Multivariable Neural Network Based Controllers for Smart Structures

Abstract

This paper details identification and robust control of smart structures using artificial neural networks. To demonstrate the use of artificial neural networks in the control of smart structural systems, two smart structure test articles were fabricated. Active materials like piezoelectric (PZT), polyvinylidene (PVDF) and shape memory alloys (SMA) were used as actuators and sensors. The Eigensystem Realization Algorithm (ERA), a structural identification method has been utilized to determine a minimal order discrete time state space model of the test articles. The ERA requires the Markov parameters of the physical system. A neural network based method has been developed to estimate the Markov parameters of a multi input multi output system from experimental test data. The accelerated adaptive learning rate algorithm and the adaptive activation function were utilized to improve the learning characteristics of the network and reduce the learning time. The identified models were used to design a robust controllers for vibration suppression of smart structures using a modified Linear Quadratic Gaussian with Loop Transfer Recovery (LQG/LTR) method. This control design methodology has better loop transfer recovery properties while accommodating the limited control force available from the SMA and the PZT actuators. This controller was copied into a feedforward neural network using the connectionist approach. This neural network controller was implemented using a PC based data acquisition system. The closed loop performance and robustness properties of the conventional and the neural network based controller are compared experimentally.

Fuzzy model reference learning control: a new control paradigm for smart structures

“…Other intelligent controllers such as neural networks can also be used in controlling a cantilever beam system [11,13,14]. The major advantage of using FMRLC over neural networks and neural fuzzy systems deals with training issues.…”

Neural Network Discrimination in Intelligent Vibration Control

“…For instance, g ij indicates the ratio between the electric field developed in ith direction to the stress in Equation (6) applied in jth direction, and the output voltage is represented by the following equation: (12) For the cantilever beam case, Equation (12) can be rewritten as (13) where t s is the distance between the neutral line of the beam and the center of the piezoelectric sensor. Substituting Equation (11) into Equation (13) yields (14) where k = g 31 t s E. The value p s is the location of the sensor, and…”

“…For instance, g ij indicates the ratio between the electric field developed in ith direction to the stress in Equation (6) applied in jth direction, and the output voltage is represented by the following equation: (12) For the cantilever beam case, Equation ( 12) can be rewritten as (13) where t s is the distance between the neutral line of the beam and the center of the piezoelectric sensor. Substituting Equation (11) into Equation ( 13) yields (14) where k = g 31 t s E. The value p s is the location of the sensor, and [recall Equation (4a)]. If there are two sensors on the cantilever beam system, then Equation ( 14) will be used separately for each one yielding the absolute output voltages V s1 (t) and V s2 (t) where the subscripts s 1 and s 2 represent the two different location of the sensors.…”

Neural network based optimizing controllers for smart structural systems

“…The main limitation to real time implementation was the available hardware and computational power. Recently, neural network based robust controllers using PC based data acquisition systems were implemented on smart structure test articles [7][8][9]. The next step towards implementation of neural network based controllers is the utilization of Intel's electronically trainable analog neural network (ETANN) chip i80170NX [10][11][12][13].…”