METHOD AND APPARATUS FOR PNEUMATICALLY CONVEYING PARTICULATE MATERIAL INCLUDING A USER-VISIBLE IOT-BASED CLASSIFICATION AND PREDICTIVE MAINTENANCE SYSTEM NOTING MAINTENANCE STATE AS BEING ACCEPTABLE, CAUTIONARY, OR DANGEROUS

• US 20190154469A1
• Filed: 01/22/2019
• Published: 05/23/2019
• Est. Priority Date: 02/23/2015
• Status: Active Grant

• Current Assignee: Machinesense LLC
• Original Assignee: Machinesense LLC
• Inventors: Pal, Biplab, Purohit, Amit
• Granted Patent: US 10,598,520 B2
• Time in Patent Office: Days
• CPC Class Codes: B23Q 17/0971 by measuring mechanical vibrations of parts of the machine arrangements for measuring vibrations B23Q17/12
• CPC Class Codes: B65G 53/66 Use of indicator or control devices, e.g. for controlling gas pressure, for controlling proportions of material and gas, for indicating or preventing jamming of material controlling the flow of coal firing systems C21B5/003
• CPC Class Codes: G01D 7/005 Indication of measured value by colour change
• CPC Class Codes: G05B 19/0428 Safety, monitoring G05B19/0423 takes precedence
• CPC Class Codes: G05B 19/4184 characterised by fault tolerance, reliability of production system
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G16Y 40/40 Maintenance of things

Abstract

A method and system of a predictive maintenance IoT system comprises receiving a plurality of sensor data over a communications network and determining one or more clusters from the sensor data based on a pre-determined rule set. Further, the sensor data is classified through a machine learning engine and the sensor data is further base-lined through a combination of database architecture, data training architecture, and a base-lining algorithm. Intensity or degree of fault state is mapped to a fuel gauge to be depicted on a user interface and a predictive maintenance state is predicted through a regression model and appropriate alarm is raised for user action.

Claims

1. A method of pneumatically conveying particulate material while providing a user visible IoT-based classification and predictive maintenance reading respecting performance of the method as being acceptable, cautionary or dangerous on a numerical scale ranging from 0 to 100, comprising:

a) providing a vacuum pump comprising;

i) a motor;

ii) a blower; and

iii) a plurality sensors for measuring vibration, magnetic filed, pressure, and temperature at various positions on the vacuum pump;

b) by operation of the vacuum pump, drawing a vacuum through a conduit leading from the vacuum pump to a material receiver and on to a particulate material pickup device thereby picking up and transporting particulate material from a source thereof to the receiver;

c) providing data from the sensors to a communications network;

d) receiving in mobile middleware a plurality of sensor data from the communications network;

e) determining one or more clusters from the sensor data based on a pre-determined rule set;

f) classifying the sensor data through a machine learning engine connected to the middleware;

g) base-lining the sensor data, in a real time data processing system communicating with the machine learning engine, using a combination of database architecture, data training architecture, and a base-lining algorithm;

h) using a regression model calculating the predictive maintenance state of the vacuum pump; and

i) presenting the maintenance state of the method on a fuel gauge representation based on a predictive maintenance state calculated by the regression model.

2. The method of claim 1, wherein the machine learning engine is associated with at least one of a physics based model, a rule based model and a vector classifier model.

3. The method of claim 1, wherein the data training architecture receives as input, a baseline reading and anomalous reading for a component with a sensor attached.

4. The method of claim 1, wherein the calculated predictive maintenance state displayed on the fuel gage in a color scheme in which red indicates a worst maintenance condition, yellow indicates an intermediate condition, and green indicates a best maintenance condition.

5. The method of claim 4, further comprising setting a user defined alarm system based on a field calibration of the fuel gauge representation.

6. The method of claim 1 further comprising raising an alarm when color is at least one of yellow and red.

7. The method of claim 1, further comprising:

the mobile middleware being a mobile application, we or a desktop application, and the mobile middleware calibrates and base-lines the sensor data.

8. The method of claim 7, wherein the alarm is raised over the communications network through notification on the mobile application of via short message service, email, or a combination thereof.

9. Apparatus for pneumatically conveying particulate material including a user visible IoT-based classification and predictive maintenance system noting apparatus maintenance state as being acceptable, cautionary, or dangerous, comprising:

a) a vacuum pump comprising;

i) a motor;

ii) a blower; and

iii) a plurality of sensors mounted on the pump for measuring vibration, magnetic field, pressure, power factor, and temperature, and supplying data indicative of such measurements;

b) a communications network communicating with the sensors;

c) mobile middleware receiving a plurality of the sensor data of the communications network;

d) a real time data processing system connected to the mobile middleware and including associated distributed databases, the data processing system further comprising;

i) a clustering module for determining presence of one or more data clusters from the sensor data based on a pre-determined rule set;

ii) a computer database for storing the pre-determined rule set;

iii) a machine learning engine for classifying the sensor data according to the predetermined rule set;

iv) a base-lining architecture for base-lining the sensor data, the base-lining architecture comprising;

(1) a combination of database architecture, data training architecture, and a base-lining algorithm; and

(2) a regression module associated with a processor to predict a predictive maintenance state;

e) a receiver for storage of conveyed material received pneumatically from the pick-up device;

f) tubular segments for pneumatically connecting the receiver to the vacuum pump and for pneumatically connecting the pickup device to the receiver for pneumatic conveyance of the particulate material from the pickup device to the receiver through the tubing in response to vacuum drawn by the pump;

g) a user interface, connected to the pump, for visibly displaying the determined state of maintenance of the pneumatic conveying apparatus;

h) the real-time data processing system mapping the predicted maintenance state of the pneumatic conveying apparatus as a depiction on the user interface.

10. The apparatus of claim 9, wherein the machine learning engine at least one of a physics based model, a rule based model and a vector classifier model.

11. The of claim 9, wherein the data training architecture receives as input a baseline reading and anomalous reading from a component associated with a sensor.

12. The system of claim 10, wherein the depiction on a user interface is a fuel gauge, associated with a color scheme in which, red indicates a worst maintenance condition, yellow indicates an intermediate condition, and green indicates a best maintenance condition.

13. The apparatus of claim 9, further comprising:

raising an alarm when the depicted color is at least one of yellow and red.

14. Apparatus of claim 9, wherein the mobile middleware is at least one of a mobile application, a web application, and a desktop application;

and wherein the mobile middleware calibrates the base-lines of the sensor data.

15. Apparatus of claim 12 wherein the mobile middleware calibrates and base-lines the sensor data.

16. Apparatus of claim 12, wherein the alarm raised of the communications network is through one of notification on the mobile application, by short message service, email, or a combination thereof.