The Boeing Company

Shervin Beygi

Omid B Nakhjavani

Mohammad Mojtahedzadeh

Robert Anthony Bernicchi

Darren Brian Macer

Andrey Aleksandrovich Zaikin

Catherine M Crandall

Karin E Bauer

Allen Lee

Emily Samuelson

Brandi E Fleming

Michael John Avendt

A method for aircraft maintenance comprises loading, into computer memory, a plurality of unstructured aircraft component records originating from one or more different component status monitors, the plurality of unstructured aircraft component records describing observed maintenance conditions of a plurality of different aircraft components. The plurality of unstructured aircraft component records are provided from computer memory to a natural language processing (NLP) model configured to output a corresponding plurality of digital component, condition, and location (CCL) records for the plurality of different aircraft components. CCL records for a plurality of different CCL types are independently computer aggregated. The CCL records for a selected CCL type are computer aggregated to determine a time-dependent failure distribution for the selected CCL type.

Component record processing for aircraft maintenance

A system to predict a startup condition of an auxiliary power unit (APU) of an aircraft includes a machine learning device configured to receive data including sensor data of the aircraft and weather forecast data of a destination airport. The machine learning device is also configured to process the data to generate a prediction regarding the startup condition and to generate a message based on the prediction. The message indicates that an alternate startup procedure of the APU is to be performed after the aircraft has landed at the destination airport to avoid an error condition associated with a primary startup procedure of the APU.

Auxiliary power unit startup condition prediction

Systems and methods for generating a sensor driven optimized maintenance program are provided. A first maintenance plan for an apparatus type is received; the first maintenance plan defining maintenance tasks for the apparatus type and defining intervals at which the maintenance tasks are to be performed. Historical sensor data, historical scheduled maintenance data, and historical unscheduled maintenance data are received and correlated to determine a predictive value of the sensor data. One or more maintenance optimization objectives of an operator of an apparatus of the apparatus type are received, and the sensor driven optimized maintenance program is generated, based at least on the predictive value of the sensor data and the maintenance optimization objectives. The sensor driven optimized maintenance program includes an adjusted one of the defined intervals.

Systems and methods for optimizing maintenance plans in the presence of sensor data

A method includes receiving a component history for a processor module, the component history including identities of host vehicles in a set of host vehicles in which the processor module was installed; receiving an operational history for the set of host vehicles for a time period the processor module was installed on the set of host vehicles; receiving indirect sensor measurements related to the set of host vehicles for the time period; receiving a part survival model that is based at least in part on a part status of a plurality of historical processor modules, the plurality of historical processor modules having a historical component history, a historical operational history, and historical indirect sensor measurements; and determining a survival probability of the processor module based at least in part on the component history, the operational history, the indirect sensor measurements, and the part survival model.

Systems and methods for processor module failure assessment

A computer device is provided. The computer device includes at least one memory and at least one processor in communication with the at least one memory. The at least one processor is programmed to receive a plurality of aircraft flight data associated with a plurality of aircraft and determine one or more non-operational gaps for each aircraft. The non-operational gap represents a series of consecutive non-operating days for the aircraft. The at least one processor is also programmed to compare the one or more non-operational gaps for the plurality of aircraft based on each aircraft's corresponding in-service date, detect a plurality of anchors in the plurality of aircraft flight leg data, compare the one or more non-operational gaps for the plurality of aircraft to the plurality of anchors, and determine a future maintenance event for a first aircraft based on the comparison.

Growing community of inventors

Seattle, WA, United States of America

Shervin Beygi