Condition monitoring of Self aligning carrying idler (SAI) in belt-conveyor system using statistical features and decision tree algorithm

摘要

Self aligning carrying idler (SAI) is a key component of belt-conveyor has two main functions: power transmission, controlling the belt sway and change the direction of conveyor belt. As the SAI is found to be critical in heavy duty conveyor systems, it becomes an essential activity to monitor its smooth functioning. To ensure this, condition monitoring of SAI needs to be carried out which basically forms a classification problem. Self aligning carrying idler consists of the following components such as bearing, shaft, labyrinth seal and outer roller. The SAI was analyzed with the following cases such as SAI running at good condition (Good), SAI with bearing fault (BF), SAI with shaft fault (SF), SAI with labyrinth fault (LF) and SAI with outer roller fault (RF). From the experimental setup, the vibration signals were acquired for different conditions of SAI. Some useful features were extracted using statistical measures. The features were classified by decision tree algorithms. The classification results are presented in the conclusion part. The effort is to apply the statistical features and decision tree classifier to SAI and examine whether would it be made online.