Wax risk assessment and mitigation using advanced data analytics and pipe flow modeling

Patent metadata

Field	Value
Publication number	US-11513111-B2
Application number	US-201716604199-A
Country	US
Kind code	B2
Filing date	Apr 10, 2017
Priority date	Apr 10, 2017
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Described herein are systems and methods for evaluating and mitigating the wax risks of a given hydrocarbon composition such as crude oil. The disclosed systems and methods enable rapid and ready prediction of wax risks using algorithms based on a small sample of the hydrocarbon composition. The wax risks are predicted using predictive models developed from machine learning. The disclosed systems and methods include mitigation strategies for wax risks that can include chemical additives, operation changes, and/or hydrocarbon blend.

First claim

What is claimed is:

1. A method of determining and mitigating wax risk of a hydrocarbon composition, the method comprising:
obtaining a sample of the hydrocarbon composition;
analyzing the sample of the hydrocarbon composition to determine one or more attributes of the sample of the hydrocarbon composition;
developing a first predictive model representative of hydrocarbon production, transportation, refining, refined hydrocarbon production, and/or processing based on the analysis of the sample of the hydrocarbon composition, wherein the first predictive model is developed using one or more machine learning algorithms;
determining wax risks based on the first predictive model;
developing, using the one or more machine learning algorithms, a second predictive model for selecting one or more chemical additives to add to the hydrocarbon composition based on the determined wax risks; and
mitigating one or more of the determined wax risks by introducing the one or more chemical additives during at least one of the production, transportation, storage, processing, or distribution of the hydrocarbon composition.

2. The method of claim 1 , wherein the second predictive model is a pipe flow model for a pipeline and wherein the one or more chemical additives are selected based on the pipe flow model and the determined wax risks.

3. The method of claim 1 , wherein the one or more chemical additives are selected based on matching precipitation characteristics between the one or more chemical additives and wax in the hydrocarbon composition, and/or the attributes related to composition of the hydrocarbon.

4. The method of claim 1 , wherein analyzing the sample of the hydrocarbon composition to determine one or more attributes of the sample of the hydrocarbon composition comprises performing one or more of fingerprint analysis of the sample, high temperature gas chromatography (HTGC) analysis of the sample, differential scanning calorimetry analysis, or inductively coupled plasma mass spectrum analysis of the sample to determine one or more attributes of the sample.

5. The method of claim 1 , wherein the one or more attributes include Total Acid Number (TAN), American Petroleum Institute gravity (API gravity), specific gravity (SG), SARA (saturates, aromatics, resins, asphaltenes), Colloid Instability Index (CII), viscosity, rheology, wax content, heavy wax content, Wax Appearance Temperature (WAT), and Pour Point (PP).

6. The method of claim 1 , wherein the one or more machine learning algorithms include principal component analysis (PCA), linear regression and logistic regression.

7. The method of claim 1 , wherein the determined wax risks include one or more of wax content, heavy wax content, Wax Appearance Temperature (WAT), Pour Point (PP), and wax deposition potential.

8. The method of claim 1 , wherein mitigating one or more of the determined wax risks further comprises modifying the production, transportation, storage, processing, and/or distribution of the hydrocarbon composition to reduce the determined wax risks.

9. A method of reducing wax risks in a hydrocarbon composition, the method comprising:
obtaining a sample of the hydrocarbon composition;
determining one or more wax risks by:
analyzing the sample of the hydrocarbon composition to determine one or more attributes of the sample of the hydrocarbon composition;
developing a first predictive model for the hydrocarbon composition based on the analysis of the sample of the hydrocarbon composition, wherein the first predictive model is developed using one or more machine learning algorithms;
determining the wax risks using the first predictive model;
developing, using the one or more machine learning algorithms, a second predictive model for selecting one or more chemical additives to add to the hydrocarbon composition based on the determined wax risks; and
introducing the one or more chemical additives during at least one of production, transportation, storage, processing, and/or distribution of the hydrocarbon composition to reduce the wax risks.

10. The method of claim 9 , wherein the second predictive model is a pipe flow model for a pipeline and wherein the one or more chemical additives are selected based on the pipe flow model and the determined wax risks.

11. The method of claim 9 , wherein the one or more chemical additives are selected based on matching precipitation characteristics between the one or more chemical additives and wax in the hydrocarbon composition, and/or the attributes related to composition of the hydrocarbon.

12. The method of claim 9 , wherein analyzing the sample of the hydrocarbon composition to determine one or more attributes of the sample of the hydrocarbon composition comprises performing one or more of fingerprint analysis of the sample, high temperature gas chromatography (HTGC) analysis of the sample, differential scanning calorimetry analysis, or inductively coupled plasma mass spectrum analysis of the sample to determine one or more attributes of the sample.

13. The method of claim 9 , wherein the one or more machine learning algorithms include principal component analysis (PCA), linear regression and logistic regression.

14. The method of claim 9 , wherein the determined wax risks include one or more of Wax Appearance Temperature (WAT), Pour Point (PP), wax content, heavy wax content, and wax deposition potential.

15. A system for using predictive analytics in management of a hydrocarbon process, said system comprising:
a memory, wherein the memory stores computer-readable instructions; and
a processor communicatively coupled with the memory, wherein the processor executes the computer-readable instructions stored on the memory, the computer-readable instructions causing the processor to:
receive an analysis of a hydrocarbon sample,
develop a first predictive model for a hydrocarbon based on one or more attributes of the sample of the hydrocarbon composition determined in the analysis of the hydrocarbon sample, wherein the first predictive model is developed using one or more machine learning algorithms;
determine the wax risks using the predictive model;
develop, using the one or more machine learning algorithms, a second predictive model for selecting one or more chemical additives to add to the hydrocarbon composition based on the determined wax risks; and
control aspects of the hydrocarbon process based on the determined wax risks to mitigate one or more of the determined wax risks by, at least, introducing the one or more chemical additives during at least one of production, transportation, storage, processing, or distribution of the hydrocarbon composition;
wherein the analysis is obtained by the following steps:
obtaining a sample of the hydrocarbon composition; and
analyzing the sample of the hydrocarbon composition to determine the one or more attributes of the sample of the hydrocarbon composition.

16. The system of claim 15 , wherein the second predictive model is a pipe flow model for a pipeline and wherein the one or more chemical additives are selected based on the determined wax risks.

17. The system of claim 15 , wherein the one or more chemical additives are selected based on matching precipitation characteristics between the one or more chemical additives and wax in the hydrocarbon composition.

18. The system of claim 15 , wherein analyzing the sample of the hydrocarbon composition to determine one or more attributes of the sample of the hydrocarbon composition comprises performing one or more of fingerprint analysis of the sampl

Assignees

• Bl Technologies Inc

Inventors

• Patel Nimeshkumar Kantilal
• Bagaria Hitesh Ghanshyam
• Wang Guoliang
• Xie Xiaoan
• Zhang Xiao
• Peng Yun
• Peng Wenqing
• Zheng Sheng
• Mcdermott John Brian
• Perez Diaz Peter Larry

Classifications

• G01N33/2876

  Total acid number · CPC title

• C10G75/02

  by addition of corrosion inhibitors · CPC title

• C10G75/00

  Inhibiting corrosion or fouling in apparatus for treatment or conversion of hydrocarbon oils, in general (C10G7/10, C10G9/16 take precedence) · CPC title

• C10G31/00

  Refining of hydrocarbon oils, in the absence of hydrogen, by methods not otherwise provided for (by distillation C10G7/00) · CPC title

• G01N33/2835 Primary

  Specific substances contained in the oils or fuels · CPC title