Full
Outline
In response to the problems of imbalanced sample data and low prediction accuracy in the construction of rock burst intensity grade prediction models, a rock burst intensity grade prediction model (BO-CNN-LSTM-Multi-head Attention) based on convolutional neural networks (CNN) and long short-term memory networks (LSTM) was proposed by integrating Bayesian parameter optimization algorithm (BO) and Multi-head attention mechanism (Multi-head Attention) under the rock burst sample data balancing strategy. 224 sets of rock burst cases were collected from both domestic and international sources, and Box-Cox transformation and support vector machine synthesis for few class oversampling technique (SVM SMOTE) were used to normalize and balance the rock burst sample data. The processed dataset was input into the CNN-LSTM prediction model for training and prediction, and the model was gradually optimized by Bayesian parameter optimization algorithm and multi-head attention mechanism. The prediction results indicate that Box-Cox transformation and SVM SMOTE sampling can effectively reduce the impact of outliers and data imbalance on the model, and enhance the separability of the dataset. The accuracy of the BO-CNN-LSTM-Multi-head Attention rock burst intensity grade prediction model is 95%. This model can effectively improve the prediction accuracy of rock burst intensity in the case of imbalanced sample data, and has a high feasibility and practicality.
76
39
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
