Title :
Research on Drill String Failure in Gas Drilling Based on Statistical Learning Theory
Author_Institution :
Sch. of Oil & Gas Eng., Chongqing Univ. of Sci. & Technol., Chongqing, China
Abstract :
The failure of drill string in gas drilling has become a technical problem for drilling workers. In this paper, based on the analysis of drill string failure data at home and abroad using Statistical Learning Theroy and Support Vector Machine which have a very rapid development in recent years, a new predictive model of drill string failure has been established in gas drilling. Experimental results show that the model has very high accuracy for the prediction of drill string failure in gas drilling.
Keywords :
drilling (geotechnical); failure analysis; learning (artificial intelligence); support vector machines; drill string failure; gas drilling; statistical learning theory; support vector machine; Data models; Drilling; Kernel; Predictive models; Statistical learning; Support vector machine classification; dring string failure; gas drilling; research; statistical learning theory;
Conference_Titel :
Computational and Information Sciences (ICCIS), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8814-8
Electronic_ISBN :
978-0-7695-4270-6
DOI :
10.1109/ICCIS.2010.103
