Predictive maintenance is a prominent strategy to minimize downtime, associated costs and failure risks. In this paper, a study review of some supervised learning algorithms is presented. Multi-layer perceptron (MLP), Support vector machine (SVM) and decision tree (DT) are compared in terms of prediction accuracy. The data considered for simulation is often used in literature; it is applied to aircraft engine sensors measurements to predict in-service engine failure. The performance of the algorithms, cited above, has been compared in terms of classification accuracy, precision, recall and F-score. In this study, the support vector machine provides better results than other techniques for maintenance prediction.
Maintenance Prediction by Machine learning: Study Review of some Supervised Learning Algorithms
2 Views
1 Downloads