Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the
coverage of the most important and influential journals
to meet the needs of the global scientific community.
In this research, GA is employed to determine constant
coefficients of Bourgoyne and Young model and consequently predict drilling
rate with high accuracy. Bourgoyne and Young model represents a general
mapping between drilling rate and some drilling variables. There are eight
unknown parameters in this model, which are dependent to the ground formation
types. These eight parameters can be determined using previous drilling
experiences. Previous drilling experiences include date sets of eight
different drilling parameters such as depth, bit weight, rotary speed
and pore pressure. In this research, sensory data of drilling nine different
wells of Khangiran Iranian gas field has been collected to obtain needed
sets. Bourgoyne and Young recommended multiple regression method to determine
unknown coefficients. However, applying multiple regression method leads
to physically meaningless values in some situations. Although, some new
mathematical methods have recently been issued to reach meaningful results,
applying them diminishes drilling rate prediction accuracy in practice.
In order to reach more accurate prediction and physically meaningful coefficients,
we applied Genetic Algorithm (GA) to determine unknown parameters of Bourgoyne
and Young model. Afore-mentioned wells were considered for applying the
new approach and testing it. Simulation results prove the proficiency
of the new methodology to determine constant coefficients of Bourgoyne
and Young model.