Abstract:

In order to solve the problems of the distortion, damage and leakage of the casing pipes caused by the high temperature, high pressure, and the sand erosion of the thermal production wells during the exploitation of the heavy oil, a life prediction model based on the immune algorithm（IA） and the support vector machine（SVM） was built. Firstly, the IA was used to obtain the exact values of three parameters that affected the prediction accuracy of the SVM. Secondly, the life prediction model was built by taking 5 factors that affected the life of the casing as the input variables of the SVM, and the casing life as the target output. Finally, the casing wells running in Liaohe oilfield were taken as the examples to test the performance of the model. The results showed that the model could predict the casing life well with small errors and high coincidence. It provides a reference for the maintenance and repair of the casing.

Key words: heavy oil recovery, casing pipe of thermal production well, life prediction, immune algorithm, support vector machine