A proposed model for predicting the drilling path based on hybrid Pso-Bp neural network

In the early days Hydrocarbon wells were normally drilled vertically which rarely requires making decisions. As the technology progressed, the capability to do some deviation of the bit was used resulting in deviated or directional wells to follow the Hydrocarbon formation. This type of drilling requires real-time drilling directions decisions. In this paper, the aim is to develop a real-time intelligent system that can model and predict the optimal drilling path for a new well before actual drilling is done based on the geological layers of the pre-drilled surrounding wells. In the presented work, a hybrid method of stochastic population-based search algorithm (Particle Swarm Optimization) and a gradient based algorithm (Back Propagation) is used to train a Multiplicative Neural Network. The proposed network topology and training algorithms have shown superiority on the traditional Neural Network for determining the drilling optimal drilling path. The proposed system generated proposed drilling plans that achieved more than 88% drilling decision accuracy which is measured according to the actual drilling path.