Please use this identifier to cite or link to this item:
Title: Turbine system controller based on extreme learning machine
Authors: Tan, Yee Chin.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
Issue Date: 2009
Abstract: This project is mainly aimed at the application of ELM (Extreme Learning Machine) algorithm in neural network to design a turbine system controller. This project has 4 main objectives and is separated into various parts. Firstly, since the author is required to know the existing turbine system controller and set up models of turbine system in this project. So, Chapter 1&2 will include the process of understanding the existing robust controller as well as to set up a model of turbine system. In Chapter 1, there will be an introduction to the basic concept of the robust controller and its various types of main components. Different models of system’s main components will also be shown in this chapter. This is follow by the Chapter 2, which introduces the different equations and methods employed to set up the turbine system controller. Secondly, the second objective of this project is to study and understanding the fundamentals of Extreme Learning Machine. So, in the following chapter this is Chapter 3, which will introduce the fundamentals of neural network and the equation employed to the ELM controller. Thirdly, in the following chapter, author will touch on the design of the ELM controller. Here, MATLAB is used to employ to process, calculate and display the results obtained. Some algorithm and source code will be presented in this chapter. Last but not least, in Chapter 5, author will evaluate the performance of the turbine system by the computer simulation for both of the ELM and robust controller. Some analyst and comment will also be included in this chapter.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.48 MBAdobe PDFView/Open

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.