Predictive Maintenance Algorithm Based on Machine Learning for Industrial Asset

This article proposes a predictive maintenance algorithm based on machine learning to predict the remaining useful life of industrial assets. The synthetic dataset N-CMAPSS was used, which contains a performance degradation dataset until the presence of failure of an aircraft fleet under real flight conditions is detected. The principal element of maintenance focuses on the predictability of the remaining useful life; predictive models need performance information of an asset from the beginning to failure. [1]. The approach considers the data analysis to understand the data behavior. Monotonicity and principal component analysis are applied in the variable selection. Furthermore, convolutional neural networks are integrated to predict the remaining useful life, resulting in a 10.91 mean of RSME. The “DS01” dataset was used for training; six engines were used for the training dataset and the remaining four for the test dataset.