Vehicle system prognosis device and method

• US 10,304,263 B2
• Filed: 12/13/2016
• Issued: 05/28/2019
• Est. Priority Date: 12/13/2016
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Martin, Charles E., Lu, Tsai-Ching, Murphy, Alice A., Wezdenko, Christopher R., Slaughter, Steve
• Primary Examiner(s): Heinle, Courtney D
• Assistant Examiner(s): Martinez Borrero, Luis A
• Application Number:
  US15/377,532
• Publication Number:
  US 20180165894A1
• Time in Patent Office: 896 Days
• Field of Search: 701 299, 701 321, 701 319, 701 302
• CPC Class Codes: G06F 18/21345 enforcing sparsity or involving a domain transformation
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G07C 5/08 Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A method for determining a vehicle system prognosis includes detecting a predetermined characteristic of a vehicle with one or more sensors, obtaining a plurality of sensor signals corresponding to the predetermined characteristic, receiving the plurality of sensor signals from the one or more sensors and determining an input time series of data based on the sensor signals, generating, a matrix of time series data based on the input time series of data, clustering the matrix of time series data based on predetermined clustering criteria into a predetermined number of clusters, generating a sparse temporal matrix based on the predetermined number of clusters, extracting extracted features that are indicative of an operation of a vehicle system from the sparse temporal matrix and determining an operational status of the vehicle system based on the extracted features, and communicating the operational status of the vehicle system to an operator or crew member of the vehicle.

Claims

1. A method for determining a vehicle system prognosis, the method comprising:

detecting a predetermined characteristic of a vehicle with one or more sensors onboard the vehicle;

obtaining a plurality of sensor signals corresponding to the predetermined characteristic from the one or more sensors;

receiving, with a processor onboard the vehicle, the plurality of sensor signals from the one or more sensors onboard the vehicle and determining, with the processor onboard the vehicle, an input time series of data based on the sensor signals;

generating, with the processor onboard the vehicle, a matrix of time series data based on the input time series of data;

clustering, with the processor onboard the vehicle, the matrix of time series data based on predetermined clustering criteria into a predetermined number of clusters;

generating a sparse temporal matrix, with the processor onboard the vehicle, based on the predetermined number of clusters, where each cluster comprises a hyperplane within the sparse temporal matrix;

extracting, with the processor onboard the vehicle, extracted features that are indicative of an operation of a vehicle system from the sparse temporal matrix based on data point behavior with respect to two or more hyperplanes within the sparse temporal matrix and determining an operational status of the vehicle system based on the extracted features; and

communicating, with the processor onboard the vehicle, the operational status of the vehicle system to an operator or crew member of the vehicle.

2. The method of claim 1, wherein the matrix of time series data exists in a data distribution space having a dimension corresponding to a number of input time series and a size of a time window used to determine the matrix of time series data.

3. The method of claim 1, wherein extracting the extracted features that are indicative of the operation of the vehicle system comprises monitoring a stability of data points within the predetermined number of clusters where a change in stability of the data points within the predetermined number of clusters is indicative of a transition to a fault in the vehicle system.

4. The method of claim 1, wherein extracting the extracted features that are indicative of the operation of the vehicle system comprises monitoring behavior of data points within the sparse temporal matrix with respect to an existence of the data points within one or more of the a predetermined number of clusters.

5. The method of claim 4, wherein the extracted features that are indicative of the operation of the vehicle system include a fracturing behavior of the data points where the data points serially transition between two or more clusters of the predetermined number of clusters.

6. The method of claim 5, wherein the fracturing behavior is indicative of a pre-transition to a fault in the vehicle system.

7. The method of claim 4, wherein the extracted features that are indicative of the operation of the vehicle system include a transition behavior of the data points where the data points permanently transition from one cluster to a different cluster.

8. The method of claim 7, wherein the transition behavior is indicative of a transition to a fault in the vehicle system.

9. The method of claim 1, wherein the predetermined number of clusters includes more than two temporally contiguous clusters.

10. A vehicle system prognosis device comprising:

one or more sensors onboard a vehicle, the one or more sensors being configured to detect a predetermined characteristic of the vehicle system and generate a plurality of sensor signals corresponding to the predetermined characteristic;

an indicator device; and

a processor onboard the vehicle, the processor being connected to the one or more sensors and the indicator device and being configured to

receive the plurality of sensor signals from the one or more sensors onboard the vehicle and determine an input time series of data based on the sensor signals;

generate a matrix of time series data based on the input time series of data;

cluster the matrix of time series data based on predetermined clustering criteria into a predetermined number of clusters;

generate a sparse temporal matrix based on the predetermined number of clusters, where each cluster comprises a hyperplane within the sparse temporal matrix;

extract extracted features that are indicative of an operation of a vehicle system from the sparse temporal matrix based on data point behavior with respect to two or more hyperplanes within the sparse temporal matrix and determine an operational status of the vehicle system based on the extracted features; and

communicate the operational status of the vehicle system to an operator or crew member of the vehicle through the indicator device.

11. The vehicle system prognosis device of claim 10, wherein the processor is configured to generate the matrix of time series data so that the matrix of time series data exists in a data distribution space having a dimension corresponding to a number of input time series and a size of a time window used to determine the matrix of time series data.

12. The vehicle system prognosis device of claim 10, wherein the processor is configured to extract the extracted features that are indicative of the operation of the vehicle system by monitoring a stability of data points within the predetermined number of clusters where a change in stability of the data points within the predetermined number of clusters is indicative of a transition to a fault in the vehicle system.

13. The vehicle system prognosis device of claim 10, wherein the processor is configured to extract the extracted features that are indicative of the operation of the vehicle system by monitoring behavior of data points within the sparse temporal matrix with respect to an existence of the data points within one or more of the a predetermined number of clusters.

14. The vehicle system prognosis device of claim 13, wherein the extracted features that are indicative of the operation of the vehicle system include a fracturing behavior of the data points where the data points serially transition between two or more clusters of the predetermined number of clusters.

15. The vehicle system prognosis device of claim 13, wherein the extracted features that are indicative of the operation of the vehicle system include a transition behavior of the data points where the data points permanently transition from one cluster to a different cluster.

16. A method for determining a vehicle system prognosis, the method comprising:

detecting a predetermined characteristic of a vehicle with one or more sensors onboard the vehicle;

obtaining a plurality of sensor signals corresponding to the predetermined characteristic from the one or more sensors;

receiving, with a processor onboard the vehicle, the plurality of sensor signals from the one or more sensors onboard the vehicle and determining, with the processor onboard the vehicle, an input time series of data based on the sensor signals;

generating, with the processor onboard the vehicle, a matrix of time series data within a data distribution space based on the input time series of data;

clustering, with the processor onboard the vehicle, the matrix of time series data based on predetermined clustering criteria into a predetermined number of data regions of the data distribution space;

generating a sparse temporal matrix, with the processor onboard the vehicle, based on data within the predetermined number of data regions, where each data region comprises a hyperplane within the sparse temporal matrix;

extracting, with the processor onboard the vehicle, extracted features that are indicative of an operation of a vehicle system from the sparse temporal matrix based on data point behavior with respect to at least two hyperplanes within the sparse temporal matrix and determining an operational status of the vehicle system based on the extracted features; and

communicating, with the processor onboard the vehicle, the operational status of the vehicle system to an operator or crew member of the vehicle.

17. The method of claim 16, wherein the predetermined number of data regions of the data distribution space comprises a predetermined number of subspaces within the data distribution space.

18. The method of claim 16, wherein extracting the extracted features that are indicative of the operation of the vehicle system comprises monitoring behavior of the data points within the sparse temporal matrix with respect to an existence of the data points within one or more of the at least two hyperplanes.

19. The method of claim 16, wherein the predetermined number of data regions of the data distribution space comprises a predetermined number of non-linear manifolds within the data distribution space.

20. The method of claim 16, wherein the predetermined number of data regions of the data distribution space comprise a predetermined number of localized regions within the data distribution space.