本文已被:浏览次 下载次 |
码上扫一扫! |
|
|
Research on classification and discrimination of polyhalite with drilling and logging data by BP neural network |
CHEN Kegui1, LIU Li2,3, CHEN Yuanyuan4, WEI Hang5, WANG Gang6
|
(1.School of Geoscience and Technology, Southwest Petroleum University, Chengdu 610500, China;2.School of Mechatronic Engineering, Southwest Petroleum University, Chengdu 610500, China;3.SINOPEC Zhongyuan Oilfield Company, Puyang 457001, China;4.Geophysical Exploration Company, Chuanqing Drilling Engineering Company Limited, Chengdu 610213, China;5.Shixi Oilfield Operating Area, PetroChina Xinjiang Oilfield Company, Karamay 834000, China;6. Research Institute of Development, PetroChina Xinjiang Oilfield Company, Karamay 834000, China)
|
Abstract: |
Based on the theory of back propagation neural network and logging interpretation methods, a neural network model with logging curves as input was built, and applied to the polyhalite reservoirs in the lower-middle Triassic strata. The discrimination results were compared with logging data. The accuracy rate of the model reaches 86.3%, and achieves 97% if changing the constraint conditions, suggesting that the discrimination ability of the new model is good. The new model shows the accuracy rate reaches 82.51% to classify the polyhalite reservoirs. The model can efficiently discriminate pure polyhalite reservoirs, gypsiferous polyhalite reservoirs and polyhalite-gypsum reservoirs, thus is more advanced than regular logging interpretation methods. This study demonstrates the great potential applying the BP neural network in potash exploration. |
Key words: polyhalite BP neural network model classification and discrimination logging response |
|
|