Least Square Support Vector Machines Laguerre Hammerstein Model Identification and Non-linear Model Predictive Controller Design for pH Neutralization Process

Akshaykumar Naregalkar; Subbulekshmi D

Makale detayları

Least Square Support Vector Machines Laguerre Hammerstein Model Identification and Non-linear Model Predictive Controller Design for pH Neutralization Process

Yazarlar:

Akshaykumar Naregalkar | Subbulekshmi D

Yayıncı:

Gazi University

Ana Başlıklar:

Engineering

Dergi:

Gazi University Journal of Science Vol.36 Issue 1, pp.80-94

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001281255

pISSN:

2147-1762

Anahtar kelimeler:

Özet:

 The ability to describe the nonlinear process dynamics is an essential feature of the Hammerstein model that paved more research and application studies in system identification and control. Using the Hammerstein model, this study shows an alternative approach to identify and control the highly nonlinear pH neutralization process. This Hammerstein model called Laguerre Least Square Support Vector Machines LLSSVM models the static nonlinearity with LSSVM and the linear part with Laguerre filter. The identified LLSSVM Hammerstein model performance evaluation with Mean Squared Error MSE and Variance Accounted For VAF is better than the Linear Laguerre model. We apply the identified LLSSVM Hammerstein model to implement a Nonlinear Model Predictive Controller NMPC to control the pH neutralization process. Then evaluated NMPC performance in terms of Integral Squared Error ISE, Integral Absolute Error IAE, and Total Variation TV and Control Effort CE parameters to verify its effectiveness in set-point tracking and disturbance rejection problems. The comparison of the NMPC with the Linear Laguerre Model-based Predictive Controller LMPC shows better performance of the NMPC than the LMPC. Results show that the LLSSVM Hammerstein model replicates the pH neutralization process well than the Linear Laguerre model. Also, the identified LLSSVM Hammerstein model provides an efficient NMPC than the LMPC for the pH neutralization process.

 The ability to describe the nonlinear process dynamics is an essential feature of the Hammerstein model that paved more research and application studies in system identification and control. Using the Hammerstein model, this study shows an alternative approach to identify and control the highly nonlinear pH neutralization process. This Hammerstein model called Laguerre Least Square Support Vector Machines LLSSVM models the static nonlinearity with LSSVM and the linear part with Laguerre filter. The identified LLSSVM Hammerstein model performance evaluation with Mean Squared Error MSE and Variance Accounted For VAF is better than the Linear Laguerre model. We apply the identified LLSSVM Hammerstein model to implement a Nonlinear Model Predictive Controller NMPC to control the pH neutralization process. Then evaluated NMPC performance in terms of Integral Squared Error ISE, Integral Absolute Error IAE, and Total Variation TV and Control Effort CE parameters to verify its effectiveness in set-point tracking and disturbance rejection problems. The comparison of the NMPC with the Linear Laguerre Model-based Predictive Controller LMPC shows better performance of the NMPC than the LMPC. Results show that the LLSSVM Hammerstein model replicates the pH neutralization process well than the Linear Laguerre model. Also, the identified LLSSVM Hammerstein model provides an efficient NMPC than the LMPC for the pH neutralization process.

 The ability to describe the nonlinear process dynamics is an essential feature of the Hammerstein model that paved more research and application studies in system identification and control. Using the Hammerstein model, this study shows an alternative approach to identify and control the highly nonlinear pH neutralization process. This Hammerstein model called Laguerre Least Square Support Vector Machines LLSSVM models the static nonlinearity with LSSVM and the linear part with Laguerre filter. The identified LLSSVM Hammerstein model performance evaluation with Mean Squared Error MSE and Variance Accounted For VAF is better than the Linear Laguerre model. We apply the identified LLSSVM Hammerstein model to implement a Nonlinear Model Predictive Controller NMPC to control the pH neutralization process. Then evaluated NMPC performance in terms of Integral Squared Error ISE, Integral Absolute Error IAE, and Total Variation TV and Control Effort CE parameters to verify its effectiveness in set-point tracking and disturbance rejection problems. The comparison of the NMPC with the Linear Laguerre Model-based Predictive Controller LMPC shows better performance of the NMPC than the LMPC. Results show that the LLSSVM Hammerstein model replicates the pH neutralization process well than the Linear Laguerre model. Also, the identified LLSSVM Hammerstein model provides an efficient NMPC than the LMPC for the pH neutralization process.

 The ability to describe the nonlinear process dynamics is an essential feature of the Hammerstein model that paved more research and application studies in system identification and control. Using the Hammerstein model, this study shows an alternative approach to identify and control the highly nonlinear pH neutralization process. This Hammerstein model called Laguerre Least Square Support Vector Machines LLSSVM models the static nonlinearity with LSSVM and the linear part with Laguerre filter. The identified LLSSVM Hammerstein model performance evaluation with Mean Squared Error MSE and Variance Accounted For VAF is better than the Linear Laguerre model. We apply the identified LLSSVM Hammerstein model to implement a Nonlinear Model Predictive Controller NMPC to control the pH neutralization process. Then evaluated NMPC performance in terms of Integral Squared Error ISE, Integral Absolute Error IAE, and Total Variation TV and Control Effort CE parameters to verify its effectiveness in set-point tracking and disturbance rejection problems. The comparison of the NMPC with the Linear Laguerre Model-based Predictive Controller LMPC shows better performance of the NMPC than the LMPC. Results show that the LLSSVM Hammerstein model replicates the pH neutralization process well than the Linear Laguerre model. Also, the identified LLSSVM Hammerstein model provides an efficient NMPC than the LMPC for the pH neutralization process.

Makale detayları

Least Square Support Vector Machines Laguerre Hammerstein Model Identification and Non-linear Model Predictive Controller Design for pH Neutralization Process

Yazarlar:

Akshaykumar Naregalkar | Subbulekshmi D

Yayıncı:

Gazi University

Ana Başlıklar:

Engineering

Dergi:

Gazi University Journal of Science Vol.36 Issue 1, pp.80-94

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001281255

pISSN:

2147-1762

Hammerstein model

Non-linear System

Identification & Control

Laguerre filter

LSSVM

pH neutralization

Sayı

Makale detayları

Least Square Support Vector Machines Laguerre Hammerstein Model Identification and Non-linear Model Predictive Controller Design for pH Neutralization Process

Yazarlar: Akshaykumar Naregalkar | Subbulekshmi D

Yayıncı: Gazi University

Ana Başlıklar: Engineering

Dergi: Gazi University Journal of Science Vol.36 Issue 1, pp.80-94

Belge Tipi: Makale

Yayın Tarihi: 1/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001281255

pISSN: 2147-1762

Hammerstein model

Non-linear System

Identification & Control

Laguerre filter

LSSVM

pH neutralization

Sayı

Yazarlar:

Akshaykumar Naregalkar | Subbulekshmi D

Yayıncı:

Gazi University

Ana Başlıklar:

Engineering

Dergi:

Gazi University Journal of Science Vol.36 Issue 1, pp.80-94

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001281255

pISSN:

2147-1762