Abstract: In intelligent shield tunneling, the accuracy of dump volume measurements is compromised by distortions in the raw point cloud data of the dump carriages. To address this issue, a model that utilizes a deep convolutional selfcoding network for selfadaptive distortionremoval in dump carriages is developed. This model combines point cloud processing with deeplearning techniques. Initially, surround box filtering and antidistanceweighted interpolation are applied for the data refinement. Subsequently, the actual size of the slag soil carriage is utilized to establish the ideal output of the network, transforming the point cloud into pseudosymbols using grayscale values to create a network dataset. Furthermore, the dump carriage selfcoding network based on a traditional convolutional selfcoding framework is constructed. This involves an integrated network design with stacked convolutional layers and autoencoders to enhance the network depth to achieve superior feature representation. Finally, the method is tested using shield tunneling data. The experimental results indicate that the proposed method significantly outperforms traditional selfcoding networks and geometric constraint correction methods in terms of time efficiency. With a peak signaltonoise ratio of 29.73 and a structural similarity index of 0.86, the proposed approach demonstrates its superiority and validity. This advancement not only enhances the utility of dump carriage point cloud data, but also lays a theoretical foundation for applying point cloud distortionremoval technology in 3D reconstruction and engineering projects.

Key words: shield method, dump carriage, muck volume measurement, point cloud distortion correction, deep learning, convolutional autoencoder