A Multi-sensor Fusion Algorithm for Monitoring the Health Condition of Conveyor Belt in Process Industry

Abstract

Conveyor belts are some key equipments for transmission in the process industry. Belt wear is inevitable in the process of conveying. In order to evaluate the state of the belt, the inspection workers regularly check the belt. However, it can’t be tested comprehensively. Also, a lot of labor costs occur. In this paper, we propose a multi-sensor fusion method for the detection of conveyor belt surface damage, and builds a data acquisition system combining camera and lidar to obtain image data and point cloud data on the conveyor belt surface. On the basis of using traditional machine vision algorithms to detect surface damages, combined with the depth information obtained from the lidar points cloud, the fusion detection of the damage detection of two kinds of sensors is realized. Experiments show that the use of multi-sensor detection can effectively reduce misdetection caused by vision and improve the reliability of detection.