Current paper presents a features extraction method when analyzing the acoustic emission (AE) control data of the technical condition of construction facilities as a part of decision support in cyber physical monitoring system. A set of statistical parameters that describe local properties of AE time series in time and frequency domains has been proposed. Furthermore, a features calculation method based on utilizing sliding windows with overlays in two time scales was introduced. Presented method has been pilot-tested during the technical diagnostics of the oil tank containing defects of different hazard classes.