Predicting Rate of Penetration and optimization Weight on bit using Artificial Neural Networks

Abstract

Obtaining the maximum Rate of Penetration (ROP) by optimization drilling parameters is the aim of every drilling engineer. This is because it could save time, reduce cost and minimize drilling problems. However, ROP depends on a lot of parameters which lead to difficulties in its prediction. Therefore, it is necessary and important to investigate a solution predicting ROP with high accuracy to determine the suitable drilling parameters. In this study, a new approach using Artificial Neural Network (ANN) has been proposed to predict ROP from real – time drilling data of several wells in Nam Rong - Doi Moi field with more than 900 datasets included important parameters such as the weight on bit (WOB), weight of mud (MW), rotary speed (RPM), standpipe pressure (SPP), flow rate (FR), torque (TQ). In the process of training the network, algorithms and the number of neurons in the hidden layer were varied to find the optimal model. The ANN model shows high accuracy when compared to actual ROP, therefore it can be recommended as an effective and suitable method to predict the ROP of other wells in the research area. Besides, base on the proposed ANN model, authors carried out experiments and determind the optimal weight on bit value for the drilling interval from 1800 to 2300 m of wells in Nam Rong Doi Moi field