Development of computational methods for estimation of current efficiency and cell voltage in a Chlor-alkali membrane cell

ABSTRACT

This work presents proposing two artificial intelligence methods including Least squares support vector machine (LSSVM) and Adaptive neuro fuzzy inference system (ANFIS) for the prediction of caustic current efficiency (CCE) and cell voltage as a function of pH, current density, brine concentration, electrolyte velocity, operating temperature, and run time. The predictions of LSSVM and ANFIS models were evaluated by the experimental values of this process graphically and statistically. The overall R-squared values of LSSVM and ANFIS for prediction of CCE were 0.999 and 0.972, respectively. On the other hand, these values for cell voltage prediction were 1 and 0.998. According to the CCE and cell voltage predictions results, LSSVM algorithm has great performance in prediction of chlor-alkali membrane cell processes. Furthermore, artificial intelligence methods can have wide use in electrolytic processes to enhance power consumption.

KEYWORDS:

• ANFIS
• lssvm
• chlor-alkali
• electrolysis
• brine
• membrane cell

Nomenclature

LSSVM	=	Least squares support vector machine
ANFIS	=	Adaptive neuro fuzzy inference system
CCE	=	Caustic current efficiency
CA	=	Chlor-alkali
SVM	=	Support vector machine
ANN	=	Artificial neural network
STD	=	Standard deviations
R2	=	R-squared
MSE	=	Mean squared error
RMSE	=	Root mean square error
ARD	=	Average relative deviation
$\phi$	=	Nonlinear function
$\omega$	=	Weight vector
ei	=	Regression parameter
$\gamma$	=	Tuning parameter
${\alpha }_k$	=	Lagrangian multiplier
${\sigma }^2$	=	Radial basis function width
$\mathrm{\Omega }$	=	Kernel function
K	=	Kernel function
In	=	Identity matrix
O	=	Layer output
Z	=	Gaussian center
qi	=	linear variable
pi	=	linear variable
ri	=	linear variable

Additional information

Notes on contributors

Alexei Valerievich Yumashev

Alexei Valerievich Yumashev, is from Department of Prosthetic Dentistry, Sechenov First Moscow State Medical University, Moscow, Russia. Recently, He has started working on AI algorithm.

Seyed Morteza Fateminasab

Seyed Morteza Fateminasab, is holding a Master’s degree in Chemical Engineering from Tarbiat Modares University, Tehran, Iran. He have collaborated on the Nano-Membrane Liquid Mixture Separation in the Laboratory of Membrane Processes, Department of Chemical Engineering, Tarbiat Modares University.

Azam Marjani

Azam Marjani is from Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam. Marjani is working on machine learning algorithms and their applications in chemical engineering.

Amin B. Lirgeshas

Amin B. Lirgeshas, is holding a Master’s degree in Petroleum Engineering from Petroleum university of technology, Ahwaz, Iran. He have some researches on machine learning algorithm.