Parametric trending architecture concept and design
A method for foreign object debris detection in a gas turbine engine may comprise receiving, by a controller, a plurality of master configuration parameters, receiving, by the controller, a plurality of individual configuration parameters in response to the plurality of master configuration parameters, receiving, by the controller, a first time-series data from a database, pre-processing, by the controller, the first time-series data to generate a second time-series data, implementing, by the controller, an anomaly detector model, the anomaly detector model configured to generate a third time-series data, and implementing, by the controller, a foreign object debris (FOD) damage model, the FOD damage model receiving the third time-series data. The pre-processing the first time-series data, the implementing the anomaly detector model, and the implementing the FOD damage model may be defined by the plurality of individual configuration parameters.
1. A method for foreign object debris detection in a gas turbine engine comprising:
receiving, by a controller, a plurality of master configuration parameters, wherein the plurality of master configuration parameters include at least one of a limit, a Boolean value, a coefficient, or a characteristic value;
receiving, by the controller, a plurality of individual configuration parameters in response to the controller receiving the plurality of master configuration parameters, wherein the plurality of individual configuration parameters include at least one of a limit, a Boolean value, a coefficient, or a characteristic value;
receiving, by the controller, a first time-series data from a database, wherein the first time-series data comprises data received from a debris monitoring sensor for the gas turbine engine;
pre-processing, by the controller, the first time-series data to generate a second time-series data, the pre-processing defined by the plurality of individual configuration parameters;
implementing, by the controller, an anomaly detector model, the anomaly detector model configured to generate a third time-series data, the implementing the anomaly detector model defined by the plurality of individual configuration parameters; and
implementing, by the controller, a foreign object debris (FOD) damage model, the FOD damage model receiving the third time-series data, the implementing the FOD damage model defined by the plurality of individual configuration parameters;
determining, by the controller, that a FOD event has occurred based upon the third time-series data in response to the FOD damage model being implemented; and
generating a health report (HR) in response to the FOD event being detected, wherein the HR is based upon the third time-series data;
wherein at least one of the anomaly detector model and the FOD damage model are configurable in response to the master configuration parameter and the individual configuration parameter.
2. The method of claim 1 , wherein the implementing the anomaly detector model includes calculating, by the controller, the third time-series data, the third time-series data comprising an anomaly detector, wherein the anomaly detector is based upon the second time-series data.
3. The method of claim 2 , wherein the third time-series data comprises an anomaly detection signal.
4. The method of claim 2 , wherein the pre-processing causes the controller to at least one of:
calculate a derived parameter, wherein the derived parameter is calculated using the first time-series data;
evaluate an integrity of the first time-series data;
evaluate a health of a debris monitoring sensor;
clean the first time-series data;
align the first time-series data with respect to time;
define a filter for the first time-series data; or
define a point of interest of the first time-series data.
5. The method of claim 1 , wherein the controller determines that the FOD event has occurred based upon at least one of the master configuration parameter and the individual configuration parameter.