Acoustic Emission (AE) and Electromagnetic Radiation (EMR) are playing an increasingly important role in the field of coal and rock dynamic disaster early warning due to their accurate response to the evolution process. However, blasting, drilling, and other coal mine technical activities are easily to produce interference signals, which seriously affect the credibility of early warning information. Moreover, unbalanced samples and complex characteristic characterization cannot achieve accurate identification. This paper presents a novel identification method for effective and interference signal of AE and EMR based on generative adversarial learning and image feature mining. First, Kalman filter is applied to AE and EMR monitoring signals to remove noise and retain key features. The Wasserstein Generative Adversarial Network, then, resolves the imbalance between the sample numbers of effective and various types of interference signals to ensure generalization of the identification. The effective and interference signal samples are further converted graphically by Symmetrized Dot Pattern, and intuitive different distribution characteristics are obtained. Finally, the EfficientNet model accurately identified typical effective and six interference signals collected downhole. The practical case of a coal mine in Liaoning Province shows that the proposed method is feasible and effective, and can provide a basis for reliable early warning of coal and rock dynamic disasters.

The long-term stability of coal mine roadway engineering is critical to the safe mining of coal resources and the protection of the surface environment. In this paper, the creep test of coal samples in coal roadway was carried out by multi-stage constant load method, and the test results showed that when the stress level was low, the creep curve had a attenuated stage and a steady-state stage, and the steady-state creep rate tended to increase with the increase in the stress level; When the stress level was higher than the yield stress, the creep rate curve appeared to have an acceleration stage after the steady-state stage. The instability failure mode of the coal sample was mainly shear failure with local tension failure. For this, a New Fractional-order Nonlinear Viscoelastic-plastic Rheological Model (NFNVRM) was established by introducing Abel elements and Nonlinear elements, and the constitutive equation of the model was deduced. The new model can fully reflect the stable decay stage and accelerated rheological stages of coal samples, and the parameter identification curve was consistent with the experimental results, which verifies the correctness and reasonableness of the NFNVRM. Meanwhile, based on the FLAC3D secondary development interface, the constitutive equations of the NFNVRM were written into the software to obtain new Dynamic Link Library (DLL) files. The simulation results were consistent with the experimental results when the DLL file was called. Finally, the NFNVRM.dll was applied to predict the surrounding rock deformation of an S mine. The study’s findings offer suggestions for environmental protection.