Yahia ElSayed Khamis; Shady Galal El-Rammah; Adel M Salem
Abstract
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear ...
Read More
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear behavior of drilling parameters with the rate of penetration, these mathematical models cannot accurately and comprehensively predict the rate of penetration. Machine learning (ML) seems to be an attractive alternative to model this complicated physical process. This research paper introduces new data-driven models used to predict ROP using different parameters such as (depth, weight on bit (WOB), revolution per minute (RPM), Torque (T), standpipe pressure (SPP), flow in pump (pumping flow rate(Q), mud weight, hours on bit (HOB), revolutions on bit, bit diameter, total flow area (TFA), pore pressure, overburden pressure, and pit volume). Data-driven models are built using two different machine learning techniques, using 1771 raw real field data. The coding is built using the python programming language. The k-nearest neighbors (KNN) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.94. The multi-layer perceptron (MLP) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.98. We can conclude that MLP has a better accuracy, and removing outliers enhances model performance.
M. Sakizadeh; R. Mirzaei
Abstract
The aim of this work is to examine the feasibilities of the support vector machines (SVMs) and K-nearest neighbor (K-NN) classifier methods for the classification of an aquifer in the Khuzestan Province, Iran. For this purpose, 17 groundwater quality variables including EC, TDS, turbidity, pH, total ...
Read More
The aim of this work is to examine the feasibilities of the support vector machines (SVMs) and K-nearest neighbor (K-NN) classifier methods for the classification of an aquifer in the Khuzestan Province, Iran. For this purpose, 17 groundwater quality variables including EC, TDS, turbidity, pH, total hardness, Ca, Mg, total alkalinity, sulfate, nitrate, nitrite, fluoride, phosphate, Fe, Mn, Cu, and Cr(VI) from 41 wells and springs were used during an eight-year time period (2006 to 2013). The cluster analysis was used, leading to a dendrogram that differentiated two distinct groups. The factor analysis extracted eight factors accumulatively, accounting for 90.97% of the total variance. Thus the variations in 17 variables could be covered by just eight factors. K-NN and SVMs were applied for the classification of the aquifer under study. The results of SVMs indicated that the best performed model was related to an exponent of degree one with an accuracy of 94% for the test data set, in which the sensitivity and specificity were 1.00 and 0.87, respectively. In addition, there was no significant difference among the results of different kernels, indicating that an acceptable result can be achieved by selecting the optimum parameters for a kernel. The results of K-NN showed roughly a lower efficiency compared with those of SVMs, where the sensitivity and specificity was reduced to 0.90 and 0.88, respectively, although the accuracy of the model was 93%. A sensitivity analysis was performed on the groundwater quality variables, suggesting that calcium next to nitrate were the most influential parameters in the classification of this aquifer.
