Abstract: The advanced seismic-while-excavating detection technology can achieve parallel exploration and excavation, providing the possibility of real-time and accurate geological support in the scenario of rapid and intelligent excavation of roadways. The signals generated by the excavation seismic source are complex, variable frequency, and continuous. The recognition of signal features directly affects the accuracy of data processing and imaging. However, currently, the recognition of seismic-while-excavating signal features for rock tunnel boring machine (TBM) is still unclear, and there is currently no targeted research on signal processing and imaging. In order to solve the above problems, taking the TBM advanced seismic-while-excavating detection test of the gas control roadway in Xieqiao Coal Mine as an example, the time domain, frequency domain, and frequency domain features of the cutterhead pilot signal and the rock wall received signal are analyzed. The proportion of different amplitude energy components in the rock roadway TBM seismic-while-excavating signal show a pyramid shape. But the distribution is random and the degree of asymmetry is high. The energy of the mechanical operation signal is relatively high, and the strength of the cutterhead pilot signal is about 200 times that of the signal received by the rock wall. The frequency domain frequency conversion features are obvious. The basic frequency of the mechanical operation signal is relatively low, and the frequency components of the cutterhead pilot signal are mainly concentrated in the range of 10-80 Hz and 150-200 Hz, with a main frequency of 36.99 Hz. The frequency components of the rock wall received signal are mainly concentrated in the range of 50-200 Hz, with a main frequency of 137.97 Hz. The frequency domain energy distribution of the cutterhead pilot signal is more regular than that of the rock wall received signal, and the phenomenon of multiple source excitation is obvious. The difference features between energy clusters indicate the randomness of amplitude energy and duration during multiple source excitations. The data processing and imaging experiments of TBM seismic-while-excavating signals in rock roadways are carried out using the pulse algorithm and diffraction stacking migration imaging method. The results show the following points. ① The pulse equivalent single shot record has strong consistency with the advanced detection single shot record obtained from conventional seismic-while-excavating sources, with clear and continuous in-phase axes, which can meet the needs of on-site detection analysis.② The advanced prediction results of the rock mass situation within the detection range are consistent with the actual exposure, indicating that TBM advanced seismic-while-excavating detection in rock roadways can provide effective geological support.