The use of artificial neural networks in completion stimulation and design

Optimizing well-completion procedures is often difficult because of (1) variables related to reservoir quality and (2) a general lack of understanding regarding the complex interactions between well-completion/stimulation procedures and the reservoir. In many situations, well completion is a compromise between reservoir conditions and operational procedures. However, artificial neural networks (ANNs), can be used to help improve well economics. ANN models trained to interpret reservoir, well, and completion information can predict well cumulative production with an acceptable degree of accuracy. Sensitivity studies of these networks indicate that, for a given reservoir quality, completion methods can significantly affect well production. This paper presents case histories in which ANN sensitivity analyses were used to justify changes in completion/stimulation procedures. ANN-enhanced completions resulted in better overall well production than standard completion optimization methods normally used in these fields. This paper discusses well-completion analyses performed with ANN technology. The economic advantages of various completion techniques are also discussed. ANN technology has been used in areas where conventional engineering methods produced unacceptable results. These completions were performed in (1) the Red Fork formation of Roger Mills and Custer County, Oklahoma, USA (2) the Frontier formation of Lincoln County, Wyoming, USA and (3) the Granite Wash formation of Roberts County, Texas, USA. Areas of interest include quantifiable well, reservoir, and completion characteristics, such as porosity, pressure, and completion/stimulation procedures, that affect well production. Net present value is used to quantify the economic effect of ANN enhancement on well completion. (C) 2000 Elsevier Science Ltd. All rights reserved.