Experimental implementation of an artificial neural network-based active vibration control

Yong Xia, Ryerson University

Date of Award

2005

Degree Type

Thesis

Degree Name

Master of Applied Science (MASc)

Department

Mechanical Engineering

First Advisor

Ahmad Ghasempoor

Abstract

Vibration control strategies strive to reduce the effect of harmful vibrations on machinery and people. In general, these strategies are classified as passive or active. While passive vibration control techniques are generally less complex, there is a limit to their effectiveness. Active vibration control strategies, on the other hand, require more complex algorithms but can be very effective. In this current work, a novel active vibration control experimental system, including the hardware setup and software development environment, has been successfully implemented. 

A static artificial neural network-based active vibration control system has been designed and tested based on the experimental system. The artificial neural network is trained to model the plant using a backpropagation algorithm. After training, the network model is used as part of a feedforward controller. the efficiency of this controller is shown through experimental tests.