Method for the Relative Pose Reconstruction of Hydraulic Supports Driven by Digital Twins

The undulating coal seam floor in a mine leads to the complicated posture of the hydraulic supports. The existing methods for monitoring the pose of hydraulic supports have a poor monitoring effect, and are especially characterized by a lack of support position information. Therefore, this article proposes a relative pose reconstruction method for hydraulic supports driven by digital twins. First, the pose plane and relative pose matrix of the hydraulic support are defined to describe the pose state of the support by analyzing the pose deviation between adjacent supports. Then, a digital twin system is built for a hydraulic support model, and a pose deduction method based on ray detection is proposed. The accurate position and attitude of the hydraulic support are deduced in the virtual space driven by actual laser sensor information, and 3-D pose reconstruction is realized. Finally, a relative pose reconstruction experiment of the hydraulic support model is designed and conducted. The results show that the relative pose data obtained by the virtual reconstruction method are very close to the experimental measurements, and the highest reconstruction accuracy is found to be 97.44%. The feasibility of the laser sensor layout scheme and the virtual reconstruction method of the pose of the hydraulic support is proven. This method provides a new way to monitor the pose of hydraulic supports, and can provide a reference for the support operation of hydraulic supports in the real fully mechanized mining process.