Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes
Abstract
:Highlights
- What are the main findings?
- Machine learning algorithms perform more efficiently than deep learning methods in classifying gas-liquid flow regimes in pipelines.
- Extreme gradient boosting is the best-performing algorithm for the six-class flow regime classification problem.
- What is the implication of the main findings?
- The current model can be implemented for the accurate classification of gas-liquid flow patterns in industrial pipelines with greater confidence.
Abstract
1. Introduction
- (1)
- Data acquisition and pre-processing;
- (2)
- Feature extraction;
- (3)
- Model training and testing.
- (1)
- Unsupervised learning;
- (2)
- Supervised learning.
- (1)
- The effectivity of the state-of-the-art ML models for classifying flow regime patterns into three different classification frameworks were investigated for the original dataset without any attempt of incorporating artificial data points in order to balance the class distribution.
- (2)
- The database used for the current study comprises 11,837 experimental measurements.
- (3)
- Six ML and three DL frameworks were designed and tested to model the flow patterns.
- (4)
- The feature importance analysis was performed thoroughly.
- (5)
- The best performing model was compared to the relevant models available in the literature.
2. Materials and Methods
2.1. Data Classification
- (1)
- Dispersed bubble (DB): 830 DP;
- (2)
- Stratified smooth (SS): 638 DP;
- (3)
- Stratified wavy (SW): 1516 DP;
- (4)
- Annular (A): 2138 DP;
- (5)
- Intermittent (I): 6354 DP;
- (6)
- Bubble (B): 362 DP.
2.2. Feature Normalization
2.3. Feature Relevance and Importance Analysis
- (a)
- Feature importance analysis by extra tree (ET) classifier;
- (b)
- Principle component analysis.
2.4. Machine-Learning Algorithms
2.4.1. RF
2.4.2. ET
2.4.3. Extreme GBM
2.4.4. SVM
2.4.5. KNN
2.4.6. AB
2.5. Deep-Learning Algorithms
2.5.1. DNN
2.5.2. CNN
2.5.3. Bi-LSTM RNN
2.6. Machine-Learning Model Training
2.7. Evaluation Metrics for Model Assessment
2.7.1. Accuracy
2.7.2. Precision
2.7.3. Recall
2.7.4. F1-Score
2.7.5. Cohen’s Kappa
2.7.6. Confusion Matrix
2.7.7. AUC-ROC Curve
3. Results
3.1. Feature Importance and Non-Linearity
3.2. Machine-Learning Model Training
3.3. Deep-Learning Model Training
3.4. Classification Performance
3.5. Hyperparameter Optimization
3.6. AUC-ROC Curves with Confidence Interval
3.7. Comparative Analysis
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Ghanbarzadeh, S.; Pedram, H.; Said, M. Intelligent image-based gas-liquid two-phase flow regime recognition. J. Fluids Eng. 2012, 134, 061302. [Google Scholar] [CrossRef]
- Strand, A.; Smith, I.E.; Unander, T.E.; Steinsland, I.; Hellevik, L.R. Uncertainty Propagation through a Point Model for Steady-State Two-Phase Pipe Flow. Algorithms 2020, 13, 53. [Google Scholar] [CrossRef] [Green Version]
- Bjørlo, I. Uncertainty in Multiphase Flow Estimates for a Field Development Case. Master’s Thesis, Norwegian University of Science and Technology, Trondheim, Norway, 2013. Available online: https://ntnuopen.ntnu.no/ntnu-xmlui/bitstream/handle/11250/235160/648709_FULLTEXT01.pdf?sequence=1&isAllowed=y (accessed on 1 January 2023).
- Klinkert, J. The Characterization of Uncertainty for Steady State Multiphase Flow Models in Pipelines. Master’s Thesis, Delft University of Technology, Delft, The Netherlands, 2018. Available online: http://resolver.tudelft.nl/uuid:4968494c-464e-46f9-b635-5828cedaadfa (accessed on 1 January 2023).
- Posluszny, D.; Klavetter, K.; Cremaschi, S.; Sarica, C.; Subramani, H.J. Uncertainty Analysis of Multiphase Flow Modelling: A Case Study for Vertical Flows. In Proceedings of the 7th North American Conference on Multiphase Technology, Banff, AB, Canada, 2–4 June 2010. [Google Scholar]
- Duns, H.; Ros, N.C.J. Vertical Flow of Gas and Liquid Mixtures from Boreholes; Bataafse Internationale Petroleum Maatschappij, NV: The Hague, The Netherlands, 1963. [Google Scholar]
- Hagedorn, A.R.; Brown, K.E. Experimental study of pressure gradients occurring during continuous two-phase flow in small-diameter vertical conduits. J. Pet. Technol. 1965, 17, 475–484. [Google Scholar] [CrossRef]
- Aziz, K.; Govier, G.W. Pressure drop in wells producing oil and gas. J. Can. Pet. Technol. 1972, 11, PETSOC-72-03-04. [Google Scholar] [CrossRef]
- Beggs, D.H.; Brill, J.P. A study of two-phase flow in inclined pipes. J. Pet. Technol. 1973, 25, 607–617. [Google Scholar] [CrossRef]
- Mukherjee, H.; Brill, J.P. Pressure drop correlations for inclined two-phase flow. J. Energy Resour. Technol. 1985, 107, 549–554. [Google Scholar] [CrossRef]
- Asheim, H. MONA, an accurate two-phase well flow model based on phase slippage. SPE Prod. Eng. 1986, 1, 221–230. [Google Scholar] [CrossRef]
- Pucknell, J.K.; Mason, J.N.E.; Vervest, E.G. An Evaluation of Recent Mechanistic Models of Multiphase Flow for Predicting Pressure Drops in Oil and Gas Wells. In Proceedings of the SPE Offshore Europe, Aberdeen, UK, 7–10 September 1993. [Google Scholar] [CrossRef]
- Rouhani, S.Z.; Sohal, M.S. Two-phase flow patterns: A review of research results. Prog. Nucl. Energy 1983, 11, 219–259. [Google Scholar] [CrossRef]
- Hewitt, G.F.; Hall-Taylor, N.S. Annular Two-Phase Flow; Elsevier Ltd.: Amsterdam, The Netherlands, 1970. [Google Scholar] [CrossRef]
- Taitel, Y.; Bornea, D.; Dukler, A.E. Modelling flow pattern transitions for steady upward gas-liquid flow in vertical tubes. AIChE J. 1980, 26, 345–354. [Google Scholar] [CrossRef]
- Barnea, D.; Shoham, O.; Taitel, Y. Flow pattern characterization in two phase flow by electrical conductance probe. Int. J. Multiph. Flow 1980, 6, 387–397. [Google Scholar] [CrossRef]
- Barnea, D.; Shoham, O.; Taitel, Y.; Dukler, A.E. Flow pattern transition for gas-liquid flow in horizontal and inclined pipes. Comparison of experimental data with theory. Int. J. Multiph. Flow 1980, 6, 217–225. [Google Scholar] [CrossRef]
- Oddie, G.; Shi, H.; Durlofsky, L.J.; Aziz, K.; Pfeffer, B.; Holmes, J.A. Experimental study of two and three phase flows in large diameter inclined pipes. Int. J. Multiph. Flow 2003, 29, 527–558. [Google Scholar] [CrossRef]
- Zhang, H.Q.; Wang, Q.; Sarica, C.; Brill, J.P. Unified model for gas-liquid pipe flow via slug dynamics—Part 1: Model development. J. Energy Resour. Technol. 2003, 125, 266–273. [Google Scholar] [CrossRef]
- Dreyer, W.J.; Bennett, J.C. The molecular basis of antibody formation: A paradox. Proc. Natl. Acad. Sci. USA 1965, 54, 864. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cong, T.; Su, G.; Qiu, S.; Tian, W. Applications of ANNs in flow and heat transfer problems in nuclear engineering: A review work. Prog. Nucl. Energy 2013, 62, 54–71. [Google Scholar] [CrossRef]
- Wang, S.Q.; Xu, K.W.; Kim, H.B. Slug flow identification using ultrasound Doppler velocimetry. Int. J. Heat Mass Transf. 2020, 148, 119004. [Google Scholar] [CrossRef]
- Peddu, A.; Chakraborty, S.; Das, P.K. Visualization and flow regime identification of downward air–water flow through a 12 mm diameter vertical tube using image analysis. Int. J. Multiph. Flow 2018, 100, 1–15. [Google Scholar] [CrossRef]
- Chen, S.W.; Lin, M.S.; Kuo, F.J.; Chai, M.L.; Liu, S.Y.; Lee, J.D.; Pei, B.S. Experimental investigation and identification of the transition boundary of churn and annular flows using multi-range differential pressure and conductivity signals. Appl. Therm. Eng. 2017, 114, 1275–1286. [Google Scholar] [CrossRef]
- Hobold, G.M.; da Silva, A.K. Machine learning classification of boiling regimes with low speed, direct and indirect visualization. Int. J. Heat Mass Transf. 2018, 125, 1296–1309. [Google Scholar] [CrossRef]
- Manjrekar, O.N.; Dudukovic, M.P. Identification of flow regime in a bubble column reactor with a combination of optical probe data and machine learning technique. Chem. Eng. Sci. X 2019, 2, 100023. [Google Scholar] [CrossRef]
- Mask, G.; Wu, X.; Ling, K. An improved model for gas-liquid flow pattern prediction based on machine learning. J. Pet. Sci. Eng. 2019, 183, 106370. [Google Scholar] [CrossRef]
- Julia, J.E.; Ozar, B.; Jeong, J.J.; Hibiki, T.; Ishii, M. Flow regime development analysis in adiabatic upward two-phase flow in a vertical annulus. Int. J. Heat Fluid Flow 2011, 32, 164–175. [Google Scholar] [CrossRef]
- Paranjape, S.; Chen, S.W.; Hibiki, T.; Ishii, M. Flow regime identification under adiabatic upward two-phase flow in a vertical rod bundle geometry. J. Fluids Eng. 2011, 133, 9. [Google Scholar] [CrossRef]
- Sawant, P.; Schelegel, J.; Paranjape, S.; Ozar, B.; Hibiki, T.; Ishii, M. Flow regime identification in large diameter pipe. Int. Conf. Nucl. Eng. 2008, 48167, 341–351. [Google Scholar]
- Tambouratzis, T.; Pázsit, I. Non-invasive on-line two-phase flow regime identification employing artificial neural networks. Ann. Nucl. Energy 2009, 36, 464–469. [Google Scholar] [CrossRef]
- Paranjape, S.; Ritchey, S.N.; Garimella, S.V. Electrical impedance-based void fraction measurement and flow regime identification in microchannel flows under adiabatic conditions. Int. J. Multiph. Flow 2012, 42, 175–183. [Google Scholar] [CrossRef] [Green Version]
- Mi, Y.; Ishii, M.; Tsoukalas, L.H. Vertical two-phase flow identification using advanced instrumentation and neural networks. Nucl. Eng. Des. 1998, 184, 409–420. [Google Scholar] [CrossRef]
- Sunde, C.; Avdic, S.; Pázsit, I. Classification of two-phase flow regimes via image analysis and a neuro-wavelet approach. Prog. Nucl. Energy 2005, 46, 348–358. [Google Scholar] [CrossRef]
- Jing, C.; Bai, Q.; Liu, B. Improved Void Fraction Measurement by Flow Regime Identification for Gas Liquid Two-Phase Flows. In Proceedings of the Seventh International Symposium on Instrumentation and Control Technology: Measurement Theory and Systems and Aeronautical Equipment, Beijing, China, 16 November 2008; Volume 7128, pp. 352–357. [Google Scholar]
- Harirchian, T.; Garimella, S.V. Boiling heat transfer and flow regimes in microchannels—A comprehensive understanding. J. Electron. Packag. 2011, 133, 011001. [Google Scholar] [CrossRef]
- Fraces, C.G.; Tchelepi, H. Physics Informed Deep Learning for Flow and Transport in Porous Media. In Proceedings of the SPE Reservoir Simulation Conference, Demand, 26 October 2021. [Google Scholar] [CrossRef]
- Maucec, M.; Jalali, R. GeoDIN—Geoscience-Based Deep Interaction Networks for Predicting Flow Dynamics in Reservoir Simulation Models. SPE J. 2022, 27, 1671–1689. [Google Scholar] [CrossRef]
- Tan, C.; Dong, F.; Wu, M. Identification of gas/liquid two-phase flow regime through ERT-based measurement and feature extraction. Flow Meas. Instrum. 2007, 18, 255–261. [Google Scholar] [CrossRef]
- Wang, H.X.; Zhang, L.F. Identification of two-phase flow regimes based on support vector machine and electrical capacitance tomography. Meas. Sci. Technol. 2009, 20, 114007. [Google Scholar] [CrossRef]
- Shanthi, C.; Pappa, N. An artificial intelligence based improved classification of two-phase flow patterns with feature extracted from acquired images. ISA Trans. 2017, 68, 425–432. [Google Scholar] [CrossRef] [PubMed]
- Nnabuife, S.G.; Pilario, K.E.S.; Lao, L.; Cao, Y.; Shafiee, M. Identification of gas-liquid flow regimes using a non-intrusive Doppler ultrasonic sensor and virtual flow regime maps. Flow Meas. Instrum. 2019, 68, 101568. [Google Scholar] [CrossRef]
- Cai, S.; Toral, H.; Qiu, J.; Archer, J.S. Neural network based objective flow regime identification in air-water two phase flow. Can. J. Chem. Eng. 1994, 72, 440–445. [Google Scholar] [CrossRef]
- Hernandez, L.; Juliá, J.E.; Chiva, S.; Paranjape, S.; Ishii, M. Fast classification of two-phase flow regimes based on conductivity signals and artificial neural networks. Meas. Sci. Technol. 2006, 17, 1511. [Google Scholar] [CrossRef]
- Rosa, E.S.; Salgado, R.M.; Ohishi, T.; Mastelari, N. Performance comparison of artificial neural networks and expert systems applied to flow pattern identification in vertical ascendant gas–liquid flows. Int. J. Multiph. Flow 2010, 36, 738–754. [Google Scholar] [CrossRef]
- Santoso, B.; Indarto, D.; Thomas, S.W. The identification of gas-liquid co-current two phase flow pattern in a horizontal pipe using the power spectral density and the artificial neural network (ANN). Mod. Appl. Sci. 2012, 6, 56–67. [Google Scholar] [CrossRef]
- Ghosh, S.; Pratihar, D.K.; Maiti, B.; Das, P.K. Identification of flow regimes using conductivity probe signals and neural networks for counter-current gas–liquid two-phase flow. Chem. Eng. Sci. 2012, 84, 417–436. [Google Scholar] [CrossRef]
- Figueiredo, M.M.F.; Goncalves, J.L.; Nakashima, A.M.V.; Fileti, A.M.F.; Carvalho, R.D.M. The use of an ultrasonic technique and neural networks for identification of the flow pattern and measurement of the gas volume fraction in multiphase flows. Exp. Therm. Fluid Sci. 2016, 70, 29–50. [Google Scholar] [CrossRef]
- Abbagoni, B.M.; Yeung, H. Non-invasive classification of gas–liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network. Meas. Sci. Technol. 2016, 27, 84002. [Google Scholar] [CrossRef] [Green Version]
- Zou, S.; Guo, L.; Xie, C. Fast recognition of global flow regime in pipeline-riser system by spatial correlation of differential pressures. Int. J. Multiph. Flow 2017, 88, 222–237. [Google Scholar] [CrossRef]
- Liu, L.; Bai, B. Flow regime identification of swirling gas-liquid flow with image processing technique and neural networks. Chem. Eng. Sci. 2019, 199, 588–601. [Google Scholar] [CrossRef]
- Liu, W.; Xu, Q.; Zou, S.; Chang, Y.; Guo, L. Optimization of differential pressure signal acquisition for recognition of gas–liquid two-phase flow patterns in pipeline-riser system. Chem. Eng. Sci. 2021, 229, 116043. [Google Scholar] [CrossRef]
- Pereyra, E.; Torres, C.; Mohan, R.; Gomez, L.; Kouba, G.; Shoham, O. A methodology and database to quantify the confidence level of methods for gas–liquid two-phase flow pattern prediction. Chem. Eng. Res. Des. 2012, 90, 507–513. [Google Scholar] [CrossRef]
- Kihara, T.; Obata, H.; Hirano, H. Quantitative visualization of fluid mixing in slug flow for arbitrary wall-shaped microchannel using Shannon entropy. Chem. Eng. Sci. 2019, 200, 225–235. [Google Scholar] [CrossRef]
- Jung, S.; Yang, H.; Park, K.; Seo, Y.; Seong, W. Monitoring severe slugging in pipeline-riser system using accelerometers for application in early recognition. Sensors 2019, 19, 3930. [Google Scholar] [CrossRef] [Green Version]
- Hanus, R.; Zych, M.; Kusy, M.; Jaszczur, M.; Petryka, L. Identification of liquid-gas flow regime in a pipeline using gamma-ray absorption technique and computational intelligence methods. Flow Meas. Instrum. 2018, 60, 17–23. [Google Scholar] [CrossRef]
- Xu, Q.; Li, W.; Liu, W.; Zhang, X.; Yang, C.; Guo, L. Intelligent recognition of severe slugging in a long-distance pipeline-riser system. Exp. Therm. Fluid Sci. 2020, 113, 110022. [Google Scholar] [CrossRef]
- Xu, Q.; Zhou, H.; Zhu, Y.; Cao, Y.; Huang, B.; Li, W.; Guo, L. Study of identification of global flow regime in a long pipeline transportation system. Powder Technol. 2020, 362, 507–516. [Google Scholar] [CrossRef]
- Xu, Q.; Liu, C.; Wang, X.; Cao, Y.; Yu, H.; Li, W.; Guo, L. Machine learning classification of flow regimes in a long pipeline-riser system with differential pressure signal. Chem. Eng. Sci. 2021, 233, 116402. [Google Scholar] [CrossRef]
- Du, M.; Yin, H.; Chen, X.; Wang, X. Oil-in-water two-phase flow pattern identification from experimental snapshots using convolutional neural network. IEEE Access 2018, 7, 6219–6225. [Google Scholar] [CrossRef]
- Xu, Z.; Yang, X.; Chen, B.; Zhang, M.; Li, Y. Imaging of Flow Pattern of Gas-Oil Flows with Convolutional Neural Network. In Proceedings of the 2019 IEEE International Conference on Imaging Systems and Techniques (IST), Abu Dhabi, United Arab Emirates, 9–10 December 2019; pp. 1–6. [Google Scholar]
- Zhang, Y.; Azman, A.N.; Xu, K.W.; Kang, C.; Kim, H.B. Two-phase flow regime identification based on the liquid-phase velocity information and machine learning. Exp. Fluids 2020, 61, 212. [Google Scholar] [CrossRef]
- Kuang, B.; Nnabuife, S.G.; Rana, Z. Pseudo-image-feature-based identification benchmark for multi-phase flow regimes. Chem. Eng. J. Adv. 2021, 5, 100060. [Google Scholar] [CrossRef]
- Wang, N.; Zhang, D.; Chang, H.; Li, H. Deep learning of subsurface flow via theory-guided neural network. J. Hydrol. 2020, 584, 124700. [Google Scholar] [CrossRef] [Green Version]
- Lin, Z.; Liu, X.; Lao, L.; Liu, H. Prediction of two-phase flow patterns in upward inclined pipes via deep learning. Energy 2020, 210, 118541. [Google Scholar] [CrossRef]
- Abdul-Majeed, G.H. Liquid holdup in horizontal two-phase gas—Liquid flow. J. Pet. Sci. Eng. 1996, 15, 271–280. [Google Scholar] [CrossRef]
- Al-Dogail, A.S.; Gajbhiye, R.N. Effects of density, viscosity and surface tension on flow regimes and pressure drop of two-phase flow in horizontal pipes. J. Pet. Sci. Eng. 2021, 205, 108719. [Google Scholar] [CrossRef]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Geurts, P.; Ernst, D.; Wehenkel, L. Extremely randomized trees. Mach. Learn. 2006, 63, 3–42. [Google Scholar] [CrossRef] [Green Version]
- Friedman, J.H. Stochastic gradient boosting. Comput. Stat. Data Anal. 2002, 38, 367–378. [Google Scholar] [CrossRef]
- Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
- Zhang, Z. Introduction to machine learning: K-nearest neighbors. Ann. Transl. Med. 2016, 4, 218. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Zhu, J.; Zou, H.; Rosset, S.; Hastie, T. Multi-class AdaBoost. Stat. Its Interface 2009, 2, 349–360. [Google Scholar] [CrossRef] [Green Version]
- O’Shea, K.; Nash, R. An Introduction to Convolutional Neural Networks. arXiv 2015, arXiv:1511.08458. [Google Scholar]
- Sherstinsky, A. Fundamentals of Recurrent Neural Network and Long Short-Term Memory Network. Phys. D Nonlinear Phenom. 2018, 404, 132306. [Google Scholar] [CrossRef] [Green Version]
- Arteaga-Arteaga, H.B.; Mora-Rubio, A.; Florez, F.; Murcia-Orjuela, N.; Diaz-Ortega, C.E.; Orozco-Arias, S.; Tabares-Soto, R. Machine learning applications to predict two-phase flow patterns. PeerJ Comput. Sci. 2021, 7, e798. [Google Scholar] [CrossRef] [PubMed]
ML Algorithm | Instrument | Experimental Measurement | References |
---|---|---|---|
ANN | Pressure Transducer | Pressure | [43] |
Electrical Conductivity Probe | Void Fraction | [44] | |
Electrical Resistivity Probe | Void Fraction | [45] | |
Pressure Transducer | Pressure | [46] | |
Electrical Conductivity Probe | Void Fraction | [47] | |
Doppler Ultrasonic Sensor | Ultrasound Signals | [48] | |
Doppler Ultrasonic Sensor | Ultrasound Signals | [49] | |
Pressure Transducer | Pressure | [50] | |
Camera | Image | [51] | |
Pressure Transducer | Pressure | [52] | |
SOM | Impedance Meter | Void Fraction | [30] |
Neutron Radiography | Images | [31] | |
Conductivity Probe | Bubble Chord Length | [28] | |
Impedance Meter | Void Fraction | [29] | |
Impedance Meter | Void Fraction | [32] | |
BPN | Impedance Void Meter | Void Fraction | [33] |
Neuron Radiography | Images | [34] | |
Pressure Transmitter | Pressure | [58] | |
SVM | Electrical Resistance Tomography | Tomography Image | [39] |
Pressure Transducer | Pressure | [50] | |
Camera | Image | [25] | |
Accelerometer Signal | Superficial Velocity | [55] | |
Optical Probe | Optical Probe Signals | [26] | |
Doppler Ultrasonic Sensor | Ultrasound Signals | [42] | |
CNN | Camera | Image | [60] |
Electrical Capacitance Tomography | Tomography Image | [61] | |
Ultrasound Transducer | Superficial velocity | [62] | |
DNN | Ultrasound Transducer | Superficial Velocity | [65] |
TgNN | None | Theoretical Data | [22] |
SONN | Camera | Image | [51] |
FCN | Pseudo-image Feature | Image | [63] |
VOF | Camera | Image | [54] |
Reference | Institution, Location | Parameters (Inputs: Maximum—Average—Minimum) and Fluids | |
---|---|---|---|
[53] | TelAviv University, Israel University of Tulsa, USA University of Alberta, Canada University of Ohio, USA NASA, USA Intevep, Venezuela Waseda University, Japan SINTEF, USA | ρL: 1059—953—77 kg/m3 ρG: 102.5—4.183—0.125 kg/m3 μL: (483—6.62—0.01) × 10−3 Pa.s μL: (6.96—1.43—0.05) × 10−5 Pa.s σ: 238.07—3.30—0.01 N/m ID: (189—47—9) × 10−3 m Vsl: 25.517—0.792—0.0002 m/s Vsg: 200.61—5.93—0.004 m/s Inclination angle (θ): 90°—3.7°—−90° | |
Liquid: Water Nitrogen Hydrogen Kerosene Oil Naphtha | Gas: Air Nitrogen Hydrogen Carbon dioxide Natural gas | ||
[66] | King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia | Liquid density (ρL): 805—795—790 kg/m3 Gas density (ρG): 10.08—5.08—2.14 kg/m3 Liquid viscosity (μL): (1.98—1.50—1.30) × 10−3 Pa.s Gas viscosity (μL): (1.95—1.91—1.85) × 10−5 Pa.s Surface tension (σ): (2.63—2.45—2.35) × 10−2 N/m Internal diameter (ID): (50.8—50.8—50.8) × 10−3 m Superficial liquid velocity (Vsl): 0.556—0.101—0.0006 m/s Superficial gas velocity (Vsg): 14.91—3.90—0.06 m/s Inclination angle (θ): 0° (Horizontal pipe) | |
Liquid: Kerosene | Gas: Air | ||
[67] | KFUPM, Saudi Arabia | ρL: 1510—1081—1000 kg/m3 ρG: 1.225—1.225—1.225 kg/m3 μL: (3.10—1.54—1.00) × 10−3 Pa.s μL: (1.81—1.81—1.81) × 10−5 Pa.s σ: 0.071—0.057—0.032 N/m ID: (25.4—25.4—25.4) × 10−3 m Vsl: 2.653—0.833—0.049 m/s Vsg: 18.64—6.38—0.008 m/s θ: 0° (Horizontal pipe) | |
Liquid: Water Water + Surfactants Water + Glycerine Water + Calcium bromide + Surfactant | Gas: Air |
Model | Hyperparameters | Range | Six-Class | Three-Class | Two-Class |
---|---|---|---|---|---|
XGBoost | colsample_bytree | (0.5, 5) | 0.9 | 0.9 | 0.9 |
max_depth | (100, 200) | 10 | 25 | 25 200 | |
n_estimators | (10, 25) | 200 | 200 | ||
ET | n_estimators | (1, 150) | 101 | 111 | 141 |
min_samples_split | (2, 100) | 2 | 7 | 2 | |
RF | criterion | (‘gini’, ‘entropy’) | entropy | entropy | gini |
n_estimators | (1, 150) | 111 | 131 | 121 | |
SVM | C | (1, 10) | 9 | 9 | 9 |
gamma | (0.001, 1.0) | 0.9 | 0.9 | 0.9 | |
KNN | leaf_size | (1, 100) | 4 | 1 | 99 |
n_neighbors | (2, 100) | 7 | 7 | 2 | |
weights | (‘uniform’) | uniform | uniform | uniform | |
p | (1, 2) | 1 | 1 | 1 | |
AB | n_estimators | (20, 100) | 100 | 50 | 70 |
learning_rate | (0.0001, 0.3) | 0.2 | 0.2 | 0.3 |
Model | Train Accuracy | Test Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|---|
XGBoost | 0.934 ± 0.74 | 0.943 | 0.943 | 0.943 | 0.943 | 0.913 |
RF | 0.931 ± 0.82 | 0.938 | 0.938 | 0.938 | 0.938 | 0.905 |
ET | 0.929 ± 1.02 | 0.932 | 0.932 | 0.932 | 0.932 | 0.897 |
SVM | 0.871 ± 0.93 | 0.874 | 0.874 | 0.874 | 0.874 | 0.806 |
KNN | 0.861 ± 0.83 | 0.868 | 0.868 | 0.868 | 0.868 | 0.802 |
AB | 0.624 ± 1.05 | 0.597 | 0.493 | 0.597 | 0.520 | 0.294 |
Model | Train Accuracy | Test Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|---|
XGBoost | 0.946 ± 0.84 | 0.955 | 0.955 | 0.955 | 0.955 | 0.921 |
RF | 0.945 ± 0.72 | 0.945 | 0.945 | 0.945 | 0.945 | 0.904 |
ET | 0.946 ± 0.78 | 0.932 | 0.932 | 0.932 | 0.932 | 0.897 |
SVM | 0.899 ± 0.87 | 0.90 | 0.902 | 0.90 | 0.90 | 0.823 |
KNN | 0.887 ± 0.63 | 0.892 | 0.892 | 0.892 | 0.892 | 0.811 |
AB | 0.703 ± 0.95 | 0.704 | 0.745 | 0.701 | 0.685 | 0.441 |
Model | Training Accuracy | Test Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|---|
XGBoost | 0.944 ± 1.10 | 0.95 | 0.95 | 0.95 | 0.95 | 0.90 |
RF | 0.942 ± 0.83 | 0.941 | 0.942 | 0.941 | 0.941 | 0.882 |
ET | 0.944 ± 0.72 | 0.943 | 0.944 | 0.943 | 0.943 | 0.90 |
SVM | 0.90 ± 0.92 | 0.891 | 0.891 | 0.891 | 0.891 | 0.781 |
KNN | 0.895 ± 0.88 | 0.901 | 0.901 | 0.901 | 0.900 | 0.799 |
AB | 0.798 ± 0.95 | 0.779 | 0.785 | 0.779 | 0.778 | 0.555 |
Model | Training Accuracy | Test Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|---|
CNN | 0.961 | 0.921 | 0.921 | 0.921 | 0.921 | 0.88 |
DNN | 0.945 | 0.915 | 0.915 | 0.915 | 0.915 | 0.87 |
RNN | 0.944 | 0.913 | 0.913 | 0.913 | 0.913 | 0.87 |
Model | Training Accuracy | Test Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|---|
DNN | 0.955 | 0.939 | 0.939 | 0.939 | 0.939 | 0.894 |
CNN | 0.965 | 0.931 | 0.931 | 0.931 | 0.931 | 0.879 |
RNN | 0.966 | 0.927 | 0.927 | 0.927 | 0.927 | 0.0872 |
Model | Accuracy | Precision | Recall | F1-Score | Cohens Kappa |
---|---|---|---|---|---|
ET | 0.926 | 0.927 | 0.926 | 0.926 | 0.887 |
XGBoost | 0.924 | 0.924 | 0.924 | 0.923 | 0.883 |
RF | 0.921 | 0.921 | 0.921 | 0.920 | 0.879 |
SVM | 0.807 | 0.803 | 0.807 | 0.801 | 0.697 |
KNN | 0.921 | 0.921 | 0.921 | 0.920 | 0.879 |
AB | 0.609 | 0.555 | 0.609 | 0.532 | 0.303 |
Classification | [76] | [65] | Current Study | ||
---|---|---|---|---|---|
ML Model | DL Model | DL Model | ML Model | DL Model | |
Six-class | 93% | 91% | 90% | 94% | 92% |
Three-class | 94% | 92% | 93% | 95% | 94% |
Classification | [76] | [65] | Current Study | ||
---|---|---|---|---|---|
ML Model | DL Model | DL Model | ML Model | DL Model | |
Six-class | 94% | 91% | 93% | 94% | 93% |
Three-class | 96% | 93% | 94% | 96% | 95% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hafsa, N.; Rushd, S.; Yousuf, H. Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes. Processes 2023, 11, 177. https://doi.org/10.3390/pr11010177
Hafsa N, Rushd S, Yousuf H. Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes. Processes. 2023; 11(1):177. https://doi.org/10.3390/pr11010177
Chicago/Turabian StyleHafsa, Noor, Sayeed Rushd, and Hazzaz Yousuf. 2023. "Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes" Processes 11, no. 1: 177. https://doi.org/10.3390/pr11010177
APA StyleHafsa, N., Rushd, S., & Yousuf, H. (2023). Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes. Processes, 11(1), 177. https://doi.org/10.3390/pr11010177