A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system
Abstract The diagnosis of resistance variable multifault location (RVMFL) in a mine ventilation system is an essential function of the mine intelligent ventilation system, which is of great significance to mine-safe production. In this paper, a supervised machine learning model based on a decision t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-32530-7 |
| _version_ | 1797853886446305280 |
|---|---|
| author | Dong Wang Jian Liu Deng Lijun Wang Honglin |
| author_facet | Dong Wang Jian Liu Deng Lijun Wang Honglin |
| author_sort | Dong Wang |
| collection | DOAJ |
| description | Abstract The diagnosis of resistance variable multifault location (RVMFL) in a mine ventilation system is an essential function of the mine intelligent ventilation system, which is of great significance to mine-safe production. In this paper, a supervised machine learning model based on a decision tree (DT), multilayer perceptron (MLP), and ranking support vector machine (Rank-SVM) is proposed for RVMFL diagnosis in a mine ventilation system. The feasibility of the method and the predictive performance and generalization ability of the model were verified using a tenfold cross-validation of a multifault sample set of a 10-branch T-shaped angle-joint ventilation network and a 54-branch experimental ventilation network. The reliability of the model was further verified by diagnosing the RVMFL of the experimental ventilation system. The results show that the three models, DT, MLP, and Rank-SVM, can be used for the diagnosis of RVMFL in mine ventilation systems, and the prediction performance and generalization ability of the MLP and DT models perform better than the Rank-SVM model. In the diagnosis of multifault locations of the experimental ventilation system, the diagnostic accuracy of the MLP model reached 100% and that of the DT model was 44.44%. The results confirm the MLP model outperforms the three models and can meet engineering needs. |
| first_indexed | 2024-04-09T19:58:03Z |
| format | Article |
| id | doaj.art-e94cc5cd13d447a8aa90bec3ac686753 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T19:58:03Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e94cc5cd13d447a8aa90bec3ac6867532023-04-03T05:23:33ZengNature PortfolioScientific Reports2045-23222023-03-0113111210.1038/s41598-023-32530-7A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation systemDong Wang0Jian Liu1Deng Lijun2Wang Honglin3College of Safety Science and Engineering, Liaoning Technical UniversityCollege of Safety Science and Engineering, Liaoning Technical UniversityCollege of Safety Science and Engineering, Liaoning Technical UniversityCollege of Safety Science and Engineering, Liaoning Technical UniversityAbstract The diagnosis of resistance variable multifault location (RVMFL) in a mine ventilation system is an essential function of the mine intelligent ventilation system, which is of great significance to mine-safe production. In this paper, a supervised machine learning model based on a decision tree (DT), multilayer perceptron (MLP), and ranking support vector machine (Rank-SVM) is proposed for RVMFL diagnosis in a mine ventilation system. The feasibility of the method and the predictive performance and generalization ability of the model were verified using a tenfold cross-validation of a multifault sample set of a 10-branch T-shaped angle-joint ventilation network and a 54-branch experimental ventilation network. The reliability of the model was further verified by diagnosing the RVMFL of the experimental ventilation system. The results show that the three models, DT, MLP, and Rank-SVM, can be used for the diagnosis of RVMFL in mine ventilation systems, and the prediction performance and generalization ability of the MLP and DT models perform better than the Rank-SVM model. In the diagnosis of multifault locations of the experimental ventilation system, the diagnostic accuracy of the MLP model reached 100% and that of the DT model was 44.44%. The results confirm the MLP model outperforms the three models and can meet engineering needs.https://doi.org/10.1038/s41598-023-32530-7 |
| spellingShingle | Dong Wang Jian Liu Deng Lijun Wang Honglin A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system Scientific Reports |
| title | A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| title_full | A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| title_fullStr | A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| title_full_unstemmed | A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| title_short | A supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| title_sort | supervised diagnostic experiment of resistance variable multifault locations in a mine ventilation system |
| url | https://doi.org/10.1038/s41598-023-32530-7 |
| work_keys_str_mv | AT dongwang asuperviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT jianliu asuperviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT denglijun asuperviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT wanghonglin asuperviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT dongwang superviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT jianliu superviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT denglijun superviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem AT wanghonglin superviseddiagnosticexperimentofresistancevariablemultifaultlocationsinamineventilationsystem |