Recognition method of drilling conditions based on support vector machine

Abstract

With the proposal of oilfield digital transformation and intelligent development, intelligent analysis technology has become an important means to solve the problem of oil and gas research and generation. Aiming at the problem of working condition identification in the process of drilling, based on the monitoring data collected in the process of drilling, a drilling condition identification method based on support vector machine is proposed in this paper. The grid search algorithm is used to optimize the support vector machine, and then combined with 10000 measured data on the drilling site to compare and verify the recognition accuracy. The results show that the recognition rate of drilling conditions based on the optimized the support vector machine is more than 95%, which shows that this method can recognize drilling conditions, improve drilling efficiency to a certain extent, and meet the requirements of efficient utilization of oilfield data resources.