Method of sequential kernel regression modeling for forecasting and prognostics

• US 9,256,224 B2
• Filed: 07/19/2011
• Issued: 02/09/2016
• Est. Priority Date: 07/19/2011
• Status: Active Grant

• Current Assignee: GE Intelligent Platforms Incorporated (Emerson Electric Company)
• Original Assignee: GE Intelligent Platforms Incorporated (Emerson Electric Company)
• Inventors: Herzog, James P.
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Gonzales, Vincent
• Application Number:
  US13/186,200
• Publication Number:
  US 20130024416A1
• Time in Patent Office: 1,666 Days
• Field of Search: 706/62
• US Class Current: 1/1
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models

Abstract

A method for determining the future operational condition of an object includes obtaining reference data that indicates the normal operational state of the object, and obtaining input pattern arrays. Each input pattern array has a plurality of input vectors, while each input vector represents a time point and has input values representing a plurality of parameters indicating the current condition of the object. At least one processor generates estimate values based on a calculation that uses an input pattern array and the reference data to determine a similarity measure between the input values and reference data. The estimate values, in the form of an estimate matrix, include at least one estimate vector of inferred estimate values, and represents at least one time point that is not represented by the input vectors. The inferred estimate values are used to determine a future condition of the object.

Claims

1. A method for determining the future operational condition of an object, comprising:

obtaining input matrices of the input matrices having a plurality of input vectors, each of the plurality of input vectors representing a time point and having input values representing a plurality of parameters indicating the current condition of the object obtained from one or more first sensors at the time point, each input vector arranged and maintained in a predetermined and ordered time relationship with the others; and

obtaining reference matrices that indicate the normal operational state of the object, one or more of the reference matrices being generated from reference data, each of the plurality of reference matrices having a same number of input vectors as input matrix, wherein each input vector represents a time point and has input values representing the same parameters as those in input matrix, each input vector arranged and maintained in the predetermined and ordered time relationship with the others as those in the input matrix;

generating, by at least one processor, estimate values based on a calculation that uses one of the input matrices and one or more of the reference matrices to determine a matrix similarity measure between the input values and reference data, the matrix similarity measure accounting for the predetermined and ordered time relationship, wherein the estimate values are in the form of an estimate matrix that is calculated using the input matrix, the reference matrix, and a time weight value matrix with a plurality of contribution elements, each contribution element representing a similarity contribution at a discrete moment in time, the estimate matrix includes at least one estimate vector of inferred estimate values for at least one future point in time or a plurality of second sensors being different from the one or more first sensors, wherein estimate matrices include at least one additional value that represents parameters which are not represented by the input matrix and which indicate the condition of the object, each estimate vector arranged and maintained in the predetermined and ordered time relationship with the others; and

using the inferred estimate values to determine a future condition of the object.

2. The method of claim 1 wherein the estimate matrices only include estimate vectors that represent time points that are not represented by the input vectors.

3. The method of claim 1 wherein the estimate matrices include at least one estimate vector that represents the same time point represented by the input vectors and at least one estimate vector that represents a time point that is not represented by the input vectors.

4. The method of claim 1 wherein the estimate matrices include estimate values that represent parameters that indicate the condition of the object and that are not represented by the input values.

5. The method of claim 1 wherein each estimate matrix represents a current time point and time points not represented by the input vectors and that are succeeding time points relative to the current time point.

6. The method of claim 1 wherein the reference data used in the calculation with the weight values comprises reference values that represent time points that are not represented by the input pattern arrays.

7. The method of claim 6 wherein the reference data used in the calculation with the weight values represents a primary current time point, and wherein the time points not represented by the input pattern arrays are succeeding time points relative to the current time point.

8. The method of claim 1 wherein the same time point is represented in multiple estimate matrices.

9. The method of claim 1 wherein using the inferred estimate values comprises using the most recent estimate matrix to update the inferred estimate values for use to determine the condition of the object.

10. The method of claim 1 wherein using the inferred estimate values comprises providing values for a single estimate vector to represent a single time point across multiple estimate matrices.

11. The method of claim 10 wherein the single estimate vector is generated by determining an average, a weighted average, or a weighted norm of all of the estimate vectors at the single time point.

12. The method of claim 1 wherein using the inferred estimate values comprises providing values for a single estimate vector to represent each estimate matrix.

13. The method of claim 12 wherein the single estimate vector is generated by taking an average, weighted average, or weighted norm of the estimate vectors within the estimate matrix.

14. The method of claim 1 wherein using the inferred estimate values comprises forming a trend line for at least one parameter represented by the inferred estimate values to indicate the expected behavior of the object.

15. The method of claim 14 comprising forming a new trend line with each new estimate matrix.

16. The method of claim 14 comprising forming boundary trend lines to define a range of expected behavior of the object.

17. The method of claim 16 comprising forming an upper boundary trend line with maximum inferred estimate values at the time points, and a lower boundary trend line with minimum inferred estimate values at the time points.