Research on the Identification Method of Lithology Drilling with PDC Bit

While drilling with PDC Bit, Some problems are come out when using the methods of traditional recorder well because Lithology is hard to identify. The data collected by mud-logging equipment, for examples, ROP, WOB, torque et al., reflects the different properties of rock in the formation of subsurface. The relation among them is complex and BP neural network is adopted in three layers. The depth section between 2,500m and 2,700m of Well Zhang2104 is used to train predictive model in Zhangdian oil field. In order to test the precision of the model, the depth section (2,000m~2,200m) of Well Zhang2104 and Well Zhang2201 (2,600m~2,800m) are predicted. The precision predicted to Zhang2104 is 93.6% and Well Zhang2201 is 89.2%, but it is almost 100% in the pure rocks. The identification errors center on the rock filled with about 50% clay. The result proves that this method is practical.