Add to Favourites
To login click here
This research studied how a one-class SVM can be optimized for machinery diagnostics and prognostics in the Internet of Things (IoT) era. It focused on how to avoid machinery failures and false alarms, as well as how to identify the location of faults and pre-process condition monitoring data. A variational Bayesian for Gaussian mixture algorithm and a Random Forest were tested for feature selection and creating indifference to load. The goal is to combine and merge these techniques to improve machinery diagnostic tools and prepare for the coming era of digitalization.