METHODS AND SYSTEMS FOR DATA COLLECTION, LEARNING, AND STREAMING OF MACHINE SIGNALS FOR ANALYTICS AND MAINTENANCE USING THE INDUSTRIAL INTERNET OF THINGS

Fecha de publicación: 14/05/2020
Fuente: WIPO "swarm"
An industrial machine predictive maintenance method and system may include an industrial machine data analysis facility that collects data representative of conditions of portions of industrial machines received via a data collection network. Vibration data representative of a vibration of at least a portion of an industrial machine can be received from a wearable device including at least one vibration sensor used to capture the vibration data. A frequency of the captured vibration can be determined by processing the captured vibration data and, based on the frequency, a segment of a multi-segment vibration frequency spectra that bounds the captured vibration can be determined. A severity unit for the captured vibration can be calculated based on the determined segment a signal in a predictive maintenance circuit for executing a maintenance action on at least the portion of the industrial machine based on the severity unit can be generated.