CN114912675A - Prediction method and device for scrappage of aero-engine blade - Google Patents

Prediction method and device for scrappage of aero-engine blade Download PDF

Info

Publication number
CN114912675A
CN114912675A CN202210486431.8A CN202210486431A CN114912675A CN 114912675 A CN114912675 A CN 114912675A CN 202210486431 A CN202210486431 A CN 202210486431A CN 114912675 A CN114912675 A CN 114912675A
Authority
CN
China
Prior art keywords
blade
predicting
rejection rate
blades
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210486431.8A
Other languages
Chinese (zh)
Inventor
王可也
丁天璇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Shanshu Network Technology Co ltd
Shanshu Science And Technology Suzhou Co ltd
Shanshu Science And Technology Beijing Co ltd
Shenzhen Shanzhi Technology Co Ltd
Original Assignee
Shanghai Shanshu Network Technology Co ltd
Shanshu Science And Technology Suzhou Co ltd
Shanshu Science And Technology Beijing Co ltd
Shenzhen Shanzhi Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Shanshu Network Technology Co ltd, Shanshu Science And Technology Suzhou Co ltd, Shanshu Science And Technology Beijing Co ltd, Shenzhen Shanzhi Technology Co Ltd filed Critical Shanghai Shanshu Network Technology Co ltd
Priority to CN202210486431.8A priority Critical patent/CN114912675A/en
Publication of CN114912675A publication Critical patent/CN114912675A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Geometry (AREA)
  • Evolutionary Computation (AREA)
  • Human Resources & Organizations (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • General Health & Medical Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Computer Hardware Design (AREA)
  • Primary Health Care (AREA)
  • Pure & Applied Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for predicting the scrappage of an aircraft engine blade, wherein the method comprises the following steps: obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data condition and the historical rejection rate of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades; obtaining the blade type of an aeroengine blade to be predicted, wherein the blade type comprises a common blade and a hot-end key blade; based on the blade type and the prediction model, the rejection rate of the part to which the aero-engine blade is to be predicted is predicted, prediction results of the rejection rates of different parts are obtained for different parts, and therefore a certain guiding effect can be provided for predicting repair cost.

Description

Prediction method and device for scrappage of aero-engine blade
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for predicting the scrappage of an aircraft engine blade.
Background
The blade of the aero-engine is an important part of the aero-engine and also a key inspection object for factory maintenance, and when the single blade does not reach the corresponding factory standard, the blade needs to be scrapped and replaced.
Wherein, the blades at the hot end are expensive and the replacement cost is relatively high.
Therefore, how to effectively predict the rejection rate of the blade before repair is a technical problem to be solved urgently at present.
Disclosure of Invention
In view of the above, the present invention has been made in order to provide a method and a device for predicting the scrappage of an aircraft engine blade that overcome or at least partially solve the above problems.
In a first aspect, the present invention further provides a method for predicting an aircraft engine blade rejection rate, including:
obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data condition and the historical rejection rate of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades;
obtaining blade types of blades of a target component of an aeroengine to be predicted, wherein the blade types comprise common blades and hot end key blades;
and predicting the rejection rate of the target part of the aircraft engine to be predicted based on the blade type and the prediction model.
Further, the obtaining of the prediction model for predicting the rejection rate of the aircraft engine blade based on the historical usage data and the historical rejection rate of the plurality of groups of historical aircraft engine blades includes:
taking common blades belonging to the same name type in the multiple groups of historical aviation engine common blades as an integral object, and obtaining a first prediction model for predicting the rejection rate of the common blades based on the historical use data condition and the rejection rate of the integral object of the multiple groups of historical aviation engines;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the hot end key blades of the multiple groups of historical aero-engines.
Further, the step of taking the common blades belonging to the same name in the multiple groups of historical common blades of the aircraft engine as an overall object, and obtaining a first prediction model for predicting the rejection rate of the common blades based on the historical use data condition and the rejection rate of the overall object of the multiple groups of historical aircraft engines includes:
taking common blades belonging to the same name type in the multiple groups of historical aviation engine common blades as an integral object as input data of a training sample;
clustering the rejection rates of the whole objects of the multiple groups of historical aero-engines by adopting a clustering algorithm to obtain the processed rejection rates as output data of the training samples;
based on the input data and the output data, a first prediction model for predicting the rejection rate of the common blade is obtained.
Further, the obtaining a first prediction model for predicting the rejection rate of the common blade based on the input data and the output data includes:
inputting the input data and the output data into a combined integrated algorithm model, wherein the combined integrated algorithm model comprises a random forest algorithm model and a self-adaptive enhancement algorithm model to obtain an optimal algorithm model;
and taking the optimal algorithm model as a first prediction model for predicting the rejection rate of the common blade.
Further, the obtaining a second prediction model for predicting the rejection rate of hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aircraft engine includes:
determining missing data from the historical use data conditions and the rejection rates of the multiple groups of historical aviation engine hot end key blades, and filling the missing data by adopting a KNN algorithm;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aero-engine after filling.
Further, the predicting the rejection rate of the target component of the aircraft engine to be predicted based on the blade type and the prediction model comprises:
when the blade type is a common blade, predicting the rejection rate of a first target component to which the common blade of the aero-engine to be predicted belongs based on the first prediction model;
and when the type of the blade is a hot end key blade, predicting the rejection rate of a second target component to which the hot end key blade of the aero-engine to be predicted belongs based on the second prediction model.
Further, when a hot end key blade of the blade type is used, predicting the rejection rate of a second target component to which the hot end key blade of the aircraft engine to be predicted belongs based on the second prediction model includes:
when the type of the blade is a hot end key blade, inputting the service condition data of each hot end key blade in a second target component to which the hot end key blade of the aero-engine to be predicted belongs into the second prediction model to obtain the rejection rate of each hot end key blade;
and obtaining the rejection rate of the second target component of the hot end key blade of the aero-engine to be predicted through mathematical expectation and weighted average calculation based on the rejection rate of each hot end key blade.
In a second aspect, the present invention further provides an apparatus for predicting the scrappage of an aircraft engine blade, including:
the obtaining module is used for obtaining a prediction model for predicting the rejection rate of the aero-engine blades based on the historical use data conditions and the historical rejection rates of a plurality of groups of historical aero-engine blades, and the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades;
the device comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring the blade type of a blade of a target component of the aeroengine to be predicted, and the blade type comprises a common blade and a hot end key blade;
and the prediction module is used for predicting the rejection rate of the target part of the aero-engine to be predicted based on the blade type and the prediction model.
In a third aspect, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned method steps when executing the program.
In a fourth aspect, the invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method steps.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a method for predicting the scrappage of an aero-engine blade, which comprises the following steps: obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data condition and the historical rejection rate of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades; obtaining the blade type of an aeroengine blade to be predicted, wherein the blade type comprises a common blade and a hot-end key blade; based on the blade type and the prediction model, the rejection rate of the part to which the aero-engine blade is to be predicted is predicted, prediction results of the rejection rates of different parts are obtained for different parts, and therefore a certain guiding effect can be provided for predicting repair cost.
Drawings
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 drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating steps of a method for predicting the scrappage of an aircraft engine blade according to an embodiment of the invention;
FIG. 2 is a schematic structural diagram of a prediction device for the rejection rate of an aircraft engine blade according to an embodiment of the invention;
fig. 3 shows a schematic structural diagram of a computer device for implementing the prediction method of the aircraft engine blade rejection rate in the embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
The embodiment of the invention provides a method for predicting the scrappage of an aircraft engine blade, which comprises the following steps of:
s101, obtaining a prediction model for predicting the rejection rate of the aero-engine blades based on the historical use data conditions and the historical rejection rates of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades;
s102, obtaining blade types of the aeroengine blade to be predicted, wherein the blade types comprise a common blade and a hot-end key blade;
s103, predicting the rejection rate of the part to which the blade of the aero-engine to be predicted belongs based on the blade type and the prediction model.
In particular embodiments, the aero-engine blades are divided into two categories, one being normal blades and the other being hot-end accent blades.
Common blades, for example: low pressure turbine stator blades, low pressure turbine rotor blades, and the like.
Hot end key blades, for example: high pressure turbine rotor blades, high pressure turbine stator blades, fan unit rotor blades, and the like.
Firstly, in S101, corresponding prediction models are obtained by training different types of aero-engine blades, respectively. The method comprises the steps that common blades belonging to the same name type in multiple groups of historical aviation engine common blades are taken as an integral object, and a first prediction model for predicting the rejection rate of the common blades is obtained based on the historical use data condition and the rejection rate of the integral object of each group of historical aviation engines; and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the hot end key blades of the multiple groups of historical aero-engines.
Specifically, for a common blade, the blades belonging to the same name type are taken as an integral object, and of course, a plurality of blades of the same name type correspond to integral objects of a plurality of groups of historical aero-engines. That is to say, for the common leaves, the leaves with the same name type are used as an integral object to train the machine learning model so as to obtain a first prediction model for predicting the rejection rate of the common leaves.
Firstly, common blades belonging to the same name type in a plurality of groups of historical aviation engine common blades are taken as an integral object and taken as input data of a training sample; clustering the rejection rates of the whole objects of the multiple groups of historical aero-engines by adopting a clustering algorithm to obtain the processed rejection rates as output data of training samples; finally, based on the input data and the output data, a first prediction model for predicting the rejection rate of the normal blade is obtained.
When the clustering algorithm is adopted to cluster the rejection rates of the whole objects of the multiple groups of historical aircraft engines, the K-means algorithm is specifically adopted to perform clustering, the K value is tried from 6 to the next until the result is stable, the obtained clustering centers are {0.011,0.24,0.55 and 0.94}, and after the normalization processing, the determined clustering centers are {0.01,0.25,0.50 and 0.95 }.
For a data set formed by historical use data conditions and historical rejection rates of multiple groups of historical aviation engine common blades, K-Fold cross validation is adopted, the data set is divided into 5 groups, and training and testing are performed in a mode that one group is selected as a test and other groups are selected as training sets each time, so that the accuracy of the model is improved.
The model adopted in the training process is a joint integration algorithm model, and the joint integration algorithm model comprises the following steps: a random forest algorithm model and a self-adaptive enhancement algorithm model.
And inputting the input data and the output data into the combined integrated algorithm model to obtain an optimal algorithm model.
Specifically, when input data and output data are input into the combined integrated algorithm model for training, a random forest algorithm and a self-adaptive enhancement algorithm are respectively used for predicting the rejection rate of common blades so as to obtain an optimal algorithm model.
The mean square error of the two algorithm models is obtained respectively, so that the algorithm model with the minimum Mean Square Error (MSE) is obtained, and the optimal algorithm model is obtained.
After the optimal algorithm model is obtained, the parameters are adjusted by using network search according to two parameters, namely max _ depth (maximum depth) and min _ sample _ leaf (minimum limit), so that the generalization error is minimum, and the optimal parameters of the optimal algorithm model are obtained.
And through changing different groups of test set and training set combinations, repeating the process of searching the optimal algorithm model, and taking the finally obtained optimal algorithm model as a first prediction model for predicting the rejection rate of the common blade.
The above is the step of obtaining the first prediction model, and next, the process of obtaining the second prediction model will be described.
Firstly, determining missing data from historical use data conditions and rejection rates of key blades at hot ends of multiple groups of historical aero-engines, and filling the missing data by adopting a KNN algorithm;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aero-engine after filling.
The hot end key blade is a blade at the hot end of the engine, and the blade is more easily damaged because the blade runs in the hot end component. Thus, blades of different duration of use exist in the same component.
For the sample data of the hot-end key blade, because the sample data of the hot-end key blade has missing data, in order to complement the missing data, the missing data is determined from the historical use data condition and the rejection rate of the hot-end key blades of the multiple groups of historical aeroengines, and then the missing data is filled by adopting a KNN algorithm. The method comprises the steps of searching k nearest samples of missing data, and filling the missing data by counting the categories with the most appearance so as to supplement the missing data in the hot-end key blade set of the engine.
For a hot-end key blade, the sample data is more detailed than that of a common blade, including the number of times of entering the hot-end key blade.
After missing data is supplemented, based on historical use data conditions and rejection rates of multiple groups of historical aviation engine starting end key blades after filling, a gradient descent number algorithm is adopted, through multiple iterations, each iteration generates a weak classifier, each classifier is trained on the basis of residual errors of the last classifier, and finally a strong classifier is constructed through weighted combination of a large number of weak classifiers for prediction.
Thereby, a second prediction module for predicting the rejection rate of hot end key blades is obtained.
Then, S102 is executed, and the blade type of the blade of the target component of the aircraft engine to be predicted is obtained, wherein the blade type comprises a common blade and a hot-end key blade.
This step can distinguish the type of blade directly from its name.
After determining the blade type of the blade of the target component of the aero-engine to be predicted, S103 is executed, and based on the blade type and the prediction model, the rejection rate of the target component of the aero-engine to be predicted is predicted.
Specifically, when the blade type is a common blade, predicting the rejection rate of a first target component to which the common blade of the aero-engine to be predicted belongs based on the first prediction model; and when the type of the blade is a hot-end key blade, predicting the rejection rate of a second target component to which the hot-end key blade of the aero-engine to be predicted belongs based on the second prediction model.
For the common blade, the use condition data of each blade in the first target component is directly input into the first prediction model, and the rejection rate result of the first target component to which the common blade of the aircraft engine belongs can be obtained.
For the hot end key blade, inputting the service condition data of each hot end key blade in a second target component to which the hot end key blade of the aero-engine to be predicted belongs into a second prediction model to obtain the rejection rate of each hot end key blade;
and obtaining the rejection rate of the second target component of the hot end key blade of the aero-engine to be predicted through mathematical expectation and weighted average calculation based on the rejection rate of each hot end key blade.
The weighted average calculation is as follows:
Figure BDA0003629330200000081
blade (i) refers to each hot end focus blade in the second target component. prob blade(i) The rejection rate of each hot end key blade is obtained by solving the mathematical expectation and then weighting the average of each hot end key blade in the second target component, so that the rejection rate of the second target component of the hot end key blade of the aircraft engine to be predicted is obtained.
After the rejection rate of the target part of the aircraft engine to be predicted is obtained, the replacement cost of the repaired blade can be reasonably estimated.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a method for predicting the scrappage of an aero-engine blade, which comprises the following steps: obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data condition and the historical rejection rate of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades; obtaining the blade type of an aeroengine blade to be predicted, wherein the blade type comprises a common blade and a hot-end key blade; based on the blade type and the prediction model, the rejection rate of the part to which the aero-engine blade is to be predicted is predicted, prediction results of the rejection rates of different parts are obtained for different parts, and therefore a certain guiding effect can be provided for predicting repair cost.
Example two
Based on the same inventive concept, an embodiment of the present invention further provides a device for predicting a blade rejection rate of an aircraft engine, as shown in fig. 2, including:
the obtaining module 201 is used for obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data conditions and the historical rejection rates of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of a common blade and a second prediction model for predicting the rejection rate of a hot-end key blade;
the obtaining module 202 is used for obtaining blade types of blades of a target component of the aircraft engine to be predicted, wherein the blade types comprise common blades and hot end key blades;
and the prediction module 203 is used for predicting the rejection rate of the target part of the aircraft engine to be predicted based on the blade type and the prediction model.
In an optional implementation, the obtaining module 201 includes:
the first obtaining unit is used for taking the common blades belonging to the same name type in the multiple groups of historical aviation engine common blades as an integral object, and obtaining a first prediction model for predicting the rejection rate of the common blades based on the historical use data condition and the rejection rate of the integral object of the multiple groups of historical aviation engines;
and the second obtaining unit is used for obtaining a second prediction model for predicting the rejection rate of the hot end key blade based on the historical use data conditions and the rejection rates of the hot end key blades of the multiple groups of historical aero-engines.
In an optional implementation, the first obtaining unit includes:
the input subunit is used for taking common blades belonging to the same name type in the multiple groups of common blades of the historical aeroengine as an integral object as input data of a training sample;
the output subunit is used for clustering the rejection rates of the whole objects of the multiple groups of historical aircraft engines by adopting a clustering algorithm to obtain the processed rejection rates as output data of the training samples;
an obtaining subunit, configured to obtain, based on the input data and the output data, a first prediction model for predicting a rejection rate of a common blade.
In an alternative embodiment, the obtaining subunit is configured to:
inputting the input data and the output data into a combined integrated algorithm model, wherein the combined integrated algorithm model comprises a random forest algorithm model and a self-adaptive enhancement algorithm model to obtain an optimal algorithm model;
and taking the optimal algorithm model as a first prediction model for predicting the rejection rate of the common blade.
In an optional implementation, the second obtaining unit is configured to:
determining missing data from the historical use data conditions and the rejection rates of the multiple groups of historical aviation engine hot end key blades, and filling the missing data by adopting a KNN algorithm;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aero-engine after filling.
In an alternative embodiment, the predictive model includes:
the first prediction unit is used for predicting the rejection rate of a first target component to which the common blade of the aero-engine to be predicted belongs based on the first prediction model when the blade type is the common blade;
and the second prediction unit is used for predicting the rejection rate of a second target component to which the hot end key blade of the aero-engine to be predicted belongs based on the second prediction model when the blade type is the hot end key blade.
In an optional embodiment, the second prediction unit is configured to:
when the type of the blade is a hot end key blade, inputting the service condition data of each hot end key blade in a second target component to which the hot end key blade of the aero-engine to be predicted belongs into the second prediction model to obtain the rejection rate of each hot end key blade;
and obtaining the rejection rate of the second target component of the hot end key blade of the aero-engine to be predicted through mathematical expectation and weighted average calculation based on the rejection rate of each hot end key blade.
EXAMPLE III
Based on the same inventive concept, the embodiment of the present invention provides a computer device, as shown in fig. 3, including a memory 304, a processor 302, and a computer program stored on the memory 304 and executable on the processor 302, where the processor 302 executes the program to implement the steps of the method for predicting the blade rejection rate of an aircraft engine.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Example four
Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for predicting aircraft engine blade rejection rate described above.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the apparatus, computer device, or device for predicting aircraft engine blade rejection rates in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design 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 not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (10)

1. A method for predicting the scrappage of an aircraft engine blade is characterized by comprising the following steps:
obtaining a prediction model for predicting the rejection rate of the aero-engine blade based on the historical use data condition and the historical rejection rate of a plurality of groups of historical aero-engine blades, wherein the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades;
obtaining blade types of blades of a target component of an aeroengine to be predicted, wherein the blade types comprise common blades and hot end key blades;
and predicting the rejection rate of the target part of the aircraft engine to be predicted based on the blade type and the prediction model.
2. The prediction method of claim 1, wherein obtaining a prediction model for predicting the rejection rate of an aircraft engine blade based on historical usage data and historical rejection rates of a plurality of groups of historical aircraft engine blades comprises:
taking common blades belonging to the same name type in the multiple groups of historical aviation engine common blades as an integral object, and obtaining a first prediction model for predicting the rejection rate of the common blades based on the historical use data condition and the rejection rate of the integral object of the multiple groups of historical aviation engines;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aero-engine.
3. The prediction method according to claim 2, wherein the step of taking the common blades belonging to the same name in the multiple groups of historical common blades of the aircraft engine as a whole object, and obtaining a first prediction model for predicting the rejection rate of the common blades based on the historical use data and the rejection rate of the whole object of the multiple groups of historical aircraft engines comprises the following steps:
taking common blades belonging to the same name type in the multiple groups of historical aviation engine common blades as an integral object as input data of a training sample;
clustering the rejection rates of the whole objects of the multiple groups of historical aero-engines by adopting a clustering algorithm to obtain the processed rejection rates as output data of the training samples;
based on the input data and the output data, a first prediction model for predicting the rejection rate of the common blade is obtained.
4. The prediction method according to claim 3, wherein the obtaining a first prediction model for predicting the rejection rate of a normal blade based on the input data and the output data comprises:
inputting the input data and the output data into a combined integrated algorithm model, wherein the combined integrated algorithm model comprises a random forest algorithm model and a self-adaptive enhancement algorithm model to obtain an optimal algorithm model;
and taking the optimal algorithm model as a first prediction model for predicting the rejection rate of the common blade.
5. The prediction method according to claim 2, wherein the obtaining of the second prediction model for predicting the rejection rate of the hot end key blade based on the historical usage data and the rejection rates of the multiple groups of historical hot end key blades of the aircraft engine comprises:
determining missing data from the historical use data conditions and the rejection rates of the multiple groups of historical aviation engine hot end key blades, and filling the missing data by adopting a KNN algorithm;
and obtaining a second prediction model for predicting the rejection rate of the hot end key blades based on the historical use data conditions and the rejection rates of the multiple groups of historical hot end key blades of the aero-engine after filling.
6. The prediction method according to claim 1, wherein the predicting the rejection rate of the aero-engine target component to be predicted based on the blade type and the prediction model comprises:
when the blade type is a common blade, predicting the rejection rate of a first target component to which the common blade of the aero-engine to be predicted belongs based on the first prediction model;
and when the type of the blade is a hot end key blade, predicting the rejection rate of a second target component to which the hot end key blade of the aero-engine to be predicted belongs based on the second prediction model.
7. The prediction method according to claim 6, wherein the predicting, based on the second prediction model, the rejection rate of a second target component to which the aero-engine hot end key blade to be predicted belongs when the hot end key blade of the blade type is used for predicting comprises:
when the type of the blade is a hot end key blade, inputting the service condition data of each hot end key blade in a second target component to which the hot end key blade of the aero-engine to be predicted belongs into the second prediction model to obtain the rejection rate of each hot end key blade;
and obtaining the rejection rate of the second target component of the hot end key blade of the aero-engine to be predicted through mathematical expectation and weighted average calculation based on the rejection rate of each hot end key blade.
8. An aircraft engine blade rejection rate prediction device, comprising:
the obtaining module is used for obtaining a prediction model for predicting the rejection rate of the aero-engine blades based on the historical use data conditions and the historical rejection rates of a plurality of groups of historical aero-engine blades, and the prediction model comprises a first prediction model for predicting the rejection rate of common blades and a second prediction model for predicting the rejection rate of hot-end key blades;
the device comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring the blade type of a blade of a target component of the aeroengine to be predicted, and the blade type comprises a common blade and a hot end key blade;
and the prediction module is used for predicting the rejection rate of the target part of the aero-engine to be predicted based on the blade type and the prediction model.
9. 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 implements the method steps of any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
CN202210486431.8A 2022-05-06 2022-05-06 Prediction method and device for scrappage of aero-engine blade Pending CN114912675A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210486431.8A CN114912675A (en) 2022-05-06 2022-05-06 Prediction method and device for scrappage of aero-engine blade

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210486431.8A CN114912675A (en) 2022-05-06 2022-05-06 Prediction method and device for scrappage of aero-engine blade

Publications (1)

Publication Number Publication Date
CN114912675A true CN114912675A (en) 2022-08-16

Family

ID=82766059

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210486431.8A Pending CN114912675A (en) 2022-05-06 2022-05-06 Prediction method and device for scrappage of aero-engine blade

Country Status (1)

Country Link
CN (1) CN114912675A (en)

Similar Documents

Publication Publication Date Title
US20200258057A1 (en) Repair management and execution
US11756349B2 (en) Electronic control unit testing optimization
US20200134574A1 (en) Equipment repair management and execution
US8781782B2 (en) System and method for conditional multi-output regression for machine condition monitoring
EP3223095B1 (en) Method and apparatus for optimizing diagnostics of rotating equipment
WO2020140073A1 (en) Neural architecture search through a graph search space
CN110689141B (en) Fault diagnosis method and equipment for wind generating set
CN110987439B (en) Aeroengine fault prediction method based on Logitics regression and Xgboost model
CN110413775A (en) A kind of data label classification method, device, terminal and storage medium
CN112767106B (en) Automatic auditing method, system, computer readable storage medium and auditing equipment
CN113221362B (en) Satellite launching field performance test subject purpose selection method and device and electronic equipment
US11341780B2 (en) Maintenance of an aircraft via similarity detection and modeling
CN112379325A (en) Fault diagnosis method and system for intelligent electric meter
CN117150359A (en) Small sample fault diagnosis method, system, device and medium based on model independent element learning
CN111177135B (en) Landmark-based data filling method and device
CN116226676B (en) Machine tool fault prediction model generation method suitable for extreme environment and related equipment
CN114912675A (en) Prediction method and device for scrappage of aero-engine blade
CN112712305B (en) Aircraft system and health assessment method and device thereof
US20220068042A1 (en) Automated prediction of repair based on sensor data
CN110852544B (en) Reliability evaluation method and device for wind generating set
CN113344087A (en) Method for establishing sample set and computing equipment
CN114764741A (en) Method and system for predicting running wind power of wind driven generator
Hao et al. A fault diagnosis algorithm of the dedicated equipment based on CBAM-ResNET mechanism
CN114021455B (en) Water chilling unit fault detection and diagnosis method combining improvement DRAGAN and data driving
CN111596641B (en) Fault analysis method and device, storage medium and equipment for emergency diesel engine of nuclear power station

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination