Intelligent techniques for system identification and controller tuning in pH process

Abstract

-This paper presents an application of Artificial Neural Network (ANN) and Genetic Algorithm (GA) for system identification for controller tuning in a pH process. In this paper, the ANN based approach is applied to estimate the system parameters. Once the variations in parameters are identified frequently, GA optimally tunes the controller. The simulation results show that the proposed intelligent technique is effective in identifying the parameters and has resulted in a minimum value of the Integral Square Error, peak overshoot and minimum settling time as compared to conventional methods. The experimental results show that their performance is superior and it matches favorably with the simulation results.

Diseño, implementación y validación de un controlador PID autosintonizado

“…Usando este conocimiento, se pueden emplear métodos apropiados para diseñar el controlador óptimo (Bobál et al, 2005). Algunos acercamientos comprenden el uso de redes neuronales para la estimación de los parámetros del sistema (Cajueiro & Hemerly, 2003), y a partir de estos realizar el cálculo de los pará-metros del controlador con técnicas como algoritmos genéticos (Valarmathi et al, 2009). Otros esquemas comprenden la estimación en línea de los parámetros de un modelo de la planta, generalmente discreto, utilizando algún método de identificación, como el método de mínimos cuadrados o proyección ortogonal, unido al diseño de un controlador basado en dichos parámetros, los cuales se ajustan en línea (Aguado & Martinez, 2003).…”

Identification of Industrial Furnace Temperature for Sintering Process in Nuclear Fuel Fabrication Using NARX Neural Networks

“…The application of ANNs to modeling and control nonlinear process has been intensively studied in recent years [1]. In addition, all numerous studies have shown that multilayer perceptrons (MLPs) neural network is very good choice for nonlinear system identification [2]. Basically there are four types of basic learning rules: Competitive Learning, Error Correction Learning, Hebbian Learning, and Boltzmann Learning [3].…”

Relationship of lambda and overshoot of step response for a direct synthesis PI controller

“…In industrial processes such as chemical processes, food processes, manufacturing processes and so on, more than 95% of the control tools are PI and PID controls (Åström and Hägglund, 1995;Dufour, 2006;Shamsuzzoha and Skogestad, 2010). They are adequate to be used in blending (Chua et al, 2009), spray drying (Tan et al, 2009), pH control (Valarmathi et al, 2009), biochemical (Rodrigues and Maciel Filho, 1997) and other manufacturing processes.…”