Adaptive Gain and Order Scheduling of Optimal Fractional Order PI{\lambda}D{\mu} Controllers with Radial Basis Function Neural-Network

TL;DR

This paper proposes an adaptive method for tuning fractional order PI{ extlambda}D{ extmu} controllers using Radial Basis Function neural networks, enabling effective online gain and order scheduling for higher order processes.

Contribution

It introduces a novel approach combining RBF neural networks with fractional order controllers for real-time parameter scheduling in complex processes.

Findings

RBFNN effectively schedules controller parameters online.

The method adapts to random set-point and process changes.

Simulation confirms improved control performance.

Abstract

Gain and order scheduling of fractional order (FO) PI{\lambda}D{\mu} controllers are studied in this paper considering four different classes of higher order processes. The mapping between the optimum PID/FOPID controller parameters and the reduced order process models are done using Radial Basis Function (RBF) type Artificial Neural Network (ANN). Simulation studies have been done to show the effectiveness of the RBFNN for online scheduling of such controllers with random change in set-point and process parameters.