Drilling oil wells in deep waters aims to achieve the best point of extraction of oil and natural gas reservoirs present in a few thousand meters in the seabed. A better understanding of the drilling dynamics through the analysis of real time operation parameters is important to optimize drilling process and reduce operation time. For this purpose petroleum operator companies have been made great investments in developing tools that measure and transmit parameters during drilling operation, such as the weight on bit, pipes rotation per minute and drilling fluid flow. Among the advantages to monitor this real time data there is the operational parameters optimization looking for the least expenditure of energy as possible. In a rotary drilling operation this energy is often lost partially due to column vibration caused by the interaction between bit and formation.In this master s thesis in order to extract common features that could help on the drilling operation optimization a technique using unsupervised neural networks for analyze an extensive database which was built over drilling campaigns in a big oil field . The field data analyzed were obtained during drilling vertical wells exclusively employing PDC bits and presented high levels of torcional vibration. The study was made from drilling parameters records, wells characteristics and vibration responses obtained in real time by downhole tools. Employing the WEKA data mining code and the computing analysis platform TIBCO potfire it was possible determine a bit wear curve and the real influence of navigation tools on the severity levels of vibration during drilling operations.