Steering drilling wellbore trajectory prediction based on the NOA-LSTM-FCNN method
Yi Gao1,2, Na Wang3, Fei Li4,5
1Shaanxi Key Laboratory of Measurement and Control Technology for Oil and Gas Wells, Xi'an Shiyou University, Xi'an, 710065, China. gy@xsyu.edu.cn.
Scientific Reports
|February 12, 2025
Summary
A novel NOA-LSTM-FCNN method improves wellbore trajectory prediction accuracy in complex geology. This approach enhances steering drilling by optimizing Long Short-Term Memory (LSTM) and Fully Connected Neural Network (FCNN) models using Novel Optimization Algorithm (NOA).
Area of Science:
- Petroleum Engineering
- Geological Engineering
- Artificial Intelligence in Geosciences
Background:
- Accurate wellbore trajectory prediction is crucial for efficient drilling operations, especially in complex geological formations.
- Existing methods often struggle with the intricate geological conditions encountered during directional drilling.
Purpose of the Study:
- To propose a novel prediction method for steering drilling wellbore trajectory that overcomes limitations in complex geological conditions.
- To enhance the accuracy and adaptability of wellbore trajectory prediction using advanced machine learning techniques.
Main Methods:
- A hybrid model combining Long Short-Term Memory (LSTM) for data dependency extraction and Fully Connected Neural Network (FCNN) for feature extraction.
- Integration of Novel Optimization Algorithm (NOA) for hyperparameter optimization of the LSTM-FCNN model.
- Validation against traditional machine learning (LR, SVM, BP) and deep learning (CNN, LSTM, GRU) methods using well deviation angle data.
Main Results:
- The proposed NOA-LSTM-FCNN method demonstrated superior prediction performance compared to existing techniques.
- Significant improvements in the R² evaluation index were observed, indicating enhanced prediction accuracy.
- The method showed strong adaptability across various wellbore trajectory datasets and complex geological conditions.
Conclusions:
- The NOA-LSTM-FCNN method offers a robust and accurate solution for wellbore trajectory prediction in challenging geological environments.
- This approach effectively enhances steering drilling capabilities, leading to more efficient and precise well placement.
- The study highlights the potential of integrating advanced AI techniques for solving complex problems in the oil and gas industry.
Keywords:
Fully connected neural networkLong short-term memory networkNutcracker optimization algorithmSteering drilling systemWellbore trajectory prediction
