Sample class balancing based on borderline-SMOTE for lost circulation recognition.
Saved in:
| Title: | Sample class balancing based on borderline-SMOTE for lost circulation recognition. |
|---|---|
| Authors: | Sun, Weifeng1 (AUTHOR) sunwf@upc.edu.cn, Gong, Chentao1 (AUTHOR), Bu, Saisai1,2 (AUTHOR), Wang, Dongyue1 (AUTHOR), Huang, Weimin3 (AUTHOR) |
| Source: | Journal of Petroleum Exploration & Production Technology. Aug2026, Vol. 16 Issue 8, p1-16. 16p. |
| Subject Terms: | *Long short-term memory, *Gas well drilling |
| Company/Entity: | DCC PLC |
| Abstract: | During complex oil and gas drilling, minor lost circulation is a common yet hard-to-monitor downhole incident, and its accurate detection facilitates the timely implementation of on-site well control measures to mitigate economic losses caused by such incidents. Two primary reasons contribute to this challenge: first, the scarcity of lost circulation data compared to normal drilling data leads to severe class imbalance; second, conventional intelligent monitoring methods fail to capture long-term data trends. To develop classification capabilities, intelligent monitoring models must learn from samples composed of data segments extracted from data sequences corresponding to normal drilling and minor lost circulation. However, the aforementioned two issues impair the models' ability to extract and identify the feature of minor lost circulation. To address these dual challenges, this study introduces an integrated framework. First, a training sample class balancing method based on the Borderline-Synthetic Minority Oversampling Technique (Borderline-SMOTE) is proposed, which generates synthetic data specifically for samples near the decision boundary between normal drilling and minor lost circulation. Second, a novel recognition model combining Dilated Causal Convolution (DCC) and Long Short-Term Memory (LSTM) networks is developed to effectively capture long-range dependencies in sensor data. Notably, this study considers both sample class balance and model design as key factors influencing monitoring accuracy and proposes innovative solutions for each, in contrast to previous studies that focused only on one of these aspects. Experimental results on field data show that the proposed DCC-LSTM model achieves a recognition accuracy of 96.38%. When trained on the balanced dataset, six common intelligent models (k-Nearest Neighbor (kNN), decision tree, random forest, LSTM, Gated Recurrent Unit (GRU), and DCC-LSTM) exhibit significant performance improvements, with a maximum accuracy increase of 6.76%. The proposed method can be applied for minor lost circulation recognition in scenarios with limited samples, and is expected to be extended to other drilling anomaly detection tasks or complex downhole condition monitoring in the future. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 195285404 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Sample class balancing based on borderline-SMOTE for lost circulation recognition. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Sun%2C+Weifeng%22">Sun, Weifeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> sunwf@upc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Gong%2C+Chentao%22">Gong, Chentao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bu%2C+Saisai%22">Bu, Saisai</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Dongyue%22">Wang, Dongyue</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Weimin%22">Huang, Weimin</searchLink><relatesTo>3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Petroleum+Exploration+%26+Production+Technology%22">Journal of Petroleum Exploration & Production Technology</searchLink>. Aug2026, Vol. 16 Issue 8, p1-16. 16p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br />*<searchLink fieldCode="DE" term="%22Gas+well+drilling%22">Gas well drilling</searchLink> – Name: SubjectCompany Label: Company/Entity Group: Su Data: <searchLink fieldCode="DE" term="%22DCC+PLC%22">DCC PLC</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: During complex oil and gas drilling, minor lost circulation is a common yet hard-to-monitor downhole incident, and its accurate detection facilitates the timely implementation of on-site well control measures to mitigate economic losses caused by such incidents. Two primary reasons contribute to this challenge: first, the scarcity of lost circulation data compared to normal drilling data leads to severe class imbalance; second, conventional intelligent monitoring methods fail to capture long-term data trends. To develop classification capabilities, intelligent monitoring models must learn from samples composed of data segments extracted from data sequences corresponding to normal drilling and minor lost circulation. However, the aforementioned two issues impair the models' ability to extract and identify the feature of minor lost circulation. To address these dual challenges, this study introduces an integrated framework. First, a training sample class balancing method based on the Borderline-Synthetic Minority Oversampling Technique (Borderline-SMOTE) is proposed, which generates synthetic data specifically for samples near the decision boundary between normal drilling and minor lost circulation. Second, a novel recognition model combining Dilated Causal Convolution (DCC) and Long Short-Term Memory (LSTM) networks is developed to effectively capture long-range dependencies in sensor data. Notably, this study considers both sample class balance and model design as key factors influencing monitoring accuracy and proposes innovative solutions for each, in contrast to previous studies that focused only on one of these aspects. Experimental results on field data show that the proposed DCC-LSTM model achieves a recognition accuracy of 96.38%. When trained on the balanced dataset, six common intelligent models (k-Nearest Neighbor (kNN), decision tree, random forest, LSTM, Gated Recurrent Unit (GRU), and DCC-LSTM) exhibit significant performance improvements, with a maximum accuracy increase of 6.76%. The proposed method can be applied for minor lost circulation recognition in scenarios with limited samples, and is expected to be extended to other drilling anomaly detection tasks or complex downhole condition monitoring in the future. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=195285404 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s13202-026-02162-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 1 Subjects: – SubjectFull: Long short-term memory Type: general – SubjectFull: Gas well drilling Type: general – SubjectFull: DCC PLC Type: general Titles: – TitleFull: Sample class balancing based on borderline-SMOTE for lost circulation recognition. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Sun, Weifeng – PersonEntity: Name: NameFull: Gong, Chentao – PersonEntity: Name: NameFull: Bu, Saisai – PersonEntity: Name: NameFull: Wang, Dongyue – PersonEntity: Name: NameFull: Huang, Weimin IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Text: Aug2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 21900558 Numbering: – Type: volume Value: 16 – Type: issue Value: 8 Titles: – TitleFull: Journal of Petroleum Exploration & Production Technology Type: main |
| ResultId | 1 |
