IP Library › Granted Patent US 10,699,556
Granted Patent B1
US 10,699,556 · App. 16/290,724 · Granted Jun 30, 2020

System and method for plant operation gap analysis and guidance solution

Inventors: Ramakrishnan Ganapathi (Bangalore, IN); Prangya Priyadarsini (Bangalore, IN); Anand Narayan (Uttarakhand, IN); Viraj Srivastava (New Delhi, IN)
Assignee: Honeywell International Inc.
G08B29/04G05B19/058G08B21/02G08B29/16G05B2219/14005
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,699,556
App. No.
16/290,724
Granted
Jun 30, 2020
Kind
B1
Abstract

A method includes receiving one or more operating conditions from one or more field devices of one or more industrial plants in response to receiving one or more alarm signals. The method also includes determining one or more industrial plant states based on the one or more operating conditions. The method further includes identifying one or more historical alarm episodes stored in one or more data stores based on the one or more industrial plant states. In addition, the method includes identifying one or more recommended historical alarm episodes of the one or more historical alarm episodes based on one or more benchmark metrics of the one or more historical alarm episodes. The method also includes generating the one or more recommended historical alarm episodes for display on a user interface.

Claims (75)

1. A method comprising:

receiving, by at least one processing device, one or more operating conditions from one or more field devices of one or more industrial plants in response to receiving one or more alarm signals;

determining, by the at least one processing device, one or more industrial plant states based on the one or more operating conditions;

identifying, by the at least one processing device, one or more historical alarm episodes stored in one or more data stores based on the one or more industrial plant states;

identifying, by the at least one processing device, one or more recommended historical alarm episodes of the one or more historical alarm episodes based on one or more benchmark metrics of the one or more historical alarm episodes; and

generating, by the at least one processing device, the one or more recommended historical alarm episodes for display on a user interface,

wherein the one or more benchmark metrics comprise at least one of:

an integral of a difference between an actual and alarm trip point during a span of an alarm of the alarm episode,

a quantity of operator actions that require a least amount of time to return one or more components of an industrial plant to a normal state from an alarm state,

a fewest quantity of operator actions to be performed to return one or more components of an industrial plant to a normal state from an alarm state,

a fewest quantity of additional adverse conditions that would be generated by performed operator actions to return one or more components of an industrial plant to a normal state from an alarm state, or

a fewest quantity of plant rules or engineering guidelines that need to be violated to return one or more components of an industrial plant to a normal state from an alarm state.

2. The method of claim 1 , wherein receiving, by the at least one processing device, the one or more operating conditions from the one or more field devices of the one or more industrial plants in response to receiving the one or more alarm signals comprises:

analyzing, by the at least one processing device, all operating conditions related to the one or more alarm signals; and

isolating, by the at least one processing device, the one or more operating conditions of all of the operating conditions based on one or more similarity patterns of the one or more operating conditions.

3. The method of claim 1 , wherein the one or more historical alarm episodes comprise an indication of one or more previously performed operator actions.

4. The method of claim 3 , further comprising:

after generating, by the at least one processing device, the one or more recommended historical alarm episodes for display on the user interface:

receiving, by the at least one processing device, an indication of one or more real-time operator actions;

comparing, by the at least one processing device, the one or more real-time operator actions with the one or more previously performed operator actions; and

categorizing, by the at least one processing device, the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions.

5. The method of claim 4 , wherein categorizing, by the at least one processing device, the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions further comprises:

categorizing, by the at least one processing device, the one or more real-time operator actions based on a time when the at least one processing device receives the one or more operating conditions and a time when the at least one processing device receives an indication of one or more normal operating conditions.

6. The method of claim 4 , wherein categorizing, by the at least one processing device, the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions further comprises:

categorizing, by the at least one processing device, the one or more real-time operator actions based on a quantity of the one or more real-time operator actions received in the indication of the one or more real-time operator actions and a quantity of the one or more previously performed operator actions.

7. An apparatus comprising:

a memory; and

at least one processor configured to:

receive one or more operating conditions from one or more field devices of one or more industrial plants in response to receiving one or more alarm signals,

determine one or more industrial plant states based on the one or more operating conditions,

identify one or more historical alarm episodes stored in one or more data stores based on the one or more industrial plant states,

identify one or more recommended historical alarm episodes of the one or more historical alarm episodes based on one or more benchmark metrics of the one or more historical alarm episodes, and

generate the one or more recommended historical alarm episodes for display on a user interface,

wherein the one or more benchmark metrics comprise at least one of:

an integral of a difference between an actual and alarm trip point during a span of an alarm of the alarm episode,

a quantity of operator actions that require a least amount of time to return one or more components of an industrial plant to a normal state form an alarm state,

a fewest quantity of operator actions to be performed to return one or more components of an industrial plant to normal state from an alarm state,

a fewest quantity of additional adverse conditions that would be generated by performed operator actions to return one or more components of an industrial plant to a normal state from an alarm state, or

a fewest quantity of plant rules or engineering guidelines that need to be violated to return one or more components of an industrial plant to a normal state from an alarm state.

8. The apparatus of claim 7 , wherein to receive the one or more operating conditions from the one or more field devices of the one or more industrial plants in response to receiving the one or more alarm signals, the at least one processor is configured to:

analyze all operating conditions related to the one or more alarm signals; and

isolate the one or more operating conditions of all of the operating conditions based on one or more similarity patterns of the one or more operating conditions.

9. The apparatus of claim 7 , wherein the one or more historical alarm episodes comprise an indication of one or more previously performed operator actions.

10. The apparatus of claim 9 , wherein the at least one processor is further configured to:

after generating the one or more recommended historical alarm episodes for display on the user interface:

receive an indication of one or more real-time operator actions;

compare the one or more real-time operator actions with the one or more previously performed operator actions; and

categorize the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions.

11. The apparatus of claim 10 , wherein to categorize the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions, the at least one processor is configured to:

categorize the one or more real-time operator actions based on a time when the at least one processor receives the one or more operating conditions and a time when the at least one processor receives an indication of one or more normal operating conditions.

12. The apparatus of claim 10 , wherein to categorize the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions, the at least one processor is configured to:

categorize the one or more real-time operator actions based on a quantity of the one or more real-time operator actions received in the indication of the one or more real-time operator actions and a quantity of the one or more previously performed operator actions.

13. A non-transitory, computer-readable storage medium storing one or more computer executable instructions that, when executed by at least one processor, cause the at least one processor to:

receive one or more operating conditions from one or more field devices of one or more industrial plants in response to receiving one or more alarm signals;

determine one or more industrial plant states based on the one or more operating conditions;

identify one or more historical alarm episodes stored in one or more data stores based on the one or more industrial plant states;

identify one or more recommended historical alarm episodes of the one or more historical alarm episodes based on one or more benchmark metrics of the one or more historical alarm episodes; and

generate the one or more recommended historical alarm episodes for display on a user interface,

wherein the one or more benchmark metrics comprise at least one of:

an integral of a difference between an actual and alarm trip point during a span of an alarm of the alarm episode,

a quantity of operator actions that require a least amount of time to return one or more components of an industrial plant to a normal state from an alarm state,

a fewest quantity of operator actions to be performed to return one or more components of an industrial plant to a normal state from an alarm state,

a fewest quantity of additional adverse conditions that would be generated by performed operator actions to return one or more components of an industrial plant to a normal state from an alarm state, or

a fewest quantity of plant rules or engineering guidelines that need to be violated to return one or more components of an industrial plant to a normal state from an alarm state.

14. The non-transitory, computer-readable storage medium of claim 13 , wherein to receive the one or more operating conditions from the one or more field devices of the one or more industrial plants in response to receiving the one or more alarm signals, the one or more computer executable instructions cause the at least one processor to:

analyze all operating conditions related to the one or more alarm signals; and

isolate the one or more operating conditions of all of the operating conditions based on one or more similarity patterns of the one or more operating conditions.

15. The non-transitory, computer-readable storage medium of claim 13 , wherein the one or more historical alarm episodes comprise an indication of one or more previously performed operator actions.

16. The non-transitory, computer-readable storage medium of claim 15 , wherein the one or more computer executable instructions further cause the at least one processor to:

after generating the one or more recommended historical alarm episodes for display on the user interface:

receive an indication of one or more real-time operator actions;

compare the one or more real-time operator actions with the one or more previously performed operator actions; and

categorize the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions.

17. The non-transitory, computer-readable storage medium of claim 16 , wherein to categorize the one or more real-time operator actions based on the comparison of the one or more real-time operator actions with the one or more previously performed operator actions, the one or more computer executable instructions cause the at least one processor to:

categorize the one or more real-time operator actions based on a time when the at least one processor receives the one or more operating conditions and a time when the at least one processor receives an indication of one or more normal operating conditions.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 1, 2019
From: GANAPATHI, RAMAKRISHNAN; PRIYADARSINI, PRANGYA; NARAYAN, ANAND; SRIVASTAVA, VIRAJ
To: HONEYWELL INTERNATIONAL INC.
Reel/Frame 048485/0032 →
Cited By (2)
US 12,591,226 US 12,626,209