Abstract: A vehicle includes a first system, a first sensor, a second sensor, and a processor. The first sensor is configured to generate first sensor data indicative of an operational status of the first system. The second sensor is configured to generate second sensor data associated with an adaptive performance metric adjustment criterion. The processor is configured to, in response to determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, determine, based on the second sensor data, an adaptive performance metric to be compared to the first sensor data to identify anomalous behavior of the first system. The processor is further configured to compare the first sensor data to the adaptive performance metric and to generate a maintenance alert in response to determining that the first sensor data fails to satisfy the adaptive performance metric.

Abstract: Methods include qualifying a qualification dataset of fatigue-related parameters calculated from data collected during a first group of flights of a first aircraft that experienced a replacement of a structural component during heavy maintenance. Methods include receiving a qualified selection of the fatigue-related parameters and verifying a verification dataset of the qualified selection of the fatigue-related parameters calculated from data collected during a second group of flights of a second aircraft that experienced heavy maintenance without replacement of the structural component. Methods include receiving a set of verified and qualified fatigue-related parameters and building a predictive model for structural repair during heavy maintenance with a training dataset of the verified and qualified fatigue-related parameters calculated from data collected during additional flights of the fleet. Hybrid feature selection systems also are disclosed.

Abstract: A data processing system may include instructions stored in a memory and executed by a processor to categorize a plurality of systems into clusters using an unsupervised machine learning method to analyze repair data parameters of a historical dataset relating to the plurality of systems. The system may assign a repair forecast to each cluster, and may generate a system repair forecasting model using selected predictor variables, the historical data set, and the repair forecasts according to a supervised machine learning method. The selected predictor variables may correspond to a mathematical combination of operational data parameters in the historical dataset.

Abstract: A data processing system may include instructions stored in a memory and executed by a processor to categorize a plurality of systems into clusters using an unsupervised machine learning method to analyze repair data parameters of a historical dataset relating to the plurality of systems. The system may assign a repair forecast to each cluster, and may generate a system repair forecasting model using selected predictor variables, the historical data set, and the repair forecasts according to a supervised machine learning method. The selected predictor variables may correspond to a mathematical combination of operational data parameters in the historical dataset.

Abstract: A method is provided that includes accessing a multivariate time series of flight data for an aircraft, and iteratively performing runs of genetic programming on groups of the sensors. A population of computer programs is randomly generated from a selected group of the plurality of sensors, and primitive functions selected from a library of primitive functions. The population is iteratively transformed into new generations of the population, and includes sub-rankings of the group of sensors based on a quantitative fitness determined according to selected fitness criterion. A ranking of the group of sensors from the sub-rankings of the group of sensors is produced. An aggregate ranking of the plurality of sensors is produced from the ranking of the group of sensors over a plurality of iterations. And the subset of sensors is selected from the aggregate ranking of the plurality of sensors, and according to selected optimization criterion.

Abstract: Methods include qualifying a qualification dataset of fatigue-related parameters calculated from data collected during a first group of flights of a first aircraft that experienced a replacement of a structural component during heavy maintenance. Methods include receiving a qualified selection of the fatigue-related parameters and verifying a verification dataset of the qualified selection of the fatigue-related parameters calculated from data collected during a second group of flights of a second aircraft that experienced heavy maintenance without replacement of the structural component. Methods include receiving a set of verified and qualified fatigue-related parameters and building a predictive model for structural repair during heavy maintenance with a training dataset of the verified and qualified fatigue-related parameters calculated from data collected during additional flights of the fleet. Hybrid feature selection systems also are disclosed.

Abstract: Hybrid feature selection methods include methods of creating a predictive model for structural repair during heavy maintenance in a fleet of aircraft. Methods include qualifying a qualification dataset of fatigue-related parameters calculated from data collected during a first group of flights of a first aircraft that experience a replacement of a structural component during heavy maintenance. Methods include receiving a qualified selection of the fatigue-related parameters and verifying a verification dataset of the qualified selection of the fatigue-related parameters calculated from data collected during a second group of flights of a second aircraft that experienced heavy maintenance without replacement of the structural component.

Abstract: A vehicle includes a first system, a first sensor, a second sensor, and a processor. The first sensor is configured to generate first sensor data indicative of an operational status of the first system. The second sensor is configured to generate second sensor data associated with an adaptive performance metric adjustment criterion. The processor is configured to, in response to determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, determine, based on the second sensor data, an adaptive performance metric to be compared to the first sensor data to identify anomalous behavior of the first system. The processor is further configured to compare the first sensor data to the adaptive performance metric and to generate a maintenance alert in response to determining that the first sensor data fails to satisfy the adaptive performance metric.

Abstract: A data processing system may include instructions stored in a memory and executed by a processor to categorize a plurality of systems into clusters using an unsupervised machine learning method to analyze repair data parameters of a historical dataset relating to the plurality of systems. The system may assign a repair forecast to each cluster, and may generate a system repair forecasting model using selected predictor variables, the historical data set, and the repair forecasts according to a supervised machine learning method. The selected predictor variables may correspond to a mathematical combination of operational data parameters in the historical dataset.

Abstract: Hybrid feature selection methods include methods of creating a predictive model for structural repair during heavy maintenance in a fleet of aircraft. Methods include qualifying a qualification dataset of fatigue-related parameters calculated from data collected during a first group of flights of a first aircraft that experience a replacement of a structural component during heavy maintenance. Methods include receiving a qualified selection of the fatigue-related parameters and verifying a verification dataset of the qualified selection of the fatigue-related parameters calculated from data collected during a second group of flights of a second aircraft that experienced heavy maintenance without replacement of the structural component.

Abstract: Predictive aircraft maintenance methods include extracting feature data from flight data collected during a flight of the aircraft, calculating a performance classifier indicator that indicates a performance category of the selected flight control surface component within a threshold number of future flights based on the feature data, and determining the performance status of the selected flight control surface component relative to the threshold number of future flights based on the performance classifier indicator. Such methods may include classifying the feature data with an ensemble of related primary classifiers to produce a primary classifier indicator for each primary classifier and aggregating the primary classifier indicators to produce the performance classifier indicator indicating the performance category of the selected active component for the threshold number of future flights.

Abstract: A platform management system, apparatus, and method are disclosed that track schedule interruption data and at least one of delay risk data, deferral risk data, deferral data, and dispatch reliability data over time, compute cross-correlations between the schedule interruption data and the at least one of the delay risk data, the deferral risk data, the deferral data, and the dispatch reliability data, and computing a statistically significant probability of a schedule interruption based on the cross-correlations and a trend of the at least one of the delay risk data, the deferred maintenance data, the deferral data, and the dispatch reliability data projected over a predetermined time period into the future, and that compute delay risk data based on projected schedule interruption data and delay data.