Prediction of Remaining Useful Lifetime (RUL) of turbofan engine using machine learning

Maintenance of equipment is a critical activity for any business involving machines. Predictive maintenance is the method of scheduling maintenance based on the prediction about the failure time of any equipment. The prediction can be done by analyzing the data measurements from the equipment. Machine learning is a technology by which the outcomes can be predicted based on a model prepared by training it on past input data and its output behavior. The model developed can be used to predict machine failure before it actually happens. There are different approaches available for developing a machine learning model. In this paper, a comparative study of existing set of machine learning algorithms to predict the Remaining Useful Lifetime of aircraft's turbo fan engine is done. The machine learning models were constructed based on the datasets from turbo fan engine data from the Prognostics Data Repository of NASA. Using a training set, a model was constructed and was verified with a test data set. The results obtained were compared with the actual results to calculate the accuracy and the algorithm that results in maximum accuracy is identified. We have selected ten machine learning algorithms for comparing the prediction accuracy. The different algorithms were compared to obtain the prediction model having the closest prediction of remaining useful lifecycle in terms of number of life cycles.