Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning

  • Hong Xu (Sino-French Institute of Nuclear Engineering and Technology, Sun Yat-sen University) ;
  • Tao Tang (School of Microelectronics and Communication Engineering, Chongqing University)
  • Received : 2022.01.08
  • Accepted : 2022.07.23
  • Published : 2022.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system.

Keywords

References

  1. C. Sunde, S. Avdic, I. Pazsit, Classification of two-phase flow regimes via image analysis and a neuro-wavelet approach, Progress in Nuclear Energy 46 (3-4) (2005) 348-358.  https://doi.org/10.1016/j.pnucene.2005.03.015
  2. D. Ju, Z. Huang, X. Jia, X. Qiao, J. Xiao, Z. Huang, Macroscopic characteristics and internal flow pattern of dimethyl ether flash-boiling spray discharged through a vertical twin-orifice injector, Energy 114 (2016) 1240-1250.  https://doi.org/10.1016/j.energy.2016.08.082
  3. J.E. Julia, Y. Liu, S. Paranjape, M. Ishii, Upward vertical two-phase flow local flow regime identification using neural network techniques, Nuclear Engineering and Design 238 (2008) 156-169.  https://doi.org/10.1016/j.nucengdes.2007.05.005
  4. Z. Wang, B. Bai, Instrument of on line streamline recognition for multiple-phase stream of oil-gas and water, Process Automation Instrumentation 23 (5) (2002) 5-9. 
  5. H. Chen, J. Xu, Z. Li, F. Xing, J. Xie, Stratified two-phase flow pattern modulation in a horizontal tube by the mesh pore cylinder surface, Applied Energy 112 (2013) 1283-1290.  https://doi.org/10.1016/j.apenergy.2012.11.062
  6. S.G. Nnabuife, B. Kuang, Z.A. Rana, J. Whidborne, Classification of flow regimes using a neural network and a non-invasive ultrasonic sensor in an S-shaped pipeline-riser system, Chemical Engineering Journal Advances 9 (2022), 100215. 
  7. Z. Lin, X. Liu, L. Lao, H. Liu, Prediction of Two-phase Flow Patterns in Upward Inclined Pipes via Deep Learning, Energy, 2020, 118541. 
  8. P. Tang, J. Yang, J. Zheng, I. Wong, S. He, J. Ye, G. Ou, Failure analysis and prediction of pipes due to the interaction between multiphase flow and structure, Engineering Failure Analysis 16 (5) (2009) 1749-1756.  https://doi.org/10.1016/j.engfailanal.2009.01.002
  9. K. Jiao, J. Bachman, Y. Zhou, J.W. Park, Effect of induced cross flow on flow pattern and performance of proton exchange membrane fuel cell, Applied Energy 115 (2014) 75-82.  https://doi.org/10.1016/j.apenergy.2013.10.026
  10. Y. Liu, Z. Zhao, Y. Li, Real-time quality monitoring and diagnosis using convolutional neural network: an application to the pasting process of battery manufacturing, in: J. Hung, N. Yen, J.W. Chang (Eds.), Frontier Computing. FC 2019. Lecture Notes in Electrical Engineering, vol. 551, Springer, Singapore, 2020. 
  11. T. Tambouratzis, I. Pazsit, A general regression artificial neural network for two-phase flow regime identification, Annals of Nuclear Energy 37 (5) (2010) 672-680.  https://doi.org/10.1016/j.anucene.2010.02.004
  12. C.M. Salgado, C.M.N.A. Pereira, R. Schirru, L.E.B. Brandao, Flow regime identification and volume fraction prediction in multiphase flows by means of gamma-ray attenuation and artificial neural networks, Progress in Nuclear Energy 52 (6) (2010) 555-562.  https://doi.org/10.1016/j.pnucene.2010.02.001
  13. A.M.C. Chan, D. Bzovey, Measurement of mass flux in high temperature pressure steam-water two-phase flow using a combination of Pitot tubes and a gamma densitometer, Nuclear Engineering and Design 122 (1990) 95-104.  https://doi.org/10.1016/0029-5493(90)90199-8
  14. L. Hernandez, J.E. Julia, S. Chiva, S. Paranjape, M. Ishii, Fast classification of two-phase flow regimes based on conductivity signals and artificial neural networks, Measurement Science and Technology 17 (2006) 1511-1521.  https://doi.org/10.1088/0957-0233/17/6/032
  15. Z. Yang, H. Ji, Z. Huang, B. Wang, Application of convolution neural network to flow pattern identification of gas-liquid two-phase flow in small-size pipe, Proceedings of 2017 Chinese Automation Congress (CAC) (2017) 20-22. Jinan,China, October. 
  16. C. Shen, Q. Zheng, M. Shang, L. Zha, Y. Su, Using deep learning to recognize liquid-liquid flow patterns in microchannels, AIChE Journal 66 (2020), e16260, 2020. 
  17. A.M. Quintino, D.L.L.N. da Rocha, R.F. Junior, O.M.H. Rodriguez, Flow pattern transition in pipes using data-driven and physics-informed machine learning, Journal of Fluids Engineering 143 (2021), 031401. 
  18. Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based Learning Applied to Document Recognition, Porceedings of the IEEE, USA, 1998, pp. 2278-2324. 
  19. M. Du, H. Yin, X. Chen, X. Wang, Oil-in-water two-phase flow pattern identification from experimental snapshots using convolutional neural network, IEEE Access 7 (2019) 6219-6225.  https://doi.org/10.1109/ACCESS.2018.2888733
  20. J. Zhao, F. Dong, C. Tan, Fast flow regime recognition method of gas/water two-phase flow based on extreme learning machine, IEEE International Instrumentation and Measurement Technology Conference (I2MTC) (2013) 1807-1811. 
  21. T. Xie, S.M. Ghiaasiaan, S. Karrila, Flow regime identification in gas/liquid/pulp fiber slurry flows based on pressure fluctuations using artificial neural networks, Industrial & Engineering Chemistry Research 42 (26) (2003) 7017-7024.  https://doi.org/10.1021/ie0304199
  22. D. Xie, Z. Huang, H. Ji, H. Li, An online flow pattern identification system for gas-oil two-phase flow using electrical capacitance tomography, IEEE Transactions on Instrumentation and Measurement 55 (5) (2006) 1833-1838.  https://doi.org/10.1109/TIM.2006.881558
  23. S.G. Nnabuife, B. Kuang, J.F. Whidborne, Z. Rana, Non-intrusive classification of gas-liquid flow regimes in an S-shaped pipeline riser using a Doppler ultrasonic sensor and deep neural networks, Chemical Engineering Journal 403 (2021), 126401. 
  24. B. Kuang, S.G. Nnabuife, S. Sun, J.F. Whidborne, Z.A. Rana, Gas-liquid flow regimes identification using non-intrusive Doppler ultrasonic sensor and convolutional recurrent neural networks in an s-shaped riser, Digital Chemical Engineering 2 (2022), 100012. 
  25. F. Chiarello, P. Belingheri, G. Fantoni, Data science for engineering design: state of the art and future directions, Computers in Industry 129 (2021), 103447. 
  26. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, CoRR abs/1409 (2014) 4842. 
  27. K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, Proceeding of International Conference on Learning Representations (ICLR2015), 2015. 
  28. K. He, X. Zhang, S. Ren, J. Sun, Identity mappings in deep residual networks, European Conference on Computer Vision (ECCV) (2016) 630-645, 2016. 
  29. R. Yamashita, M. Nishio, R.K.G. Do, K. Togashi, Convolutional neural networks: an overview and application in radiology, Insights into Imaging 9 (2018) 611-629.  https://doi.org/10.1007/s13244-018-0639-9
  30. Y. Kim, Convolutional neural networks for sentence classification, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, 2014. 
  31. M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional neural networks, European conference on computer vision (ECCV) 2014, I, LNCS 8689 (2014) 818-833. 
  32. J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Gai, T. Chen, Recent advances in convolutional neural networks, Pattern Recognition 77 (2018) 354-377.  https://doi.org/10.1016/j.patcog.2017.10.013
  33. H. Wu, Q. Huang, D. Wang, L. Gao, A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals, Journal of Electromyography and Kinesiology 42 (2018) 136-142.  https://doi.org/10.1016/j.jelekin.2018.07.005
  34. A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA 2 (2012) 1097-1105. 
  35. Q. Li, W. Cai, X. Wang, Y. Zhou, D.D. Feng, M. Chen, Medical Image Classification with Convolutional Neural Network, 13th International Conference on Control Automation Robotics & Vision (ICARCV), Singapore, 2014, pp. 844-848. 
  36. X. Lei, H. Pan, X. Huang, A dilated CNN model for image classification, IEEE Access 7 (2019) 124087-124095.  https://doi.org/10.1109/ACCESS.2019.2927169
  37. S. Lu, Z. Lu, Y.D. Zhang, Pathological brain detection based on AlexNet and transfer learning, Journal of Computational Science 30 (2018) 41-47. 
  38. J. Llamas, P.M. Lerones, R. Medina, E. Zalama, J. Gomez-Garcia-Bermejo, Classification of architectural heritage images using deep learning techniques, Applied Sciences 7 (10) (2017) 992. 
  39. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016) 2921-2929. 
  40. F.N. Iandola, S. Han, M.W. Moskewicz, K. Ashraf, W.J. Dally, K. Keutzer, SqueezeNet: AlexNet-level accuracy with 50 × fewer parameters and <0.5 MB model size, 2016. https://arxiv.org/pdf/1602.07360.pdf. 
  41. W. Sun, Z. Zhang, J. Huang, RobNet: real-time road-object 3D point cloud segmentation based on SqueezeNet and cyclic CRF, Soft Computing 24 (2020) 5805-5818.  https://doi.org/10.1007/s00500-019-04355-y
  42. C. Xia, Z. Pan, Z. Fei, S. Zhang, H. Li, Vision based defects detection for Keyhole TIG welding using deep learning with visual explanation, Journal of Manufacturing Processes 56 (2020) 845-855.  https://doi.org/10.1016/j.jmapro.2020.05.033
  43. C. Gonzalez-Val, A. Pallas, V. Panadeiro, et al., A convolutional approach to quality monitoring for laser manufacturing, Journal of Intelligent Manufacturing 31 (2020) 789-795.  https://doi.org/10.1007/s10845-019-01495-8
  44. O. Russakovsky, J. Deng, H. Su, et al., ImageNet large scale visual recognition challenge, International Journal of Computer Vision 115 (2015) 211-252.  https://doi.org/10.1007/s11263-015-0816-y
  45. I. Sutskever, J. Martens, G. Dahl, G. Hinton, On the importance of initialization and momentum in deep learning, Proceedings of the 30th International Conference on Machine Learning, PMLR 28 (3) (2013) 1139-1147. 
  46. H. Chu, X. Liao, P. Dong, Z. Chen, X. Zhao, J. Zou, An automatic classification method of well testing plot based on convolutional neural network (CNN), Energies 12 (2019) 2846. 
  47. A.J. Ghajar, Two-Phase Gas-Liquid Flow in Pipes with Different Orientations, Springer International Publishing, Cham, Switzerland, 2020. 
  48. Y. Bengio, Y. Grandvalet, No unbiased estimator of the variance of K-fold cross-validation, Journal of Machine Learning Research 5 (2004) 1089-1105. 
  49. H. Xu, T. Tang, B. Zhang, Y. Liu, Identification of two-phase flow regime in the energy industry based on modified convolutional neural network, Progress in Nuclear Energy 147 (2022), 104191. 
  50. T. Lundstrom, J. Baqersad, C. Niezrecki, Monitoring the dynamics of a helicopter main rotor with high-speed stereophotogrammetry, Experimental Techniques 40 (2016) 907-919.  https://doi.org/10.1007/s40799-016-0092-y
  51. M. Al-Naser, M. Elshafei, A. Al-Sarkhi, Artificial neural network application for multiphase flow patterns detection: a new approach, Journal of Petroleum Science and Engineering 145 (2016) 548-564. https://doi.org/10.1016/j.petrol.2016.06.029