Research on Rockburst Prediction Classification Based on GA-XGB Model
Rockburst is a typical engineering geological disaster under the condition of high geostress. The rockburst classification and prediction are of great significance for the prevention and control of engineering geological disasters under the high geostress environment, and can reduce or even avoid th...
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | article |
| Langue: | EN |
| Publié: |
IEEE
2021
|
| Sujets: | |
| Accès en ligne: | https://doaj.org/article/547e3c47bf4346a798d4065be2ebd7f8 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| Résumé: | Rockburst is a typical engineering geological disaster under the condition of high geostress. The rockburst classification and prediction are of great significance for the prevention and control of engineering geological disasters under the high geostress environment, and can reduce or even avoid the loss of personnel, equipment, and property. Thus, the GA-XGB model for rockburst classification prediction is proposed in this paper. Specifically, the parameter search process of extreme gradient boosting (XGB) is optimized based on the genetic algorithm (GA), and 10-fold cross-validation is performed on the Dataset collected from literature research. There are 275 sets of complete data, including 6 parameters: <inline-formula> <tex-math notation="LaTeX">$\sigma _{\theta }$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\sigma _{\mathrm {c}}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\sigma _{\mathrm {t}}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\sigma _{\theta }/\sigma _{\mathrm {c}}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\sigma _{\mathrm {c}}/\sigma _{\mathrm {t}}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\text{W}_{\mathrm {et}}$ </tex-math></inline-formula>. Afterward, the impact of different indicator parameter combinations on the performance of the proposed model is explored and compared to existing machine learning models (such as SVM and XGB). Finally, the classification evaluation indexes (precision, recall, and F1 score) are calculated and compared to those obtained by several other algorithms. The results indicate that the method proposed in this paper performs better than other machine algorithms such as XGB, SVM, DT, and Bayes. |
|---|