An oil well working fluid level self-adaptive prediction method based on fuzzy evaluation

Abstract

The invention provides an oil well working fluid level self-adaptive prediction method based on fuzzy evaluation, and relates to the technical field of petroleum production. Firstly,establishing a multi-working-condition prediction model according to production working conditions of an oil field, adopting a reinforcement learning algorithm for different working conditions to establish sub-models,and matching an optimal working condition output model according to different production characteristics; dynamically determining a weighted weight of the integrated sub-model; establishing a fuzzy expert system related to liquid production fluctuation change trend reasoning by utilizing the working fluid level data and the pump efficiency parameters of the on-line measurement output model, and evaluating the working condition model; and performing online self-adaptive updating modeling by utilizing a new model performance evaluation index of fuzzy evaluation, and dynamically updating the model by judging the fitting goodness of the fluctuation change trend of the liquid production amount and an actual value. According to the oil well working fluid level self-adaptive prediction method based on fuzzy evaluation, the defects that when a single model algorithm is used for working fluid level prediction, the prediction precision is not high, the generalization performance is poor, overfitting is likely to happen and the like are effectively overcome.

Description

technical field [0001] The invention relates to the technical field of petroleum production, in particular to an adaptive prediction method for oil well fluid level based on fuzzy evaluation. Background technique [0002] In the actual production process of the oil field, in order to maximize the liquid production, the pumping unit needs to adjust its pumping frequency according to the changing parameters of the oil well to make it reach a reasonable working state. The dynamic liquid level of an oil well is the depth of the liquid level in the annular space of the oil well casing during the production process. It directly reflects the liquid supply capacity of the oil layer and the downhole supply and drainage relationship. an important parameter of . At present, the measurement of dynamic liquid level in most oil wells still adopts traditional manual measurement methods, such as echo measurement, pressure measurement and buoy method, etc. Traditional manual measurement has...

AI Technical Summary

Problems solved by technology

The traditional method of evaluating and updating based on error indicators, due to the time lag in the acquisition of dynamic liquid level data, cannot correct the model in a timely and effective manner, and cannot meet the actual production needs of the oilfield

Images