Fault Diagnosis of Drilling Process Based on Rough Set and Support Vector Machine

Abstract

Drilling process is a complicated system with characteristics of uncertainty, fuzziness and time-varying. A new way of the fault diagnosis based on RS-SVM (Rough Set and Support Vector Machine) was proposed in this paper. The related engineering factors were reduced by Rough Set theory and the main factors of the drilling process were obtained. Then the Support Vector Machine was used to establish the diagnosis models, and then the problems that the traditional SVM cannot deal with dynamic data and are prone to dimension disasters with large samples were avoided. The application in Ha35 well, Liao He Oilfield indicates that the system can diagnose the type of faults quickly and accurately. So the method can be used to diagnose the drilling process.