Drillstring vibration is a major concern during drilling wellbore and it can be split into three types axial, torsional, and lateral. Many problems associate with the high drillstring vibrations as tear and wear in downhole tools, inefficient drilling performance, loss of mechanical energy, and hole wash-out. The high cost for the downhole measurement of the drillstring vibrations encourages machine learning applications toward downhole vibration prediction during drilling. Consequently, the objective of this paper is to develop an artificial neural network (ANN) model for predicting the drillstring vibration while drilling a horizontal section. The ANN model uses the surface drilling parameters as model inputs to predict the three types of drillstring vibrations. These surface drilling parameters are flow rate, mud pumping pressure, surface rotating speed, top drive torque, weight on bit, and rate of penetration. The study utilized a dataset of 13,927 measurements from a horizontal well that was used to train the ANN model. In addition, a different data set (9,284 measurements) was employed to validate the developed ANN model. Correlation coefficient (R) and average absolute percentage error (AAPE) are statistical metrics that are used to evaluate the model accuracy based on the difference between the actual and predicted values for the axial, torsional, and lateral vibrations. The results of the optimized parameters for the developed model showed a high correlation coefficient between the predicted and the actual drillstring vibrations that showed R higher than 0.95 and AAPE below 3.5% for all phases of model training, testing, and validation. The developed model proposed a model-based equation for real-time estimation for the downhole vibrations.

During the drilling operations and because of the harsh downhole drilling environment, the drill string suffered from downhole vibrations that affect the drilling operation and equipment. This problem is greatly affecting the downhole tools (wear and tear), hole problems (wash-out), mechanical energy loss, and ineffective drilling performance. Extra non-productive time to address these complications during the operation, and hence, extra cost. Detecting the drillstring vibrations during drilling through the downhole sensors is costly due to the extra service and downhole sensors. Currently, the new-technology-based solutions are providing huge capabilities to deal intelligently with the data, and machine learning applications provide high computational competencies to learn and correlate the parameters for technical complex problems. This research presented a successful case study for developing machine learning models through a comprehensive methodology process for vibration detection using surface rig data through data collection, preprocessing, analytics, training and optimizing the models’ parameters, and evaluating the performance to have the best prediction results. Evaluating the models’ performance showed that obtained predictions have a great match with actual measurements for the different stages of training, testing, and even during models’ validation with unseen well data. Real-field horizontal drilling data was utilized to feed and train the models through different tools named radial basis function (RBF), support vector machines (SVMs), adaptive neuro-fuzzy inference system (ANFIS), and functional networks (FN) to auto-detect the three types of downhole vibrations (axial, torsional, and lateral). The study results showed a high correlation coefficient (higher than 0.9) and technically accepted average absolute percentage error (below 7.5%) between actual readings and predictions of the developed ML models. The study outcomes will add to the automation process of drilling operations to avoid many tools failure by comparing predicted vibrations versus downhole tools limits such as red zone and continuing drilling without interruption to the well total depth especially while drilling horizontal sections.

During the drilling operations and because of the harsh downhole drilling environment, the drill string suffered from downhole vibrations that affect the drilling operation and equipment. This problem is greatly affecting the downhole tools (wear and tear), hole problems (wash-out), mechanical energy loss, and ineffective drilling performance. Extra non-productive time to address these complications during the operation, and hence, extra cost. Detecting the drillstring vibrations during drilling through the downhole sensors is costly due to the extra service and downhole sensors. Currently, the new-technology-based solutions are providing huge capabilities to deal intelligently with the data, and machine learning applications provide high computational competencies to learn and correlate the parameters for technical complex problems. Consequently, the objective of this paper is to develop a machine learning model for predicting the drillstring vibration while drilling using machine learning via artificial neural networks (ANN) for horizontal section drilling. The developed ANN model was designed to only implement the surface rig sensors drilling data as inputs to predict the downhole drilling vibrations (axial, lateral, and torsional). The research used 5000 data set from drilling operation of a horizontal section. The model accuracy was evaluated using two metrics and the obtained results after optimizing the ANN model parameters showed a high accuracy with a correlation coefficient R higher than 0.97 and average absolute percentage error below 2.6%. Based on these results, a developed ANN algorithm can predict vibration while drilling using only surface drilling parameters which ends up with saving the deployment of the downhole sensors.