Work

A Proximal Policy Optimization-Based Proportional-Integral Tuning Scheme for Pitch Control of Floating Offshore Wind Turbines

Year: 2026

Type: article

Abstract: Blade pitch control is critical for stabilizing floating offshore wind turbines (FOWTs) in above-rated regions. However, conventional proportional-integral (PI) controllers rely on gains tuned from simplified linear models. For highly nonlinear FOWTs, such gains may become suboptimal, limiting control performance and multi-objective capability. To overcome these limitations, this article proposes a deep reinforcement learning-based PI tuning framework for blade pitch control under above-rated operating conditions, implemented using the proximal policy optimization (PPO) algorithm. Characterized by its model-free nature, the PPO agent is trained directly via real-time interaction with a high-fidelity FOWT nonlinear model under stochastic turbulent wind and irregular wave loads. Comparative simulations against baseline gain-scheduled PI, individual pitch control, and the reference open-source controller were conducted. The results demonstrate superior performance of the proposed strategy. The generator speed root mean square error is reduced by 78% on average, indicating significantly improved power regulation. Meanwhile, aerodynamic thrust fluctuations decrease by 5.3% while maintaining the mean thrust level, suggesting that load mitigation is achieved without sacrificing power capture. In addition, the platform pitch standard deviation is reduced by 27% with notable low-frequency attenuation, enhancing overall structural stability under above-rated conditions. However, the proposed method exhibits performance degradation as wind speeds approach near-rated conditions. This study explores a data-driven approach for FOWT control, with potential implications for improving system resilience and efficiency in complex marine environments.

Source: Journal of Offshore Mechanics and Arctic Engineering

DOI: 10.1115/1.4072614

Authors: Zhihao Yang, Mingyue Liu, Jianing Guo

Institutions: Shanghai Jiao Tong University, State Key Laboratory of Ocean Engineering, Bay Institute

Language: English

Topic: Wind Turbine Control Systems

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: hybrid

Funder: National Natural Science Foundation of China