Robust model reconstruction for intelligent health monitoring of tunnel structures

Abstract

Advanced robotic systems will encounter a rapid breakthrough opportunity and become increasingly important, especially with the aid of the accelerated development of artificial intelligence technology. Nowadays, advanced robotic systems are widely used in various fields. However, the development of artificial intelligence-based robot systems for structural health monitoring of tunnels needs to be further investigated, especially for data modeling and intelligent processing for noises. This research focuses on integrated B-spline approximation with a nonparametric rank method and reveals its advantages of high efficiency and noise resistance for the automatic health monitoring of tunnel structures. Furthermore, the root-mean-square error and time consumption of the rank-based and Huber’s M-estimator methods are compared based on various profiles. The results imply that the rank-based method to model point cloud data has a comparative advantage in the monitoring of tunnel, as well as the large-area structures, which requires high degrees of efficiency and robustness.