Work

Neural network-based super-twisting control for floating wind turbines: Design and real-time validation

Year: 2025

Type: article

Abstract: Floating Offshore Wind Turbines (FOWTs) pose significant control challenges due to their nonlinear dynamics, sensitivity to environmental disturbances, and underactuated nature. This paper presents a control strategy for collective blade pitch regulation in Region III of a 5 MW semi-submersible FOWT. The approach combines a Radial Basis Function Neural Network (RBFNN) with a Super-Twisting Algorithm (STA) to improve robustness against disturbances and enhance dynamic performance. The control design is based on a reformulated nonlinear control-oriented model to support the synthesis of adaptive control laws. This work also introduces a real-time Hardware-in-the-Loop (HIL) platform, specifically designed for the validation of FOWT control strategies. The platform ensures a strictly synchronized execution framework for accurate real-time emulation and integrates OpenFAST for high-fidelity dynamic simulations. Experimental results confirm the real-time feasibility of the proposed RBFNN-based STA controller and its effectiveness in regulating generator speed and mitigating platform pitch motion under varying wind conditions.

Source: Ocean Engineering

DOI: 10.1016/j.oceaneng.2025.121973

Authors: Flavie Didier, Hedi Basbas, Djelalli Larioumlil, Salah Laghrouche, Daniel Depernet

Institutions: Centre National de la Recherche Scientifique, Franche-Comté Électronique Mécanique Thermique et Optique - Sciences et Technologies, Université de technologie de belfort-montbéliard, Université Marie et Louis Pasteur

Language: English

Topic: Wind Turbine Control Systems

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Affordable and clean energy

Open Access status: hybrid

Estimated APC paid: $4,150