The Boeing Company

The Boeing Compoany

Changzhou Wang

Guijun Wang

Haiqin Wang

Jun Yuan

Jai Joon Choi

Rodolfo Acuna Santiago

Alice Chen

Ali Bahrami

Robert J Winig

Mingyan Li

William R Ferng

Sharon Filipowski Arroyo

Yong-Long Calvin Ling

Brian Predmore

Casey Fung

Darren Puigh

Omid B Nakhjavani

Anne Kao

Darren Brian Macer

Alimuddin Mohammad

Raju Shankar Mattikalli

Robert E Cranfill

Arnold W Nordsieck

Sidney Ly

Hamid Reza Nikjou

Greg Jackson

Rodney Allen Tjoelker

Stephen A Uczekaj

Nicholas Multari

William Suhail Hanna

Yichi C Pierce

Jihad Boulos

Mark Mazarek

Lesley Quach

Shiang-Yu Lee

Steve Uczekaj

Victor Lukasik

Jingwen Jin

Mark A Mazarek

Dongliang Lin

Brian K Predmore

Victor J Lukasik

Casey K Fung

Nicholas J Multari

A method, apparatus, system for managing a maintenance for a component in a vehicle. Sensor data is received for the vehicle. Target parameters are predicted using behavior machine learning models trained using first training data to predict the target parameters for a normal behavior of the component operating in a tolerance, wherein the target parameters characterize behavior of the component. Prediction metrics are determined from predicted values for the target parameters predicted by behavior machine learning models and actual values for the target parameters. Whether the component will fall out of the tolerance after a time period is predicted using the prediction metrics and a maintenance machine learning model trained using second training data to predict whether the maintenance is needed for the component, wherein the second training data comprises historical prediction metrics determined for the target parameters.

Component maintenance prediction system with behavior modeling

A computing device predicts whether a given component currently installed on a vehicle should be removed from the vehicle, and if so, identifies the location of the given component on the vehicle. The prediction is based on a prediction model that is generated by the computing device using maintenance data associated with the maintenance of components currently installed on, and/or previously removed from, the vehicle, as well as removal data associated with the previous removal of the same type of components from the vehicle. Information associated with the prediction is then output graphically to a display so that an operator can effect the removal of the component.

Multisource component removal location labeling

Aspects of the present disclosure provide a method and apparatus for predicting noncompliance conditions of rotating machinery in aerial vehicles. Embodiments include receiving records related to historical noncompliance conditions of a plurality of rotating machines. The records include deceleration time values related to the plurality of rotating machines. Embodiments include generating, based at least on the deceleration time values and the historical noncompliance conditions, a predictive model. Embodiments include receiving sensor data related to a rotating machine of an aerial vehicle. Embodiments include determining, based on the sensor data, a series of deceleration time values for the rotating machine. Embodiments include using the predictive model to determine whether a noncompliance condition is predicted to occur for the rotating machine based on the series of deceleration time values.

Predicting noncompliance conditions of rotating machinery in aerial vehicles

A method for performing an operation on a flight sensor parameter includes receiving instructions indicating a description of a flight sensor parameter and an operation to be performed on the flight sensor parameter. The method includes generating executable code based on the instructions indicating the description and the operation. The method includes, after generating the executable code, associating the executable code with flight sensor data from one or more sensors. The flight sensor parameter includes a variable of the flight sensor data. The method further includes executing the executable code at a processor using the flight sensor data as an input to generate an output that indicates results of the operation.

System and method for performing operations on flight sensor data

Disclosed herein is a method that comprises detecting that a rate of decrease in fuel quantity for an aircraft exceeds a previously-determined baseline rate of decrease in fuel quantity for the aircraft by a threshold rate during a corresponding segment of flight of the aircraft. The method also comprises determining that a fuel jettison setting for the aircraft is enabled in response to the detected increase in the rate of decrease in fuel quantity. The method further comprises determining that an angle of one or more flaps of the aircraft satisfies a threshold angle. The method additionally comprises generating an alert indicating possible fuel contamination of the one or more flaps due to jettisoned fuel.

Detecting a fuel jettison event

A method includes obtaining, at a processor, first data associated with operation of a vehicle. The first data includes sensor data from sensor(s) onboard the vehicle and indicates one or more parameter values of a first parameter measured by the sensor(s) and one or more associated timestamps. The method includes determining, by the processor, a first amount of storage space associated with storing a first portion of the first data in accordance with a first storage scheme and a second amount of storage space associated with storing the first portion in accordance with a second storage scheme that is different than the first storage scheme. The method further includes storing the first portion of the first data in a memory in accordance with the first storage scheme based on the first amount of storage space satisfying a first threshold that is based on the second amount of storage space.

System and method for vehicle sensor data storage and analysis

A method includes obtaining data associated with operation of an aircraft and determining a first operational phase of the aircraft based on the data. The method includes identifying a candidate operational phase transition from the first operational phase to a candidate operational phase based on a first portion of the data satisfying a first condition associated with the candidate operational phase, the first portion of the data corresponding to a first time. The method includes evaluating a second portion of the data based on a second condition associated with the candidate operational phase, the second portion of the data corresponding to a second time that is subsequent to the first time. The method further includes, based on the second condition being satisfied, generating an operational phase transition indication that indicates an occurrence of an operational phase transition to the candidate operational phase at the first time.

System and method for operational phase detection

A method and system operable to perform the method is provided for control of an autonomous or unmanned system. The method includes obtaining a mission model, wherein the mission model comprises a goal and one or more assets that are used to accomplish the goal; producing, by a first hardware processor, a plan goal graph (PGG) model based on the mission model; transforming, by a second hardware processor, the PGG model into a Bayesian Network (BN) model; computing a feasibility to execute a plan and an achievability of accomplishing the goal; and providing control instructions to the one or more assets to be used to accomplish the goal.

System and method for transforming mission models from plan goal graph to Bayesian network for autonomous system control

A method, apparatus, and scheduling system for managing a mix of time-critical messages and general messages. Messages, which are referenced by message identifiers stored in a transmission queue buffer, are scheduled for transmission using a schedule configuration table. The schedule configuration table defines an order for processing a mix of time-critical messages and general messages. The messages are scheduled according to the characteristics for time-critical messages and general messages defined in columns of configuration tables and status tables. The messages that have been scheduled are transmitted from an end system in which the time-critical messages are prioritized during transmission over the general messages.

Integrated scheduling of general messages and time-critical messages

A method includes obtaining data associated with operation of a vehicle and determining a first operational phase of the vehicle based on the data. The method includes identifying a candidate operational phase transition from the first operational phase to a candidate operational phase based on a first portion of the data satisfying a first condition associated with the candidate operational phase, the first portion of the data associated with a first time. The method includes evaluating a second portion of the data based on a second condition associated with the candidate operational phase, the second portion of the data associated with a second time that is subsequent to the first time. The method further includes, based on the second condition being satisfied, generating an operational phase transition indication associated with the first time and that indicates an operational phase transition to the candidate operational phase.

A system for determining a worst case latency for a specific information flow that is part of a plurality of information flows and a worst case backlog for a specific queue that is part of a plurality of queues is disclosed. The plurality of information flows and plurality of queues are part of a configuration. The system performs operations including determining a maximum busy period length for the configuration. The operations include determining a set of candidate starting times for the configuration based on the maximum busy period length. The operations further include determining a maximum layout for a plurality of information flows within the configuration. The operations include updating the worst case latency and the worst case backlog based on the maximum layout. Finally, the operations include determining the worst case latency for the specific information flow and the worst case backlog for a specific queue.

System and method for identifying performance characteristics in asynchronous networks

A dynamic network and a method for performing data analysis within a dynamic network. A query request generated by a root node in the dynamic network is propagated through other nodes in the dynamic network in a number of request messages. A number of response messages responding to the query request are received at the root node from the other nodes in the dynamic network. Data analysis is performed using data contained in the number of response messages as the number of response messages is received. A request index that keeps count of the number of request messages propagated through the dynamic network is updated using a tracking parameter in each of the number of response messages.

Performing dynamic data analysis within a dynamic network

Methods and systems for use in validating input data in a computing system. Input data associated with a destination software application, such as a database, is received at a computing system. The input data is forwarded to an intermediate software application, such as a web application. When the input includes one or more patterns, a query produced by the intermediate software application based on the input data is validated, such as by comparing the structure of the query to one or more expected query structures. If the validation succeeds, the query is forwarded to the destination software application. Otherwise, the query is discarded.

Methods and systems for validating input data

Methods and systems for information state sharing and consistency maintenance in a distributed and decentralized network are presented. At a first node of a network, a first information state message (ISM) in a hypothesis phase is generated. The first ISM is propagated to at least one node of a spanning tree of the network, the spanning tree having a root at the first node. A verification opinion is received from the at least one node indicating if a state in the first ISM is verified by the at least one node. A consensus regarding the state in the first ISM is determined based on the verification opinion from the at least one node. A second ISM indicating a confirmed phase is propagated to the spanning tree if the consensus on the state of the ISM is reached.

Methods and systems for shared awareness through local observations and global state consistency in distributed and decentralized systems

One or more systems, methods, routines and/or techniques for mission-driven autonomous and adaptive resource management, for example to achieve mission objectives in Quality of Service-managed networked systems, are described. One or more resource allocation algorithms and one or more associated control architectures including component services may be used. A system and/or method may collect input parameters, evaluate system workloads and performance metrics, optimize resource allocations, and adapt to changing workloads and performance metrics to achieve mission objectives. One or more objective functions, one or more constraints and one or more optimization algorithms may be utilized to achieve optimal allocation of resources to maximize the delivered value of an objective function and/or the system. The systems, methods, routines and/or techniques described herein may be autonomic and self-adaptive without requiring human administrators to pre-determine parameters (e.g., demands on resources or performance properties) for specific applications, processes and/or clients.

Mission-driven autonomous and adaptive resource management

Growing community of inventors

Bellevue, WA, United States of America

Changzhou Wang