Abstract
To address the current challenges of low single-sensor recognition accuracy for coal and rock cutting states, redundant channel feature responses, and poor performance in traditional neural network models, this paper proposes a new multi-sensor coal and rock cutting state recognition model based on a graph neural network (GNN). This model, consisting of a feature encoder, an information exchange module, and a feature decoder, enhances the communication of feature responses between filters within the same layer, thereby improving feature capture and reducing channel redundancy. Comparative, ablation, and noise-resistance experiments on multi-sensor datasets validate the effectiveness, versatility, and robustness of the proposed model. Experimental results show that compared to the baseline models, CNN3, ResNet, and DenseNet achieve improvements of 2.47%, 2.78%, and 1.50%, respectively. With the addition of the ACI block, the ResNet model achieves the best noise-resistance performance, achieving an accuracy of 93.27% even in 6 dB noise, demonstrating excellent robustness. Embedded deployment experiments further confirmed that the proposed model maintains an inference time of less than 216.1 ms/window on the NVIDIA Jetson Nano, meeting the real-time requirements of actual industrial scenarios and demonstrating its broad application prospects in resource-constrained underground working environments.