Research on fast marking method for indicator diagram of pumping well based on K-means clustering
Indicator diagram is the key basis for fault diagnosis of pumping wells in oil exploitation. With the rapid development of machine learning, the fault diagnosis of indicator diagram based on deep learning has garnered increasing attention. This kind of methods train neural network models with marked...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023076764 |
| _version_ | 1797646539220320256 |
|---|---|
| author | Xiang Wang Zhiwei Shao Yancen Shen Yanfeng He |
| author_facet | Xiang Wang Zhiwei Shao Yancen Shen Yanfeng He |
| author_sort | Xiang Wang |
| collection | DOAJ |
| description | Indicator diagram is the key basis for fault diagnosis of pumping wells in oil exploitation. With the rapid development of machine learning, the fault diagnosis of indicator diagram based on deep learning has garnered increasing attention. This kind of methods train neural network models with marked samples, and then inputs images into the trained models and outputs their categories. At present, the preparation of indicator diagram sample set relies on experts' analysis of indicator diagram images one by one. However, it involves extensive manual work and manual marking is prone to errors, so the marked samples are often insufficient in quantity. In order to quickly mark a large number of indicator diagram samples, the oil well data was plotted into standardized indicator diagram, and then three feature extraction methods for indicator diagrams were proposed: feature extraction based on original vector, feature extraction based on three-dimensional pixel tensor, feature extraction based on convolutional neural network. These methods convert the indicator diagram into corresponding feature vectors, which are then clustered using the K-means clustering algorithm, enabling the corresponding indicator diagrams to be classified into different categories based on the clustering results. Using 20,000 randomly selected pieces of data from 100 pumping wells, this study clusters the sample set using the three proposed methods. The results indicated that the time consumption were 0.2, 8.3, and 0.7 h, with accuracy rates of 98%, 92%, and 95%, respectively. For indicator diagrams, the clustering method based on the original vector has outstanding performance in terms of efficiency and accuracy. This provides an automatic tool for the preparation of the pumping well fault diagnosis dataset, and its efficiency can be increased by tens of times compared with manual marking. |
| first_indexed | 2024-03-11T15:04:09Z |
| format | Article |
| id | doaj.art-be0c79de5d274ef7a504f1cabc2d4aa1 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-11T15:04:09Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-be0c79de5d274ef7a504f1cabc2d4aa12023-10-30T06:06:14ZengElsevierHeliyon2405-84402023-10-01910e20468Research on fast marking method for indicator diagram of pumping well based on K-means clusteringXiang Wang0Zhiwei Shao1Yancen Shen2Yanfeng He3Corresponding author.; School of Petroleum and Natural Gas Engineering, Changzhou University, Changzhou, 213164, ChinaSchool of Petroleum and Natural Gas Engineering, Changzhou University, Changzhou, 213164, ChinaSchool of Petroleum and Natural Gas Engineering, Changzhou University, Changzhou, 213164, ChinaSchool of Petroleum and Natural Gas Engineering, Changzhou University, Changzhou, 213164, ChinaIndicator diagram is the key basis for fault diagnosis of pumping wells in oil exploitation. With the rapid development of machine learning, the fault diagnosis of indicator diagram based on deep learning has garnered increasing attention. This kind of methods train neural network models with marked samples, and then inputs images into the trained models and outputs their categories. At present, the preparation of indicator diagram sample set relies on experts' analysis of indicator diagram images one by one. However, it involves extensive manual work and manual marking is prone to errors, so the marked samples are often insufficient in quantity. In order to quickly mark a large number of indicator diagram samples, the oil well data was plotted into standardized indicator diagram, and then three feature extraction methods for indicator diagrams were proposed: feature extraction based on original vector, feature extraction based on three-dimensional pixel tensor, feature extraction based on convolutional neural network. These methods convert the indicator diagram into corresponding feature vectors, which are then clustered using the K-means clustering algorithm, enabling the corresponding indicator diagrams to be classified into different categories based on the clustering results. Using 20,000 randomly selected pieces of data from 100 pumping wells, this study clusters the sample set using the three proposed methods. The results indicated that the time consumption were 0.2, 8.3, and 0.7 h, with accuracy rates of 98%, 92%, and 95%, respectively. For indicator diagrams, the clustering method based on the original vector has outstanding performance in terms of efficiency and accuracy. This provides an automatic tool for the preparation of the pumping well fault diagnosis dataset, and its efficiency can be increased by tens of times compared with manual marking.http://www.sciencedirect.com/science/article/pii/S2405844023076764Pumping wellIndicator diagramFault diagnosisK-means clustering |
| spellingShingle | Xiang Wang Zhiwei Shao Yancen Shen Yanfeng He Research on fast marking method for indicator diagram of pumping well based on K-means clustering Heliyon Pumping well Indicator diagram Fault diagnosis K-means clustering |
| title | Research on fast marking method for indicator diagram of pumping well based on K-means clustering |
| title_full | Research on fast marking method for indicator diagram of pumping well based on K-means clustering |
| title_fullStr | Research on fast marking method for indicator diagram of pumping well based on K-means clustering |
| title_full_unstemmed | Research on fast marking method for indicator diagram of pumping well based on K-means clustering |
| title_short | Research on fast marking method for indicator diagram of pumping well based on K-means clustering |
| title_sort | research on fast marking method for indicator diagram of pumping well based on k means clustering |
| topic | Pumping well Indicator diagram Fault diagnosis K-means clustering |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023076764 |
| work_keys_str_mv | AT xiangwang researchonfastmarkingmethodforindicatordiagramofpumpingwellbasedonkmeansclustering AT zhiweishao researchonfastmarkingmethodforindicatordiagramofpumpingwellbasedonkmeansclustering AT yancenshen researchonfastmarkingmethodforindicatordiagramofpumpingwellbasedonkmeansclustering AT yanfenghe researchonfastmarkingmethodforindicatordiagramofpumpingwellbasedonkmeansclustering |