Active Vibration Control of a Smart Structure Using Neural Network

Vibration is a major problem that can cause structures to wear out prematurely and even fail. Smart structures are a promising solution to this problem because they can be equipped with actuators, sensors, and controllers to reduce or eliminate vibration. This work will study a complete analytical model of a cantilever beam equipped with a pair of piezoelectric actuators and a single piezoelectric sensor. First, we will use a couple of collocated piezoelectric actuators and a sensor to measure and control vibration levels based on a PID controller. Next, we are going to design an artificial neural network (ANN) to enhance the ability of the classical PID controller to self-tune its parameters. For training the artificial neural network, we will use one of the evolutionary algorithms to generate a dataset of the system for the training. Finally, we will compare the effect of the PID self-tuned by ANN and the classical PID controller on the system's stability and performance. Thus, this work will thoroughly understand the potential vibration control of the cantilever beam.