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

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