Discriminant Analysis and Neural Nets: Valuable Tools To Optimize Completion Practices
- G. Nitters (Koninklijke/Shell E and P Laboratorium) | D.R. Davies (Koninklijke/Shell E and P Laboratorium) | W.J.M. Epping (Koninklijke/Shell E and P Laboratorium)
- Document ID
- Society of Petroleum Engineers
- SPE Drilling & Completion
- Publication Date
- June 1995
- Document Type
- Journal Paper
- 127 - 133
- 1995. Society of Petroleum Engineers
- 1.11 Drilling Fluids and Materials, 6.1.5 Human Resources, Competence and Training, 1.11.2 Drilling Fluid Selection and Formulation (Chemistry, Properties), 2 Well Completion, 3.2.4 Acidising, 2.4.5 Gravel pack design & evaluation, 2.7.1 Completion Fluids, 5.6.4 Drillstem/Well Testing, 4.1.2 Separation and Treating, 2.2.2 Perforating, 1.6 Drilling Operations, 4.1.5 Processing Equipment, 3.2.3 Hydraulic Fracturing Design, Implementation and Optimisation
- 0 in the last 30 days
- 210 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 12.00|
|SPE Non-Member Price:||USD 35.00|
This paper describes the application of multi-variate statistical techniques, discriminant analysis and neural networks in identifying drilling and other completion practices that impact on well productivity. Discriminant analysis determines whether a well can be assigned to a group of wells, on the basis of a number of common characteristics and using linear multivariate correlations. Neural nets enable the use of nonlinear correlations for such a classification.
In this study. 47 gas wells from two fields were classified Into three groups: Group 1: no production; Group 2: production below 5900 std m3/h (5 MMscf/D); Group 3: production over 5900 std m3/h (5 MMscf/D).
The variables used in the discriminant analysis included parameters such as completion type. total height of the perforated interval, mud weight. drawdown during perforation, type of mud and perforation size.
The study has identified and, to some extent, quantified those parameters that either adversely or favorably affect well productivity. parameters that either adversely or favorably affect well productivity. The results can be used to adjust operational procedures to maximize well productivity. The parameters identified as increasing productivity reflect, for the most part. sound engineering practices.
Application of neural nets enables further quantification of the effects of petroleum engineering parameters on well productivity and is being developed to make it possible for the most economical preventive and remedial measures to be selected. preventive and remedial measures to be selected. However, statistical techniques are applicable only when a sufficiently large data base is available, i.e., they are suitable for reasonably large and fairly mature fields and/or areas.
Probably several thousand stimulation treatments are carried out each year with a total expenditure of many millions of US dollars. The prerequisites for successful stimulation are simple: prerequisites for successful stimulation are simple: 1. Does the reservoir Contain sufficient amounts of hydrocarbons? 2. Are reservoir pressure and permeability high enough to move the hydrocarbons from the reservoir towards the wellbore?
In other words there should be a clear indication that substantial gains are possible. i.e., enough producable hydrocarbons should be present to justify the treatment for a particular well. This holds for both present to justify the treatment for a particular well. This holds for both fracturing and matrix treatments.
Hence, the selection of candidates for stimulation treatments requires knowledge about the general performance of oil and gas wells in specific fields or areas. A stimulation campaign should start with the identification of field-wide trends with respect to production-impairing mechanisms, using a statistical evaluation of field production-impairing mechanisms, using a statistical evaluation of field data. At the same time, such a statistical approach can, and often will, produce correlations between the productivity in a field and specific produce correlations between the productivity in a field and specific drilling and completion parameters. This is very useful, for instance, in identifying those practices that will prevent impairment in future wells.
|File Size||1 MB||Number of Pages||7|