Method for generating a process model

Patent metadata

Field	Value
Publication number	US-12449781-B2
Application number	US-202217977355-A
Country	US
Kind code	B2
Filing date	Oct 31, 2022
Priority date	Apr 30, 2020
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

A method for generating a process model modeling a manual mode procedure instance of a plant process includes providing log events of operational actions; selecting related sequences of manual mode operational actions from the log events; filtering the related sequences according to an individual plant section; identifying a sequential order from the filtered related sequences; determining statistical properties of values of related process variables and/or statistical properties of values of related set point changes to each sequential ordered manual mode operational action from the filtered related sequences; generating the process model of the manual mode procedure instance by arranging related manual mode operational actions with the sequential order of each operational action assigned with the statistical properties of the values of related process variables and/or assigned with the statistical properties of the values of the related set point changes.

First claim

What is claimed is:

1. A method for generating a process model modeling a manual mode procedure instance of a plant process, the procedure instance comprising a related sequence of operational actions, including the steps of:
providing a plurality of log events of a plurality of operational actions of the plant process;
selecting a plurality of related sequences of manual mode operational actions from the plurality of log events;
filtering the plurality of related sequences of manual mode operational actions according to an individual plant section;
identifying a sequential order from the plurality of filtered related sequences of the manual mode operational actions;
determining statistical properties of values of related process variables and/or statistical properties of values of related set point changes to each sequential ordered manual mode operational action from the plurality of filtered related sequences of the manual mode operational actions;
generating the process model of the manual mode procedure instance by arranging related manual mode operational actions with the sequential order of each operational action assigned with the statistical properties of the values of related process variables and/or assigned with the statistical properties of the values of the related set point changes,
wherein the process model is configured to provide guidance through execution of corresponding manual procedures using the generated process model.

2. The method according to claim 1 , wherein the filtering of the plurality of related sequences of manual mode operational actions is performed according to an individual plant condition.

3. The method according to claim 2 , wherein the individual plant condition is determined by at least a threshold value of a related process variable at the beginning of the manual mode procedure instance.

4. The method according to claim 3 , wherein the individual plant condition is determined by threshold values of a subset of the related process variables at the beginning of the manual mode procedure instance.

5. The method according to claim 2 , wherein the individual plant condition is determined by at least one time series of values of related process variables of the plant section within a time period before the start of the manual mode procedure instance.

6. The method according to claim 2 , wherein the individual plant condition is determined by a clustered number of time series of values of process variables of the plant section within a time period before the start of the manual mode procedure instance, wherein the cluster is built by scoring similarities of time series of values of related process variables.

7. The method according to claim 1 , wherein annotations related to a manual mode operational action is assigned to the respective manual mode operational action.

8. The method according to claim 1 , wherein a manual mode operational action with an assigned statistical property of the values of the related process variables is above a limit value is omitted from the process model.

9. The method according to claim 1 , wherein a specific manual mode operational action of the plurality of related sequences of manual mode operational actions, which rarely occurs within the plurality of related sequences of manual mode operational actions, is omitted from the process model.

10. The method according to claim 1 , further comprising generating a recommended set point for a manual mode operational action of a manual mode procedure instance, wherein the recommended set point is determined using a machine learning model by means of the plurality of related set points related to an individual plant condition, to be assigned to the related manual mode operational action in respect to the individual plant condition.

11. The method according to claim 1 , further comprising monitoring a compliance of the execution of the corresponding manual procedures with a set of related rules specified by the process model.

Assignees

• Abb Schweiz Ag

Inventors

• Schmidt Benedikt
• Dix Marcel
• Hollender Martin
• Cohen Andrew
• Kotriwala Arzam Muzaffar
• Gaertler Marco
• Maczey Sylvia
• Kloepper Benjamin

Classifications

• G05B2219/14009

  Manual overide control, digital or analog, between plc and machine · CPC title

• G05B17/02

  electric · CPC title

• G05B19/0428 Primary

  Safety, monitoring (G05B19/0423 takes precedence) · CPC title