IP3 2023 – Artificial Intelligence & Machine Learning 4 (LOT 14834)

This lot is generally related to a technique to create a detection model for use in machine condition monitoring by ranking functionality and determine a cut-off between active and non-active fault states. Disclosed is a technique for creating a model by receiving a set of labels, ranking the set of labels, and partitioning the ranked set of labels into a first subset of labels and a second subset of labels. Also disclosed are techniques to insert a zero-point label between the first subset of labels and the second subset of labels. The technology may be implemented in machine condition monitoring systems, machine fault diagnosis systems, etc.