Systems and methods for rapid prediction of hydrogen-induced cracking (HIC) in pipelines, pressure vessels, and piping systems and for taking action in relation thereto

Patent metadata

Field	Value
Publication number	US-10990873-B2
Application number	US-201715630428-A
Country	US
Kind code	B2
Filing date	Jun 22, 2017
Priority date	Jun 22, 2016
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

Methods and systems of predicting the growth rate of hydrogen-induced cracking (HIC) in a physical asset (e.g., a pipeline, storage tank, etc.) are provided. The methodology receives a plurality of inputs regarding physical characteristics of the asset and performs parametric simulations to generate a simulated database of observations of the asset. The database is then used to train, test, and validate one or more expert systems that can then predict the growth rate and other characteristics of the asset over time. The systems herein can also generate alerts as to predicted dangerous conditions and modify inspection schedules based on such growth rate predictions.

First claim

What is claimed is:

1. A system for determining a growth rate of hydrogen induced cracking (HIC) damage of an asset, the system comprising:
a computer having a processor, a memory, and an artificial neural network configured to operate as an expert system for determining the growth rate of the HIC damage of the asset, the expert system being trained from a database that stores simulation data corresponding to a plurality of input parameters and to an output parameter corresponding to the growth rate of HIC damage, the simulation data being obtained from running a mechanistic model on values of the plurality of input parameters to obtain corresponding values of the growth rate of HIC damage;
a data gathering device configured to gather input data at a region of the asset, the gathered input data corresponding to one or more of the plurality of input parameters; and
wherein the processor is configured to execute instructions that configure the processor to operate the expert system by:
receiving from the data gathering device the input data gathered at the region of the asset;
extracting values of the one or more of the plurality of input parameters from the received input data of the region of the asset;
processing the extracted values of the one or more of the plurality of input parameters through the artificial neural network to output the growth rate of HlC damage at the region of the asset;
deriving a curve of a maximum allowable working pressure (“MAWP”) versus time for the region of the asset;
comparing a value of the received input data over time to the curve to determine whether the difference in values of the received input data and the MAWP falls below a threshold;
generating an alert of the region of the asset in response to the determined difference falling below the threshold; and
in response to generating the alert, automatically adjusting operating conditions at the region of the asset to increase the difference in values of the received input data and the MAWP above the threshold.

2. The system according to claim 1 , wherein the executed instructions further configure the processor to operate the expert system by:
maintaining a HIC map of the region of the asset;
extracting values of other of the plurality of input parameters from the maintained HIC map; and
processing the extracted values of the other of the plurality of input parameters through the artificial neural network to output the growth rate of HIC damage at the region of the asset.

3. The system according to claim 2 , wherein the executed instructions further configure the processor to operate the expert system by processing the extracted values of the plurality of input parameters to output a new said HIC map of the region of the asset.

4. The system according to claim 3 , wherein the executed instructions further configure the processor to operate the expert system by extracting the values of the other of the plurality of input parameters from the new HIC map.

5. The system according to claim 1 , wherein the data gathering device is a robot, an intrusive probe system, a non-intrusive probe system, or a patch probe.

6. The system according to claim 1 , wherein the plurality of input parameters include crack geometry data, crack location data, material properties data, hydrogen charging data, operating conditions data, or a combination thereof.

7. The system according to claim 1 , wherein the value of the received input data is a value of the operating pressure at the region of the asset.

8. The system according to claim 7 , wherein the executed instructions further configure the processor to operate the expert system by:
determining a remaining lifetime of the region of the asset using a minimum operating pressure and the derived curve of MAWP versus time;
adjusting the operating pressure at the region of the asset in response to the determined difference falling below the threshold;
scheduling a fitness-for-service inspection at the region of the asset based on the determined remaining lifetime of the region of the asset; and
generating an alert in response to the determined remaining lifetime of the region of the asset falling below another threshold.

9. The system according to claim 1 , wherein the executed instructions further configure the processor to operate the expert system by scheduling, based on the output growth rate of HlC damage at the region of the asset, a fitness-for-service inspection at the region of the asset.

10. The system according to claim 1 , wherein the asset is a steel pipeline, a pressure vessel, a storage tank, or a piping system.

Assignees

• Saudi Arabian Oil Co

Inventors

• Traidia Abderrazak
• Sherik Abdelmounam

Classifications

• G06N3/042 Primary

  Knowledge-based neural networks; Logical representations of neural networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G05B17/02 Primary

  electric · CPC title

• G05B23/0254

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title