Bootstrap data methodology for sequential hybrid model building

• US 20060047487A1
• Filed: 08/26/2004
• Published: 03/02/2006
• Est. Priority Date: 08/26/2004
• Status: Active Grant

• Current Assignee: Rtx Corporation
• Original Assignee: United Technologies Corporation (Rtx Corporation)
• Inventors: Volponi, Allan J., Brotherton, Thomas
• Granted Patent: US 7,277,838 B2
• Time in Patent Office: Days
• US Class Current: 703/9
• CPC Class Codes: G05B 17/02 electric

Abstract

A method for modeling engine operation comprising the steps of: 1. collecting a first plurality of sensory data, 2. partitioning a flight envelope into a plurality of sub-regions, 3. assigning the first plurality of sensory data into the plurality of sub-regions, 4. generating an empirical model of at least one of the plurality of sub-regions, 5. generating a statistical summary model for at least one of the plurality of sub-regions, 6. collecting an additional plurality of sensory data, 7. partitioning the second plurality of sensory data into the plurality of sub-regions, 8. generating a plurality of pseudo-data using the empirical model, and 9. concatenating the plurality of pseudo-data and the additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least one of the plurality of sub-regions.

Claims

1. A method for modeling engine operation comprising the steps of:

1. collecting a first plurality of sensory data;

2. partitioning a flight envelope into a plurality of sub-regions;

3. assigning said first plurality of sensory data into said plurality of sub-regions;

4. generating an empirical model of at least one of said plurality of sub-regions;

5. generating a statistical summary model for at least one of said plurality of sub-regions;

6. collecting an additional plurality of sensory data;

7. partitioning said second plurality of sensory data into said plurality of sub-regions;

8. generating a plurality of pseudo-data using said empirical model; and

9. concatenating said plurality of pseudo-data and said additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least one of said plurality of sub-regions.

2. The method of claim 1 comprising the additional step of repeating steps 5 through 8 until an updated empirical model and an updated statistical summary model is generated for each of said plurality of sub-regions.

3. The method of claim 1 wherein said collecting said sensory data comprises collecting sensory data from a gas turbine engine.

4. The method of claim 1 wherein said partitioning said first plurality of sensory data comprises the steps of:

selecting a first sensory parameter and a second sensory parameter;

plotting each of said plurality of sensory data by using said first sensory parameter as a first axis and said second sensory parameter as a second axis;

dividing said first axis and said second axis into a plurality of subdivisions to create a grid comprising a plurality of sub-regions.

5. The method of claim 4 wherein said selecting said first sensory parameter and said second sensory parameter comprises selecting ambient pressure and Reynold'"'"'s Index.

6. The method of claim 1 wherein said generating said empirical model comprises generating a multi-level perceptron artificial neural network (MLP ANN).

7. The method of claim 1 wherein said generating said empirical model comprises concatenating a plurality of said empirical models each corresponding to one of said plurality of sub-regions.

8. The method of claim 1 wherein said generating said statistical summary model comprises generating a radial basis function (RBF) ANN.

9. The method of claim 1 wherein collecting said plurality of sensory data comprises collecting a plurality of residuals each formed from the difference between an engine measurement and an output of a physical model of said engine.

14. The method of claim 1 wherein collecting said plurality of sensory data comprises collecting a plurality of residuals each formed from the difference between an engine measurement and an output of a physical model of said engine.

10. A method for modeling engine operation comprising the steps of:

collecting a first plurality of sensory data;

partitioning a flight envelope into a plurality of sub-regions;

assigning said first plurality of sensory data into said plurality of sub-regions;

generating an empirical model of a portion of said plurality of sensory data;

generating a statistical summary model for said portion of said plurality of sensory data;

collecting an additional plurality of sensory data;

generating a plurality of pseudo-data using said empirical model; and

concatenating said plurality of pseudo-data and said additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least a portion of said sensory data.

11. The method of claim 10 wherein said collecting said sensory data comprises collecting sensory data from a gas turbine engine.

12. The method of claim 10 wherein said generating said empirical model comprises generating a multi-level perceptron artificial neural network (MLP ANN).

13. The method of claim 10 wherein said generating said statistical summary model comprises generating a radial basis function (RBF) ANN.

15. An apparatus for modeling engine operation comprising:

means for collecting a first plurality of sensory data;

means for partitioning said first plurality of sensory data into a plurality of sub-regions;

means for generating an empirical model of at least one of said plurality of sub-regions;

means for generating a statistical summary model for at least one of said plurality of sub-regions;

means for collecting an additional plurality of sensory data;

means for partitioning said second plurality of sensory data into said plurality of sub-regions;

means for generating a plurality of pseudo-data using said empirical model; and

means for concatenating said plurality of pseudo-data and said additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least one of said plurality of sub-regions.

16. A method of constructing an empirical model, comprising the steps of:

1. collecting a first plurality of sensory data;

2. partitioning an operating envelope into a plurality of sub-regions;

3. assigning said first plurality of sensory data into said plurality of sub-regions;

4. generating an empirical model of at least one of said plurality of sub-regions;

5. generating a statistical summary model for at least one of said plurality of sub-regions;

6. collecting an additional plurality of sensory data;

7. partitioning said second plurality of sensory data into said plurality of sub-regions;

8. generating a plurality of pseudo-data using said empirical model; and

9. concatenating said plurality of pseudo-data and said additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least one of said plurality of sub-regions.