Please use this identifier to cite or link to this item: http://localhost:8081/xmlui/handle/123456789/11273
Title: ARTIFICIAL NEURAL NETWORK BASED INTELLIGENT CONTROLLER
Authors: Jaiswal, Neetu
Keywords: ELECTRICAL ENGINEERING;ARTIFICIAL NEURAL NETWORK;INTELLIGENT CONTROLLER;NEURO-CONTROL TECHNIQUE
Issue Date: 1998
Abstract: Currently, artificial neural networks are being used to solve problems related to control. To determine reliability of the neuro-control technique is to test it on a variety of realistic problems with the aim of seeing whether it works well and where it needs further refinement. In the presented work, a multilayered back propagation ANN is first trained, to learn the inverse dynamic model of a temperature' control system and then configured as a direct controller to the process. The ability of ANN to learn the inverse model of the process plant is based on input vectors with no a-priori knowledge regarding its dynamics. Three artificial neural networks with different structures are trained for other first order plant characteristics. Finally, a generalised ANN is obtained, which can be used as a direct controller for any of the first order plant characteristics subject to variations of any or all plant parameters with a range of ± 25 %.
URI: http://hdl.handle.net/123456789/11273
Other Identifiers: M.Tech
Research Supervisor/ Guide: Verma, H. K.
Kumar, Vinod
metadata.dc.type: M.Tech Dessertation
Appears in Collections:MASTERS' DISSERTATIONS (Electrical Engg)

Files in This Item:
File Description SizeFormat 
EED248138.pdf2.35 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.