Hysteresis Identification of Piezoelectric Actuator Using Neural Network Trained By Jaya Algorithm

The hysteresis nonlinearity widely existing in smart materials yields undesirable responses, which cause the hysteresis control problem even more challenging. Therefore, many studies based on the neural network have been introduced to cope with the hysteresis nonlinearity. However, the popular back-propagation algorithm used in training neural network model often performs local optima with stagnation and slow convergence speed. To overcome these drawbacks, this paper proposes a new training algorithm based on Jaya technique to optimally identify the neural network weighting values. This approach is applied to estimate the nonlinear hysteresis loop of the piezo-based device. The identification results demonstrate that the proposed algorithm successfully identities the highly nonlinear hysteresis with perfect precision.