Open AccessPID TUNING OF FOPDT SYSTEM USING MULTIVARIATE LINEAR REGRESSION WITH GRADIENT DESCENT
Author(s) -
Thaker Maharsh Kalpeshbhai,
Patel Vinod Purushottamdas
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v05i09.030
Subject(s) - pid controller , control theory (sociology) , gradient descent , computer science , controller (irrigation) , multivariate statistics , control engineering , engineering , artificial intelligence , temperature control , control (management) , machine learning , artificial neural network , agronomy , biology
PID controllers are popular in industries forcontrolling process of a system or a plant. There aremany different tuning techniques available to tune a PIDcontroller. In this paper machine learning andoptimization approach is used to tune the controller.Multiple Linear Regression algorithm of MachineLearning and Gradient Descent based optimizationalgorithm is used to obtain PID parameters. PID tuningis performed on a PID controller of Blending ControlSystem. This paper presents a method of obtainingFOPDT model from system’s transient specifications,generating data-set of FOPDT model and then applyingMultivariate Linear Regression with Gradient Descent toobtain optimal tuned values of , and parametersof PID controller.