Thirsty Reservoirs - Challenges in Drilling Through Severe Lost Circulation Zones

Gooneratne, Chinthaka P.; Gonzalez, Ernesto S. Gomez; Al-Musa, Abdulaziz S.; Osorio, Hugo F.

doi:10.2118/188461-ms

Cited by 11 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using the neural network model to train the sample data, we need to consider the high dimension, which will cause the neural network model to run slowly and consume hardware. In addition, in the case of large data dimensions, there is the problem of "dimension disaster" [29]. Therefore, it is necessary to select features of the data to achieve the purpose of dimensionality reduction.…”

Section: Feature Selectionmentioning

confidence: 99%

Prediction of Lost Circulation in Southwest Chinese Oil Fields Applying Improved WOA-BiLSTM

Liu,

Jia,

et al. 2023

Processes

View full text Add to dashboard Cite

Drilling hazards can be significantly decreased by anticipating potential mud loss and then putting the right well control measures in place. Therefore, it is critical to provide early estimates of mud loss. To solve this problem, an enhanced WOA (Whale Optimization Algorithm) and a BiLSTM (Bidirectional Long Short Term Memory) optimization based prediction model of lost circulation prior to drilling has been created. In order to minimize the noise in the historical comprehensive logging data, a wavelet filtering technique was first used. Then, according to the nonlinear Spearman rank correlation coefficient between mud loss and logging parameter values from large to small, seven characteristic parameters were preferred, and the sliding window was used to extract the relevant data. Secondly, the number of neurons in the first and second hidden layers, the maximum training time, and the initial learning rate of the BiLSTM model were optimized using the enhanced WOA method. The BiLSTM network was given the acquired superparameters in order to improve the model’s ability to predict occurrences. Finally, the model was trained and tested using the processed data. In comparison to the LSTM model, BiLSTM model, and WOA-BiLSTM model, respectively, the improved WOA-BiLSTM early mud loss prediction in southwest Chinese oil fields suggested in this study beat the others, receiving 22.3%, 18.7%, and 4.9% higher prediction accuracy, respectively.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Prediction of Lost Circulation in Southwest Chinese Oil Fields Applying Improved WOA-BiLSTM

Liu,

Jia,

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…In cases where circulation losses are minimal, the drilling operation may continue with partial returns of mud to the surface and under necessary precautions to ensure safe drilling operations. However, when circulation losses are severe, the drilling operation has to be stopped, and losses must be cured to regain circulation [3,4].…”

Section: A Backgroundmentioning

confidence: 99%

“…We applied MAF twice for each feature with ∈ [24,48] records, which correspond to [2,4] minutes, respectively, in the most common data frequency of 0.2 Hz. This allows for two levels of macroscopic trends and also two denoising stages, which the ML/DL model can learn from during training.…”

Section: ) Feature Engineeringmentioning

confidence: 99%

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

et al. 2021

View full text Add to dashboard Cite

Drilling operations consist of breaking the rock to deepen a wellbore for oil or gas extraction. A drilling fluid, circulating from the surface through the drill pipe and from the annulus to the surface, is used to remove rock cuttings and maintain hydrostatic pressure. Drilling fluid lost circulation incidents (LCIs) are major sources of non-productive time (NPT) in drilling operations. These incidents occur due to preexisting natural fractures (vugs, caverns, etc.) and/or drilling-induced hydraulic fractures. The initiation of an LCI could lead to other hazardous drilling phenomena, such as formation influx or kick/blowout, stuck pipe incidents, among others. LCIs are typically monitored at the rig site by observing drilling fluid levels in the fluid tanks. This manual process incurs missing the occurrence or late detection of LCIs. Machine learning (ML) and deep learning (DL) classification algorithms are powerful in processing time-series data and achieving early detection of such temporal phenomena. In this study, we performed a large-scale analysis of the surface drilling and rheology data obtained from historical wells with LCIs. This analysis includes primary and secondary preprocessing steps including, aggressive sampling, feature engineering, and window normalization to derive generalizable DL models for real-time operations. Focal loss was utilized to account for data class imbalance and train robust and generalizable models. The results obtained from different ML/DL algorithms showed that one-dimensional convolutional neural network models resulted in the best performance with state-of-the-art precision, recall, and F1 scores of 87.34%, 73.40%, and 79.77%, respectively, on unseen test drilling data.

show abstract

“…Stuck pipe incidents occur when downhole force(s) prevent the movement of the drillstring [23][24][25]52]. Mud circulation losses occur when the drilling mud flows from the wellbore into the formations (due to natural or induced factors) [26,27,53,54]. Finally, well influx refers to the flow of gas, water, or hydrocarbons from the geology into the wellbore [55,56].…”

Section: A Drillingmentioning

confidence: 99%

Well Control Space Out: A Deep-Learning Approach for the Optimization of Drilling Safety Operations

Magana-Mora

Affleck²,

Ibrahim

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

As drilling of new oil and gas wells increase to meet energy demands, it is essential to optimize processes to ensure the health and safety of the crew as well as the protection of the environment. Drilling operations represent a dynamic and challenging environment with natural and mechanical factors that need to be closely managed. Well control refers to the technique employed while drilling for balancing the hydrostatic and formation pressures to prevent the influx of water, gas, or hydrocarbons that would ultimately result in an uncontrolled flow to the surface. In the event of a well control incident, the crew must take proper and prompt actions to mitigate the risks and shut-in the well. In this study, we introduce the Well Control Space Out technology, an internet-of-things (IoT) environment that couples cameras and an edge server to implement stateof-the-art deep-learning models for the real-time processing of video images recording the drillstring. The computational models automatically perform object detection to keep track of key drilling rig components. The results from the video analysis are displayed on a dashboard describing the state and steps to follow in a well control incident without the need for any time-consuming, manual calculations. The internet-of-things edge foundation laid in drilling can be seamlessly expanded to other upstream sectors, where time-sensitive, critical decisions can be made in real-time, in the field, closer to operations. Finally, this technology can be seamlessly integrated with the current technologies to develop an automated closed-loop control system.INDEX TERMS Automation, deep-learning, computer vision, edge computing, internet-of-things, oil and gas drilling, well control.

show abstract

Thirsty Reservoirs - Challenges in Drilling Through Severe Lost Circulation Zones

Cited by 11 publications

References 16 publications

Prediction of Lost Circulation in Southwest Chinese Oil Fields Applying Improved WOA-BiLSTM

Prediction of Lost Circulation in Southwest Chinese Oil Fields Applying Improved WOA-BiLSTM

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

Well Control Space Out: A Deep-Learning Approach for the Optimization of Drilling Safety Operations

Contact Info

Product

Resources

About