As wind energy is becoming a significant utility source, minimizing the Operation and Maintenance (O&M) expenses has raised a crucial issue to make wind energy competitive to fossil fuels. Wind Turbines (WTs) are subject to unexpected failures due to operational and environmental conditions, aging, etc. An accurate estimation of time to failures assures reliable power production and lower maintenance costs. In recent years, a notable amount of research has been undertaken to propose prognosis techniques that can be employed to forecast the Remaining Useful Life (RUL) of wind farm assets. This paper provides a recent literature review on modeling developments for the remaining useful life prediction of critical WT components including physics-based, Artificial Intelligence (AI)-based, stochastic-based, and hybrid prognostics. In particular, the pros and cons of the prognosis models are investigated to assist researchers in selecting proper models for certain applications of WT RUL forecast. Our comprehensive review has revealed that hybrid methods are now the leading and most accurate tools for WT failure predictions over individual hybrid components. Strong candidates for future research include the consideration of variable operating environments, component interaction, physicsbased prognostics, and Bayesian application in the development of WT prognosis methods.

This paper introduces a new condition monitoring approach for extracting fault signatures in wind turbine blades by utilizing the data from a real-time Supervisory Control and Data Acquisition (SCADA) system. A hybrid fault detection system based on a combination of Generalized Regression Neural Network Ensemble for Single Imputation (GRNN-ESI) algorithm, Principal Component Analysis (PCA), and wavelet-based Probability Density Function (PDF) approach is proposed in this work. The proposed fault detection strategy accurately detects incipient blade failures and leads to improved maintenance cost and availability of the system. Experimental test results based on data from a wind farm in southwestern Ontario, Canada, illustrate the effectiveness and high accuracy of the proposed monitoring approach.

In North America, many utility-scale turbines are approaching the half-way point of their anticipated initial lifespan. Accurate remaining useful life (RUL) estimation can provide wind farm owners insight into how to optimize the life and value of their farm assets. An improved understanding of the RUL of turbine components is particularly essential as many owners consider retiring, life-extending, or repowering their farms. In this article, an integrated prognosis method based on signal processing and an adaptive Bayesian algorithm is proposed to predict the RUL of various faulty bearings in wind turbines. The signal processing leverages feature extraction, feature selection, and signal denoising to detect the dynamics of various failures. Then, RUL of the faulty bearings is forecast via the adaptive Bayesian algorithm using the extracted features. Finally, a new fusion method based on an ordered weighted averaging (OWA) operator is applied to the RUL obtained from the features to improve accuracy. The efficacy of the method is evaluated using data from historical failures across three different Canadian wind farms. Experimental test results indicate that the OWA operator delivers a higher accuracy for RUL prediction compared to the other feature-based methods and Choquet integral fusion technique.

The failure progression of Wind Turbine (WT) bearings comprises of multiple degraded health states due to applied load by Varying Operating Conditions (VOC). Therefore, determining the VOC impact on the failure dynamics severity is an essential task for bearing failure prognostics. This paper introduces a hybrid prognosis method using real-time Supervisory Control and Data Acquisition (SCADA) and vibration signals to predict Remaining Useful Life (RUL) for wind turbine bearings. The SCADA data is utilized to define the role of environmental conditions such as wind speed and ambient temperature in bearing failure dynamics. Afterward, for each environmental condition, failure dynamics are identified by the vibration signal. Finally, RUL of the faulty bearings is forecast via an adaptive Bayesian Algorithm using the failure dynamics, conditional to the VOC. The efficacy of the method is validated using experimental data, and test results indicate a higher RUL accuracy compared to the Bayesian Algorithm.

Condition Monitoring (CM) is an essential element of securing reliable operating conditions of Wind Turbines (WT) in a wind farm. CM helps optimize maintenance by providing Remaining Useful Life (RUL) forecast. However, the expected RUL is not often reliable due to uncertainty associated with the prediction horizon. In this paper, we employ high-level fusion methods to expect the RUL of WT bearings. For this purpose, various features are extracted by vibration signals to capture deterioration paths. Then, a Bayesian algorithm is utilized to determine RUL for each selected feature. Eventually, high-level fusion schemes, including Hurwicz, Choquet integral, Ordered Weighted Averaging operator, are employed to integrate RUL numbers and lessen associated uncertainty in the prediction horizons. Besides, a pessimistic fusion strategy is driven to obtain a bounded uncertainty for the worst RUL prediction. The fusion methods are assessed by ten-year vibration signals of Canadian wind farms. Experimental results confirm accurate results with bounded uncertainty for high-level fusion approaches.