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

Abstract

An industrial machine predictive maintenance system may collect data indicative of operating characteristics of an industrial machine. The system can include a computerized maintenance management system (CMMS) that produces orders and/or requests for service and parts responsive to industrial machine service recommendations, including a mobile data collector that indicates the industrial machine service recommendation or the produced orders or requests for service and parts to a worker who uses the mobile data collector. A self-organizing data collector can cause a new record to be stored in a ledger, the new record indicating at least one of the industrial machine service recommendation or the produced orders or requests for service and parts. The ledger can use a blockchain structure to track records of transactions for each of the orders and requests for service and parts, wherein each record is stored as a block in the blockchain structure.

Claims

1. A system comprising: a computerized maintenance management system (CMMS) that produces at least one of orders or requests for service and parts responsive to receiving an industrial machine service recommendation corresponding to an industrial machine and that generates a signal indicative of the produced at least one of the orders or requests for service and parts; a mobile data collector that receives the signal and indicates the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts to a worker who uses the mobile data collector; and a self-organizing data collector that causes a new record to be stored in a ledger, the new record indicating at least one of the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts, wherein the ledger uses a blockchain structure to track records of transactions for each of the at least one of the orders and the requests for service and parts, wherein each record is stored as a block in the blockchain structure.

2. The system of claim 1, wherein the mobile data collector is a wearable device, wherein the wearable device indicates the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts to the worker by outputting data indicative of the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts to a display of the wearable device.

3. The system of claim 1, wherein the mobile data collector is a handheld device, wherein the handheld device indicates the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts to the worker by outputting data indicative of the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts to a display of the handheld device.

4. The system of claim 1, further comprising: a self-organizing data collector that causes a new record to be stored in the ledger, the new record indicating at least one of the industrial machine service recommendation or the produced at least one of the orders or requests for service and parts.

5. The system of claim 1, wherein the CMMS generates subsequent blocks of the ledger by combining data from at least one of shipment readiness, installation, operational sensor data, service events, parts orders, service orders, or diagnostic activity with a hash of a most recently generated block in the ledger.

6. The system of claim 1, further comprising: an industrial machine predictive maintenance facility that produces the industrial machine service recommendation based on industrial machine health monitoring data by applying machine fault detection and classification algorithms thereto.

7. The system of claim 6, further comprising: an industrial machine data analysis facility that generates streams of the industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of the industrial machine received via a data collection network.

8. A method comprising: detecting an operating characteristic of an industrial machine using one or more sensors of a mobile data collector, the operating characteristic of the industrial machine relating to vibrations detected for at least a portion of the industrial machine; determining a severity of the operating characteristic, the severity representing an impact of the operating characteristic on the industrial machine, based on a segment of a multi-segment vibration frequency spectra that bounds the vibrations, wherein the severity corresponds to a severity unit, wherein the segment of a multi-segment vibration frequency spectra that bounds the vibrations is determined by mapping the vibrations to one of a number of severity units based on the determined segment, wherein each of the severity units corresponds to a different range of the multi-segment vibration frequency spectra; predicting a maintenance action to perform against the industrial machine based on the severity of the operating characteristic; and storing a transaction record of the predicted maintenance action within a ledger of service activity associated with the industrial machine, wherein the ledger uses a blockchain structure to track transaction records for predicted maintenance actions for the industrial machine, wherein each of the transaction records is stored as a block in the blockchain structure.

9. The method of claim 8, wherein the mobile data collector is a mobile robot.

10. The method of claim 8, wherein the mobile data collector is a mobile vehicle.

11. The method of claim 8, wherein the mobile data collector is a handheld device.

12. The method of claim 8, wherein the mobile data collector is a wearable device.

13. The method of claim 8, wherein determining the severity of the operating characteristic comprises: mapping the vibrations to a first severity unit when the frequency of the vibrations corresponds to a below a low-end knee threshold-range of the multi-segment vibration frequency spectra; mapping the vibrations to a second severity unit when the frequency of the vibrations corresponds to a mid-range of the multi-segment vibration frequency spectra; and mapping the vibrations to a third severity unit when the frequency of the vibrations corresponds to an above a high-end knee threshold-range of the multi-segment vibration frequency spectra.