Abstract：Based on random forest algorithms, a prediction and analysis model of the in-use measurement of ultrasonic flowmeter is established to guarantee the accuracy of ultrasonic flowmeter. The study first establishes the in-use measurement procedure of the ultrasonic flowmeter. By obtaining data of the flowmeter signal index, flow rate characteristics,sound velocity and flow velocity etc., the flow deviation of ultrasonic flow meter is predicted by random forest algorithm, and the difference between predicated value and true value is smaller than 0.76%. Furthermore, the degree of influence for different factors on the accuracy of ultrasonic flowmeter are analyzed. The uncertainty of the model is evaluated, with extended uncertainty U=0.92%~0.22%(k=2).
［1］Lynnworth L C, Yi L. Ultrasonic flowmeters: half-century progress report, 1955—2005［J］. Ultrasonics, 2006, 44 (4):e1371-e1378.
［2］Drenthen J G, Boer G D. The manufacturing of ultrasonic gas flowmeters［J］. Flow Measurement and Instrumentation, 2002, 12 (2):89-99.
［3］Zhou A G, Ruan J Y, Liu K, et al. Analysis and strategy for impacts on ultrasonic flowmeters［J］. Chinese Journal of Construction Machinery, 2009, 7(4):469-473.
［4］JJG 1030—2007超声流量计检定规程［S］. 2007.
［5］Mitchell T M. Machine Learning［M］. New York:McGraw-Hill, 2003.
［6］Zhao H, Peng L, Takahashi T, et al. ANN Based Data Integration for Multi-Path Ultrasonic Flowmeter［J］. IEEE Sensors Journal, 2013, 14 (2): 362-370.
［7］Zheng D, Zhang P, Xu T. Study of acoustic transducer protrusion and recess effects on ultrasonic flowmeter measurement by numerical simulation［J］. Flow Measurement & Instrumentation, 2011, 22 (5):488-493.
［8］李跃忠, 李昌禧, 华志斌. 基于神经网络的多声道超声气体流量计研究［J］. 仪器仪表学报, 2007, 28(12):170-174.
Li Y Z, Li C X, Hua Z B.Research on multipath ultrasonic gas flowmeter based on neural network［J］. Chinese Journal of Scientific Instrument, 2007, 28(12):170-174.
［9］张立峰,朱炎峰. 基于MO-PLP-ELM及电容层析成像的两相流流型辨识［J］. 计量学报, 2021, 42 (3):334-338.
Zhang L F, Zhu Y F. Identification of Two-phase Flow Based on MO-PLP-ELM and Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2021, 42 (3):334-338.
［10］Yeh T T, Espina P I, Osella S A. An intelligent ultrasonic flowmeter for improved flow measurement and flow calibration facility［C］// IEEE. IEEE Instrumentation & Measurement Technology Conference.2002.
［11］GB/T 30500—2014气体超声流量计使用中检验声速检验法［S］. 2014.
［12］Breiman L. Random forest［J］. Machine Learning, 2001, 45:5-32.
［13］陈剑,蔡坤奇,陶善勇,等. 基于IITD模糊熵与随机森林的滚动轴承故障诊断方法［J］. 计量学报, 2021, 42 (6):774-779.
Chen J, Cai K Q,Tao S Y, et al. Fault Diagnosis Method of Rolling Bearing Based on IITD Fuzzy Entropy and Random Forest［J］. Acta Metrologica Sinica, 2021, 42(6):774-779.
［14］Dietterich T G. An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization［J］. Machine Learning, 2000, 40 (2):139-157.
［15］Pan X Y, Shen H B. Robust prediction of B-factor profile from sequence using two-stage SVR based on random forest feature selection［J］. Protein & Peptide Letters, 2009, 16 (12):1447-1454.
［16］Al-Mukhtar M. Random forest, support vector machine, and neural networks to modelling suspended sediment in Tigris River-Baghdad ［J］. Environmental Monitoring and Assessment, 2019, 191(11): 673.1-673.12.
［17］周志华. 机器学习［M］. 北京:清华大学出版社, 2016.
［18］Ling J, Templeton J. Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty［J］. Physics of Fluids, 2015, 27 (8):042032-94.
［19］Solomatine D P, Shrestha D L. A novel method to estimate model uncertainty using machine learning techniques［J］. Water Resources Research, 2009, 45 (12): W00B11.
［20］Lie M, Glaser B, Huwe B. Uncertainty in the spatial prediction of soil texture: Comparison of regression tree and Random Forest models［J］. Geoderma, 2012, 170 (3):70-79.
［21］AGA Transmission Measurement Committee Report No.10, Speed of Sound in Natural Gas and Others Related Hydrocarbon Gases［S］. 2003.
2022, Vol. 43 
