Supervised data-driven approach to early kick detection during drilling operation

The margin between pore pressure and fracture gradient in new offshore discoveries continues to get narrower. This poses greater risks and higher cost of ensuring safety of lives, facilities and the environment. The 2010 Macondo blowout has fueled increased interests in monitoring downhole parameter for early kick detection. Early detection of kick is important part of the process safety. It provides opportunity to activate safety measures. This work investigates the simplest supervised learning-based kick detection system to ensure higher reliability using experimental data. It combines an Artificial Neural Network (ANN), binary classifier and downhole monitoring of drilling flow parameters to build data-driven kick detection models. Data was generated from experiment that monitors downhole parameters when kick occurs. Recorded parameters such as mud flow-out rate, conductivity, density and downhole pressure are combined to build the model capable of detecting kick events. Abnormal pressure and flow regimes in the wellbore provide early warnings and was shown to be more significant parameters than others, however relying on them alone could increase susceptibility to a false alarm. The model has been tested on data from two different laboratory scale drilling simulator.