Implementation of Neuroidentifiers Trained by PSO on a PLC Platform for a Multimachine Power System
This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1674
There were 7 downloads as of 28 Jun 2016.
Abstract
Power systems are nonlinear with fast changing dynamics. In order to design a nonlinear adaptive controller for damping power system oscillations, it becomes necessary to identify the dynamics of the system. This paper demonstrates the implementation of a neural network based system identifier, referred to as a neuroidentifier, on a programmable logic controller (PLC) platform. Two separate neuroidentifiers are trained using the particle swarm optimization (PSO) algorithm to identify the dynamics in a two-area four machine power system, one neuroidentifier for Area 1 and the other for Area 2. The power system is simulated in real time on the Real Time Digital Simulator (RTDS). The PLC implementing two neural networks and the PSO training algorithm is interfaced in a real time to the RTDS. Typical results are presented showing that PLC platform is able to implement the neuroidentifiers to sufficiently identify the dynamics of the two-area four machine power system.
