| Case-based reasoning in drilling |
Case-based reasoning in drilling papers:
This paper is one of the first papers about CBR in oil-well drilling. A case-based reasoning system to study the problem given in the title is described. The paper also presents statistical material of stuck pipe incidents from an operator for the years 1990-1996, together with how this material was used to select the parameters for building our knowledge model. A realistic case demonstrated the idea and how the overall system will help an operator to reduce downtime. Published in Proceedings of IADC Middle East Drilling Conference, Dubai, Nov. 1998. Copyright: IADC.Combining case-based reasoning and data mining [2] This is a paper about the re-use of previous experience for safety, reliability and maintainability (RAMS) tasks. An approach is presented where statistical methods for extracting interesting relationships in data (data mining), are combined with knoledge-based methods for capturing and re-using problem solving knowledge in the form of specific experiences (CBR). The work was done within the earlier EU project NOEMIE. Paper published in Safety and Reliability; Proceedings of ESREL 98, Trondheim, June 16-10, 1998. pp. 1345-1351. Copyright: Balkena. Learning retrieval knowledge from data In CBR, situation-specific user experiences are typically captured in cases. In the approach presented here, cases are linked within a semantic network of more general domain knowledge. In this paper we present a way to automate the construction and dynamical refinement of such a model of case-specific and general knowledge, on the basis of external process data continuously being generated. A data mining method based on a Bayesian Networks approached is used. The results are from the earlier NOEMIE EU project. Published in Sixteenth International Joint Conference on Artificial Intelligence, Workshop in Automating the Construction of Case-Based Reasoners. Stockholm, 1999. pp. 77-82. Copyright: IJCAI. Improved efficiency of oil well drilling through case-based reasoning [3] This paper summarized the results from teh NOEMIE project (EU 1996-99). the problem of 'lost circulation', i.e. loss of circulating drilling fluid into the geological formation, was picked out as the pilot problem. An extensive general knowledge model was developed for the domain of oil well drilling. About fifty different cases were created on the basis of the information from one North Sea operator. When the completed CBR-system was tested the best matching cases proved to give the operator valuable advice. Published in Lecture Notes in Artificial Intelligence, PRICAI 2000 Topics in Case-Based Reasoning, Vol. 1886/2000, pp. 712-722. Copyright: Springer. Representing temporal knowledge for case-based prediction Most current CBR methods deal with snapshot cases, while many applications call for case features tha span over a time period. Based on a well-established theory of temporal intervals, a method is presented that represents temporal cases inside the knowledge-intensive CBR system Creek. The paper presents the teoretical foundation fo the metho, the representation formalism and basic reasoninc algorithms, and an expample applied to the prediction of unwanted events in oil well drilling. Published in Lecure Notes in Computer Science, Advances in Case-Based Reasoning, Vol. 2416/2002, pp. 225-234. Copyright: Springer. Case-based reasoning for advice-giving in a data-intensive environment [4] This paper summarizes the architecture of the current DrillEdge software, at some point of development. Re-using past experiences by reasoning from past cases poses particular problems when the input to case retrieval comes from large amounts of online data. The paper describes how data from oil well drilling logs are continuously monitored, interpreted, and used to check if previous incidents exists that may indicate that an unwanted event is about to develop. Published in Frontiers in Artificial Intelligence and Applications, Vol. 173 (2006), tenth Scandinavian Conference on Artificial Intelligence, pp. 201-205. Copyright: IOS Press. Knowledge-based decision support in oil well drilling [5] The paper describes an experimental system in which the TrollCreek tool is used to support fault diagnosis and prediction of unwanted events in oil drilling. It is shown how the two components of TrollCreek, the case base and the semantic network of general domain knowledge, are combined to achieve the intended effect. Published in Proceedings of the International Conference on Intelligent Information Systems, ICIIP 2004, Beijing, 2004, pp. 443-445. Copyright: Springer.
This paper is based on an experimental research version of the DrillEdge software, and addresses problems related to insufficient hole cleaning in drilling. The task is to correctly classify between seven root causes, e.g. hole collapse, swelling, lost circulation, etc. It is shown how general domain knowledge can be incorporated into the CBR proess for determining the root cause of a problem. Published in Proceedings of the 8th Internatonal Conference on Case-Based Reasoning, ICCBR 2009, Seattle, July 2009. Lecture notes in Artificial Intelligence 5650, Springer Verlag, ISSN-0302-9743. pp. 509-523. Copyright: Springer. [1] Copyright © IADC |
