Recurrent Neural Networks for Permanent Downhole Gauge Data Analysis
- Chuan Tian (Stanford University) | Roland N. Horne (Stanford University)
- Document ID
- Society of Petroleum Engineers
- SPE Annual Technical Conference and Exhibition, 9-11 October, San Antonio, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 2.3 Completion Monitoring Systems/Intelligent Wells, 7.6 Information Management and Systems, 5 Reservoir Desciption & Dynamics, 7.6.7 Neural Networks, 2 Well completion, 7.6.6 Artificial Intelligence, 2.3.2 Downhole Sensors & Control Equipment, 5.6 Formation Evaluation & Management, 7 Management and Information, 5.1 Reservoir Characterisation, 5.1.5 Geologic Modeling, 5.6.11 Reservoir monitoring with permanent sensors
- Permanent Downhole Gauge, NARX, Recurrent Neural Network, Deep Learning, Well Testing
- 28 in the last 30 days
- 301 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
The rich information contained in permanent downhole gauge (PDG) data has drawn attention from researchers. Previous work has demonstrated feature-based machine learning to be promising for PDG data analysis. The recent rise of deep learning was powered by techniques including recurrent neural networks (RNNs), which have been shown useful for processing sequential information. In this work, we explored how RNN can be utilized to analyze PDG data for better reservoir characterization and modeling, by examining two specific RNN structures: nonlinear autoregressive exogenous model (NARX) and standard RNN.
RNN is a special type of artificial neural network designed for sequential data processing. Unlike a nonrecurrent neural network, the hidden layers in RNN take memories of previous computations (e.g. hidden layers or outputs computed in previous time) into account. In that way, the information contained in the measurements prior to a certain time can be used to model the response at that time, i.e. the convolutional effects are modeled by the recurrent structure of the RNN. Another favorable property of RNN is that it requires no assumptions on physics in advance. Both the inputs and outputs come directly from the raw measurements, and no handcrafted features need to be extracted from the forward physics model. Compared with feature-based machine learning, RNN is more powerful for the modeling where the forward model has not been determined.
In this work, RNN was first tested on a series of synthetic and real flow rate-pressure datasets. The patterns learned by RNN from those data helped correctly identify the reservoir model and forecast the reservoir performance. RNN was also applied on temperature transient data, to demonstrate its advantage over feature-based machine learning with no assumptions on the physics model. The study also showed that RNN has the noise tolerance and computational efficiency that make it a promising candidate to analyze PDG data in practice.
|File Size||1 MB||Number of Pages||12|
Liu, Y. and Horne, R.N. 2012. Interpreting Pressure and Flow-Rate Data From Permanent Downhole Gauges by Use of Data-Mining Approaches. SPE Journal, 18(1), 69–82. doi:10.2118/147298-PA
Liu, Y. and Horne, R.N. 2013a. Interpreting Pressure and Flow Rate Data from Permanent Downhole Gauges Using Convolution-Kernel-Based Data Mining Approaches. Paper SPE 165346 presented at the SPE Western Regional & AAPG Pacific Section Meeting 2013 Joint Technical Conference, Monterey, 19-25 April.
Palabiyik, Y., Onur, M., Tureyen, O. I., and Cinar, M. 2016. Transient Temperature Behavior and Analysis of Single-Phase Liquid-Water Geothermal Reservoirs During Drawdown and Buildup Tests: Part I. Theory, New Analytical and Approximate Solutions. Journal of Petroleum Science and Engineering, 146(1): 637–656.