Haifeng Zhang
ABSTRACT
The measurement of the instantaneous flow rate of gas-liquid two-phase flow is a key technology in the industrial production process, and how to build an instantaneous model with long-term cumulative flow labels is also an important technical problem. In order to solve it, we propose a novel CNN (convolutional neural network) modeling algorithm for the instantaneous flow measurement. Firstly, the one-dimensional convolutional neural network is used to build the instantaneous model. Then the long-term flow label slice and average technology are applied for the constraint model. Finally, based on the supervised model, the instantaneous flow model can be trained unsupervised. Test results show that the method can observe instantaneous flow changes and the novel CNN prediction results are generally superior to the other prediction model directly used the average flow samples labels and CNN. The novel CNN modeling algorithm proposes in this paper will have important application value for industrial process measurement.
- Yan Y, Wang L, Wang T, et al. Application of soft computing techniques to multiphase flow measurement: A review[J]. Flow Measurement and Instrumentation, 2018, 60: 30--43.Google Scholar
Cross Ref
- Fan S, Yan T. Two-phase air-water slug flow measurement in horizontal pipe using conductance probes and neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2013, 63(2): 456--466.Google ScholarCross Ref
- Hu D, Li J, Liu Y, et al. Flow Adversarial Networks: Flowrate Prediction for Gas-Liquid Multiphase Flows Across Different Domains[J]. IEEE transactions on neural networks and learning systems, 2019: 1-11Google Scholar
- Zhao C, Wu G, Zhang H, et al. Measurement of water-to-liquid ratio of oil-water-gas three-phase flow using microwave time series method[J]. Measurement, 2019, 140: 511--517.Google ScholarCross Ref
- Chanklan R, Kaoungku N, Suksut K, et al. Runoff Prediction with a Combined Artificial Neural Network and Support Vector Regression[J]. International Journal of Machine Learning and Computing, 2018, 8(1).Google ScholarCross Ref
- Zheng H, Wu C. Predicting Personality Using Facebook Status Based on Semi-supervised Learning[C] //Proceedings of the 2019 11th International Conference on Machine Learning and Computing. ACM, 2019: 59--64.Google Scholar
- Kim B, Ye J C. Multiphase Level-Set Loss for Semi-Supervised and Unsupervised Segmentation with Deep Learning[J]. arXiv preprint arXiv: 1904.02872, 2019.Google Scholar
- Ismail I, Gamio J C, Bukhari S F A, et al. Tomography for multi-phase flow measurement in the oil industry[J]. Flow Measurement and Instrumentation, 2005, 16(2-3): 145--155.Google ScholarCross Ref
- Zhang Q, Xu Y, Zhang T. Wet gas metering based on dual differential pressure of long throat Venturi tube[J]. Journal of Tianjin University, 2012, 45(2): 147--153.Google Scholar
- Hinton G E, Salakhutdinov RR. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786): 504--507.Google Scholar
- Silver D, Huang A, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. nature, 2016, 529(7587): 484--492.Google Scholar
- Wang W, Zhu M, Wang J, et al. End-to-end encrypted traffic classification with one-dimensional convolution neural networks[C]//2017 IEEE International Conference on Intelligence and Security Informatics (ISI). IEEE, 2017: 43--48.Google Scholar
- Yang N, Zheng Z, Wang T. Model Loss and Distribution Analysis of Regression Problems in Machine Learning[C]//Proceedings of the 2019 11th International Conference on Machine Learning and Computing. ACM, 2019: 1--5.Google Scholar
Index Terms
- A Novel CNN Modeling Algorithm for the Instantaneous Flow Rate Measurement of Gas-liquid Multiphase Flow
Recommendations
A numerical method for three-dimensional gas-liquid flow computations
A numerical method for multiphase flow computations based on a finite-difference formulation with a fixed grid is described. The method combines ideas from front tracking and the Ghost Fluid Method, with a numerical technique for velocity extrapolation ...
Computation of three-dimensional multiphase flow dynamics by Fully-Coupled Immersed Flow (FCIF) solver
This work presents a Fully-Coupled Immersed Flow (FCIF) solver for the three-dimensional simulation of fluidfluid interaction by coupling two distinct flow solvers using an Immersed Boundary (IB) method. The FCIF solver captures dynamic interactions ...
Lattice Boltzmann modeling of microchannel flow in slip flow regime
We present the lattice Boltzmann equation (LBE) with multiple relaxation times (MRT) to simulate pressure-driven gaseous flow in a long microchannel. We obtain analytic solutions of the MRT-LBE with various boundary conditions for the incompressible ...
Comments