Probabilistic prediction of tunnel geology using a Hybrid Neural-HMM
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
Taking into account internal and exterior factors of rockburst, a model using BP neural network is proposed, in which the in-situ stress, the compressive strength, the tensile strength and the elastic energy index of the cavern are chosen as criteria indexes. Some representative engineering projects at home and aboard are collected as learning and training samples, so as to improve the extensive ability of neural network, and Levenberg-Marquardt algorithm is applied to achieve better performance during the training process. The instances indicate that the evaluated results agree well with the practical records, which shows the model is effective in prediction of rockburst.