Abstract: The present application relates to a system comprising a processor configured to execute a digital system model based on simulated conditions to generate simulated data. The processor may also be configured to train a surrogate model using at least the simulated data to approximate the digital system model of the system and generate, using the trained surrogate model, estimated values for conditions or parameters of the systems based on operational data, wherein the operational data includes sensor data or in-service data from the system. Further, the processor may be configured to execute the digital system model of the system to generate simulation data based on the operational data and the estimated values or parameters generated by the surrogate model and synchronize or update a digital twin of the system based on the simulation data, wherein the digital twin represents a state or condition of the system.

Abstract: A method includes training a model to identify anomalous portions of a test component using training images and labels that indicate anomalous portions of training components within the training images. The method also includes compressing a source image of the test component to generate a first input image having a first resolution and making a first determination of whether the first input image indicates that the test component is anomalous. The method also includes making a second determination, for each section of a second input image, of whether the section indicates that the test component is anomalous. The second input image has a second resolution that is greater than the first resolution. The method also includes providing an indication of whether the first input image indicates that the test component is anomalous and providing an indication of whether the second input image indicates that the test component is anomalous.

Abstract: A method of categorizing natural language text using a processor configured to execute instructions stored on a memory to perform the steps. The method includes selecting candidate keywords from a list of potential keywords based on the natural language text, the candidate keywords having a probability of success being greater than a threshold value. The method also includes generating, using a classification machine learning model (MLM), a list of candidate categories based on the potential keywords. The method also includes generating, using a similarity comparison MLM, a similarity score based on the candidate categories and a set of pre-determined categories. The method also includes assigning a selected category based on the similarity score to the natural language text.

Abstract: A vehicle maintenance scheduling and fault monitoring apparatus includes a vehicle system maintenance rules generation module and a vehicle system fault detection module. The rules generation module determines a correlation between pairs of precedent historical vehicle fault data, of historical time-stamped vehicle fault data, and a subsequent different historical vehicle fault data, and generates vehicle system maintenance rules based on the correlation determined for the pairs of the precedent historical vehicle fault data and the subsequent different historical vehicle fault data. The fault detection module monitors faults of the vehicle system, determines an imminent occurrence of a subsequent vehicle fault, based on application of the vehicle system maintenance rules to the plurality of time-stamped precedent vehicle fault data, and generates a maintenance report corresponding to the imminent occurrence of the subsequent vehicle fault so that proactive maintenance is performed on the vehicle system.

Abstract: A maintenance interval adjuster and methods for improving accuracy of maintenance scheduling and changing a maintenance interval are presented. Scheduled maintenance data and unscheduled in-service maintenance data for a maintenance task are retrieved for a plurality of platforms. A distribution of lifetimes for the maintenance task in the scheduled maintenance data and unscheduled in-service maintenance data are analyzed for high variance or multiple modes. A number of conditions in sensor data of the plurality of platforms correlated to a length of the lifetimes for the maintenance task is identified, in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes. The lifetimes are divided into a plurality of groups based on the number of conditions. A respective recommended maintenance interval is determined for each group of the plurality of groups based on respective lifetimes for the maintenance task of a respective group.

Abstract: A method includes receiving, by an equipment monitoring system (EMS), first training data and second training data from a plurality of sensors of an article over a first operating interval and over a second operating interval of the article, respectively, appending buffer data to the first training data, and the second training data to the buffer data to provide extended training data, and clustering the extended training data into a plurality of data clusters associated with operational states of the article. Subsequent to clustering, the EMS receives operational data associated with the plurality of sensors of the article over a third operating interval. The EMS determines a particular data cluster of the plurality of data clusters to which the operational data belongs, and communicates data indicative of an operational state of the article associated with the particular data cluster to a control system.

Abstract: The disclosed examples relate to arranging graph data for display on a display device. One example provides, on a computing device, a method comprising determining one or more connected groups of nodes in directed acyclic graph data, for each connected group of nodes, determining a reachability from each node with no inputs to each of one or more nodes with no outputs to determine a plurality of initial node/terminal node pairs, and for each initial node/terminal node pair, determining a path from the initial node to the terminal node. The method further comprises initializing a grid based upon the determined paths, placing each node at a corresponding initial grid location, and placing edges between nodes based upon the determined paths to form an initial grid representation, modifying the initial grid representation via a cost function to form a modified grid representation, and outputting the modified grid representation for display.

Abstract: The disclosed examples relate to arranging graph data for display on a display device. One example provides, on a computing device, a method comprising determining one or more connected groups of nodes in directed acyclic graph data, for each connected group of nodes, determining a reachability from each node with no inputs to each of one or more nodes with no outputs to determine a plurality of initial node/terminal node pairs, and for each initial node/terminal node pair, determining a path from the initial node to the terminal node. The method further comprises initializing a grid based upon the determined paths, placing each node at a corresponding initial grid location, and placing edges between nodes based upon the determined paths to form an initial grid representation, modifying the initial grid representation via a cost function to form a modified grid representation, and outputting the modified grid representation for display.

Abstract: A maintenance interval adjuster and methods for improving accuracy of maintenance scheduling and changing a maintenance interval are presented. Scheduled maintenance data and unscheduled in-service maintenance data for a maintenance task are retrieved for a plurality of platforms. A distribution of lifetimes for the maintenance task in the scheduled maintenance data and unscheduled in-service maintenance data are analyzed for high variance or multiple modes. A number of conditions in sensor data of the plurality of platforms correlated to a length of the lifetimes for the maintenance task is identified, in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes. The lifetimes are divided into a plurality of groups based on the number of conditions. A respective recommended maintenance interval is determined for each group of the plurality of groups based on respective lifetimes for the maintenance task of a respective group.

Abstract: Method and apparatus for detecting anomalous flights. Embodiments collect sensor data from a plurality of sensor devices onboard an aircraft during a flight. Feature definitions are determined, specifying a sensor device and an algorithm for deriving data values from sensor data collected from the device. Embodiments determine whether anomalous activity occurred during the flight using an anomaly detection model. An anomaly is detected including at least one of (i) a contextual anomaly where a data instance of a plurality of data instances is anomalous relative to a specific context, or (ii) a collective anomaly where two or more data instances are anomalous relative to a remainder of the plurality of data instances, even though each of the two or more data instances is not anomalous in and of itself. A report specifying a measure of the anomalous activity for the flight is generated.

Abstract: Hybrid feature selection methods include methods of creating a predictive model for valve performance in a fleet of aircraft. Methods include qualifying a qualification dataset of valve-related parameters calculated from data collected during a first series of flights at least before and after a non-performance event of a valve. Methods include receiving a qualified selection of the valve-related parameters and verifying a verification dataset of the qualified selection of the valve-related parameters calculated from data collected during a second series of flights. Methods include receiving a set of verified and qualified valve-related parameters and building a predictive model for valve non-performance with a training dataset of the verified and qualified valve-related parameters calculated from data collected during additional flights of the fleet.

Abstract: Method and apparatus for detecting anomalous flights. Embodiments collect sensor data from a plurality of sensor devices onboard an aircraft during a flight. Feature definitions are determined, specifying a sensor device and an algorithm for deriving data values from sensor data collected from the device. Embodiments determine whether anomalous activity occurred during the flight using an anomaly detection model. An anomaly is detected including at least one of (i) a contextual anomaly where a data instance of a plurality of data instances is anomalous relative to a specific context, or (ii) a collective anomaly where two or more data instances are anomalous relative to a remainder of the plurality of data instances, even though each of the two or more data instances is not anomalous in and of itself. A report specifying a measure of the anomalous activity for the flight is generated.

Abstract: A vehicle maintenance scheduling and fault monitoring apparatus includes a vehicle system maintenance rules generation module and a vehicle system fault detection module. The rules generation module determines a correlation between pairs of precedent historical vehicle fault data, of historical time-stamped vehicle fault data, and a subsequent different historical vehicle fault data, and generates vehicle system maintenance rules based on the correlation determined for the pairs of the precedent historical vehicle fault data and the subsequent different historical vehicle fault data. The fault detection module monitors faults of the vehicle system, determines an imminent occurrence of a subsequent vehicle fault, based on application of the vehicle system maintenance rules to the plurality of time-stamped precedent vehicle fault data, and generates a maintenance report corresponding to the imminent occurrence of the subsequent vehicle fault so that proactive maintenance is performed on the vehicle system.

Abstract: Method and apparatus for detecting anomalous flights. Embodiments collect sensor data from a plurality of sensor devices onboard an aircraft during a flight. A plurality of feature definitions are determined, where a first one of the feature definitions specifies one or more of the plurality of sensor devices and an algorithm for deriving data values from sensor data collected from the one or more sensor devices. Embodiments determine whether anomalous activity occurred during the flight using an anomaly detection model, where the anomaly detection model describes a pattern of normal feature values for at least the feature definition, and comprising comparing feature values calculated from the collected sensor data with the pattern of normal feature values for the first feature definition. A report specifying a measure of the anomalous activity for the flight is generated.

Abstract: A vehicle health monitoring system including a rules generation module that receives historical time-stamped vehicle fault data for a vehicle system, determines a correlation between pairs of a precedent historical vehicle fault data, of the historical time-stamped vehicle fault data, and a subsequent different historical vehicle fault data, of the historical time-stamped vehicle fault data, and generates maintenance rules based on the correlation determined for the pairs. A fault detection module of the system monitors faults of the vehicle system, where the vehicle faults include a plurality of time-stamped precedent vehicle fault data, applies the rules to the plurality of time-stamped precedent vehicle fault data, determines an imminent occurrence of a subsequent vehicle fault, and generates a maintenance report corresponding to the imminent occurrence of the subsequent vehicle fault so that proactive maintenance is performed on the vehicle system.

Abstract: Systems and methods of the present disclosure include determining a performance status of a selected component in an aircraft. An ensemble of related machine learning models is applied to feature data extracted from flight data of the aircraft. Each model produces a positive score and a complementary negative score related to performance of the selected component. The positive scores are weighted based on the false positive rates of the models and the negative scores are weighted based on the false negative rates of the models. The weighted positive scores are combined, e.g., by averaging, and the weighted negative scores are combined, e.g., by averaging. The performance status of the selected component is determined as one of a positive category, a negative category, or an unclassified category based on the values of the combined weighted positive scores and the combined weighted negative scores.

Abstract: Hybrid feature selection methods include methods of creating a predictive model for valve performance in a fleet of aircraft. Methods include qualifying a qualification dataset of valve-related parameters calculated from data collected during a first series of flights at least before and after a non-performance event of a valve. Methods include receiving a qualified selection of the valve-related parameters and verifying a verification dataset of the qualified selection of the valve-related parameters calculated from data collected during a second series of flights. Methods include receiving a set of verified and qualified valve-related parameters and building a predictive model for valve non-performance with a training dataset of the verified and qualified valve-related parameters calculated from data collected during additional flights of the fleet.

Abstract: A vehicle health monitoring system including a rules generation module that receives historical time-stamped vehicle fault data for a vehicle system, determines a correlation between pairs of a precedent historical vehicle fault data, of the historical time-stamped vehicle fault data, and a subsequent different historical vehicle fault data, of the historical time-stamped vehicle fault data, and generates maintenance rules based on the correlation determined for the pairs. A fault detection module of the system monitors faults of the vehicle system, where the vehicle faults include a plurality of time-stamped precedent vehicle fault data, applies the rules to the plurality of time-stamped precedent vehicle fault data, determines an imminent occurrence of a subsequent vehicle fault, and generates a maintenance report corresponding to the imminent occurrence of the subsequent vehicle fault so that proactive maintenance is performed on the vehicle system.

Abstract: Predictive aircraft maintenance systems and methods are disclosed. Predictive maintenance methods may include extracting feature data from flight data collected during a flight of the aircraft, applying an ensemble of related classifiers to produce a classifier indicator for each classifier of the ensemble of classifiers, aggregating the classifier indicators to produce an aggregate indicator indicating an aggregate category of a selected component for a threshold number of future flights, and determining the performance status of the selected component based on the aggregate indicator. The classifiers are each configured to indicate a category of the selected component within a given number of flights. The given number of flights for each classifier is different. The threshold number of future flights is greater than or equal to the maximum of the given numbers of the classifiers.

Abstract: Systems and methods of the present disclosure include determining a performance status of a selected component in an aircraft. An ensemble of related machine learning models is applied to feature data extracted from flight data of the aircraft. Each model produces a positive score and a complementary negative score related to performance of the selected component. The positive scores are weighted based on the false positive rates of the models and the negative scores are weighted based on the false negative rates of the models. The weighted positive scores are combined, e.g., by averaging, and the weighted negative scores are combined, e.g., by averaging. The performance status of the selected component is determined as one of a positive category, a negative category, or an unclassified category based on the values of the combined weighted positive scores and the combined weighted negative scores.