LSTM Recurrent Neural Network Based Method for Identification of Drilling Operating Conditions and its Application

ABSTRACT: Polycrystalline Diamond Compact (PDC) bit underground operating conditions identification is one of the difficulties during the drilling operation. It is of great significant for the drilling improvement and accurate construction formation to accurately identify the complex operating conditions during drilling the operation such as PDC bit wearing and stick-slip vibration, etc. In this paper, data of relationship between torque, rate of penetration (ROP) signal and weight on bit (WOB), rev were obtained through lab simulation experiment, after which, a relationship database of torque, ROP signal and WOB, rev was established, a single-layer Long Short Term Memory (LSTM) recurrent neural network (LSTM) was constructed, the number of neurons, batch size and optimizer type of LSTM layer were optimized. With BPTT algorithm, LSTM model was trained and tested on the training set containing 6000 groups of data, and achieved the goal of identifying the bit operation conditions against the input of WOB, torque, rev and ROP signal parameters. Based on this model, the PDC bit underground operating conditions identification software was compiled, and was connected to the logging unit to realize real-time identification of bit underground operating conditions, and field test application was successfully carried out in Mahu 1 Well Region. The research showed that the convergence speed was fast and the time cost was at the lowest when the number of neurons of LSTM model was 50, and that the optimized Adam optimizer model could meet the requirements of convergence speed and prediction accuracy with the lowest loss value. The classification accuracy of this model on the test set reached 94% and the accuracy of the prediction method was also verified by field test application. 1. INTRODUCTION During the drilling, complex underground conditions such as PDC bit wearing and stick slip may a impact the drilling cycle and drilling cost directly, in that bit wearing reduces the rock breaking efficiency. Either too early or too late pulling out of the hole(POOH) can affect the drilling effectiveness. After the bit stick-slip vibration, the cutting teeth can not effectively eat the rock, hence reducing the rock breaking efficiency. Serious bit stick-slip vibration may cause accidents such as increase of drill string torque and even breaking of drilling tool[1-3]. Therefore, real-time and accurate prediction of underground operating conditions of PDC bit and accurate guidance of tripping operation can effectively improve the mechanical ROP, reduce NPT and shorten the well construction cycle[4].