SYSTEM AND METHOD FOR ASSET FLEET MONITORING AND PREDICTIVE DIAGNOSTICS USING ANALYTICS FOR LARGE AND VARIED DATA SOURCES

• US 20160282847A1
• Filed: 09/30/2015
• Published: 09/29/2016
• Est. Priority Date: 03/25/2015
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Germann, David J., Light, Marc, Stewart, Gregory E., Mylaraswamy, Dinkar
• Granted Patent: US 10,503,145 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B23K 11/00 Resistance welding; Severing by resistance heating
• CPC Class Codes: G05B 19/4065 Monitoring tool breakage, life or condition
• CPC Class Codes: G05B 2219/34427 Diagnostic, monitoring incorporated in controller
• CPC Class Codes: G05B 23/0216 Human interface functionality, e.g. monitoring system providing help to the user in the selection of tests or in its configuration
• CPC Class Codes: G05B 23/0243 model based detection method, e.g. first-principles knowledge model
• CPC Class Codes: Y02P 90/80 Management or planning

Abstract

A method includes receiving information associated with operation of multiple pieces of industrial equipment at multiple sites. The multiple pieces of industrial equipment are of a same or similar type, and the information represents different types of data including operational data associated with the multiple pieces of industrial equipment and text-based data associated with the multiple pieces of industrial equipment. The method also includes analyzing the information to identify correlations in the information associated with one or more conditions involving the pieces of industrial equipment. The method further includes, based on the analyzing, generating one or more monitoring rules or routines to be used to identify the one or more conditions. The multiple pieces of industrial equipment could include machines with rotating components, machines with heat transfer equipment, or general process equipment.

Claims

1. A method comprising:

receiving information associated with operation of multiple pieces of industrial equipment at one or more sites, the multiple pieces of industrial equipment being of a same or similar type, the information comprising different types of data including operational data associated with the multiple pieces of industrial equipment and text-based data associated with the multiple pieces of industrial equipment;

analyzing the information to identify correlations in the information associated with one or more conditions involving the pieces of industrial equipment; and

based on the analyzing, generating one or more monitoring rules or routines to be used to identify the one or more conditions.

2. The method of claim 1, further comprising:

receiving additional information comprising at least one of;

(i) more information associated with the operation of the pieces of industrial equipment and (ii) information associated with operation of additional pieces of industrial equipment; and

generating one or more new or updated monitoring rules or routines using the additional information.

3. The method of claim 1, wherein analyzing the information comprises at least one of:

clustering the information to identify behavioral characteristics of the pieces of industrial equipment;

processing the information using machine learning to identify possible causes of abnormal behavioral characteristics and probabilities of the abnormal behavioral characteristics; and

performing text mining to identify root causes and solutions for the abnormal behavioral characteristics and to catalogue behavioral characteristics of the pieces of industrial equipment.

4. The method of claim 1, wherein analyzing the information comprises performing statistical modeling augmented with at least one of:

one or more physical first principles models and one or more semi-empirical models.

5. The method of claim 1, wherein the multiple pieces of industrial equipment comprise at least one of:

machines with rotating components, machines with heat transfer equipment, and general process equipment.

6. The method of claim 1, wherein:

the operational data comprises real-time or time-stamped instrumentation data associated with the multiple pieces of industrial equipment; and

the text-based data comprises maintenance information associated with the multiple pieces of industrial equipment.

7. The method of claim 1, wherein the information associated with the operation of the pieces of industrial equipment comprises information associated with historical operations of the pieces of industrial equipment.

8. The method of claim 1, wherein the one or more conditions involving the pieces of industrial equipment comprise one or more faults with the pieces of industrial equipment.

21. The method of claim 1, wherein:

the information is received from multiple sites associated with multiple organizations; and

the information is received and analyzed using one of;

a server remote from the multiple sites; and

a computing cloud.

9. A system comprising:

at least one interface configured to receive information associated with operation of multiple pieces of industrial equipment at one or more sites, the multiple pieces of industrial equipment being of a same or similar type, the information comprising different types of data including operational data associated with the multiple pieces of industrial equipment and text-based data associated with the multiple pieces of industrial equipment; and

at least one processing device configured to;

analyze the information to identify correlations in the information associated with one or more conditions involving the pieces of industrial equipment; and

based on the analysis, generate one or more monitoring rules or routines to be used to identify the one or more conditions.

10. The apparatus of claim 9, wherein:

the at least one interface is further configured to receive additional information comprising at least one of;

(i) more information associated with the operation of the pieces of industrial equipment and (ii) information associated with operation of additional pieces of industrial equipment; and

the at least one processing device is further configured to generate one or more new or updated monitoring rules or routines using the additional information.

11. The apparatus of claim 9, wherein the at least one processing device is configured to analyze the information by at least one of

clustering the information to identify behavioral characteristics of the pieces of industrial equipment;

processing the clustered information using machine learning to identify possible causes of abnormal behavioral characteristics and probabilities of the abnormal behavioral characteristics; and

performing text mining to identify root causes and solutions for the abnormal behavioral characteristics and to catalogue behavioral characteristics of the pieces of industrial equipment.

12. The apparatus of claim 9, wherein the at least one processing device is configured to analyze the information by performing statistical modeling augmented with at least one of:

one or more physical first principles models and one or more semi-empirical models.

13. The apparatus of claim 9, wherein:

the operational data comprises real-time or time-stamped instrumentation data associated with the multiple pieces of industrial equipment; and

the text-based data comprises maintenance information associated with the multiple pieces of industrial equipment.

14. The apparatus of claim 9, wherein the one or more conditions involving the pieces of industrial equipment comprise at least one of:

one or more user-defined conditions involving the pieces of industrial equipment; and

one or more faults with the pieces of industrial equipment.

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

obtain information associated with operation of multiple pieces of industrial equipment at one or more sites, the multiple pieces of industrial equipment being of a same or similar type, the information comprising different types of data including operational data associated with the multiple pieces of industrial equipment and text-based data associated with the multiple pieces of industrial equipment;

analyze the information to identify correlations in the information associated with one or more conditions involving the pieces of industrial equipment; and

based on the analysis, generate one or more monitoring rules or routines to be used to identify the one or more conditions.

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:

receive additional information comprising at least one of;

(i) more information associated with the operation of the pieces of industrial equipment and (ii) information associated with operation of additional pieces of industrial equipment; and

generate one or more new or updated monitoring rules or routines using the additional information.

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

computer readable program code that when executed causes the at least one processing device to at least one of;

cluster the information to identify behavioral characteristics of the pieces of industrial equipment;

process the clustered information using machine learning to identify possible causes of abnormal behavioral characteristics and probabilities of the abnormal behavioral characteristics; and

perform text mining to identify root causes and solutions for the abnormal behavioral characteristics and to catalogue behavioral characteristics of the pieces of industrial equipment.

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

computer readable program code that when executed causes the at least one processing device to perform statistical modeling augmented with at least one of;

one or more physical first principles models and one or more semi-empirical models.

19. The non-transitory computer readable medium of claim 15, wherein:

the operational data comprises real-time or time-stamped instrumentation data associated with the multiple pieces of industrial equipment; and

the text-based data comprises maintenance information associated with the multiple pieces of industrial equipment.

20. A method comprising:

providing first information associated with operation of at least one piece of industrial equipment at a site, the first information comprising different types of data including operational data associated with the at least one piece of industrial equipment and text-based data associated with the at least one piece of industrial equipment;

receiving one or more monitoring rules or routines, the one or more monitoring rules or routines based on second information associated with operation of multiple pieces of industrial equipment at multiple sites, the multiple pieces of industrial equipment being of a same or similar type; and

identifying any conditions with the at least one piece of industrial equipment using the one or more monitoring rules or routines.