File(s) under permanent embargo
Prediction interval-based neural network controller for nonlinear processes
conference contribution
posted on 2015-09-28, 00:00 authored by Anwar HosenAnwar Hosen, Abbas KhosraviAbbas Khosravi, Saeid Nahavandi, Douglas CreightonDouglas Creighton, Syed Moshfeq SalakenPrediction interval (PI) has been extensively used to predict the forecasts for nonlinear systems as PI-based forecast is superior over point-forecast to quantify the uncertainties and disturbances associated with the real processes. In addition, PIs bear more information than point-forecasts, such as forecast accuracy. The aim of this paper is to integrate the concept of informative PIs in the control applications to improve the tracking performance of the nonlinear controllers. In the present work, a PI-based controller (PIC) is proposed to control the nonlinear processes. Neural network (NN) inverse model is used as a controller in the proposed method. Firstly, a PI-based model is developed to construct PIs for every sample or time instance. The PIs are then fed to the NN inverse model along with other effective process inputs and outputs. The PI-based NN inverse model predicts the plant input to get the desired plant output. The performance of the proposed PIC controller is examined for a nonlinear process. Simulation results indicate that the tracking performance of the PIC is highly acceptable and better than the traditional NN inverse model-based controller.
History
Event
Neural Networks. International Joint Conference (2015 : Killarney, Ireland)Pagination
1 - 6Publisher
IEEELocation
Killarney, IrelandPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2015-07-12End date
2015-07-17ISBN-13
9781479919604Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2015, IEEETitle of proceedings
IJCNN 2015 : Proceedings of the International Joint Conference on Neural NetworksUsage metrics
Categories
No categories selectedKeywords
prediction intervaluncertainties and disturbancesnonlinear controllersPICneural networksScience & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Hardware & ArchitectureEngineering, Electrical & ElectronicComputer ScienceEngineeringGENERATION FORECASTSPOWER-GENERATIONBATCH REACTORPOLYMERIZATIONINVERSE
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC