TY - GEN
T1 - Horizontal Two-Phase Flow Regime Identification with Machine Learning Classification Models
AU - Manikonda, Kaushik
AU - Islam, Raka
AU - Obi, Chinemerem Edmond
AU - Hasan, Abu Rashid
AU - Sleiti, Ahmad Khalaf
AU - Abdelrazeq, Motasem Wadi
AU - Hassan, Ibrahim Galal
AU - Rahman, Mohammad Azizur
N1 - Publisher Copyright:
Copyright © 2022, International Petroleum Technology Conference.
PY - 2022
Y1 - 2022
N2 - This paper presents a follow-up study to Manikonda et al. (2021), which identified the best machine learning (ML) models for classifying the flow regimes in vertical gas-liquid two-phase flow. This paper replicates their study but with horizontal, gas-liquid two-phase flow data. Many workflows in the energy industry like horizontal drilling and pipeline fluid transport involve horizontal two-phase flows. This work and Manikonda et al. (2021) focus on two-phase flow applications during well control and extended reach drilling. The study started with a comprehensive literature survey and legacy data collection, followed by additional data collection from original experiments. The experimental data originates from a 20-ft long inclinable flow loop, with an acrylic outer tube and a PVC inner tube that mimics a horizontal drilling scenario. Following these data collection and processing exercises, we fit multiple supervised and unsupervised machine learning (ML) classification models on the cleaned data. The models this study investigated include K-nearest-neighbors (KNN) and Multi-class support vector machine (MCSVM) in supervised learning, along with K-means and Hierarchical clustering in unsupervised learning. The study followed this step with model optimization, such as picking the optimal K for KNN, parameter tuning for MCSVM, deciding the number of clusters for K-means, and determining the dendrogram cutting height for Hierarchical clustering. These investigations found that a 5-fold cross-validated KNN model with K = 50 gave an optimal result with a 97.4% prediction accuracy. The flow maps produced by KNN showed six major and four minor flow regimes. The six significant regimes are Annular, Stratified Wavy, Stratified Smooth at lower liquid superficial velocities, followed by Plug, Slug, and Intermittent at higher liquid superficial velocities. The four minor flow regions are Dispersed Bubbly, Bubbly, Churn, and Wavy Annular flows. A comparison of these KNN flow maps with those proposed by Mandhane, Gregory, and Aziz (1974) showed reasonable agreement. The flow regime maps from MCSVM were visually similar to those from KNN but severely underperformed in terms of prediction accuracy. MCSVM showed a 99% training accuracy at very high parameter values, but it dropped to 50% - 60% at typical parameter values. Even at very high parameter values, the test prediction accuracy was only at 50%. Coming to unsupervised learning, the two clustering techniques pointed to an optimal cluster number between 13-16. A robust horizontal two-phase flow classification algorithm has many applications during extended reach drilling. For instance, drillers can use such an algorithm as a black box for horizontal two-phase flow regime identification. Additionally, these algorithms can also form the backbone for well control modules in drilling automation software. Finally, on a more general level, these models could have applications in production, flow assurance, and other processes where two-phase flow plays an important role.
AB - This paper presents a follow-up study to Manikonda et al. (2021), which identified the best machine learning (ML) models for classifying the flow regimes in vertical gas-liquid two-phase flow. This paper replicates their study but with horizontal, gas-liquid two-phase flow data. Many workflows in the energy industry like horizontal drilling and pipeline fluid transport involve horizontal two-phase flows. This work and Manikonda et al. (2021) focus on two-phase flow applications during well control and extended reach drilling. The study started with a comprehensive literature survey and legacy data collection, followed by additional data collection from original experiments. The experimental data originates from a 20-ft long inclinable flow loop, with an acrylic outer tube and a PVC inner tube that mimics a horizontal drilling scenario. Following these data collection and processing exercises, we fit multiple supervised and unsupervised machine learning (ML) classification models on the cleaned data. The models this study investigated include K-nearest-neighbors (KNN) and Multi-class support vector machine (MCSVM) in supervised learning, along with K-means and Hierarchical clustering in unsupervised learning. The study followed this step with model optimization, such as picking the optimal K for KNN, parameter tuning for MCSVM, deciding the number of clusters for K-means, and determining the dendrogram cutting height for Hierarchical clustering. These investigations found that a 5-fold cross-validated KNN model with K = 50 gave an optimal result with a 97.4% prediction accuracy. The flow maps produced by KNN showed six major and four minor flow regimes. The six significant regimes are Annular, Stratified Wavy, Stratified Smooth at lower liquid superficial velocities, followed by Plug, Slug, and Intermittent at higher liquid superficial velocities. The four minor flow regions are Dispersed Bubbly, Bubbly, Churn, and Wavy Annular flows. A comparison of these KNN flow maps with those proposed by Mandhane, Gregory, and Aziz (1974) showed reasonable agreement. The flow regime maps from MCSVM were visually similar to those from KNN but severely underperformed in terms of prediction accuracy. MCSVM showed a 99% training accuracy at very high parameter values, but it dropped to 50% - 60% at typical parameter values. Even at very high parameter values, the test prediction accuracy was only at 50%. Coming to unsupervised learning, the two clustering techniques pointed to an optimal cluster number between 13-16. A robust horizontal two-phase flow classification algorithm has many applications during extended reach drilling. For instance, drillers can use such an algorithm as a black box for horizontal two-phase flow regime identification. Additionally, these algorithms can also form the backbone for well control modules in drilling automation software. Finally, on a more general level, these models could have applications in production, flow assurance, and other processes where two-phase flow plays an important role.
UR - http://www.scopus.com/inward/record.url?scp=85128957541&partnerID=8YFLogxK
U2 - 10.2523/IPTC-22153-MS
DO - 10.2523/IPTC-22153-MS
M3 - Conference contribution
AN - SCOPUS:85128957541
T3 - International Petroleum Technology Conference, IPTC 2022
BT - International Petroleum Technology Conference, IPTC 2022
PB - International Petroleum Technology Conference (IPTC)
T2 - 2022 International Petroleum Technology Conference, IPTC 2022
Y2 - 21 February 2022 through 23 February 2022
ER -