Automated rock mass condition assessment during TBM tunnel excavation using deep learning

Rock mass condition assessment during tunnel excavation is a critical step for the intelligent control of tunnel boring machine (TBM). To address this and achieve automatic detection, a visual assessment system is installed to the TBM and a lager in-situ rock mass image dataset is collected from the water conveyance channel project. The rock mass condition assessment task is transformed into a fine-grain classification task. To fulfill the task, a self-convolution based attention fusion network (SAFN) is designed in this paper. The core of our method is the discovery and fusion of the object attention map within a deep neural network. The network consists of two novel modules, the self-convolution based attention extractor (SAE) module and the self-convolution based attention pooling algorithm (SAP) module. The former is designed to detect the intact rock regions generating the attention map, and the latter is designed to improve the performance of classifier by fusing the attention map that focuses on the intact rock regions. The results of SAFN are evaluated from aspects of interpretability, ablation, accuracy and cross-validation, and it outperforms state-of-the-art models in the rock mass assessment dataset. Furthermore, the dynamic filed test show that our assessment system based on the SAFN model is accurate and efficient for automated classification of rock mass.

Automated summary

In this study, a self-convolution based attention fusion network (SAFN) is proposed for rock mass condition assessment. The network is designed to discover and fuse object attention maps within a deep neural network, enabling fine-grain classification of rock mass. Experimental results show that the proposed method outperforms state-of-the-art models in rock mass assessment and the field test demonstrates its accuracy and efficiency in automated classification of rock mass.