Session: 14-06-01: Applied mechanics and materials in micro- and nanosystems

Paper Number: 166934

Wind Turbine Blade Morphing Using Dielectric Elastomer Membrane 

The efficient and adaptive design of offshore wind turbine blades has led to the exploration of novel blade-morphing technologies. Traditional turbine pitch control mechanisms encounter limitations in dynamic response and load mitigation under fluctuating wind conditions like wind gusts and turbulence. This research investigates the optimization of wind turbine blade morphing using Dielectric Elastomer Membranes (DEMs) through Fluid-Structure Interaction (FSI) modeling and Machine Learning (ML) to enhance aerodynamic efficiency, reduce structural loads, and maximize power generation. The study is conducted using ANSYS Fluent for CFD and FSI simulations, coupled with ML-based control algorithms to optimize real-time blade adaptation.

DEMs, a class of electroactive polymers, exhibit large, reversible deformations under an applied electric field, making them ideal candidates for real-time blade shape adaptation. Unlike conventional mechanical actuators, DEMs offer lightweight, low-energy, and high-strain actuation, allowing wind turbine blades to undergo localized camber, twist, and trailing-edge deformations. This morphing capability enhances aerodynamic efficiency by optimizing lift-to-drag ratios and delaying stall effects, thereby improving overall power output and turbine longevity.

To optimize DEM actuation, Machine Learning (ML) algorithms are incorporated to predict the most efficient blade morphing configurations under varying wind conditions. Various ML techniques, including Reinforcement Learning (RL), Neural Networks (NN), and Genetic Algorithms (GA), are employed to analyze wind speed, turbulence intensity, and load variations. The trained ML models dynamically adjust the voltage inputs to DEM actuators, ensuring optimal shape adaptation for maximum power extraction and minimal structural stress.

The study employs Computational Fluid Dynamics (CFD) and Fluid-Structure Interaction (FSI) simulations using ANSYS Fluent to assess the aerodynamic performance of morphing blades under real-world wind conditions. The structural behavior of DEMs is simulated using hyperelastic material models, while aerodynamic influence is evaluated using CFD simulations in ANSYS Fluent. The FSI coupling between structural deformation and aerodynamic forces enables a comprehensive analysis of the impact of blade morphing on flow separation, pressure distribution, and power coefficient enhancement. Additionally, Python-based ML frameworks are developed to integrate real-time sensor data with DEM actuation. The ML-driven control system is trained on historical wind turbine performance datasets to refine adaptive morphing strategies, ensuring enhanced performance over conventional rigid blade designs.

The outputs of this research include detailed CFD and FSI simulation results demonstrating the aerodynamic benefits of DEM-based morphing, optimized ML-driven control algorithms for real-time shape adaptation, and quantitative improvements in lift-to-drag ratio, power output, and structural load reduction. Additionally, stress-strain analysis of DEM actuators provides insights into their durability and operational efficiency. The study also yields trained ML models capable of predicting optimal morphing configurations, validated through numerical simulations and experimental testing. Finally, a prototype wind turbine blade with integrated DEM actuators is fabricated and tested to assess real-world applicability. These findings will contribute to the development of intelligent, self-optimizing wind turbine blades, offering a scalable and high-performance alternative for offshore and onshore wind energy applications.

 

Presenting Author: Gazi Raihan University of New Orleans

Presenting Author Biography: Gazi Raihan is a graduate student who is doing his Ph.D. in Mechanical Engineering at the University of New Orleans. Currently, he is working under Dr. Uttam Chakravarty, a professor in, the Department of Mechanical Engineering at the University of New Orleans. His current research focuses on offshore wind turbine blade design.

Authors:

Gazi Raihan University of New Orleans
Uttam Chakravarty University of New Orleans