A method and apparatus for damage progression prediction of an aeroengine
By constructing a damage prediction model and utilizing historical damage datasets and machine learning algorithms, the damage development and remaining life of aero-engine components are predicted, solving the problem of insufficient on-wing life monitoring of aero-engines and realizing effective life prediction and planned maintenance.
Patent Information
- Application Number
- CN202210499994.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-06
- Publication Date
- 2026-02-13
- Estimated Expiration
- 2042-05-06
AI Technical Summary
Existing technologies are unable to effectively monitor the on-wing lifespan of aircraft engines, leading to frequent unplanned launches.
By acquiring historical damage datasets, a damage prediction model is constructed to predict the damage measurements of various components of the aero-engine. Combined with historical data on the deployment of equipment, the remaining on-wing life is predicted.
It enables effective monitoring of the remaining on-wing life of aircraft engines, avoiding flight delays caused by unplanned engine launches.
Smart Images
Figure CN114818503B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of artificial intelligence, and particularly relates to an engine damage development prediction method and device. BACKGROUND
[0002] In the daily maintenance of an engine, periodic borescope inspection is required to be performed through an engine observation hole to confirm the damage condition of important unit bodies and components inside the engine, so as to determine whether the engine meets the next delivery condition.
[0003] However, the periodic borescope inspection cannot meet the in-flight life monitoring of the engine, and often causes unplanned delivery.
[0004] Therefore, how to effectively monitor the in-flight life of the engine is a technical problem to be solved at present. SUMMARY
[0005] In view of the above problems, the present application is proposed to provide an engine damage development prediction method and device which can overcome the above problems or at least partially solve the above problems.
[0006] In a first aspect, the present application provides an engine damage development prediction method, comprising:
[0007] obtaining a historical damage data set of a historical engine, the historical damage data set comprising borescope data, operating state data and repair data;
[0008] obtaining a damage prediction model for predicting engine damage development based on the historical damage data set;
[0009] predicting the damage development of a target engine based on the damage prediction model to obtain damage measurement values of each component of the target engine;
[0010] obtaining historical delivery condition data of the target engine;
[0011] predicting the remaining in-flight life of the target engine based on the historical delivery condition data of the target engine and the damage measurement values of each component.
[0012] Preferably, the damage prediction model for predicting engine damage development is obtained based on the historical damage data set, comprising:
[0013] correcting the historical damage data set;
[0014] training a machine learning model based on the corrected historical damage data set to obtain the damage prediction model for predicting engine damage development.
[0015] Preferably, the training of the machine learning model based on the corrected historical damage data set obtains a damage prediction model for predicting the damage development of the aero-engine, comprising:
[0016] The gradient boosting decision tree model is trained using the corrected historical damage data set to obtain a damage prediction model for predicting the damage development of the aero-engine.
[0017] Preferably, the prediction of the damage development of the target aero-engine based on the damage prediction model obtains the damage measurement values of each component of the target aero-engine, comprising:
[0018] Obtaining target damage data of the target aero-engine;
[0019] Inputting the target damage data into the damage prediction model to obtain the damage measurement values of each component of the target aero-engine.
[0020] Preferably, the prediction of the remaining in-flight life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component comprises:
[0021] Constructing a life prediction model of the remaining in-flight life of the aero-engine based on the historical delivery condition data of the historical aero-engine and the historical damage measurement values of each component;
[0022] Inputting the historical delivery condition data of the target aero-engine and the damage measurement values of each component into the life prediction model of the remaining in-flight life of the aero-engine to obtain the remaining in-flight life of the target aero-engine.
[0023] Preferably, the construction of the life prediction model of the remaining in-flight life of the aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component comprises:
[0024] Based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component, a quantile regression forest method is used to set the quantile to a preset value to construct a life prediction model of the remaining in-flight life of the aero-engine.
[0025] Preferably, the inputting of the historical delivery condition data of the target aero-engine and the damage measurement values of each component into the life prediction model of the remaining in-flight life of the aero-engine to obtain the remaining in-flight life of the target aero-engine comprises:
[0026] Input the historical delivery condition data of the target aero-engine and the damage measurement values of the components into a remaining in-service life prediction model of the aero-engine, to obtain the remaining in-service life of the target aero-engine, wherein the related unit body is a unit body to which the components of the target aero-engine belong.
[0027] Based on the remaining in-service life of the related unit body, the remaining in-service life of the target aero-engine is obtained.
[0028] In a second aspect, the present application further provides an aero-engine damage development prediction device, comprising:
[0029] A first obtaining module is configured to obtain a historical damage data set of a historical aero-engine, wherein the historical damage data set comprises bore probe data, aero-engine operating state data and aero-engine repair data;
[0030] An obtaining module is configured to obtain a damage prediction model for predicting aero-engine damage development based on the historical damage data set;
[0031] A first prediction module is configured to predict the damage development of a target aero-engine based on the damage prediction model, to obtain damage measurement values of components of the target aero-engine;
[0032] A second obtaining module is configured to obtain historical delivery condition data of the target aero-engine;
[0033] A second prediction module is configured to predict the remaining in-service life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components.
[0034] In a third aspect, the present application further provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to realize the method steps described above.
[0035] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program executable by a processor to realize the method steps described above.
[0036] One or more technical solutions in the embodiments of the present application have at least the following technical effects or advantages:
[0037] The application provides a damage development prediction method of an aero-engine, including: obtaining a historical damage data set of a historical aero-engine, the historical damage data set including bore probe data, aero-engine operation state data and aero-engine repair data; obtaining a damage prediction model for predicting aero-engine damage development based on the historical damage data set; predicting damage development of a target aero-engine based on the damage prediction model to obtain damage measurement values of each component of the target aero-engine; obtaining historical delivery situation data of the target aero-engine; and predicting the remaining in-flight life of the target aero-engine based on the historical delivery situation data of the target aero-engine and the damage measurement values of each component, so that the remaining in-flight life of the aero-engine is predicted by predicting the damage development of the aero-engine and combining the historical delivery situation of the aero-engine, and effective monitoring of the remaining in-flight life of the aero-engine is realized. BRIEF DESCRIPTION OF DRAWINGS
[0038] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the application. Furthermore, the drawings are not necessarily drawn to scale and in the drawings:
[0039] Figure 1 A step flow schematic diagram of the damage development prediction method of the aero-engine in the embodiment of the application is shown;
[0040] Figure 2 A structural schematic diagram of the damage development prediction device of the aero-engine in the embodiment of the application is shown;
[0041] Figure 3 A structural schematic diagram of the computer device for realizing the damage development prediction method of the aero-engine in the embodiment of the application is shown. DETAILED DESCRIPTION
[0042] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.
[0043] Embodiment one
[0044] The embodiment of the application provides a damage development prediction method of an aero-engine, as shown in the figure, including: Figure 1
[0045] S101, obtain a historical damage data set of a historical aero-engine, the historical damage data set comprising bore probe data, aero-engine operating state data and engine repair data;
[0046] S102, obtain a damage prediction model for predicting aero-engine damage development based on the historical damage data set;
[0047] S103, predict damage development of a target aero-engine based on the damage prediction model to obtain damage measurement values of each component of the target aero-engine;
[0048] S104, obtain historical delivery condition data of the target aero-engine;
[0049] S105, predict the remaining in-flight life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component.
[0050] In a specific embodiment, the remaining in-flight life of the aero-engine refers to the time from the current time to the next delivery of the aero-engine, and delivery refers to disassembling the engine for repair.
[0051] By effectively monitoring the health status of the aero-engine, the prediction of the remaining in-flight life of the aero-engine is realized.
[0052] First, in S101, the historical damage data set of the historical aero-engine is obtained, although it is a historical damage data set, but in the historical damage data set, not only the bore probe data corresponding to each type of engine, but also the operating state data and repair data of each type of engine are included.
[0053] The bore probe data specifically includes bore probe inspection records, bore probe damage states, etc.
[0054] The operating state data specifically refers to different thrusts of different models (models of aircrafts on which the aero-engine is loaded), routes, segment ratios (such as the number of engine start-stop times, etc.).
[0055] The operating state data includes future operating states and used conditions, wherein the used conditions include engine health states and damage descriptions, and of course, there are other factors which are not described in detail here.
[0056] The used conditions refer to historical repair data and state descriptions of sent damage, and the future operating state is a description of the future state of the engine.
[0057] The repair data specifically refers to repair time, repair method, etc.
[0058] The above data is reorganized on a time axis to form a historical damage data set.
[0059] After obtaining the historical damage data set of the historical aero-engine, S102 is performed to obtain a damage prediction model for predicting the damage development of the aero-engine based on the historical damage data set.
[0060] In the historical damage data set, the bore inspection data, the repair data, and the engine health state in the operating state are taken as input data, and the damage description in the operating state of the engine is taken as output data.
[0061] The historical damage data set may have abnormal points. The input data and the output data are corrected for different abnormal points, a machine learning model is trained based on the corrected historical damage prediction model, and a damage prediction model for predicting the damage development of the aero-engine is obtained.
[0062] The output data, i.e., the damage description in the historical damage data set, satisfies monotonicity without repair, and the abnormal points of the output data are found according to the law of monotonicity, and the abnormal points are corrected by using a nearest neighbor interpolation method, as shown in the following formula:
[0063] M t+v (the to-be-corrected damage measurement value) = M t (t is the minimum distance t + v time)
[0064] If the time characteristic data of the engine operating state in the input data of the historical damage data set is abnormal, a bilinear interpolation method is used for regression correction, as shown in the following formula:
[0065]
[0066] The above correction method can effectively remove the interference caused by manual recording.
[0067] The corrected historical damage data set is input into a machine learning model for training to obtain a damage prediction model for predicting the damage development of the aero-engine.
[0068] The machine learning model can be any machine learning model, and the gradient boosting decision tree model is the optimal model.
[0069] When the gradient boosting decision tree model is used for training, the growth value of the damage measurement value is predicted to predict the damage measurement value itself, as shown in the following formula:
[0070] M (damage measurement value) = ΔM (Growth value of damage measurement value) + M0
[0071] = M0 + Opearte (future operating state) + Health (engine health state) + daamage (damage description)
[0072] + Other (other factors)
[0073] After obtaining the damage prediction model for predicting the damage development of the aero-engine, S103 is performed, and the damage development of the target aero-engine is predicted based on the damage prediction model to obtain the damage measurement values of each component of the target aero-engine.
[0074] The components in the aero-engine can refer to HPT stg1 blade, HPT stg2 hub, HPT stg2 blade under HPT (a unit body), and can also be LPT vane, LPT BLADE under LPC (another unit body), and other components, which are not described in detail here. These components all have the unit body structure.
[0075] When the damage development of the target aero-engine is predicted based on the damage prediction model to obtain the damage measurement values of each component of the target aero-engine, specifically:
[0076] Obtain target damage data of the target aero-engine; input the target damage data into the damage prediction model to obtain the damage measurement values of each component of the target aero-engine.
[0077] The target aero-engine is specifically the aero-engine to be predicted. First, the target damage data of the aero-engine to be predicted is extracted, and the target damage data specifically includes the historical bore data, the used state data and the repair data of the aero-engine to be predicted. By inputting the target damage data into the damage prediction model, the damage measurement values of the target aero-engine are obtained, i.e. the damage state of the future situation.
[0078] The damage state of the future situation is for each component of the aero-engine mentioned above.
[0079] After obtaining the damage measurement values of each target of the target aero-engine, S104 is performed, and the historical delivery situation data of the target aero-engine is obtained.
[0080] The historical delivery situation data refers to the time information, repair situation information and the like recorded by the target aero-engine before the current time.
[0081] Finally, S104, based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component, the remaining in-flight life of the target aero-engine is predicted.
[0082] Before the prediction, a life prediction model for predicting the remaining in-flight life of the aero-engine needs to be obtained.
[0083] Specifically, the historical delivery condition data of the historical aero-engine and the historical damage measurement values of each component are collected, wherein the historical damage measurement values are the damage measurement values predicted by the damage prediction model.
[0084] Based on the historical delivery condition data of the historical aero-engine and the historical damage measurement values of each component, a life prediction model for the remaining in-flight life of the aero-engine is constructed; the historical delivery condition data of the target aero-engine and the damage measurement values of each component are input into the life prediction model for the remaining in-flight life of the aero-engine to obtain the remaining in-flight life of the target aero-engine.
[0085] Wherein, when constructing the remaining in-flight life of the aero-engine, it is specifically constructed by the following way.
[0086] Based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component, a quantile regression forest method is used to construct a life prediction model for the remaining in-flight life of the aero-engine by setting the quantile to a preset value. The preset value of the quantile is a value greater than 75 percentiles, preferably a value of 99 percentiles. By using the value of 99 percentiles, the prediction result is more robust under the condition of small sample data.
[0087] After the life prediction model for the remaining in-flight life of the aero-engine is constructed by the above-mentioned way, the historical delivery condition data of the target aero-engine and the damage measurement values of each component are input into the life prediction model for the remaining in-flight life of the aero-engine to obtain the remaining in-flight life of the target aero-engine. Specifically:
[0088] The historical delivery condition data of the target aero-engine and the damage measurement values of each component are input into the life prediction model for the remaining in-flight life of the aero-engine. First, the remaining in-flight life of the related unit body of the target aero-engine is obtained, which is the unit body to which each component of the target aero-engine belongs; then, based on the remaining in-flight life of the related unit body, the remaining in-flight life of the target aero-engine is obtained.
[0089] Through the damage measurement value of each component of the aero-engine, the residual in-service life of the related unit body can be predicted, and finally, the residual in-service life of the target aero-engine, that is, the time length of the target engine from the next delivery, can be obtained, so as to make preparations in advance and avoid flight delays and other accidents caused by unplanned aero-engine delivery.
[0090] The one or more technical solutions in the embodiments of the present application have at least the following technical effects or advantages:
[0091] The present application provides an aero-engine damage development prediction method, comprising: obtaining a historical damage data set of a historical aero-engine, the historical damage data set comprising: hole probe data, aero-engine operating state data and aero-engine repair data; based on the historical damage data set, obtaining a damage prediction model for predicting aero-engine damage development; based on the damage prediction model, predicting the damage development of a target aero-engine to obtain the damage measurement value of each component of the target aero-engine; obtaining historical delivery condition data of the target aero-engine; based on the historical delivery condition data of the target aero-engine and the damage measurement value of each component, predicting the residual in-service life of the target aero-engine, by predicting the damage development of the aero-engine and combining the historical delivery condition of the aero-engine, the residual in-service life of the aero-engine is predicted, and effective monitoring of the residual in-service life of the aero-engine is realized.
[0092] Embodiment two
[0093] Based on the same inventive concept, the present application also provides an aero-engine damage development prediction device, as shown in Figure 2 , comprising:
[0094] The first acquisition module 201 is configured to acquire a historical damage data set of a historical aero-engine, and the historical damage data set comprises: hole probe data, operating state data and repair data;
[0095] The obtaining module 202 is configured to obtain a damage prediction model for predicting aero-engine damage development based on the historical damage data set;
[0096] The first prediction module 203 is configured to predict the damage development of a target aero-engine based on the damage prediction model to obtain the damage measurement value of each component of the target aero-engine;
[0097] The second acquisition module 204 is configured to acquire historical delivery condition data of the target aero-engine;
[0098] The second prediction module 205 is configured to predict the remaining on-wing life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components.
[0099] In an optional implementation, the obtaining module 202 includes:
[0100] The correction unit is configured to correct the historical damage data set.
[0101] The first obtaining unit is configured to train the machine learning model based on the corrected historical damage data set to obtain a damage prediction model for predicting the damage development of the aero-engine.
[0102] In an optional implementation, the obtaining unit is configured to:
[0103] The gradient boosting decision tree model is trained based on the corrected historical damage data set to obtain the damage prediction model for predicting the damage development of the aero-engine.
[0104] In an optional implementation, the first prediction module 203 includes:
[0105] The obtaining unit is configured to obtain target damage data of the target aero-engine.
[0106] The obtaining unit is configured to input the target damage data into the damage prediction model to obtain the damage measurement values of the components of the target aero-engine.
[0107] In an optional implementation, the second prediction module 205 includes:
[0108] The constructing unit is configured to construct a life prediction model of the remaining on-wing life of the aero-engine based on the historical delivery condition data of the historical aero-engine and the historical damage measurement values of the components.
[0109] The second obtaining unit is configured to input the historical delivery condition data of the target aero-engine and the damage measurement values of the components into the life prediction model of the remaining on-wing life of the aero-engine to obtain the remaining on-wing life of the target aero-engine.
[0110] In an optional implementation, the constructing unit is configured to:
[0111] The life prediction model of the remaining on-wing life of the aero-engine is constructed based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components by using the quantile regression forest method with a preset quantile.
[0112] In one optional implementation, the second obtaining unit includes:
[0113] The first obtaining subunit is used to input the historical delivery data of the target aero-engine and the damage measurement values of each component into the life prediction model of the remaining on-wing life of the aero-engine, so as to obtain the remaining on-wing life of the relevant unit of the target aero-engine, wherein the relevant unit is the unit to which each component of the target aero-engine belongs;
[0114] The second obtaining subunit is used to obtain the remaining on-wing lifetime of the target aero-engine based on the remaining on-wing lifetime of the relevant unit body.
[0115] Example 3
[0116] Based on the same inventive concept, embodiments of the present invention provide a computer device, such as... Figure 3 As shown, it includes a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302. When the processor 302 executes the program, it implements the steps of the above-mentioned damage development prediction method for aero-engines.
[0117] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 306 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.
[0118] Example 4
[0119] Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned damage development prediction method for aero-engines.
[0120] The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems can be used with programs in accordance with the teachings herein, or it can prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will be apparent from the description above. In addition, the present application is not intended to be limited to any particular programming language. It will be appreciated that there are many programming languages that can be used to implement the teachings herein, and any specific language can be chosen for use in this application.
[0121] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order to not obscure the understanding of this description.
[0122] Similarly, it is to be understood that the narrative provided above with respect to the exemplary embodiments of the application sometimes collectively sets forth various features in a single embodiment, drawing, or description of an embodiment in order to streamline the disclosure and aid in the understanding of one or more of the various inventive aspects. The method of this disclosure, however, is not to be interpreted to reflect an intention that the claimed application requires more features than are explicitly recited in each claim. Rather, it is to be understood that the inventive aspects lie in less than all features of a single embodiment disclosed. Accordingly, the claims, as follows, define the scope of the claimed application. In this respect, note that depending on the context, in some cases, the word "comprising" can, in fact, mean "including". Similarly, the word "comprising" can mean "consisting of", and the phrase "consisting of" can mean "consisting exclusively of" or "consisting exactly of". The term "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations. Unless specifically stated otherwise, it is appreciated that throughout this specification discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," "generating," "identifying," "selecting," "solving," "optimizing," "estimating," "recommending," "receiving," "sending," "transmitting," or the like, can refer to actions taken by one or more computing devices or processing devices that manipulate or transform data represented as physical electronic or magnetic quantities within memories, registers, or other information storage devices or combinations thereof. Be it understood, however, that such terms can mclude not only actions or processes performed by a computer system or specific computing device, but also the action or processes performed by a human being using a computing device or a human being using a computing device to assist in the performance of a process or action.
[0123] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and further can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, all combinations of all features disclosed in this specification (including accompanying claims, abstract and drawings) and all processes or units of any methods or apparatuses disclosed so far can be adopted. Unless explicitly stated otherwise, each feature disclosed in this specification (including accompanying claims, abstract and drawings) can be replaced by an alternative feature providing the same, equivalent or similar purpose.
[0124] Furthermore, those skilled in the art will recognize that, while certain embodiments described herein include certain features that are not included in other embodiments, combinations of features of the different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the claims below, any of the claimed embodiments can be used in any combination.
[0125] Various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components of the damage progression prediction apparatus for a gas turbine engine, the computer device according to embodiments of the present application. The present application can also be implemented as a program (e.g., computer program and computer program product) for executing any or all of the methods described herein on a device or apparatus (e.g., computer device). Such a program implementing the present application can be stored on a computer readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or can be available for
[0126] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that one skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of elements or steps other than those listed in a claim. The word 'a' or 'an' preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the word 'at least' followed by a list of one or more members does not exclude additional members of the same class or logical type. The word 'comprising' and 'comprise', and the like, does not exclude the presence of elements or steps other than those listed in a claim. The word "first", "second", "third", and the like, when used in the description and in the claims, does not imply any order or precedence.
Claims
1. A method of damage progression prediction for an aeroengine, characterized in that, The method comprises the following steps: obtaining a historical damage data set of historical aero-engines, wherein the historical damage data set comprises bore-scanning data, operating state data and repair data; obtaining a damage prediction model for predicting damage development of aero-engines based on the historical damage data set; predicting damage development of a target aero-engine based on the damage prediction model to obtain damage measurement values of each component of the target aero-engine; obtaining historical delivery condition data of the target aero-engine; predicting remaining in-flight life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component. The method for predicting remaining in-flight life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of each component comprises the following steps: constructing a life prediction model of remaining in-flight life of aero-engines based on historical delivery condition data of historical aero-engines and historical damage measurement values of each component; inputting the historical delivery condition data of the target aero-engine and the damage measurement values of each component into the life prediction model of remaining in-flight life of aero-engines to obtain remaining in-flight life of the target aero-engine. The method for inputting the historical delivery condition data of the target aero-engine and the damage measurement values of each component into the life prediction model of remaining in-flight life of aero-engines to obtain remaining in-flight life of the target aero-engine comprises the following steps: inputting the historical delivery condition data of the target aero-engine and the damage measurement values of each component into the life prediction model of remaining in-flight life of aero-engines to obtain remaining in-flight life of a relevant unit body of the target aero-engine, wherein the relevant unit body is a unit body to which each component of the target aero-engine belongs; obtaining remaining in-flight life of the target aero-engine based on the remaining in-flight life of the relevant unit body.
2. The method of claim 1, wherein, The method for obtaining a damage prediction model for predicting damage development of aero-engines based on the historical damage data set comprises the following steps: correcting the historical damage data set; training a machine learning model based on the corrected historical damage data set to obtain a damage prediction model for predicting damage development of aero-engines.
3. The method of claim 2, wherein, The method for training a machine learning model based on the corrected historical damage data set to obtain a damage prediction model for predicting damage development of aero-engines comprises the following steps: training a gradient boosting decision tree model based on the corrected historical damage data set to obtain a damage prediction model for predicting damage development of aero-engines.
4. The method of claim 1, wherein, The method for predicting damage development of a target aero-engine based on a damage prediction model to obtain damage measurement values of each component of the target aero-engine comprises the following steps: obtaining target damage data of the target aero-engine; inputting the target damage data into the damage prediction model to obtain damage measurement values of each component of the target aero-engine.
5. The method of claim 1, wherein, The life prediction model of the remaining in-service life of the aero-engine is constructed based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components. The life prediction model of the remaining in-service life of the aero-engine is constructed based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components.
6. An engine damage progression prediction device for an aeroengine, characterized by, The method comprises the steps of: The first obtaining module is configured to obtain a historical damage data set of historical aero-engines, wherein the historical damage data set comprises bore-scanning data, aero-engine operating state data and aero-engine repair data; The obtaining module is configured to obtain a damage prediction model for predicting damage development of aero-engines based on the historical damage data set; The first prediction module is configured to predict damage development of a target aero-engine based on the damage prediction model to obtain damage measurement values of components of the target aero-engine; The second obtaining module is configured to obtain historical delivery condition data of the target aero-engine; The second prediction module is configured to predict the remaining in-service life of the target aero-engine based on the historical delivery condition data of the target aero-engine and the damage measurement values of the components; The second prediction module is further configured to construct a life prediction model of the remaining in-service life of the aero-engine based on historical delivery condition data of historical aero-engines and historical damage measurement values of the components; The historical delivery condition data of the target aero-engine and the damage measurement values of the components are input into the life prediction model of the remaining in-service life of the aero-engine to obtain the remaining in-service life of the target aero-engine; The historical delivery condition data of the target aero-engine and the damage measurement values of the components are input into the life prediction model of the remaining in-service life of the aero-engine to obtain the remaining in-service life of the relevant unit body of the target aero-engine, wherein the relevant unit body is a unit body to which the components of the target aero-engine belong; The remaining in-service life of the target aero-engine is obtained based on the remaining in-service life of the relevant unit body.
7. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method steps of any one of claims 1-5.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method steps of any one of claims 1-5.