Automated prediction of repair based on sensor data

A method for automating prediction of a repair for an aircraft, the method comprising:

• receiving, via a communications device mounted to the aircraft from an aircraft sensor device monitoring an electrical, hydraulic, or propulsion aircraft operating system of the aircraft, a time series of measurements of a plurality of operating conditions of the aircraft recorded during a flight operation of the aircraft;
• clustering, via a processing circuit mounted to the aircraft, the time series of measurements into respective clusters of measurements;
• identifying, via the processing circuit, a pattern across the clusters of measurements, including:
• compressing sensor data points in the time series of measurements to form compressed data, wherein the compression is based on:
• computing a distance between a data point of the sensor data points and a cluster state that represents a mean value of data points in a cluster of a plurality of clusters of the clusters of measurements, and
• assigning the cluster state to the data point based on determining that the computed distance between the data point and the state is the shortest from a set of distances computed between the data point and cluster states of the plurality of clusters, and
• sequencing latent states for the compressed data computed for n seconds in a sliding window;
• defining, via the processing circuit, a current state of the aircraft that includes the pattern across the clusters of measurements;
• accessing, via the processing circuit, a knowledge base including a set of historical cases describing historical problem states of the aircraft and respective solutions, the historical problem states of the aircraft including patterns across clusters of measurements of the plurality of operating conditions of the aircraft recorded during previous instances of operation of the aircraft during which failure modes of the aircraft operating systems of the aircraft occurred, and the respective solutions including repair actions performed to address respective ones of the failure modes;
• identifying, via the processing circuit searching the knowledge base, a historical case describing a respective solution to a historical problem state of the historical problem states similar to the current state, the respective solution being identified as a candidate solution to the current state, the respective solution to the historical problem state including a repair action;
• and
• generating an output display indicating the repair action to address the current state.

A computer-readable storage medium comprising:

• computer-readable program code and a knowledge-based system stored therein, the knowledge-based system including an inference engine and a knowledge base, the computer-readable program code, in response to execution by processing circuitry, causing the inference engine and thereby an apparatus mounted to an aircraft to:
• receive, via a communications device mounted to the aircraft from an aircraft sensor device monitoring an electrical, hydraulic, or propulsion aircraft operating system of the aircraft, a time series of measurements of a plurality of operating conditions of the aircraft recorded during a flight operation of the aircraft;
• cluster the time series of measurements into respective clusters of measurements;
• identify a pattern across the clusters of measurements, including:
• compressing sensor data points in the time series of measurements to form compressed data, wherein the compression is based on:
• computing a distance between a data point of the sensor data points and a cluster state that represents a mean value of data points in a cluster of a plurality of clusters of the clusters of measurements, and
• assigning the cluster state to the data point based on determining that the computed distance between the data point and the state is the shortest from a set of distances computed between the data point and cluster states of the plurality of clusters, and
• sequencing latent states for the compressed data computed for n seconds in a sliding window;
• define a current state of the aircraft that includes the pattern across the clusters of measurements;
• access the knowledge base including a set of historical cases describing historical problem states of the aircraft and respective solutions, the historical problem states of the aircraft including patterns across clusters of measurements of the plurality of operating conditions of the aircraft recorded during previous instances of operation of the aircraft during which failure modes of the aircraft operating systems of the aircraft occurred, and the respective solutions including repair actions performed to address respective ones of the failure modes;
• identify, by searching the knowledge base, a historical case describing a respective solution to a historical problem state of the historical problem states similar to the current state, the respective solution being identified as a candidate solution to the current state, the respective solution to the historical problem state including a repair action;
• and
• generate an output display indicating the repair action to address the current state.