Real-Time Implementation of a Neural Integrator Backstepping Control via Recurrent Wavelet First Order Neural Network

Abstract

Wavelets are designed to have compact support in both time and frequency, giving them the ability to represent a signal in the two-dimensional time–frequency plane. The Gaussian, the Mexican hat, and the Morlet wavelets are crude wavelets that can be used only in continuous decomposition. The Morlet wavelet is complex-valued and suitable for feature extraction using continuous wavelet transform. Continuous wavelets are favoured when a high temporal resolution is required at all scales. In this paper, considering the properties from the Morlet wavelet and based on the structure of a recurrent high-order neural network model, a novel wavelet neural network structure, here called recurrent wavelet first-order neural network, is proposed in order to achieve a better identification of the behavior of dynamic systems. The effectiveness of our proposal is explored through the design of a centralized neural integrator backstepping control scheme for a two degree-of-freedom robot manipulator evolving in the vertical plane. The performance of the overall neural identification and control scheme is verified through numerical simulation using the mathematical model for a benchmark prototype. Moreover, real-time results validate the effectiveness of our proposal when using a robotic arm, of our own design, powered by industrial servomotors.