Application of Fuzzy Inference Prediction Method in Petroleum Drilling Accident System

摘要

The research on fuzzy inference prediction method is of great significance. In this study, Fuzzy Determined Parameters Means Clustering Method (FDPM) is proposed which determines the weighting exponent and the initial clustering center, solving the problems about excessive dependence of classification results on the weighting exponent m and the initial center of Fuzzy C-means Clustering Method (FCM).By utilizing the Fuzzy Determined Parameters Means Clustering Method (FDPM) algorithm presented in this study, it is conveniently realized to determine the membership function of the two important variables in the system of oil drilling accident forecast: the changing of total volume and the flow out rate of drilling slurry which has solved the problem that the membership function is hard to be defined. To forecast the well kick accident, the rules of fuzzy inference system are extracted. In the example of simulation, the forecast result is a fixed value. This is objectively consilient to uncertainty of accidents in the petroleum drilling.