The energy system is in a transformation for a sustainable society. The overall targets are to meet climate goals and to reach energy independence. Wind turbines provide a main solution converting renewable energy resources into electricity with a resulting enormous global growth. A challenge is, however, to reduce the operation and maintenance costs for wind generation to ensure good investments. Asset management (AM) aims to handle assets in an optimal way in order to fulfil an organization’s goal whilst considering risk. This chapter proposes a novel method for AM and preventive maintenance using condition monitoring. The suggested model is an autoencoder-based anomaly detection method for tracking the condition of wind turbines. First, the technique uses supervisory control and data acquisition (SCADA) signals as its data input. The method then analyses the discrepancies between the acquired data from the SCADA system and the estimated values by the autoencoder models. The distribution of the output error is then calculated using the Kernel Density Estimation. Finally, a novel dynamic thresholding approach is employed to effectively extract anomalies in the data. The results show that the approach can identify significant irregularities before a breakdown happens. Additionally, it confirms that the method may notify operators of prospective changes in wind turbines even in the absence of alarm recordings.