TY - GEN
T1 - A new technique to develop rock strength correlation using artificial intelligence tools
AU - Tariq, Zeeshan
AU - Elkatatny, Salaheldin
AU - Mahmoud, Mohammed
AU - Ali, Abdelwahab Z.
AU - Abdulraheem, Abdulazeez
N1 - Generated from Scopus record by KAUST IRTS on 2023-09-20
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Unconfined compressive strength (UCS) is the key parameter to; estimate the insitu stresses of the rock, design optimal hydraulic fracture geometry and avoid drilling problems like wellbore instability. UCS can be estimated by rock mechanical tests on core plugs retrieved from the depth of interest but retrieving reservoir rock samples throughout the depth of the reservoir section and performing laboratory tests on them are extremely expensive as well as time consuming. In absence of core plugs, UCS can be estimated from empirical correlations. Most of the empirical correlations for UCS prediction reported in the literature are based on elastic parameters or on compressional wave velocity. These correlations were developed using linear or non-linear regression techniques. Artificial intelligence tools once optimized for training can successfully model UCS since these tools can capture highly complex and non-linear relationship between input parameters and the output parameter. The objective of this research study is to accurately predict UCS of rock using basic geophysical well logs namely; bulk density, compressional, and shear wave velocities, by applying different artificial intelligence techniques namely; Support Vector Machine (SVM), Adaptive neuro fuzzy inference system (ANFIS) and Artificial neural network (ANN). The data set used in this study, comprised of 200 laboratory measured UCS values on core plugs and their corresponding well logs. The data were collected from 10 wells which were located in a giant carbonate reservoir. Based on minimum average absolute percentage error (AAPE) and highest coefficient of determination (R2) between actual and predicted data, ANN model proposed as the best model to predict UCS. A rigorous empirical correlation was developed using the weights and biases of ANN model to predict without the need of any software incorporating AI. A comparison of proposed model with other correlations to predict UCS on new data set also suggested that the proposed model gives less AAPE. Therefore, the proposed model seems very promising and can serve as a handy tool to help geo-mechanical engineers to determine the UCS of the carbonate rock.
AB - Unconfined compressive strength (UCS) is the key parameter to; estimate the insitu stresses of the rock, design optimal hydraulic fracture geometry and avoid drilling problems like wellbore instability. UCS can be estimated by rock mechanical tests on core plugs retrieved from the depth of interest but retrieving reservoir rock samples throughout the depth of the reservoir section and performing laboratory tests on them are extremely expensive as well as time consuming. In absence of core plugs, UCS can be estimated from empirical correlations. Most of the empirical correlations for UCS prediction reported in the literature are based on elastic parameters or on compressional wave velocity. These correlations were developed using linear or non-linear regression techniques. Artificial intelligence tools once optimized for training can successfully model UCS since these tools can capture highly complex and non-linear relationship between input parameters and the output parameter. The objective of this research study is to accurately predict UCS of rock using basic geophysical well logs namely; bulk density, compressional, and shear wave velocities, by applying different artificial intelligence techniques namely; Support Vector Machine (SVM), Adaptive neuro fuzzy inference system (ANFIS) and Artificial neural network (ANN). The data set used in this study, comprised of 200 laboratory measured UCS values on core plugs and their corresponding well logs. The data were collected from 10 wells which were located in a giant carbonate reservoir. Based on minimum average absolute percentage error (AAPE) and highest coefficient of determination (R2) between actual and predicted data, ANN model proposed as the best model to predict UCS. A rigorous empirical correlation was developed using the weights and biases of ANN model to predict without the need of any software incorporating AI. A comparison of proposed model with other correlations to predict UCS on new data set also suggested that the proposed model gives less AAPE. Therefore, the proposed model seems very promising and can serve as a handy tool to help geo-mechanical engineers to determine the UCS of the carbonate rock.
UR - https://onepetro.org/SPERCSC/proceedings/17RCSC/3-17RCSC/Abu%20Dhabi,%20UAE/208264
UR - http://www.scopus.com/inward/record.url?scp=85045001953&partnerID=8YFLogxK
U2 - 10.2118/186062-ms
DO - 10.2118/186062-ms
M3 - Conference contribution
SN - 9781510841970
SP - 1340
EP - 1353
BT - Society of Petroleum Engineers - SPE Reservoir Characterisation and Simulation Conference and Exhibition, RCSC 2017
PB - Society of Petroleum Engineers
ER -