Modeling and identification of heat exchanger process using least squares support vector machines

Abstract

In this paper, Hammerstein model and non-linear autoregressive with eXogeneous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system without requiring any a priori assumptions regarding its structure. The results indicate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.

Parameter learning for the nonlinear system described by Hammerstein model with output disturbance

“…In the field of nonlinear systems, the Hammerstein model is the most common block-oriented model. This model can well characterize the process properties and represent a large class of nonlinear processes, for instance, neutralization process [1], heat exchanger [2], power system [3], distillation towers [4,5], drying processes [6], and continuous stirred tank reactors [7,8].…”

Comparison of optimal homotopy analysis method and fractional homotopy analysis transform method for the dynamical analysis of fractional order optical solitons

“…In the recent decades, fractional calculus has proved to be a useful branch of mathematics to understand the complex physical problems. Fractional analysis has been considered to study the electric and magnetic fields, 7 theory of hydrologic modeling, 8 fluid dynamics, study of visco-elasticity, 9 modeling of heat exchanger, 10 mechanical engineering problems, 11 solitons theory, 12 and many other engineering problems including mass transportation.…”

Modelos Neuroevolucionários Com Echo State Networks Aplicados À Identificação De Sistemas

“…Figura 29 -Estrutura de um trocador de calor. Fonte: Adaptado de Bittanti & Piroddi (1997) Tal processo é caracterizado por possuir comportamento não linear, de fase nãomínima e variante no tempo (Bittanti & Piroddi, 1997;Al-Dhaifallah et al, 2015;Soleimani et al, 2010). A base de dados utilizada neste trabalho pode ser acessada online (De Moor, 2018) e contém 4000 amostras (simuladas) da vazão do líquido na entrada do trocador ( -entrada) e a temperatura do líquido na saída do trocador ( -saída) que foram obtidas com um período de amostragem de 1,0 s e mantendo-se a temperatura do líquido e a do vapor aplicados na entrada do trocador constantes (Bittanti & Piroddi, 1997) (figura 30).…”