• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1032-1038
• /
• 2021

Rate of penetration(ROP) is one of the important variables for maximizing the drilling performance. In order to maximize drilling efficiency, it is necessary to increase the drilling speed, and real-time ROP prediction is important so that the driller can identify problems during drilling. The ROP has a high correlation with the drillstring rotational speed, weight on bit, and flow rate. In this paper, the ROP was predicted using a data-driven supervised learning model trained from the drilling efficiency parameters. As a result of comparison through the performance evaluation metrics of the regression model, the root mean square error(RMSE) of the RF model was 4.20 and the mean absolute percentage error(MAPE) was 9.08%, confirming the best predictive performance. The proposed method can be used as a base model for ROP prediction when constructing a real-time drilling operation guide system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.204-206
• /
• 2021

Real-time drilling parameters prediction is a considerably important study from the viewpoint of maximizing drilling efficiency. Among the methods of maximizing drilling, the method of improving the drilling speed is common, which is related to the rate of penetration, drillstring rotational speed, weight on bit, and drilling mud flow rate. This study proposes a method of predicting the drilling rate, one of the real-time drilling parameters, using a recurrent neural network-based deep learning model, and compares the existing physical-based drilling rate prediction model with a prediction model using deep learning.

• Journal of the Korean Institute of Gas
• /
• v.24 no.1
• /
• pp.66-75
• /
• 2020

Drilling operation is the most important and costly essential work in oil and gas exploration and development. Therefore, the studies about rate of penetration have been carried out continuously to improve drilling efficiency. In recent years, data-driven models have been developed by various researchers to overcome disadvantages of traditional mathematical models. For the data-driven models, selecting proper algorithms and parameters is very important. In addition, data-driven models should be retrained in real-time during continuous drilling operations in order to improve the model performance. In this paper, the latest studies are investigated to provide information about algorithms, drilling parameters and model retraining intervals that used in drilling optimization.

• The Journal of Engineering Geology
• /
• v.18 no.4
• /
• pp.359-369
• /
• 2008

For the design and effective management of underground storage caverns, preliminary investigation on the hydrogeologic parameters around caverns and analysis on the groundwater flow must be carried out. The data collection is very imporatnat task for the hydrogeologic design so various hydraulic tests have been performed. When analyzing the injection/fall off test data, existing graphical method to estimate the parameters in Theis' equation is widely used. However this method has some sources of error when estimating parameters by means of human faults. Therefore the method of estimating parameters by means of statistical methods such as regression type is evaluated as a useful tool. In this study, nonlinear regression analysis for the Theis' equation is suggested and applied to the estimation of parameters for the real field interference data around underground storage caverns. Damping parameter which reduce the iteration numbers and inhance the convergence is also introduced.

• Economic and Environmental Geology
• /
• v.45 no.1
• /
• pp.41-48
• /
• 2012

A theoretical $CO_2$ storage capacity is estimated on the southwestern continental shelf margin of Ulleung Basin, offshore Korea using 2D/3D multi-channel seismic and wellbore data acquired in the area over the two decades since the late 1980s. For the first time in Korea, the present study applies an efficiency factor to the capacity calculation, together with the other required parameters. For possible $CO_2$ storage volume estimation of the study area, we interpreted the seismic data in the Gorae area from 800 m to 3,000 m below the seafloor integrated with the well data, and identified five different seismic units; the limited depth interval is considered because of fluid state of $CO_2$ and tightness of the formation. The total volumes of each seismic unit were converted with a time-depth relation inferred from the checkshot surveys before the other required parameters including porosity and density were applied to compute the potential storage capacity. The accumulated possible storage volume from the five depositional units in the study area is estimated to be approximately 5,100 Mton ($P_{50}$). The approaches made in this study will be applied to the rest area of the basin and other continental shelves (i.e., Yellow Sea and northern part of East China Sea) in the next phase.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.155-159
• /
• 2004

Recently, there are many trials about Artificial neural networks : ANNs structure and studying method of researches for forecasting traffic volume. ANNs have a powerful capabilities of recognizing pattern with a flexible non-linear model. However, ANNs have some overfitting problems in dealing with a lot of parameters because of its non-linear problems. This research deals with the application of a variety of model selection criterion for cancellation of the overfitting problems. Especially, this aims at analyzing which the selecting model cancels the overfitting problems and guarantees the transferability from time measure. Results in this study are as follow. First, the model which is selecting in sample does not guarantees the best capabilities of out-of-sample. So to speak, the best model in sample is no relationship with the capabilities of out-of-sample like many existing researches. Second, in stability of model selecting criterion, AIC3, AICC, BIC are available but AIC4 has a large variation comparing with the best model. In time-series analysis and forecasting, we need more quantitable data analysis and another time-series analysis because uncertainty of a model can have an effect on correlation between in-sample and out-of-sample.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2005.09a
• /
• pp.21-36
• /
• 2005

Although the main geology of Korea consists of granite and gneiss, it Is not uncommon to encounter anisotropy Phenomena in crosshole radar tomography even when the basement is crystalline rock. To solve the anisotropy Problem, we have developed and continuously upgraded an anisotropic inversion algorithm assuming a heterogeneous elliptic anisotropy to reconstruct three kinds of tomograms: tomograms of maximum and minimum velocities, and of the direction of the symmetry axis. In this paper, we discuss the developed algorithm and introduce some case histories on the application of anisotropic radar tomography in Korea. The first two case histories were conducted for the construction of infrastructure, and their main objective was to locate cavities in limestone. The last two were performed In a granite and gneiss area. The anisotropy in the granite area was caused by fine fissures aligned in the same direction, while that in the gneiss and limestone area by the alignment of the constituent minerals. Through these case histories we showed that the anisotropic characteristic itself gives us additional important information for understanding the internal status of basement rock. In particular, the anisotropy ratio defined by the normalized difference between maximum and minimum velocities as well as the direction of maximum velocity are helpful to interpret the borehole radar tomogram.

• Geophysics and Geophysical Exploration
• /
• v.10 no.4
• /
• pp.229-240
• /
• 2007

In this study, seismic anisotropic tomography algorithm was developed for imaging the seismic velocity anisotropy of the subsurface. This algorithm includes several inversion schemes in order to make the inversion process stable and robust. First of all, the set of the inversion parameters is limited to one slowness, two ratios of slowness and one direction of the anisotropy symmetric axis. The ranges of the inversion parameters are localized by the pseudobeta transform to obtain the reasonable inversion results and the inversion constraints are controlled efficiently by ACB(Active Constraint Balancing) method. Especially, the inversion using the Fresnel volume is applied to the anisotropic tomography and it can make the anisotropic tomography more stable than ray tomography as it widens the propagation angle coverage. The algorithm of anisotropic tomography is verified through the numerical experiments. And, it is applied to the real field data measured at limestone region and the results are discussed with the drill log and geological survey data. The anisotropic tomography algorithm will be able to provide the useful tool to evaluate and understand the geological structure of the subsurface more reasonably with the anisotropic characteristics.