Unsupervised machine learning methods to estimate a health indicator for condition monitoring using acoustic and vibration signals : a comparison based on a toy data set from a coffee vending machine Universiteit Gent
Automating the task of assessing an assetU+2019s status based on sensor data would not only relieve trained engineers from this time intensive task, it would also allow a continuous follow-up of assets, potentially resulting in a fine-grained view on the assetU+2019s status. In this work three unsupervised machine learning approaches that define a Health Indicator (HI) based on acoustic and vibration signals were empirically assessed. Such a HI ...