Predicting a time of failure of a device

Patent metadata

Field	Value
Publication number	US-9292473-B2
Application number	US-201313966887-A
Country	US
Kind code	B2
Filing date	Aug 14, 2013
Priority date	Dec 28, 2012
Publication date	Mar 22, 2016
Grant date	Mar 22, 2016

Abstract

The present disclosure relates generally to the field of predicting a time of failure of a device. In various examples, predicting a time of failure of a device may be implemented in the form of methods and/or algorithms.

First claim

What is claimed is:

1. A method implemented in connection with a device for predicting a time of failure of the device, the method comprising:
receiving by the device at least one laboratory test result, wherein the at least one laboratory test result is a test result of a laboratory stress test associated with the device;
generating by the device at least one physical measurement associated with the device, wherein the at least one physical measurement is selected from the group comprising: a temperature measurement; a current measurement; a voltage measurement; an acceleration measurement; a tension measurement; a compression measurement; a force measurement; a magnetic field measurement; and an electro-magnetic field measurement;
determining by the device as a residual a difference between the at least one generated physical measurement and at least one value from a model;
determining by the device a difference between: (a) information associated with the at least one received laboratory test result; and (b) the residual;
generating by the device a predicted time of failure of the device, wherein the generation of the predicted time of failure of the device is based at least in part upon an amplitude of the determined difference between: (a) the information associated with the at least one received laboratory test result; and (b) the residual;
outputting by the device: (a) the predicted time of failure of the device; and (b) an indication of at least one component of the device that is predicted as leading to the failure; and
providing predictive maintenance by servicing the device via at least one of: (a) repairing the at least one component of the device that is predicted as leading to the failure; and (b) replacing the at least one component of the device that is predicted as leading to the failure.

2. The method of claim 1 , wherein the at least one physical measurement is made in real-time.

3. The method of claim 1 , wherein the output is made to a display screen associated with the device.

4. The method of claim 1 , further comprising:
receiving by the device a plurality of laboratory test results, wherein each of the plurality of laboratory test results is a test result of a laboratory stress test associated with the device;
generating by the device a plurality of physical measurements associated with the device;
determining by the device as a residual a difference between each of the plurality of generated physical measurements and at least one respective value from the model; and
determining by the device a plurality of differences between: (a) information associated with each of the plurality of received laboratory test results; and (b) each respective residual;
wherein the generation of the predicted time of failure of the device is based at least in part upon an amplitude of each determined difference between: (a) information associated with each of the plurality of received laboratory test results; and (b) each respective residual.

5. The method of claim 4 , wherein:
each of the plurality of laboratory test results is received at different times; and
each of the plurality of physical measurements is generated at different times.

6. The method of claim 1 , wherein the device is selected from the group comprising: a smart phone; a tablet; a laptop computer; a desktop computer; a refrigerator; a freezer; a stove; a range; a hot water heater; a boiler; a furnace; and a vehicle mounted device.

7. The method of claim 1 , wherein:
the outputting of the indication of at least one component of the device that is predicted as leading to the failure comprises outputting an indication of a plurality of components of the device that are predicted as leading to the failure; and
the servicing the device comprises at least one of: (a) repairing the plurality of components of the device that are predicted as leading to the failure; and (b) replacing the plurality of components of the device that are predicted as leading to the failure.

8. The method of claim 1 , further comprising outputting by the device at least one reason for the predicted failure.

9. The method of claim 1 , further comprising outputting by the device, after the servicing, an indication of an updated predicted time of failure of the device.

10. The method of claim 1 , wherein:
(i) the receiving by the device at least one laboratory test result, (ii) the generating by the device the at least one physical measurement associated with the device, (iii) the determining by the device as the residual the difference between the at least one generated physical measurement and the at least one value from a model, and (iv) the determining by the device the difference between: (a) the information associated with the at least one received laboratory test result; and (b) the residual are performed for each of a plurality of subsystems of the device; and
the generating by the device the predicted time of failure of the device is based upon an aggregation of results of steps (i)-(iv) for each of the plurality of subsystems.

11. The method of claim 10 , wherein the predicted time of failure of the device is an earliest predicted time of failure of any of the plurality of subsystems.

12. The method of claim 10 , wherein the aggregation is performed by a centralized system of the device.

Assignees

• IBM

Inventors

• Ba Amadou

Classifications

• G06F11/008 Primary

  Reliability or availability analysis · CPC title

• G06F11/3495

  for systems · CPC title

• G06F11/3058

  Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations (thermal management in cooling arrangements of a computing system G06F1/206) · CPC title

• G06F11/22

  Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing · CPC title

• G06F17/00 Primary

  Digital computing or data processing equipment or methods, specially adapted for specific functions (information retrieval, database structures or file system structures therefor G06F16/00) · CPC title