Search

EP-3872718-B1 - ADJUSTING MAINTENANCE INTERVALS FOR INDIVIDUAL PLATFORMS BASED ON OBSERVABLE CONDITIONS

EP3872718B1EP 3872718 B1EP3872718 B1EP 3872718B1EP-3872718-B1

Inventors

  • STURLAUGSON, Liessman E.
  • Paul, Ranjan Kumar
  • DEITS, Christopher David

Dates

Publication Date
20260506
Application Date
20210226

Claims (7)

  1. A computer-implemented method (600) of improving accuracy of maintenance scheduling, the method comprising: retrieving (602) scheduled maintenance data (112) and unscheduled in-service maintenance data (114) for a maintenance task (116) for a plurality of platforms (118); analyzing (604) a distribution of lifetimes (120) for the maintenance task (116) in the scheduled maintenance data (112) and unscheduled in-service maintenance data (114) for high variance or multiple modes; identifying (606), in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes (120), a number of conditions (122) in sensor data (124) of the plurality of platforms (118) correlated to a length of the lifetimes (120) for the maintenance task (116); dividing (608) the lifetimes (120) into a plurality of groups (126) based on the number of conditions (122); determining (610) a respective recommended maintenance interval (128) for each group of the plurality of groups (126) based on respective lifetimes (120) for the maintenance task (116) of a respective group; and calculating (614) a time point (130) comprising a minimum quantity of cycles, after which an acceptable amount of sensor data is available for a platform (104) such that an analysis can be performed to determine if the number of conditions (122) is present for the platform (104).
  2. The computer-implemented method (600) of claim 1 further comprising: retrieving (612) the sensor data (124) of the plurality of platforms (118).
  3. The computer-implemented method (600) of any of claims 1-2, wherein (618) each of the respective recommended maintenance intervals is an interval of time between performances of the maintenance task (116) that maximizes a probability that anomalies associated with a set of components are detected during preventive scheduled maintenance.
  4. An apparatus comprising: a bus system (702); a communications system (710) coupled to the bus system (702); and a processor unit (704) coupled to the bus system (702), wherein the processor unit executes the computer-usable program code (718) to retrieve scheduled maintenance data (112) and unscheduled in-service maintenance data (114) for a maintenance task (116) for a plurality of platforms (118); analyze a distribution of lifetimes (120) for the maintenance task (116) in the scheduled maintenance data (112) and unscheduled in-service maintenance data (114) for high variance or multiple modes; identify, in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes (120), a number of conditions (122) in sensor data (124) of the plurality of platforms (118) correlated to a length of the lifetimes (120) for the maintenance task (116); divide the lifetimes (120) into a plurality of groups (126) based on the number of conditions (122); and determine a respective recommended maintenance interval for each group of the plurality of groups (126) by performing an customized maintenance program (132) analysis on each of the plurality of groups (126); wherein the processor unit (704) also calculates a time point (130) comprising a minimum quantity of cycles, after which an acceptable amount of sensor data (144) is available for a platform (104) such that an analysis can be performed to determine if the number of conditions (122) is present for the platform (104).
  5. The apparatus of claim 4, wherein the processor unit (704) also sends analysis results of performing the customized maintenance program (132) analysis on the plurality of groups (126) to regulatory authorities for approval.
  6. The apparatus of claim 4 or 5, wherein the communications system (710) receives the sensor data (124) of the plurality of platforms (118).
  7. The apparatus of any of claims 4 to 6 wherein each of the respective recommended maintenance intervals (128) is an interval of time between performances of the maintenance task (116) that maximizes a probability that anomalies associated with a set of components (129) are detected on a respective platform (104) during preventive scheduled maintenance.

Description

BACKGROUND INFORMATION 1. Field: The present disclosure relates generally to maintenance and more specifically to adjusting maintenance intervals for an individual platform. 2. Background: An apparatus, such as an aircraft, construction equipment, or an automobile, may periodically be taken out of service for the performance of scheduled maintenance on the apparatus. Maintenance is performed to ensure that all component parts are operating with efficiency and safety. Different maintenance tasks may need to be performed at different intervals than other maintenance tasks. For example, in an automobile, air filters may need to be checked and replaced more frequently than the tires or the timing belt. Therefore, different maintenance tasks are typically scheduled to occur at different intervals. Maintenance tasks are provided with an original equipment manufacturer (OEM) recommended maintenance interval. An example of an original equipment manufacturer (OEM) recommended maintenance interval is changing oil in an automobile every 3,000 miles (or 5000 km) or three months. Often OEM maintenance intervals are overly conservative. Following the OEM recommendation may result in inefficient and non-standard maintenance scheduling programs. Following an OEM may cause operators to perform non-value-added maintenance which may be an unnecessary cost burden. In such cases, the current overly conservative scheduling of maintenance tasks may be cost ineffective and result in performance of unnecessary maintenance procedures. Therefore, it would be desirable to have a method and apparatus that takes into account at least some of the issues discussed above, as well as other possible issues. US 2019/066061 A1 describes a method for operating aircraft involves using analyzed data to improve future operational performance of aircraft by ordering changes in how component of aircraft performs during operation of aircraft based on analyzed data. EP 3 379 359 A1 describes a method and system for detecting abnormal valve operation based on a data-driven, unsupervised algorithm for analyzing sensor data. Furthermore, conventional approaches are targeted at diagnosing abnormal operation of a specific valve, or type of valve. US 2010/070237 A1 describes a method of identifying interval for performing maintenance task for, e.g. aircraft, involves performing statistical analysis on mapped maintenance data for identifying optimal interval for performing maintenance task. SUMMARY An example of the present disclosure provides a computer-implemented method. It is determined if sensor data of a platform indicates a condition affecting a frequency of a maintenance task. The maintenance interval for performing the maintenance task is changed for the platform to an updated value if a condition affecting the frequency of the maintenance task is indicated in the sensor data. The maintenance task is performed at or before the maintenance interval having the updated value. Another example of the present disclosure provides a computer-implemented method of improving accuracy of maintenance scheduling. Scheduled maintenance data and unscheduled in-service maintenance data for a maintenance task for a plurality of platforms is retrieved. A distribution of lifetimes for the maintenance task in the scheduled maintenance data and unscheduled in-service maintenance data is analyzed for high variance or multiple modes. A number of conditions in sensor data of the plurality of platforms correlated to a length of the lifetimes for the maintenance task is identified in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes. The lifetimes are divided into a plurality of groups based on the number of conditions. A respective recommended maintenance interval is determined for each group of the plurality of groups based on respective lifetimes for the maintenance task of a respective group. Yet another example of the present disclosure provides an apparatus. The apparatus comprises a bus system; a communications system coupled to the bus system; and a processor unit coupled to the bus system, wherein the processor unit executes the computer-usable program code to retrieve scheduled maintenance data and unscheduled in-service maintenance data for a maintenance task for a plurality of platforms; analyze a distribution of lifetimes for the maintenance task in the scheduled maintenance data and unscheduled in-service maintenance data for high variance or multiple modes; identify, in response to identifying at least one of high variance or multiple modes in the distribution of lifetimes, a number of conditions in sensor data of the plurality of platforms correlated to a length of the lifetimes for the maintenance task; divide the lifetimes into a plurality of groups based on the number of conditions; and determine a respective recommended maintenance interval for each group of the plurality of groups by performing an cu