System and method of forecasting aircraft engine operational data for predictive analytics

A method, comprising:

• receiving, by one or more computing devices, engine data associated with an engine, the engine data including data points each defined in part by a value associated with an operational parameter;
• determining, by the one or more computing devices, forecasted data points associated with the operational parameter, each of the forecasted data points being defined in part by a forecasted value associated with the operational parameter, and wherein a given one of the forecasted data points is determined by:
• generating, by the one or more computing devices, a preliminary regression line relative to the data points;
• filtering out, by the one or more computing devices, outlier data points from the data points to render filtered data points, the outlier data points being filtered out based at least in part on a position of a given data point of the data points relative to the preliminary regression line;
• generating, by the one or more computing devices, a final regression line relative to the filtered data points;
• generating, by the one or more computing devices, a set of coefficients for a forecasting function based at least in part on the final regression line;
• generating, by the one or more computing devices, a forecasted regression line based at least in part on the forecasting function and the set of coefficients;
• selecting, by the one or more computing devices, a residual from a residual table, the residual defining a distance between a data point of the data points and the preliminary regression line, and
• wherein the given one of the forecasted data points is determined, by the one or more computing devices, based at least in part on the residual selected from the residual table and the forecasted regression line.

A system, comprising:

• one or more memory devices;
• one or more processors, the one or more processors being configured to:
• receive data associated with an asset, the data including data points for operational parameters, each of the data points being defined in part by a value associated with one of the operational parameters;
• determine forecasted data points for each of the operational parameters, the forecasted data points for a given one of the operational parameters being determined by applying one or more regression techniques to the data points associated with the given one of the operational parameters, each of the forecasted data points being defined in part by a forecasted value associated with one of the operational parameters;
• generate a plurality of forecasts based at least in part on the forecasted data points, the plurality of forecasts each predicting a damage sum associated with the asset;
• and
• output a cumulative probability distribution indicating a cumulative probability of the plurality of forecasts exceeding a predetermined threshold prior to a next scheduled service visit for the asset.