Drilling speed prediction method based on BP neural network and drilling speed optimization method based on BP neural network and particle swarm algorithm

Abstract

The invention discloses a drilling speed prediction method based on a BP (Back Propagation) neural network, which is used for acquiring torque, drilling pressure, pump pressure and displacement of a drilling tool and predicting the drilling speed based on the BP neural network, and specifically comprises the following steps of: 1, measuring parameters of the torque Nm, the drilling pressure Pm, the pump pressure Pb and the displacement Qm of the drilling tool through a sensor according to a sampling period; 2, normalizing the parameters in sequence, and determining an input layer vector x = {x1, x2, x3, x4} of the three-layer BP neural network; wherein x1 is the torque coefficient of the drilling tool, x2 is the bit pressure coefficient, x3 is the pump pressure coefficient, and x4 is the displacement coefficient; 3, mapping the input layer vector to an intermediate layer; 4, obtaining an output layer vector o = {o1}; wherein o1 is a drilling speed prediction coefficient; and 5, predicting the drilling speed of the drilling tool, namely outputting a drilling speed prediction coefficient of the layer vector in the ith sampling period, omega m _ max being the maximum drilling speed ofthe drilling tool, and omega m (i + 1) being the predicted drilling speed of the drilling tool in the (i + 1) th sampling period. The invention discloses a drilling speed optimization method based ona BP neural network and a particle swarm algorithm.

Description

technical field [0001] The present invention relates to the fields of petroleum exploration and drilling engineering, more specifically, the present invention relates to a drilling speed prediction method based on BP neural network and a drilling speed optimization method based on BP neural network and particle swarm algorithm. Background technique [0002] In the process of oil and gas exploration and exploitation, drilling engineering is an extremely critical link. How to effectively control drilling construction costs, reduce operational risks, and finally achieve safe and fast drilling has become the main goal of experts and scholars in domestic and foreign petroleum companies and schools to study new technologies. For drilling engineering, the primary goal must be safe production and cost savings, and safety and stability mainly depend on standardized operations and safety systems. The cost saving lies in reducing mechanical loss, especially the loss of expensive drill...

AI Technical Summary

Problems solved by technology

Similarly, in this method, the baseline value of the ideal unit of rock-breaking work is disturbed by other factors, and the fluctuation range is large, so it is difficult to determine its specific value. Like the above-mentioned patent, the drilling parameters such as the pressure on bit and the rotational speed need to be continuously adjusted cyclically. , after multiple manual adjustments, the optimal value of a specific stratum can be reached, and the optimization process is not automatic and intelligent enough

Images