Completion Design Improvement Using a Deep Convolutional Network
- Liwei Li (West Virginia University) | Nasser Nasrabadi (West Virginia University) | Timothy Carr (West Virginia University)
- Document ID
- Society of Petroleum Engineers
- SPE Annual Technical Conference and Exhibition, 26-29 October, Virtual
- Publication Date
- Document Type
- Conference Paper
- 2020. Society of Petroleum Engineers
- 4.3.4 Scale, 0.2.2 Geomechanics, 3 Production and Well Operations, 3 Production and Well Operations, 5 Reservoir Desciption & Dynamics, 2.1 Completion Selection and Design, 1.6 Drilling Operations, 2.1 Completion Selection and Design, 5.8 Unconventional and Complex Reservoirs, 7.6.6 Artificial Intelligence, 3.3 Well & Reservoir Surveillance and Monitoring, 7.6.7 Neural Networks, 2 Well completion, 5.8.2 Shale Gas, 1.12 Drilling Measurement, Data Acquisition and Automation, 3.3.2 Borehole Imaging and Wellbore Seismic, 7.6.4 Data Mining, 1.10 Drilling Equipment, 2.4 Hydraulic Fracturing, 2.2 Installation and Completion Operations, 1.12.1 Measurement While Drilling, 7.6 Information Management and Systems, 4.2 Pipelines, Flowlines and Risers, 7 Management and Information, 0.2 Wellbore Design, 1.6.6 Directional Drilling, 1.12.2 Logging While Drilling
- Logging while drilling, Well completion optimization, Deep convolutional neural network, Signal processing and pattern recognition, Marcellus shale gas
- 162 in the last 30 days
- 167 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Maximizing stimulated natural and hydraulic fracture network is one of the primary hydraulic fracturing concerns for economic production from a horizontal shale gas well. Geomechanical facies and preexisting fractures in each stage are identified based on similarities in formation characteristics to optimize the locations of perforation clusters. This often requires analyzing large volumes of drilling, Logging While Drilling (LWD) and Measurement While Drilling (MWD) data. In this paper, we develop a methodology that calculates the mechanical specific energy (MSE) using real-time drill string acceleration signals directly from its definition. High resolution vibration signals have been collected using a tri-axial accerlometer, which was an auxiliary tool included in acoustic borehole imager. This technique provides a cost-efficient solution for engineered completion design. Furthermore, we adopt deep Convolutional Neural Network (CNN) with signal processing to build a data pipeline that effectively extracts patterns from dynamic acceleration signals for rock lateral MSE classification. First, we apply discrete wavelet transform and Short-Time Fourier Transform (STFT) for signal denoising and pattern recognition. Then we construct an image dataset using multi-scale image fusion at pixel level from 3 sensor channels, including axial, lateral acceleration spectrograms and zero-padded revolutions per minute (RPM). The resulted RGB image dataset includes 4,000 images of 5 MSE ranges with various rock strength conditions. Our results demonstrate that the proposed deep learning model can achieve more than 90% classification accuracy. The deep learning results, as a reference source, were applied in selected Marcellus Shale Energy and Environmental Lab (MSEEL) wells engineered completion located in the Marcellus shale gas site.
|File Size||1 MB||Number of Pages||18|
Aimene, Y. E., Yams, J. M., Davila, C., Dusterhoft, R. and Siddiqui, S., 2016. Combining the stochastic earth model with geomechanical modeling to quantify well performance: application to Mississippian shale. SPE/AAPG/SEG Unconventional Resources Technology Conference, 1-3 August, San Antonio, Texas, USA.
Ajisafe, F. O., Pope, T. L., Azike, 0., Reischman, R., Herman, D., Burkhardt, C. G., Helmreich, A. S. and Phelps, M. W., 2014. Engineered completion workflow increases reservoir contact and production in the Wolfcamp Shale, West Texas. SPE Annual Technical Conference and Exhibition, 27-29 October, Amsterdam, The Netherlands.
Carr, T. R., Wilson, T. H., Kavousi, P., Amini, S., Sharma, S., Hewitt, J., Costello, I., Carney, B. J., Jordan, E., Yates, M. and MacPhail, K., 2017. Insights from the Marcellus shale energy and environment laboratory (MSEEL). SPE/AAPG/SEG Unconventional Resources Technology Conference, 24-26 July, Austin, Texas, USA.
Kavousi, P., Can, T., Wilson, T., Amini, S., Wilson, C., Thomas, M., MacPhail, K., Crandall, D., Carney, B. J., Costello, I. and Hewitt, J., 2017. Correlating distributed acoustic sensing (DAS) to natural fracture intensity for the Marcellus Shale. 2017 SEG International Exposition and Annual Meeting, 24-29 September, Houston,Texas.