Predictive maintenance

• US 10,096,004 B2
• Filed: 10/10/2014
• Issued: 10/09/2018
• Est. Priority Date: 10/10/2014
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Viswanath, Anoop, Dabholkar, Abhay, Ford, Brad, Hettinger, Mengling, Reese, Kevin, Sorrells, Carl, Tsai, Christopher, Jones, Alfonso
• Primary Examiner(s): Shaawat, Mussa A
• Application Number:
  US14/511,354
• Publication Number:
  US 20160104123A1
• Time in Patent Office: 1,460 Days
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance

Abstract

Vehicular maintenance is predicted using real time telematics data and historical maintenance data. Different statistical models are used, and an intersecting set of results is generated. Environmental weather may also be used to further refine predictions.

Claims

1. A system, comprising:

a hardware processor; and

a memory device, the memory device storing instructions, the instructions when executed causing the hardware processor to perform operations, the operations comprising;

wirelessly receiving sensor data reported via a wireless communications network by a fleet of multiple vehicles;

wirelessly receiving maintenance data reported via the wireless communications network, the maintenance data associated with the fleet of multiple vehicles;

machine generating a first prediction of maintenance from a first statistical analysis of the sensor data reported by the fleet of multiple vehicles, the first statistical analysis using a first statistical model;

machine generating a second prediction of maintenance from a second statistical analysis of the maintenance data, the second statistical analysis using a second statistical model different from the first statistical model;

machine comparing the first prediction of maintenance generated from the first statistical analysis of the sensor data to the second prediction of maintenance generated from the second statistical analysis of the maintenance data;

machine determining a match between the first prediction of maintenance generated from the first statistical analysis of the sensor data and the second prediction of maintenance generated from the second statistical analysis of the maintenance data; and

machine generating a final prediction of maintenance based on the match between the first prediction of maintenance generated from the first statistical analysis of the sensor data and the second prediction of maintenance generated from the second statistical analysis of the maintenance data.

2. The system of claim 1, wherein the operations further comprise adding weather data to the sensor data to generate the first prediction of maintenance.

3. The system of claim 1, wherein the operations further comprise adding weather data to the maintenance data to generate the second prediction of maintenance.

4. The system of claim 1, wherein the operations further comprise estimating outliers from an intersection of the first prediction of maintenance with the second prediction of maintenance.

5. The system of claim 1, wherein the operations further comprise generating a graphical user interface for displaying the final prediction of maintenance.

6. The system of claim 1, wherein the operations further comprise downloading the final prediction of maintenance to a client device.

7. The system of claim 1, wherein the operations further comprise generating a repair ticket for the final prediction of maintenance.

8. A memory device storing instructions that when executed cause a hardware processor to perform operations, the operations comprising:

wirelessly receiving sensor data reported via a wireless communications network by a fleet of multiple vehicles;

wirelessly receiving maintenance data reported via the wireless communications network, the maintenance data associated with the fleet of multiple vehicles;

generating a first prediction of maintenance from a first statistical analysis of the sensor data wirelessly reported by the fleet of multiple vehicles, the first statistical analysis using a first statistical model;

generating a second prediction of maintenance from a second statistical analysis of the maintenance data, the second statistical analysis using a second statistical model different from the first statistical model;

comparing the first prediction of maintenance generated from the first statistical analysis of the sensor data wirelessly reported by the fleet of multiple vehicles to the second prediction of maintenance generated from the second statistical analysis of the maintenance data;

determining a match between the first prediction of maintenance generated from the first statistical analysis of the sensor data and the second prediction of maintenance generated from the second statistical analysis of the maintenance data; and

generating a final prediction of maintenance based on the match between the first prediction of maintenance generated from the first statistical analysis of the sensor data and the second prediction of maintenance generated from the second statistical analysis of the maintenance data.

9. The memory device of claim 8, wherein the operations further comprise adding weather data to the sensor data to generate the first prediction of maintenance.

10. The memory device of claim 8, wherein the operations further comprise adding weather data to the maintenance data to generate the second prediction of maintenance.

11. The memory device of claim 8, wherein the operations further comprise estimating outliers from an intersection of the first prediction of maintenance with the second prediction of maintenance.

12. The memory device of claim 8, wherein the operations further comprise generating a graphical user interface for displaying the final prediction of maintenance.

13. The memory device of claim 8, wherein the operations further comprise downloading the final prediction of maintenance to a client device.