Deep learning-based method for reducing the number of transmitting coils in logging while drilling tool

Abstract

Abstract Electromagnetic wave logging while drilling (LWD) technology is an important tool for evaluation of formation oil and gas content. It generally adopts multi-transmitter-receiver coil system structure and the symmetrical coil system arrangement with equal transmitter-receiver spacing can obtain the measurement results with borehole compensation, thus reducing the influence of environmental factors on formation resistivity parameters. At present, the space of the drill collar to hold the coil system is limited and the power supply of the LWD instrument is limited. However, under the premise that the drilling quality remains unchanged, reducing the number of transmitting coils is beneficial to shorten the length of the LWD tool and reduce the power consumption. This paper focuses on reasonable inversion of logging data through deep learning technology, which is combined with Levenberg-Marquardt (LM) algorithm, modular and fast construction of deep neural network (DNN) model. Under the condition of reducing outermost transmitting coil, the measurement results with borehole compensation are realized by inversion, thereby we can shorten the instrument length to reduce drilling tool sticking risk and reduce the LWD instrument structure complexity, high power and other problems. At the same time, the accuracy of inversion is tested. The results show that the DNN method can achieve high-precision inversion, and the average error is reduced by about 50% compared with the traditional algorithm such as linear regression.