A ROP Optimization Approach Based on Improved BP Neural Network PSO

Effective optimization of ROP (Rate of Penetration) is a crucial part of successful well drilling process. Due to the penetration complexities and the formation heterogeneity, traditional way such as ROP equations and regression analysis are confined by their limitations in the drilling prediction. Intelligent methods like ANN and PSO become powerful tools to obtain the optimized parameters with the accumulation of the geology data and drilling logs. This paper presents a ROP optimization approach based on improved BP neural network and PSO algorithm. The main idea is, first, to build prediction model of the target well from well logs using BP neural network, and then obtain the optimized well operating parameters by applying PSO algorithm. During the modelling process, the traditional BP training algorithm is improved by introducing momentum factor. Penalty function is also introduced for the constraints fulfillment. We collect and analyze the well log of the No.104 well in Yuanba, China. The experiment results show that the proposed approach is able to effectively utilize the engineering data to provide effective ROP prediction and optimize well drilling parameters.