Abstract: A method includes obtaining a plurality of data sets, where each data set of the plurality of data sets includes multivariate time series data for a respective sample period of a plurality of sample periods. The method also includes, for each data set of the plurality of data sets, determining recurrence data indicative of recurrent states in the data set and determining, based on the recurrence data, determinism values of a determinism metric and laminarity values of a laminarity metric. The method further includes determining that a particular data set of the plurality of data sets includes data representing an anomalous state based on a determinism-laminarity curve representing the particular data set, where the determinism-laminarity curve is based on the determinism values of the particular data set and the laminarity values of the particular data set. The method also includes generating output data indicating the anomalous state.

Abstract: A method includes receiving input data including a plurality of feature vectors and labeling each feature vector based on a temporal proximity of the feature vector to occurrence of a fault. Feature vectors that are within a threshold temporal proximity to the occurrence of the fault are labeled with a first label value and other feature vectors are labeled with a second label value. The method includes determining, for each feature vector of a subset, a probability that the label associated with the feature vector is correct. The subset includes feature vectors having labels that indicate the first label value. The method includes reassigning labels of one or more feature vectors of the subset having a probability that fails to satisfy a probability threshold and, after reassigning the labels, training an aircraft fault prediction classifier using supervised training data including the plurality of feature vectors and the labels.

Abstract: A diagnostic system for a closed fluid system is provided. The closed fluid system includes a first fluid subsystem and a second fluid subsystem connected using a valve or valve/actuator. The diagnostic system includes a first sensor disposed in the first fluid subsystem, a second sensor disposed in the second fluid subsystem and a computer. The computer receives first time-ordered fluid level measurements and second time-ordered fluid level measurements from respectively the first sensor and the second sensor and performs a comparison of first fluid level of the first fluid subsystem and second fluid level of the second fluid subsystem. The computer produces a notification indicating a predicted transfer of hydraulic fluid when the first time-ordered fluid level measurements and the second time-ordered fluid level measurements have at least a threshold divergence and outputs the notification for display to a user.

Abstract: A method includes obtaining a plurality of data sets, where each data set of the plurality of data sets includes multivariate time series data for a respective sample period of a plurality of sample periods. The method also includes, for each data set of the plurality of data sets, determining recurrence data indicative of recurrent states in the data set and determining, based on the recurrence data, determinism values of a determinism metric and laminarity values of a laminarity metric. The method further includes determining that a particular data set of the plurality of data sets includes data representing an anomalous state based on a determinism-laminarity curve representing the particular data set, where the determinism-laminarity curve is based on the determinism values of the particular data set and the laminarity values of the particular data set. The method also includes generating output data indicating the anomalous state.

Abstract: A system and method for drift detection is disclosed. The method may comprise training and testing an autoencoder, and using the trained and tested autoencoder to automatically detect data drift. The training may include initializing the autoencoder and training the autoencoder based on a first set of sensor data. The testing of the autoencoder with a second set of sensor data may comprise: for an empirical distribution of the reconstruction errors of the second set of sensor data, determining a value of a reconstruction error at the percentile threshold; determining that data drift is not present when the reconstruction error of the second set of sensor data is less than a threshold; and calculating a deviation output for at least one of the one or more sensors. Using the trained and tested autoencoder to automatically detect data drift in sensor data.

Abstract: A method includes receiving input data including a plurality of feature vectors and labeling each feature vector based on a temporal proximity of the feature vector to occurrence of a fault. Feature vectors that are within a threshold temporal proximity to the occurrence of the fault are labeled with a first label value and other feature vectors are labeled with a second label value. The method includes determining, for each feature vector of a subset, a probability that the label associated with the feature vector is correct. The subset includes feature vectors having labels that indicate the first label value. The method includes reassigning labels of one or more feature vectors of the subset having a probability that fails to satisfy a probability threshold and, after reassigning the labels, training an aircraft fault prediction classifier using supervised training data including the plurality of feature vectors and the labels.

Abstract: An apparatus for detecting fault states of an aircraft is provided. The apparatus receives training data including operational parameters of the aircraft operating over a plurality of training flight legs and applies a first clustering algorithm separately to the training data to produce first clustered data. The apparatus applies a second clustering algorithm to the first clustered data to produce second clustered data that indicates a plurality of states describing behavior of the aircraft operating over the training legs and applies a third clustering algorithm to identify one or more fault states of the aircraft from the plurality of states based on the training data and the second clustered data. The apparatus receives messages carrying data from the aircraft over a digital datalink, detects a fault state of the one or more fault states from the data, and generates an alert of the fault state.

Abstract: A system for monitoring aircraft operational messages is provided. The system includes a computing device including a processor in communication with a memory. The computing device is programmed to receive a plurality of historical messages for a plurality of aircraft. Each message of the plurality of historical messages is a message from one of the plurality of aircraft. The computing device is also programmed to receive a plurality of historical maintenance operations performed on the plurality of aircraft, compare the plurality of historical messages to the plurality of historical maintenance operations to determine at least one message type associated with at least one maintenance operation type, and generate a plurality of message type correlations between message types and maintenance operation types based on the comparison.

Abstract: A diagnostic system for a closed fluid system is provided. The closed fluid system includes a first fluid subsystem and a second fluid subsystem connected using a valve or valve/actuator. The diagnostic system includes a first sensor disposed in the first fluid subsystem, a second sensor disposed in the second fluid subsystem and a computer. The computer receives first time-ordered fluid level measurements and second time-ordered fluid level measurements from respectively the first sensor and the second sensor and performs a comparison of first fluid level of the first fluid subsystem and second fluid level of the second fluid subsystem. The computer produces a notification indicating a predicted transfer of hydraulic fluid when the first time-ordered fluid level measurements and the second time-ordered fluid level measurements have at least a threshold divergence and outputs the notification for display to a user.

Abstract: A system for monitoring aircraft operational messages is provided. The system includes a computing device including a processor in communication with a memory. The computing device is programmed to receive a plurality of historical messages for a plurality of aircraft. Each message of the plurality of historical messages is a message from one of the plurality of aircraft. The computing device is also programmed to receive a plurality of historical maintenance operations performed on the plurality of aircraft, compare the plurality of historical messages to the plurality of historical maintenance operations to determine at least one message type associated with at least one maintenance operation type, and generate a plurality of message type correlations between message types and maintenance operation types based on the comparison.

Abstract: A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A monitoring system is in communication with the operative sub-system(s). The monitoring system is configured to correlate the one or more sensor signals with respect to time, compile initial statistics of the one or more sensor signals with respect to a plurality of variables; and correlate the plurality of variables.

Abstract: A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A fault detection system may be in communication with the operative sub-system(s). The fault detection system is configured to generate at least one early warning signal based on the one more sensor signals, and determine at least one derivative of the early warning signal(s).

Abstract: A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A monitoring system is in communication with the operative sub-system(s). The monitoring system is configured to correlate the one or more sensor signals with respect to time, compile initial statistics of the one or more sensor signals with respect to a plurality of variables; and correlate the plurality of variables.

Abstract: A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A fault detection system may be in communication with the operative sub-system(s). The fault detection system is configured to generate at least one early warning signal based on the one more sensor signals, and determine at least one derivative of the early warning signal(s).