To achieve automatic disc cutter replacement of shield machines, measuring the accurate pose of the disc cutter holder by machine vision is crucial. However, under polluted and restricted illumination conditions, achieving pose estimation by vision is a great challenge. This paper proposes a line-features-based pose estimation method for the disc cutter holder of the shield machine by using a monocular camera. For the blurring effect of rounded corners on the image edge, a rounded edge model is established to obtain edge points that better match the 3D model of the workpiece. To obtain the edge search box corresponding to each edge, a contour separation method based on an adaptive threshold region growing method is proposed. By preprocesses on the edge points of each edge, the efficiency and the accuracy of RANSAC linear fitting are improved. The experimental result shows that the proposed pose estimation method is highly reliable and can meet the measurement accuracy requirements in practical engineering applications.

In addressing the challenge of measuring the relative pose between adjacent shields in multi-shield tunnel boring machine (TBM), a multi-sensor integrated measurement method combined with artificial neural networks (ANNs) is proposed. The adjacent shields, along with the articulation cylinders, collectively form a parallel mechanism. While solving for the relative pose between the shields, the parallel arrangement of the articulation cylinders results in insufficient constraints provided by the lengths of the cylinders. After analyzing the sensitivities of changes in the articulation cylinder strokes and relative pose parameters, additional sensors, including a photosensitive target, a collimated laser, and two inclinometers are added. These are integrated with the articulation cylinder displacement sensors to form the sensing system. An ANN model is established to calculate the relative pose between adjacent shields based on data from these sensors. The required dataset for training the ANN is obtained through the kinematic inverse solution of the parallel mechanism. The proposed method was validated on emulation test platform for pose measurement. Compared to the existing methods, it achieved higher accuracy and stronger environmental adaptability to dust and fog interference. The proposed method was also applied to a 6m-class double-shield TBM, it achieved an accuracy of 4 mm for relative positions and 1 mrad for relative attitudes, meeting the guidance requirements for multi-shield TBM.