Abstract：A flow pattern identification method of gas-liquid two-phase flow based on deep forest algorithm and electrical resistance tomography (ERT) was proposed. Firstly, ERT experimental device was used to collect data of four typical flow patterns, and the collected data was preprocessed by averaging multi-frame data. Then, some proper basic classifiers were selected to construct a deep forest model, and the maximum number of layers of the model was adjusted to ensure the accuracy of classification. Finally, the validity of multi-frame data averaging and the flow pattern identification ability of deep forest model were verified, and compared with two traditional deep learning algorithms, deep neural network and convolutional neural network. The results show that the accuracy of flow pattern identification of deep forest is better than that of other two algorithms, and the average identification accuracy can reach 98.75%. The preprocessing method of multi-frame data averaging is more conducive to flow pattern identification.
Zhang L F, Zhu Y F. Two phase flow pattern identification based on MO-PLP-ELM and electrical capacitance tomography［J］. Acta metrologica Sinica, 2021, 42(3):334-338.
Hu H L, Tang K H, Tang C H, et al. Principle and application of two-phase flow parameter detection based on capacitance sensor ［J］. Journal of Northwest University, 2019, 49 (5): 681-690.
Sun H L, Li Y L, Liu C L, et al Electrical resistance tomography technology and its application in hydrate mining simulation experiment［J］. Acta Metrologica Sinica, 2019, 40 (3): 455-461.
［7］
Guo W, Liu C P, Wang L. Temperature fluctuation on pipe wall induced by gas-liquid flow and its application in flow pattern identification［J］. Chemical Engineering Science, 2021, 237:116568.
Tong W G, Pang X C, Zhu G H. Gas-liquid Two-phase Flow Pattern Recognition Method Based on Convolutional Neural Network ［J］. Journal of System Simulation, 2021, 33(4):883-891.
Li G Y, Li H P, Wan H W, et al. Application of random forest algorithm in the study of influencing factors of species richness in Xinjiang ［J］. China Environmental Science, 2021,41 (2): 941-950.
Jin K G, Yu D J. Protein contact graph prediction based on Weighted Naive Bayes classifier and extreme random tree ［J］. Journal of Nanjing University of Aeronautics and Astronautics, 2018, 50(5):619-628.
Cultrera A, Milano G, De L N, et al. Recommended implementation of electrical resistance tomography for conductivity mapping of metallic nanowire networks using voltage excitation［J］. Scientific Reports, 2021, 11(1):13162-13167.
Chen J, Cai K Q, Tao S Y, et al. Rolling bearing fault diagnosis method based on IITD fuzzy entropy and random forest［J］. Acta Metrologica Sinica, 2021,42(6):774-779.
Liu S G, Dong X, Lou X, et al. Classification and density inversion of wetland plants based on Optimization of random forest characteristic variables ［J］. Journal of Tongji University:Natural Science, 2021, 49(5):695-704.
Wang X X, Wang B, Chen Y Z, et al. Two phase flow pattern recognition based on reconstructed image of electrical capacitance tomography ［J］. Acta Metrologica Sinica, 2020, 41(8):942-946.
Li K F, Wang B L, Huang Z Y, et al. Application of k-means clustering in flow pattern identification of CCERT system ［J］. Journal of Beijing University of Aeronautics and Astronautics: Natural Science, 2017, 43 (11): 2280-2285.
［11］
Mao S S, Yang J Y, Gou S P, et al. Multi-Scale Fused SAR Image Registration Based on Deep Forest［J］. Remote Sensing, 2021, 13(11):2227.
［15］
Xu Y H, Zhao X, Chen Y S, et al. Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree［J］. Applied Sciences, 2019, 9(9):1728.
Xu C L, Liu X B, Wang H K, et al. A study of predicting irradiation-induced transition temperature shift for RPV steels with XGBoost modeling［J］. Nuclear Engineering and Technology, 2021, 53(8):2610-2615.
［21］
Fan Y, Qi L, Tie Y. The Cascade Improved Model Based Deep Forest for Small-scale Datasets Classification ［J］. International Symposium on Next Generation Electronics, 2019, 8(10):1-3.
Zhang L F, Wang H X. Two phase flow pattern recognition based on SVM and electrical capacitance tomography ［J］. Journal of instrumentation, 2009, 30 (4): 812-816.
Wu X J, Huang G X, Wang J W. Application of compressed sensing in flow pattern identification of electrical capacitance tomography ［J］. Optical precision engineering, 2013, 21(4):1062-1068.
Zhang Y, Xu T H, Chen C, et al. A hierarchical method based on improved deep forest and case-based reasoning for railway turnout fault diagnosis［J］. Engineering Failure Analysis, 2021, 127.
Xu W, Xia Z X, Xing H Y. Lightning warning method based on integrated empirical mode decomposition and extreme gradient lifting ［J］. Journal of instrumentation, 2020, 41(8):235-243.
Zhang Y W, Feng B, Chen Y, et al. Fault diagnosis method of oil immersed transformer based on genetic algorithm optimization of xgboost ［J］. Power automation equipment, 2021, 41(2):200-206.
2023, Vol. 44 
