Title page for ETD etd-041812-134324

Document Type thesis

Author Name Mitchell, Ryan

URN etd-041812-134324

Title A WANFIS Model for Use in System Identification and Structural Control of Civil Engineering Structures

Degree MS

Department Civil & Environmental Engineering

Advisors
Yeesock Kim, Advisor
Tahar El-Korchi, Department Head
Leonard Albano, Committee Member

Keywords
system identification
structural control
neural network
fuzzy logic
wavelet transform
earthquake

Date of Presentation/Defense 2012-04-17

Availability unrestricted

Abstract
With the increased deterioration of infrastructure in this country, it has become important to find ways to maintain the strength and integrity of a structure over its design life. Being able to control the amount a structure displaces or vibrates during a seismic event, as well as being able to model this nonlinear behavior, provides a new challenge for structural engineers. This research proposes a wavelet-based adaptive neuro- fuzzy inference system for use in system identification and structural control of civil engineering structures. This algorithm combines aspects of fuzzy logic theory, neural networks, and wavelet transforms to create a new system that effectively reduces the number of sensors needed in a structure to capture its seismic response and the amount of computation time needed to model its nonlinear behavior. The algorithm has been tested for structural control using a three-story building equipped with a magnetorheological damper for system identification, an eight-story building, and a benchmark highway bridge. Each of these examples has been tested using a variety of earthquakes, including the El-Centro, Kobe, Hachinohe, Northridge, and other seismic events.

Files
RMitchell1.pdf
RMitchell2.pdf

Browse by Author | Browse by Department | Search all available ETDs

Questions? Email etd-questions@wpi.edu
Maintained by webmaster@wpi.edu

Document Type	thesis
Author Name	Mitchell, Ryan
URN	etd-041812-134324
Title	A WANFIS Model for Use in System Identification and Structural Control of Civil Engineering Structures
Degree	MS
Department	Civil & Environmental Engineering
Advisors	Yeesock Kim, Advisor Tahar El-Korchi, Department Head Leonard Albano, Committee Member
Keywords	system identification structural control neural network fuzzy logic wavelet transform earthquake
Date of Presentation/Defense	2012-04-17
Availability	unrestricted
Abstract With the increased deterioration of infrastructure in this country, it has become important to find ways to maintain the strength and integrity of a structure over its design life. Being able to control the amount a structure displaces or vibrates during a seismic event, as well as being able to model this nonlinear behavior, provides a new challenge for structural engineers. This research proposes a wavelet-based adaptive neuro- fuzzy inference system for use in system identification and structural control of civil engineering structures. This algorithm combines aspects of fuzzy logic theory, neural networks, and wavelet transforms to create a new system that effectively reduces the number of sensors needed in a structure to capture its seismic response and the amount of computation time needed to model its nonlinear behavior. The algorithm has been tested for structural control using a three-story building equipped with a magnetorheological damper for system identification, an eight-story building, and a benchmark highway bridge. Each of these examples has been tested using a variety of earthquakes, including the El-Centro, Kobe, Hachinohe, Northridge, and other seismic events.
Files	RMitchell1.pdf RMitchell2.pdf