HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES

The main aim of predictive maintenance is to minimize downtime, failure risks and costs in manufacturing systems. Over the past few years, machine learning methods gained ground with diverse successful applications area maintenance. This study shows that performing preprocessing techniques such as oversampling features selection for prediction, promising. For instance, handle imbalanced data, SMOTE-Tomek method used. selection, three different can be applied: Recursive Feature Elimination, Random Forest Variance Threshold. data considered this paper simulation used literature; it applied aircraft engine sensors measurements predict engines failure, while predicting algorithm a Support Vector Machine. results show classification accuracy significantly boosted by using techniques.