Steering drilling wellbore trajectory prediction based on the NOA-LSTM-FCNN method DOI Creative Commons
Yi Gao, Na Wang, Fei Li

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 12, 2025

Aiming at the problem that it is difficult to accurately predict wellbore trajectory under complex geological conditions, NOA-LSTM-FCNN prediction method for steering drilling proposed by combining NOA, LSTM and FCNN. This adopts layer receive input data capture long-term dependencies within data, extracting important information. The FCNN performs nonlinear mapping on output of further extracts relevant features enhance accuracy. NOA employed hyperparameter optimization LSTM-FCNN model. experimental results show effect better than other methods. Taking well deviation angle H21 as an example, compared with traditional machine learning methods (LR, SVM BP) deep (CNN, GRU), evaluation index R² this was improved 0.17887, 0.03129, 0.0259, 0.00054, 0.00032 0.00031 respectively, showing significant accuracy advantages strong adaptability. In addition, applies various types effectively enhancing capabilities conditions.

Язык: Английский

Steering drilling wellbore trajectory prediction based on the NOA-LSTM-FCNN method DOI Creative Commons
Yi Gao, Na Wang, Fei Li

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 12, 2025

Aiming at the problem that it is difficult to accurately predict wellbore trajectory under complex geological conditions, NOA-LSTM-FCNN prediction method for steering drilling proposed by combining NOA, LSTM and FCNN. This adopts layer receive input data capture long-term dependencies within data, extracting important information. The FCNN performs nonlinear mapping on output of further extracts relevant features enhance accuracy. NOA employed hyperparameter optimization LSTM-FCNN model. experimental results show effect better than other methods. Taking well deviation angle H21 as an example, compared with traditional machine learning methods (LR, SVM BP) deep (CNN, GRU), evaluation index R² this was improved 0.17887, 0.03129, 0.0259, 0.00054, 0.00032 0.00031 respectively, showing significant accuracy advantages strong adaptability. In addition, applies various types effectively enhancing capabilities conditions.

Язык: Английский

Процитировано

0