Harvesting Knowledge To Improve Drilling Performance In Real Time

Reusing past experience—that is, being reminded of similar situations and making use of decision steps made earlier—has turned out to be an efficient way for human beings to handle new situations. Case-based reasoning (CBR) builds upon this principle to provide improved computer assistance to people in their daily work. As CBR is becoming more utilized for experience capture and reuse in real-world industrial settings, methods for linking human experiences to the observed data related to those experiences are getting increased attention.

Many industries, including the oil and gas industry, have access to large amounts of data and information, and advanced tools for displaying various types of information. As the amount of available data increases, the need for tools to extract, or filter out, the relevant information in a given situation increases correspondingly. A new technology has been developed to meet this need that will assist oil well personnel during drilling and production operations in improving the quality and efficiency of operations. This development is supported by the Norwegian oil company StatoilHydro, which has enhanced drilling performance as one of its prioritized areas.

Although many oil companies have implemented state-of-the-art real-time operations centres (RTOC) that continuously monitor streams of data from field operations, there exists no truly instantaneous, automated delivery of relevant historical knowledge of how to solve problems indicated by the data. RTOCs are an elegant way to concentrate expertise and efficient decision-making efficiency to reduce risk. Despite their implementation, non-productive time (NPT)—meaning time not spent in actual drilling— remains at around 15% to 35%. With spread costs for offshore rigs averaging $1M/day, there is ample incentive to address NPT, particularly in current times, as the industry continues to lose its base of expertise.