System and method for predictive maintenance

• US 10,447,552 B2
• Filed: 02/23/2017
• Issued: 10/15/2019
• Est. Priority Date: 02/23/2017
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Tec Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Channa, Jonathan
• Primary Examiner(s): Baturay, Alicia
• Application Number:
  US15/440,241
• Publication Number:
  US 20180241637A1
• Time in Patent Office: 964 Days
• Field of Search: 709217
• CPC Class Codes: H04L 41/0213 Standardised network management protocols, e.g. simple network management protocol [SNMP]
• CPC Class Codes: H04L 41/046 comprising network management agents or mobile agents therefor
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/149 for prediction of maintenance
• CPC Class Codes: H04N 1/00217 only involving computer data transmission protocols, e.g. SMTP, WAP or HTTP communication protocol aspects and techniques in packet data networks H04L69/00; network-specific arrangements or communication protocols supporting networked applications H04L67/00
• CPC Class Codes: H04N 1/00323 with a measuring, monitoring or signaling apparatus, e.g. for transmitting measured information to a central location
• CPC Class Codes: H04N 1/00344 with a management, maintenance, service or repair apparatus monitoring H04N1/00002
• CPC Class Codes: H04N 1/32122 in a separate device, e.g. in a memory or on a display separate from image data
• CPC Class Codes: H04N 1/32523 a plurality of output devices
• CPC Class Codes: H04N 2201/0094 Multifunctional device, i.e. a device capable of all of reading, reproducing, copying, facsimile transception, file transception
• CPC Class Codes: H04N 2201/3202 of communication or activity log or report

Abstract

A system and method for predictive maintenance of multifunction peripherals includes a data collection agent configured to receive and store simple network management protocol (SNMP) data including metered data from one or more multifunction peripherals, and a service prediction system configured to selectively perform linear regression analysis on one or more of the metered data to predict one or more service events for at least one multifunction peripheral based on the linear regression analysis. Notifications for each predicted service event are sent to service technicians associated with the associated multifunction peripheral. Service technicians can preemptively perform service and maintenance functions on the multifunctional peripherals before error or faults occur on the multifunction peripherals.

Claims

1. A system comprising:

a data collection agent including a processor, a memory, and a network interface, configured to

receive simple network management protocol (SNMP) data including metered data and device fault data from a document processing device over the network interface,

store the received SNMP data; and

a service prediction system configured to access stored SNMP data,

perform linear regression analysis on metered data and device fault data of the SNMP data,

determine at least one service event out of a plurality of service events for the document processing device based on the linear regression analysis,

determine at least one component out of a plurality of components corresponding to the at least one service event, and

predict a time to servicing a determined component for at the least one determined service event.

2. The system of claim 1, wherein the service prediction system is further configured to

store a predicted service event for the document processing device, and

send a notification about the predicted service event to a user associated with the document processing device.

3. The system of claim 2, wherein the user is a service technician and wherein the service prediction system is further configured to

receive a response from the service technician in response to the notification.

4. The system of claim 3, wherein the service prediction system selects a user to which to send the notification based upon the type of predicted service event, and wherein the user is selected from the group consisting of an information technology user local to the document processing device, and a remote service technician.

5. The system of claim 2, wherein the service prediction system is further configured to

analyze the metered data, and

perform linear regression analysis on at least one metered data only when there is sufficient metered data to perform the linear regression analysis.

6. The system of claim 2, wherein the notification includes the predicted service event and a predicted time of the predicted service event.

7. The system of claim 1, wherein each predicted service event is selected from the group consisting of a scheduled maintenance of a component of the document processing device, a request to preemptively replace a component of the document processing device prior to failure of the component, and an inspection request for a component of the document processing device.

8. The system of claim 1, wherein the data collection agent and the service prediction system are processes executing on a common platform, and wherein the platform is selected from the group consisting of a multifunction peripheral device, a network server, one or more of a plurality of network servers, and a third party cloud service platform.

9. The system of claim 1, wherein the metered data is selected from the group consisting of a count of printed pages, a count of printed color pages, a toner level, and a paper cartridge level.

10. A method comprising:

receiving device data including metered data and device fault data from a document processing device;

storing the received device data;

analyzing metered data and device fault data of the device data;

performing a linear regression analysis on the device data;

determining at least one service event out of a plurality of service events for the document processing device based on the analyzing of the device data;

determining at least one component out of a plurality of components corresponding to the at least one service event; and

predicting a time to servicing a determined component for the at least one service event.

11. The method of claim 10, further comprising:

storing the at least one predicted service event for the document processing device; and

sending a notification about each stored predicted service event to a user associated with the document processing device.

12. The method of claim 11, further comprising:

receiving a response from the user, the user being a service technician, in response to the notification.

13. The method of claim 11, wherein the user to which the notification is sent is selected based upon the type of predicted service event, and wherein the user is selected from the group consisting of an information technology user local to the document processing device, and a remote service technician.

14. The method of claim 11, wherein the notification includes the predicted service event and a predicted time of the predicted service event.

15. The method of claim 10, wherein the metered data is selected from the group consisting of a count of printed pages, a count of printed color pages, a toner level, and a paper cartridge level.

16. A document processing device, comprising:

a device controller including a processor and memory; and

a network interface,

wherein the processor is configured to

receive device data including metered data and device fault data from a second document processing device via the network interface,

save metered data and device fault data to a database,

perform linear regression analysis on stored metered data and device fault data,

determine at least one service event out of a plurality of service events for the second document processing device based on the linear regression analysis,

determine at least one component out of a plurality of components corresponding to the at least one service event, and

predict a time to servicing a determined component for the at least one determined service event.

17. The document processing device of claim 16, wherein linear regression analysis is performed on at least one metered data only when there is sufficient metered data to perform the linear regression analysis.

18. The document processing device of claim 16, wherein the processor is further configured to

store a predicted service event for the second document processing device,

send a notification about the predicted service event to a user associated with the second document processing device, and

receive a response from the service technician in response to the notification,

wherein the user is selected based upon the type of predicted service event.

19. The document processing device of claim 16, wherein the metered data is selected from the group consisting of a printed pages, printed color pages, toner level, and paper cartridge level, and wherein each predicted service event is selected from the group consisting of a low toner event, a low paper event, a scheduled maintenance of a component of the second document processing device, a request to preemptively replace a component of the second document processing device prior to failure of the component, and an inspection request for a component of the second document processing device.