Abstarct: The process of drilling formations holds considerable significance in the upstream oil and gas industry, primarily due to its impact on both time and cost. It is estimated that this operation accounts for approximately one-third of the total well completion time in onshore fields, while in the case of deep wells, this figure can increase to almost half. Two categories of controllable (CDP) and uncontrollable parameters affect the productivity of drilling formation operation, the result of which is the drilling response parameters (DRP) including rate of penetration (ROP), torque on bit (TRQ), bit wearing rate (BWR) and mechanical specific energy (MSE). Over the last decade, the optimization of the CDP has been of great interest to researchers and large drilling companies. Nevertheless, the literature review indicated that often little attention has been paid to the geomechanical parameters. Therefore, the current research aims to achieve optimal values for CDP, with a particular focus on geomechanical parameters. To this end, data from six wells located in a southwestern Iranian oil field were utilized, and after data preprocessing, influential parameters on drilling response parameters (ROP, TRQ and BWR) were selected using intelligent algorithms. Accordingly, geomechanical parameters such as depth, elastic modulus (E), cohesion (Coh), maximum horizontal stress (SH), Poisson's ratio (PR), internal friction angle (Fang), and confined compressive strength (CCS), along with drilling parameters such as weight on bit (WOB), rotation speed of bit (RPM), flow pump rate (FPR), bit diameter (BS), and bit friction (BF), were selected to estimate drilling response parameters. Various algorithms were employed to develop AI estimator models, among which a multilxayer artificial neural network (ANN-MLP) demonstrated higher accuracy and generalizability in estimating all three DPR. The MSE was also calculated using an analytical model baxsed on the highest correlation with the CCS of the rock. Furthermore, to optimize the WOB, RPM, and FPR, in addition to Best Practices (BP) approach, a multi-objective optimization algorithm (MOOA) was developed, taking into account the cost functions including maximum ROP and minimum TRQ, BWR, and MSE. The results of the multi-objective optimization, in diferent scenarios (real-time, formation, stand length, and geomechanical units), demonstrated significant improvements in drilling time and bit wear, while the use of best practices proved to be less effective. Finally, a workflow was presented for industry use, baxsed on the demonstrated effectiveness of the developed multi-objective optimization algorithm in this study.