Generating a soft sensor for crude stabilization in the petroleum industry

Patent metadata

Field	Value
Publication number	US-11078428-B2
Application number	US-201715670679-A
Country	US
Kind code	B2
Filing date	Aug 7, 2017
Priority date	Aug 7, 2017
Publication date	Aug 3, 2021
Grant date	Aug 3, 2021

Abstract

A global theoretical graphical representation of a soft sensor is generated based on a cursory model, where the soft sensor is used to control crude stabilization. A plurality of local real-life graphical representations are generated for the soft sensor, each of the plurality of local real-life graphical representations corresponding to a respective local regime. A global real-life graphical representation is generated for the soft sensor by combining the plurality of local real-life graphical representations. A set of numerical values for the soft sensor are generated based on the global real-life graphical representation. The soft sensor is updated based on lab results and a crude stabilization operation is controlled using the soft sensor.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
generating a global theoretical graphical representation of a soft sensor based on a cursory model;
generating a plurality of local real-life graphical representations for the soft sensor based on the global theoretical graphical representation of the soft sensor, each of the plurality of local real-life graphical representations corresponding to a respective local regime;
generating a global real-life graphical representation for the soft sensor by combining the plurality of local real-life graphical representations;
generating a set of numerical values for the soft sensor based on the global real-life graphical representation;
updating the soft sensor based on lab results and the set of numerical values; and
using the updated soft sensor to control at least one of a stabilizer bottom temperature or a steam injection ratio in a crude production process.

2. The computer-implemented method of claim 1 , further comprising: identifying a primary input variable based on sensitivity study of the cursory model.

3. The computer-implemented method of claim 1 , wherein the local regime is partitioned based on statistical analysis on historical data.

4. The computer-implemented method of claim 1 , further comprising: performing statistical analysis on the lab results before updating the soft sensor based on the lab results.

5. The computer-implemented method of claim 1 , wherein the soft sensor is a hydrogen sulfide (H2S) sensor.

6. The computer-implemented method of claim 1 , wherein the soft sensor is a Reid vapor pressure (RVP) sensor.

7. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
generating a global theoretical graphical representation of a soft sensor based on a cursory model;
generating a plurality of local real-life graphical representations for the soft sensor based on the global theoretical graphical representation of the soft sensor, each of the plurality of local real-life graphical representations corresponding to a respective local regime;
generating a global real-life graphical representation for the soft sensor by combining the plurality of local real-life graphical representations;
generating a set of numerical values for the soft sensor based on the global real-life graphical representation;
updating the soft sensor based on lab results and the set of numerical values; and
using the updated soft sensor to control at least one of a stabilizer bottom temperature or a steam injection ratio in a crude production process.

8. The non-transitory, computer-readable medium of claim 7 , the operations comprising: identifying a primary input variable based on sensitivity study of the cursory model.

9. The non-transitory, computer-readable medium of claim 7 , wherein the local regime is partitioned based on statistical analysis on historical data.

10. The non-transitory, computer-readable medium of claim 7 , the operations comprising: performing statistical analysis on the lab results before updating the soft sensor based on the lab results.

11. The non-transitory, computer-readable medium of claim 7 , wherein the soft sensor is a hydrogen sulfide (H2S) sensor.

12. The non-transitory, computer-readable medium of claim 7 , wherein the soft sensor is a Reid vapor pressure (RVP) sensor.

13. A computer-implemented system, comprising:
a computer memory; and
a hardware processor interoperably coupled with the computer memory and configured to perform operations comprising:
generating a global theoretical graphical representation of a soft sensor based on a cursory model;
generating a plurality of local real-life graphical representations for the soft sensor based on the global theoretical graphical representation of the soft sensor, each of the plurality of local real-life graphical representations corresponding to a respective local regime;
generating a global real-life graphical representation for the soft sensor by combining the plurality of local real-life graphical representations;
generating a set of numerical values for the soft sensor based on the global real-life graphical representation;
updating the soft sensor based on lab results and the set of numerical values; and
using the updated soft sensor to control at least one of a stabilizer bottom temperature or a steam injection ratio in a crude production process.

14. The computer-implemented system of claim 13 , the operations comprising: identifying a primary input variable based on sensitivity study of the cursory model.

15. The computer-implemented system of claim 13 , wherein the local regime is partitioned based on statistical analysis on historical data.

16. The computer-implemented system of claim 13 , the operations comprising: performing statistical analysis on the lab results before updating the soft sensor based on the lab results.

17. The computer-implemented system of claim 13 , wherein the soft sensor is a hydrogen sulfide (H2S) sensor.

Assignees

• Saudi Arabian Oil Co

Inventors

• Lee Shuyee
• Al-Mohisin Omar
• Al-Saeed Mohammed

Classifications

• G01K13/026

  of moving liquids · CPC title

• C10G7/02

  Stabilising gasoline by removing gases by fractioning · CPC title

• G05B13/04

  involving the use of models or simulators · CPC title

• G01L19/0092

  Pressure sensor associated with other sensors, e.g. for measuring acceleration or temperature (G01L9/025, G01L9/045, G01L9/065, G01L9/085, G01L9/105, G01L9/125, G01L19/02, G01L19/04 take precedence; measuring two or more variable G01D21/02; temperature sensors with pressure compensation G01K1/26) · CPC title

• C01B17/16

  Hydrogen sulfides · CPC title