Dynamic estimation method and device for production and operation working conditions of natural gas shaft

Abstract

The invention provides a natural gas shaft production operation condition dynamic estimation method and device, and the method comprises the steps: obtaining production data, carrying out the ash bin system identification of a natural gas shaft through employing an identification technology constructed by a learning algorithm according to the production data, building a dynamic identification model library of a nonlinear autoregression ash bin, and carrying out the dynamic estimation of the production operation condition of the natural gas shaft. Constructing a shaft state space equation; constructing a state transition equation according to the identification model in the dynamic identification model library, constructing an observation equation through the observation matrix, and reconstructing a shaft state space equation through the state transition equation and the observation equation; combining the reconstructed wellbore state space equation with unscented Kalman filtering-ensemble Kalman filtering to fuse the estimated value of the identification model and the measured value of the wellbore observation point; and according to the fused estimation value and measurement value, fusing the estimation result of the unscented Kalman filter-ensemble Kalman filter, and carrying out dynamic estimation on the production operation condition of the natural gas shaft to obtain a target estimation value.

Description

technical field [0001] The invention relates to the field of fluid calculation, in particular to a method and device for dynamically estimating the production and operation conditions of a natural gas wellbore. Background technique [0002] With the development of offshore oil and gas resources, the operation monitoring of offshore natural gas production system based on gas-liquid two-phase flow mixed transportation technology faces the following problems. First, the high installation and maintenance costs make the installation of multiphase flowmeters insufficient, and the single well production cannot be observed. Second, for observable variables such as temperature and pressure, the real-time production data collected by its sensors will be disturbed by significant errors and random errors, making the measured data violate the basic control equations; these errors usually come from the uncertainty of the instrument itself, ocean currents Disturbances and manual calibrati...

AI Technical Summary

Problems solved by technology

First, the high installation and maintenance costs make the installation of multiphase flowmeters insufficient, and the production of single wells cannot be observed

Second, for observable variables such as temperature and pressure, the real-time production data collected by the sensors will be disturbed by significant errors and random errors, making the measured data violate the basic control equations; these errors usually come from the uncertainty of the instrument itself, ocean currents disturbances and manual calibration errors, etc.

Third, the subsea environment is harsh, and instruments face a higher risk of failure, especially the temperature and pressure sensors at the bottom of the well

Therefore, it is difficult to directly obtain effective and reliable production and operation information

Images