APPARATUS AND METHOD FOR MODEL ADAPTATION

• US 20160195857A1
• Filed: 09/06/2013
• Published: 07/07/2016
• Est. Priority Date: 09/06/2013
• Status: Active Grant

• Current Assignee: GE Intelligent Platforms Incorporated (Emerson Electric Company)
• Original Assignee: GE Intelligent Platforms Incorporated (Emerson Electric Company)
• Inventors: GANDHI, Devang Jagdish, HERZOG, James Paul
• Granted Patent: US 10,295,965 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G05B 13/041 in which a variable is automatically adjusted to optimise the performance
• CPC Class Codes: G05B 23/0262 Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred

Abstract

A vector of actual sensor values is received. A maturity of a model is determined and the maturity is defined for sensors. A function that transLates model maturity to model range inhibition measure is determined. A model range inhibition (MRI) measure is determined. An MRI limit based upon the MRI measure is determined. The received vector is compared to the MRI limit and the model is selectively changed based upon the comparing. In other aspects, vectors are received having actual values of driver and response sensors. A function that provides a set of boundaries between acceptable observations and unacceptable observations is also determined. Measures of similarity between vectors are determined. The measures of similarity and the function are compared and the model is selectively changed based upon the comparing.

Claims

1. A method of determining whether to modify a process model, the method comprising:

receiving a vector of actual sensor values;

determining a maturity of a model, the maturity being defined for each of a plurality of sensors and further defined in an upward direction and a downward direction for each sensor;

determining a function that translates model maturity to model range inhibition measure;

determining a model range inhibition (MRI) measure based upon the maturity of the model and the determined function;

determining an MRI limit based upon the MRI measure; and

comparing the received vector to the MRI limit and selectively changing the model based upon the comparing.

2. The method of claim 1 further comprising:

receiving a first vector, the first vector having actual values for driver sensors;

receiving a second vector, the second vector having actual values for response sensors;

receiving a third vector, the third vector having an estimate values for driver sensors;

receiving a fourth vector, the fourth vector having an estimate values for response sensors;

determining a function that provides a set of boundaries between acceptable observations and unacceptable observations;

determining a first measure of similarity between the first vector and the third vector;

determining a second measure of similarity between the second vector and the fourth vector; and

comparing the first measure of similarity, the second measure of similarity, and the function and selectively changing the model based upon the comparing.

3. The method of claim 1 further comprising determining whether a component represented by the model is near failure.

4. The method of claim 3 further comprising generating an alert to a user when the component is near failure.

5. The method of claim 4 further comprising presenting the alert to a user on a graphical display medium.

6. A method of determining whether to modify a process model, the method comprising:

receiving a first vector, the first vector having actual values for driver sensors;

receiving a second vector, the second vector having actual values for response sensors;

receiving a third vector, the third vector having an estimate values for driver sensors;

receiving a fourth vector, the fourth vector having an estimate values for response sensors;

determining a function that provides a set of boundaries between acceptable observations and unacceptable observations;

determining a first measure of similarity between the first vector and the third vector;

determining a second measure of similarity between the second vector and the fourth vector; and

comparing the first measure of similarity, the second measure of similarity, and the function and selectively changing a model based upon the comparing.

7. The method of claim 6 further comprising determining whether a component represented by the model is near failure.

8. The method of claim 7 further comprising generating an alert to a user when the component is near failure.

9. The method of claim 8 further comprising presenting the alert to a user on a graphical display medium.

10. An apparatus that is configured to determine whether to modify a process model, the apparatus comprising:

an interface having an input and an output, the input configured to receive a vector of actual sensor values and a maturity of a model, the maturity being defined for each of a plurality of sensors and further defined in an upward direction and a downward direction for each sensor;

a processor, the processor coupled to the interface, the processor configured to determine a model range inhibition (MRI) measure based upon the maturity of the model and the determined function, the processor configured to determining an MRI limit based upon the MRI measure, and compare the received vector to the MRI limit, the processor configured to selectively changing the model based upon the comparing via one or more control signals sent at via output.

11. The apparatus of claim 10 wherein the interface is configured to further receive at the input a first vector, the first vector having actual values for driver sensors, a second vector, the second vector having actual values for response sensors, a third vector, the third vector having an estimate values for driver sensors, a fourth vector, the fourth vector having an estimate values for response sensors;

and a function that provides a set of boundaries between acceptable observations and unacceptable observations;

wherein the processor is configured to determine a first measure of similarity between the first vector and the third vector, and a second measure of similarity between the second vector and the fourth vector; and

wherein the processor is further configured to compare the first measure of similarity, the second measure of similarity, and the function and selectively change the model based upon the comparison.

12. The apparatus of claim 10 wherein the processor is configured to determine whether a component represented by the model is near failure.

13. The apparatus of claim 12 wherein the processor is configured to generate an alert to a user at the output when the component is near failure.

14. The apparatus of claim 13 wherein the alert is presented to a user on a graphical display medium.