Piecewise affine identification of a hydraulic pumping system using evolutionary computation

Barbosa, Bruno Henrique Groenner; Aguirre, Luís A.; Braga, Antônio de Pádua

doi:10.1049/iet-cta.2018.5621

Cited by 10 publications

(2 citation statements)

References 44 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then, the algorithm is tested in an experimental hydraulic pumping system data presented in Barbosa et al (2011) and Barbosa et al (2019). Figure 3 shows part of the input and output training data.…”

Section: Methodsmentioning

confidence: 99%

Multi-gene Genetic Programming for Structure Selection of Polynomial NARMAX models

Castro

Barbosa

2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

In the area of black-box identication, NARMAX models are of great interest. The main diculty faced when working with such models is the selection of the correct structure to represent the underlying system in the data. Orthogonal Least Squares (OLS) methods are widely used for this task, however, there are systems with a high degree of non-linearity and long term dependencies, which makes the use of traditional OLS methods computationally impracticable. In this sense, this paper studies the use of Multi-Gene Genetic Programing (MGGP) together with the traditional OLS method to increase the search space and turn the structure selection practicable for average performance computer. It is shown that, in real-life problem data, the algorithm can nd better models than previous works' models. The MGGP found a model for a hydraulic pumping system with a better one-step-ahead prediction error (0:058 mlc2 against 0:070 mlc2) using PEM technique and better free-run simulation error (0:997 mlc2 against 1:120 mlc2) using SEM technique. The MGGP found a model with such a degree of non-linearity and maximum input-output lags that totalizes 142505 candidate terms for traditional OLS analysis, which is impracticable for average performance computers.

show abstract

Section: Methodsmentioning

confidence: 99%

Multi-gene Genetic Programming for Structure Selection of Polynomial NARMAX models

Castro

Barbosa

2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

show abstract

“…Nosúltimos anos, tem-se observado um empenho crescente em técnicas de identificação de sistemas com modelos afim chaveados (do inglês -switched affine models) (Du et al, 2018;Zwart, 2019;Hojjatinia et al, 2019;Fey et al, 2020) e modelos afim por partes (do inglês -piecewise affine models) (Barbosa et al, 2018;Schirrer et al, 2018;Lassoued e Abderrahim, 2019;Kersting e Buss, 2019;Du et al, 2020). Isto se deve ao fato de que identificar um modelo global que consiga cobrir diversas situações pode torná-lo muito complexo.…”

Section: Introductionunclassified

Determinação da Estrutura de Modelos PWARX com Base no Erro Dinâmico de Predição

Braga

Oliveira

Martins

2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

O presente trabalho propõe uma metodologia completa com base no problema de identificação de sistemas não lineares utilizando modelos autoregressivos com entrada exógena afim por partes, denominados como modelos PWARX (PieceWise affine AutoRegressive eXogenous). A abordagem proposta tem como base dar uma atenção exclusiva aos regressores que compõem o vetor de regressores dessa classe de modelos. Sendo assim, foi identificado um sistema real composto por um conversor CC-CC buck e os resultados mostraram que uma maior representatividade do sistema está diretamente associada a quais regressores utilizar nessa classe de modelo.

show abstract

An Introduction to Nonlinear System Identification

Aguirre

2023

Understanding Complex Systems

View full text Add to dashboard Cite

Piecewise affine identification of a hydraulic pumping system using evolutionary computation

Cited by 10 publications

References 44 publications

Multi-gene Genetic Programming for Structure Selection of Polynomial NARMAX models

Multi-gene Genetic Programming for Structure Selection of Polynomial NARMAX models

Determinação da Estrutura de Modelos PWARX com Base no Erro Dinâmico de Predição

An Introduction to Nonlinear System Identification

Contact Info

Product

Resources

About