Multiscale Fractal-Dimension-Constrained Coherent Phase Processing of Seismic-While-Tunneling Signals for Fault Prediction

Seismic-while-tunneling signals acquired during coal-mine excavation are typically characterized by strong nonstationarity, intense mechanical noise, weak reflection responses, unstable inter-trace phases, and complex waveform fluctuations. These characteristics make conventional energy- or amplitude-based picking methods susceptible to false triggers and missed detections. To reveal the local complexity mutation of mine seismic signals under strong-noise backgrounds, this study proposes a multiscale fractal-dimension-constrained coherent phase processing method for signal enhancement, first-arrival picking, and fault prediction. First, the raw seismic-while-tunneling records are reorganized into shot gathers, windowed, and downsampled to preserve the effective early-arrival information. A damped multichannel singular spectrum analysis method is then used to extract coherent low-rank components and suppress incoherent random noise. Second, short-window and long-window box-counting fractal dimensions are calculated to characterize local and background waveform complexity, and a fractal-dimension mutation index is constructed to identify abrupt complexity transitions associated with effective seismic arrivals. On this basis, the fractal mutation index is incorporated into a coherent phase picking function that combines multichannel phase consistency and stacked amplitude, forming a fractal-dimension-constrained CCPP detection criterion. This criterion enhances true coherent arrivals while suppressing isolated noise spikes and unstable local amplitude disturbances. Finally, phase-weighted stacking is applied to further strengthen phase-consistent reflection responses and improve the interpretability of seismic-while-tunneling imaging profiles. Field application at the WII02040503 working face of Tunbao Coal Mine demonstrates that the proposed method can effectively improve the continuity of coherent events, stabilize automatic picking results, and enhance anomalous reflection bands under complex underground noise conditions. During the engineering trial, a total of 2558 m of ahead prospecting was completed, and 29 faults were predicted. The field-confirmation rates of the predicted faults with throws greater than 3 m, between 1 and 3 m, and less than 1 m were 100%, 87.50%, and 81.25%, respectively. Overall, 25 of the 29 predicted faults were confirmed by field exposure, corresponding to an overall field-confirmation rate of 86.21%. After velocity-synchronization time-difference correction, the average planar positioning deviation of the confirmed fault predictions decreased from 7.86 m to 5.08 m, corresponding to a 35.37% reduction in positioning error. These results indicate that the proposed fractal-dimension-constrained coherent processing framework provides an effective approach for complexity-aware signal enhancement and robust fault prediction in seismic-while-tunneling monitoring.