Shear wave time is an important parameter participating in the calculation of rock mechanics properties. Many evaluation processes including wellbore stability analysis and sand production prediction are based on rock mechanics properties so these processes are directly related to the estimation of shear wave time. Several empirical correlations have been developed to predict shear wave time using regression analysis and artificial neural network techniques for the estimation of relationships between a dependent variable and one or more independent variables for certain conditions of the reservoir. However, they are not appropriate for reservoirs with different conditions as well as all effective parameters are not considered in previous relationships. In this study, the artificial neural network is adopted for predicting shear wave time using datasets consisting of 1922 data points for a certain directional oil well from Iraqi Fauqi oil field wells. Two sets of input parameters are tried: the first trial includes the readings of seven logs (Gamma-ray, caliper, compressional sonic wave, density, neutron, deep resistivity, true vertical depth), while the second trial includes the azimuth and the inclination angles in addition to the above seven readings. The optimum structure for both datasets is obtained using 12 neurons in a single hidden layer (ANN-7-12-1 and ANN-9-12-1). The statistical results reveal that an improvement is achieved when the well azimuth and inclination are included in the ANN model. A mathematical model with high performance using an artificial neural network has been developed. The mean square error and the determination coefficient for the developed model were 14.22 and 0.952 for ANN-7-12-1, while they were 9.62 and 0.966 for ANN-9-12-1, respectively. This study presents a simple mathematical model for further determination of shear wave velocities using ANN techniques which can be then integrated with the existent petroleum software programs.

Wellbore instability and sand production onset modeling are very affected by Sonic Shear Wave Time (SSW). In any field, SSW is not available for all wells due to the high cost of measuring. Many authors developed empirical correlations using information from selected worldwide fields for SSW prediction. Recently, researchers have used different Artificial Intelligence methods for estimating SSW. Three existing empirical correlations of Carroll, Freund, and Brocher are used to estimate SSW in this paper, while a fourth new empirical correlation is established. For comparing with the empirical correlation results, another study's Artificial Neural Network (ANN) was used. The same data that was adopted by the ANN study was used here where it is comprised of 1922 measured points of SSW and the other nine parameters of Gamma Ray, Compressional Sonic, Caliper, Neutron Log, Density Log, Deep Resistivity, Azimuth Angle, Inclination Angle, and True Vertical Depth from one Iraqi directional well. Three existing empirical correlations are based only on Compressional Sonic Wave Time (CSW) for predicting SSW. In the same way of developing previous correlations, a fourth empirical correlation was developed by using all measured data points of SSW and CSW. A comparison demonstrated that utilizing ANN was better for SSW predicting with a higher R2 equal to 0.966 and lower other statistical coefficients than utilizing four empirical correlations, where correlations of Carroll, Freund, Brocher, and developed fourth had R2 equal to 0.7826, 0.7636, 0.6764, and 0.8016, respectively, with other statistical parameters that show the new developed correlation best than the other three existing. The use of ANN or new developed correlation in future SSW calculations is relevant to decision makers due to a number of limitations and target SSW accuracy.

Heterogeneity refers to a not uniform distribution of reservoir properties. To overcome the problem of heterogeneity, most reservoir studies split the reservoir into different zones. In general, this disparity affects all log tools. Sonic shear wave time (SSW) is a critical metric in geomechanical modeling that is strongly influenced by reservoir heterogeneity and the kind of porous fluid composition. To detect the effect of reservoir heterogeneity on SSW prediction, an artificial neural network (ANN) was applied as an intelligent technique. One Iraqi vertical well that penetrated the Asmari reservoir was selected for this study. It contains 2462 SSW measured points as well as the following seven log parameters: Gamma Ray, Caliper, Density, Neutron, Compressional sonic, and True resistivity log over measured depth. Based on formation assessment and available well data, the Asmari reservoir was classified into six zones (with different lithology and different fluid content): A, B1, B2, B3, B4, and C. To investigate the effect of lithology on SSW, two runs of ANN had been conducted in this study. Initially, we developed a single ANN for all 2462 measured points, while in the second, six ANNs were built, one for each zone. The optimum structure for all the developed ANNs was obtained with one hidden layer of 12 neurons (7-12-1). The statistical parameters used for comparison are average percent error (APE), absolute average percent error (AAPE), standard deviation (SD), mean square error (MSE), and correlation coefficient (R2). It was observed that these parameters are approximately close to each other for the developed seven ANNs. The R2 values of the seven ANNs are 0.98 for all zones, and 0.99, 0.99, 0.99, 0.99, 0.99 and 0.96 for each zone respectively. The insignificant differences of results can be explained by the fact that the log readings (i.e. inputs variables) are already reflected the effect of lithology. Therefore, we recommended using the ANN based on 2462 for predicting SSW to any lithology zone. A mathematical model for representing the suggested ANN to simplify the calculation.

Sand production is undesirable matters, occurring in wells that are producing from sand reservoirs. It causes many problems such as erosion and grains accumulation in downhole and surface equipment’s, and formation subsidence. Important stage in sanding problem solution is a prediction of likelihood sand production intervals. In present paper, a vertical well X1 that is producing from Asmari reservoir in Y field at southern Iraq was selected for study.  Asmari reservoir was classified to six units: A, B1, B2, B3, B4, and C. B zones consisted from sandstone with others rock types. Eight approaches were used for prediction sanding onset intervals by dealing with X1 well as open hole completion. Utilized eight prediction methods are compressional sonic wave (CSW), unconfined compressive strength (UCS), total porosity (PHIT), shear modulus to bulk compressibility (G/Cb), B-Index, Schlumberger index (S- Index), combined index (Ec-Index) and critical drawdown pressure (CDDP). All these methods performed based on 2462 measured points of CSW, sonic shear wave log (SSW), and density log (DL). Sand production likelihood intervals was selected by determination of cutoff values of adopted methods. Sand is possible to occur if interval has values lower than cutoff values of G/Cb, UCS, B-Index, S-Index, Ec, and CDDP and greater than cutoff values of CSW, and PHIT. Obtained cutoff values of eight approaches were 800 x 109 psi2, 36 Mpa, 0.2, 80 us/ft, 10000 Mpa, 108 Mpa, and 2700 Mpa, of G/Cb, UCS, PHIT, CSW, B-Index, S-Index, and Ec respectively. As well as sand production is possible to occur of bottomhole flowing pressure lower than calculated CDDP. Some Intervals had high CDDP that referred to abnormal pressure zones consisted from shale. Determination of sand onset intervals is a key for selecting best methods for controlling.