Abstract: A computer implemented method that enables collective voting from an ensemble model to predict bit wear is described. The method includes obtaining input data from a target well in real-time by an ensemble model. At least one physics-based model and at least one trained artificial intelligence model are applied to the input data to generate bit wear predictions. A collective voting scheme is applied to the bit wear predictions to obtain a final bit wear prediction. Drilling operations are updated responsive to the final bit wear prediction.

Abstract: A computer implemented method that enables training an artificial intelligence model to predict bit wear is described. The method includes applying multiple filters to a data pool associated with offset wells, wherein the filters comprise physics-based filters and data driven filters. A training set of relevant offset wells is created from a first set of relevant offset wells and a second set of relevant offset wells. An artificial intelligence model is trained to predict bit wear using the training set of relevant offset wells.

Abstract: Example methods and systems for detecting anomalies in wellbore drilling operations are disclosed. One example method includes obtaining, from one or more sensors, field data measured during a drilling operation of a wellbore, where the field data includes drilling data of a drill bit used to drill the wellbore and logging data of the wellbore. The field data is monitored based on one or more physics-based models to detect one or more anomalies in the field data. In response to a detection of the one or more anomalies in the field data, a warning signal is sent to check the one or more sensors.