Method for solving time-varying failure probability of reverse thrust actuating mechanism of aero-engine based on first failure moment

Abstract

The invention discloses a method for solving the time-varying failure probability of a reverse thrust actuating mechanism of an aero-engine based on the first failure moment, and relates to the technical field of reliability analysis, and the method comprises the steps: obtaining the time-varying failure probability of the reverse thrust actuating mechanism of the aero-engine according to distribution parameters of input variables of the reverse thrust actuating mechanism of the aero-engine; constructing an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuating mechanism; extracting sample points from the alternative sample pool, constructing an initial training set, and constructing an initial Kriging agent model according to the initial training set; newly added training sample points are selected according to the estimation precision of the first failure moment of the engine reverse thrust actuating mechanism, and the Kriging agent model is updated based on the newly added training sample points until the Kriging agent model capable of accurately estimating the first failure moment of the engine reverse thrust actuating mechanism is obtained; and solving the time-varying failure probability of the aero-engine reverse thrust actuating mechanism by using the convergent Kriging agent model. According to the method, the calculation efficiency of the time-varying failure probability is improved.

Description

Background Art

[0002] The time-varying failure probability can quantify the random uncertainty of input variables and the influence of time variables on the safety level of a structural system, and can be used as an important indicator for evaluating the safety level of a structural system. As the mechanical transmission part of an aircraft engine thrust reverser, the thrust reverser actuator realizes the functions of fully opening the thrust reverser during the aircraft landing stage and fully retracting it during the aircraft takeoff stage. During multiple uses, the key transmission parts of the thrust reverser actuator will change due to friction and wear, affecting its motion accuracy and even causing it to jam and fail to fully deploy, thus affecting the safe landing of the aircraft. Therefore, solving the time-varying failure probability of the thrust reverser actuator is crucial for understanding the overall reliability level of the aircraft.

[0003] Among the existing calculation methods for the time-varying failure probability of the thrust reverser actuator, it can be implemented based on a double-loop algorithm; however, this method has problems such as large computational amount and low computational efficiency in the process of solving the time-varying failure probability of the thrust reverser actuator.

[0004] Therefore, there is still a lack of an efficient and accurate method for solving the time-varying failure probability of the thrust reverser actuator in a friction and wear environment.

[0005] It should be noted that the information in the above Background Art section is only used to enhance the understanding of the background of the present invention, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for solving the time-varying failure probability of an aircraft engine thrust reverser actuator based on the first failure time, so as to at least to some extent overcome the problems of large computational amount and low computational efficiency caused by the limitations and defects of the prior art.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions:

[0008] A method for solving the time-varying failure probability of an aircraft engine thrust reverser actuator based on the first failure time, comprising:

[0009] Construct an alternative sample pool for solving the time-varying failure probability of the aircraft engine thrust reverser actuator according to the distribution parameters of the input variables of the aircraft engine thrust reverser actuator;

[0010] Randomly extract sample points from the alternative sample pool to construct an initial training set, and construct an initial Kriging surrogate model under different failure modes according to the initial training set;

[0011] Select the second training sample points according to the estimation accuracy of the first failure moment of the sample points of the aero-engine reverse thrust actuator mechanism, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained;

[0012] Use the convergent Kriging surrogate model to solve the time-varying failure probability of the aero-engine reverse thrust actuator mechanism.

[0013] The construction of an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuator mechanism according to the distribution parameters of the input variables of the aero-engine reverse thrust actuator mechanism includes:

[0014] Obtain the input variables of the aero-engine reverse thrust actuator mechanism and the time interval of interest; wherein, the input variables include the initial radii of 20 pin shafts corresponding to the aero-engine reverse thrust actuator mechanism, and the time interval of interest is the number of uses of the reverse thrust actuator mechanism;

[0015] Calculate the distribution parameters of the input variables; wherein, the distribution parameters include the variable mean and variable standard deviation of the input variables;

[0016] Determine the distribution form of the distribution parameters and determine the probability density function of the input variables;

[0017] Determine the input variable samples according to the probability density function of the input variables and the time interval of interest;

[0018] Construct an alternative sample pool for solving the time-varying failure probability according to the input variable samples.

[0019] The random extraction of sample points from the alternative sample pool, the construction of an initial training set, and the construction of an initial Kriging surrogate model under different failure modes according to the initial training set include:

[0020] Randomly extract a preset number of training sample points from the alternative sample pool;

[0021] Based on the training sample points and the failure modes of the aero-engine reverse thrust actuator mechanism, construct an initial training set under different failure modes; wherein, the failure modes include the first failure mode, the second failure mode,..., the mth failure mode, and m is the number of failure modes of the aero-engine reverse thrust actuator mechanism; the initial training set includes the first initial training set corresponding to the first failure mode, the second initial training set corresponding to the second failure mode,..., and the mth initial training set corresponding to the mth failure mode;

[0022] Construct initial Kriging surrogate models for different failure modes according to the initial training sets under different failure modes and the failure modes of the aero-engine reverse thrust actuator mechanism; the initial Kriging surrogate models include the first initial Kriging surrogate model, the second initial Kriging surrogate model, …, the m-th initial Kriging surrogate model.

[0023] Select second training sample points according to the estimation accuracy of the first failure moment of the sample points of the aero-engine reverse thrust actuator mechanism, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained, including:

[0024] According to the initial Kriging surrogate model, predict the predicted mean value and the predicted standard deviation of the input variable samples in the aero-engine reverse thrust actuator mechanism;

[0025] According to the predicted mean value and the predicted standard deviation, determine the misjudgment probability of the first failure moment of the input variable samples in the aero-engine reverse thrust actuator mechanism, and select second training sample points based on the misjudgment probability of the first failure moment;

[0026] Determine the failure mode to which the second training sample point belongs based on the predicted mean value and the predicted standard deviation of the second training sample point, and add the second training sample point to the training sample set corresponding to the failure mode based on the failure mode to obtain a target training sample set;

[0027] Update the initial Kriging surrogate model based on the target training sample set, and repeat the above steps until a convergent Kriging surrogate model is obtained.

[0028] According to the predicted mean value and the predicted standard deviation, determine the misjudgment probability of the first failure moment of the input variable samples in the aero-engine reverse thrust actuator mechanism, including:

[0029] Determine the connection mode of the failure mode of the aero-engine reverse thrust actuator mechanism; the connection mode of the failure mode includes a series mode or a parallel mode;

[0030] According to the connection mode of the failure mode of the aero-engine reverse thrust actuator mechanism, the predicted mean value and the predicted standard deviation, determine the calculation rule of the misjudgment probability of the first failure moment;

[0031] Substitute the predicted mean value and the predicted standard deviation into the calculation rule to obtain the misjudgment probability of the first failure moment of the aero-engine reverse thrust actuator mechanism.

[0032] Select second training sample points based on the misjudgment probability of the first failure moment, including:

[0033] Determine the probability that the input variable sample causes misjudgment of the first failure time of the reverse thrust actuator mechanism of the aero-engine according to the misjudgment probability of the first failure time;

[0034] Sort the input variable samples based on the probability of misjudgment of the first failure time, and select the second training sample points from the input variable samples in the alternative sample pool based on the sorting result.

[0035] Determine the failure mode to which the second training sample point belongs based on the predicted mean and predicted standard deviation of the second training sample point, including:

[0036] Determine the improved U learning function values of the second training sample point under different failure modes based on the predicted mean and predicted standard deviation of the second training sample point;

[0037] Determine the failure mode to which the second training sample point belongs based on the improved U learning function value.

[0038] Update the initial Kriging surrogate model based on the target training sample set to obtain a converged Kriging surrogate model, including:

[0039] Update the training sample set to which the second training sample point belongs to the failure mode, and obtain the predicted mean and predicted standard deviation of the sample points in the alternative sample pool based on the updated Kriging surrogate model;

[0040] Estimate the misjudgment probability of the first failure time of the alternative sample pool according to the predicted mean and predicted standard deviation;

[0041] Judge whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time;

[0042] If the updated Kriging surrogate model meets the model convergence condition, use the updated Kriging surrogate model as the converged Kriging surrogate model; if the updated Kriging surrogate model does not meet the model convergence condition, loop the model update step until the updated Kriging surrogate model meets the model convergence condition to obtain a converged Kriging surrogate model.

[0043] Judge whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time, including:

[0044] Count the number of sample points N that can accurately judge the first failure time and the first failure time is within the time interval of interest f1 and the number of sample points N that cannot accurately judge the first failure time and the first failure time is within the time interval of interest f2and the number of sample points N2 for which the first failure time cannot be accurately determined;

[0045] According to the said N f1 , N f2 and N2, estimate the maximum estimation error of the time-varying failure probability, and determine whether the updated Kriging surrogate model meets the model convergence condition according to the said maximum estimation error and the maximum estimation error threshold.

[0046] A method for solving the time-varying failure probability of an aero-engine reverse thrust actuator based on the first failure time provided by the present invention. On the one hand, according to the distribution parameters of the input variables of the aero-engine reverse thrust actuator, construct an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuator; then extract sample points from the alternative sample pool to construct an initial training set, and construct an initial Kriging surrogate model under different failure modes according to the said initial training set; then select the second training sample points according to the estimation accuracy of the first failure time of the sample points of the reverse thrust actuator, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained; finally, use the convergent Kriging surrogate model to solve the time-varying failure probability of the reverse thrust actuator; since a convergent Kriging surrogate model can be obtained based on the distribution parameters of the input variables of the aero-engine reverse thrust actuator, and then the time-varying failure probability of the reverse thrust actuator is solved based on the convergent Kriging surrogate model, there is no need to calculate the time-varying failure probability based on the double-loop algorithm, thus solving the problems of large computational amount and poor computational efficiency caused by solving the time-varying failure probability based on the double-loop algorithm, and realizing the improvement of computational efficiency on the basis of reducing the computational amount; on the other hand, since the convergent Kriging surrogate model can be used to solve the time-varying failure probability of the aero-engine reverse thrust actuator, the accuracy of the obtained time-varying failure probability is improved.

[0047] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. Brief Description of the Drawings

[0048] The drawings here are incorporated into the specification and constitute a part of this specification, showing the embodiments in line with the present invention, and are used together with the specification to explain the principles of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0049] Figure 1 Schematically shows a flowchart of a method for solving the time-varying failure probability of an aero-engine reverse thrust actuator based on the first failure time according to an embodiment of the present invention.

[0050] Figure 2 Schematic diagram showing an example of a reverse thrust actuating mechanism model of an aeroengine according to an embodiment of the present invention.

[0051] Figure 3 Schematic diagram showing specific direction examples of 20 pin shafts of input variables of a reverse thrust actuating mechanism of an aeroengine according to an embodiment of the present invention.

[0052] Figure 4 Schematic flow chart showing a method for constructing an initial Kriging surrogate model under different failure modes according to a first training sample point according to an embodiment of the present invention.

[0053] Figure 5 Schematic flow chart showing a method for updating an initial Kriging surrogate model based on a second training sample point to obtain a convergent Kriging surrogate model according to an embodiment of the present invention.

[0054] Figure 6 Schematic diagram showing an example of the time-varying failure probability of a reverse thrust actuating mechanism of an aeroengine according to an embodiment of the invention.

[0055] Figure 7 Schematic block diagram showing a device for solving the time-varying failure probability of a reverse thrust actuating mechanism of an aeroengine based on the first failure moment according to an embodiment of the present invention.

[0056] Figure 8 Schematic diagram showing an electronic device for implementing the method for solving the time-varying failure probability of a reverse thrust actuating mechanism of an aeroengine based on the first failure moment as described above according to an embodiment of the present invention. Detailed implementation manners

[0057] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this invention will be more complete and comprehensive, and the concept of the example embodiments will be fully conveyed to those skilled in the art. The features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present invention. However, those skilled in the art will realize that the technical solutions of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present invention.

[0058] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0059] In this exemplary embodiment, a method for solving the time-varying failure probability of an aero-engine thrust reverser actuator based on the first failure time is first provided. This method can run on a server, a server cluster, a cloud server, etc. Of course, those skilled in the art can also run the method of the present invention on other platforms according to requirements, and no special limitation is made in this exemplary embodiment. Specifically, referring to Figure 1 as shown, the method for solving the time-varying failure probability of an aero-engine thrust reverser actuator based on the first failure time may include the following steps:

[0060] Step S110. Construct an alternative sample pool for solving the time-varying failure probability of the aero-engine thrust reverser actuator according to the distribution parameters of the input variables of the aero-engine thrust reverser actuator;

[0061] Step S120. Randomly extract sample points from the alternative sample pool to construct an initial training set, and construct an initial Kriging surrogate model under different failure modes according to the initial training set;

[0062] Step S130. Select second training sample points according to the first failure time estimation accuracy of the sample points of the aero-engine thrust reverser actuator, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained;

[0063] Step S140. Use the convergent Kriging surrogate model to solve the time-varying failure probability of the aero-engine thrust reverser actuator.

[0064] In the above method for solving the time-varying failure probability of the aero-engine reverse thrust actuator based on the first failure moment, on the one hand, according to the distribution parameters of the input variables of the aero-engine reverse thrust actuator, an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuator is constructed; then sample points are extracted from the alternative sample pool to construct an initial training set, and an initial Kriging surrogate model under different failure modes is constructed according to the initial training set; then, according to the estimation accuracy of the first failure moment of the sample points of the reverse thrust actuator, the second training sample points are selected, and the initial Kriging surrogate model is updated based on the second training sample points until a convergent Kriging surrogate model is obtained; finally, the convergent Kriging surrogate model is used to solve the time-varying failure probability of the reverse thrust actuator; since a convergent Kriging surrogate model can be obtained based on the distribution parameters of the input variables of the aero-engine reverse thrust actuator, and then the time-varying failure probability of the reverse thrust actuator is solved based on the convergent Kriging surrogate model, there is no need to calculate the time-varying failure probability based on the double-loop algorithm, thus the problems of large computational amount and poor computational efficiency caused by solving the time-varying failure probability based on the double-loop algorithm can be solved, and the computational efficiency is improved on the basis of reducing the computational amount; on the other hand, since the convergent Kriging surrogate model can be used to solve the time-varying failure probability of the aero-engine reverse thrust actuator, the accuracy of the obtained time-varying failure probability is improved.

[0065] Next, the method for solving the time-varying failure probability of the aero-engine reverse thrust actuator based on the first failure moment recorded in this embodiment will be explained and described in detail with reference to the accompanying drawings.

[0066] First, the aero-engine reverse thrust actuator model recorded in this embodiment will be explained and described. Specifically, the aero-engine reverse thrust actuator model recorded here can be referred to Figure 2 as shown.

[0067] Second, the input variables of the aero-engine reverse thrust actuator recorded in this embodiment will be explained and described. Specifically, the input variables of the aero-engine reverse thrust actuator may include the initial radii of 20 pin shafts corresponding to the reverse thrust actuator. Specifically, it can be referred to Figure 3 as shown. There are a total of 5 choke valves, and each choke valve has 4 pin shafts, for a total of 20 pin shafts.

[0068] Furthermore, the distribution parameters of the input variables recorded in this embodiment will be explained and described. Specifically, the distribution form and distribution parameters of the input variables of the aero-engine reverse thrust actuator are as shown in Table 1 below:

[0069] Table 1

[0070]

[0071] Specifically, and are the initial radii of the four pin shafts shown in (a), (b), (c), and (d) at the i-th choke door. Based on the content shown in Table 1 above, it can be known that the initial radii of the 20 pin shafts recorded in this embodiment all follow a normal distribution. At the same time, the distribution parameters of the initial pin shaft radius can include the initial radius mean and the initial radius standard deviation. Figure 3

[0072] Next, in combination with Figure 2 and Figure 3 for Figure 1 the time-varying failure probability solution method of the aero-engine reverse thrust actuating mechanism based on the first failure moment shown in is further explained and described. Specifically:

[0073] In step S110, according to the distribution parameters of the input variables of the aero-engine reverse thrust actuating mechanism, an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuating mechanism is constructed.

[0074] In the exemplary embodiment of the present disclosure, first, according to the distribution parameters of the input variables of the aero-engine reverse thrust actuating mechanism, an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuating mechanism is constructed; specifically, the specific construction process of the alternative sample pool can be as follows: First, obtain the input variables of the aero-engine reverse thrust actuating mechanism and the time interval of interest; wherein, the input variables include the initial radii of 20 pin shafts corresponding to the aero-engine reverse thrust actuating mechanism, and the time interval of interest is the number of uses of the reverse thrust actuating mechanism; secondly, calculate the distribution parameters of the input variables; wherein, the distribution parameters include the variable mean and the variable standard deviation of the input variables; then, determine the distribution form of the distribution parameters and determine the probability density function of the input variables; again, according to the probability density function of the input variables and the time interval of interest, determine the input variable samples; finally, according to the input variable samples, construct an alternative sample pool for solving the time-varying failure probability.

[0075] Specifically, in the actual application process, the specific construction process of the alternative sample pool can be as follows: First, according to the joint probability density function f X (x) of the random input variables, a random input variable sample pool S x with a capacity of N x is generated = {x1, x2,..., x N} T ; secondly, for the time interval of interest [0, t e , it is regarded as a variable uniformly distributed in [0, t e to obtain a capacity of N​t Time-variable sample pool Combination S x With S t To form an alternative sample pool for solving the time-varying failure probability

[0076] In step S120, sample points are drawn from the alternative sample pool to construct an initial training set, and an initial Kriging surrogate model under different failure modes is constructed according to the initial training set.

[0077] Specifically, referring to Figure 4 As shown, drawing sample points from the alternative sample pool to construct an initial training set, and constructing an initial Kriging surrogate model under different failure modes according to the initial training set may include the following steps:

[0078] Step S310, draw a preset number of training sample points from the alternative sample pool according to the sampling density function;

[0079] Step S320, based on the training sample points and the failure modes of the aero-engine reverse thrust actuator, construct an initial training set under different failure modes; wherein, the failure modes include the first failure mode, the second failure mode,..., the mth failure mode, and m is the number of failure modes of the aero-engine reverse thrust actuator; the initial training set includes a first initial training set corresponding to the first failure mode, a second initial training set corresponding to the second failure mode,..., and an mth initial training set corresponding to the mth failure mode;

[0080] Step S330, construct an initial Kriging surrogate model under different failure modes according to the initial training set under different failure modes and the failure modes of the aero-engine reverse thrust actuator; the initial Kriging surrogate model includes a first initial Kriging surrogate model, a second initial Kriging surrogate model,..., and an mth initial Kriging surrogate model.

[0081] Hereinafter, steps S310 - S330 will be explained and described. Specifically, in the construction process of the initial Kriging surrogate model, first, N in training sample points can be randomly drawn from the alternative sample pool; wherein, N in can be determined according to actual needs; for example, 10 or 15 or 20 sample points can be drawn; here N in only needs to satisfy a small amount; secondly, according to the failure modes of the aero-engine reverse thrust actuator, construct a corresponding initial training sample set T c(c = 1, 2, ..., m); Meanwhile, m is the number of failure modes of the reverse thrust actuating mechanism; that is, for each failure mode, an initial training sample set needs to be corresponding; assuming the failure modes include the first failure mode, the second failure mode, ..., the m-th failure mode, and m is the number of failure modes of the reverse thrust actuating mechanism; then the initial training sample set includes the first initial sample set corresponding to the first failure mode, the second initial sample set corresponding to the second failure mode, ..., the m-th initial sample set corresponding to the m-th failure mode; further, the initial training sample set constructs an initial Kriging surrogate model; where the initial Kriging surrogate model can also include m; that is, there are as many initial Kriging surrogate models as there are failure modes.

[0082] It should be supplemented here that random sampling can ensure that the selected initial training set can cover the entire parameter space as much as possible, preventing the problem that the accuracy of the obtained Kriging surrogate model is poor due to the training sample points being too concentrated or too dispersed.

[0083] In step S130, according to the estimated accuracy of the first failure time of the sample points of the aero-engine reverse thrust actuating mechanism, select the second training sample points, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained.

[0084] Specifically, referring to Figure 5 as shown, according to the estimated accuracy of the first failure time of the sample points of the aero-engine reverse thrust actuating mechanism, select the second training sample points, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained, which can include the following steps:

[0085] Step S410, according to the initial Kriging surrogate model, predict the predicted mean value and predicted standard deviation of the input variable samples in the aero-engine reverse thrust actuating mechanism;

[0086] Step S420, according to the predicted mean value and predicted standard deviation, determine the misjudgment probability of the first failure time of the input variable samples in the aero-engine reverse thrust actuating mechanism, and select the second training sample points based on the misjudgment probability of the first failure time;

[0087] Step S430, based on the predicted mean value and predicted standard deviation of the second training sample points, determine the failure mode to which the second training sample points belong, and add the second training sample points to the training sample set corresponding to the failure mode based on the failure mode to obtain the target training sample set;

[0088] Step S440: Update the initial Kriging surrogate model based on the target training sample set, and repeat the above steps until a convergent Kriging surrogate model is obtained.

[0089] In an exemplary embodiment, according to the predicted mean value and the predicted standard deviation, the misjudgment probability of the first failure time of the input variable sample in the aeroengine reverse thrust actuator can be determined in the following manner: First, determine the connection mode of the failure modes of the aeroengine reverse thrust actuator; wherein, the connection mode of the failure modes includes a series mode or a parallel mode; then, according to the connection mode of the failure modes of the aeroengine reverse thrust actuator, the predicted mean value, and the predicted standard deviation, determine the calculation rule for the misjudgment probability of the first failure time; finally, substitute the predicted mean value and the predicted standard deviation into the calculation rule to obtain the misjudgment probability of the first failure time of the aeroengine reverse thrust actuator.

[0090] In an exemplary embodiment, the selection of the second training sample point based on the misjudgment probability of the first failure time can be achieved in the following manner: First, according to the misjudgment probability of the first failure time, determine the probability that the input variable sample causes a misjudgment of the first failure time of the aeroengine reverse thrust actuator; secondly, sort the input variable samples based on the probability of causing a misjudgment of the first failure time, and based on the sorting result, select the second training sample point from the input variable samples in the alternative sample pool.

[0091] In an exemplary embodiment, the determination of the failure mode to which the second training sample point belongs based on the predicted mean value and the predicted standard deviation of the second training sample point can be achieved in the following manner: First, based on the predicted mean value and the predicted standard deviation of the second training sample point, determine the improved U learning function values of the second training sample point under different failure modes; secondly, determine the failure mode to which the second training sample point belongs based on the improved U learning function values.

[0092] In an exemplary embodiment, the initial Kriging surrogate model is updated based on a target training sample set to obtain a converged Kriging surrogate model, which can be achieved in the following manner: First, the training sample set of the failure mode to which the second training sample points belong is updated, and based on the updated Kriging surrogate model, the predicted mean and predicted standard deviation of the sample points in the alternative sample pool are obtained; Second, according to the predicted mean and predicted standard deviation, the misjudgment probability of the first failure time of the alternative sample pool is estimated; Then, it is judged whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time; Finally, if the updated Kriging surrogate model meets the model convergence condition, the updated Kriging surrogate model is used as the converged Kriging surrogate model; If the updated Kriging surrogate model does not meet the model convergence condition, the model update step is looped until the updated Kriging surrogate model meets the model convergence condition to obtain a converged Kriging surrogate model.

[0093] In an exemplary embodiment, it can be achieved in the following manner to judge whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time: First, count the number of sample points N that can accurately judge the first failure time and the first failure time is within the time interval of interest f1 , the number of sample points N that cannot accurately judge the first failure time and the first failure time is within the time interval of interest f2 and the number of sample points N2 that cannot accurately judge the first failure time; Second, according to the N f1 , N f2 and N2, estimate the maximum estimation error of the time-varying failure probability, and judge whether the updated Kriging surrogate model meets the model convergence condition according to the maximum estimation error and the maximum estimation error threshold.

[0094] Hereinafter, steps S410 - S440 will be explained and described. Specifically, in the process of updating the initial Kriging surrogate model, it is first necessary to select the second training sample points based on the misjudgment probability of the first failure time of the reverse thrust actuator; Based on this, it is necessary to first calculate the misjudgment probability of the first failure time of the reverse thrust actuator. Specifically, the specific calculation process of the misjudgment probability of the first failure time corresponding to the input variable samples included in the alternative sample pool can be shown in the following formula (1):

[0095]

[0096] where U X (·) is an improved U learning function, which reflects the misjudgment probability of the first failure time of the aero-engine reverse thrust actuator, U X(·) The larger it is, the smaller the misjudgment probability of the first failure moment of the aero-engine reverse thrust actuator mechanism. x ∈ S x is a sample of random input variables. is the improved U-learning function under the series system, and its specific calculation process can be shown in the following formula (2). is the improved U-learning function under the parallel system, and its specific calculation process can be shown in formula (8).

[0097]

[0098] where U s (·,·) is the U-learning function corresponding to the single-mode time-varying performance function of the series system, and its specific calculation process can be shown in the following formula (3). is the minimum moment of the time-varying performance function corresponding to x under the series system within the time interval of interest, and its specific calculation process can be shown in formula (6).

[0099]

[0100] where U c (·,·) (c = 1, 2,..., m) is the U-learning function under the c-th failure mode, and its specific calculation process can be shown in the following formula (4). is the minimum performance function g s (x, t) corresponding to the mode label, and its specific calculation process can be shown in formula (5).

[0101]

[0102] where and respectively represent the mean and standard deviation predicted by the Kriging surrogate model of the c-th failure mode performance function g c (x, t). The mean and standard deviation predicted by the Kriging surrogate model.

[0103]

[0104] where represents the set of mode labels where the state sign(g c (x, t)) at (x, t) is not accurately identified by the current Kriging surrogate model , ( is the complement of c ) represents the set of mode labels where the state sign(g (x, t)) at (x, t) is accurately identified by the current Kriging surrogate model, and φ represents the empty set.

[0105]

[0106] where represents the set of moments when the state sign(g(x, t)) at (x, t) is not accurately identified by the current Kriging surrogate model accurately. represents the set of moments when the state sign(g s (x, t)) at (x, t) is accurately identified by the current Kriging surrogate model accurately. μ s (x, t) is the predicted mean of the Kriging surrogate model of the single-mode time-varying function g(x, t) corresponding to the multi-mode time-varying series system function, and its specific calculation process can be shown as the following formula (7):

[0107]

[0108] where, U p (·, ·) is the U learning function corresponding to the single-mode time-varying function of the parallel system, and its specific calculation process can be shown as the following formula (9). is the minimum moment of the time-varying function corresponding to x under the parallel system within the time interval of interest, and its specific calculation process can be shown as formula (11).

[0109]

[0110] where is the mode label corresponding to the maximum value function g p (x, t), and its specific calculation process can be shown as the following formula (10).

[0111]

[0112] where represents the set of mode labels when the state sign(g c (x, t)) at (x, t) is not accurately identified by the current Kriging surrogate model accurately, represents the set of mode labels when the state sign(g c (x, t)) at (x, t) is accurately identified by the current Kriging surrogate model accurately.

[0113]

[0114] where represents the state sign(g p ​The set of moments when (x,t)) is not accurately identified by the current Kriging surrogate model The set of moments when (x,t)) is accurately identified by the current Kriging surrogate model Denote the state at (x,t) as sign(g p (x,t)) is accurately identified by the current Kriging surrogate model The set of moments. μ p (x,t) is the Kriging surrogate model of the single-mode time-varying function g(x,t) corresponding to the multi-mode time-varying parallel system performance function The predicted mean value, and its specific calculation process can be shown in the following formula (12):

[0115]

[0116] Furthermore, after obtaining the misjudgment probability of the system's first failure moment, the second training sample point (x new ,t new ) can be selected from the alternative sample pool S based on the misjudgment probability of the system's first failure moment; among them, the specific determination process of the second training sample point can be realized by formulas (13)-(14):

[0117]

[0118] Even further, after obtaining the second training sample point, it is also necessary to determine the initial training sample set to which the second training sample point belongs. Specifically, the specific determination process of the initial training sample set can be shown in the following formula (15):

[0119]

[0120] Furthermore, after obtaining the second training sample point and the failure mode of the second training sample point, the second training sample point can be added to the corresponding initial training sample set to obtain the target training sample set That is Finally, based on this target training sample set, the initial Kriging surrogate model is updated to obtain a convergent Kriging surrogate model

[0121] In an exemplary embodiment, during the update process of the initial Kriging surrogate model, it can be based on Update the Kriging surrogate model of the c new th failure mode Calculate the maximum estimation error of the time-varying failure probability of the aero-engine thrust reverser actuator obtained under the current Kriging prediction of the aero-engine thrust reverser actuator Until the corresponding convergence condition is met, a convergent Kriging surrogate model can be obtained Among them Less than 0.05 is selected as the convergence condition The specific calculation process can be shown as the following formula (16):

[0122]

[0123] where N f1 is the number of samples for accurately judging the first failure time and the first failure time is within the time interval of interest. Its specific calculation process can be shown as formula (17). N f2 is the number of samples for which the first failure time cannot be accurately judged and the first failure time is within the time interval of interest. Its specific calculation process can be shown as formula (21). N2 is the number of samples for which the first failure time cannot be accurately judged, specifically the set of random input samples for which the current Kriging surrogate model cannot accurately estimate the first failure time in the number of samples. is the number of samples among those for which the first failure time cannot be accurately judged and the true first failure time is within the time interval of interest. Its value range is

[0124]

[0125] where contains the random input sample points x for which the current Kriging surrogate model can accurately estimate the first failure time. is the failure domain indicator function of the random input variable. Its specific calculation process can be shown as formula (18).

[0126]

[0127] where is the failure domain indicator function of the random input variable under the series system. Its specific calculation process can be shown as formula (19). is the failure domain indicator function of the random input variable under the parallel system. Its specific calculation process can be shown as formula (20).

[0128]

[0129] In step S140, the time-varying failure probability of the aero-engine reverse thrust actuator mechanism is solved using the converged Kriging surrogate model.

[0130] Specifically, the time-varying failure probability P f (0, t e ) of the aero-engine reverse thrust actuator mechanism is solved using the converged Kriging surrogate model. Specifically, it can be achieved through the following formula (22):

[0131] P f (0, t e) = (N f1 + N f2 ) / N x Equation (22)

[0132] where N x is the capacity of the random input variable sample pool.

[0133] So far, the method for solving the time-varying failure probability of the aero-engine thrust reverser actuator based on the first failure time recorded in the embodiments of the present invention has been fully implemented. Next, the method for solving the time-varying failure probability of the aero-engine thrust reverser actuator provided by the embodiments of the present invention will be further illustrated by specific examples. Specifically, in the actual application process, the time interval of interest is t ∈ [0, 2×10 4 .

[0134] For example, a time-varying series system performance function g c (R0, t) (c = 1, 2, 3, 4, 5) shown in the following Equation (23) can be established:[[]]

[0135]

[0136] where is a random input vector composed of the initial radii of 20 pins. g c (R0, t) (c = 1, 2, 3, 4, 5) represents the final lower angle of the c-th blocker door. This time-varying performance function indicates that the failure mode of the thrust reverser actuator is that the final lower angle of any blocker door exceeds the range of 73° ± 0.5°. Further, considering the influence of friction and wear, the actual pin radii and of the thrust reverser actuator will change with time, and their change laws can be shown by the following Equation (24):

[0137]

[0138] Further, the scale N x of the distribution parameter sample pool can be set to 1×10 6 ; further, 20 initial training sample points (the first training sample points) are used to establish the initial training sample set T c (c = 1, 2, 3, 4, 5) of each failure mode, and the initial Kriging surrogate model c is constructed according to T Furthermore, 10, 21, 2, 31, and 6 training sample points (the second training sample points) are respectively added to the training sets T1 - T5 to obtain a convergent Kriging surrogate model At this time Finally, use the converged Kriging surrogate model to solve for the time-varying failure probability of the reverse thrust actuator mechanism; wherein, the obtained time-varying failure probability of the reverse thrust actuator mechanism can be referred to Figure 6 as shown

[0139] The following are the device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For the details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention

[0140] The embodiments of the present invention also provide a device for solving the time-varying failure probability of an aero-engine reverse thrust actuator mechanism based on the first failure moment. Specifically, referring to Figure 7 as shown, the device for solving the time-varying failure probability of an aero-engine reverse thrust actuator mechanism based on the first failure moment may include an alternative sample pool construction module 710, an initial Kriging surrogate model construction module 720, an initial Kriging surrogate model update module 730, and a time-varying failure probability solving module 740. Wherein

[0141] The alternative sample pool construction module 710 can be used to construct an alternative sample pool for solving the time-varying failure probability of the aero-engine reverse thrust actuator mechanism according to the distribution parameters of the input variables of the aero-engine reverse thrust actuator mechanism

[0142] The initial Kriging surrogate model construction module 720 can be used to randomly extract sample points from the alternative sample pool, construct an initial training set, and construct an initial Kriging surrogate model under different failure modes according to the initial training set

[0143] The initial Kriging surrogate model update module 730 can be used to select second training sample points according to the first failure moment estimation accuracy of the sample points of the aero-engine reverse thrust actuator mechanism, and update the initial Kriging surrogate model based on the second training sample points until a converged Kriging surrogate model is obtained

[0144] The time-varying failure probability solving module 740 can be used to solve the time-varying failure probability of the aero-engine reverse thrust actuator mechanism using the converged Kriging surrogate model

[0145] In an exemplary embodiment of the present disclosure, an alternative sample pool for solving the time-varying failure probability of an aeroengine reverse thrust actuating mechanism is constructed according to the distribution parameters of the input variables of the aeroengine reverse thrust actuating mechanism, including: obtaining the input variables of the aeroengine reverse thrust actuating mechanism and the time interval of interest; wherein, the input variables include the initial radii of 20 pin shafts corresponding to the aeroengine reverse thrust actuating mechanism, and the time interval of interest is the number of uses of the reverse thrust actuating mechanism; calculating the distribution parameters of the input variables; wherein, the distribution parameters include the variable mean and variable standard deviation of the input variables; determining the distribution form of the distribution parameters and determining the probability density function of the input variables; determining input variable samples according to the probability density function of the input variables and the time interval of interest; and constructing an alternative sample pool for solving the time-varying failure probability according to the input variable samples.

[0146] In an exemplary embodiment of the present invention, sample points are randomly selected from the alternative sample pool to construct an initial training set, and an initial Kriging surrogate model under different failure modes is constructed according to the initial training set, including: randomly selecting a preset number of training sample points from the alternative sample pool; constructing an initial training set under different failure modes based on the training sample points and the failure modes of the aeroengine reverse thrust actuating mechanism; wherein, the failure modes include a first failure mode, a second failure mode, …, an mth failure mode, and m is the number of failure modes of the aeroengine reverse thrust actuating mechanism; the initial training set includes a first initial training set corresponding to the first failure mode, a second initial training set corresponding to the second failure mode, …, an mth initial training set corresponding to the mth failure mode; constructing an initial Kriging surrogate model under different failure modes according to the initial training sets under different failure modes and the failure modes of the aeroengine reverse thrust actuating mechanism; the initial Kriging surrogate models include a first initial Kriging surrogate model, a second initial Kriging surrogate model, …, an mth initial Kriging surrogate model.

[0147] In an exemplary embodiment of the present invention, second training sample points are selected according to the estimation accuracy of the first failure time of the sample points of the aero-engine reverse thrust actuating mechanism, and the initial Kriging surrogate model is updated based on the second training sample points until a convergent Kriging surrogate model is obtained, including: predicting the predicted mean value and the predicted standard deviation of the input variable samples in the aero-engine reverse thrust actuating mechanism according to the initial Kriging surrogate model; determining the misjudgment probability of the first failure time of the input variable samples in the aero-engine reverse thrust actuating mechanism according to the predicted mean value and the predicted standard deviation, and selecting second training sample points based on the misjudgment probability of the first failure time; determining the failure mode to which the second training sample points belong based on the predicted mean value and the predicted standard deviation of the second training sample points, and adding the second training sample points to the training sample set corresponding to the failure mode based on the failure mode to obtain a target training sample set; updating the initial Kriging surrogate model based on the target training sample set, and repeating the above steps until a convergent Kriging surrogate model is obtained.

[0148] In an exemplary embodiment of the present invention, determining the misjudgment probability of the first failure time of the input variable samples in the aero-engine reverse thrust actuating mechanism according to the predicted mean value and the predicted standard deviation includes: determining the connection mode of the failure modes of the aero-engine reverse thrust actuating mechanism; wherein, the connection mode of the failure modes includes a series mode or a parallel mode; determining the calculation rule of the misjudgment probability of the first failure time according to the connection mode of the failure modes of the aero-engine reverse thrust actuating mechanism and the predicted mean value and the predicted standard deviation; substituting the predicted mean value and the predicted standard deviation into the calculation rule to obtain the misjudgment probability of the first failure time of the aero-engine reverse thrust actuating mechanism.

[0149] In an exemplary embodiment of the present disclosure, selecting second training sample points based on the misjudgment probability of the first failure time includes: determining the probability that the input variable samples cause misjudgment of the first failure time of the aero-engine reverse thrust actuating mechanism according to the misjudgment probability of the first failure time; sorting the input variable samples based on the probability of causing misjudgment of the first failure time, and selecting the second training sample points from the input variable samples in the alternative sample pool based on the sorting result.

[0150] In an exemplary embodiment of the present disclosure, determining the failure mode to which the second training sample points belong based on the predicted mean value and the predicted standard deviation of the second training sample points includes: determining the improved U learning function values of the second training sample points under different failure modes based on the predicted mean value and the predicted standard deviation of the second training sample points; determining the failure mode to which the second training sample points belong based on the improved U learning function values.

[0151] In an exemplary embodiment of the present disclosure, updating the initial Kriging surrogate model based on a target training sample set to obtain a converged Kriging surrogate model includes: updating the training sample set of the failure mode to which the second training sample points belong, and based on the updated Kriging surrogate model, obtaining the predicted mean value and the predicted standard deviation of the sample points in the alternative sample pool; estimating the misjudgment probability of the first failure time of the alternative sample pool according to the predicted mean value and the predicted standard deviation; judging whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time; if the updated Kriging surrogate model meets the model convergence condition, using the updated Kriging surrogate model as the converged Kriging surrogate model; if the updated Kriging surrogate model does not meet the model convergence condition, looping the model update step until the updated Kriging surrogate model meets the model convergence condition to obtain a converged Kriging surrogate model.

[0152] In an exemplary embodiment of the present disclosure, judging whether the updated Kriging surrogate model meets the model convergence condition according to the misjudgment probability of the first failure time includes:

[0153] Counting the number of sample points N that can accurately judge the first failure time and the first failure time is within the time interval of interest f1 and the number of sample points N that cannot accurately judge the first failure time and the first failure time is within the time interval of interest f2 and the number of sample points N2 that cannot accurately judge the first failure time; according to the N f1 , N f2 and N2, estimating the maximum estimation error of the time-varying failure probability, and judging whether the updated Kriging surrogate model meets the model convergence condition according to the maximum estimation error and the maximum estimation error threshold.

[0154] The specific details of each module in the above time-varying failure probability solving device of the aero-engine reverse thrust actuator based on the first failure time have been described in detail in the corresponding time-varying failure probability solving method of the aero-engine reverse thrust actuator based on the first failure time, so they will not be repeated here.

[0155] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0156] In addition, although the steps of the methods in the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all of the shown steps must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0157] In an exemplary embodiment of the present invention, an electronic device capable of implementing the above method is also provided.

[0158] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as "circuitry", "module", or "system".

[0159] The following refers to Figure 8 to describe the electronic device 800 according to this embodiment of the present invention. Figure 8 The shown electronic device 800 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0160] As Figure 8 shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one of the above-mentioned processing units 810, at least one of the above-mentioned storage units 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0161] Among them, the storage unit 820 stores program code, and the program code can be executed by the processing unit 810, so that the processing unit 810 executes the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification. For example, the processing unit 810 can execute as Figure 1Step S110 shown in FIG. 0: Construct an alternative sample pool for solving the time-varying failure probability of the aeroengine thrust reverser actuator according to the distribution parameters of the input variables of the aeroengine thrust reverser actuator; Step S120: Randomly extract sample points from the alternative sample pool to construct an initial training set, and construct an initial Kriging surrogate model under different failure modes according to the initial training set; Step S130: Select second training sample points according to the estimation accuracy of the first failure time of the sample points of the aeroengine thrust reverser actuator, and update the initial Kriging surrogate model based on the second training sample points until a convergent Kriging surrogate model is obtained; Step S140: Use the convergent Kriging surrogate model to solve the time-varying failure probability of the aeroengine thrust reverser actuator.

[0162] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 8201 and / or a cache storage unit 8202, and may further include a read-only storage unit (ROM) 8203.

[0163] The storage unit 820 may further include a program / utilities 8204 having a set (at least one) of program modules 8205. Such program modules 8205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0164] The bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0165] The electronic device 800 may also communicate with one or more external devices 900 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through the input / output (I / O) interface 850. And, the electronic device 800 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 860. As Figure 8As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0166] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a portable hard drive, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0167] In an exemplary embodiment of the present invention, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the methods described in this specification. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0168] The program product for implementing the above method according to the embodiments of the present invention may adopt a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In the present invention, the readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0169] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0170] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0171] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0172] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Matlab, Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0173] In addition, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0174] Those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the present invention. This application is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include known common knowledge or conventional technical means in the technical field not disclosed by the present invention. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A method for solving the time-varying failure probability of an aircraft engine thrust reverser actuator based on the first failure moment, characterized in that: include: According to the distribution parameters of the input variables of the reverse thrust actuating mechanism of the aircraft engine, a candidate sample pool for solving the time-varying failure probability of the reverse thrust actuating mechanism of the aircraft engine is constructed; Randomly extracting sample points from the candidate sample pool to construct an initial training set, and constructing an initial Kriging proxy model under different failure modes based on the initial training set; Selecting a second training sample point according to the estimation accuracy of the first failure moment of the sample point of the reverse thrust actuating mechanism of the aircraft engine, and updating the initial Kriging proxy model based on the second training sample point until a converged Kriging proxy model is obtained; The convergent Kriging surrogate model is used to solve the time-varying failure probability of the thrust reverser actuator of an aero-engine.

2. The method according to claim 1, characterized in that According to the distribution parameters of the input variables of the reverse thrust actuating mechanism of the aircraft engine, an alternative sample pool for solving the time-varying failure probability of the reverse thrust actuating mechanism of the aircraft engine is constructed, including: Obtaining input variables of the reverse thrust actuation mechanism of the aircraft engine and a time interval of interest; wherein the input variables include the initial radii of 20 pins corresponding to the reverse thrust actuation mechanism of the aircraft engine, and the time interval of interest is the number of times the reverse thrust actuation mechanism is used; Calculating the distribution parameters of the input variables; wherein the distribution parameters include the variable mean and variable standard deviation of the input variables; Determining the distribution form of the distribution parameters and determining the probability density function of the input variables; Determining input variable samples according to the probability density function of the input variable and the time interval of interest; Based on the input variable samples, a candidate sample pool for solving the time-varying failure probability is constructed.

3. The method according to claim 1, characterized in that: Randomly extract sample points from the candidate sample pool to construct an initial training set, and construct an initial Kriging proxy model under different failure modes based on the initial training set, including: Randomly extracting a preset number of training sample points from the candidate sample pool; Based on the training sample points and the failure modes of the reverse thrust actuating mechanism of the aircraft engine, initial training sets under different failure modes are constructed; wherein the failure modes include a first failure mode, a second failure mode, ..., an mth failure mode, and m is the number of failure modes of the reverse thrust actuating mechanism of the aircraft engine; the initial training set includes a first initial training set corresponding to the first failure mode, a second initial training set corresponding to the second failure mode, ..., an mth initial training set corresponding to the mth failure mode; According to the initial training sets under different failure modes and the failure modes of the reverse thrust actuating mechanism of the aircraft engine, initial Kriging proxy models under different failure modes are constructed; the initial Kriging proxy models include a first initial Kriging proxy model, a second initial Kriging proxy model, ..., and an mth initial Kriging proxy model.

4. The method according to claim 1, characterized in that: Selecting a second training sample point according to the estimation accuracy of the first failure moment of the sample point of the reverse thrust actuating mechanism of the aircraft engine, and updating the initial Kriging proxy model based on the second training sample point until a converged Kriging proxy model is obtained, including: According to the initial Kriging proxy model, predicting the predicted mean and predicted standard deviation of the input variable samples in the candidate sample pool in the reverse thrust actuating mechanism of the aircraft engine; Determine the probability of misjudgment of the first failure moment of the input variable sample in the reverse thrust actuating mechanism of the aircraft engine according to the predicted mean and the predicted standard deviation, and select a second training sample point based on the probability of misjudgment of the first failure moment; Determine the failure mode to which the second training sample point belongs based on the predicted mean and the predicted standard deviation of the second training sample point, and add the second training sample point to a training sample set corresponding to the failure mode based on the failure mode to obtain a target training sample set; The initial Kriging proxy model is updated based on the target training sample set, and the above steps are repeated until a converged Kriging proxy model is obtained.

5. The method according to claim 4, characterized in that Determining the probability of misjudgment of the first failure moment of the input variable sample in the reverse thrust actuating mechanism of the aircraft engine according to the predicted mean and the predicted standard deviation, including: Determining a connection mode of a failure mode of the reverse thrust actuating mechanism of the aircraft engine; the connection mode of the failure mode includes a series mode or a parallel mode; Determining a calculation rule for the probability of misjudgment of the first failure moment according to the connection mode of the failure mode of the reverse thrust actuating mechanism of the aircraft engine, the predicted mean value and the predicted standard deviation; Substituting the predicted mean and the predicted standard deviation into the calculation rule, the probability of misjudgment of the first failure moment of the reverse thrust actuating mechanism of the aircraft engine is obtained.

6. The method according to claim 4, characterized in that Selecting a second training sample point based on the first failure moment misjudgment probability includes: Determining the probability of misjudgment of the first failure moment of the aircraft engine thrust reverser actuating mechanism caused by the input variable sample according to the misjudgment probability of the first failure moment; The input variable samples are sorted based on the probability of generating a first failure moment misjudgment, and based on the sorting result, a second training sample point is selected from the input variable samples in the candidate sample pool.

7. The method according to claim 4, characterized in that Determining the failure mode to which the second training sample point belongs based on the predicted mean and the predicted standard deviation of the second training sample point includes: Determining an improved U learning function value of the second training sample point under different failure modes based on the predicted mean and predicted standard deviation of the second training sample point; The failure mode to which the second training sample point belongs is determined based on the improved U learning function value.

8. The method according to claim 4, characterized in that The initial Kriging proxy model is updated based on the target training sample set to obtain a converged Kriging proxy model, including: Based on the second training sample point, the training sample set of the corresponding failure mode is updated, and based on the updated Kriging proxy model, the predicted mean and predicted standard deviation of the sample points in the candidate sample pool are obtained; According to the predicted mean and the predicted standard deviation, the probability of misjudgment of the first failure moment of the candidate sample pool is estimated; Judging whether the updated Kriging proxy model meets the model convergence condition according to the misjudgment probability of the first failure moment; If the updated Kriging proxy model meets the model convergence condition, the updated Kriging proxy model is used as a converged Kriging proxy model; if the updated Kriging proxy model does not meet the model convergence condition, the model updating step is looped until the updated Kriging proxy model meets the model convergence condition to obtain a converged Kriging proxy model.

9. The method according to claim 8, characterized in that Judging whether the updated Kriging proxy model meets the model convergence condition according to the first failure moment misjudgment probability includes: Count the number of sample points N that can accurately determine the first failure time and whose first failure time is within the time interval of interest f1 , the number of sample points N that cannot accurately determine the first failure time and whose first failure time is within the time interval of interest f2 And the number of sample points N2 that cannot accurately determine the first failure moment; According to the N f1 、N f2 And N2 estimates the maximum estimation error of the time-varying failure probability, and judges whether the updated Kriging proxy model meets the model convergence condition based on the maximum estimation error and the maximum estimation error threshold.

Images