METHOD AND SYSTEM FOR REAL-TIME DAMAGE PREDICTION AND QUANTIFICATION

• US 20180314232A1
• Filed: 05/01/2017
• Published: 11/01/2018
• Est. Priority Date: 05/01/2017
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Srinivasan, Sridhar
• Granted Patent: US 10,642,249 B2
• Time in Patent Office: Days
• CPC Class Codes: G05B 19/4065 Monitoring tool breakage, life or condition
• CPC Class Codes: G05B 2219/42155 Model
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0289 Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence

Abstract

A method for real-time damage prediction includes obtaining a damage prediction model that mathematically models expected damage to equipment in an industrial process based on a plurality of process parameters. The method also includes obtaining real-time state information for at least one of the plurality of process parameters. The method further includes determining, based on the real-time state information and the damage prediction model, a real-time prediction of damage to at least one component of the equipment in the industrial process. The method may also include obtaining historical data for the plurality of process parameters, and the real-time prediction of damage can be based on the historical data, the real-time state information, and the damage prediction model. The method may further include identifying and adjusting a high limit and a low limit for the at least one of the plurality of process parameters.

Claims

1. A method for real-time damage prediction comprising:

obtaining a damage prediction model that mathematically models expected damage to equipment in an industrial process based on a plurality of process parameters;

obtaining real-time state information for at least one of the plurality of process parameters; and

determining, based on the real-time state information and the damage prediction model, a real-time prediction of damage to at least one component of the equipment in the industrial process.

2. The method of claim 1, further comprising:

obtaining historical data for the plurality of process parameters;

wherein determining the real-time prediction of damage comprises determining the real-time prediction of damage based on the historical data, the real-time state information, and the damage prediction model.

3. The method of claim 1, further comprising:

determining at least one action for altering the real-time prediction of damage; and

transmitting a notification identifying the at least one action to an operator.

4. The method of claim 1, further comprising:

generating, based on the real-time prediction of damage, at least one notification; and

transmitting the at least one notification to an operator.

5. The method of claim 1, further comprising:

identifying a high limit and a low limit for the at least one of the plurality of process parameters;

wherein determining the real-time prediction of damage includes determining, based on the real-time state information, whether the at least one of the plurality of process parameters has passed the high limit or the low limit.

6. The method of claim 5, further comprising:

adjusting at least one of the high limit and the low limit for the at least one of the plurality of process parameters.

7. The method of claim 1, further comprising:

storing the real-time prediction of damage in a memory.

8. An apparatus for real-time damage prediction comprising:

at least one memory configured to store a damage prediction model that mathematically models expected damage to equipment in an industrial process based on a plurality of process parameters; and

at least one processing device configured to;

obtain real-time state information for at least one of the plurality of process parameters; and

determine, based on the real-time state information and the damage prediction model, a real-time prediction of damage to at least one component of the equipment in the industrial process.

9. The apparatus of claim 8, further comprising at least one network interface configured to receive historical data for the plurality of process parameters;

wherein the at least one processing device is configured to determine the real-time prediction of damage based on the historical data, the real-time state information, and the damage prediction model.

10. The apparatus of claim 8, wherein the at least one processing device is further configured to determine at least one action for altering the real-time prediction of damage;

further comprising at least one network interface configured to transmit a notification identifying the at least one action to an operator.

11. The apparatus of claim 8, wherein the at least one processing device is further configured to generate, based on the real-time prediction of damage, at least one notification;

and

further comprising at least one network interface configured to transmit the at least one notification to an operator.

12. The apparatus of claim 8, wherein the at least one processing device is further configured to:

identify a high limit and a low limit for the at least one of the plurality of process parameters;

determine, based on the real-time state information, whether the at least one of the plurality of process parameters has passed the high limit or the low limit.

13. The apparatus of claim 12, wherein the at least one processing device is further configured to adjust the high limit and the low limit for the at least one of the plurality of process parameters.

14. The apparatus of claim 8, wherein the at least one processing device is further configured to store the real-time prediction of damage in the at least one memory.

15. A non-transitory computer readable medium containing computer readable program code that when executed causes at least one processing device to:

obtain a damage prediction model that mathematically models expected damage to equipment in an industrial process based on a plurality of process parameters;

obtain real-time state information for at least one of the plurality of process parameters; and

determine, based on the real-time state information and the damage prediction model, a real-time prediction of damage to at least one component of the equipment in the industrial process.

16. The non-transitory computer readable medium of claim 15, further containing computer readable program code that when executed causes the at least one processing device to obtain historical data for the plurality of process parameters;

wherein the computer readable program code that when executed causes the at least one processing device to determine the real-time prediction of damage comprises;

computer readable program code that when executed causes the at least one processing device to determine the real-time prediction of damage based on the historical data, the real-time state information, and the damage prediction model.

17. The non-transitory computer readable medium of claim 15, further containing computer readable program code that when executed causes the at least one processing device to:

determine at least one action for altering the real-time prediction of damage; and

transmit a notification identifying the at least one action to an operator.

18. The non-transitory computer readable medium of claim 15, further containing computer readable program code that when executed causes the at least one processing device to:

generate, based on the real-time prediction of damage, at least one notification; and

transmit the at least one notification to an operator.

19. The non-transitory computer readable medium of claim 15, further containing computer readable program code that when executed causes the at least one processing device to:

identify a high limit and a low limit for the at least one of the plurality of process parameters; and

determine, based on the real-time state information, whether the at least one of the plurality of process parameters has passed the high limit or the low limit.

20. The non-transitory computer readable medium of claim 19, further containing computer readable program code that when executed causes the at least one processing device to adjust at least one of the high limit and the low limit for the at least one of the plurality of process parameters.