Intelligent Techniques Employing LSTM and ANFIS Models for Fault Detection and Isolation in a Wind Turbine Machine

With the increasing reliance on wind energy as a renewable power source and the expanding deployment of wind farms, a multitude of technical challenges arise, necessitating the implementation of effective maintenance strategies to ensure optimal performance and reliable operation. Through the execution of regular inspections, proactive repairs, and condition-based monitoring, wind farm operators can identify potential issues and address them before they lead to costly breakdowns or significant energy production losses. In this regard, preventive maintenance has emerged as a proactive approach aimed at identifying and rectifying potential issues before they escalate into costly failures or downtime. This paper provides an overview of the application of artificial intelligence (AI) techniques in preventive maintenance for wind turbines. LSTM (Long Short-Term Memory) algorithms are used, relying on historical and real-time data to identify patterns, detect anomalies, and predict potential failures, enabling proactive maintenance actions. Additionally, an ANFIS (Adaptive Neuro-Fuzzy Inference System) approach is employed for fault classification. The results obtained demonstrate the efficiency of the proposed model. (