Use of Historic Data to Improve Drilling Efficiency: A Pattern Recognition Method and Trial Results

Kristjansson, Sean D.; Neudfeldt, Adam; Lai, Stephen W.; Wang, Julian; Tremaine, Dean

doi:10.2118/178901-ms

Cited by 13 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [46], the authors proposed a novel k-means clustering algorithm for multi-view data employing a learning mechanism for computation of weights corresponding to new features, which are later used for updation of cluster centers member-ship and view weights. A maximum likelihood-based approach was developed based on clustering techniques to improve the efficiency of the boreholes [47]. In another study presented in [48], the authors determined the linear relationship between digging wells and geological parameters of rock and soil.…”

Section: Literature Reviewmentioning

confidence: 99%

“…It can be used to save time and cost of the digging process because it used surface parameters only High computational cost due to modifying surface parameters using brute force Pattern recognition method [47] The presented study aimed to utilize data-driven methods that searches historic data to identify patterns for future well for efficient drilling.…”

Section: Random Forest (Rf)mentioning

confidence: 99%

See 1 more Smart Citation

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

et al. 2021

View full text Add to dashboard Cite

During the last decade, substantial resources have been invested to exploit massive amounts of boreholes data collected through groundwater extraction. Furthermore, boreholes depth can be considered one of the crucial factors in digging borehole efficiency. Therefore, a new solution is needed to process and analyze boreholes data to monitor digging operations and identify the boreholes shortcomings. This research study presents a boreholes data analysis architecture based on data and predictive analysis models to improve borehole efficiency, underground safety verification, and risk evaluation. The proposed architecture aims to process and analyze borehole data based on different hydrogeological characteristics using data and predictive analytics to enhance underground safety verification and planning of borehole resources. The proposed architecture is developed based on two modules; descriptive data analysis and predictive analysis modules. The descriptive analysis aims to utilize data and clustering analysis techniques to process and extract hidden hydrogeological characteristics from borehole history data. The predictive analysis aims to develop a bi-directional long short-term memory (BD-LSTM) to predict the boreholes depth to minimize the cost and time of the digging operations. Furthermore, different performance measures are utilized to evaluate the performance of the proposed clustering and regression models. Moreover, our proposed BD-LSTM model is evaluated and compared with conventional machine learning (ML) regression models. The R 2 score of the proposed BD-LSTM is 0.989, which indicates that the proposed model accurately and precisely predicts boreholes depth compared to the conventional regression models. The experimental and comparative analysis results reveal the significance and effectiveness of the proposed borehole data analysis architecture. The experimental results will improve underground safety management and the efficiency of boreholes for future wells.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Random Forest (Rf)mentioning

confidence: 99%

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For discovering a hidden pattern in drilling, data clustering is a suitable technique, as it can identify the density and sparsity of particular regions in a dataset having their attributes-clustering group similar objects into one group by calculating the distances between objects. In [26], the authors presented a maximum likelihood-based approach for clustering to improve drilling performance. The proposed approach generated patterns for recommending optimal drilling parameters.…”

Section: Related Workmentioning

confidence: 99%

Toward Effective Pattern Recognition Based on Enhanced Weighted K-Mean Clustering Algorithm for Groundwater Resource Planning in Point Cloud

Rizwan¹,

Iqbal

Khan

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recently groundwater scarcity has accelerated drilling operations worldwide as drilled boreholes are substantial for replenishing the needs of safe drinking water and achieving long-term sustainable development goals. However, the quest for achieving optimal drilling efficiency is ever continued. This paper aims to provide valuable insights into borehole drilling data utilizing the potential of advanced analytics by employing several enhanced cluster analysis techniques to propel drilling efficiency optimization and knowledge discovery. The study proposed an L2-weighted K-mean clustering algorithm in which the mean is computed from transformed weighted feature space. To verify the effectiveness of our proposed L2-weighted K-mean algorithm, we performed a comparative analysis of the proposed work with traditional clustering algorithms to estimate the digging time and depth for different soil materials and land layers. The proposed clustering scheme is evaluated widely used evaluation metrics such as Dunn Index, Davies-Bouldin index (DBI), Silhouette coefficient (SC), and Calinski-Harabaz Index (CHI). The study results highlight the significance of the proposed clustering algorithm as it achieved better clustering results than conventional clustering approaches. Moreover, for facilitation of subsequent learning, achievement of reliable classification, and generalization, we performed feature extraction based on the time interval of the drilling process according to soil material and land layer. We formulated the solution by grouping the extracted features into six different blocks to achieve our desired objective. Each block corresponds to various characteristics of soil materials and land layers. Extracted features are examined and visualized in point cloud space to analyze the water level patterns, depth, and days required to complete the drilling operations.INDEX TERMS data analysis; features extraction; unsupervised learning; machine learning; strategic planning and management;

show abstract

“…Because pattern recognition is a branch of artificial intelligence concerned with classification or description of observations, and which was applied to find patterns among non-linear and interdependent parameters involving in complex system [11][12][13][14][15]. Therefore, this thesis will use the methods and principles of pattern recognition to improve the system designed in [8].…”

Section: Introductionmentioning

confidence: 99%

Design for intelligent prediction system of oilfield development index based on pattern recognition

Zhong¹,

Lv²,

Bao³

et al. 2018

Filomat

View full text Add to dashboard Cite

In order to realize Digital Oil Field, some key problems need to be improved, esp. accurate and automatic prediction of oilfield development indexes which may be resolved by designing of intelligent prediction system. With the shortcoming of inference of system designed by us, automatic inference problem for a complicated intelligent prediction system was improved using pattern recognition method. First, intelligent prediction system and the methods as well as principles of pattern recognition were introduced. Then the framework of intelligent prediction system based on pattern recognition was formulated by using technologies and methods of human-computer interface, fuzzy processing and pattern recognition. Secondly, the knowledge base was extended as augmented knowledge base with introducing credibility to measure uncertainty of knowledge. Particularly, the methods and principles of pattern recognition were used to design two recognizers and one inferring machine. Moreover, the method of selecting predictive model based on reasoning of pattern recognition was presented by coupling them and intelligent prediction system. Finally, the design of improving intelligent prediction system of oilfield development indexes was simulated. Simulation result shows that improved system may automatically realize to select optimal prediction model by computer according to different reservoirs and different development stages. The results obtained in this thesis will helpful to design for intelligent prediction system.

show abstract

Use of Historic Data to Improve Drilling Efficiency: A Pattern Recognition Method and Trial Results

Cited by 13 publications

References 8 publications

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

Boreholes Data Analysis Architecture Based on Clustering and Prediction Models for Enhancing Underground Safety Verification

Toward Effective Pattern Recognition Based on Enhanced Weighted K-Mean Clustering Algorithm for Groundwater Resource Planning in Point Cloud

Design for intelligent prediction system of oilfield development index based on pattern recognition

Contact Info

Product

Resources

About