Error pattern identification in an installed base of systems

• US 8,595,553 B2
• Filed: 06/03/2010
• Issued: 11/26/2013
• Est. Priority Date: 06/03/2010
• Status: Expired due to Fees

• Current Assignee: Siemens Healthcare GMBH (Siemens AG)
• Original Assignee: Siemens AG
• Inventors: Goertler, Georg, Bertossi, Robert, Schultz, Harald, Rackow, Bastian, Engels, Norbert, Haeuser, Peter
• Primary Examiner(s): Lottich, Joshua P
• Application Number:
  US12/793,247
• Publication Number:
  US 20110302461A1
• Time in Patent Office: 1,272 Days
• Field of Search: 714/4.3, 714/4.4, 714/25, 714/26
• US Class Current: 714/26
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G16H 40/40 for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades

Abstract

A system and method of servicing a group of similar types of equipment that maybe installed at geographically separated locations is described. The method makes use of error messages produced by the equipment and service requests received by a servicing center. Data mining techniques are used to establish error patterns associated with specific failure modes so that future error messages may be processed to determine if an identified failure mode has occurred. This will enable the efficient dispatch of spare parts and service personnel to the location where the failure has occurred.

Claims

1. A system for managing the servicing of a geographically separated installed base of equipment, the system comprising:

an interface configured to receive, over a wide area network, one or more error reports from the geographically separated installed base of equipment;

a processor geographically remote from the geographically separated installed base of equipment, the processor configured to store the one or more error reports as a data base on a non-volatile medium; and

a data miner configured to process the data base containing the one or more error reports and to formulate an error pattern rule indicating a failure to be the subject of a service event, wherein formulation of the error pattern rule comprises a variant of pattern generation selected from the group consisting of a metric pattern variation and an error pattern variation;

wherein the geographically remote processor is configured to compare a currently received error report with the error pattern rule and output a notification of the service event when a match between the currently received error report and the error pattern rule occurs, and

wherein the service event notification output includes a location of equipment of the geographically separated installed base of equipment to be serviced and a hardware module to be replaced, an adjustment to be performed, a diagnostic procedure to be performed at the location of the equipment to be serviced, or a combination thereof.

2. The system of claim 1, wherein the wide area network is the Internet.

3. The system of claim 1, wherein the error pattern rule is a plurality of error pattern rules including error pattern rules resulting from data mining and from heuristic analysis.

4. The system of claim 1, wherein the service event notification output includes an identification of a plurality of hardware modules to be evaluated at a location of equipment of the geographically separated installed base of equipment, from which the currently received error report was received.

5. The system of claim 1, wherein the service event notification output includes a request to the equipment of the geographically separated installed base of equipment for error reports stored locally at the location of the equipment.

6. The system of claim 1, wherein the processor is further configured to identify and store error reports that do not result in a match to the error pattern rule.

7. A method of servicing geographically dispersed equipment, the method comprising:

receiving an error report over a wide area network from the geographically dispersed equipment;

storing the error report in a non-volatile data base;

operating a computer configured to perform data mining of a plurality of error reports in the data base to produce error pattern rules indicative of a specific failure type, the plurality of error reports comprising the error report, the computer being geographically remote from the geographically dispersed equipment;

comparing a subsequent error report received from equipment of the geographically dispersed equipment with the error pattern rules to determine when a match between the subsequent error report and a rule of the error pattern rules occurs; and

outputting, with the geographically remote computer, a report when the match occurs, the report including specific equipment of the geographically dispersed equipment and a specific failure type associated with the matched rule;

wherein the specific failure type is associated with an adjustment to be performed at a location of the specific equipment, a diagnostic test to be performed at the location of the specific equipment, or a combination thereof; and

wherein formulation of the error pattern rules comprises a variant of pattern generation selected from the group consisting of a metric pattern variation and an error pattern variation.

8. The method of claim 7, wherein the specific failure type is associated with a replaceable hardware module.

9. The method of claim 7, wherein the computer is further configured to store data, the data comprising error reports and an identification of hardware modules that are replaced without being identified with an error pattern rule of the error pattern rules, wherein the stored data includes a time stamp relating to a time of an event or a time of the replacement.

10. The method of claim 7, wherein the output report includes a specific hardware module to be retrieved from an inventory location.

11. The method of claim 10, wherein the inventory location, a location of the equipment and a location of the computer are different locations.

12. A computer program product comprising:

instructions stored on a non-transitory computer-readable medium, the instructions operable to configure a computer to;

receive error reports over a wide area network from geographically dispersed equipment, the computer being geographically remote from the geographically dispersed equipment;

store the error reports in a non-volatile data base;

perform data mining of the error reports to produce error pattern rules indicative of a specific failure type;

compare a subsequently received error report with the error pattern rules to determine when a match between the error report and a rule of the error pattern rules occurs; and

output a report when the match occurs, the report including specific equipment of the geographically dispersed equipment and the specific failure type associated with the matched rule;

wherein the report includes an identification of a hardware module to be replaced, an adjustment to be made to the specific equipment, a diagnostic routine to be performed on the specific equipment, or a combination thereof; and

wherein formulation of the error pattern rules comprises a variant of pattern generation selected from the group consisting of a metric pattern variation and an error pattern variation.