Odd-harmonic repetitive controller with extreme learning machine approach for precise tracking and robust disturbance rejection in servo systems

View at publisher Summarise with VIRAT
Authors: Edi Kurniawan, Enggar Banifa Pratiwi, Samsul Hafiz, Purwowibowo Purwowibowo, Sensus Wijonarko, Tatik Maftukhah, Jalu A. Prakosa
Cited by: 0
References: 45

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Odd–harmonic repetitive control (OHRC) is a control scheme specifically designed for reference tracking and disturbance rejection of odd–harmonic signals, which are commonly found in servo systems and various power applications. However, OHRC suffers from critical limitations in rejecting multi-periodic disturbances, handling aperiodic signals, and maintaining stability under plant uncertainties. These drawbacks restrict its applicability in real-world systems with complex disturbances and time-varying dynamics. To overcome these challenges, this paper proposes ELM–OHRC, a control framework that integrates OHRC, a PD stabilizer, and an extreme learning machine (ELM) module. In this framework, OHRC is responsible for accurately tracking periodic signals composed of odd–harmonic components and rejecting corresponding disturbances, while the PD controller ensures closed-loop stability of the plant. Meanwhile, the ELM serves as a nonlinear adaptive estimator that complements the model-based OHRC, enabling effective rejection of complex disturbances beyond the scope of odd–harmonic components. Stability of the closed-loop system is ensured through Lyapunov–based analysis. Simulation results show that the proposed ELM–OHRC provides improved tracking accuracy and enhanced steady-state disturbance rejection under aperiodic and unmodeled periodic disturbances, compared with conventional OHRC and switching-based hybrid approaches. The learning-based disturbance estimation enables effective compensation of complex and unmodeled disturbances while preserving robust closed-loop performance.

Fields of Study & Subjects

Iterative Learning Control Systems Adaptive Control of Nonlinear Systems Advanced Control Systems Design

Publication details

Journal / source
Engineering Research Express
Volume
8
Issue
8
Pages
085309–085309
Publication date
1 April 2026
Language
EN