Volume 8, Issue 1 (2024)
IQBQ 2024, 8(1): 26-35 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Badinloo M, Farashiani J, Khoozan D, Mansoori M, Daneshkhah V. Real-time Drilling Event Detection Based on Mud-logging data Using Long Short Term Memory Neural Networks. IQBQ 2024; 8 (1) :26-35
URL: http://arcpe.modares.ac.ir/article-38-76529-en.html
URL: http://arcpe.modares.ac.ir/article-38-76529-en.html
1- Faculty of Chemical Engineering, Tarbiat Modares University, Tehran, Iran
2- Faculty of Chemical Engineering, Tarbiat Modares University, Tehran, Iran ,khoozan@modares.ac.ir
3- Dana Energy Company, Tehran, Iran
2- Faculty of Chemical Engineering, Tarbiat Modares University, Tehran, Iran ,
3- Dana Energy Company, Tehran, Iran
Abstract: (119 Views)
Research Subject:Drilling operations frequently encounter numerous challenges that can lead to significant financial, human, and environmental losses. Therefore, predicting potential problems before they occur and implementing necessary preventive measures is crucial to minimizing risks. In this context, this study investigates the impact of employing artificial intelligence (AI) algorithms to forecast drilling complications using real-time mud logging data collected from existing wells in an Iranian oilfield.
Research approach: A hybrid architecture combining Long Short-Term Memory (LSTM) and Fully Connected neural networks was developed for the identification and detection of anomalies such as kicks and stuck pipe. Given the scarcity of these anomalies in the dataset, which could adversely affect model accuracy and performance, the Synthetic Minority Oversampling Technique (SMOTE) was applied to balance class distribution and enhance the overall effectiveness of the network. Furthermore, the influence of varying hyperparameters on reducing network error was systematically analyzed.
Main Results: Various network architectures and structures were examined. The experimental results indicated that the optimal model achieved an accuracy of 94.45% on the testing dataset with the following hyperparameters: a lookback of 7, a learning rate of 0.001, a dropout rate of 0.2, a batch size of 32, and a four-layer network architecture with 512, 256, and 256 units in the first, second, and third hidden layers, respectively. This configuration yielded higher accuracy and fewer false alarms in anomaly detection compared to other tested models. Based on the obtained results, this approach demonstrates significant potential for real-time anomaly detection in drilling operations.
Research approach: A hybrid architecture combining Long Short-Term Memory (LSTM) and Fully Connected neural networks was developed for the identification and detection of anomalies such as kicks and stuck pipe. Given the scarcity of these anomalies in the dataset, which could adversely affect model accuracy and performance, the Synthetic Minority Oversampling Technique (SMOTE) was applied to balance class distribution and enhance the overall effectiveness of the network. Furthermore, the influence of varying hyperparameters on reducing network error was systematically analyzed.
Main Results: Various network architectures and structures were examined. The experimental results indicated that the optimal model achieved an accuracy of 94.45% on the testing dataset with the following hyperparameters: a lookback of 7, a learning rate of 0.001, a dropout rate of 0.2, a batch size of 32, and a four-layer network architecture with 512, 256, and 256 units in the first, second, and third hidden layers, respectively. This configuration yielded higher accuracy and fewer false alarms in anomaly detection compared to other tested models. Based on the obtained results, this approach demonstrates significant potential for real-time anomaly detection in drilling operations.
Article Type: Original Research |
Subject:
drilling
Received: 2024/08/12 | Accepted: 2024/11/19 | Published: 2024/03/20
Received: 2024/08/12 | Accepted: 2024/11/19 | Published: 2024/03/20
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |