A BiGRU joint optimized attention network for recognition of drilling conditions  

作　　者：Ying Qiao Hong-Min Xu Wen-Jun Zhou Bo Peng Bin Hu Xiao Guo 

机构地区：[1]National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation,Southwest Petroleum University,Chengdu,610500,Sichuan,China [2]School of Computer Science,Southwest Petroleum University,Chengdu,610500,Sichuan,China [3]Information Management Center of Sinopec Southwest Oil and Gas Branch,Chengdu,610500,Sichuan,China

出　　处：《Petroleum Science》2023年第6期3624-3637,共14页石油科学（英文版）

基　　金：supported by open fund(PLN2021-23)of National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation(Southwest Petroleum University).

摘　　要：The identification and recording of drilling conditions are crucial for ensuring drilling safety and efficiency. However, the traditional approach of relying on the subjective determination of drilling masters based on experience formulas is slow and not suitable for rapid drilling. In this paper, we propose a drilling condition classification method based on a neural network model. The model uses an improved Bidirectional Gated Recurrent Unit (BiGRU) combined with an attention mechanism to accurately classify seven common drilling conditions simultaneously, achieving an average accuracy of 91.63%. The model also demonstrates excellent generalization ability, real-time performance, and accuracy, making it suitable for actual production. Additionally, the model has excellent expandability, which enhances its potential for further application.

关 键 词：Drilling condition classification BiGRU Machine learning Attention mechanism 

分 类 号：TE24[石油与天然气工程—油气井工程]