Active vibration control of smart composite plates using self-adaptive neuro-controller

Abstract

A neural network-based control system is developed for self-adapting vibration control of laminated plates with piezoelectric sensors and actuators. The conventional vibration control approaches are limited by the requirement of an explicit and often accurate identification of the system dynamics and subsequent 'offline' design of an optimal controller. The present study utilizes the powerful learning capabilities of neural networks to capture the structural dynamics and to evolve optimal control dynamics. A hybrid control system developed in this paper is comprised of a feed-forward neural network identifier and a dynamic diagonal recurrent neural network controller. Sensing and actuation are achieved using piezoelectric sensors and actuators. The performance of the hybrid control system is tested by numerical simulation of a composite plate with embedded piezoelectric actuators and sensors. Finite-element equations of motion are developed based on shear deformation theory and implemented for the plate element. The dynamic effects of the mass and stiffness of the piezoelectric patches are considered in the model. Numerical results are presented for a flat plate. A robustness study including the effects of structural parameter variation and partial loss of the sensor and actuator is performed. The hybrid control system is shown to perform effectively in all of these cases.

A vision-based vibration sensing and active control for a piezoelectric flexible cantilever plate

“…In general, any number of modes can be learned depending upon the dynamic vibration characteristics of the system. However, for most practical structures, only a few modes provide significant vibration characteristics since it is generally more difficult to excite higher modes (Valoor et al, 2000). Therefore, the high-frequency modes can be neglected on physical grounds and truncated in the experimental system.…”

“…The control algorithms applied to active control of flexible plates include: proportional plus derivative (PD) control, positive position feedback (PPF) control, positive velocity feedback and H 1 control (Shimon et al, 2005), adaptive FIR controller based on the LMS algorithm (St-Amant and Cheng, 2000), H 1 control with m-analysis (Iorga et al, 2009), parallel neurofuzzy control with genetic algorithm tuning (Lin and Zheng, 2012), time-delay controller (Chen et al, 2009), self-adaptive neuro-controller (Valoor et al, 2000), etc. Among the implemented controllers, complex controllers are difficult to test and time-consuming due to mass computation.…”

A review of active vibration and noise suppression of plate-like structures with piezoelectric transducers

“…The authors stated the advantages of hybrid controller based on neural network as non-necessity of the explicit and accurate modeling, and robustness to parameter variations. For more details, readers are referred to Valoor et al (2000b).…”

“…adaptation and learning) (Antsaklis, 1997;Fu, 1971;Gang, 2006;Linkens and Nyongesa, 1996). Within the scope of this review article, the self-adapting control system developed by Valoor et al (2000aValoor et al ( , 2000b) is chosen as an example of an intelligent control algorithm developed for active vibration suppression. Using the FE model of a simply supported plate with multiple piezoelectric sensors and actuators, Valoor and his colleagues designed and investigated a selfadapting hybrid controller which learns the dynamics of the system and provides the required control actuation.…”

Active Stiffening and Active Damping Effects on Closed Loop Vibration Control of Composite Beams and Plates

“…In recent years, the active control technology with smart materials as actuators and sensors has been applied to vibration control of distributed parameter system successfully. Valoor et al [4] developed a hybrid control system with a feed-forward neural network identifier and a dynamic diagonal recurrent neural network controller. The control procedure was numerically implemented to suppress the vibration of laminated plates with piezoelectric materials.…”