Related references
Note: Only part of the references are listed.
Article
Chemistry, Multidisciplinary
Qian Li et al.
Summary: During drilling operations, stuck pipe often occurs due to various reasons. However, there is a lack of scientific basis and studies in identifying the type of stuck pipe. In this paper, a method based on a friction torque rigid rod model and the SAX method was proposed to accurately identify the stuck pipe type. The results showed that this method can combine digital twins and knowledge graphs to provide a basis for targeted measures to deal with stuck pipe incidents.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Loris Alif Syahputra et al.
Summary: This article discusses the application of unsupervised learning, specifically self-organizing maps, for hydrocarbon exploration. It demonstrates how unsupervised learning can provide a more objective and efficient analysis compared to traditional methods. The study utilizes self-organizing maps to detect and delineate hydrocarbons, as well as eliminate attribute redundancy. The proposed method shows promise in early hydrocarbon detection and is validated using well log simulations and real seismic data.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Shuo Zhu et al.
Summary: This study presents three methods for predicting stuck pipe, including detection of friction coefficient, prediction of stuck pipe probability using artificial neural network, and establishment of a comprehensive indicator using fuzzy mathematics. The results indicate that the last model is the best, with a high prediction accuracy.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Chuanzhen Zang et al.
Summary: With the development of China's oil and gas exploration and development, optimizing drilling parameters has become increasingly important in complex formations. This paper proposes an intelligent ROP prediction model using logging data and a hard-string model to calculate string drag. The drilling parameters are optimized using the NSGA-II algorithm, resulting in improved ROP and reduced drag.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Zhaopeng Zhu et al.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Hongtao Liu et al.
Summary: This study proposes an intelligent prediction model based on LSTM-FNN for ROP prediction in ultra-deep wells. The results show that this model outperforms traditional FNN and LSTM models in terms of accuracy and has good generalization performance for adjacent wells.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Hadyan Pratama et al.
Summary: This article demonstrates a semi-supervised learning technique for automatically detecting geological features in seismic data. By utilizing unsupervised learning and supervised Convolutional Neural Network (CNN) model, the authors successfully achieve accurate delineation of geological features in complex seismic data. The method is validated in two cases with different geological settings, and it proves to be accurate and reliable.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Chunfei Fang et al.
Summary: This paper proposes a multi-scale perceptual convolutional neural network algorithm to evaluate cementing quality. By identifying VDL logging data, the algorithm can assess cementing quality more accurately, while having lower time and space complexity.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Minsoo Ji et al.
Summary: This study proposes a deep-learning-based model for generating synthetic compressional wave velocity (Vp) from well-logging data, and applies it to the study of gas hydrates in the Ulleung Basin in the East Sea, Republic of Korea. By detecting the morphology of the hydrate and identifying the bottom-simulating reflector (BSR), the model can accurately estimate missing well-logging data, contributing to the reservoir characterization of gas-hydrate-bearing sediments.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Hu Yin et al.
Summary: This study analyzes and compares the two main forms of gas kicks in drilling fractured carbonate reservoirs, which are underbalanced pressure and gravity displacement. A two-phase flow model with a wellbore-formation coupling is developed, and an identification method based on dynamic time warping (DTW) is proposed to identify the type of gas kick using real-time surface measurement parameters.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Hangyu Li et al.
Summary: This study uses machine learning to predict the performance of CO2-WAG under different injection parameters. The results show that this method can predict the performance of CO2-WAG rapidly and accurately, with high computational efficiency.
APPLIED SCIENCES-BASEL
(2022)