Automatic Method for Anomaly Detection while Drilling

摘要: Summary A lot of anomalies can occur and lead to failures during drilling process. It is crucial detect these deviations from normal process as soon possible, so engineers analyse decide what activities take in order prevent potential NPT. In this work we propose a new machine learning based approach for detection abnormal behaviour an online manner. The idea cluster data, which preprocessed very special way. Our aproach allows using all available data training it does not need any labeled incorporates both raw parameters expert knowledge, thus enhancing prediction results.