With the expansion of oil and gas exploration and the development of complex oil and gas resource areas, the probability of risk is increasing. Kick is one of the high-risk risks of drilling, and timely and accurate early warning is increasingly important. Based on the kick generation mechanism, kick characterization parameters are preliminarily selected. According to the characteristics of the data and previous research progress, Random Forest (RF), Support Vector Machine (SVM), Fully Connected Neural Network (FNN), and Long Short-term Memory Neural Network (LSTM) are established using experimental data from Memorial University of Newfoundland. The test results show that the accuracy of the SVM-linear model is 0.952, and the missing alarm, the false alarm rate is only 0.064, 0.035. Also, through the analysis of the kick response time, the lag time of the SVM-linear model is 3.6s, and the comprehensive equivalent time is 23.13, which shows the best performance. This paper lays a good foundation for the establishment of an intelligent kick early warning model.
18 December 2024 in Geoenergy Science and Engineering
Accurate description of cuttings slippage in the gas-liquid phase is of great significance for wellbore cleaning and the control accuracy of bottom hole pressure during MPD. In this study, the wellbore bubble flow environment was simulated by a constant pressure air pump and the transparent wellbore, and the settling characteristics of spherical particles under different gas volume concentrations were recorded and analyzed by highspeed photography. A total of 225 tests were conducted to analyze the influence of particle diameter (1–12mm), particle density (2700–7860kg/m^3), liquid viscosity and bubble volume concentration on particle settling velocity. Gas drag force is defined to quantitatively evaluate the bubble’s resistance to particle slippage. The relationship between bubble drag coefficient and particle Reynolds number is obtained by fitting the experimental results. An explicit settling velocity equation is established by introducing Archimedes number. This explicit equation with an average relative error of only 8.09% can directly predict the terminal settling velocity of the sphere in bubble containing Newtonian fluids. The models for predicting bubble drag coefficient and the terminal settling velocity are valid with particle Reynolds number ranging from 0.05 to 167 and bubble volume concentration ranging from 3.0% to 20.0%. Besides, a trial-and-error procedure and an illustrative example are presented to show how to calculate bubble drag coefficient and settling velocity in bubble containing fluids. The results of this study will provide the theoretical basis for wellbore cleaning and accurate downhole pressure to further improve the performance of MPD in treating gas influx.