High-Order Sliding Modes Based On-Line Training Algorithm for Recurrent High-Order Neural Networks. Issue 2 (2020)

• Record Type: Journal Article
• Authors: Alanis, Alma Y.; Rios-Huerta, Daniel; Rios, Jorge D.; Arana-Daniel, Nancy; Lopez-Franco, Carlos; Sanchez, Edgar N.
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 2(2020)
• Page Start: 8187
• Page End: 8192
• Publication Date: 2020
• Subjects: Extended Kalman Filter -- High order sliding mode -- Neural identification -- Neural network training -- Robust exact differentiators; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2020.12.2320
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: This work presents a discrete on-line training algorithm for recurrent high-order neural networks (RHONN). The proposed training algorithm is based on the arbitrary order differentiators of high-order sliding modes (HOSM) theory. Due to HOSM-based differentiators can approximate derivatives in finite time, the proposed training algorithm avoids the compute of the derivatives, unlike conventional training algorithms. The proposed HOSM-based algorithm is implemented for the training of a RHONN identifier, and its performance is compared with the results using the extended Kalman filter (EKF) training algorithm. Results of a implementation of the identifier for the Lorenz system and an implementation of the identifier for a tracked robot using experimental data are presented.