Normal view MARC view ISBD view

Identification of hammerstain model using stochastic perturbation simultaneous approximation [electronic resource] / Nurriyah Mohd Noor

By:

Nurriyah Mohd Noor

Material type:

Computer filePublication details: Kuantan, Pahang : UMP, 2016Description: 1 computer disc : digital data ; 12 cmISBN:

THE0005150(Local)

Subject(s):

Online resources:

Access in library only

Dissertation note: Project Paper (Bachelor of Electrical Engineering (Hons.) (Electronics)) -- Universiti Malaysia Pahang – 2016 Abstract: This project study an identification of continuous Hammerstein based on simultaneous Perturbation Stochastic Approximation (SPSA). Furthermore, the Identification is done using MATLAB Simulink to simulate the Hammerstein Model. The structure of non-linear is assumed to be completely unknown. However, the system order assumed to be known For handling it, piecewise-linear function are used as a tool to approximate the unknown non-linear function. The SPSA algorithms was proposed to identify the problem of Hammerstein model. The main benefit of the SPSA-based method is it can be applied to identification of Hammerstein systems even though less restrictive assumptions. The SPSA based method is then used to estimate the parameters in both the linear and non-linear parts based on the given input and output data with the present of delay in time. Besides that, this project analysed the efficient of the SPSA in identify nonlinear system in term of object function and error with different noise variance. A numerical example is given to illustrate that the SPSA based algorithms can give accurate parameter estimate of the Hammerstein models with high probability through detailed simulation.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes ( 4 )

Holdings
Item type	Current library	Call number	Copy number	Status	Date due	Barcode
Final Year Report	UMPLIB PEKAN	FKEE .N87 2016 r Bc. \| CD 10729 (Browse shelf(Opens below))	1	Not for loan		0000117745

Faculty of Electrical & Electronics Engineering

Project Paper (Bachelor of Electrical Engineering (Hons.) (Electronics)) -- Universiti Malaysia Pahang – 2016

This project study an identification of continuous Hammerstein based on simultaneous Perturbation Stochastic Approximation (SPSA). Furthermore, the Identification is done using MATLAB Simulink to simulate the Hammerstein Model. The structure of non-linear is assumed to be completely unknown. However, the system order assumed to be known For handling it, piecewise-linear function are used as a tool to approximate the unknown non-linear function. The SPSA algorithms was proposed to identify the problem of Hammerstein model. The main benefit of the SPSA-based method is it can be applied to identification of Hammerstein systems even though less restrictive assumptions. The SPSA based method is then used to estimate the parameters in both the linear and non-linear parts based on the given input and output data with the present of delay in time. Besides that, this project analysed the efficient of the SPSA in identify nonlinear system in term of object function and error with different noise variance. A numerical example is given to illustrate that the SPSA based algorithms can give accurate parameter estimate of the Hammerstein models with high probability through detailed simulation.

Item in pdf format