|
چکیده
|
Wind turbines, being essential elements of renewable energy infrastructure, require robust problem detection techniques to guarantee optimal performance and prevent costly downtime. The presence of noise, missing data, and the overlapping signatures of different faults make it complicated to precisely identify specific faults. Furthermore, the task of differentiating between normal operational anomalies and actual malfunctions, together with the challenge of creating models that may apply to different types of turbines and environmental conditions, poses significant challenges. The limited number of faulty data in wind turbine systems is a notable obstacle for multifault detection. This paper presents a new method for identifying multiple faults and determining the underlying cause in wind turbines. The method utilizes multivariate time series data and a model based on autoencoders. Multivariate Kernel Density Estimation (KDE) is employed to perform data cleansing by detecting and eliminating anomalous data points, so as to preserve just the ``normal" data. KDE facilitates the identification of outliers or anomalies that depart considerably from the expected distribution, allowing for the selection of data that corresponds to the normative pattern for the next analysis. The autoencoder is specifically developed to acquire knowledge about the normal operational patterns of the wind turbine by analyzing historical data. It accomplishes this by capturing complex relationships among various variables. The model discovers probable anomalies by lowering the dimensionality of the data and recreating it, hence detecting abnormalities. This methodology offers significant knowledge for maintenance strategies, and ultimately increases the efficiency and durability of wind turbine operation.
|