Adjusting maintenance intervals of a subject platform based on observable conditions

Abstract

This application discloses adjusting maintenance intervals of an entity platform according to observable conditions. A maintenance interval adjuster and several methods are presented for improving accuracy of maintenance schedules and changing maintenance intervals. For a plurality of platforms, maintenance data for scheduled maintenance tasks and unscheduled service maintenance data are retrieved. Distributions of lifespans of the maintenance tasks in the scheduled maintenance data and the unscheduled service maintenance data are analyzed for high variance or multiple patterns. In response to identifying at least one of the high variance or the multiple patterns in the distributions of the lifespans, several conditions in sensor data of the plurality of platforms are identified that are related to lengths of the lifespans of the maintenance tasks. The lifespans are grouped into a plurality of groups based on the several conditions. A respective recommended maintenance interval is determined for each of the plurality of groups based on respective lifespans of the maintenance tasks of the respective groups.

Description

Technical Field

[0001] This disclosure generally pertains to maintenance, specifically to adjusting the maintenance intervals for individual platforms. Background Technology

[0002] Equipment such as aircraft, construction equipment, or automobiles may be periodically taken out of service to perform scheduled maintenance. Maintenance ensures that all components operate effectively and safely. Different maintenance tasks may need to be performed at different intervals compared to other maintenance tasks. For example, in a car, air filters may need to be checked and replaced more frequently than tires or timing belts. Therefore, different maintenance tasks are typically scheduled to occur at different intervals.

[0003] The maintenance tasks include maintenance intervals recommended by the original equipment manufacturer (OEM). An example of an OEM-recommended maintenance interval is to change the engine oil in the car every 3,000 miles or three months.

[0004] Typically, OEM maintenance intervals are overly conservative. Following OEM recommendations can lead to inefficient and non-standard maintenance schedules. Adhering to OEMs may force operators to perform non-value-added maintenance, which can be an unnecessary costly burden. In such cases, an overly conservative plan for maintenance tasks may be costly and result in unnecessary maintenance procedures.

[0005] Therefore, it is desirable to have a method and apparatus that take into account at least some of the issues discussed above, as well as other possible issues. Summary of the Invention

[0006] The examples disclosed herein provide a computer-implemented method. It determines whether sensor data from the platform indicates conditions that affect the frequency of maintenance tasks. If the sensor data indicates conditions that affect the frequency of maintenance tasks, the maintenance interval used by the platform to perform the maintenance tasks is changed to an updated value. The maintenance task is performed at or before the maintenance interval with the updated value.

[0007] Another example of this disclosure provides a computer-implemented method for improving the accuracy of maintenance planning. The method involves retrieving planned maintenance data and unplanned maintenance data for maintenance tasks across multiple platforms. It then analyzes the distribution of the lifespan of maintenance tasks in both the planned and unplanned maintenance data for high variance or multiple patterns. In response to identifying at least one of high variance or multiple patterns in the distribution of lifespans, it identifies several conditions in sensor data from multiple platforms that are related to the length of the maintenance task lifespan. The lifespans are then divided into multiple groups based on these conditions. Finally, based on the corresponding lifespan of the maintenance tasks in each group, a corresponding recommended maintenance interval is determined for each of the multiple groups.

[0008] Another example of this disclosure provides an apparatus. The apparatus includes a bus system; a communication system coupled to the bus system; and a processor unit coupled to the bus system, wherein the processor unit executes computer-usable program code to retrieve planned maintenance data and unplanned maintenance data for maintenance tasks across multiple platforms; analyzes the distribution of the lifespan of maintenance tasks in the planned and unplanned maintenance data for high variance or multiple patterns; identifies several conditions in sensor data across multiple platforms related to the length of the maintenance task's lifespan in response to identifying at least one of high variance or multiple patterns in the lifespan distribution; divides the lifespan into multiple groups based on the conditions; and determines a corresponding recommended maintenance interval for each of the multiple groups by performing a customized maintenance planning analysis on each of the multiple groups.

[0009] Features and functions can be implemented independently in the various examples of this disclosure, or they can be combined in other examples, in which more details can be seen with reference to the following description and figures. Attached Figure Description

[0010] The appended claims set forth novel features that are considered to be features of the illustrative example. However, the illustrative example and its preferred mode of use, further objects and features, will be best understood when read in conjunction with the accompanying drawings by referring to the following detailed description of the illustrative example of this disclosure, wherein:

[0011] Figure 1 It is a diagram illustrating the maintenance environment in which illustrative examples can be implemented;

[0012] Figure 2 It is a diagram illustrating the lifecycle distribution of maintenance tasks based on an illustrative example;

[0013] Figure 3 It is a diagram of a flowchart for using a maintenance interval adjuster, based on an illustrative example;

[0014] Figure 4 It is a diagram of a flowchart for adjusting maintenance intervals based on an illustrative example;

[0015] Figure 5 It is a flowchart illustration of a computer-implemented method for performing maintenance tasks by changing maintenance intervals according to an illustrative example;

[0016] Figure 6 It is a flowchart illustrating a computer-implemented method for improving the accuracy of maintenance plans based on illustrative examples;

[0017] Figure 7It is a diagram of a block diagram of a data processing system based on an illustrative example;

[0018] Figure 8 An illustration of an aircraft manufacturing and service method, presented in block diagram form as an illustrative example; and

[0019] Figure 9 It is an illustration of an aircraft in the form of a block diagram, in which illustrative examples can be implemented. Detailed Implementation

[0020] The illustrative example recognizes and takes into account one or more different considerations. The illustrative example recognizes and takes into account that maintenance intervals can be measured based on usage cycles, usage time, or calendar days. The illustrative example recognizes and takes into account that for aircraft, maintenance intervals can be measured over multiple flight cycles, multiple flight hours, multiple calendar days, or any other preferable type of measurement.

[0021] This illustrative example recognizes and considers the current availability of customized maintenance plans (CMPs) to individual aircraft operators, such as airlines. During the CMP process, service data from the operator's fleet is analyzed, and maintenance intervals for individual maintenance tasks are identified. These intervals may change in addition to the potential magnitude of variation. A possible outcome of the CMP analysis is that maintenance task intervals can be extended, resulting in a lower frequency of maintenance tasks compared to the original intervals recommended by the OEM. This reduced frequency of maintenance tasks saves the airline money by reducing the labor and material costs associated with performing these tasks. This illustrative example recognizes and considers that the OEM's original baseline intervals are determined based on a global fleet across all operators and environments, while CMP can leverage differences in operator environment, aircraft usage, maintenance methods, and other factors to determine the maintenance intervals designed for that specific operator.

[0022] The illustrative example recognizes and considers the statistical analysis of the historical lifecycles of the maintenance tasks under discussion in current Customized Airline Maintenance Planning (CMP) processes. Acceptable maintenance intervals can be determined for each planned maintenance task by calculating confidence intervals around the cumulative distribution function of the lifecycle. Existing solutions assume that maintenance intervals are the same across the operator's entire fleet. For tasks exhibiting high variability throughout their lifecycles, the lower bound of the confidence interval for the lifecycle distribution is taken too low, and the CMP analysis is necessarily overly cautious. The illustrative example recognizes and considers that this may leave value for operators, as they must perform more maintenance over the lifecycles of those aircraft with longer lifecycles.

[0023] The illustrative example recognizes and considers that today's CMP is performed across the entire fleet for a specific operator. It also recognizes and considers the expectation of drilling down to another level to see if maintenance intervals can be designed for aircraft-level efficiency beyond the operator level. Furthermore, it recognizes and considers that differentiating maintenance intervals at the aircraft level requires differentiation between aircraft in the fleet. However, current CMPs do not take into account the operational condition of each specific aircraft, as can be seen from sensors and other data. The illustrative example attempts to reduce within-group variance and allow condition-based intervals to identify potentially increased maintenance intervals for certain groups by transforming the CMP process to differentiate between lifecycle groups based on observable conditions.

[0024] The illustrative example provides an apparatus and methods for making aircraft-level maintenance interval recommendations to determine the regulatory approval interval for each aircraft based on its condition. The illustrative example uses a statistical distribution of the overall lifespan of the aircraft to make maintenance interval recommendations. The illustrative example extends the CMP process by considering multiple groups with several potentially different distributions. The illustrative example provides an apparatus and methods for determining which distribution applies to each aircraft based on its actual observable condition.

[0025] The illustrative example provides an apparatus and methods for improving the routine maintenance intervals of a single aircraft. The illustrative example considers the manufacturer-recommended routine maintenance intervals for the systems being inspected on the aircraft. The illustrative example uses aircraft health management system sensor data from the systems being inspected during each flight of the aircraft. The illustrative example analyzes the sensor data according to the manufacturer-recommended routine maintenance intervals for the systems being inspected.

[0026] The illustrative example processes analyzed data based on multiple historical health and condition observations of the inspected system under the manufacturer's recommended routine maintenance events. When assured by the analyzed data, the illustrative example provides improved recommended routine maintenance intervals for the inspected systems on individual aircraft at intervals longer than the manufacturer's recommended routine maintenance intervals. The illustrative example attempts to reduce within-group variance and allow condition-based interval determination to potentially increase maintenance intervals for certain groups by transforming the CMP process to differentiate between groups throughout the lifecycle based on observable condition.

[0027] Now go to Figure 1 The diagram illustrates a block diagram of a maintenance environment where illustrative examples can be implemented. Maintenance environment 100 includes a maintenance interval adjuster 102 configured to improve the accuracy of maintenance plans. Maintenance interval adjuster 102 enables condition-based interval determination for platform 104 within maintenance environment 100.

[0028] Maintenance interval adjuster 102 identifies condition maintenance interval set 106 from historical data 108. Condition maintenance interval set 106 includes maintenance tasks 110 with lifetimes of multiple identifiable groups based on observable conditions.

[0029] Maintenance tasks are those related to the inspection, maintenance, repair, and / or replacement of parts or sub-components. Maintenance tasks to be performed on equipment are typically scheduled solely based on the review and analysis of planned maintenance data. The analysis and review of maintenance data do not include line station and operational maintenance data. Furthermore, current analysis and review do not utilize any scientific methods to evaluate and analyze data within the service. Additionally, the format of planned maintenance data may not be submitted in a consistent manner, and operators may submit it voluntarily. Therefore, the current scheduling of maintenance data can be identified based on a limited scope of data that does not represent all aspects of aircraft maintenance events.

[0030] A maintenance event is any event related to the maintenance, repair, or replacement of equipment components. Maintenance events may include, but are not limited to, functional component failure, system failure, loss of function, reduced function, service interruption, corrosion, wear, slow response time, reduced efficiency, reduced fuel efficiency, tire pressure loss, or any other event requiring maintenance, repair, or replacement of a component or sub-component of a component.

[0031] Maintenance interval adjuster 102 retrieves maintenance data 111 for a given platform type, including planned maintenance data 112 and unplanned maintenance data 114. The given platform type is a specific platform type or model. For example, if the platform is an aircraft, the platform type could include all aircraft of a specific model, such as the Boeing 787. The platform type could also include all aircraft with one or more common characteristics, such as, but not limited to, all cargo aircraft using the same engine type or any other characteristic, or all aircraft. Therefore, the platform type can include platforms of the same or similar types.

[0032] Although several illustrative examples have been described for the purpose of an aircraft, these illustrative examples can be applied to other types of platforms. Platforms can be, for example, mobile platforms, fixed platforms, land-based structures, water-based structures, and air-based structures. Specifically, platforms can be surface ships, tanks, personnel carriers, trains, spacecraft, space stations, satellites, submarines, automobiles, power plants, bridges, dams, houses, manufacturing facilities, buildings, and other suitable platforms.

[0033] To improve the accuracy of the maintenance plan for maintenance task 116, maintenance interval adjuster 102 retrieves planned maintenance data 112 and unplanned maintenance data 114 for maintenance task 116 across multiple platforms 118. Maintenance interval adjuster 102 performs high variance or multiple pattern analysis on the distribution of the lifecycle 120 of maintenance task 116 within the planned maintenance data 112 and unplanned maintenance data 114. High variance or multiple patterns within the lifecycle 120 indicate the likelihood of different groupings within the lifecycle 120.

[0034] Use any desirable tests to identify multiple patterns. In some illustrative examples, one of the following is used to identify multiple patterns: Silverman's test, Hall and York test, redundant mass test, or Bayesian mixture model. In some illustrative examples, kernel density estimation or histogram-based methods known to those skilled in the art are used to identify multiple patterns.

[0035] In response to identifying at least one of high variance or multiple patterns in the distribution of lifetime 120, maintenance interval adjuster 102 identifies several conditions 122 in sensor data 124 of multiple platforms 118 that are related to the length of lifetime 120 of maintenance task 116.

[0036] The maintenance interval adjuster 102 divides the lifespan 120 into multiple groups 126 based on several conditions 122. The multiple groups 126 can have any number of groups that can be identified by identifiable conditions.

[0037] The maintenance interval adjuster 102 determines a corresponding recommended maintenance interval for each of the plurality of groups 126 based on the corresponding lifespan 120 of the maintenance tasks 116 for the corresponding group. The recommended maintenance intervals 128 for the plurality of groups 126 are based on the lifespan 120 of the maintenance tasks 116. Each of the corresponding recommended maintenance intervals 128 is the time interval between performing the maintenance tasks 116, which maximizes the probability of detecting anomalies related to the component set 129 on the corresponding platform during preventative planned maintenance.

[0038] Maintenance interval adjuster 102 calculates time point 130 after which an acceptable amount of sensor data is available for the platform (e.g., platform 104), allowing analysis to be performed to determine if several conditions 122 exist on the platform. Time point 130 can be measured based on usage cycles, usage time, or calendar days. When platform 104 is an aircraft 154, time point 130 is measured in several flight cycles, several flight hours, several calendar days, or any other desirable measurement type. In some illustrative examples, time point 130 is described as a minimum number of cycles.

[0039] In some illustrative examples, the maintenance interval adjuster 102 determines the appropriate recommended maintenance interval by performing a customized maintenance planning analysis 132 on each of multiple groups 126. In some illustrative examples, the analysis results 134 of the customized maintenance planning analysis 132 performed on the multiple groups 126 are sent to a regulatory agency for approval. Each distinct maintenance interval is pre-approved by the regulatory agency based on monitoring conditions and the ability to perform statistical CMP analysis for each interval.

[0040] Platform 104 has maintenance tasks 116 with maintenance intervals 136. Maintenance interval 136 initially has a default value 138. The default value 138 can be primitive 140, such as a maintenance interval recommended by the original equipment manufacturer (OEM). The default value 138 can also be fleet-based 142. When the default value 138 is fleet-based 142, statistical analysis of data from all platforms 118 for multiple platforms is used to determine the default value 138 for maintenance task 116.

[0041] In some illustrative examples, unplanned downtime of platform 104 can be reduced by changing the maintenance interval 136 for maintenance task 116 performed on platform 104. When maintenance task 116 has multiple associated groups 126 and platform 104 has a time point 145 greater than or equal to time point 130, sensor data 144 of platform 104 is analyzed for several conditions 122. In some illustrative examples, the processor 146 of platform 104 determines whether the sensor data 144 of platform 104 indicates that condition 147 affects the frequency of maintenance task 116.

[0042] If sensor data 144 indicates a condition 147 that affects the frequency of maintenance task 116, the maintenance interval 136 for maintenance task 116 on execution platform 104 is changed to the updated value 148. In these illustrative examples, the updated value 148 is based on condition 150. When sensor data 144 does not indicate a condition 147 that affects the frequency of maintenance task 116, the maintenance interval 136 retains the default value 138.

[0043] In some illustrative examples, sensor data 144 includes manually generated and automatically generated data. In some illustrative examples, sensor data 144 includes pilot-generated data. In some illustrative examples, sensor data 144 is generated by a plurality of sensors 152. The plurality of sensors 152 includes any preferable number or type of sensors. In some illustrative examples, the plurality of sensors 152 includes at least one of a temperature sensor, pressure sensor, proximity sensor, force sensor, light sensor, humidity sensor, displacement sensor, current sensor, or any other preferable type of sensor. The plurality of sensors 152 are located on platform 104 or at any preferable location on platform 104.

[0044] The type of condition 147 and the types of sensors among the multiple sensors 152 are at least somewhat related to the component set 129 or maintenance task 116. For example, condition 147 is the temperature of the components in component set 129. As another example, condition 147 is a certain amount of pressure on the components exposed to component set 129. In some illustrative examples, platform 104 is aircraft 154, and sensor data 144 is flight sensor data.

[0045] In some illustrative examples, changing maintenance interval 136 to the update value 148 decreases maintenance interval 136. In some illustrative examples, changing maintenance interval 136 to the update value 148 increases maintenance interval 136.

[0046] To improve the accuracy of the maintenance plan for the second maintenance task 156, the maintenance interval adjuster 102 retrieves planned maintenance data 112 and unplanned maintenance data 114 for the second maintenance task 156 across multiple platforms 118. The maintenance interval adjuster 102 performs high variance or multiple pattern analysis on the distribution of the lifecycle 158 of the second maintenance task 156 within the planned maintenance data 112 and the unplanned maintenance data 114. High variance or multiple patterns in the lifecycle 158 indicate the likelihood of different groupings within the lifecycle 158.

[0047] The maintenance interval adjuster 102 responds to identifying at least one of high variance or multiple patterns in the distribution of the lifetime 158 to identify a second condition 160 in the sensor data 124 of the multiple platforms 118 that is related to the length of the lifetime 158 of the second maintenance task 156.

[0048] The maintenance interval adjuster 102 divides the lifespan 158 into a second plurality of groups 162 based on a second plurality of conditions 160.

[0049] Maintenance interval adjuster 102 determines a corresponding recommended maintenance interval for each of the second plurality of groups 162 based on the corresponding lifespan 158 of the second maintenance task 156 for the corresponding group. The recommended maintenance intervals 164 of the second plurality of groups 162 are based on the lifespan 158 of the second maintenance task 156. Each of the corresponding recommended maintenance intervals 164 is a time interval between the execution of the second maintenance task 156 that maximizes the probability of anomalies associated with the second component set 166 detected during preventative planned maintenance.

[0050] Maintenance interval adjuster 102 calculates a second time point 168 after which an acceptable amount of sensor data is available for the platform (e.g., platform 104), allowing analysis to be performed to determine if a second condition 160 exists on the platform. The second time point 168 can be measured based on usage cycles, usage time, or calendar days. When platform 104 is an aircraft 154, the second time point 168 is measured over multiple flight cycles, multiple flight hours, multiple calendar days, or any other preferable measurement type. In some illustrative examples, the second time point 168 is described as a minimum number of cycles.

[0051] In some illustrative examples, the maintenance interval adjuster 102 determines the appropriate recommended maintenance interval by performing a customized maintenance planning analysis 132 on each of the second plurality of groups 162. In some illustrative examples, the analysis results 134 of the customized maintenance planning analysis 132 performed on the second plurality of groups 162 are sent to a regulatory agency for approval. Each distinct maintenance interval is pre-approved by the regulatory agency based on monitoring conditions and the ability to perform statistical CMP analysis for each interval.

[0052] Platform 104 has a second maintenance task 156 with a second maintenance interval 170. The second maintenance interval 170 initially has a second default value 172. The second default value 172 can be a raw value, such as a maintenance interval recommended by the original equipment manufacturer (OEM). The second default value 172 can be fleet-based. When the second default value 172 is fleet-based, the second default value 172 is determined using statistical analysis of data from all platforms of the multiple platforms 118 for the second maintenance task 156.

[0053] In some illustrative examples, unplanned downtime of platform 104 can be reduced by changing the second maintenance interval 170 for performing the second maintenance task 156 on platform 104. When the second maintenance task 156 has associated second plurality of groups 162 and platform 104 has a second time point 174 greater than or equal to a second time point 168, second sensor data 176 of platform 104 is analyzed for a second plurality of conditions 160. In some illustrative examples, the processor 146 of platform 104 determines whether the second sensor data 176 of platform 104 indicates a second condition 178 affecting the frequency of maintenance task 116.

[0054] If the second sensor data 176 indicates a second condition 178 affecting the frequency of the second maintenance task 156, then the second maintenance interval 170 for the second maintenance task 156 performed on the platform 104 is changed to a second updated value 180. In these illustrative examples, the second updated value 180 is condition-based. When the second sensor data 176 does not indicate a second condition 178 affecting the frequency of the second maintenance task 156, the second maintenance interval 170 remains at the second default value 172.

[0055] Maintenance task 116 and the second maintenance task 156 are different maintenance tasks. Recommended maintenance interval 128 and recommended maintenance interval 164 are independent of each other. Each of recommended maintenance interval 128 and recommended maintenance interval 164 is independently determined. In some illustrative examples, maintenance task 116 and the second maintenance task 156 have at least one common component between component set 129 and component set 166. In some illustrative examples, maintenance task 116 and the second maintenance task 156 do not have any common components between component set 129 and component set 166.

[0056] In some illustrative examples, sensor data 144 and second sensor data 176 have at least some overlap. In some other illustrative examples, sensor data 144 and second sensor data 176 do not overlap.

[0057] Maintenance task 116 is performed on platform 104 at or before maintenance interval 136. Maintenance task 116 is performed on platform 104 at or before maintenance interval 136 with updated value 148 after maintenance interval 136 is updated. After performing maintenance task 116, the time point counter used for sensor data 144 is reset to its default value. After performing maintenance task 116, the maintenance interval 136 for which maintenance task 116 was performed is reset to its default value 138.

[0058] Figure 1 The illustrations of maintenance interval adjuster 102 and platform 104 do not imply any physical or architectural limitations on how the exemplary examples can be implemented. Other components besides those shown, or components that replace those shown, may be used. Some components may be unnecessary. Furthermore, boxes are provided to illustrate some functional components. When implemented in the illustrative example, one or more of these boxes may be combined, divided, or combined and divided into different boxes.

[0059] For example, although in Figure 1The document describes two maintenance tasks, but any number of maintenance tasks can exist. The number of maintenance tasks monitored during a service update is related to the number of maintenance tasks with multiple lifecycle modes. The number of maintenance tasks monitored during a service update is also related to the number of maintenance tasks with conditions that are statistically significantly correlated with multiple modes.

[0060] As another example, although maintenance task 116 is described as relating to condition 147, maintenance task 116 can relate to any number of conditions. Furthermore, although processor 146 is depicted as being within platform 104, in other illustrative examples, processor 146 is outside platform 104.

[0061] In some illustrative examples, the database 182 with historical data 108 and the maintenance interval adjuster 102 are part of the same computer system. In other illustrative examples, the database 182 and the maintenance interval adjuster 102 are part of different computer systems. In some illustrative examples, the database 182 and the maintenance interval adjuster 102 are controlled by different parties. For example, the database 182 may be controlled and maintained by a client. In some examples, the maintenance interval adjuster 102 is controlled and maintained by a service company.

[0062] Now go to Figure 2 A diagram illustrating the lifecycle distribution for a maintenance task is provided, based on an illustrative example. Graph 200 has an x-axis 202 for time and a y-axis 203 for quantity. Data 204 depicts the number of instances of platforms with lifecycles along the x-axis 202. Shorter lifecycles are closer to the y-axis 203. Data 204 has two peaks, peak 206 and peak 208. Data 204 exhibits multiple modes. In this instance, the lifecycle may be distinguishable into two or more groups. Peaks 206 and 208 can be delimited by marker 210, which indicates the delimitation point for the bimodality. After identifying the potential multimodality in the lifecycle distribution of data 204, sensor data is used to determine whether this multimodality is likely a function of a relevant operational condition (not described).

[0063] Now go to Figure 3 The illustration describes a flowchart for utilizing a maintenance interval adjuster, based on illustrative examples. In some illustrative examples, flowchart 300 can be... Figure 1 The process of maintenance interval adjuster 102 is described. Flowchart 300 can be used for analysis. Figure 2 Data 204.

[0064] Collect the historical lifecycle for maintenance tasks (Operation 302). Collect the lifecycle for maintenance tasks for multiple platforms controlled by the operator. For example, when the operator is a car rental company, the platform is the vehicle. As another example, when the operator is a construction company, the platform is construction equipment. In some illustrative examples, each of the multiple platforms has the same type or model.

[0065] Analyze the distribution of lifetimes for high variance or multiple patterns (Operation 304). Multiple patterns can be identified using any desirable test. In some illustrative examples, one of the following is used to identify multiple patterns: Silverman's test, Hall and York test, redundant mass test, or Bayesian mixture model. In some illustrative examples, kernel density estimation or histogram-based methods known to those skilled in the art are used to identify multiple patterns.

[0066] Determine whether it is possible to separate the lifespan into two or more groups (Operation 306). During the analysis, determine whether the two or more groups are statistically significant. Use any desirable method to determine the statistical significance of the differences between the two or more groups. In some illustrative examples, the statistical significance of the differences between the two or more groups is determined by analysis of the variance test, the Kolmogorov-Smirnov test, or another desirable statistical test.

[0067] If it is not possible to divide the lifecycle into two or more groups, then group the lifecycles into one group (Operation 308). Run a CMP analysis on the lifecycle group (Operation 310). Determine if CMP analysis has been performed on all groups (Operation 312). In some illustrative examples, the analysis is packaged and submitted to the regulatory body for approval (Operation 314). Each distinct maintenance interval is pre-approved by the regulatory body based on the monitoring status and the capability of statistical CMP analysis for each interval.

[0068] If the lifespan can be divided into two or more groups in Operation 306, sensor data is collected for multiple platforms including each lifespan (Operation 316). When the multiple platforms are multiple aircraft, the sensor data is in the form of flight sensor data. The sensor data is analyzed for several conditions related to the length of the historical lifespan (Operation 318). It is determined whether there are differences between the different groups for one or more conditions. In some illustrative examples, conditions are identified by calculating cumulative statistics for sensor values ​​related to maintenance and identifying the statistics with the strongest correlation to different groups. Cumulative statistics are cumulative sums, cumulative maximums, cumulative variances, or other statistics. The correlation is a Pearson or Spearman correlation between the cumulative statistics and the length of the historical lifespan, or an analysis of the variance test or Kolmogorov-Smirnov test between the cumulative statistics and the classification groups of the historical lifespan.

[0069] Design a time point t for the highest relevance with an acceptable lead time to determine the interval (Operation 320). In these illustrative examples, t is the time before determining whether a condition exists in the data. The time point t can be measured based on usage cycle, usage time, or calendar days.

[0070] Determine if there are several conditions that distinguish lifetime and time point t by an acceptable lead time (Operation 322). Divide the lifetime into two or more groups based on the conditions (Operation 324).

[0071] Next, CMP analysis is run for each group throughout its lifecycle (Operations 310 and 312). In some illustrative examples, the analysis for all group lifecycles is packaged and submitted to the regulatory body for approval (Operation 314). After the analysis is submitted to the regulatory body, flowchart 300 ends.

[0072] Turn now Figure 4 The illustration describes a flowchart for adjusting maintenance intervals, based on illustrative examples. In some illustrative examples, flowchart 400 can be... Figure 1 A description of the process executed by processor 146. Flowchart 400 can be used for updating. Figure 1 The maintenance interval of platform 104. In some illustrative examples, flowchart 400 utilizes... Figure 3 Several situations are identified in flowchart 300.

[0073] Platform cycle complete (Operation 402). When the platform is an aircraft, the aircraft flight cycle is complete.

[0074] Determine if time point t has been exceeded (Operation 404). Provide time point t for determination (Operation 406). Time point t is generated by operation 320 of flowchart 300. Time point t can be measured based on usage cycle, usage time, or calendar days.

[0075] If time point t has not been exceeded in operation 404, then determine whether the maintenance interval for the maintenance task has been reached (operation 408). If the maintenance interval has not been reached, flowchart 400 returns to operation 402.

[0076] If the maintenance interval has been reached, perform the planned maintenance (Operation 418). After performing the maintenance task, reset the time point counter and set the maintenance interval to the default value (Operation 420). After resetting the time point counter, the time point counter will start from zero again. When the maintenance interval is set to the default value, the maintenance interval is one of the original OEM maintenance interval or the fleet-based CMP maintenance interval.

[0077] If time point t has been exceeded in operation 404, then analyze sensor data for one or more conditions related to the maintenance task (operation 410). Provide a condition-to-interval mapping to perform sensor analysis (operation 412). The condition-to-interval mapping is... Figure 3 The output of the analysis of flowchart 300. The mapping from condition to interval is a list of several conditions associated with the corresponding maintenance interval of the maintenance task.

[0078] The maintenance interval is updated based on the current status (operation 414). If a status is associated with the updated value, the maintenance interval is changed to the updated value in operation 414. The updated value is based on the status. If no status is associated with the updated value, the maintenance interval remains unchanged compared to the previous value. In some illustrative examples, if no status is associated with the updated value, the maintenance interval is maintained at the default value. The maintenance interval is provided (operation 416) to determine whether the maintenance interval for the task has been reached.

[0079] Now go to Figure 5 The illustration depicts a flowchart of a computer-implemented method for changing maintenance intervals to perform maintenance tasks, based on an illustrative example. Method 500 can be executed to update... Figure 1 The maintenance interval of platform 104. Implementation method 500 can reduce unplanned downtime by changing the maintenance interval. Implementation method 500 can reduce unnecessary downtime caused by unnecessarily frequent performance of maintenance tasks.

[0080] Determine whether the platform's sensor data indicates conditions that affect the frequency of maintenance tasks (Operation 502). A condition is an observable condition that can be differentiated into groups throughout the lifecycle. A condition may take any desirable form that differentiates between groups throughout the lifecycle. In some illustrative examples, a condition is at least one of sensor variance, sensor readings exceeding tolerance, hard landings, or any other desirable condition. In some illustrative examples, a condition is the number of sensor variances, the number of sensor readings exceeding tolerance, the number of hard landings, or any other observable condition accumulated over all flights from the last reset of the time point counter until the time point has exceeded or not exceeded a specified threshold.

[0081] If the sensor data indicates a condition affecting the frequency of maintenance tasks, the maintenance interval for the maintenance tasks performed on the platform is changed to an updated value (operation 504). Based on the existence of the condition, the updated value is assigned to the platform respectively. The maintenance task is performed at or before the maintenance interval with the updated value (operation 506). Afterwards, method 500 terminates.

[0082] In some illustrative examples, it is determined whether sensor data meets a time point, wherein, in response to determining that the sensor data does indeed meet a time point, it is determined whether the platform's sensor data indicates a condition affecting the frequency of maintenance tasks (Operation 508). Time periods can be measured based on usage cycles, usage time, or calendar days. In some illustrative examples, the time point is in the form of a minimum number of cycles, and determining whether sensor data meets a time point includes determining whether the sensor data meets the minimum number of cycles.

[0083] In some illustrative examples, the maintenance interval is changed to an updated value to decrease the maintenance interval (operation 510). In some illustrative examples, the maintenance interval is changed to an updated value to increase the maintenance interval (operation 512). In some illustrative examples, after performing a maintenance task, the time counter for the point in time when the maintenance task was performed and the maintenance interval are reset to their default values ​​(operation 514).

[0084] In some illustrative examples, method 500 determines whether the platform's second sensor data indicates a second condition affecting the frequency of a second maintenance task (operation 516). In some illustrative examples, the sensor data and the second sensor data have some overlap. In some illustrative examples, the sensor data and the second sensor data do not overlap.

[0085] In some illustrative examples, if the second sensor data indicates a second condition affecting the frequency of the second maintenance task, method 500 changes the second maintenance interval for performing the second maintenance task on the platform to an updated value (operation 518). In some illustrative examples, method 500 performs the second maintenance task at or before the second maintenance interval with the updated value (operation 520). In some illustrative examples, method 500 determines whether the second sensor data meets a second time point, wherein in response to determining that the second sensor data does indeed meet the second time point, it is determined whether the second sensor data of the platform indicates a second condition affecting the frequency of the second maintenance task (operation 522).

[0086] Now go to Figure 6 The diagram illustrates a flowchart of a computer-implemented method for improving the accuracy of maintenance plans, based on illustrative examples. It can be derived from... Figure 1 The maintenance interval adjuster 102 executes method 600. It can be used... Figure 2 Data 204 execution method 600.

[0087] Method 600 retrieves planned maintenance data and unplanned service maintenance data for maintenance tasks across multiple platforms (Operation 602). Method 600 analyzes the distribution of the lifecycle of maintenance tasks in the planned and unplanned service maintenance data for high variance or multiple patterns (Operation 604). In response to identifying at least one of high variance or multiple patterns in the lifecycle distribution, Method 600 identifies several conditions in the sensor data of multiple platforms related to the lifecycle length of the tasks (Operation 606). Method 600 divides the lifecycle into multiple groups based on these conditions (Operation 608). Method 600 determines the corresponding recommended maintenance interval for each of the multiple groups by performing a customized maintenance planning analysis on each group (Operation 610). Method 600 then terminates.

[0088] In some illustrative examples, sensor data from multiple platforms is retrieved (operation 612). In some illustrative examples, method 600 calculates a time point after which an acceptable amount of sensor data is available for the platform, allowing analysis to be performed to determine if certain conditions exist on the platform (operation 614). In some illustrative examples, the time point is a minimum number of cycles (operation 616). In some illustrative examples, method 600 sends the results of a customized maintenance planning analysis performed on multiple groups to a regulatory agency for approval (operation 618). In some illustrative examples, each of the corresponding recommended maintenance intervals is a time interval between performing maintenance tasks that maximizes the probability of detecting anomalies related to the component set during preventative planned maintenance (operation 620).

[0089] As used in this article, when the phrase “at least one” is used with a list of items, it means that different combinations of one or more of the listed items may be used, and perhaps only one of each item in the list is required. For example, “at least one of item A, item B, or item C” can be, but is not limited to, item A, item A and item B, or item B. This example could also include item A, item B, and item C, or item B and item C. Of course, any combination of these items can exist. In other examples, “at least one” can be, for example, but not limited to, two of item A; one of item B; ten of item C; four of item B and seven of item C; or other suitable combinations. The item can be a specific object, thing, or category. In other words, “at least one” means that any combination of items and any number of items in the list can be used, but not all items in the list are required.

[0090] As used in this article, when “several” is used in reference items, it means one or more items.

[0091] The flowcharts and block diagrams in the various examples described illustrate the architecture, functionality, and operation of some possible implementations of the devices and methods in the exemplary examples. In this regard, each block in the flowchart or block diagram may represent at least one of a module, segment, function, or part of an operation or step.

[0092] In some alternative implementations of the illustrative examples, one or more functions marked in the boxes may occur in a different order than those shown in the figures. For example, in some cases, depending on the functions involved, two consecutively shown boxes may be executed substantially simultaneously, or sometimes they may be executed in reverse order. Furthermore, additional boxes may be added besides those shown in the flowchart or block diagram. Some boxes may be optional. For example, operations 508 through 514 may be optional. As another example, operations 612 through 620 may be optional.

[0093] Now go to Figure 7 A block diagram of a data processing system is described below, based on an illustrative example. Data processing system 700 can be used for implementation. Figure 1 The maintenance interval adjuster 102 or processor 146 are one or more of these. The data processing system 700 can be used to execute at least one of flowchart 300, flowchart 400, method 500, or method 600. In this illustrative example, the data processing system 700 includes a communication framework 702 that provides communication between the processor unit 704, memory 706, persistent storage 708, communication unit 710, input / output unit 712, and display 714. In this example, the communication framework 702 may take the form of a bus system.

[0094] Processor unit 704 is used to execute instructions for software that can be loaded into memory 706. Processor unit 704 may be several processors, a multiprocessor core, or some other type of processor, depending on the specific implementation. In an example, processor unit 704 includes one or more conventional general-purpose central processing units (CPUs). In an alternative example, processor unit 704 includes one or more graphics processing units (GPUs).

[0095] Memory 706 and persistent storage 708 are examples of storage device 716. A storage device is any hardware capable of storing information (e.g., but not limited to, data, at least one of program code in functional form, or other suitable information on a temporary or permanent basis, or both). In these illustrative examples, storage device 716 may also be referred to as a computer-readable storage device. In these examples, memory 706 may be, for example, random access memory or any other suitable volatile or non-volatile storage device. Persistent storage 708 may take various forms depending on the specific implementation.

[0096] For example, persistent storage 708 may include one or more components or devices. For example, persistent storage 708 may be a hard disk drive, flash memory, rewritable optical disc, rewritable magnetic tape, or a combination thereof. The media used in persistent storage 708 may also be removable. For example, a removable hard disk drive may be used for persistent storage 708.

[0097] In these illustrative examples, communication unit 710 provides communication with other data processing systems or devices. In these illustrative examples, communication unit 710 is a network interface card. In some illustrative examples, communication unit 710 receives sensor data 124 from multiple platforms 118.

[0098] The input / output unit 712 allows data input and output to other devices that can be connected to the data processing system 700. For example, the input / output unit 712 can provide a connection for user input via at least one of a keyboard, mouse, or other suitable input device. Furthermore, the input / output unit 712 can send output to a printer. The display 714 provides a mechanism for displaying information to the user.

[0099] Instructions for at least one of an operating system, application, or program may be located in storage device 716, which communicates with processor unit 704 via communication frame 702. Processes of various examples may be executed by processor unit 704 using computer-implemented instructions, which may reside in memory such as memory 706.

[0100] These instructions are referred to as program code, computer-usable program code, or computer-readable program code that can be read and executed by the processor in processor unit 704. The program code in different examples may be embodied on different physical or computer-readable storage media, such as memory 706 or persistent storage 708.

[0101] Program code 718 is functionally located on a computer-readable medium 720, which can be selectively removed and can be loaded onto or transferred to a data processing system 700 for execution by a processor unit 704. Program code 718 and computer-readable medium 720 form a computer program product 722 in these illustrative examples. In one example, computer-readable medium 720 may be a computer-readable storage medium 724 or a computer-readable signal medium 726.

[0102] Furthermore, as used herein, "computer-readable medium 720" can be singular or plural. For example, program code 718 may be located in a computer-readable medium 720 in the form of a single storage device or system. In another example, program code 718 may be located in computer-readable media 720 distributed across multiple data processing systems. In other words, some instructions in program code 718 may be located in one data processing system, while other instructions in program code 718 may be located in a data processing system. For example, a portion of program code 718 may be located in a computer-readable medium 720 in a server computer, while another portion of program code 718 may be located in a computer-readable medium 720 situated in a collection of client computers.

[0103] The different components described for data processing system 700 do not imply any architectural limitations on how different examples can be implemented. In some illustrative examples, one or more components may be incorporated into another component or otherwise formed as part of another component. For example, in some illustrative examples, memory 706 or a portion thereof may be incorporated into processor unit 704. Different illustrative examples may be implemented in a data processing system that includes components other than those described for data processing system 700 or components that replace those components. Figure 7 The other components shown may differ from the illustrative example shown. Different examples can be implemented using any hardware device or system capable of running program code 718.

[0104] In these illustrative examples, computer-readable storage medium 724 is a physical or tangible storage device for storing program code 718, rather than a medium for propagating or transmitting program code 718. Alternatively, computer-readable signal medium 726 may be used to transmit program code 718 to data processing system 700.

[0105] The computer-readable signal medium 726 may be, for example, a propagated data signal containing program code 718. For example, the computer-readable signal medium 726 may be at least one of electromagnetic signals, optical signals, or any other suitable type of signal. These signals can be transmitted via at least one communication link, such as a wireless communication link, fiber optic cable, coaxial cable, wire, or any other suitable type of communication link.

[0106] The different components described for data processing system 700 do not imply any architectural limitations on how different examples can be implemented. Different illustrative examples can be implemented in the data processing system, which includes components other than those described for data processing system 700 or components that replace those components. Figure 7 The other components shown may differ from the illustrative example shown. Different examples can be implemented using any hardware device or system capable of running program code 718.

[0107] It can be like Figure 8 The aircraft manufacturing and service methods shown in 800 and such Figure 9 An illustrative example of this disclosure is described in the context of the aircraft 900 shown. First, turn to... Figure 8 The illustration depicts an aircraft manufacturing and service method based on illustrative examples. During pre-production, the aircraft manufacturing and service method 800 may include... Figure 9 Specifications and design of CM900 802 and material procurement 804.

[0108] During production, the manufacturing of components and subassemblies of aircraft 900 is carried out (806), as well as system integration (808). Afterward, aircraft 900 may undergo certification and delivery (810) for service (812). While in service (812) through the customer, aircraft 900 is scheduled for routine maintenance and service (814), which may include modifications, reconfigurations, refurbishments, or other maintenance and service.

[0109] Each process in the Aircraft Manufacturing and Service Method 800 can be performed or implemented by a systems integrator, a third party, and / or an operator. In these examples, the operator can be the customer. For the purposes of this specification, a systems integrator can include, but is not limited to, any number of aircraft manufacturers and major systems subcontractors; a third party can include, but is not limited to, any number of vendors, subcontractors, and suppliers; and an operator can be an airline, leasing company, military entity, service organization, etc.

[0110] Now for reference Figure 9 The illustration depicts an aircraft, in which illustrative examples can be implemented. In this example, aircraft 900... Figure 8 The aircraft manufacturing and service method 800 produces an aircraft and may include a fuselage 902 having multiple systems 904 and an interior 906. Examples of systems 904 include one or more of a propulsion system 908, an electrical system 910, a hydraulic system 912, and an environmental system 914. Any number of other systems may be included.

[0111] The equipment and methods embodied herein may be used during at least one stage of the aircraft manufacturing and service method 800. Figure 8 One or more illustrative examples are used during Service 812 or during maintenance and Service 814. Method 500 can be executed during Service 812 to update the maintenance interval. Figure 8 During maintenance and service 814, maintenance tasks with update maintenance intervals from method 500 are performed.

[0112] Aircraft 900 can be with Figure 1 The same applies to aircraft 154. Method 500 can be used to update the maintenance intervals for maintenance tasks of aircraft 900. As an example, method 500 can be used to update the maintenance intervals of any one of the fuselage 902, multiple systems 904, or internal systems 906.

[0113] Method 600 can be used to set recommended maintenance intervals for a portion of aircraft 900. Method 600 can also be used to set recommended maintenance intervals for any of the fuselage 902, multiple systems 904, or internal systems 906.

[0114] The illustrative examples provide devices and methods for setting up effective condition-based maintenance intervals. Condition-based maintenance intervals utilize additional data sources from a single aircraft. Condition-based maintenance intervals also consider statistical analysis of data from multiple platforms that have the same model or characteristics as the platform.

[0115] Illustrative examples identify potential multimodalities in the lifetime distribution as a function of relevant operational conditions, thereby deriving dynamic interval recommendations.

[0116] The illustrative example detection depends on / is associated with different groups of the lifecycle of a certain operating condition. For a condition to be valid for maintenance interval analysis, it must be possible to dynamically monitor the operating condition.

[0117] Use the decision point at the correlation peak as the time to determine the actual maintenance interval for the tail under consideration.

[0118] Depending on the state of the monitored conditions, different / modified planned maintenance intervals can be used for different subsets of the aircraft. Each different maintenance interval is pre-approved by the regulatory authority based on the monitoring conditions and the ability to conduct statistical CMP analysis for each interval.

[0119] Various illustrative examples have been presented for purposes of explanation and description, and are not intended to be exhaustive or limited to the examples of the disclosed form. Many modifications and variations will be apparent to those skilled in the art. Furthermore, different illustrative examples may provide different features compared to other illustrative examples. Because various examples are suited to the specific use considered, the disclosure and description of one or more selected examples are provided to best explain the principles and practical applications of the examples and to enable others skilled in the art to understand the various examples with various modifications.

[0120] Clause 1: A computer-implemented method comprising determining whether sensor data of a platform indicates a condition affecting the frequency of a maintenance task; if the sensor data indicates a condition affecting the frequency of the maintenance task, changing a maintenance interval for performing the maintenance task on the platform to an updated value; and performing the maintenance task at or before the maintenance interval having the updated value.

[0121] Clause 2: The method according to Clause 1, wherein the maintenance interval is changed to the update value reducing the maintenance interval.

[0122] Clause 3: The method according to Clause 1 or 2, wherein the maintenance interval is changed to increase the maintenance interval by the update value.

[0123] Clause 4: The method according to any one of Clauses 1-3 further includes resetting the time counter for the time point of the maintenance task and the maintenance interval to default values ​​after the maintenance task is performed.

[0124] Clause 5: The method according to any one of Clauses 1-4 further includes determining whether the sensor data meets a time point, wherein in response to determining that the sensor data does indeed meet the time point, it is determined whether the sensor data of the platform indicates a condition affecting the frequency of the maintenance task.

[0125] Clause 6: The method described in Clause 5, wherein the point in time is one of a number of usage cycles, a number of usage times, or a number of calendar days.

[0126] Clause 7: The method according to any one of Clauses 1-6 further includes determining whether second sensor data of the platform indicates a second condition affecting the frequency of the second maintenance task; if the second sensor data indicates a second condition affecting the frequency of the second maintenance task, then changing the second maintenance interval for performing the second maintenance task of the platform to a second updated value; performing the second maintenance task at or before the second maintenance interval having the second updated value.

[0127] Clause 8: The method according to Clause 7 further includes determining whether the second sensor data meets a second time point, wherein in response to determining that the second sensor data does indeed meet the second time point, it is determined whether the second sensor data of the platform indicates a second condition affecting the frequency of the second maintenance task.

[0128] Clause 9: The method according to any one of Clauses 1-8, wherein the platform is an aircraft and the sensor data is flight sensor data.

[0129] Clause 10: A computer-implemented method for improving the accuracy of maintenance planning, the method comprising: retrieving planned maintenance data and unplanned maintenance data for maintenance tasks across multiple platforms; analyzing the distribution of the lifespan of the maintenance tasks in the planned maintenance data and the unplanned maintenance data for high variance or multiple patterns; identifying, in response to identifying at least one of high variance or multiple patterns in the distribution of the lifespan, several conditions in sensor data of the multiple platforms related to the length of the lifespan of the maintenance tasks; dividing the lifespan into multiple groups based on the several conditions; and determining a corresponding recommended maintenance interval for each of the multiple groups based on the corresponding lifespan of the maintenance tasks in the corresponding groups.

[0130] Clause 11: The method described in Clause 10 further includes retrieving the sensor data from the plurality of platforms.

[0131] Clause 12: The method according to Clause 10 or 11 further includes calculating a time point after which an acceptable amount of sensor data is available to the platform, enabling analysis to be performed to determine whether the platform is in any of the aforementioned conditions.

[0132] Clause 13: The method described in Clause 12, wherein the time point is a minimum number of cycles.

[0133] Clause 14: The method according to any one of Clauses 10-13, wherein each of the respective recommended maintenance intervals is a time interval between the performance of the maintenance task, the time interval maximizing the probability of detecting an anomaly associated with the component set during preventive planned maintenance.

[0134] Clause 15: An apparatus comprising a bus system; a communication system coupled to the bus system; and a processor unit coupled to the bus system, wherein the processor unit executes computer-usable program code to retrieve planned maintenance data and unplanned maintenance data for maintenance tasks across multiple platforms; analyzes the distribution of the lifespan of the maintenance tasks in the planned maintenance data and the unplanned maintenance data for high variance or multiple patterns; in response to identifying at least one of high variance or multiple patterns in the distribution of the lifespan, identifies several conditions in sensor data of the multiple platforms related to the length of the lifespan of the maintenance tasks; divides the lifespan into multiple groups based on the several conditions; and determines a corresponding recommended maintenance interval for each of the multiple groups by performing a customized maintenance planning analysis on each of the multiple groups.

[0135] Clause 16: The device as described in Clause 15, wherein the processor unit also sends the analysis results of the customized maintenance planning analysis performed on the plurality of groups to a regulatory authority for approval.

[0136] Clause 17: The device according to Clause 15 or 16, wherein the communication system receives the sensor data from the plurality of platforms.

[0137] Clause 18: The device according to any one of Clauses 15-17, wherein the processor unit further calculates a time point after which an acceptable amount of sensor data is available to the platform, such that analysis can be performed to determine whether the platform is subject to the aforementioned conditions.

[0138] Clause 19: The device as described in Clause 18, wherein the time point is a minimum number of cycles.

[0139] Clause 20: The device according to any one of Clauses 15-19, wherein each of the respective recommended maintenance intervals is a time interval between the execution of the maintenance task, the time interval maximizing the probability of detecting an anomaly associated with a set of components on the respective platform during preventive planned maintenance.

Claims

1. A computer-implemented method for adjusting maintenance intervals, comprising: Determine whether the platform’s sensor data indicates conditions that affect the frequency of maintenance tasks to be performed on the platform, wherein the conditions are observable conditions that are distinguished between groups of the lifecycle of the maintenance tasks. If the sensor data indicates a condition affecting the frequency of the maintenance task, the maintenance interval for performing the maintenance task on the platform will be changed to an updated value. The maintenance task is performed on the platform at or before the maintenance interval that has the updated value; as well as After the maintenance task is executed, the time counter for the execution of the maintenance task and the maintenance interval will be reset to their default values.

2. The method of claim 1, wherein the maintenance interval is changed to the update value reducing the maintenance interval.

3. The method of claim 1, wherein the maintenance interval is changed by increasing the maintenance interval with the update value.

4. The method according to claim 1, further comprising: Determine whether the sensor data meets a time point, wherein in response to determining that the sensor data does indeed meet the time point, it is determined whether the sensor data of the platform indicates a condition affecting the frequency of the maintenance task.

5. The method according to claim 4, wherein the time point is one of a certain number of usage cycles, a certain number of usage times, or a certain number of calendar days.

6. The method according to claim 1, further comprising: Determine whether the platform’s second sensor data indicates a second condition that affects the frequency of the second maintenance task; If the second sensor data indicates a second condition that affects the frequency of the second maintenance task, then the second maintenance interval for performing the second maintenance task on the platform will be changed to a second updated value. and The second maintenance task is performed at or before the second maintenance interval when the second update value is available.

7. The method of claim 6, further comprising: Determine whether the second sensor data meets a second time point, wherein in response to determining that the second sensor data does indeed meet the second time point, it is determined whether the second sensor data of the platform indicates a second condition affecting the frequency of the second maintenance task.

8. The method according to any one of claims 1 to 7, wherein the platform is an aircraft and the sensor data is flight sensor data.

9. A computer-implemented method for improving the accuracy of maintenance plans, the method comprising: For maintenance tasks to be performed on multiple platforms, retrieve planned maintenance data and maintenance data from unplanned services; For high variance or multiple patterns, analyze the distribution of the lifecycle of maintenance tasks in the planned maintenance data and the unplanned service maintenance data; In response to identifying at least one of high variance or multiple patterns in the distribution of the lifetime, identify several conditions in the sensor data of the plurality of platforms that are related to the length of the lifetime of the maintenance task; Based on the aforementioned conditions, the lifespan is divided into multiple groups; and Based on the corresponding lifespan of the maintenance tasks in the respective groups, a corresponding recommended maintenance interval is determined for each of the multiple groups.

10. The computer-implemented method according to claim 9, further comprising: Retrieve the sensor data from the multiple platforms.

11. The computer-implemented method according to claim 9, further comprising: A time point is calculated after which an acceptable amount of sensor data is available for the platform, enabling analysis to be performed to determine whether the aforementioned conditions exist for the platform.

12. The computer-implemented method of claim 11, wherein the time point is a minimum number of cycles.

13. The computer-implemented method according to any one of claims 9 to 12, wherein each of the respective recommended maintenance intervals is a time interval between the execution of the maintenance tasks, the time interval maximizing the probability of detecting anomalies associated with the component set during preventative planned maintenance.

14. An apparatus comprising: Bus system; A communication system coupled to the bus system; and A processor unit coupled to the bus system, wherein the processor unit executes computer-usable program code to retrieve planned maintenance data and unplanned maintenance data for maintenance tasks to be performed for multiple platforms; and performs high-variance or multi-pattern analysis on the distribution of the lifetime of the maintenance tasks in the planned maintenance data and the unplanned maintenance data. In response to identifying at least one of high variance or multiple patterns in the distribution of the lifetime, identify several conditions in the sensor data of the plurality of platforms that are related to the length of the lifetime of the maintenance task; Based on the aforementioned conditions, the lifespan is divided into multiple groups; And by performing customized maintenance planning analysis on each of the plurality of groups, a corresponding recommended maintenance interval is determined for each of the plurality of groups.

15. The device of claim 14, wherein the processor unit further sends the analysis results of the customized maintenance planning analysis performed on the plurality of groups to a regulatory agency for approval.

16. The device of claim 14, wherein the communication system receives the sensor data from the plurality of platforms.

17. The device of claim 14, wherein the processor unit further calculates a time point after which an acceptable amount of sensor data is available to the platform, enabling analysis to be performed to determine whether the certain conditions exist for the platform.

18. The device of claim 17, wherein the time point is a minimum number of cycles.

19. The device according to any one of claims 14-18, wherein each of the respective recommended maintenance intervals is a time interval between the execution of the maintenance task, the time interval maximizing the probability of detecting an anomaly associated with a set of components on the respective platform during preventative planned maintenance.

Images