SPE-207805-MS

Approach for Real-Time Prediction of Pipe Stuck Risk Using a Long

Short-Term Memory Autoencoder Architecture

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

Yujin Nakagawa and Tomoya Inoue, Japan Agency for Marine-Earth Science and Technology; Hakan Bilen,
University of Edinburgh; Konda R. Mopuri, Indian Institute of Technology; Keisuke Miyoshi and Shungo Abe, Japan
Oil, Gas and Metals National Corporation; Ryota Wada, University of Tokyo; Kouhei Kuroda, Japan Petroleum
Exploration Co., Ltd; Masatoshi Nishi and Hiroyasu Ogasawara, INPEX corporation

Copyright 2021, Society of Petroleum Engineers

This paper was prepared for presentation at the Abu Dhabi International Petroleum Exhibition & Conference to be held in Abu Dhabi, UAE, 15 – 18 November 2021.
The official proceedings were published online on 9 December 2021.

This paper was selected for presentation by an SPE program committee following review of information contained in an abstract submitted by the author(s). Contents
of the paper have not been reviewed by the Society of Petroleum Engineers and are subject to correction by the author(s). The material does not necessarily reflect
any position of the Society of Petroleum Engineers, its officers, or members. Electronic reproduction, distribution, or storage of any part of this paper without the written
consent of the Society of Petroleum Engineers is prohibited. Permission to reproduce in print is restricted to an abstract of not more than 300 words; illustrations may
not be copied. The abstract must contain conspicuous acknowledgment of SPE copyright.

Abstract
Pipe-sticking during drilling operations causes severe difficulties, including economic losses and safety
issues. Therefore, real-time stuck-pipe predictions are an important tool to preempt this problem and avoid
the aforementioned troubles. In this study, we have developed a prediction technique based on artificial
intelligence, in collaboration with industry, the government, and academia. This technique was developed
by combining an unsupervised learning model built using an encoder-decoder, long short-term memory
architecture, with a relative error function. The model was trained with the time series data of normal drilling
operations and based on an important hypothesis: reconstruction errors between observed and predicted
values are higher around the time of pipe sticking than during normal drilling operations. An evaluation
method of stuck-pipe possibilities using a relative error function reduced false predictors caused by large
variations of drilling parameters. The prediction technique was then applied to 34 actual stuck-pipe events,
where it was found that reconstruction errors calculated with the relative error function increased 0.5-10
hours prior to the pipe sticking for 17 out of 34 stuck-pipe events (thereby partly confirming our hypothesis).

Introduction
The occurrence of pipe-sticking during drilling operations leads to extreme delays in the completion of
the operation, well abandonment and, in the worst case, an uncontrolled spout of crude oil or gas into the
surroundings. These troubles are unexpected and cause economic losses and safety issues. An important
reason behind these troubles is the difficulty in the antecedent collection of information about the lithological
characteristics of the wells. Of the techniques used to reduce and avoid these troubles, two approaches are
eminent: one is the detection of stuck pipes as soon as possible after the pipe-sticking has started (hereafter
referred to as stuck-pipe detections), while the other is the prediction of pipe-sticking before it has occurred
(hereafter referred to as stuck-pipe predictions). The latter approach is more appropriate because it could
give crews sufficient time to take preventative or remedial actions. Therefore, stuck-pipe predictions that
2 SPE-207805-MS

use mud logging data that reflect the conditions inside the wells are an important step taken to avoid or
reduce the troubles associated with pipe-sticking.
Several ideas have been proposed to make stuck-pipe predictions using mud logging data. One involves
the use of statistical and/or analytical models (Hess 2016; Magana-Mora et al. 2019; Meor Hashim et
al. 2021b; Salminen et al. 2017; Shoraka et al. 2011), while another employs a combination of physics-
based and data-driven models (Zhang et al. 2019). Ideas based on supervised machine learning have been
proposed using the architecture of neural networks and/or support vector machines (Abbas et al. 2019;

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

Ahmed et al. 2019; Al-Baiyat et al. 2012; Alshaikh et al. 2019; Brankovic et al. 2020; Chamkalani et al.
2013; Meor Hashim et al. 2021a; Siruvuri et al. 2006; Zhu et al. 2019). In addition, prediction methods based
on unsupervised machine learning have also been put forth, including a three-dimensional convolutional
neural network with depth-domain data (Tsuchihashi et al. 2021), a mixture probability model with fully-
connected neural networks (Inoue et al. 2021) and a long short-term memory autoencoder (LSTM-AE)
model (Nakagawa et al. 2021).
To make real-time stuck-pipe predictions using artificial intelligence, we embarked on a project in
collaboration with industry, the government, and academia (Inoue et al. 2020). Most existing works of
research into stuck-pipe predictions are conducted using models based on supervised machine learning. The
time-tagged mud logging data (hereafter referred to as the time series data) of the actual drilling operations
in various wells, which were obtained by the collaborating companies, were used to make real-time stuck-
pipe predictions based on a binary classification model involving supervised machine learning. This model
requires negative and positive labels, which indicate the time periods during normal operation and before the
start of pipe-sticking, respectively; these labels were mapped to the time series data. The performance of this
model is, however, inadequate in the following ways. The first flaw is the insufficient accuracy of the labels
given to the time series data; this is caused by a difficulty in defining the time periods of the positive labels
since the time point corresponding to the exact start of pipe-sticking is unknown. The second deficiency
is the significant imbalance in the numbers of negative and positive labels; this arises from the fact that
the pipe-sticking scenario required for positive labels is a rare event relative to the time periods of normal
drilling operations. Models based on supervised machine learning, which requires accurate labeling, are
therefore unsuitable for stuck-pipe predictions. In contrast, models based on unsupervised machine learning
can be trained solely with the time series data of normal drilling operations and are hence more suited to
make stuck-pipe predictions.
We have developed the LSTM-AE model based on unsupervised machine learning for stuck-pipe
predictions (Nakagawa et al. 2021). The fundamental design of our unsupervised learning model was based
on two concepts. The first concept is that an unsupervised learning model is trained only with the time
series data of normal drilling operations. The second concept is the hypothesis that the differences between
the actual and predicted values of the time series data increase around the starting of pipe sticking, when
compared to the time of normal drilling operations. If this hypothesis could be proven to be correct, real-
time stuck-pipe predictions can be certainly be made before the start of pipe-sticking. In some cases,
reconstruction errors calculated with a mean squared error (MSE) function (hereafter referred to as MSE
reconstruction errors) increased prior to the pipe-sticking event which implies high possibilities of pipe-
sticking. However, the MSE reconstruction errors are sensitive to large variations in drilling parameters; this
was not unique to stuck-pipe predictions, but was common to all time series data. In this study, we developed
a new evaluation method of stuck-pipe possibilities using reconstruction errors calculated with a relative
error (RE) function (hereafter referred to as RE reconstruction errors), to make accurate real-time stuck-
pipe predictions. Fig. 1 shows a schematic of differences between this study and previous studies including
our previous study reported in Nakagawa et al. 2021. The novelty of our research is the development of
an evaluation method to make accurate real-time stuck-pipe predictions which can be less affected by large
variations in the drilling parameters unlike the MSE reconstruction errors. We believe that our method can be
SPE-207805-MS 3

applied to various types of wells and has the possibility of making accurate real-time stuck-pipe predictions
that cannot be achieved by supervised learning approaches.

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

Figure 1—Schematic of differences between this study and previous studies including our previous study.

Methods
In this study, we applied the new evaluation method of stuck-pipe possibilities using the RE reconstruction
errors to input and output data of the LSTM-AE model (Fig. 1). This method is expected to reduce false
predictors caused by the large variations in the drilling parameters found in our previous study.

Data
This study was performed using the time series data of actual drilling operations in 34 distinct wells,
obtained by the collaborating companies. The time series data spans 3,382 days and has a resolution of
4 s. To remove anomalous or inaccurate values, the data were filtered so that all 13 drilling parameters
simultaneously satisfied the minimum and maximum criteria presented in Table 1. The data were then
normalized by a standard scaler whose variables were calculated for each drilling parameter. As a result, we
found 63,694,136 datasets, where a single dataset consisted of 150 continuous time bins (i.e., 600 seconds)
and 13 drilling parameters.

Table 1—Summary of drilling parameters used in this study.

Parameter Name Description Unit Minimum Value Maximum Value

TD_spd Top drive rotation speed rpm −300 300

TD_trq Top drive torque kNm −100 100
ROP_ave Average rate of penetration m/h −9000 9000
Bitdepth Bit depth m −50 9000
Totdepth Total hole depth m −50 9000
Hookheight Hook height m −10 100
Hookload Hook load ton −20 500
WOB Weight on bit (calculated from hook load) kN – –
MRetFlow Return flow rate of mud % −30 100
SPP_pressA Pressure of stand-pipe manifold A MPa −5 50
MPP_SPM1 Stroke of mud pump #1 spm −1 160
MPP_SPM2 Stroke of mud pump #2 spm −1 160
FlowIn Flow from the mud pumps L/min −100 6000
4 SPE-207805-MS

As described in the "Introduction" section, the LSTM-AE model was designed to be trained with the time
series data of normal drilling operations. These data points were obtained by filtering the complete dataset
using two boundaries that indicated normal drilling operations: 7,200 s before the start of pipe-sticking
and 1,800 s after its end. As a result, we obtained 62,745,111 datasets corresponding to the normal drilling
operations of all 34 wells, among which we randomly extracted 375,000 datasets for training the model.
To evaluate the performance of the trained LSTM-AE model, we defined the time periods corresponding
to the normal operation of the drill and to the detection and prediction of pipe-sticking by using the daily

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

drilling reports obtained from the collaborating companies as follows. Labels of detector time periods
indicate the duration from 0 to 600 s after the start of pipe-sticking (hereafter referred to as detector labels).
We identified the detector time periods of 34 stuck-pipe events using the daily drilling report. Labels of
predictor time periods, on the other hand, indicate the duration from 604 to 4 s before the start of the pipe-
sticking event (hereafter referred to as predictor labels). In addition, labels of the normal operating time
periods were categorized into two types of durations — one before the predictor time period and one after
the detector time period. In this study, the first type was defined as 7,200 s before the start of pipe-sticking,
while the second type was defined as 1,800 s after the end of pipe-sticking. Based on the above three aspects,
detector, predictor, and normal operation labels were assigned to each time bin of the datasets for 30 distinct
wells which contain all 34 stuck-pipe events and were used to evaluate the performances of stuck-pipe
detections, predictions, and both detections and predictions, respectively. As a result, we obtained 5,023,
4,950 and 58,712,293 datasets for detector, predictor, and normal operation labels, respectively. It should
be noted here that the performances are highly dependent on the definitions of the time periods of detector,
predictor and normal operation.
Test datasets were then extracted from all the datasets for 30 distinct wells which contain all 34 stuck-pipe
events. The definition of negative and positive labels was necessary at this point to evaluate the performances
of the stuck-pipe detections and predictions. To evaluate the performance of stuck-pipe detections, the time
periods corresponding to normal operation and detection were taken as the negative and positive labels.
Similarly, the durations corresponding to normal operation and prediction were considered as the negative
and positive labels to evaluate the performance of stuck-pipe predictions.

Model
We have developed an autoencoder model using an encoder-decoder LSTM architecture — a feedback
neural network that is more suitable for time series predictions than standard feedforward neural networks
(Nakagawa et al. 2021). The LSTM-AE model was intended to reconstruct the input data consisting of
the 13 drilling parameters by first encoding them and then decoding them back to their original values to
make the output data consistent with input data. A major detail of this model is that the dimensions of
input data were narrowed down into a latent layer during the encoding stage of the process. Therefore,
the appropriate extraction of features from the latent layer is required for accurate reconstructions of input
and output data. If the LSTM-AE model were trained solely with the time series data from normal drilling
operations, differences between the input and output data would be expected to be small. Prior to and during
pipe-sticking, however, these differences were expected to increase. Thus, reconstruction errors were used
as indicators of the stuck-pipe predictions and detections.
In this study, we newly trained the LSTM-AE model using the following configurations. The input and
output shapes of the LSTM-AE model are represented by (150, 13), consistent with the shape of a single
dataset consisting of 150 time bins and the 13 drilling parameters defined in the "Data" section. Here, we
used 150 time bins (i.e., 600 seconds) by assuming the values of the drilling parameters to be affected
by the time-based variations during the 600 seconds under consideration. Following discussions with the
collaborating companies, we also chose the 13 drilling parameters (Table 1) that were likely to have the
most influence on pipe-sticking. For simplicity, we adopted only a single latent layer. The choice of suitable
latent dimensions is highly dependent on the training datasets used. Therefore, considering the (150, 13)
SPE-207805-MS 5

shapes of the input and output data, a latent dimension of 128 was adopted. Finally, an Adam optimizer
(Diederik et al. 2015; Sashank et al. 2018) was employed with a learning rate of 0.00001. The LSTM-AE
model was then, overall, trained by minimizing reconstruction errors calculated with the MSE function,
which is defined as:

(1)

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

where n is the number of time bins and xi and denote vectors of true and predicted values, respectively.
Since both these vectors consist of the 13 drilling parameters; therefore, EMSE is a vector of their averaged
MSE reconstruction errors.

Model Training
Using the training datasets, parameters of the LSTM-AE model were updated through 240,000 iterations.
A mini-batch of one iteration consisted of 64 randomly chosen datasets from the larger superset of training
data. To avoid overfitting, we utilized a function to halt the training process if the MSE reconstruction errors
did not improve even after a certain number of iterations. This function did not stop the training before
240,000 iterations. Fig. 2 shows the averaged MSE reconstruction error calculated by the mean squared error
function over each 500 iterations; these errors decreased with progressive iterations. The state of the model
was saved for performance evaluation when the averaged MSE reconstruction error indicated a minimum
value at 229,500 iterations.

Figure 2—The variation of averaged MSE reconstruction error with the number of iterations.

Evaluation of Trained Model

As described in the "Introduction" section, the MSE reconstruction errors were sensitively responding to
the large variations in the drilling parameters. Then, we evaluated possibilities of pipe-sticking using the RE
reconstruction errors which are suitable to compare accuracies of predicted values of different magnitudes.
Therefore, the RE reconstruction errors allow us to compare possibilities of pipe-sticking for each time bins
more directly than the MSE reconstruction errors. The RE function is defined as follows.

(2)
6 SPE-207805-MS

Since both xi and consist of the 13 drilling parameters; therefore, ERE is a vector of their averaged RE
reconstruction errors.

Case Studies
Statistics of RE Reconstruction Errors and Area Under Cover
Using the test datasets for 34 stuck-pipe events from 30 wells, RE reconstruction errors were calculated for

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

the detector, predictor, and normal operating time periods defined in the "Data" section. In Fig. 3, the left
panel shows distributions of the RE reconstruction errors for the stuck-pipe predictions, where histograms
labeled as negative and positive indicate the normal operating and predictor time periods, respectively. The
number of datasets for the normal operating time periods (i.e., 58,712,293 datasets) and predictor time
periods (i.e., 4,950 datasets) are highly imbalanced. On the same note, the right panel in Fig. 3 shows
distributions of the RE reconstruction errors for stuck-pipe detections, where histograms labeled as negative
and positive indicate the normal operating and detector time periods, respectively. The number of datasets
for the normal operating time periods (i.e., 58,712,293 datasets) and detector time periods (i.e., 5,023
datasets) are also highly imbalanced.

Figure 3—Left: Distributions of the RE reconstruction error for stuck-pipe predictions. Histograms
labeled as negative and positive indicate the normal operating and predictor time periods, respectively.
Right: Distributions of the RE reconstruction error for stuck-pipe detections. Histograms labeled
as negative and positive indicate the normal operating and detector time periods, respectively.

To evaluate the trained LSTM-AE model, area under cover (AUC), a performance indicator, was
calculated for each stuck-pipe event using the receiver operating characteristic (ROC) curve of the above
reconstruction errors, which quantifies the performance of a classification model at all classification
thresholds. The ROC curve and the AUC are commonly used for imbalanced classification problems with
few samples of the minority class and are suitable for the datasets in this study. The ROC curve depicts the
relation between the true positive rate (RTPR) and the false positive rate (RFPR), which are defined as:

(2)

and
SPE-207805-MS 7

(3)

where NTP, NFN, NFP, and NTN denote the numbers of results where the model correctly predicted positive
labels, incorrectly predicted negative labels, incorrectly predicted positive labels, and correctly predicted
negative labels, respectively. The AUC is then defined as the complete two-dimensional area underneath the
entire ROC curve. Using the above RE reconstruction errors and ROC curves computed from them shown
in Fig. 4, AUC values were calculated for the 34 stuck-pipe events from the 30 wells: 0.74 and 0.82 for the

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

predictor and detector time periods, respectively.

Figure 4—ROC curves for stuck-pipe predictions (left) and stuck-pipe detections (right).

Time Variations of RE Reconstruction Errors

To systematically evaluate the LSTM-AE model, RE reconstruction errors of each drilling parameter were
calculated for the test datasets representative of all 34 stuck-pipe events. Predictions were made by the
trained LSTM-AE model for each of the 150 continuous time bins by individually shifting through them.
This was followed by the calculation of RE reconstruction errors for each time bin and averaging them out
over all 150 time bins for each drilling parameter. As a result, we obtained 13 RE reconstruction errors for
every dataset. Fig. 5 shows an example of the time variations of the RE reconstruction errors averaged over
13 drilling parameters (top) and the contour map of the RE reconstruction errors for each drilling parameter
(bottom). The gray-hatched areas in Fig. 5 indicate the time periods corresponding to pipe-sticking.
8 SPE-207805-MS

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

Figure 5—Time variations of RE reconstruction errors averaged over 13 drilling parameters
(top) and a contour map of the RE reconstruction errors for each drilling parameter
(bottom). The gray-hatched areas indicate the time periods corresponding to pipe-sticking.

Discussion
Performance Evaluation Using AUC
There seems to be a difference in the distributions of the RE reconstruction errors between the negative
labels and the positive labels for both the predictor and detector time periods (Fig. 3). The difference is
more clearly than the difference in distribution of the MSE reconstruction errors reported in Nakagawa et
al. 2021. The RE reconstruction errors for the positive labels seem to be greater than those for the negative
labels for both the predictor and detector time periods. In addition, marginally good performances are given
by the AUC values of 0.74 and 0.82 for the predictor and detector time periods, respectively. These imply
the capability of the trained LSTM-AE model to detect and predict certain types of stuck-pipe events. In
addition, the AUC values are marginally improved compared with those values of 0.72 and 0.78 for predictor
and detector time periods using the MSE reconstruction errors, respectively (Nakagawa et al. 2021). Further
investigations into specific types of stuck-pipe events and their AUC values are required for a more detailed
evaluation of the performances of the trained LSTM-AE model.

Performance Evaluation Using Time Variation of RE Reconstruction Errors

The RE reconstruction errors increased 0.5-10 hours prior to the pipe sticking for 17 out of 34 stuck-
pipe events. Among all 13 drilling parameters in Fig. 5, the RE reconstruction errors of WOB and TD_trq
(depicted by the bottom panel in Fig. 5) were particularly high about 0.5 hours before the start of pipe-
SPE-207805-MS 9

sticking. In addition, the RE reconstruction errors of MRetFlow affected the RE reconstruction errors
averaged over 13 drilling parameters (indicated by the top panel in Fig. 5) about 2.5 hours before the start
of pipe-sticking. The above RE reconstruction errors are less affected by large variations in the drilling
parameters unlike the MSE reconstruction errors; this might be unique to stuck-pipe predictions. Therefore,
the use of the RE reconstruction errors is suitable to distinguish reliable, true predictors of pipe-sticking
from misleading, false ones caused by these large variations. The optimization of the drilling parameters
used as features and hyperparameters such as the input and output shapes is expected to lead to a decrease

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

in the number of false predictors and, thereby, more accurate predictions of pipe-sticking.

Conclusions
To make real-time stuck-pipe predictions using artificial intelligence, we undertook a project in
collaboration with industry, government, and academia (Inoue et al. 2020). This led to the development
of a stuck-pipe prediction technique comprising an evaluation method of stuck-pipe possibilities using the
RE reconstruction errors and an LSTM-AE model based on unsupervised machine learning. The model
was trained with the time-tagged mud logging data of normal drilling operations based on the hypothesis
that reconstruction errors between true and predicted values increase around the time of occurrence of the
stuck-pipe event, when compared to the time of normal drilling operations. The trained model and the
evaluation method of the stuck-pipe possibilities were applied to all 34 stuck-pipe events from 30 wells,
and results showed high AUC values for these events. We also found that the RE reconstruction errors did
increase prior to pipe-sticking in some cases (thereby partially confirming our hypothesis). In addition, we
also found that the RE reconstruction errors much reduced false predictors caused by large variations in
the drilling parameters unlike the MSE reconstruction errors, while there still remain slight responses to
the large variations. Therefore, we conclude that while the technique comprising the evaluation method of
stuck-pipe possibilities using the RE reconstruction errors and the LSTM-AE model appears promising for
the making of real-time stuck-pipe predictions which could give crews sufficient time to take preventative
or remedial actions, hyperparameter optimization is required for more accurate predictions.

Acknowledgements
This work was supported by the Japan Oil, Gas and Metals National Corporation.

References
Abbas, A. K., Flori, R., Almubarak, H. et al. 2019. Intelligent Prediction of Stuck Pipe Remediation Using Machine
Learning Algorithms. Paper presented at the SPE Annual Technical Conference and Exhibition, Calgary, Alberta,
Canada, September. SPE-196229-MS. https://doi.org/10.2118/196229-MS
Ahmed, O. S., Aman, B. M., Zahrani, M. A. et al. 2019. Stuck Pipe Early Warning System Utilizing Moving Window
Machine Learning Approach. Paper presented at the Abu Dhabi International Petroleum Exhibition & Conference,
Abu Dhabi, UAE, November. SPE-197674-MS. https://doi.org/10.2118/197674-MS
Al-Baiyat, I., and Lloyd H. 2012. Implementing Artificial Neural Networks and Support Vector Machines in Stuck Pipe
Prediction. Paper presented at the SPE Kuwait International Petroleum Conference and Exhibition, Kuwait City,
Kuwait, December. SPE-163370-MS. https://doi.org/10.2118/163370-MS
Alshaikh, A., Magana-Mora, A., Gharbi, S. A. et al. 2019. Machine Learning for Detecting Stuck Pipe Incidents: Data
Analytics and Models Evaluation. Paper presented at the International Petroleum Technology Conference, Beijing,
China, March. IPTC-19394-MS. https://doi.org/10.2523/IPTC-19394-MS
Brankovic, A., Matteucci, M., Restelli, M. et al. 2020. A Data-Based Approach for the Prediction of Stuck-Pipe Events
in Oil Drilling Operations. Paper presented at the Abu Dhabi International Petroleum Exhibition & Conference, Abu
Dhabi, UAE, November. SPE-202625-MS. https://doi.org/10.2118/202625-MS
Chamkalani, A., Pordel S. M., and Saeed P. 2013. Support Vector Machine Model: A New Methodology for Stuck Pipe
Prediction. Paper presented at the SPE Unconventional Gas Conference and Exhibition, Muscat, Oman, January.
SPE-164003-MS. https://doi.org/10.2118/164003-MS
10 SPE-207805-MS

Diederik, K., Jimmy, B. 2015. Adam: A Method for Stochastic Optimization. Published as a conference paper at the 3rd
International Conference for Learning Representations, San Diego. https://arxiv.org/abs/1412.6980v8
Hess, J. 2016. Pipe Sticking Prediction Using LWD Real-Time Measurements. Paper presented at the IADC/SPE Drilling
Conference and Exhibition, Fort Worth, Texas, USA, March. SPE-178828-MS. https://doi.org/10.2118/178828-MS
Inoue, T., Wada, R., Miyoshi, K. et al. 2020. Research Project on Safety Improvement by Applying Digital Technology
for Drilling Operations (in Japanese), Proceedings of the Japan Society of Naval Architects and Ocean Engineers.
ISSN: 2185-1840.
Inoue, T., Nakagawa, Y., Wada, R. et al. 2021. Attempt of Early Stuck Detection Using Unsupervised Deep Learning with

Downloaded from http://onepetro.org/SPEADIP/proceedings-pdf/21ADIP/4-21ADIP/D041S112R001/2542614/spe-207805-ms.pdf by U. of Alberta Library user on 15 September 2023

Probability Mixture Model. Proceedings of the ASME 2021 40th International Conference on Ocean, Offshore and
Arctic Engineering OMAE2021. Virtual, Online.
Magana-Mora, A., Gharbi, S., Alshaikh, A. et al. 2019. AccuPipePred: A Framework for the Accurate and Early Detection
of Stuck Pipe for Real-Time Drilling Operations. Paper presented at the SPE Middle East Oil and Gas Show and
Conference, Manama, Bahrain, March. SPE-194980-MS. https://doi.org/10.2118/194980-MS
Meor Hashim, M. M., Yusoff, H. M., Arriffin, F. M. et al. 2021a. Utilizing Artificial Neural Network for Real-Time
Prediction of Differential Sticking Symptoms. Paper presented at the International Petroleum Technology Conference,
Virtual, March. IPTC-21221-MS. https://doi.org/10.2523/IPTC-21221-MS
Meor Hashim, M. M., Yusoff, H. M., Arriffin, F. M. et al. 2021b. Performance Improvement of Wells Augmented Stuck
Pipe Indicator via Model Evaluations. Paper presented at the International Petroleum Technology Conference, Virtual,
March. IPTC-21455-MS. https://doi.org/10.2523/IPTC-21455-MS
Nakagawa, Y., Inoue, T., Bilen, H. et al. 2021. An Unsupervised Learning Model For Pipe Stuck Predictions Using A Long
Short-Term Memory Autoencoder Architecture. Paper accepted by SPE/IATMI Asia Pacific Oil & Gas Conference
and Exhibition, SPE-205677-MS
Salminen, K., Cheatham, C., Smith, M. et al. 2017. Stuck-Pipe Prediction by Use of Automated Real-Time Modeling and
Data Analysis. SPE Drill & Compl 32 (2017): 184–193. SPE-178888-PA. https://doi.org/10.2118/178888-PA
Sashank, J. R., Satyen, K., and Sanjiv, K. 2018. On the Convergence of Adam and Beyond. International Conference on
Learning Representations. https://openreview.net/forum?id=ryQu7f-RZ
Shoraka, S. A., Shadizadeh, S. R., and Pordel Shahri, M. 2011. Prediction of Stuck Pipe in Iranian South Oil Fields Using
Multivariate Statistical Analysis. Paper presented at the Nigeria Annual International Conference and Exhibition,
Abuja, Nigeria, July. SPE-151076-MS. https://doi.org/10.2118/151076-MS
Siruvuri, C., Nagarakanti, S., and Samuel, R. 2006. Stuck Pipe Prediction and Avoidance: A Convolutional Neural
Network Approach. Paper presented at the IADC/SPE Drilling Conference, Miami, Florida, USA, February.
SPE-98378-MS. https://doi.org/10.2118/98378-MS
Tsuchihashi, N., Wada, R., Ozaki, M. et al. 2021. Early Stuck Pipe Sign Detection with Depth-Domain 3D
Convolutional Neural Network Using Actual Drilling Data. SPE J. 26 (2021): 551–562. SPE-204462-PA. https://
doi.org/10.2118/204462-PA
Zhang, F., Islam, A., Zeng, H. et al. 2019. Real Time Stuck Pipe Prediction by Using a Combination of Physics-
Based Model and Data Analytics Approach. Paper presented at the Abu Dhabi International Petroleum Exhibition &
Conference, Abu Dhabi, UAE, November. SPE-197167-MS. https://doi.org/10.2118/197167-MS
Zhu, Q., Wang, Z., and Jian H. 2019. Stuck Pipe Incidents Prediction Based On Data Analysis. Paper presented
at the SPE Gas & Oil Technology Showcase and Conference, Dubai, UAE, Octobe. SPE-198672-MS. https://
doi.org/10.2118/198672-MS