A Data Driven Approach in Screenout Detection for Horizontal Wells
- Xiaodan Yu (Colorado School of Mines) | Whitney Trainor-Guitton (Colorado School of Mines) | Jennifer Miskimins (Colorado School of Mines)
- Document ID
- Society of Petroleum Engineers
- SPE Hydraulic Fracturing Technology Conference and Exhibition, 4-6 February, The Woodlands, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2020. Society of Petroleum Engineers
- Machine Learning, Time Series Analysis, Hydraulic Fracturing, Statistical Model, Hidden Markov Model
- 5 in the last 30 days
- 332 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Multi-stage hydraulic fracturing has gained popularity all over the world as more tight geologic formations are developed economically for hydrocarbon resources. However, due to the stages' operating complexity, different kinds of disruptions in fracturing operations may occur and even result in great economic loss. Screenout is one of the issues caused by the blockage of proppant inside the fractures. This paper presents a screenout classification system based on Gaussian Hidden Markov Models (GHMMs), trained on simulated data, that predicts screenouts and provides early warning by learning pre-screenout patterns in the simulated surface pressure signals. The simulated data are generated in a hydraulic fracturing software using a horizontal well with three fracturing stages landing in the Niobrara B shale, Denver-Julesburg (DJ) Basin. During the 270 simulations, various synthetic fracturing treatment data are forward modeled for both screenout and non-screenout scenarios. The classification system consists of two Gaussian Hidden Markov Models (screenout and non-screenout), each of which is fitted and optimized by its respective training set. Both Hidden Markov Models are assigned with two 1D Gaussian probability density functions to represent the distribution of their associated simulated surface pressure signals. During the classification process, once a new surface pressure sequence is observed, the maximum log likelihood is calculated under both fitted models and the model with a greater likelihood will be predicted as the class of this new observation. The classification system is validated with a hold-out testing data set from the simulations and the statistics of the performance is visualized in a confusion matrix. The results indicate the classification system achieves an overall classification accuracy of 81% and an accuracy of 86% for successfully predicting screenout events around 8.5 minutes prior to screenout occurring in the simulation. The described methodology is demonstrated to be a useful tool for early screenout detection and shows its promising feasibility of other fracturing time-series data analysis.
|File Size||1 MB||Number of Pages||13|
Massaras, L. V., and McNealy, T. R. 2012. Highly Accurate Prediction of Screenouts in the Eagle Ford Shale with the Screenout Index. Presented at SPE Annual Technical Conference and Exhibition, 8-10 October, San Antonio, Texas, USA. https://doi:10.2118/157613-MS.
Nolte, K. G. and Smith, M. B. 1979. Interpretation of Fracturing Pressures. Presented at the SPE Annual Technical Conference and Exhibition, 23-26 September, Las Vegas, Nevada. http://doi.org/10.2118/8297-MS.
Nordgren, R. P. 1972. Propagation of a Vertical Hydraulic Fracture. Society of Petroleum Engineers Journal, 12(04): 306-314. http://doi:10.2118/3009-PA
Speight, James G. 2017. Deep Shale Oil and Gas, second edition, 200. Gulf Professional Publishing, Boston: Chapter three - gas and oil resources in tight formations, 121-174. https://doi.org/10.1016/B978-0-12-803097-4.00003-6.