CN112082742B - A method, system and device for intelligent identification of aero-engine wheel disc cracks - Google Patents
A method, system and device for intelligent identification of aero-engine wheel disc cracks Download PDFInfo
- Publication number
- CN112082742B CN112082742B CN202010713438.XA CN202010713438A CN112082742B CN 112082742 B CN112082742 B CN 112082742B CN 202010713438 A CN202010713438 A CN 202010713438A CN 112082742 B CN112082742 B CN 112082742B
- Authority
- CN
- China
- Prior art keywords
- wheel disc
- crack
- aeroengine
- cracks
- blade
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000013598 vector Substances 0.000 claims abstract description 125
- 238000004088 simulation Methods 0.000 claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000010276 construction Methods 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 208000037656 Respiratory Sounds Diseases 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 3
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 230000003750 conditioning effect Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/003—Measuring of motor parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B7/00—Measuring arrangements characterised by the use of electric or magnetic techniques
- G01B7/14—Measuring arrangements characterised by the use of electric or magnetic techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
本发明公开一种航空发动机轮盘裂纹智能识别方法、系统及装置，方法包括航空发动机轮盘裂纹模式库构建、航空发动机轮盘裂纹模式库扩充、航空发动机轮盘裂纹在线检测以及航空发动机轮盘裂纹智能识别，本发明通过有限元仿真得到轮盘叶片叶尖径向间隙与叶片周向间距的分布情况，对仿真结果进行扩充，构建轮盘裂纹模式库。通过计算裂纹模式库样本特征向量与待识别样本特征向量之间的余弦相似度，判断轮盘上是否存在裂纹，并同时得到裂纹的类型和裂纹的位置，综合考虑叶尖间隙和叶片间距两种参数的判别结果，提高轮盘裂纹检测、分类与位置识别结果的可靠性。
The invention discloses an intelligent identification method, system and device for aero-engine roulette cracks. The method includes the construction of aero-engine roulette crack pattern library, the expansion of aero-engine roulette crack pattern library, the online detection of aero-engine roulette cracks, and the aero-engine roulette crack pattern library. Intelligent crack identification, the present invention obtains the distribution of the radial clearance of the wheel disc blade tip and the blade circumferential spacing through finite element simulation, and expands the simulation results to build a wheel disc crack mode library. By calculating the cosine similarity between the sample feature vector of the crack pattern library and the feature vector of the sample to be identified, it is judged whether there is a crack on the disc, and the type of crack and the position of the crack are obtained at the same time. The discriminant results of the parameters improve the reliability of the roulette crack detection, classification and location identification results.
Description
Technical Field
The invention belongs to the technical field of mechanical fault diagnosis, and particularly relates to an intelligent recognition method, system and device for cracks of an aircraft engine wheel disc.
Background
The wheel disc is a core rotating part and a power source of the aero-engine and has important influence on the performance and the safety of the engine. The wheel disc runs under the complex working conditions of high temperature, high pressure and high rotating speed, bears the multiple excitation of centrifugal load, thermal load and pneumatic load, and easily generates low-cycle fatigue cracks at the stress concentration part of the wheel disc. Once the crack propagates, the cracked portion of the wheel disc will fly out quickly, piercing the case, causing a serious flight accident. Therefore, the state of the wheel disc is detected in time, and the effective judgment of the fault type and the fault position has important significance for guaranteeing the flight safety.
The structure of the aircraft engine wheel disc is complex, and the internal cracks are difficult to directly detect. The traditional periodical disassembling and overhauling means has long period and low efficiency, and the running state of the wheel disc cannot be known in real time. In recent years, disk failure diagnosis methods based on blade tip parameter measurement have been widely developed at home and abroad (Abdul-Aziz A, Woike MR, Anderson RC, et al. Propulse height monitoring adopted by microwave sensor performance and blade tip timing. SPIE: Denver, CO, United states,2019: OZ Optics, Ltd.; Polytec, Inc.; The Society of Photo-Optical Instrumentation Engineers (SPIE)). Literature research finds that due to the complex structure of the wheel disc, crack failure mechanism analysis is difficult to carry out through a dynamic modeling method, so that the failure type and the test result are difficult to correspond, and the test result is difficult to explain (Kharyton V, Lane J, Thouverez F, et al. simulation of tip-timing measurements of a cracked blocked disk for the stressed. American Society of Mechanical Engineers (ASME): Glasgow, United kingdom,2010: 845-. In addition, the initiation and the expansion positions of the wheel disc cracks are variable, the tip parameter curves have similarity, and the accurate judgment cannot be realized by human eyes alone. In the operation process of the aero-engine, the working conditions such as the rotating speed, the temperature and the like of the wheel disc are changed continuously, the size and the trend of the blade tip parameters are changed accordingly, various different measuring results appear on the same crack, and the difficulty of crack identification is increased.
In a word, the means period that regular dismantlement rim plate among the prior art overhauls is long, inefficiency, can not know the running state of rim plate in real time. The wheel disc fault diagnosis method based on blade tip parameter measurement widely developed in recent years is limited by the fact that the wheel disc is complex in structure and difficult to perform dynamic modeling, so that the fault mechanism of cracks is unclear, and the test result is difficult to explain.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an intelligent recognition method, system and device for cracks of an aircraft engine wheel disc, which solve the problems that the fault type cannot be qualitatively analyzed and the fault position cannot be quantitatively diagnosed due to unclear failure mechanism, provide a basis for wheel disc crack detection, and improve the accuracy of crack detection.
In order to achieve the purpose, the invention adopts the technical scheme that the intelligent recognition method for the cracks of the disk of the aero-engine comprises the following steps:
s100, respectively establishing geometric models of a normal wheel disc and a cracked wheel disc, then establishing finite element models of the normal wheel disc and the cracked wheel disc corresponding to the geometric models respectively, calculating a rule of a curve shape of a parameter tip of the wheel disc through finite element simulation, and establishing a preliminary aeroengine wheel disc crack mode library by using the tip parameter as a characteristic vector;
s200, setting different rotating speeds and crack positions in the crack wheel disc finite element model, and obtaining the influence rule of the rotating speeds and the crack positions on the blade tip parameter curve shape through finite element simulation; based on the influence rule, longitudinally scaling and transversely shifting the sample characteristic vector in the preliminary aeroengine wheel disc crack mode library obtained in the step S100, and expanding the preliminary aeroengine wheel disc crack mode library to enable the preliminary aeroengine wheel disc crack mode library to contain crack conditions of various rotating speeds and various crack positions;
s300, testing, collecting and analyzing the blade tip parameters of the engine wheel disk based on the blade tip parameter measuring system of the aeroengine wheel disk, and taking the obtained blade tip parameters as characteristic vectors of samples to be identified;
s400, measuring the similarity between the crack pattern library sample feature vector obtained in the step S200 and the to-be-identified sample feature vector obtained in the step S300 based on a cosine similarity calculation method, counting the types of the N crack pattern library sample feature vectors with the highest similarity, outputting crack types and crack position information, and realizing accurate classification and position identification of the wheel disc cracks.
S100, constructing a preliminary aeroengine wheel disc crack pattern library, which comprises the following steps:
s101, establishing geometric models of a normal wheel disc and a crack wheel disc;
s102, respectively dividing finite element grids for the geometric model, setting material properties, grid types, contact properties of a tenon and mortise of the wheel disc, analysis step types, boundary conditions, loads and output results, and establishing finite element models of a normal wheel disc and a crack wheel disc; the material type, the contact property, the boundary condition and the load are determined by referring to the actual working condition of the engine; the output result refers to the coordinates of the leaf tip nodes in the finite element model;
s103, solving the finite element model by using an explicit dynamics method to obtain a distribution rule of the blade tip parameters;
and S104, constructing a preliminary aeroengine wheel disc crack mode library by taking the blade tip parameters of all the blades as sample characteristic vectors, and providing data support for the detection of the wheel disc cracks.
The S200 aeroengine wheel disc crack mode library expansion method comprises the following steps:
s201, establishing a geometrical model of the wheel disc containing the cracks when the cracks are at different positions, establishing a finite element model for the geometrical model, and calculating the influence rule of the cracks at different positions on the curve shape of the blade tip parameter through finite element simulation;
s202, setting different rotating speeds for the finite element model of the crack wheel disc, and calculating the influence rule of the rotating speeds on the curve shape of the blade tip parameter through finite element simulation;
s203, longitudinally scaling the sample characteristic vectors in the preliminary wheel disc crack pattern library according to the influence rule of S201, expanding the number of the sample characteristic vectors in the preliminary wheel disc crack pattern library, and constructing an aeroengine wheel disc crack pattern library;
and S204, transversely shifting the sample characteristic vectors in the preliminary crack mode library according to the influence rule of S202, expanding the number of the sample characteristic vectors in the preliminary crack mode library of the wheel disc, and constructing the crack mode library of the wheel disc of the aero-engine.
The S300 aeroengine wheel disc crack online detection method comprises the following steps:
s301, acquiring blade tip parameters of an aeroengine wheel disc at a non-resonant rotating speed based on a blade parameter testing system;
s302, based on the tip parameters in S301, denoising the tip parameters by using a low-pass filtering method, and extracting tip clearance data by using a curve fitting method;
s303, based on the blade tip parameters in the S301, extracting the blade spacing by using a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
s305, extracting two blade tip parameters when the wheel disc rotates for one circle at a constant speed in a non-resonance rotating speed state, and constructing a sample feature vector to be identified by using the blade tip parameters.
The S400 intelligent recognition method for the cracks of the aircraft engine wheel disc comprises the following steps:
s401, measuring the similarity between the sample feature vector of the crack pattern library and the feature vector of the sample to be identified based on a cosine similarity method, and calculating the distance between each sample feature vector in the crack pattern library and the feature vector of the sample to be identified;
s402, counting crack characteristics of the N crack mode library sample characteristic vectors with the maximum similarity with the characteristic vector of the sample to be identified; judging whether the crack exists or not, the type of the crack and the position of the crack, and judging the characteristic vector of the sample to be identified as the type with the most identical characteristics in the N samples; and outputting the discrimination result of the sample feature vector to be recognized.
In S200, the different rotating speeds are determined by referring to the actual working rotating speed of the engine; the different crack positions refer to different numbers of the cracks facing the blade in the radial direction of the wheel disc, and the longitudinal scaling refers to the overall scaling of the amplitude of the blade tip parameters in the crack mode library to obtain a sample set with changed amplitude and unchanged trend; the transverse shift represents that the values of all blade tip parameters of the crack pattern library move one by one according to the blade sequence, so that the extended sample set comprises all the conditions that the crack is positioned below any blade.
For a sample feature vector to be identified obtained by engine testing, two discrimination results are obtained by calculating a blade tip clearance feature vector and a blade spacing feature vector respectively; and when the two judgment results are consistent, the judgment result is taken as a final judgment result, and when the two judgment results are inconsistent, the value of N is changed until the condition that the two judgment results are consistent is more than the condition that the two judgment results are different.
An intelligent recognition system for cracks of an aircraft engine wheel disc comprises a wheel disc crack mode library construction module, a wheel disc crack mode library expansion module, a wheel disc crack online detection module and a wheel disc crack intelligent recognition module; the disc crack pattern library construction module is used for establishing geometric models of a normal disc and a crack disc, establishing finite element models of the normal disc and the crack disc corresponding to the geometric models respectively, calculating a change rule of a disc tip parameter through finite element simulation, and obtaining a preliminary disc crack pattern library of the aero-engine disc by using the disc tip parameter as a characteristic vector;
the wheel disc crack mode library expansion module is used for setting different rotating speeds and crack positions in a crack wheel disc finite element model and obtaining the influence rule of the two variables on the blade tip parameters through finite element simulation; based on the rule, carrying out longitudinal scaling and transverse shifting on the sample characteristic vector in the preliminary aeroengine wheel disc crack mode library, and expanding the preliminary aeroengine wheel disc crack mode library;
the wheel disc crack online detection module is used for testing, collecting and analyzing the blade tip parameters of the engine wheel disc based on an aeroengine wheel disc blade tip parameter measurement system, and the obtained blade tip parameters are used as characteristic vectors of samples to be identified;
the intelligent wheel disc crack identification module measures the similarity between the crack pattern library sample feature vector and the to-be-identified sample feature vector based on a cosine similarity calculation method, counts the categories of N crack pattern library sample feature vectors with the highest similarity, outputs crack types and crack position information, and realizes accurate classification and position identification of wheel disc cracks;
wherein, online detection module of rim plate crackle includes: the data acquisition unit is used for acquiring the parameters of the tip of the engine at the non-resonant rotating speed from the blade spacing test system;
the low-pass filtering unit is used for denoising the data of the blade tip clearance and extracting the blade tip clearance by using a curve fitting method;
a blade pitch extraction unit that extracts a blade pitch based on a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
and the blade tip parameter extraction unit is used for extracting two blade tip parameters when the wheel disc rotates at a constant speed for one circle under the non-resonance rotating speed state, and constructing a sample feature vector to be identified by using the blade tip parameters.
The invention discloses an intelligent recognition device for cracks of an aeroengine wheel disc, which comprises one or more processors and a memory, wherein the memory is used for storing computer executable programs, the processors read part or all of the computer executable programs from the memory and execute the computer executable programs, and when the processors execute part or all of the computer executable programs, the intelligent recognition device for cracks of the aeroengine wheel disc can realize the intelligent recognition method for cracks of the aeroengine wheel disc.
A computer readable storage medium is provided, and a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the intelligent recognition method for the cracks of the aircraft engine wheel disc can be realized.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention uses finite element simulation to construct a crack mode library, which overcomes the problem that the crack mode library can not be constructed because of insufficient actual test data, in addition, the initiation and expansion positions of the crack of the wheel disc are variable, the curve of the parameter of the blade tip has similarity, the curve can not be accurately judged by human eyes alone, the working conditions such as the rotating speed and the temperature of the wheel disc are continuously changed during the operation process of the aeroengine, the size and the trend of the parameter of the blade tip are changed along with the change of the initiation and the expansion positions of the crack of the wheel disc, the same crack has various different measurement results, the difficulty of crack identification is increased, the cosine similarity uses the cosine value of the included angle of two vectors in the vector space as the size for measuring the difference between two individuals, the difference between different parameter curves can be accurately measured, compared with distance measurement, the cosine similarity emphasizes the difference of the two vectors in the direction rather than the distance or the length, therefore, the cosine similarity is not influenced by the working condition change of the wheel disc and the position of the crack, the method can accurately judge the crack types under different working conditions, can judge whether the wheel disc has the cracks through similarity calculation, and can simultaneously obtain the characteristics of the crack types, the crack positions and the like.
Further, for a sample feature vector to be identified obtained by engine testing, two discrimination results are obtained by calculating a blade tip clearance feature vector and a blade spacing feature vector respectively; when the two discrimination results are consistent, the discrimination result is taken as the final discrimination result, and the accuracy of the judgment can be improved.
Furthermore, the blade tip parameters of the aeroengine wheel disc are collected at the non-resonance rotating speed, the covering phenomenon of the vibration on the crack information at the resonance rotating speed is avoided, and the influence of the crack on the blade tip parameters can be reflected.
Drawings
FIG. 1 is a flow chart of a method that can be implemented in accordance with the present invention.
Fig. 2 is a technical route diagram of an aeroengine disk crack pattern library construction method and an aeroengine disk crack pattern library expansion method.
FIG. 3 is a technical route diagram of an aero-engine wheel disc crack online detection method and an aero-engine wheel disc crack intelligent identification method.
FIG. 4a is a finite element simulation calculation of the influence law of cracks at different positions on blade tip clearance change.
FIG. 4b is a diagram illustrating the influence rule of cracks at different positions on the blade pitch change through finite element simulation.
FIG. 5a is a diagram illustrating the influence of the rotational speed on the blade tip clearance variation in a finite element simulation.
FIG. 5b is a diagram illustrating the influence of the rotational speed on the blade pitch in the finite element simulation.
Detailed Description
The present invention will be described in detail with reference to the following examples and accompanying drawings.
The intelligent recognition method for the cracks of the aero-engine wheel disc provided by the invention comprises four parts, namely an aero-engine wheel disc crack pattern library construction process, an aero-engine wheel disc crack pattern library expansion process, an aero-engine wheel disc crack online detection process and an aero-engine wheel disc crack intelligent recognition process. The online detection method of the crack of the disc of the aircraft engine comprises the steps of obtaining a disc crack pattern library of the aircraft engine based on sample expansion, and obtaining an online detection result of the disc crack.
S100, the construction process of the aeroengine wheel disc crack pattern library comprises the following steps:
s101, establishing geometric models of a normal wheel disc and a crack wheel disc;
by way of explanatory illustration, the normal wheel disc represents a structurally intact wheel disc without crack damage; the crack wheel disc model comprises five common wheel disc cracks, namely a wheel disc web circumferential crack, a wheel disc web radial crack, a wheel disc central hole crack, a wheel disc mortise bottom crack and a wheel disc blade crack.
S102, respectively dividing the geometric model of S101 into finite element grids, setting material properties and grid types, and establishing finite element models of a normal wheel disc and a crack wheel disc;
s103, setting analysis step types, boundary conditions, loads and output results, and solving the finite element model by using an explicit dynamics method to obtain the blade tip parameters of the model.
Wherein the tip parameters include tip clearance and blade pitch; the tip clearance refers to the radial clearance between the tip of the rotating blade and the casing; the blade pitch refers to the circumferential distance between the tips of two adjacent rotating blades.
S104, taking the blade tip parameters of all the blades as characteristic vectors, constructing a preliminary aeroengine wheel disc crack mode library, and providing data support for detection of wheel disc cracks.
The S200 aeroengine wheel disc crack pattern library expansion process comprises the following steps:
s201, selecting any type of wheel disc cracks, establishing a wheel disc geometric model containing the cracks when the cracks are located at different positions, establishing a finite element model for the wheel disc geometric model, and calculating the influence rule of the cracks at different positions on the curve shape of the blade tip parameter through finite element simulation;
s202, selecting any one of the types of the rim plate cracks, establishing a finite element model for the rim plate cracks, setting different rotating speeds, and calculating the influence rule of the rotating speeds on the curve shape of the blade tip parameter curve through finite element simulation;
s203, according to the influence rule in S201, longitudinally scaling sample characteristic vectors in the preliminary crack pattern library, expanding the number of the sample characteristic vectors in the preliminary crack pattern library of the wheel disc, and constructing a crack pattern library of the wheel disc of the aero-engine;
s204, according to the influence rule of S202, transversely shifting sample characteristic vectors in the preliminary crack mode library, expanding the number of the sample characteristic vectors in the preliminary crack mode library of the wheel disc, and constructing an aeroengine wheel disc crack mode library;
s201, the different positions of the cracks mean that the numbers of the cracks facing the blades are different in the radial direction of the wheel disc; the crack type of any wheel disc comprises but is not limited to a wheel disc web circumferential crack, a wheel disc web radial crack, a wheel disc central hole crack, a wheel disc mortise bottom crack and a wheel disc blade crack;
in S203, the longitudinal scaling refers to performing overall scaling on the amplitude of the leaf tip parameter in the crack pattern library to obtain a sample set with an amplitude change and a constant trend.
S204, the transverse shift refers to that the values of all blade tip parameters of the crack pattern library move one by one according to the blade sequence, so that the extended sample set comprises all the conditions that the crack is positioned below any blade.
The S300 aeroengine wheel disc crack online detection process comprises the following steps:
a capacitive sensor, a high-frequency capacitive demodulation module, a signal conditioning module, an analog-to-digital conversion module and a computer are selected to build a blade tip clearance test system; selecting an optical fiber sensor, a photoelectric preamplifier, a signal conditioning module, a counting/timing acquisition module and a computer to build a blade spacing test system;
carrying out engine test, and collecting engine blade tip parameters at a non-resonant rotating speed;
denoising the data of the blade tip clearance by using a low-pass filtering method, and extracting the blade tip clearance by using a curve fitting method;
extracting the blade spacing by using a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
two blade tip parameters of the wheel disc rotating for one circle at a constant speed in a non-resonance rotating speed state are extracted, and the blade tip parameters are used for constructing a sample feature vector to be identified.
The S400 intelligent recognition process for the cracks of the disk of the aircraft engine comprises the following steps:
s401, extracting a feature vector from a crack pattern library, longitudinally scaling the feature vector to obtain a verification feature vector, and measuring the similarity between the feature vector of a crack pattern library sample and the verification feature vector by using a cosine similarity-based method;
s402, counting and verifying crack characteristics of the N samples with the maximum similarity of the characteristic vectors, wherein the crack characteristics comprise whether cracks exist, types of the cracks and positions of the cracks; the feature vector of the sample to be identified is judged as the class with the most identical features in the N samples,
s403, when the judgment results of the blade tip clearance characteristic vector and the blade spacing characteristic vector are consistent, taking the result as a final judgment result; and when the two discrimination results are inconsistent, changing the value of N until the two discrimination results are the same and more than different, taking the same discrimination result as a final discrimination result, and verifying the feasibility of using cosine similarity to classify the cracks.
S404, repeating S401-S403, replacing the verification characteristic vector with the characteristic vector of the sample to be identified obtained by the engine test, and judging the existence, the crack and the position of the crack of the engine wheel disc.
The calculation formula of the distance in S401 is:
in the formula, X is a sample to be identified, Y is a sample in a crack mode library, theta is an included angle between the sample to be identified and the crack mode library sample in a characteristic space, X is a characteristic vector of the sample to be identified, and Y is a characteristic vector of the crack mode library sample.
The position of the crack described in S402 indicates the number of the blade to which the crack is directed.
In S400, before classifying the characteristic vectors of the samples to be identified obtained by engine testing, a characteristic vector is extracted from a crack mode library obtained by finite element simulation, the characteristic vector is longitudinally scaled and used as the characteristic vector of the samples to be identified to participate in calculation, and the accuracy of a discrimination program can be verified.
The invention is further illustrated with reference to the following figures and examples:
1. and constructing a preliminary aeroengine wheel disc crack pattern library.
The normal wheel disc used in the embodiment has a complete structure and does not have crack damage; the crack wheel disc model comprises five common wheel disc cracks, namely a wheel disc web circumferential crack, a wheel disc web radial crack, a wheel disc central hole crack, a wheel disc mortise bottom crack and a wheel disc blade crack.
In the finite element model, materials of a wheel disc and a turbine blade are set to be nickel-based high-temperature alloy; the grid type is set as a hexahedron linear reduction integral unit; setting the contact attribute of the tenon and mortise of the wheel disc as penalty contact; setting a power explicit analysis step; limiting the degrees of freedom of all nodes of the wheel disc except the axial rotation degree of freedom; the rotation speed was set to 15000 rpm; outputting the coordinate change of the blade tip node; constructing a primary crack pattern library by using tip clearances and blade intervals of a normal wheel disc and five types of crack wheel discs, wherein tip clearance characteristic vectors and blade interval characteristic vectors are shown in tables 1 and 2 respectively:
TABLE 1
TABLE 2
2. An expansion method of an aeroengine wheel disc crack mode library.
Taking the wheel disc web circumferential crack as an example, respectively establishing a geometric model in which one crack is arranged on a disc, two cracks on the disc are 90 degrees, and two cracks on the disc are 180 degrees, establishing a finite element model for the geometric model, and calculating the influence rule of the cracks at different positions on the curve shape of the blade tip parameter curve through finite element simulation, wherein the calculation result is shown in fig. 4a and 4 b; FIG. 4a is a diagram illustrating the influence rule of cracks at different positions on blade tip clearance change through finite element simulation, and FIG. 4b is a diagram illustrating the influence rule of cracks at different positions on blade tip clearance change through finite element simulation.
Taking a wheel disc radial circumferential crack as an example, a geometric model and a finite element model of a crack on a disc are established, six rotating speeds of 2500rpm, 5000rpm, 7500rpm, 10000rpm, 12500rpm and 15000rpm are set, the influence rule of the rotating speed on the blade tip parameters is calculated through finite element simulation, the calculation results are shown in fig. 5a and 5b, fig. 5a is the influence rule of the rotating speed on the blade tip clearance change calculated through the finite element simulation, and fig. 5b is the influence rule of the rotating speed on the blade pitch calculated through the finite element simulation.
Expanding the preliminary wheel disc crack pattern library according to the rules shown in fig. 4a, fig. 4b, fig. 5a and fig. 5b, and longitudinally scaling each eigenvector in the preliminary crack pattern library to generate 1800 eigenvectors; for 1800 generated eigenvectors, respectively shifting laterally for 48 times to obtain 86400 eigenvectors, wherein in the expanded crack pattern library, the tip clearance eigenvectors and the blade pitch eigenvectors are shown in tables 3 and 4, respectively:
TABLE 3
TABLE 4
3. A verification feature vector is generated.
Extracting a feature vector from the crack pattern library, and performing longitudinal scaling on the feature vector to obtain a verification feature vector, wherein the verification feature vector is shown in a table 4:
TABLE 4
4. An intelligent recognition method for cracks of an aircraft engine wheel disc.
4.1 writing a program for classifying and identifying cracks based on a cosine similarity calculation process, measuring the similarity of the characteristic vectors of the sample of the crack pattern library and the verification characteristic vector, wherein the cosine similarity calculation formula is as follows:
in the formula, X is a sample to be identified, Y is a sample in a crack mode library, theta is an included angle between the sample to be identified and the crack mode library sample in a characteristic space, X is a characteristic vector of the sample to be identified, and Y is a characteristic vector of the crack mode library sample.
And 4.2 counting and verifying the crack characteristics of the N samples with the maximum similarity of the characteristic vectors. The crack characteristics include the presence or absence of a crack, the type of crack, and the location of the crack. And judging the sample feature vector to be identified into the class with the most identical features in the N samples.
4.3, synthesizing the discrimination results of the tip clearance characteristic vector and the blade spacing characteristic vector, outputting the final discrimination result of the characteristic vector of the sample to be recognized, verifying the feasibility of using cosine similarity to classify cracks, wherein the discrimination results of the tip clearance characteristic vector and the blade spacing characteristic vector are respectively shown in tables 5 and 6, and the comprehensive discrimination result is shown in table 7:
TABLE 5
TABLE 6
TABLE 7
5. And (6) testing and analyzing.
According to the embodiment, the blade tip radial clearance and the blade circumferential distance of different cracks are obtained through finite element simulation, the simulation results of two blade tip parameters are used for constructing the aeroengine wheel disc crack mode library, the cosine similarity is used for measuring the similarity of the characteristic vectors of the wheel disc crack mode library sample and the characteristic vector to be identified, and accurate crack detection, classification and position identification can be carried out on the sample to be identified.
The method has the following characteristics:
firstly, a crack mode library is constructed by using finite element simulation, so that the problem that the crack mode library cannot be constructed due to insufficient actual test data is solved;
and secondly, the cosine similarity is used for measuring the similarity between the feature vector of the crack pattern library and the feature vector of the sample to be identified, so that the differences of different cracks can be well measured, and the classification is more accurate.
The calculation result of the invention is not affected by the working condition of the engine to the amplitude of the blade tip parameter, and the characteristics of whether the crack exists, the type and the position of the crack and the like can be still accurately judged under the condition that the position of the crack changes.
And fourthly, synthesizing two discrimination results of the tip clearance characteristic vector and the blade spacing characteristic vector to obtain a final discrimination result, thereby realizing more reliable intelligent identification of the wheel disc cracks.
Cosine similarity uses the cosine value of the angle between two vectors in the vector space as a measure of the difference between two individuals. Cosine similarity emphasizes the difference of two vectors in direction rather than distance or length, compared to distance metrics. The cosine similarity can accurately measure the difference between different tip parameter curves, and the calculation result is not influenced by the working condition change of the wheel disc and the position of the crack. Whether cracks exist on the wheel disc can be judged through similarity calculation, and the types of the cracks, the positions of the cracks and other characteristics are obtained simultaneously, so that accurate wheel disc crack detection, classification and position identification results are provided.
As another embodiment, the invention further provides an intelligent recognition system for cracks of an aero-engine wheel disc based on blade tip clearance and blade spacing, which comprises a wheel disc crack pattern library construction module, a wheel disc crack pattern library expansion module, a wheel disc crack online detection module and a wheel disc crack intelligent recognition module; the disc crack pattern library construction module is used for establishing geometric models of a normal disc and a crack disc, establishing finite element models of the normal disc and the crack disc corresponding to the geometric models respectively, calculating a change rule of a disc tip parameter through finite element simulation, and obtaining a preliminary disc crack pattern library of the aero-engine disc by using the disc tip parameter as a characteristic vector;
the wheel disc crack mode library expansion module is used for setting different rotating speeds and crack positions in a crack wheel disc finite element model, and obtaining the influence rule of the two variables on the curve shape of the blade tip parameter through finite element simulation; based on the rule, carrying out longitudinal scaling and transverse shifting on the sample characteristic vector in the preliminary aeroengine wheel disc crack mode library, and expanding the preliminary aeroengine wheel disc crack mode library;
the wheel disc crack online detection module is used for testing, collecting and analyzing the blade tip parameters of the engine wheel disc based on an aeroengine wheel disc blade tip parameter measurement system, and the obtained blade tip parameters are used as characteristic vectors of samples to be identified;
the intelligent wheel disc crack identification module measures the similarity between the crack pattern library sample feature vector and the to-be-identified sample feature vector based on a cosine similarity calculation method, counts the categories of N crack pattern library sample feature vectors with the highest similarity, outputs crack types and crack position information, and realizes accurate classification and position identification of wheel disc cracks;
wherein, online detection module of rim plate crackle includes: the data acquisition unit is used for acquiring the parameters of the tip of the engine at the non-resonant rotating speed from the blade spacing test system;
the low-pass filtering unit is used for denoising the data of the blade tip clearance and extracting the blade tip clearance by using a curve fitting method;
a blade pitch extraction unit that extracts a blade pitch based on a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
and the blade tip parameter extraction unit is used for extracting two blade tip parameters when the wheel disc rotates at a constant speed for one circle under the non-resonance rotating speed state, and constructing a sample feature vector to be identified by using the blade tip parameters.
The invention also provides an intelligent recognition device for the cracks of the aeroengine wheel disc based on the blade tip clearance and the blade spacing, which comprises but is not limited to one or more processors and a memory, wherein the memory is used for storing computer executable programs, the processors read part or all of the computer executable programs from the memory and execute the computer executable programs, and when the processors execute part or all of the computer executable programs, part or all of the steps of the intelligent recognition method for the cracks of the aeroengine wheel disc can be realized.
The intelligent recognition device for the cracks of the aero-engine wheel disc can adopt a notebook computer, a tablet personal computer, a desktop computer, a mobile phone or a workstation.
A computer readable storage medium is provided, and a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the intelligent recognition method for the cracks of the aircraft engine wheel disc can be realized.
The processor of the present invention may be a Central Processing Unit (CPU), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), or an off-the-shelf programmable gate array (FPGA).
The memory of the invention can be an internal storage unit of a notebook computer, a tablet computer, a desktop computer, a mobile phone or a workstation, such as a memory and a hard disk; external memory units such as removable hard disks, flash memory cards may also be used.
Computer-readable storage media may include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. The computer-readable storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a Solid State Drive (SSD), or an optical disc. The Random Access Memory may include a resistive Random Access Memory (ReRAM) and a Dynamic Random Access Memory (DRAM).
Claims (9)
1. An intelligent recognition method for cracks of an aircraft engine wheel disc is characterized by comprising the following steps:
s100, respectively establishing geometric models of a normal wheel disc and a cracked wheel disc, then establishing finite element models of the normal wheel disc and the cracked wheel disc corresponding to the geometric models respectively, calculating a rule of a curve shape of a parameter tip of the wheel disc through finite element simulation, and establishing a preliminary aeroengine wheel disc crack mode library by using the tip parameter as a characteristic vector;
s200, setting different rotating speeds and crack positions in the crack wheel disc finite element model, and obtaining the influence rule of the rotating speeds and the crack positions on the blade tip parameter curve shape through finite element simulation; based on the influence rule, longitudinally scaling and transversely shifting the sample characteristic vector in the preliminary aeroengine wheel disc crack mode library obtained in the S100, expanding the preliminary aeroengine wheel disc crack mode library, and constructing the aeroengine wheel disc crack mode library to enable the aeroengine wheel disc crack mode library to contain crack conditions of various rotating speeds and various crack positions;
s300, testing, collecting and analyzing the blade tip parameters of the engine wheel disk based on the blade tip parameter measuring system of the aeroengine wheel disk, and taking the obtained blade tip parameters as characteristic vectors of samples to be identified;
s400, measuring the similarity between the characteristic vectors of the aeroengine wheel disc crack pattern library samples obtained in the step S200 and the characteristic vectors of the samples to be identified obtained in the step S300 based on a cosine similarity calculation method, counting the types of the N aeroengine wheel disc crack pattern library sample characteristic vectors with the highest similarity, outputting crack types and crack position information, and realizing accurate classification and position identification of wheel disc cracks;
s300 includes the steps of:
s301, acquiring blade tip parameters of the aircraft engine wheel disc at a non-resonant rotating speed based on a blade tip parameter measuring system;
s302, based on the tip parameters in S301, denoising the tip parameters by using a low-pass filtering method, and extracting tip clearance data by using a curve fitting method;
s303, based on the blade tip parameters in the S301, extracting the blade spacing by using a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
s304, extracting the tip clearance and the blade interval when the wheel disc rotates at a constant speed for one circle under the non-resonance rotating speed state, and constructing the characteristic vector of the sample to be identified by using the tip clearance and the blade interval.
2. The intelligent recognition method for the cracks of the aircraft engine wheel disc according to claim 1, wherein the S100 preliminary building of the model library for the cracks of the aircraft engine wheel disc comprises the following steps:
s101, establishing geometric models of a normal wheel disc and a crack wheel disc;
s102, respectively dividing finite element grids for the geometric model, setting material properties, grid types, contact properties of a tenon and mortise of the wheel disc, analysis step types, boundary conditions, loads and output results, and establishing finite element models of a normal wheel disc and a crack wheel disc; the material property, the contact property, the boundary condition and the load are determined by referring to the actual working condition of the engine; the output result refers to the coordinates of the leaf tip nodes in the finite element model;
s103, solving the finite element model by using an explicit dynamics method to obtain a distribution rule of the blade tip parameters;
and S104, constructing a preliminary aeroengine wheel disc crack mode library by taking the blade tip parameters of all the blades as sample characteristic vectors, and providing data support for the detection of the wheel disc cracks.
3. The intelligent recognition method for cracks of an aircraft engine disk according to claim 1, wherein S200 comprises the following steps:
s201, establishing a crack wheel disc geometric model when cracks are located at different positions, establishing a finite element model for the crack wheel disc geometric model, and calculating the influence rule of the cracks at the different positions on the blade tip parameter curve shape through finite element simulation;
s202, setting different rotating speeds for the finite element model of the crack wheel disc, and calculating the influence rule of the rotating speeds on the curve shape of the blade tip parameter through finite element simulation;
s203, longitudinally scaling sample characteristic vectors in the preliminary aeroengine wheel disc crack pattern library according to the influence rule of S202, expanding the number of the sample characteristic vectors in the preliminary aeroengine wheel disc crack pattern library, and constructing the aeroengine wheel disc crack pattern library;
and S204, transversely shifting sample characteristic vectors in the preliminary aeroengine wheel disc crack mode library according to the influence rule of S201, expanding the number of the sample characteristic vectors in the preliminary aeroengine wheel disc crack mode library, and constructing the aeroengine wheel disc crack mode library.
4. The intelligent recognition method for cracks of the aircraft engine disk according to claim 1, wherein S400 comprises the following steps:
s401, measuring the similarity between the sample characteristic vector of the aeroengine wheel disc crack pattern library and the characteristic vector of the sample to be identified based on a cosine similarity calculation method, and calculating the distance between each sample characteristic vector in the aeroengine wheel disc crack pattern library and the characteristic vector of the sample to be identified;
s402, counting crack characteristics of the N aeroengine wheel disc crack pattern library sample characteristic vectors with the maximum similarity to the characteristic vectors of the samples to be identified; judging whether the crack exists or not, the type of the crack and the position of the crack, and judging the characteristic vector of the sample to be identified as the type with the most identical characteristics in the N samples; and outputting the discrimination result of the sample feature vector to be recognized.
5. The intelligent recognition method for cracks on an aircraft engine disk according to claim 1, wherein in S200, the different rotation speeds are determined by referring to the actual working rotation speed of the engine; the different crack positions refer to different numbers of the cracks facing the blade in the radial direction of the wheel disc, and the longitudinal scaling refers to the integral scaling of the amplitude of the blade tip parameters in a primary aeroengine wheel disc crack mode library to obtain a sample set with the amplitude change and the trend unchanged; the transverse displacement represents that the values of all blade tip parameters of the primary aeroengine wheel disc crack mode library move one by one according to the blade sequence, so that the expanded sample set comprises all the conditions that cracks are positioned below any one blade.
6. The intelligent recognition method for the cracks of the aircraft engine wheel disc according to claim 1, wherein for the characteristic vectors of the sample to be recognized obtained by engine testing, two discrimination results are obtained by calculating the characteristic vector of the blade tip clearance and the characteristic vector of the blade pitch respectively; and when the two discrimination results are consistent, taking the discrimination result as a final discrimination result, and when the two discrimination results are inconsistent, changing the value of N until the condition that the two discrimination results are consistent is more than the condition that the two discrimination results are different.
7. An intelligent recognition system for cracks of an aeroengine wheel disc is characterized by comprising a wheel disc crack mode library construction module, a wheel disc crack mode library expansion module, a wheel disc crack on-line detection module and a wheel disc crack intelligent recognition module; the disc crack pattern library construction module is used for establishing geometric models of a normal disc and a crack disc, establishing finite element models of the normal disc and the crack disc corresponding to the geometric models respectively, calculating a change rule of a disc tip parameter through finite element simulation, and obtaining a preliminary disc crack pattern library of the aero-engine disc by using the disc tip parameter as a characteristic vector;
the wheel disc crack mode library expansion module is used for setting different rotating speeds and crack positions in a crack wheel disc finite element model and obtaining the influence rule of the two variables on the blade tip parameters through finite element simulation; based on the rule, longitudinally scaling and transversely shifting the sample characteristic vector in the preliminary aeroengine wheel disc crack pattern library, expanding the preliminary aeroengine wheel disc crack pattern library, and constructing the aeroengine wheel disc crack pattern library;
the wheel disc crack online detection module is used for testing, collecting and analyzing the blade tip parameters of the engine wheel disc based on an aeroengine wheel disc blade tip parameter measurement system, and the obtained blade tip parameters are used as characteristic vectors of samples to be identified;
the intelligent recognition module of the wheel disc cracks measures the similarity between the characteristic vectors of the sample of the aero-engine wheel disc crack pattern library and the characteristic vectors of the sample to be recognized based on a cosine similarity calculation method, counts the categories of the characteristic vectors of the sample of the N aero-engine wheel disc crack pattern libraries with the highest similarity, outputs crack types and crack position information, and realizes accurate classification and position recognition of the wheel disc cracks;
wherein, online detection module of rim plate crackle includes: the data acquisition unit is used for acquiring the parameters of the blade tip of the engine at the non-resonance rotating speed from the blade tip parameter measurement system;
the low-pass filtering unit is used for denoising the blade tip parameters and extracting the blade tip clearance by using a curve fitting method;
a blade pitch extraction unit that extracts a blade pitch based on a fixed frequency pulse filling method; performing circle-changing pretreatment on the blade interval time sequence, eliminating redundant error time sequence data and supplementing missing time sequence data;
and the blade tip parameter extraction unit is used for extracting blade tip gaps and blade intervals when the wheel disc rotates at a constant speed for one circle under the non-resonance rotating speed state, and constructing the characteristic vectors of the samples to be identified by using the blade tip gaps and the blade intervals.
8. An intelligent recognition device for cracks of an aircraft engine wheel disc is characterized by comprising one or more processors and a memory, wherein the memory is used for storing computer executable programs, the processors read part or all of the computer executable programs from the memory and execute the computer executable programs, and when the processors execute part or all of the computer executable programs, the intelligent recognition method for cracks of the aircraft engine wheel disc can be realized according to any one of claims 1 to 6.
9. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the intelligent recognition method for the cracks of the disk of the aircraft engine is realized according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010713438.XA CN112082742B (en) | 2020-07-22 | 2020-07-22 | A method, system and device for intelligent identification of aero-engine wheel disc cracks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010713438.XA CN112082742B (en) | 2020-07-22 | 2020-07-22 | A method, system and device for intelligent identification of aero-engine wheel disc cracks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112082742A CN112082742A (en) | 2020-12-15 |
| CN112082742B true CN112082742B (en) | 2021-08-13 |
Family
ID=73734694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010713438.XA Active CN112082742B (en) | 2020-07-22 | 2020-07-22 | A method, system and device for intelligent identification of aero-engine wheel disc cracks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112082742B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102498372A (en) * | 2009-09-14 | 2012-06-13 | 西门子公司 | Method for determining cracks in turbine blades |
| CN103630604A (en) * | 2012-08-29 | 2014-03-12 | 沈阳鼓风机集团股份有限公司 | Identification method for crack faults of semi-open impeller of centrifugal compressor |
| CN105352713A (en) * | 2015-11-20 | 2016-02-24 | 天津大学 | Method used for realizing blade fatigue crack detection through static blade displacement detection |
| KR20170122024A (en) * | 2016-04-26 | 2017-11-03 | 두산중공업 주식회사 | Method for life analysis of turbine blade and constructing method for data base of turbine blade |
| CN110020468A (en) * | 2019-03-21 | 2019-07-16 | 西安交通大学 | A kind of dynamic response analysis method of aero-engine wheel disc crack fault |
| CN110530973A (en) * | 2019-07-31 | 2019-12-03 | 西安交通大学 | The aero-engine turbine disk crack detection and diagnostic method of the twin driving of number |
| CN111239249A (en) * | 2020-03-18 | 2020-06-05 | 北京工业大学 | Ventilator blade crack fault diagnosis method based on Hilbert-Huang transform |
| CN111397909A (en) * | 2020-04-08 | 2020-07-10 | 西安交通大学 | An online monitoring method for low-cycle fatigue cracks in aero-engine turbine disks |
| CN111413404A (en) * | 2020-03-27 | 2020-07-14 | 天津大学 | On-line measurement method of blade crack based on blade tip timing and support vector machine principle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111043949B (en) * | 2019-12-31 | 2021-04-30 | 电子科技大学 | A device for detection of turbine blade tip clearance |
-
2020
- 2020-07-22 CN CN202010713438.XA patent/CN112082742B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102498372A (en) * | 2009-09-14 | 2012-06-13 | 西门子公司 | Method for determining cracks in turbine blades |
| CN103630604A (en) * | 2012-08-29 | 2014-03-12 | 沈阳鼓风机集团股份有限公司 | Identification method for crack faults of semi-open impeller of centrifugal compressor |
| CN105352713A (en) * | 2015-11-20 | 2016-02-24 | 天津大学 | Method used for realizing blade fatigue crack detection through static blade displacement detection |
| KR20170122024A (en) * | 2016-04-26 | 2017-11-03 | 두산중공업 주식회사 | Method for life analysis of turbine blade and constructing method for data base of turbine blade |
| CN110020468A (en) * | 2019-03-21 | 2019-07-16 | 西安交通大学 | A kind of dynamic response analysis method of aero-engine wheel disc crack fault |
| CN110530973A (en) * | 2019-07-31 | 2019-12-03 | 西安交通大学 | The aero-engine turbine disk crack detection and diagnostic method of the twin driving of number |
| CN111239249A (en) * | 2020-03-18 | 2020-06-05 | 北京工业大学 | Ventilator blade crack fault diagnosis method based on Hilbert-Huang transform |
| CN111413404A (en) * | 2020-03-27 | 2020-07-14 | 天津大学 | On-line measurement method of blade crack based on blade tip timing and support vector machine principle |
| CN111397909A (en) * | 2020-04-08 | 2020-07-10 | 西安交通大学 | An online monitoring method for low-cycle fatigue cracks in aero-engine turbine disks |
Non-Patent Citations (1)
| Title |
|---|
| 轮盘裂纹故障表征与叶端定时检测原理研究;孙亚超等;《第十三届全国振动理论及应用学术会议论文集》;20191130;第1、2.3、3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112082742A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7340265B2 (en) | Abnormality detection device, abnormality detection method, and program | |
| WO2020192621A1 (en) | Measurement method for rotor blade dynamic strain field based on blade tip timing and system thereof | |
| KR101718251B1 (en) | Method and system for monitoring rotating blade health | |
| US9818242B2 (en) | Gas turbine engine anomaly detections and fault identifications | |
| CN106169001B (en) | A method for predicting the remaining life of aero-engines based on graph matching of gas path performance parameters | |
| Cao et al. | Single-probe blade tip timing: A novel method for anomaly identification based on frequency shift | |
| CN106094570B (en) | A kind of aero-engine complete machine health evaluating method under variable working condition based on this distance of operating mode's switch and paddy | |
| Sun et al. | A non-probabilistic metric derived from condition information for operational reliability assessment of aero-engines | |
| CN110567574A (en) | A Method and System for Identifying Timing Vibration Parameters of Rotating Blade Tips | |
| Wu et al. | Blade crack detection using blade tip timing | |
| CN100472574C (en) | Fault Diagnosis System of Diesel Power Plant Based on Information Fusion | |
| WO2020090767A1 (en) | Abnormality diagnostic device, abnormality diagnostic method, and program | |
| CN113298162A (en) | Bridge health monitoring method and system based on K-means algorithm | |
| CN111626167A (en) | Blade crack identification method based on blade tip timing and improved multiple signal classification | |
| Kaszynski et al. | Accurate blade tip timing limits through geometry mistuning modeling | |
| CN104102726A (en) | Modified K-means clustering algorithm based on hierarchical clustering | |
| CN117745767A (en) | Digital twin data consistency verification method for aeroengine blisk | |
| CN116950917A (en) | Online diagnosis method for large centrifugal compressor blade cracks based on tip timing | |
| Zhao et al. | Parameter identification based on iterative signal space in blade tip timing | |
| CN112082742B (en) | A method, system and device for intelligent identification of aero-engine wheel disc cracks | |
| CN115435894A (en) | Blade tip timing vibration stress inversion method based on simulated annealing algorithm | |
| Grądzki et al. | Rotor blades diagnosis method based on differences in phase shifts | |
| Tian et al. | Experimental study on the optimization of the sensor arrangement for blade tip timing measurement | |
| CN106198745A (en) | Based on reflected energy than the anchoring defect length recognition methods of parameter | |
| CN112364886A (en) | Blade crack online measurement method based on blade tip timing and random forest |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |