Designing a Multivariate Belt Conveyor Idler Stall Detection and Identification System with Scalability Analysis

Abstract

Belt conveyor idlers are freely rotating idlers supporting the belt of a conveyor, and can induce severe frictional damage to the belt as they fail. Therefore, fast and accurate detection of idler faults is crucial for the effective maintenance of belt conveyor systems. In this article, we implement and evaluate the performance of an idler stall detection system based on a multivariate deep learning model using accelerometers and microphone sensor data. Emphasis is place on the scalability of the system, as large belt conveyor installations can span multiple kilometers, potentially requiring hundreds or even thousands of sensor units to monitor. The accuracy of the proposed system are analyzed and reported, along with its network bandwidth and energy requirements. The results suggest that while implementing accurate large-scale idler stall detection is feasible, careful consideration must be paid to observing the available network bandwidth and energy budget in order to avoid prolonged downtimes.