The first group, consisting of data points, was used to train the network ANN models. Regarding the studies on the predictability of drilling rate from ANN, making a direct comparison between the ANN models constructed in this study and the models suggested by other authors is also difficult. Comparison of derived models and previous models. Cookies are used by this site. Three ANN models that are reliable were derived. They also introduced a new rock property, termed 'destruction work', for toughness referring to drillability, and found a highly significant correlation between destruction work and drillability. Penetration rate prediction for percussive drilling via dry friction model A M Krivtsov, M Wiercigroch.
Log in to your subscription
It is a typical type of supervised learning strategy in machine learning field. The prediction model has been constructed using industrial reservoir data sets that are collected from an oil reservoir at the Bohai Bay, China. CAA1 Drilling activity logging device, system and method. If well-bore stability is not a factor, a gaseous fluid or one containing entrained gas should be considered first, followed by fluids containing hollow crush-proof beads, then oil or emulsion fluids, followed by invert-emulsion muds, freshwater muds, and brines. ELM often leads to a smaller training error with the smaller norm of weights compared with the traditional learning algorithm. This is an open access article distributed under the Creative Commons Attribution License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. US System, method and apparatus for petrophysical and geophysical measurements at the drilling bit.
Prediction of Penetration Rate for Percussive Drilling - Technische Informationsbibliothek (TIB)
An engineering geology evaluation method based on an artificial neural network and its application. The raw data was obtained from the study by Selim and Bruce Core Sampling in Geotechnical Drilling. To drive down operational costs, while continuing to push drilling activities into harsher and more challenging environments, emphasis must clearly be placed on drilling efficiency. A core bit with a higher crown impregnated with diamonds, such as the Vulcan , may also help improve penetration rates by reducing the number of times you need to change your bit. They found good correlations between the penetration rate and some rock properties.
Four types of kernels have been tested using a training data set for the ELM model, and they are the sigmoid function, radial-basis function, hardlim function, and triangular function. Although there are some studies in the literature on drillability prediction from ANNs, only one of these Aalizad, and Rashidinejad, is related to percussive drilling and includes numerous direct and indirect test results. Moreover, the pump pressure and differential pressure are selected as important hydraulic parameters that affect ROP, while RPM and WOB are treated as the equipment operational parameters. As a result, it can be said that because the ANN model constructed in this study includes one or two indirect test values, it is more practical than Aalizad and Rashidinejad's model. A back-propagation algorithm with Levenberg-Marquardt training function has been used for training.