A real-time drilling parameters optimization method for offshore large-scale cluster extended reach drilling based on intelligent optimization algorithm and machine learning

Offshore large-scale cluster extended reach wells (ERWs) are widely used to develop offshore oil & gas resources. Due to the complex downhole environments and complicated geological conditions, drilling parameters real-time optimization is challenging in offshore large-scale cluster ERWs drilling. In this paper, a real-time drilling parameters optimization method for offshore large-scale cluster extended reach drilling based on an intelligent optimization algorithm and machine learning (IOA-ML) is proposed. The method takes ROP as the objective function, establishes a ROP model based on long short-term memory (LSTM) neurons, and obtains drilling parameters optimization results asynchronously by combining the genetic algorithm, differential evolution algorithm, and particle swarm algorithm. The results show that ROP has been improved by 33.33% on average after the optimization by this real-time intelligent optimization method with an optimization time within 60s, which meets the requirements of real-time optimization of drilling parameters.

Automated summary

This paper proposes a real-time drilling parameters optimization method for offshore large-scale cluster extended reach drilling based on intelligent optimization algorithm and machine learning. By establishing a ROP model with long short-term memory neurons, and combining genetic algorithm, differential evolution algorithm, and particle swarm algorithm, the method achieves real-time optimization of drilling parameters and significantly improves the ROP.