Early Failure Detection of Belt Conveyor Idlers by Means of Ultrasonic Sensing

Belt Conveyors are the main class of machinery that compose the logistics of a port terminal. The rolling components of the conveyor may fail mainly due to damaged idlers, which may cause a severe industrial breakdown. Nowadays, the equipment protection is done by a set of sensors that indicate an already existing abnormality or by personal inspection, applying practical experience in the search of visual, sound, or temperature signatures of imminent failure. Aiming to upgrade from the current corrective system to the predictive domain, a model for early failure detection on the conveyor's idlers is proposed. Ultrasound recordings were conducted on idlers that did not present any perceptible abnormalities, labeled as non-defective, and on idlers that displayed typical failure noise, labeled as defectives. The dataset collected was used for the training and testing of Random Forest and Multilayer Perceptron machine learning algorithms. Four types of experiments were devised to test the methodology, two of them using time-domain data, and two of them using frequency domain data, with different statistical attributes. The results achieved in various classification experiments showed that there is a distinctive pattern on the ultrasound spectrum that differs non-defective from defective idlers, as pre-evaluated by traditional methods of human inspection. In the best case, the experiment that used a moving average on the frequency domain data presented an average of 83.68% of correctly classified idlers, obtaining as best result accuracy of 89.47%.