Application on Lithology Recognition with BP Artificial Neural Network
Jinhui Zhou, Jienian Yan, Pan Li · 2009
An artificial neural network (ANN) model is established to recognize the drilled formations' lithologies while drilling. The styles of output and input of ANN are designed. The nerve cells in input layer are weight of bit (WOB), speed of rotary (SOR) and rate of penetration (ROP). The number of nerve cells in output layer is designed to be three. Software system for recognizing the formation lithologies is developed basing on the error back-propagation (BP) network. The drilling data with microbit drilling and field drilling of petroleum and coal are used to validate the software system. The results indicate that the effect of recognition of formation lithology is better. The average correct ratios achieve 80%, 78% and 95% respectively in the test of microbit drilling, well H12-9 and well 107.