Intelligent and Data-Driven Reliability Evaluation Model for Wind Turbine Blades

• Published in: International journal of energy optimization and engineering 2022-01, Vol.11 (1), p.1-20
• Main Authors: Aikhuele, Daniel Osezua, Periola, Ayodele A, Aigbedion, Elijah, Nwosu, Herold U
• Format: Article
• Language: English
• Subjects: Air-turbines; Analysis; Artificial neural networks; Buildings and facilities; Errors; Force and energy; Mean square errors; Mean square values; Neural networks; Reliability analysis; System reliability; Training; Turbine blades; Turbine industry; Turbines; Wind power; Wind turbines
• ISSN: 2160-9500; 2160-9543
• DOI: 10.4018/IJEOE.298694

Wind energy is generated via the use of wind blades, turbines and generators that are deployed over a given area. To achieve a higher energy and system reliability, the wind blade and other units of the system must be designed with suitable materials. In this paper however, a computational intelligent model based on an artificial neutral network has been propose for the evaluation of the reliability of the wind turbine blade designed with the FRP material. The simulation results show that there was a reduction in the training mean square error, testing (re–training) mean square error and validation mean square error, when the number of training epochs is increased by 50% such that the minimum mean square error and maximum mean square error were 0.0011 and 0.0061, respectively. The low validation mean square error in the simulation results implies that the developed artificial neural network has a good accuracy when determining the reliability and the failure probability of the wind turbine blade.