An attention module integrated hybrid model for recognizing microseismic signals induced by high-pressure grouting in deep rock layers

Microseismic (MS) monitoring is an effective technique to detect mining-induced rock fractures. However, recognizing grouting-induced signals is challenging due to complex geological conditions in deep rock plates. Therefore, a hybrid model (WM-ResNet50) integrating data enhancement, a deep convolutional neural network (CNN), and convolutional block attention modules (CBAM) was proposed. Firstly, an MS system was established at the Xieqiao coal mine in Anhui Province, China. MS waveforms and injection parameters were acquired during grouting. Secondly, signals were categorized based on time–frequency characteristics to build a dataset, which was divided into training, validation, and test sets at a ratio of 4:1:1. Subsequently, the performance of WM-ResNet50 was evaluated based on indices such as individual precision, total accuracy, recall, and loss function. The results indicated that WM-ResNet50 achieved an average recognition accuracy of 94.38%, surpassing that of a simple CNN (90.04%), ResNet18 (91.72%), and ResNet50 (92.48%). Finally, WM-ResNet50 was applied to monitor the whole process at laboratory tests and field cases. Both results affirmed the feasibility and effectiveness of MS inversion in predicting actual slurry diffusion ranges within deep rock layers. By comparison, it was revealed that the MS sources classified by WM-ResNet50 matched grouting records well. A solution to address insufficient diffusion under long-borehole grouting has been proposed. WM-ResNet50′s accuracy was validated through in-situ coring and XRD analysis for cement-based hydration products. This study provides a beneficial reference for similar rock signal processing and in-field grouting practices.