN can accurately model the nonlinear system and identify the corresponding parameters, leading to a solution to complex nonlinear system approximation with minimized error.

show abstract

Section: Introductionmentioning

confidence: 99%

Complex Nonlinear System Modelling and Parameters Identification by Deep Neural Networks

Lin¹,

Luo²,

Cao³

et al. 2019

dtcse

View full text Add to dashboard Cite

show abstract

“…Finally, a comparison of the proposed algorithm with that in [2] was performed to show the advantages and peculiarities of the proposed method under disturbances. The results obtained and presented in this chapter have been reported in [137].…”

Section: Discussionmentioning

confidence: 95%

Identification of nonlinear systems based on extreme learning machine

Grzeidak¹

Self Cite

View full text Add to dashboard Cite

O resultado das simulações para o sistema caótico unificado mostram a eficácia e o desempenho da abordagem proposta na presença de distúrbios. Adicionalmente, para mostrar a aplicabilidade do algoritmo de aprendizado proposto para sistemas com várias dimensões, uma simulação com um sistema hipercaótico complexo é exibida. Finalmente, uma comparação do algoritmo proposto com [2] é realizada para mostrar as vantagens e peculiaridades do método proposto na presença de distúrbios. Capítulo 6 resume as contribuições teóricas da pesquisa bem como os resultados obtidos. Sugestões para pesquisa futura também são discutidas. Os apêndices contém a implementação via software dos identificadores neurais propostos nesta dissertação.3 Technical Background .

show abstract