Application of GA-BP neural network algorithm in killing well control system

Killing operation is an effective measure to restore bottom-hole pressure balance after unbalanced bottom-hole pressure shut-in. In the traditional well killing operation, the opening of the hydraulic throttle valve is manually adjusted by the throttle control box, and the manual control has the problems of uncertainty and low control precision, which makes the stability control of well killing operation a difficult problem. This paper presents a feedback control model based on a large number of real-time bottom-hole data, historical data and GA-BP neural network prediction. Through the intelligent control of throttle valve opening in the process of well killing operation, the fast, accurate and stable self-feedback control of bottom-hole pressure prediction and prediction output is realized. The analysis results show that the control model predicted by GA-BP neural network can effectively adjust the throttle opening and realize the stable and effective control of bottom-hole pressure.