• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    The invention relates to a method and system for forecasting maintenance operations to be applied to an aircraft engine comprising a plurality of elements followed by damage counters, each damage counter being limited by a ceiling of corresponding damage, characterized in that it comprises: processing means (7) adapted to simulate a consumption of said damage counters (C1-Cm) by iteratively pulling a succession of simulation missions from a database training device (9) containing experience missions, processing means (7) adapted to determine at each iteration a cumulative consumption of each of said damage counters until at least one counter of damage relative to a current simulation mission reaches the ceiling of damage associated with it, - processing means (7) adapted to apply a maintenance strategy on said current simulation mission to determine maintenance indicators representative of the maintenance operations to be provided on the aircraft engine.
    公开号:FR3014952A1
    申请号:FR1362549
    申请日:2013-12-13
    公开日:2015-06-19
    发明作者:Alexandre Anfriani；Julien Alexis Louis Ricordeau
    申请人:SNECMA SAS；
    IPC主号:
    专利说明:

    [0001] TECHNICAL FIELD OF THE INVENTION The present invention relates to the field of maintenance of an aircraft engine. In particular, the invention relates to a method and a system for predicting maintenance operations to be applied to an aircraft engine. The forecast of the maintenance operations on an aircraft engine is determined according to the estimate of the damage or wear of the various elements of the engine.
    [0002] However, the operation of an aircraft engine under conditions that may vary from one flight mission to another, as for example in the case of a military aircraft, does not make it possible to predict in a direct manner the damage to the engine. In this case, the estimate is based on damage counters that are calculated on each mission from flight parameter records.
    [0003] Indeed, an aircraft engine is divided into different modules each having different components. Each component can have several zones or elements to monitor, dimensioning in terms of the lifetime of the component. Subsequently and to simplify the description, we will only talk about components. A damage counter is associated with each component to count the number of actual cycles consumed by the component. In addition, each damage counter is associated with at least one damage ceiling. Different maintenance actions can be performed when one (or more) ceiling (s) is (are) reached. These maintenance actions are described in a maintenance plan and range from no-deposit inspection to replacement of damaged parts to inspections requiring removal. The goal of maintenance management operations is to perform maintenance operations just in time to push the use of parts or components to their maximum operating potential. However, the consumption of damage counters and the speed of these consumptions vary greatly from one mission to another, particularly depending on the type of mission. The damage counters can therefore reach their ceilings at different speeds and therefore at different flights. The maintenance defined from the damage counters may then require relatively close deposits. Indeed, the fact that damage counters can reach their ceilings at different times results in sometimes close removals. These different depositions can thus affect the availability of aircraft on their bases. The object of the present invention is therefore to optimize the maintenance operations on aircraft engines to increase the availability of aircraft while meeting all the requirements and constraints of security.
    [0004] OBJECT AND SUMMARY OF THE INVENTION The present invention relates to a method for predicting maintenance operations to be applied to an aircraft engine or a part of the aircraft engine comprising a plurality of components followed by damage counters, each damage counter being limited by a corresponding damage ceiling, said method comprising the following steps: - simulation of a consumption of said damage counters by iteratively pulling a succession of simulation missions from a database of data. learning, - determining at each iteration a cumulative consumption of each of said damage counters until at least one damage counter relating to a current simulation mission reaches a predetermined value bounded by the ceiling of damage associated with said damage counter, - application of a maintenance strategy on said sim mission current use to determine maintenance indicators representative of the maintenance operations to be provided on the aircraft engine. The simulation of the consumption of the sensors by simply drawing a sequence of missions makes it possible to predict the number and type of maintenance actions according to the committed maintenance strategy defined by the predetermined values associated with the damage ceilings. This simulation principle allows a great flexibility at lower cost of calculation steps and without asking for special knowledge in statistics. Advantageously, the method comprises the following steps: - application of a succession of different maintenance strategies comprising for each application of a current strategy, a determination of cost and availability indicators associated with the current strategy, and a determination of a compromise indicator according to said cost and availability indicators, and comparing the compromise indicators of the different strategies to select an optimum maintenance strategy. This makes it possible to value maintenance strategies by taking into account the variability of the damage counters and to find the best strategies to be applied efficiently. According to a first embodiment, the application of a maintenance strategy comprises the following steps: - estimation of the accumulation of consumption of each of the damage counters up to a fixed number of theft, and - grouping of the maintenance operations associated with damage counters reaching their damage ceilings.
    [0005] Consolidation of maintenance operations improves engine availability. For example, we can do the simulation for a horizon of 2000 flights while consolidating maintenance operations by anticipating actions that would have triggered in the next 50 or 100 flights. According to a second embodiment, the application of a maintenance strategy comprises the following steps: comparing the consumption of the damage counters of said current simulation mission with intermediate thresholds or ceilings lower than the damage ceilings, and - grouping of the maintenance operations associated with the damage counters reaching said intermediate ceilings. Advantageously, the method comprises the following steps: repeating the consumption simulation of the damage counters a plurality of times to determine a set of consumption values associated with each maintenance indicator, and calculating an average of said values of consumption associated with each maintenance indicator. This makes it possible to predict maintenance operations in a more realistic manner and to extract statistical information from them. The learning database includes: - a set of experience missions and the consumption of the potential sensors associated with each of said experience missions, and - a predetermined maintenance plan including the damage ceilings associated with the sensors of the experiment. potential and the corresponding maintenance actions. Advantageously, the learning database also includes mission indicators including a severity indicator for each mission, a flight duration indicator for each mission, and a mission type indicator. This makes it possible to enrich the database and to classify the missions according to the severity, the type or the duration. The missions are thus classified in a relevant way to improve the realism of the random draw. Advantageously, the drawing of said succession of simulation missions is performed randomly on a subset of experience missions belonging to a specific type of mission. This makes it possible to customize the simulation to an aircraft base, a fleet, or specific types of missions. Thus, the maintenance plan can be adapted to the manner in which the aircraft are used. Advantageously, the method includes an update of the database. This makes it possible to have a representative database of future and adaptive missions according to the client.
    [0006] The invention also relates to a maintenance forecasting tool to be applied to a fleet of aircraft engines by applying the maintenance operation forecasting method according to the above characteristics on each of the aircraft engines.
    [0007] The invention also relates to a system for predicting maintenance operations to be applied to an aircraft engine comprising a plurality of components followed by damage counters, each damage counter being limited by a corresponding damage ceiling, said system comprising: - processing means adapted to simulate a consumption of said damage counters by iteratively pulling a succession of simulation missions from a learning database containing experience missions, - processing means adapted to determine at each iteration a cumulative consumption of each of said damage counters until at least one damage counter relating to a current simulation mission reaches a predetermined value bounded by the damage ceiling associated with said damage counter, - processing means adapted to apply a strategy maintenance service on said current simulation mission to determine maintenance indicators representative of the maintenance operations to be provided on the aircraft engine. BRIEF DESCRIPTION OF THE DRAWINGS Other features and advantages of the device and the method according to the invention will emerge more clearly on reading the description given below, by way of indication but without limitation, with reference to the appended drawings in which: FIG. . 1 schematically illustrates a system for predicting maintenance operations to be applied to an engine or part of an engine according to the invention; FIG. 2 schematically illustrates a structure of damage counters of an aircraft engine; FIG. 3 is a flowchart schematically illustrating a method for predicting maintenance operations on an aircraft engine, according to the invention; FIG. 4A schematically illustrates a table comprising a set of experience missions and associated potential sensors; FIG. 4B schematically illustrates a table describing a maintenance plan of an aircraft engine; FIG. 5 is a block diagram illustrating the method of predicting maintenance operations, according to a preferred embodiment of the invention; and - Figs. 6A-6D schematically illustrate two examples of application of the method of the present invention.
    [0008] DETAILED DESCRIPTION OF EMBODIMENTS The general principle of the invention is to predict the consumption of the damage counters of an aircraft engine from a mission database and use this prognosis to apply at best a maintenance strategy for optimizing engine availability and maintenance costs of said engine. Fig. 1 schematically illustrates a system for predicting maintenance operations to be applied to an aircraft engine, according to the invention. Advantageously, the forecasting system 1 is installed in a ground station and comprises a computer system 3 usually comprising input means 5, processing means 7, storage means 9, and output means 11. It will be noted that the storage means 9 may comprise a computer program comprising code instructions adapted to the implementation of the forecasting method according to the invention. This computer program can be executed by the processing means 7 in relation to the storage means 9 and the input and output means 5 and 11.
    [0009] During each flight mission, the aircraft 13 proceeds to the collection and recording of the flight parameters on its embedded computers 15. These data can be downloaded regularly, for example after each mission, to be retrieved by the forecasting system 1 It should be noted that some of this data can also be transmitted to the ground station in real time. The data recovered by the forecasting system 1 are used to determine the consumption of the damage counters 17 (ie to count the actual numbers of cycles seen or consumed by the modules) making it possible to estimate the wear or the damage of the various modules. of the aircraft engine.
    [0010] Fig. 2 schematically illustrates a structure of damage counters of an aircraft engine. The aircraft engine 19 consists of a set of modules A1, A2, A3 each comprising different components B1, B2, B3. Each component can have multiple zones or elements E1-E5 that can be used to size the lifetime of the component. Then, at least one damage counter C1-Cm is associated with each element E1-E5 to count the number of actual cycles consumed by this element. The consumption of each damage counter is limited by at least one damage ceiling characterizing the service life (before failure) of the component followed by the damage counter. Thus, when one or more damage ceilings are reached, maintenance actions described in a table or maintenance plan (see Fig. 4B) should be considered. Fig. 3 is a flow diagram schematically illustrating a method for predicting maintenance operations on an aircraft engine, according to the invention. In step E1, the processing means 7 are adapted to simulate a consumption of C1-Cm damage counters by iteratively pulling a succession of simulation missions from a learning database 31 contained, for example, in FIGS. storage means 9. The learning database 31 contains a set of experience missions and a predetermined maintenance plan. The experience missions include data collected as and when actual flights and is a feedback experience. Fig. 4A schematically illustrates a table comprising a set of experience missions and associated potential sensors.
    [0011] The first column indicates the codes or numbers of the different Ml-Mn missions. The other columns refer to the various Cl-Cm damage counters associated with the different elements of the engine and indicate the consumption of each counter during each mission. The number of cycles or consumption indicated by each meter is for example a measure of the wear or damage of the corresponding component of the engine. Fig. 4B schematically illustrates a table describing a maintenance plan of an aircraft engine. The first column refers to the set of Al-An modules of the engine. The different components B1-B3 of each module are indicated in the second column. The third column refers to the different locations or different elements El-E5 of each component. The fourth column concerns the C1-Cm damage counters associated with the different elements of the engine. The fifth column refers to the S1-Sm damage caps associated with the various C1-Cm damage counters and the sixth column possibly indicates 11-1m inter-inspection intervals for items that can be inspected multiple times before to be replaced. Finally, the seventh column describes the OP1-OPm maintenance operation to be performed on each element or component when the corresponding damage ceiling is reached. Advantageously, the learning database 31 can be enriched by indicators defining the various missions. For example, each Ml-Mn mission may be defined by a severity indicator, a flight duration indicator, and a mission type indicator. The severity indicator represents the overall damage to the mission. For example, the overall damage can be a maximum value of the damage counters, an average value, or a minimum value.
    [0012] The step El thus makes it possible to simulate the consumption of the counters C1-Cm damage by successively simulating different missions from the data from the past contained in the database of learning 31. Each mission is drawn randomly and the consumption of damage counters is deducted from the drawn mission. According to a first variant, the draw is performed completely randomly without any indication of future missions in order to model the aging of an engine or a fleet of engines. According to a second variant, the simulation is carried out in an oriented manner by filtering the learning base and by randomly drawing according to the selected filter. In this case, the simulation is particularised taking into account forecast information of the next missions (type of mission, severity, duration of flight). For example, the draw of the sequence of simulation missions can be carried out randomly on a subset of experience missions that can be selected according to mission severity indicators, and / or flight duration of missions, and / or mission type. In steps E2 and E3, the processing means 7 are adapted to determine at each iteration the accumulation of consumption of each of the damage counters C1-Cm until at least one damage counter relating to a mission of current simulation reaches a predetermined value bounded by the damage ceiling associated with the damage counter. Thus, the predetermined value is less than or equal to the corresponding damage ceiling. The predetermined value is for example determined according to the number of missions and the value of the ceiling of damage.
    [0013] More particularly, for each current simulation mission from step El, the processing means 7 calculate in step E2 the accumulation of consumption of each of the counters C1-Cm damage. Step E3 is a test to check if there is at least one damage counter relating to the current simulation mission that has already reached the predetermined value associated with the ceiling of damage. If the result of the test is negative, it loops back to step El to draw a new current mission. On the other hand, if at least one damage counter has reached the predetermined value, then the following steps E4-E6 are carried out. In steps E4-E6, the processing means 7 are adapted to apply a maintenance strategy to the current simulation mission thereby determining the maintenance operations to be provided on the aircraft engine 19 and maintenance indicators representative of these operations. In particular, in step E4, the maintenance action corresponding to the damage ceiling S 1 reached by the damage counter Ci is determined.
    [0014] In step E5, it is checked whether the maintenance strategy is applicable to the maintenance action of step E4. If yes, we go to step E6 and if not, we loops back to step E1. Finally, in step E6, we apply the maintenance strategy and determine the maintenance indicators. Advantageously, these indicators include the number of depositions and types of depositions. This method thus makes it possible to predict the number and type of maintenance actions according to the strategy engaged for a mission draw sequence. Advantageously, the consumption simulation of the damage counters is repeated a plurality of times to determine a set of consumption values associated with each maintenance indicator. In addition, the processing means 7 are adapted to calculate the average of the consumption values associated with each maintenance indicator. Thus, the renewal a number of times of the steps of FIG. 2 makes it possible to estimate the mean values of the maintenance indicators with precision and also makes it possible to derive statistical information from these values, according to, for example, the Monte Carlo method. Fig. 5 is a block diagram illustrating the method of predicting maintenance operations, according to a preferred embodiment of the invention. This process is advantageously carried out by the prediction system of FIG. 1.
    [0015] This diagram comprises a first part P1 concerning a simulation of a maintenance plan and a second part P2 concerning an optimization of the maintenance strategies. In the first part P1, the blocks B11, B12, B13 and B14 are input data used to predict the consumption of the C1-Cm damage counters and can be derived from the past and possibly filtered according to the planned future missions. The data from the past can be used to complete the learning database 31. Prediction data can be used to refine predictions by providing information on the types, durations and severities of missions, thus refining the use of Learning database 31. More particularly, block B11 relates to the severity data that classify M1-Mn missions according to their severity in terms of consumption of Cl-Cm damage counters. It can be past data and possibly chosen according to the distribution of the missions according to the type of profile of the fleet for example. Block B12 concerns the duration of Ml-Mn missions. This is the flight time of each mission or possibly more detailed information such as take-off time, idle time, etc. Block B13 concerns data making it possible to classify Ml-Mn missions according to their type. These data correspond to the descriptions of the missions of the aircraft such as for example a mission of the type "training", "interception", "refueling", etc. These can be past data or forecasts of future missions. Block B14 relates to the current state of the counters C1-Cm damage. This is the current and past consumption for each damage counter on the same engine. The block B2 is a consumption simulator of the potential sensors Cl-Cm implemented by the processing means 7. At the input, the consumption simulator B2 has the data B11, B12, B13 and B14 corresponding to a list of missions for which the severity, the duration, the type of missions and the current state of the counters Cl-Cm are known. The B2 consumer simulator randomly draws in the training database 31 to derive assignments that coincide or are closest to the input data. We thus draw a succession of missions on a subset of experience missions belonging to a specific class of missions. B2 consumption simulator uses for example filters to pull missions belonging to a certain severity, and / or a certain type of missions and / or around a certain duration. Block B3 represents the output data of the B2 consumption simulator including the consumption forecast of the C1-Cm damage counters for each flight. Thus, at the end of each mission, we have the cumulative consumption of each of the counters of damage. The block B4 is a maintenance simulator implemented by the processing means 7, which compares the consumption accumulations of the damage counters C1-Cm with the predetermined values associated with the damage caps S1-Sm defined in the maintenance plan. (Fig. 4B). If none of the damage counters has reached the predetermined value associated with it, then the current state of the counters (block B14) is updated by update data (block B5) taking account of the aging of the components, and the steps of consumption simulation of the damage counters are then repeated.
    [0016] On the other hand, when at least one of the damage counters has reached the predetermined value, a maintenance strategy (block B6) is applied. For example, in order to improve the availability of the engine, it is possible to apply a strategy of anticipation according to a determined time horizon of the type "anticipation with 50 flights" which makes it possible to estimate the values of the counters of damage in 50 flights. Then, we repeat the consumption simulation steps on the determined horizon and if other damage counters reach the predetermined values associated with them, we group together the associated maintenance actions and determine the number of depositions and the types of depositions. Advantageously, the simulation on the determined horizon is carried out a large number of times (for example, a few tens of thousands of times) in order to estimate the average of the maintenance indicators (number of depositions and types of depositions) with a high accuracy. . At the end of the first part P1 (maintenance simulation), we obtain optimization indicators in addition to the maintenance indicators. The optimization indicators include two indicators: the availability (block B61) of the module or the engine and the cost (block B62) associated with the maintenance. These optimization indicators can be used by the second part P2 of the block diagram to find the best maintenance strategies to apply. The cost indicator is a mono-output or multi-output function which depends on the associated maintenance strategy and which includes the part consumption P and the cost of removal C. For example a weighted cost function J wi and w2 can have the following form: J = wi 'P + w2: C Furthermore, the availability indicator is a function that can be defined as the ratio of the operating time of a module (or the engine) on the number of depositions. Advantageously, the availability indicator can be considered as the operating time achieved divided by the sum of the operating time achieved and the operating time that could have been consumed over the lapse of time when the module is in maintenance.
    [0017] In block B7, the processing means 7 are configured to determine a compromise indicator between cost and availability. The compromise indicator can be defined according to the desirability parameters of the costs and availabilities. For example, an individual desirability as cost or availability (symbolized by Y) can be defined for each target or target determined T as follows: els (Y) - 0 for Y <LSL (Y - LSL'81 T - LSL (USL-Y '82 (1,51-T) 0 for USL <Y for LS1_, Yr1' for T <YUSL where LSL is an acceptable lower limit, USL is an acceptable upper limit, and / 3k, P2 are pre-determined parameters that depend on the application It should be noted that a desirability of 0 represents an unacceptable solution in relation to the objectives, whereas a desirability of 1 indicates the desired maximum performance Advantageously, the cost and availability indicators are combined by defining a global desirability D according to the individual desires of cost c / Ps and availability dgs of the following form: D =, 1dP.sx dr The global desirability D allows to be reduced to a conventional optimization of a single objective . At block B8, the processing means 7 are configured to implement a single-output or multi-output optimization algorithm. In general, a genetic algorithm can be used with selection, crossing and mutation steps. Advantageously, it is possible to add a local optimization of the individuals by a simulated annealing, in particular for the optimization of the parameters of the strategy. In block B9, the processing means 7 is configured to select a new maintenance strategy from a predetermined set of strategies.
    [0018] By way of example, the predetermined set of maintenance strategies comprises a strategy with a fixed horizon and a strategy with intermediate ceilings. A fixed-horizon strategy consists in a prediction of removal relative to a damage counter, to estimate the cumulative consumption of each of the other counters of damage up to a fixed number of theft. Then, the maintenance operations associated with the damage counters reaching their predetermined values are grouped together, which are, for example, equal to the damage ceilings.
    [0019] A strategy with intermediate ceilings consists in choosing predetermined values (called intermediate ceilings) lower than the values of the ceilings of damage. Thus, during a prediction of removal relative to a damage counter of a current simulation mission, the consumption of the other damage counters of the current simulation mission is compared with the corresponding intermediate ceilings. The maintenance operations associated with the damage counters reaching the intermediate ceilings are then grouped together. An intermediate cap of a damage counter can be set according to a given percentage of the damage ceiling associated with the meter. Maintenance strategies are therefore rules of good practice defined by a given structure and parameters. The goal of optimization is to look for the best strategies or combinations of strategies associated with these parameters.
    [0020] In order to test each new strategy, B6 is looped back to be applied by the maintenance simulator (block B4) and the optimization steps are repeated. Thus, a succession of different maintenance strategies is applied. For each application, cost and availability indicators associated with the current strategy are determined. A tradeoff indicator is then determined based on these cost and availability indicators. The tradeoff indicators of the different strategies are compared with each other to select an optimal maintenance strategy. Advantageously, the learning database is updated to adapt to the usual and / or future missions of a specific fleet of aircraft engines. Thus, experience missions initially recorded in the database may be replaced by data representative of the missions performed by each group of aircraft. Figs.
    [0021] 6A-6D schematically illustrate two examples of application of the method of the present invention. In each of the two examples, a cumulative consumption simulation of a set of modules of a new engine is carried out for a forecast horizon of 1400 flights. At the initial time, all damage counters are zero. In addition, the simulation on the selected horizon is carried out at least 1000 times in order to refine the precision of the results. More particularly, Figs.
    [0022] 6A-6B illustrate a first scenario where the 5 maintenances are carried out individually as and when they are triggered. Fig.
    [0023] 6A illustrates the distribution of maintenance operations identified by the corresponding damage counters. It should be noted that the inter-deposit interval can sometimes be very small. In addition, FIG.
    [0024] 6B illustrates the distribution of the number of inspections per depot and indicates 200 individual entries.
    [0025] Figs.
    [0026] 6C-6D illustrate a second scenario where close maintenance is grouped together. Thus, when a maintenance action must be triggered, all the actions that would have triggered in the next 50 flights are anticipated. Indeed, FIG.
    [0027] 6D illustrates a distribution of 140 drop offs, 50 dropouts group several maintenances, which improves the availability of the aircraft compared to the first scenario. Finally, it will be noted that the present invention is a tool that makes it possible to implement the maintenance strategies a priori or according to the current state of an engine or a fleet of engines. In other words, this tool makes it possible to choose the best strategies either by not taking into account the current state of the fleet (i.e. a priori), or taking into account the current state of the fleet in real time.
    权利要求:
    Claims (11)
    [0001]
    REVENDICATIONS1. A method for predicting maintenance operations to be applied to an aircraft engine comprising a plurality of components followed by damage counters, each damage counter being limited by a corresponding damage ceiling, characterized in that comprises the following steps: - simulation of a consumption of said damage counters (Cl-Cm) by iteratively pulling a succession of simulation missions from a learning database (31), - determination at each iteration of a cumulative consumption of each of said damage counters until at least one damage counter relating to a current simulation mission reaches a predetermined value bounded by the damage ceiling associated with said damage counter, - applying a maintenance strategy on said current simulation mission to determine representative maintenance indicators d maintenance operations to be provided on the aircraft engine (19).
    [0002]
    2. Method according to claim 1, characterized in that it comprises the following steps: - application of a succession of different maintenance strategies comprising for each application of a current strategy, a determination of cost and availability indicators associated with the current strategy, and a determination of a tradeoff indicator based on said cost and availability indicators, and - comparison of the tradeoff indicators of the different strategies to select an optimal maintenance strategy.
    [0003]
    3. Method according to claim 1 or 2, characterized in that the application of a maintenance strategy comprises the following steps: estimating the accumulation of consumption of each of the damage counters to a fixed number of flights, and grouping of maintenance operations associated with damage counters reaching their damage ceilings.
    [0004]
    4. Method according to claim 1 or 2, characterized in that the application of a maintenance strategy comprises the following steps: comparison of the consumption of the damage counters of said current simulation mission with intermediate ceilings lower than damage ceilings, and - consolidation of the maintenance operations associated with the damage counters reaching the said intermediate ceilings.
    [0005]
    5. Method according to any one of the preceding claims, characterized in that it comprises the following steps: repeating the consumption simulation of the damage counters a plurality of times to determine a set of consumption values associated with each maintenance indicator, and - calculating an average of said consumption values associated with each maintenance indicator.
    [0006]
    6. Method according to any one of the preceding claims, characterized in that the training database comprises: a set of experience missions and the consumption of the potential sensors associated with each of said experience missions, and a predetermined maintenance plan comprising the damage ceilings associated with the potential sensors and the corresponding maintenance actions.
    [0007]
    7. The method as claimed in claim 6, characterized in that the learning database furthermore comprises mission indicators including a severity indicator of each mission, an indicator of the flight duration of each mission, and an indicator of the type of mission. mission.
    [0008]
    8. Method according to any one of the preceding claims, characterized in that the drawing of said succession of simulation missions is performed randomly on a subset of experience missions.
    [0009]
    9. Method according to any one of the preceding claims, characterized in that it comprises an update of the database.
    [0010]
    A maintenance forecasting tool to be applied to a fleet of aircraft engines according to the method of any one of the preceding claims.
    [0011]
    11. System for forecasting maintenance operations to be applied to an aircraft engine comprising a plurality of elements followed by damage counters, each damage counter being limited by a corresponding damage ceiling, characterized in that it comprises: - processing means (7) adapted to simulate a consumption of said damage counters (Cl-Cm) by iteratively pulling a succession of simulation missions from a learning database (31) containing experience missions, processing means (7) adapted to determine at each iteration a cumulative consumption of each of said damage counters until at least one damage counter relating to a simulation mission current reaches the ceiling of damage associated with it, - processing means (7) adapted to apply a maintenance strategy on said simulation mission neck to determine maintenance indicators representative of the maintenance operations to be provided on the aircraft engine.
    类似技术:
    公开号 | 公开日 | 专利标题
    CA2826641C|2019-01-15|Forecasting maintenance operations for an aircraft engine
    FR3014952A1|2015-06-19|PREDICTION OF MAINTENANCE OPERATIONS TO BE APPLIED TO A MOTOR
    CA2746537C|2017-05-09|Standardization of data used for monitoring an aircraft engine
    EP2912526B1|2017-12-06|System for monitoring a set of components of a device
    CA2874943C|2021-12-14|Forecasting maintenance operations to be applied to an engine
    Zaidan et al.2015|Prognostics of gas turbine engine: An integrated approach
    FR2970358A1|2012-07-13|PROGNOSTIC OF DURATION BEFORE MAINTENANCE BY FUSION BETWEEN MODELING AND SIMULATION, FOR ELECTRONIC EQUIPMENTS ON BOARD IN AN AIRCRAFT
    EP3097455A1|2016-11-30|Method for predicting an operational malfunction in the equipment of an aircraft or aircraft fleet
    WO2015052408A1|2015-04-16|Monitoring of an aircraft engine to anticipate maintenance operations
    US20160093115A1|2016-03-31|Generating Cumulative Wear-Based Indicators for Vehicular Components
    US20180196892A1|2018-07-12|Massively accelerated bayesian machine
    EP3281157B1|2021-03-17|System for mutualizing aircraft engine data
    Dibsdale2015|Holistic prognostics
    FR3035232A1|2016-10-21|SYSTEM FOR MONITORING THE HEALTH CONDITION OF AN ENGINE AND ASSOCIATED CONFIGURATION METHOD
    CN103472392A|2013-12-25|Service life prediction method for electric actuating mechanism
    Daouayry et al.2018|Predictive maintenance for helicopter from usage data: Application to main gear box
    Landowski2010|Applying the Markov decision processes to model changes to the maintenance states of an object
    Robert2019|Health management of industrial vehicles and fleet maintenance optimization: taking into account operation constraints and mission planning
    CN112149844A|2020-12-29|Repair amount prediction method, device, equipment and medium
    FR3095424A1|2020-10-30|System and method for monitoring an aircraft engine
    Pipe2008|Practical prognostics for helicopter CBM
    FR2852417A1|2004-09-17|Ageing pattern/model parameters determining process, involves generating ageing pattern by combining deterministic simulation model and generated probabilistic model and updating pattern parameters
    同族专利:
    公开号 | 公开日
    JP6552500B2|2019-07-31|
    CN105829982B|2019-08-09|
    RU2670937C1|2018-10-25|
    EP3080670A2|2016-10-19|
    WO2015086957A3|2016-06-02|
    RU2670937C9|2018-11-21|
    CA2932933A1|2015-06-18|
    JP2017502193A|2017-01-19|
    WO2015086957A2|2015-06-18|
    FR3014952B1|2016-01-22|
    US11243525B2|2022-02-08|
    CN105829982A|2016-08-03|
    US20160313728A1|2016-10-27|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US20120179326A1|2011-01-06|2012-07-12|Eurocopter|Predicting time to maintenance by fusion between modeling and simulation for electronic equipment on board an aircraft|
    WO2013182823A1|2012-06-08|2013-12-12|Snecma|Forecasting maintenance operations to be applied to an engine|
    US4926362A|1988-04-07|1990-05-15|The United States Of America As Represented By The Secretary Of The Air Force|Airbase sortie generation analysis model |
    JP3392526B2|1994-07-29|2003-03-31|株式会社東芝|Equipment maintenance management support equipment|
    WO1998024042A1|1996-11-27|1998-06-04|Sundstrand Corporation|Method of maintaining components subject to fatigue failure|
    US6408258B1|1999-12-20|2002-06-18|Pratt & Whitney Canada Corp.|Engine monitoring display for maintenance management|
    US7283932B2|2000-07-20|2007-10-16|Albihns Goteborg Ab|Method for estimating damage to an object, and method and system for controlling the use of the object|
    US6980959B1|2000-10-17|2005-12-27|Accenture Llp|Configuring mechanical equipment|
    US6968293B2|2000-12-07|2005-11-22|Juisclan Holding Gmbh|Method and apparatus for optimizing equipment maintenance|
    US20030078708A1|2001-10-18|2003-04-24|Harper David J.|Productivity and reliability enhancement program|
    US8073653B2|2002-12-23|2011-12-06|Caterpillar Inc.|Component life indicator|
    US7627459B2|2004-01-08|2009-12-01|Georgia Tech Research Corporation|Systems and methods for reliability and performability assessment|
    US7487029B2|2004-05-21|2009-02-03|Pratt & Whitney Canada|Method of monitoring gas turbine engine operation|
    US20060111871A1|2004-11-19|2006-05-25|Winston Howard A|Method of and system for representing unscheduled events in a service plan|
    US20080172268A1|2005-01-13|2008-07-17|Standard Aero , Inc.|System and method of enhancing cost performance of mechanical systems including life-limited parts|
    US20060190280A1|2005-02-22|2006-08-24|Lockheed Martin Corporation|Method and apparatus for management for use in fleet service and logistics|
    US20070118502A1|2005-11-18|2007-05-24|Aragones James K|Methods and systems for managing a fleet of assets|
    US10248914B2|2005-11-29|2019-04-02|The Boeing Company|Sustaining a fleet of configuration-controlled assets|
    JP4699344B2|2005-12-07|2011-06-08|三菱重工業株式会社|Equipment maintenance planning method for plant equipment|
    US20100262442A1|2006-07-20|2010-10-14|Standard Aero, Inc.|System and method of projecting aircraft maintenance costs|
    US7702436B2|2006-09-29|2010-04-20|Standard Aero , Inc.|System and method of troubleshooting aircraft system failures|
    US8620714B2|2006-11-28|2013-12-31|The Boeing Company|Prognostic condition assessment decision aid|
    US8560376B2|2007-05-31|2013-10-15|Airbus Operations S.A.S.|Method, system, and computer program product for a maintenance optimization model|
    FR2917715B1|2007-06-20|2009-12-25|Eurocopter France|METHOD AND DEVICE FOR MONITORING AND CONTROLLING A GYRANE TURBOMOTOR|
    US20100250448A1|2007-10-09|2010-09-30|Towe Eric S|Logistics, maintenance, and operations data visualization system and method|
    US8112368B2|2008-03-10|2012-02-07|The Boeing Company|Method, apparatus and computer program product for predicting a fault utilizing multi-resolution classifier fusion|
    FR2934397A1|2008-07-28|2010-01-29|Eurocopter France|IMPROVED METHOD FOR ORGANIZING AIRCRAFT MAINTENANCE|
    FR2935186B1|2008-08-20|2010-09-17|Airbus France|METHOD AND DEVICE FOR AIDING THE DIAGNOSIS AND DECISION TO OPERATE AN AIRCRAFT|
    US20100063933A1|2008-09-09|2010-03-11|Eurocopter|Method of optimizing the availability of an aircraft or of a fleet of aircraft|
    US8117007B2|2008-09-12|2012-02-14|The Boeing Company|Statistical analysis for maintenance optimization|
    DE102008049170C5|2008-09-26|2020-04-09|MTU Aero Engines AG|Device and method for monitoring the service life|
    US8165826B2|2008-09-30|2012-04-24|The Boeing Company|Data driven method and system for predicting operational states of mechanical systems|
    US20100217638A1|2009-02-23|2010-08-26|Bae Systems Information And Electronic Systems Integration, Inc.|In service support center and method of operation|
    US20160005242A1|2009-03-05|2016-01-07|United States Government As Represented By The Secretary Of The Navy|Predictive Automated Maintenance System |
    US8340948B1|2009-09-29|2012-12-25|The Boeing Company|Fleet performance optimization tool for aircraft health management|
    GB0917527D0|2009-10-07|2009-11-25|Optimized Systems And Solution|Asset management system|
    US8868284B2|2009-11-12|2014-10-21|Sikorsky Aircraft Corporation|Virtual monitoring of aircraft fleet loads|
    JP2011165047A|2010-02-12|2011-08-25|Mitsubishi Heavy Ind Ltd|Maintenance planning system, maintenance planning apparatus, control method, and program|
    US8355830B2|2010-03-30|2013-01-15|Aurora Flight Sciences Corporation|Aircraft health monitoring and design for condition|
    US9167339B2|2010-07-07|2015-10-20|Iii Holdings 4, Llc|Hearing damage limiting headphones|
    FR2971595B1|2011-02-15|2013-03-22|Snecma|MONITORING AN AIRCRAFT ENGINE TO ANTICIPATE MAINTENANCE OPERATIONS|
    FR2972025B1|2011-02-25|2016-03-04|Snecma|PREDICTION OF MAINTENANCE OPERATIONS ON AN AIRCRAFT ENGINE|
    US8781982B1|2011-09-23|2014-07-15|Lockheed Martin Corporation|System and method for estimating remaining useful life|
    US8560368B1|2011-11-18|2013-10-15|Lockheed Martin Corporation|Automated constraint-based scheduling using condition-based maintenance|
    US8782467B2|2012-02-01|2014-07-15|Honeywell International Inc.|Systems and methods for creating a near optimal maintenance plan|
    US8959065B2|2012-04-09|2015-02-17|Mitek Analytics, LLC|System and method for monitoring distributed asset data|
    WO2014047555A1|2012-09-21|2014-03-27|Enphase Energy, Inc.|Method and apparatus for scheduling maintenance of alternative energy systems|
    CN103020422A|2012-11-12|2013-04-03|中航沈飞民用飞机有限责任公司|Method for calculating maintenance time interval of civil aircraft system|
    US20140244328A1|2013-02-22|2014-08-28|Vestas Wind Systems A/S|Wind turbine maintenance optimizer|
    CN103399994B|2013-07-23|2016-09-28|中国人民解放军海军航空工程学院|Military aircraft regular inspection flow optimization method based on probabilistic network scheduling technology|
    EP3127089A4|2014-04-02|2017-10-04|Sikorsky Aircraft Corporation|System and method for health assessment of aircraft structure|
    EP3173762B1|2015-11-25|2020-03-18|Sikorsky Aircraft Corporation|Systems and methods for fatigue monitoring|GB201608047D0|2016-05-09|2016-06-22|Rolls Royce Plc|Component lifing|
    US10234359B2|2016-05-23|2019-03-19|United Technologies Corporation|Gas turbine engine with lifing calculations based upon actual usage|
    US11180265B2|2016-12-02|2021-11-23|General Electric Company|Control system and method|
    US10384808B2|2016-12-02|2019-08-20|General Electric Company|Control system and method|
    JP6720101B2|2017-02-27|2020-07-08|三菱重工業株式会社|Aircraft management device, method and program|
    CN110057590B|2019-04-15|2021-05-07|中国航发湖南动力机械研究所|Aircraft engine outfield data management system and method facing machine group|
    法律状态:
    2015-12-15| PLFP| Fee payment|Year of fee payment: 3 |
    2016-12-05| PLFP| Fee payment|Year of fee payment: 4 |
    2017-11-21| PLFP| Fee payment|Year of fee payment: 5 |
    2018-02-09| CD| Change of name or company name|Owner name: SAFRAN AIRCRAFT ENGINES, FR Effective date: 20170717 |
    2019-11-20| PLFP| Fee payment|Year of fee payment: 7 |
    2020-11-20| PLFP| Fee payment|Year of fee payment: 8 |
    2021-11-18| PLFP| Fee payment|Year of fee payment: 9 |
    优先权:
    申请号 | 申请日 | 专利标题
    FR1362549A|FR3014952B1|2013-12-13|2013-12-13|PREDICTION OF MAINTENANCE OPERATIONS TO BE APPLIED TO A MOTOR|FR1362549A| FR3014952B1|2013-12-13|2013-12-13|PREDICTION OF MAINTENANCE OPERATIONS TO BE APPLIED TO A MOTOR|
    EP14821787.0A| EP3080670A2|2013-12-13|2014-12-03|Forecasting maintenance operations to be applied to an engine|
    JP2016536978A| JP6552500B2|2013-12-13|2014-12-03|Predicting maintenance work to be done on aircraft engines|
    US15/102,455| US11243525B2|2013-12-13|2014-12-03|Forecasting maintenance operations to be applied to an engine|
    PCT/FR2014/053148| WO2015086957A2|2013-12-13|2014-12-03|Forecasting maintenance operations to be applied to an engine|
    CN201480067272.1A| CN105829982B|2013-12-13|2014-12-03|For predicting that the method and system of the attended operation of aero-engine will be applied to|
    RU2016126807A| RU2670937C9|2013-12-13|2014-12-03|Forecasting maintenance operations to be applied to an engine|
    CA2932933A| CA2932933A1|2013-12-13|2014-12-03|Forecasting maintenance operations to be applied to an engine|
    [返回顶部]