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

Abstract 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.

[1]  Shuai Zhang,et al.  A new pattern recognition model for gas kick diagnosis in deepwater drilling , 2018, Journal of Petroleum Science and Engineering.

[2]  F. Khan,et al.  Experimental investigation of gas kick effects on dynamic drilling parameters , 2018, Journal of Petroleum Exploration and Production Technology.

[3]  David Hargreaves,et al.  Early Kick Detection for Deepwater Drilling: New Probabilistic Methods Applied in the Field , 2001 .

[4]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[5]  Ali Karimi Vajargah,et al.  Early kick detection and well control decision-making for managed pressure drilling automation , 2015 .

[6]  David Ha,et al.  long short term memory , 2015 .

[7]  Mohammed A. Ahmed,et al.  Early detection enhancement of the kick and near-balance drilling using mud logging warning sign , 2016 .

[8]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Fatemeh Deregeh,et al.  A New Method of Earlier Kick Assessment Using ANFIS , 2013 .

[10]  David W. Miller,et al.  Busting the Black Box Myth: Designing Out Unwanted ADMET Properties with Machine Learning Approaches , 2009 .

[11]  Andre Leibsohn Martins,et al.  Neural network based controllers for the oil well drilling process , 2019, Journal of Petroleum Science and Engineering.

[12]  Ramachandran Venkatesan,et al.  Monitoring of down-hole parameters for early kick detection , 2016 .

[13]  Hadi Fattahi,et al.  Applying improved artificial neural network models to evaluate drilling rate index , 2017 .

[14]  Mark Hibbard,et al.  Machine Learning Algorithms Applied to Detection of Well Control Events , 2017 .

[15]  Farough Agin,et al.  Application of decision tree, artificial neural networks, and adaptive neuro-fuzzy inference system on predicting lost circulation: A case study from Marun oil field , 2019, Journal of Petroleum Science and Engineering.

[16]  Phil Griffin.  Early Kick Detection Holds Kill Pressure Lower , 1967 .

[17]  Julius U. Akpabio,et al.  Artificial intelligence techniques and their applications in drilling fluid engineering: A review , 2018, Journal of Petroleum Science and Engineering.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Suresh Venugopal,et al.  Time series data analysis for automatic flow influx detection during drilling , 2019, Journal of Petroleum Science and Engineering.

[20]  Shahab D. Mohaghegh,et al.  Petroleum reservoir characterization with the aid of artificial neural networks , 1996 .

[21]  Jacek M. Zurada,et al.  Learning Understandable Neural Networks With Nonnegative Weight Constraints , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Lakhmi C. Jain,et al.  Recurrent Neural Networks: Design and Applications , 1999 .

[23]  Salaheldin Elkatatny,et al.  Real time prediction of drilling fluid rheological properties using Artificial Neural Networks visible mathematical model (white box) , 2016 .

[24]  Kwang Yeom Kim,et al.  Predicting rate of penetration during drilling of deep geothermal well in Korea using artificial neural networks and real-time data collection , 2019, Journal of Natural Gas Science and Engineering.

[25]  Faisal Khan,et al.  Real time risk analysis of kick detection: Testing and validation , 2017, Reliab. Eng. Syst. Saf..

[26]  M. Sam Mannan,et al.  Developing leading indicators-based decision support algorithms and probabilistic models using Bayesian network to predict kicks while drilling , 2019, Process Safety and Environmental Protection.

[27]  Seyed Babak Ashrafi,et al.  Application of hybrid artificial neural networks for predicting rate of penetration (ROP): A case study from Marun oil field , 2019, Journal of Petroleum Science and Engineering.

[28]  Chris Eliasmith,et al.  Solving the Problem of Negative Synaptic Weights in Cortical Models , 2008, Neural Computation.

[29]  Fathi M. Salem,et al.  Gate-variants of Gated Recurrent Unit (GRU) neural networks , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[30]  Saba Mylvaganam,et al.  Flow Rate Estimation using Dynamic Artificial Neural Networks with Ultrasonic Level Measurements , 2018 .

[31]  Ming Yang,et al.  Dynamic failure analysis of process systems using neural networks , 2017 .

[32]  M. Sam Mannan,et al.  A framework for developing leading indicators for offshore drillwell blowout incidents , 2017 .

[33]  Liangbin Xu,et al.  Development and testing of kick detection system at mud line in deepwater drilling , 2015 .