Using Neural Networks for Prediction of Formation Fracture Gradient
- T. Sadiq (Kuwait University) | I.S. Nashawi (Kuwait University)
- Document ID
- Society of Petroleum Engineers
- SPE/CIM International Conference on Horizontal Well Technology, 6-8 November, Calgary, Alberta, Canada
- Publication Date
- Document Type
- Conference Paper
- 2000. SPE/PS-CIM International Conference on Horizontal Well Technology
- 6.1.5 Human Resources, Competence and Training, 1.1 Well Planning, 3.2.3 Hydraulic Fracturing Design, Implementation and Optimisation, 1.14.1 Casing Design, 5.6.1 Open hole/cased hole log analysis, 5.6.4 Drillstem/Well Testing, 1.6.6 Directional Drilling, 1.7 Pressure Management, 1.11.2 Drilling Fluid Selection and Formulation (Chemistry, Properties), 1.6 Drilling Operations
- 6 in the last 30 days
- 668 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
Accurate formation fracture gradient prediction is an essential part of well planning. Erroneous fracture gradient estimates may jeopardize the entire drilling operation and result in serious well problems, the least of which are lost circulation and kick leading to blowout. Accurate fracture gradient values play an important role in the selection of proper casing seats, prevention of lost circulation and planning of hydraulic fracturing for the purpose of increasing well productivity in zones of low permeability. Furthermore, a good knowledge of the fracture gradient is of great importance in areas where selective production and injection is practiced. In such areas the adjacent reservoirs consist of several sequences of dense and porous zones such that, if a fracture is initiated during drilling or stimulation, it can propagate and extend, establishing communication between hydrocarbon reservoirs and can extend to a nearby water-bearing formation.
Fracture gradient depends upon several factors including magnitude of overburden stress, formation stress within the area and formation pore pressure. Any prediction method should incorporate most of the above factors for a realistic prediction of the fracture gradient.
This paper presents an artificial neural network model that yields reasonably accurate values of the fracture gradient. The input training data are actual field data. The results obtained from the model are compared with those obtained from correlation. The comparison shows that the method is promising and under some circumstances it is superior to the available techniques.
Prediction of fracture pressure gradient plays an important role in designing safer drilling operations and economical well planning. The fracture pressure gradient is defined as the pressure gradient that causes fracture of the formation. In other words, if a formation is exposed to a pressure higher than its fracture pressure limit, the formation will fracture and a loss of circulation will occur. This condition may lead to problems varying from well collapse to gas kick followed by underground blowout. The consequences of an underground blowout are unpredictable. These aspects make formation fracture pressure knowledge fundamental when drilling oil wells.
One of the main problems faced in predicting fracture gradients is the lack of data. In most cases only the leak-off test data, which frequently may have questionable results, is available to the drilling engineer. Fracture pressure gradient can be measured using either ‘direct' or ‘indirect' methods. The direct method relies on determining the pressure required to fracture the rock and the pressure required for the resulting fracture propagation. The indirect method relies on stress analysis or correlations to predict fracture gradient.
The direct method is generally based on leak-off test (LOT) data. During a leak-off test mud is used to pressurise the well until the formation fractures. A leak-off test is a normal procedure in wildcat wells where the formation fracture gradient is not previously determined. However, if the area is very well known and the casing design requirements are not difficult to achieve, quite often the pressure test is terminated before reaching the formation fracture pressure. LOT may be a ‘dynamic' or ‘static' process. In dynamic LOT, pressure and volume are recorded while pumping the fluid. In a static test small amount of fluid is pumped in the borehole and the pressure is allowed to stabilise before recording.
In addition to the operators' practices there are many factors that greatly affect the results of a leak-off test. Some of these factors include: (a) Inaccuracy of equipment (gauges and pumps), (b) Misinterpretation of the leak point, (c) Lithology changes, and (d) Mud properties.
|File Size||374 KB||Number of Pages||8|