Tunnel boring machine (TBM) is frequently used in tunnel construction due to its advantages in safety, high efficiency, environmental friendliness. However, the tunnelling efficiency of a TBM heavily depends on the rock–machine interaction conditions. To realize the real-time perception of rock–machine interaction information during the TBM tunnelling, an automatic acquisition and analysis system for rock muck is developed. Firstly, a framework for using the system to perceive the rock mass and TBM conditions was constructed. Then the method to quantitatively evaluate the geometric properties of rock muck is elaborated. Finally, the system was applied to a TBM-excavated tunnel to verify the functions of rock muck in the real-time perception of rock–machine interaction information. The results show that the geometric properties of rock muck can indicate both the rock mass conditions and the TBM performance. In rock mass condition perception: Rock blocks trend to be large in size and elongated in shape as the uniaxial compressive strength (UCS) of the surrounding rock decrease. The blocks produced from a relatively intact rock mass trend to be small in size and round in shape. Larger or smaller blocks with flat planes are frequently produced when TBM drives in the jointed rock masses. In TBM performance perception: The TBM utilization can be estimated through the ratio of the number of images with muck to the total number of captured images. A high value of the field penetration index (FPI) corresponds to blocks with large sizes and elongated shapes (or small sizes and round shapes). Elongated blocks are produced when TBM drives at a low FPI. These results are significant for the safe and efficient TBM tunnelling.

隧道掘进机(TBM)以其安全、高效、环保等优点在隧道施工中得到广泛应用。然而，TBM 的掘进效率在很大程度上取决于岩机相互作用条件。为实现TBM掘进过程中岩机相互作用信息的实时感知，开发了岩渣自动采集分析系统。首先，构建了使用该系统感知岩体和TBM 条件的框架。然后阐述了定量评价岩泥几何特性的方法。最后，将该系统应用于TBM开挖隧道，验证了岩渣在岩机相互作用信息实时感知中的功能。结果表明，岩泥的几何特性既可以指示岩体状况，也可以指示盾构机的性能。在岩体状态感知中：随着围岩单轴抗压强度（UCS）的降低，岩块趋向于变大变长。由相对完整的岩体生产的块体趋向于尺寸较小且形状呈圆形。当 TBM 在节理岩体中掘进时，经常会产生较大或较小的平面块。在TBM性能感知中：TBM利用率可以通过带泥土的图像数量与拍摄图像总数的比率来估计。场穿透指数 (FPI) 的高值对应于具有大尺寸和细长形状（或小尺寸和圆形）的块。当 TBM 以低 FPI 行驶时，会产生伸长的块体。这些成果对于TBM隧道掘进的安全高效具有重要意义。