A line scanning monitoring method for conveyor belt deviation using point cloud

Abstract A precise conveyor belt deviation monitoring method using line array point cloud data is proposed and demonstrated, which can ensure the healthy running of the conveyor system. The point cloud data characterizing the surface of the conveyor belt is collected in a line scanning way. Then, using a unique soft extraction method that weighted fusing three key features (cross-sectional variation, belt’s horizontal width, and previous frame) to process this data, the edge information of the conveyor belt can be accurately and robustly identified in real-time. Furthermore, the point cloud processing mode enables a belt-segmented deviation analysis method based on a standard sequence query. This can accurately determine the offset value and deviation trend of the conveyor belt, thereby achieving early warning of deviation faults. Experimental results show that the belt edge identification precision can reach 0.3 mm, and an early warning can be provided at least 57 m before the occurrence of a belt deviation fault. This belt deviation monitoring method can be widely applied in various working environments, especially in harsh conditions like mines and ports. It also has potential applications in automated production lines within Industry 4.0.