Abstract

In this study, the application of Recurrent Artificial Neural Network (RANN) in nonlinear system identification has been extensively explored. Three RANN-based identification models have been presented to describe the behavior of the nonlinear systems. The approximation accuracy of RANN-based models relies on two key factors: architecture and weights. Due to its inherent property of parallelism and evolutionary mechanism, a Genetic Algorithm (GA) becomes a promising technique to obtain good neural network architecture. A GA is developed to approach the optimal architecture of a RANN with multiple hidden layers in this study. In order to approach the optimal architecture of Neural Networks in the sense of minimizing the identification error, an effective encoding scheme is in demand. A new Direct Matrix Mapping Encoding (DMME) method is proposed to represent the architecture of a neural network. A modified Back-propagation (BP) algorithm, in the sense of not only tuning NN weights but tuning other adjustable parameters as well, is utilized to tune the weights of RANNs and other parameters. The RANN with optimized or approximately optimized architecture and trained weights have been applied to the identification of nonlinear dynamic systems with unknown nonlinearities, which is a challenge in the control community. The effectiveness of these models and identification algorithms are extensively verified in the identification of several complex nonlinear systems such as a "smart" actuator preceded by hysteresis and friction-plague harmonic drive.