Menu
Search
Filters
Close
Menu

Application of Machine Learning Techniques for Sand Erosion Prediction for Elbows in Multiphase Flow

Picture for Application of Machine Learning Techniques for Sand Erosion Prediction for Elbows in Multiphase Flow
Available for download


In the oil and gas industry, sand production can lead to blockage of pipelines, corrosion and erosion, which may cause the failure of the fluid transport system, pipeline leakage, and consequently environmental contamination. In the process of fluid transportation, the pipe walls are always impacted by particles entrained in flowing fluid. As a result, the corresponding erosive wear may be detrimental to pipe wall structural integrity. Although sand screens and gravel packs are frequently used to minimize sand production, technical and economic challenges or limitations with these practices are still present in the industry1.

Product Number: 51323-18995-SG
Author: Ronald E. Vieira, Farzin Darihaki, Jamie Li, Siamack A. Shirazi
Publication Date: 2023
$0.00
$20.00
$20.00

The aim of this work is to define, implement, test, and validate an AI methodology using existing machine learning (ML) algorithms to predict sand erosion in 90° elbows for a broad range of multiphase operating conditions. Based on information obtained from the experimental UT wall thickness loss data collected for different flow regimes (gas-sand, liquid-sand, dispersed-bubble, churn, annular, and low liquid loading multiphase flows), the methodology has been developed to predict the maximum erosion magnitudes in standard metallic elbows. In order to expand the range of application of the method to situations where data is not available, the erosion database has been expanded by including state-of-the-art validated CFD simulations and 2-dimensional CFD-based mechanistic model predictions. The ML algorithms, including elastic net (EN), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and k-nearest neighbors (KNN) classification. The models are optimized using cross-validation and their performance is evaluated by different metrics. More than 650 case studies from previous literature as well as ongoing research have been used to train and test the ML models. The RF and XGB results show the overall best performance for a variety of flow conditions and pipe sizes. The resulting technique helps in saving time and resources to predict erosion in elbows and develop operational limits both within and beyond the current experimental domain while utilizing the most common production input parameters used by oil and gas production operators and other industrial applications.

The aim of this work is to define, implement, test, and validate an AI methodology using existing machine learning (ML) algorithms to predict sand erosion in 90° elbows for a broad range of multiphase operating conditions. Based on information obtained from the experimental UT wall thickness loss data collected for different flow regimes (gas-sand, liquid-sand, dispersed-bubble, churn, annular, and low liquid loading multiphase flows), the methodology has been developed to predict the maximum erosion magnitudes in standard metallic elbows. In order to expand the range of application of the method to situations where data is not available, the erosion database has been expanded by including state-of-the-art validated CFD simulations and 2-dimensional CFD-based mechanistic model predictions. The ML algorithms, including elastic net (EN), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and k-nearest neighbors (KNN) classification. The models are optimized using cross-validation and their performance is evaluated by different metrics. More than 650 case studies from previous literature as well as ongoing research have been used to train and test the ML models. The RF and XGB results show the overall best performance for a variety of flow conditions and pipe sizes. The resulting technique helps in saving time and resources to predict erosion in elbows and develop operational limits both within and beyond the current experimental domain while utilizing the most common production input parameters used by oil and gas production operators and other industrial applications.

Product tags
Also Purchased
Picture for AISI 420/410 Modified Martensitic Stainless Steel bar Stock Materials Sulphide Stress Cracking (SSC) Resistance in Mildly Sour Environments
Available for download

AISI 420/410 Modified Martensitic Stainless Steel bar Stock Materials Sulphide Stress Cracking (SSC) Resistance in Mildly Sour Environments

Product Number: 51323-18759-SG
Author: Roberto Morana, Lee Smith, Perry Nice, Lucrezia Scoppio, Marc Müller, Karola Klenke, Roberta Prencipe, Luciana Intiso
Publication Date: 2023
$20.00

Martensitic Stainless Steel (SMSS) is widely used for downhole production tubing and liners in the Oil & Gas industry. Optimization of the tubular material chemistry, cleanliness and manufacturing route has delivered useful performance in H2S-containing environments (specifically SSC and stress corrosion cracking [SCC])3 resistance4,5,6. Some tubular accessories and most completion equipment require sizes not readily delivered by tubular product form. In these instances, bar stock material is a pragmatic choice.
Picture for Development of a Gas-Phase Corrosion Inhibitor for Wet-Gas Carbon Dioxide Corrosion at 200°C
Available for download

Development of a Gas-Phase Corrosion Inhibitor for Wet-Gas Carbon Dioxide Corrosion at 200°C

Product Number: 51323-18829-SG
Author: Wei Zhang, Jason Moses, William Cardwell, Samar Agha Keshmiri, Khoa Ky, David Orta, Alyn Jenkins
Publication Date: 2023
$20.00

Although organic corrosion inhibitors have been widely applied in the energy industry, many details regarding their protection mechanism remain unknown. For example, a corrosion inhibitor adsorbs on the clean steel/aqueous solution interface, driven by electrostatic interaction. With the corrosion product
layer formed, how would the inhibitor adsorption interact with the corrosion product nucleation and precipitation? What is the effect of pre-corrosion in inhibitor testing?
Picture for Corrosion Management Review of Sour Gas Pipeline – A Case Study
Available for download

Corrosion Management Review of Sour Gas Pipeline – A Case Study

Product Number: 51323-18855-SG
Author: Muntathir M. Al-Jumaah, Faisal M. Al-Mutahhar, Muhammad A. Sherwani
Publication Date: 2023
$20.00

This paper reviews the corrosion management for a critical sour gas pipeline operated by Saudi Aramco. The 38-inch diameter pipeline transports untreated sour gas from Crude Processing Facility (CPF) to downstream Gas Plant and spans a total distance of 145 km. To prevent internal corrosion inside the pipeline, the wet sour gas is dehydrated using Tri-Ethylene Glycol (TEG) unit.
Categories
Industry
Recently viewed
Popular tags
View all

Association for Materials Protection and Performance

© AMPP All Rights Reserved.
Membership Terms of Content Use
Contact Customer Support