A Supervised Model of Multivariable Control in Quadruple Tank System

• Published in: Applied artificial intelligence Vol. 37; no. 1
• Main Authors: M, Aravindan, A, Chilambuchelvan, S, Tamilselvi
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 31.12.2023; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Liquid levels; Machine learning; Multivariable control; Regression analysis; State space models; Support vector machines; Transfer functions
• ISSN: 0883-9514; 1087-6545
• DOI: 10.1080/08839514.2023.2175107

Aims to develop a precise mathematical model for multi-loop system-based Quadruple Tank Process (QTP) - a challenging task, due to strong interaction between pump inputs and sensor values. Modeling is essential for understanding the behavior of quadruple tank system, analysis and design of controllers. Traditional methods such as transfer function and state space model limitations are removed through the proposed model. Transfer function model can never be applied to multiple input and multiple output QTP system. State space model never addresses the internal state of QTP system. In this paper, Machine Learning-based Quadruple Tank Process model is proposed such as Regression Tree Quadruple Tank Process (RT-QTP) model and Support Vector Machine Quadruple Tank Process (SVM-QTP) model for runtime input and output sensor level data from laboratory based QTP station. Regression technique is performed with pump inputs and output liquid level data and it is verified with R-square values of proposed models. The models provide an accuracy of about 98% for laboratory-based data from a QTP station, according to experiments using MATLAB software.