scholarly journals Field Application of an Interpretation Method of Downhole Temperature and Pressure Data for Detecting Water Entry in Horizontal/Highly Inclined Gas Wells

2008 ◽  
Author(s):  
Ochi Ikoku Achinivu ◽  
Ding Zhu ◽  
Kenji Furui
Keyword(s):  
Water Entry ◽  
Field Application ◽  
Pressure Data ◽  
Gas Wells ◽  
Temperature And Pressure ◽  
Downhole Temperature ◽  
Interpretation Method

Field Application of Deep Learning for Flow Rate Prediction with Downhole Temperature and Pressure

2021 ◽  
Author(s):  
Fuyong Wang ◽  
Yun Zai ◽  
Jiuyu Zhao ◽  
Siyi Fang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Flow Rate ◽  
Field Application ◽  
Support Vector ◽  
Rate Prediction ◽  
Input Parameters ◽  
Temperature And Pressure ◽  
Lstm Network ◽  
Downhole Temperature

Abstract Well real-time flow rate is one of the most important production parameters in oilfield and accurate flow rate information is crucial for production monitoring and optimization. With the wide application of permanent downhole gauge (PDG), the high-frequency and large volume of downhole temperature and pressure make applying of deep learning technique to predict flow rate possible. Flow rate of production well is predicted with long short-term memory (LSTM) network using downhole temperature and pressure production data. The specific parameters of LSTM neural network are given, as well as the methods of data preprocessing and neural network training. The developed model has been validated with two production wells in the Volve Oilfield, North Sea. The field application demonstrates that the deep learning is applicable for flow rate prediction in oilfields. LSTM has the better performance of flow rate prediction than other five machine learning methods, including support vector machine (SVM), linear regression, tree, and Gaussian process regression. The LSTM with a dropout layer has a better performance than a standard LSTM network. The optimal numbers of LSTM layers and hidden units can be adjusted to obtain the best prediction results, but more LSTM layers and hidden units lead to more time of training and prediction, and LSTM model might be unstable and cannot converge. Compared with only downhole pressure or temperature data used as input parameters, flow rate prediction with both of downhole pressure and temperature used as input parameters has the higher prediction accuracy.

Aspirating Probe Measurements of the Unsteady Total Temperature Field Downstream of an Embedded Stator in a Multistage Axial Flow Compressor

1996 ◽  
Author(s):  
N. Suryavamshi ◽  
B. Lakshminarayana ◽  
J. Prato
Keyword(s):  
Axial Flow ◽  
Pressure Data ◽  
Peak Efficiency ◽  
Axial Flow Compressor ◽  
Composite Flow ◽  
Total Temperature ◽  
Temperature And Pressure ◽  
Flow Compressor ◽  
Isentropic Efficiency ◽  
Probe Measurements

The results from the area traverse measurements of the unsteady total temperature using a high response aspirating probe downstream of the second stator of a three stage axial flow compressor are presented. The measurements were conducted at the peak efficiency operating point. The unsteady total temperature data is resolved into deterministic and unresolved components. Hub and casing regions have high levels of unsteadiness and consequently high levels of mixing. These regions have significant levels of shaft resolved and unresolved unsteadiness. Comparisons are made between the total temperature and the total pressure data to examine the rotor 2 wake characteristics and the temporal variation of the stator exit flow. Isentropic efficiency calculations at the midpitch location show that there is about a 4% change in the algebraically averaged efficiency across the blades of the second rotor and if all the rotor 2 blades were behaving as a “best” blade, the improvement in efficiency would be about 1.3%. An attempt is made to create a composite flow field picture by correlating the unsteady velocity data with temperature and pressure data.

A New Approach for Reliable Estimation of Hydraulic Fracture Properties Using Elliptical Flow Data in Tight Gas Wells

2009 ◽  
Vol 12 (02) ◽  
pp. 254-262 ◽  
Author(s):  
Yueming Cheng ◽  
W. John Lee ◽  
Duane A. McVay
Keyword(s):  
Hydraulic Fracture ◽  
Finite Conductivity ◽  
Tight Gas ◽  
Well Test ◽  
Pressure Data ◽  
Gas Wells ◽  
New Approach ◽  
Fracture Properties ◽  
Elliptical Flow ◽  
Half Length

Summary Gas wells in low-permeability formations usually require hydraulic fracturing to be commercially viable. Pressure transient analysis in hydraulically fractured tight gas wells is commonly based on analysis of three flow regimes: bilinear, linear, and pseudoradial. Without the presence of pseudoradial flow, neither reservoir permeability nor fracture half-length can be independently estimated. In practice, as pseudoradial flow is often absent, the resulting estimation is uncertain and unreliable. On the other hand, elliptical flow, which exists between linear flow and pseudoradial flow, is of long duration (typically months to years). We can acquire much rate and pressure data during this flow regime, but no practical well test analysis technique is currently available to interpret these data. This paper presents a new approach to reliably estimate reservoir and hydraulic fracture properties from analysis of pressure data obtained during the elliptical flow period. The method is applicable to estimate fracture half-length, formation permeability, and skin factor independently for both infinite- and finite-conductivity fractures. It is iterative and features rapid convergence. The method can estimate formation permeability when pseudoradial flow does not exist. Coupled with stable deconvolution technology, which converts variable production-rate and pressure measurements into an equivalent constant-rate pressure drawdown test, this method can provide fracture-property estimates from readily available, noisy production data. We present synthetic and field examples to illustrate the procedures and demonstrate the validity and applicability of the proposed approach.

Low-cost flow-rate estimate in separate layers along gas wells from temperature and pressure profiles

2013 ◽  
Vol 53 (1) ◽  
pp. 285
Author(s):  
Emile Barrett ◽  
Imran Abbasy ◽  
Chii-Rong Wu ◽  
Zhenjiang You ◽  
Pavel Bedrikovetsky
Keyword(s):  
Thermal Conductivity ◽  
Mathematical Model ◽  
Flow Rate ◽  
Low Cost ◽  
Pressure Sensors ◽  
Gas Wells ◽  
Production Rates ◽  
Pressure Profiles ◽  
Temperature And Pressure ◽  
The Mathematical Model

Estimation of rate profile along the well is important information for reservoir characterisation since it allows distinction of the production rates from different layers. The temperature and pressure sensors in a well are small and inexpensive; while flow meters are cumbersome and expensive, and affect the flow in the well. The method presented in this peer-reviewed paper shows its significance in predicting the gas rate from temperature and pressure data. A mathematical model for pressure and temperature distributions along a gas well has been developed. Temperature and pressure profiles from nine well intervals in field A (Cooper Basin, Australia) have been matched with the mathematical model to determine the flow rates from different layers in the well. The presented model considers the variables as functions of thermal properties at each location, which is more accurate and robust than previous methods. The results of tuning the mathematical model to the field data show good agreement with the model prediction. Simple and robust explicit formulae are derived for the effective estimation of flow rate and thermal conductivity in gas wells. The proposed approach has been applied to determine the well gas rate and formation thermal conductivity from the acquired well pressure and temperature data in field A. It allows for recommending well stimulation of layers with low production rates.

Sign in / Sign up

Export Citation Format

Share Document