Method for optimizing key tolerance of aircraft engine compressor blade

Abstract

The invention relates to the technical field of aero-engine low-pressure compressor blade optimization design, in particular to an aero-engine compressor blade key tolerance optimization method which comprises the steps that the maximum tolerance deviation coefficient corresponding to each tolerance is obtained; the total pressure loss coefficient value of the error blade profile is obtained; a key machining error-aerodynamic performance proxy model is obtained; constructing a fitness function; and the final tolerance range of each key machining error is obtained. The method is suitable for key tolerance optimization research of compressor blades of different types and different sizes, the established proxy model has good generalization performance and high fitting precision, meanwhile, the optimization method has extremely high efficiency, and an effective means is provided for reducing the blade machining error out-of-tolerance rate and improving the blade machining production efficiency.

Description

Technical Field

[0001] The invention relates to the technical field of optimization design of low-pressure compressor blades of aircraft engines, and in particular to a method for optimizing key tolerances of aircraft engine compressor blades. Background Art

[0002] The blade is the basic unit of the compressor, and its final geometric surface is the physical response of the aerodynamic design and structural design results of the compressor. In order to meet the requirements of gas flow and structural strength, the new generation of aircraft engine compressor blades are usually designed as three-dimensional twisted, forward-bent and swept ultra-thin free-form surface structures, and use difficult-to-process materials such as titanium alloys and high-temperature alloys, and have extremely high precision requirements. The contradiction between the structural and process characteristics of difficult-to-process materials and complex thin-walled curved surface structures and the ultra-high precision requirements has led to low processing qualification rate, high processing costs and long processing cycles for compressor blades in the aircraft engine industry. The fundamental reasons for this situation are, on the one hand, the inaccurate control of the blade processing process, and on the other hand, the unreasonable blade tolerance design. Many scholars have done a lot of research on the problem of blade processing process control, mainly involving cutting force modeling, tooling and fixture optimization, processing deformation prediction, processing process parameter optimization, tool trajectory and tool axis vector optimization, tool wear prediction and processing deformation compensation. The root cause of the unreasonable blade tolerance design problem is the insufficient understanding of the impact of blade processing errors on the aerodynamic performance of the compressor, which leads to the existing blade tolerance design method being heavily dependent on experience, and the tolerance dimensions of some key features being too strict. To address this problem, a new compressor blade tolerance optimization method should be proposed based on the distribution of blade processing errors under existing process capabilities and the impact of errors on aerodynamic performance, so as to improve the blade processing qualification rate and processing efficiency.

[0003] At present, there are few studies on the tolerance optimization methods of compressor blades. Most of the research on tolerances focuses on the design of dimension chains between different parts in the assembly process, the joint optimization of part product tolerance design and process solutions under cost constraints, and the tolerance design of some relatively simple free-form surface parts. For complex thin-walled curved surface parts such as compressor blades, their blade profile tolerances include characteristic parameter tolerances (chord length, maximum thickness, leading and trailing edge radius, etc.) and form and position tolerances (position tolerance, torsion tolerance, and profile tolerance, etc.). Not only are there many types of tolerances, but also two-dimensional cross-sectional tolerances and three-dimensional free-form surface tolerances are mixed and intertwined. Existing methods are difficult to meet the needs of blade tolerance optimization for compressor service performance. Although the machining errors of compressor blades present such a complex internal correlation, existing studies have shown that among the 13 machining errors of compressor blades, the maximum thickness error, the maximum leading edge profile error, the minimum leading edge profile error and the torsion angle error are the key machining errors, and accordingly, the three tolerances associated with these four errors are determined as key tolerances, namely, the maximum thickness tolerance, the leading edge profile tolerance and the torsion angle tolerance. Although the key errors and key tolerance types have been identified, which greatly reduces the difficulty of research, there is still no applicable method.

[0004] Therefore, it is necessary to provide a method for optimizing the critical tolerances of aero-engine compressor blades to solve the above problems. Summary of the invention

[0005] The present invention provides a method for optimizing the key tolerances of aero-engine compressor blades, so as to solve the problem that existing methods are difficult to meet the blade tolerance optimization requirements for compressor service performance, which profoundly affects the qualified rate and efficiency of blade production and processing.

[0006] A method for optimizing the critical tolerance of an aero-engine compressor blade of the present invention adopts the following technical solution, including: Obtaining machining error data of key machining errors of compressor blades, and obtaining a maximum tolerance deviation coefficient corresponding to each tolerance according to a distribution range of the machining error data of each key machining error and a corresponding original tolerance range; Based on the full factor method, all machining error combinations at specific sampling points of all key machining error types are designed and the error blade profiles of the corresponding error combinations are constructed. Then, CFD numerical simulation is performed to obtain the total pressure loss coefficient value of the error blade profiles of all key machining error types at each machining error sampling point combination. A neural network is constructed, each combination of all kinds of key machining errors is used as the input of the neural network, the total pressure loss coefficient value of the error blade corresponding to each machining error combination is used as the output of the neural network, and the neural network is trained to obtain a trained machining error-aerodynamic performance proxy model; The tolerance range is obtained according to the distribution range and tolerance range of the machining error data of each key machining error, a target data is randomly selected from each tolerance range to form the target input data, and the target input data is input into the proxy model to obtain the target aerodynamic loss coefficient value; each data is selected from the original tolerance range of each key machining error to form a group of original data, and the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data is obtained by using the proxy model; the constraint violation function is obtained according to the target aerodynamic loss coefficient value and the maximum aerodynamic loss coefficient value, and the fitness function is constructed based on the constraint violation function, the maximum tolerance offset coefficient corresponding to each tolerance, and the target input data; Taking the target input data as the optimization target, the target input data is optimized based on the fitness function and the sparrow search algorithm until the fitness function value is minimum. The final tolerance range of each key machining error is obtained according to the target input data corresponding to the minimum fitness function value.

[0007] Preferably, the key processing errors include: maximum thickness error, maximum leading edge profile error, minimum leading edge profile error and torsion angle error.

[0008] Preferably, the step of obtaining the maximum tolerance deviation coefficient corresponding to each tolerance is: The ratio of the maximum limit value of the distribution range of the machining error data of each key machining error to the maximum limit value of the corresponding tolerance range is taken as a first ratio; The ratio of the minimum limit value of the distribution range of the machining error data of each key machining error to the minimum limit value of the corresponding tolerance range is used as a second ratio; The maximum value of the absolute value of the first ratio and the absolute value of the second ratio is taken as the maximum tolerance deviation coefficient.

[0009] Preferably, all machining error combinations of all kinds of key machining errors are designed based on the full factor method, and error blade profiles corresponding to the machining error combinations are constructed for CFD numerical simulation. The steps for obtaining the total pressure loss coefficient value of the error blade profiles of all key machining error types under each machining error combination are as follows: Setting error sampling values ​​of different types of key machining errors according to the distribution range of error data; The original blade design is constructed using the NURBS method, and the error sampling values ​​corresponding to each type of key processing error are inserted into the original blade design to fit the error blade shape. By performing CFD numerical simulation on the error blade profile, the total pressure loss coefficient of the error blade profile under different error sampling value combinations of all key machining error types is obtained.

[0010] Preferably, the step of inserting the error sampling values ​​corresponding to each type of key processing error into the original design blade profile to fit the error blade profile is: Discretize the contour curves of the maximum thickness area and the leading edge area of ​​the original designed blade to obtain discrete points; Determine the error value at the maximum thickness position, use the Hanning window function as a weight function to weight the error value, and insert the weighted error value into discrete points on both sides of the maximum thickness position in the maximum thickness area; The distribution range of the error data of the leading edge profile is from the minimum value of the leading edge profile to the maximum value of the leading edge profile; Generate random error data that obeys normal distribution within the distribution range of error data of leading edge contour according to the number of discrete points in the leading edge contour area; The generated random error data are sequentially added to the discrete point positions corresponding to the leading edge contour area; After inserting the maximum thickness error and leading edge profile error at the discrete points in the corresponding area, the insertion of the torsion angle error can be achieved by changing the angle of attack of the blade, and thus the contour curve of the error blade is fitted by the NURBS method.

[0011] Preferably, the chord length regions of the front 5% and the rear 5% of the maximum thickness position are taken as the maximum thickness regions.

[0012] Preferably, the step of obtaining the out-of-tolerance range according to the error range and tolerance range of the machining error data of each key machining error is: The maximum limit value of the tolerance range to the maximum limit value of the error range is taken as the maximum limit value deviation range; The minimum limit value of the error range to the minimum limit value of the tolerance range is taken as the minimum limit value deviation range.

[0013] Preferably, the constraint violation function is expressed as:

[0014] In the formula, Represents the constraint violation function value; Indicates that the target input data is The target aerodynamic loss coefficient value output by the proxy model when It means that one data is selected from the original tolerance range of each key processing error to form a group of original data, and the agent model is used to obtain the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data.

[0015] Preferably, the fitness function is expressed as:

[0016] In the formula, Represents the fitness function value; The maximum tolerance deviation factor indicating the maximum thickness error; The maximum tolerance deviation factor representing the leading edge profile error; The maximum tolerance deviation factor indicating the torsion angle error; Indicates the target data selected within the tolerance range of the maximum thickness error; Indicates target data selected within the tolerance range of leading edge profile error; Indicates target data selected within the tolerance range of the torsion angle error; Expressed as a penalty factor; represents the constraint violation function value, Indicates taking the absolute value.

[0017] Preferably, the step of obtaining the final tolerance range according to the target input data corresponding to the minimum fitness function value is: According to the target data corresponding to the tolerance range of the maximum thickness error in the target input data corresponding to the minimum fitness function value, the final tolerance range of the maximum thickness tolerance is obtained; The target data corresponding to the tolerance range of the leading edge profile error in the target input data corresponding to the minimum fitness function value is used to obtain the final tolerance range of the leading edge profile tolerance; The target data corresponding to the excess tolerance range of the torsion angle error in the target input data corresponding to the minimum fitness function value is used to obtain the final tolerance range of the torsion angle tolerance.

[0018] The beneficial effects of the present invention are: Through the method of the present invention, the key tolerance range can be optimized without reducing the influence of aerodynamic performance, and the blade processing error rate can be reduced. The present invention is suitable for the key tolerance optimization research of compressor blades of different types and sizes. The established proxy model has good generalization performance and high fitting accuracy. At the same time, the optimization method has extremely high efficiency, which provides an effective means to reduce the blade processing error rate and improve the blade processing production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic flow chart of a method for optimizing key tolerances of aero-engine compressor blades according to the present invention; Figure 2 Schematic diagram of the distribution of maximum thickness error in an embodiment of the present invention; Figure 3 Schematic diagram of the distribution of the maximum value error of the leading edge profile in an embodiment of the present invention; Figure 4 Schematic diagram of the distribution of the minimum error of the leading edge profile in an embodiment of the present invention; Figure 5 Schematic diagram of the distribution of torsion angle error in an embodiment of the present invention; Figure 6 It is a schematic diagram of a two-dimensional profile curve of a blade cross section in an embodiment of the present invention; Figure 7 A schematic diagram of the division of different regions of a blade in an embodiment of the present invention; Figure 8 A curve diagram showing the variation of the Hanning window weight function value with the sample points in an embodiment of the present invention; Fig. 9 A schematic diagram of a torsion angle error in an embodiment of the present invention; Fig.10 The error blade profile diagram of adding all types of key processing errors in the embodiment of the present invention; Fig.11 It is a diagram illustrating CFD numerical simulation conditions in an embodiment of the present invention; Fig.12 A schematic diagram of the topological structure of a BP neural network in an embodiment of the present invention; Fig.13 A flowchart of optimizing blade key tolerances based on a sparrow search algorithm in an embodiment of the present invention; Fig.14 A schematic diagram showing the comparison between the predicted value and the true value of the sample points in the test set in an embodiment of the present invention; Fig.15 is a frequency distribution histogram of relative errors of sample points in a test set in an embodiment of the present invention; Fig.16 A schematic diagram showing a comparison between the original tolerance range of maximum thickness and the optimized tolerance range in an embodiment of the present invention; Fig.17 A schematic diagram showing a comparison between an original tolerance range and an optimized tolerance range of the maximum value of the leading edge profile in an embodiment of the present invention; Fig.18 Schematic diagram of comparison between the original tolerance range and the optimized tolerance range of the minimum value of the leading edge profile in an embodiment of the present invention; Fig.19 Schematic diagram of comparison between the original tolerance range and the optimized tolerance range of the torsion angle in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] An embodiment of a method for optimizing key tolerances of an aero-engine compressor blade according to the present invention is as follows: Figure 1 As shown, including: S1. Obtain the maximum tolerance deviation coefficient corresponding to each tolerance; Specifically, machining error data of key machining errors of compressor blades are obtained, and the maximum tolerance deviation coefficient corresponding to each tolerance is obtained according to the distribution range of the machining error data of each key machining error and the corresponding original tolerance range.

[0023] In this embodiment, the steps for obtaining the maximum tolerance offset coefficient corresponding to each tolerance are: taking the ratio of the maximum limit value of the distribution range of the machining error data of each key machining error to the maximum limit value of the corresponding tolerance range as the first ratio; taking the ratio of the minimum limit value of the distribution range of the machining error data of each key machining error to the minimum limit value of the corresponding tolerance range as the second ratio; taking the maximum value between the absolute value of the first ratio and the absolute value of the second ratio as the maximum tolerance offset coefficient.

[0024] Step 11. Determine the maximum tolerance deviation factor for the maximum thickness tolerance: In this embodiment, the tolerance range of the maximum thickness error of the two-dimensional cross-sectional profile is determined to be (-0.150mm, +0.150mm) according to the blade design drawing, that is, the upper limit deviation is +0.150mm and the lower limit deviation is -0.150mm. The distribution of the processing error data of the maximum thickness error of the two-dimensional cross-sectional profile of the 38 blades at the same height is shown in the figure. Figure 2 As shown, Figure 2 The horizontal axis represents the blade number, and the vertical axis represents the processing error value of the maximum thickness error. Figure 2 It can be seen that a total of 10 data points are outside the tolerance range of the maximum thickness error, of which 6 data points exceed the upper limit deviation and 4 data points exceed the lower limit deviation. This phenomenon shows that under the existing process capabilities, the maximum thickness error has a relatively obvious over-tolerance situation. Figure 2It can also be found that the distribution range of all processing error data is between [-0.230mm, 0.240mm], so the maximum value of the tolerance offset coefficient of the maximum thickness tolerance is set to 1.60 in this example, that is, this example will explore the influence of the maximum thickness error on the aerodynamic performance of the blade within the range of [-0.240mm, +0.240mm] to obtain the total pressure loss coefficient value.

[0025] Step 12: Determine the maximum tolerance deviation factor of the leading edge profile tolerance: For the maximum and minimum leading edge profile errors, the tolerance range marked on the blade design drawing is [-0.030mm, +0.030mm], that is, the upper limit deviation is +0.030mm and the lower limit deviation is -0.030mm. The distribution of the sample data of the maximum leading edge profile error of 38 blade cross-section two-dimensional profiles in this example is as follows: Figure 3 As shown in the figure, the distribution of the minimum error sample data of the leading edge profile of the 38 blade cross-section two-dimensional profiles in this example is as follows: Figure 4 As shown, from Figure 3 and Figure 4 It can be seen that the maximum and minimum errors of the leading edge profile are both seriously out of tolerance. Not only are there many data points that exceed the tolerance range, but the data points also deviate seriously from the upper and lower limit deviation lines. Among them, the maximum error data of the leading edge profile exceeds the upper limit deviation by up to 3 times, with a maximum of 0.095mm. The sample data of the minimum error of the leading edge profile deviates from the lower limit deviation by up to -0.053mm.

[0026] Combination Figure 3 The maximum error data of the leading edge profile shown and Figure 4 The distribution range of the leading edge profile minimum error data points is shown in the figure. Considering that both the leading edge profile maximum error and the leading edge profile minimum error belong to the leading edge profile error, the two together reflect the processing level of the leading edge position of the blade. Therefore, the maximum value of the tolerance offset coefficient of the leading edge profile tolerance is set to 2.50 in this example. This setting indicates that this example will study the influence of the leading edge profile error on the aerodynamic performance parameters within the leading edge profile error distribution range of [-0.075mm, 0.075mm]. Although this maximum tolerance offset coefficient value does not include all data points, it already includes 80% of the data points. Moreover, since the leading edge has a significant impact on the aerodynamic performance, the setting of the leading edge profile tolerance offset coefficient should be more cautious.

[0027] Step 13: Determine the maximum tolerance deviation factor of the torsion angle tolerance: The lower limit deviation requirement for the torsion angle of the blade cross section with a span height of 352.742 mm on the design drawing is -0.250 , the upper limit deviation requirement is +0.250 The 38 blade torsion angle error data measured in this example are as follows: Figure 5 As shown in the figure, the horizontal axis is the blade number and the vertical axis is the error value. Figure 5 It can be seen that although the deviation of the torsion angle is not as serious as the deviation of the leading edge profile, it cannot be ignored. The distribution range of the data points in the figure is [-0.450 , +0.480 ], based on this range, this example sets the maximum tolerance deviation coefficient of the torsion angle tolerance to 1.92, that is, this example will be in [-0.480 , 0.480 ] to study the mapping relationship between torsion angle error and aerodynamic performance within the range of , and to find the maximum torsion angle tolerance that meets the aerodynamic performance requirements.

[0028] S2. Obtain the total pressure loss coefficient value of the error blade profile; Specifically, all machining error combinations of all key machining error types are designed based on the full factor method and the error blades of the corresponding error combinations are constructed. Then, CFD numerical simulation is performed to obtain the total pressure loss coefficient value of the error blades of all key machining error types under each machining error combination. That is, the error sampling values ​​of different types of key machining errors are set according to the distribution range of the error data; the original design blade is constructed using the NURBS method and the blade curve is discretized to obtain discrete points, the error values ​​corresponding to each type of key machining error are inserted into the corresponding discrete points, and then the error blade is fitted using the NURBS method; the total pressure loss coefficient of the error blade under different error sampling value combinations of all key machining error types is obtained by performing CFD numerical simulation on the error blade.

[0029] Step 21: The steps of setting the error sampling values ​​of different types of key processing errors according to the distribution range of the error data are as follows: Taking into account the different values ​​of the maximum tolerance deviation coefficients of different types of tolerances, this example sets sampling points (-0.240, -0.160, -0.008, 0, 0.008, 0.160, 0.240) for the maximum thickness error, that is, the aerodynamic performance of the two-dimensional blade profile when the maximum thickness error values ​​are -0.240 mm, -0.160 mm, -0.008 mm, 0 mm, 0.008 mm, 0.160 mm and 0.240 mm are studied respectively. The sampling points (-0.480, -0.360, -0.240, -0.120, 0, 0.120, 0.240, 0.360, 0.480) are set for the torsion angle error, that is, the aerodynamic performance of the two-dimensional blade profile when the torsion angle error is -0.480°, -0.360°, -0.240°, -0.120°, 0°, 0.120°, 0.240°, 0.360° and 0.480° are studied respectively. Since the leading edge profile error is at the starting position of the airflow, it has a significant impact on the aerodynamic performance of the blade. At the same time, because the maximum tolerance deviation coefficient of the leading edge profile tolerance is the largest among these key tolerances, in order to ensure the accuracy of the subsequent proxy model, the setting of the error sampling point interval should be more precise. In this example, the leading edge profile error sampling points are set to (0, ±0.0075, ±0.015, ±0.0225, ±0.030, ±0.0375, ±0.045, ±0.0525, ±0.060, ±0.0675, ±0.075) mm. The positive and negative signs represent the error range. Taking ±0.045 mm as an example, it means that the leading edge profile error is at (-0.045 mm, 0.045 mm). Setting the leading edge profile error range in this way actually ensures that the maximum and minimum values ​​of the leading edge profile error are both within the same range and opposite to each other. At the same time, it covers most of the leading edge profile error maximum value data and the leading edge profile error minimum value data. So far, since 7 sampling points are set for the maximum thickness error, 9 sampling points are set for the torsion angle error, and 11 sampling points are set for the leading edge profile error, based on the full factor method, this example needs to construct 7*9*11=693 combinations of error sampling values ​​of different levels for different types of errors, corresponding to 693 different error blade shapes. This also indicates that a total of 7*9*11=693 CFD numerical simulations of error blade shapes will be required for this example in the future.

[0030] Step 22: Use the NURBS method to construct the original design blade profile, and insert the error sampling value corresponding to each type of key processing error into the original design blade profile to fit the error blade profile. The steps are as follows: In practical engineering applications, the description of blade profile curves is usually achieved by fitting discrete curve coordinate points. This requires the use of parametric methods to describe the blade profile curve to ensure that the blade profile curve has continuity and smoothness without distortion. Figure 6 shown.

[0031] Step 221: Parameterization of the original blade design: In this example, the NURBS method is used to fit the two-dimensional contour curve of the original blade design, thus laying the foundation for constructing the blade profile curve with error based on the original blade profile curve. NURBS (Non-uniform rationalB-Spline) is the full name of non-uniform rational B-spline curve, which is developed based on non-rational Bezier curve and non-rational B-spline curve. It is a parametric method that can flexibly describe and control the shape of the blade profile curve. k The expressions of the sub-NURBS equations and rational basis functions are: (1) in, is the weight factor, which represents the influence of the control point on the blade curve and satisfies ; As control point, by controlling Ability to connect points in sequence to form polygons; for k The subnormal B-spline basis function can be represented by the knot vector Determined by the DeBoer-Cox formula; is the mathematical expression of NURBS curve; for k Rational basis functions for sub-NURBS (Non-Uniform Rational B-Splines) equations.

[0032] Node Vector It can be determined by parameterizing the cumulative chord length. The specific calculation formula is as follows: (2) in, is the chord length vector, is called the forward difference vector.

[0033] Step 222: Error blade profile modeling: According to the key blade machining error types determined by previous scholars, namely the maximum thickness error, the leading edge profile error (including the leading edge profile maximum error and the leading edge profile minimum error) and the torsion angle error. This section will divide the blade two-dimensional contour area based on these four key machining error types, and add different types of errors to the corresponding area discrete points, and then construct the blade contour curve with error (i.e., construct the error blade profile) through the NURBS method.

[0034] It should be noted that in order to simulate the actual processing of the leading edge contour curve, the error added to the leading edge contour is to first add random errors to the discrete data points of the leading edge contour, and then use the NURBS method to perform curve fitting. Different from the method of adding the leading edge contour error, the method of adding the maximum thickness error to the blade two-dimensional contour curve is: first add the target error value at the maximum thickness position, then use the Hanning window function as the weight function, continue to add errors on both sides of the maximum thickness position, and finally use the NURBS method to perform curve fitting. One reason for this is that the maximum and minimum errors of the leading edge contour belong to the contour error, while the maximum thickness error and the torsion angle error belong to the characteristic parameter error. Another important reason is that this example wants to simulate the actual processing of the leading edge contour curve. Using the NURBS method to fit the discrete data points with random errors can retain the peak and trough characteristics of the actual blade leading edge contour curve, and avoid the appearance of the cusp area, because the cusp generally does not appear in the blade leading edge contour after milling and polishing.

[0035] Some scholars have pointed out that the first 15% chord length area of ​​the blade profile curve contains the entire leading edge of the blade profile, and this area has a more obvious impact on the blade performance. Based on this view, this section first normalizes the chord length so that the chord length remains parallel to the horizontal axis. Then, as Figure 7 As shown in the figure, the front 15% chord length area in the blade profile curve is defined as the leading edge area, and the rear 15% chord length area is defined as the trailing edge area accordingly, and the 16%-85% chord length area is divided into the blade basin and blade back area. Since the maximum thickness position is usually in the blade basin and blade back area, there is an overlapping area between the maximum thickness area and the blade basin and blade back area. In order to reduce the impact of adding the maximum thickness error in the maximum thickness area on the blade basin and blade back area, only the front 5% and rear 5% chord length areas where the maximum thickness is located are divided into the maximum thickness area.

[0036] Step 2221, construct the maximum thickness contour curve of the error blade profile: Since the maximum thickness error is a parameter error, in order to ensure that the blade curve remains smooth after adding the maximum thickness error in the maximum thickness area, this example uses the Hanning window function as the weight function to perform weighted processing on the errors added to each discrete point in the maximum thickness area. The definition of the Hanning window function is as follows: (3) In the formula, n is the sample point number in the window, starting from 0. N Represents the length of the window function or the total number of sample points. Also, because the maximum thickness error is a parameter error, when adding the error in the maximum thickness area of ​​the blade 2D profile, half of the error value is added to the suction side and half to the pressure side.

[0037] The number of sample points of the weight function is set according to the number of discrete points in the maximum thickness area, so that the weight function value increases from 0 to 1 and then slowly decreases to 0. The weight function value changes with the sample points as shown in Figure 8 As shown in the figure. This change makes the error value gradually increase and then decrease in the maximum thickness area, ensuring the smoothness of the curve in this area. After adding the generated error value to the corresponding discrete point, the maximum thickness area contour curve of the error blade can be fitted by the NURBS method.

[0038] Step 2222, constructing a leading edge contour curve of the error blade profile; The leading edge profile error belongs to the profile error, so the way to add the leading edge profile error to the two-dimensional blade profile curve is different from the maximum thickness error. When adding the leading edge profile error, it is first necessary to clarify the leading edge profile error range, that is, the maximum and minimum values ​​of the leading edge profile. Then, according to the number of discrete points in the leading edge part, random error data that obeys the normal distribution within the error range is generated. Next, the generated random error data is added to the corresponding discrete points of the leading edge part in sequence. Finally, the known discrete points are fitted using the NURBS method to construct the two-dimensional profile leading edge curve of the blade with error (that is, the leading edge profile curve of the error blade). Adding errors in this way can simulate the real leading edge profile curve after blade milling and polishing, and retain the peak and trough characteristics of the real profile. The decision to add a normally distributed error to the leading edge profile of the blade here refers to the conclusion of previous scholars on the statistical analysis of the measured compressor blade profile error.

[0039] Step 2223, determining the twist angle of the error blade profile; Torsion angle error is a type of form and position error in blade processing quality inspection. In actual inspection, in order to correspond to the blade design, the contour method is usually used to measure the two-dimensional cross-sectional profile of the blade. The torsion angle is an important design parameter of the compressor elementary blade grid, which determines the installation direction of the blade profile in the blade grid. Although the machining accuracy of compressor blades has improved with the development of current CNC machine tools and the continuous improvement of manufacturing processes, the compressor blades are typical "cantilever beam" structures, coupled with the material stress release of the blades after three-dimensional distortion and the action of normal force during high-speed tool cutting, the elementary blade grid will deflect around its center of gravity, resulting in "over-deflection" or "under-deflection". This results in the actual installation angle of each elementary blade grid of the blade. Deviation from the design installation angle , thus forming a torsion angle error , the actual installation angle , Design installation angle , torsion angle error The specific relationship between them is: . Fig. 9 Installation angle for design , Actual installation angle And the torsion angle error When using CFD method for numerical calculation, the addition of torsion angle error can be achieved by changing the angle of attack: At this point, based on the contour curve of the original design blade, the maximum thickness error and the leading edge profile error are added to the discrete points of the maximum thickness area and the leading edge area of ​​the original design blade respectively, and the contour curves of all error blades are constructed by fitting all discrete points through the NURBS method. Fig.10 The addition of torsion angle error can be achieved by changing the angle of attack.

[0040] Step 223, CFD numerical simulation of error blade profile; This embodiment uses the total pressure loss coefficient as the aerodynamic performance evaluation index, and the specific calculation formula is: (4) In the formula, is the total inlet pressure; is the total outlet pressure; is the inlet static pressure.

[0041] The NUMECA FINE / Turbo module is used to perform CFD numerical simulation of the two-dimensional error blade profile, and the incoming flow Mach number is set to 0.7. The Reynolds-Averaged Navier-Stokes (RANS) method is used to solve the aerodynamic performance, and the Spalart-Allmaras (SA) turbulence model is selected to close the RANS control equation. Fig.11The computational grid and computational domain of the error blade are shown. The O4H type grid of the blade channel domain is generated by the NUMECA Autogrid.5 module, and the total number of grids is about 9.83×104. In order to meet the requirements of the SA turbulence model for the grid near the wall, the first layer of grid size is set to 106 to ensure that y+ is less than 3, and y+, that is, the first three layers of grids, are located in the viscous bottom layer. The inlet boundary conditions of the computational domain of the CFD numerical simulation include total pressure, total temperature (300.0K) and airflow angle; the static pressure (101300Pa) is given at the outlet boundary. The distance from the inlet of the computational domain to the leading edge is 1.0 times the chord length, and the extension section of the trailing edge is 2.5 times the chord length to ensure sufficient mixing of the outlet airflow. This example uses a two-dimensional error blade, so periodic boundary conditions are set along the pitch direction, and all solid walls are set as no-slip boundaries. Through numerical simulations corresponding to the number of error blades, the total pressure loss coefficients of all error blades are obtained.

[0042] S3, obtain the proxy model of key processing error-aerodynamic performance; Specifically, a neural network is constructed, each combination of all kinds of key processing errors is used as the input of the neural network, the total pressure loss coefficient value of the error blade corresponding to each processing error combination is used as the output of the neural network, and the neural network is trained to obtain a trained processing error-aerodynamic performance proxy model.

[0043] Step 31: Build the dataset: The total pressure loss coefficient of each error blade profile and the corresponding error sampling value are combined as a set of sample data, thereby obtaining multiple sets of sample data corresponding to different error blade profiles, thereby forming a data set of the key processing error of the blade - the total pressure loss coefficient.

[0044] Step 32: Build a neural network: In this embodiment, a BP neural network with a topological structure of 4-5-5-1 is constructed, and each group of error sampling values ​​in the data set is used as the input of the BP neural network. The total pressure loss coefficient of the error blade corresponding to the group of error sampling values ​​is used as the output of the BP neural network. The BP neural network is trained to obtain a trained processing error-aerodynamic performance proxy model.

[0045] Step 321, network initialization: The neural network has four inputs, namely the maximum thickness error, the maximum leading edge profile error, the minimum leading edge profile error and the torsion angle error. For each set of sample data, the maximum leading edge profile error and the minimum leading edge profile error should be in a positive and negative relationship, and the two together represent the range of the leading edge profile error. Therefore, the number of nodes in the input layer of the neural network is 4. The aerodynamic performance parameter selected by the present invention is the total pressure loss coefficient, so the output layer of the neural network contains only one node. The performance of different combinations of hidden layers and nodes was evaluated through cross-validation, and it was finally determined to set 2 hidden layers for the neural network structure, and each hidden layer contains 5 nodes. After this setting, you can get a Fig.12 The 4-5-5-1 BP neural network topology is shown. Fig.12 middle, represents the weight from the input layer to the first hidden layer, represents the weight from the first hidden layer to the second hidden layer, Represents the weights from the second hidden layer to the output layer. represents the bias from the input layer to the first hidden layer, represents the bias from the first hidden layer to the second hidden layer, Represents the bias from the second hidden layer to the output layer. For other hyperparameters of the BP neural network, set the learning rate η =0.001, select is the activation function.

[0046] Step 322, input layer: The input data is a combination of the sampling points of the four key errors at all levels. Since the dimensions of different types of error data vary greatly and their distribution ranges are different, in order to eliminate the adverse effects of the dimensions and ranges of different error data on the model, as well as to improve numerical stability and model performance, the error data needs to be normalized before inputting into the neural network. This example uses Z-score normalization to normalize the error data, and the calculation formula is as follows: (5) in: Indicates i Error data, Represents the normalized i Error data is the mean of the error data; is the standard deviation of the error data.

[0047] The sample data matrix of the error sampling value of the processing error input into the network after normalization is as follows: (6) in: is the total number of types of key blade machining errors entered and N =4, is the number of samples of each type of key processing error, Indicates m The sample group n Sample data of error types, m The value of is [1, M ], n The value of is [1, N ].

[0048] Step 323, hidden layer: According to the data forward propagation principle of BP neural network, the output of the first hidden layer for (9) represents the weight from the input layer to the first hidden layer, represents the bias from the input layer to the first hidden layer, Represents the first sample of each group after normalization i Error data.

[0049] The output of the second hidden layer for (10) represents the weight from the first hidden layer to the second hidden layer, Represents the bias from the first hidden layer to the second hidden layer. The weight matrix and bias matrix from the input layer to the first hidden layer are: (11) The weight matrix and bias matrix from the first hidden layer to the second hidden layer are: (12) Step 324, output layer: Output of the output layer for: (13) represents the weight from the second hidden layer to the output layer, Represents the bias from the second hidden layer to the output layer.

[0050] The weight matrix from the second hidden layer to the output layer is: (14) Step 325, BP neural network training mean square error and determination coefficient: The mean square error formula for neural network training is: (15) in, is the expected output, i.e. the true value. Predicted values ​​for the neural network. M is the number of all predicted values. is the error between the expected output and the output layer output, and .

[0051] Neural network regression fitting determination coefficient The calculation formula is as follows: (16) in is the mean of the true values ​​of the samples. R 2 It can be used to measure the degree to which the model explains the target variable during the training process, and its value range is 0 to 1. R 2 The closer it is to 1, the better the explanatory power of the constructed BP neural network is for the target variable and the better the regression performance is.

[0052] Step 326, weight and bias update: This example uses the mean square error (MSE) as the loss function and updates the weights and biases of each layer based on the gradient descent method.

[0053] Step 327, iterative update end criteria: During three consecutive training sessions MSE The difference is less than a certain threshold When , the performance of the model is considered stable and the iterative update can be terminated. At the same time, in order to avoid setting the threshold too low, which will increase the training time and cause overfitting, the maximum number of iterations is set to 1000.

[0054] At this point, the trained processing error-aerodynamic performance proxy model can be obtained.

[0055] S4, construct fitness function; Specifically, an out-of-tolerance range is obtained based on the error range and tolerance range of the machining error data of each key machining error, a target data is randomly selected from each out-of-tolerance range to form the target input data, and the target input data is input into the proxy model to obtain the target aerodynamic loss coefficient value; one data is selected from the original tolerance range of each key machining error to form a group of original data, and the proxy model is used to obtain the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data; a constraint violation function is obtained based on the target aerodynamic loss coefficient value and the maximum aerodynamic loss coefficient value, and a fitness function is constructed based on the constraint violation function, the maximum tolerance offset coefficient corresponding to each tolerance, and the target input data.

[0056] The expression of the fitness function is:

[0057] In the formula, Represents the fitness function value; The maximum tolerance deviation factor indicating the maximum thickness error; The maximum tolerance deviation factor representing the leading edge profile error; The maximum tolerance deviation factor indicating the torsion angle error; Indicates the target data selected within the tolerance range of the maximum thickness error; Indicates target data selected within the tolerance range of leading edge profile error; Indicates target data selected within the tolerance range of the torsion angle error; Expressed as a penalty factor; represents the constraint violation function value, Indicates taking the absolute value.

[0058] Step 41, the corresponding fitness function during upper limit deviation optimization is: In this implementation, since the total pressure loss coefficient of the two-dimensional blade profile has different sensitivities to the four key processing errors, the total pressure loss coefficient of the blade has different trends with the error in different error ranges (referring to the two ranges of 0 to the lower limit deviation and 0 to the upper limit deviation). In such an engineering context, the blade tolerance range optimization problem is decomposed into upper limit deviation optimization and lower limit deviation optimization. Different fitness functions are used for the two decomposed optimization problems. For the upper limit deviation optimization problem, the following function is used as its fitness function, and the specific expression is: (17) In the formula, Represents the fitness function value during upper limit deviation optimization; K 1 represents the maximum tolerance deviation factor of the maximum thickness tolerance, which is 1.6; Indicates the target maximum thickness upper limit deviation value selected within the tolerance range of the maximum thickness upper limit deviation [0.150, 0.240]; K 2 represents the maximum tolerance deviation factor of the leading edge profile tolerance, and its value is 2.5. Indicates the upper limit deviation value of the target leading edge profile selected within the tolerance range of [0.030, 0.075] of the upper limit deviation of the leading edge profile. K 3 represents the maximum tolerance deviation coefficient of the torsion angle tolerance, and its value is 1.92. Indicates the target torsion angle upper limit deviation value selected within the torsion angle upper limit deviation tolerance range [0.250, 0.480]. It is expressed as a penalty factor, and the value here is 1000; g is the constraint violation function.

[0059] The expression of constraint violation function is: (18) In the formula, Indicates that , , , Substitute the aerodynamic loss coefficient value calculated by the trained proxy model. This example has only three optimization variables, while the established BP proxy model has four input variables. The main reason for this is that the four input variables of the BP proxy model are the maximum thickness error, the maximum leading edge profile error, the minimum leading edge profile error, and the torsion angle error. When optimizing the tolerance in this example, the upper and lower limits of the tolerance are optimized separately, and the maximum leading edge profile error and the minimum leading edge profile error represent the upper and lower limits of the leading edge profile tolerance, respectively, and together represent the leading edge profile tolerance range. Since the upper and lower limits of the tolerance range are generally positive and negative numbers, here we set = - ,Right now When the BP proxy model is used for calculation, the minimum leading edge profile error and the maximum leading edge profile error have an opposite numerical relationship. It means that one data is selected from the original tolerance range of each key processing error to form a group of original data, and the proxy model is used to obtain the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data, that is, the maximum value of the total pressure loss coefficient of the blade that can be calculated within the original maximum thickness tolerance range [-0.150, +0.150], the original leading edge profile tolerance range [-0.030, +0.030], and the original torsion angle tolerance range [-0.250, +0.250].

[0060] A careful observation of the constraint violation function and the fitness function reveals that if , , The corresponding total pressure loss coefficient is [0, ], then the fitness function value will be a smaller value, only affected by , , However, if , , The corresponding total pressure loss coefficient exceeds , then due to the penalty factor If the value is set large, the obtained fitness will be large. These sparrows with large fitness values ​​tend to move towards the current optimal position when updating their positions. Combined with the engineering background of the fitness function setting in this example, this movement towards the current optimal position can be regarded as the movement of the sparrow population towards the optimal position that satisfies both the constraint conditions (i.e., the total pressure loss coefficient satisfies [0, ]), and then iteratively updates towards the position with a smaller fitness function value. In general, the fitness function setting of this example has the following three advantages: First, it reflects the urgency of optimizing the three key errors (i.e., the larger the tolerance offset coefficient, the more the tolerance range needs to be optimized); second, it reflects the error type that is most likely to exceed the tolerance under the existing process conditions (i.e., the larger the tolerance offset coefficient, the more obvious the excess tolerance phenomenon of this type of error); third, the fitness function ensures that the aerodynamic performance of the blade does not increase when the tolerance optimization is performed.

[0061] For the lower limit deviation optimization problem, the following function is used as its fitness function, and the specific expression is: (20) In the formula, Represents the fitness function value during the lower limit deviation optimization; K 1 represents the maximum tolerance deviation factor of the maximum thickness tolerance, which is 1.6; Indicates the target maximum thickness lower limit deviation value selected within the tolerance range of the maximum thickness lower limit deviation [-0.150, -0.240]; K 2 represents the maximum tolerance deviation factor of the leading edge profile tolerance, and its value is 2.5. Indicates the target leading edge profile lower limit deviation value selected within the leading edge profile lower limit deviation tolerance range [-0.030, -0.075], K 3 represents the maximum tolerance deviation coefficient of the torsion angle tolerance, and its value is 1.92. Indicates the target torsion angle lower limit deviation value selected within the torsion angle lower limit deviation tolerance range [-0.250, -0.480]. It is expressed as a penalty factor, and the value here is 1000; g is the constraint violation function.

[0062] S5. Obtain the final tolerance range of each key processing error; Specifically, the target input data is taken as the optimization target, and the target input data is optimized based on the fitness function and the sparrow search algorithm until the fitness function value is maximized. The final tolerance range of each key processing error is obtained according to the target input data corresponding to the minimum fitness function value.

[0063] Sparrow Search Algorith (SSA) is a new intelligent swarm optimization algorithm first proposed in 2020 based on the foraging behavior of sparrows and the behavior of dealing with natural enemies. Some scholars have compared the performance of various swarm intelligent optimization algorithms through experiments and found that SSA has higher search accuracy, shorter optimization time and faster convergence speed. Fig.14 To illustrate the process of blade tolerance optimization using the sparrow search algorithm in this embodiment: Step 51, population initialization: In an experiment simulating predation on a sparrow population, n The population of sparrows can be expressed in the form of a matrix: (twenty one) In the formula, n is the number of sparrows in the population; d Indicates the dimension of the variable to be optimized. Combined with the optimization goal of this example, it can be determined d =3; In the technical background of the present invention, the physical meaning of the sparrow is the combination of the maximum thickness error, the leading edge profile error and the torsion angle error in their respective tolerance ranges, and different value combinations represent different sparrow individuals. n Individual sparrows constitute a population.

[0064] Step 52, fitness function: The fitness function is set according to step S4.

[0065] Step 53, discoverer location update: In the entire population, the finder is responsible for finding food and providing foraging areas and directions for the entire sparrow population. Its position update formula is: (twenty two) In the formula, t Indicates the current iteration number; is the maximum number of iterations, which is a constant; For the i A sparrow in j The location information in the dimension and j =1, 2, 3; is a random number with a value range of ∈(0,1]; R 2 is the warning value, R 2∈[0,1]; ST is a safe value, ST ∈[0.5, 1]; B is a random number that follows a normal distribution; L is a 1× d A matrix in which all elements are 1. R 2< ST When , it indicates that there are no natural enemies around the sparrow population, the entire population is in a safe environment, and the sparrows can forage safely; when R 2≥ ST When it is detected, it indicates that natural enemies have been found around the sparrow population. The sparrows are in danger and need to fly to a safe area immediately to search for new food.

[0066] Step 54: Follower location update: In the entire population, followers closely monitor the behavior of discoverers. Once a discoverer finds a food source, followers will immediately follow the discoverer to grab the food. In the sparrow search algorithm, followers correspond to individuals with relatively low fitness values. They update their positions by following the discoverer to find a better solution. In addition, some followers may constantly monitor the discoverer to compete for food resources, which is manifested in the algorithm as a competitive and cooperative relationship between individuals. The formula for followers to update their positions based on the information of the discoverer is: (twenty three) Where: Indicates the current global optimal position; is a random number that follows a normal distribution; Indicates the current global worst position; A + =A T (AA T ) -1 , where A is a 1× d The elements in the matrix are randomly assigned 1 or -1; when i > n / 2, indicating the i The follower is now in the worst foraging area and is facing hunger. It needs to find other areas to forage for food to replenish energy.

[0067] Step 55, scout position update: In the population, the scout is responsible for monitoring the area around the foraging area. When a predator (or danger) appears around the foraging area, the scout will immediately issue an early warning. In the algorithm, the scout corresponds to an individual with specific responsibilities. They are responsible for monitoring abnormal situations in the search process, such as falling into a local optimal solution or encountering an infeasible solution. When the vigilant issues an early warning, the entire sparrow population will adjust its search strategy to avoid getting into trouble or find a new search direction. The mathematical expression for the scout's position update is: (twenty four) Where: Indicates the optimal position in the current group; The moving step length control parameter for controlling the global optimal position is a random parameter that conforms to the normal distribution and has a value range of [0, 1]; K It is also a random number and its value range is [-1, 1]; in order to avoid the denominator being 0, a minimum constant is added ; Represents the fitness function value of the current sparrow individual; and They represent the best and worst fitness function values ​​in the entire population respectively. In this example, when using the sparrow search algorithm to optimize the leaf tolerance, there are 20 sparrows in the population, of which 70% are discoverers, 30% are followers, and 20% are discoverers. The warning value is set to 0.6, and the maximum number of iterations is set to 50.

[0068] At this point, the target input data is taken as the optimization target, and the target input data is optimized based on the fitness function during the upper limit deviation optimization and the sparrow search algorithm until the fitness function value during the upper limit deviation optimization is maximized. The final upper limit tolerance of the final tolerance range of each key machining error is obtained according to the target input data corresponding to the minimum fitness function value during the upper limit deviation optimization, that is, the final upper limit tolerance corresponding to the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance is obtained; the target input data is taken as the optimization target, and the target input data is optimized based on the fitness function during the lower limit deviation optimization and the sparrow search algorithm is used. The optimization is performed until the fitness function value during the lower limit deviation optimization is the maximum. The final lower limit tolerance of the final tolerance range of each key machining error is obtained according to the target input data corresponding to the minimum fitness function value during the lower limit deviation optimization, that is, the final upper limit tolerance corresponding to the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance is obtained; the final upper limit tolerance corresponding to the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance is obtained; the final upper limit tolerance corresponding to the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance is obtained; the final tolerance range corresponding to the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance is obtained.

[0069] The following is a simulation verification of this embodiment: This example illustrates the method of the present invention based on the optimization of the maximum thickness tolerance, leading edge profile tolerance and twist angle tolerance of a blade cross section at a spanwise height of 352.742 mm for a certain type of low-pressure compressor.

[0070] In this example, the BP neural network model is constructed using MATLAB software according to the BP neural network hyperparameter settings and topology structure established in step S3. All 693 groups of sample data are randomly shuffled, and then 90% of the sample data are divided into the training set and 10% into the test set. The constructed neural network is trained with the training set data, and the fitting effect and prediction accuracy of the trained neural network model are tested with the test set. According to the grouping method of the original sample data set, the number of samples for each type of key processing error in step S3 can be determined. M =616. The constructed neural network is iteratively trained with the training set data. After 513 iterations of training, the iterative update termination condition is reached. At this time, the training set MSE 6.5×10 -6 , R 2 The total pressure loss coefficient of the error sample data in the test set is predicted using the trained BP neural network. MSE and R 2 They are 9.7×10 -6 and 0.9842. By comparison, it can be found that the two indicators of the training set and the test set are not much different, indicating that the trained BP neural network shows good performance on the test set, indicating that the model has good generalization ability.

[0071] like Fig.14 As shown, Fig.14 The predicted values ​​and true values ​​of the sample points in the test set are compared, and a relative error band of ±5% is given. Fig.14 A ±5% error band is also given to show the relative error and error distribution characteristics of the prediction. Fig.14 There are 77 data points in total. The horizontal coordinates of these points are the true values, and the vertical coordinates are the predicted values ​​of the constructed neural network model. Ideally, if the true value and predicted value of each data point are equal, then all data points should fall within y = x This straight line. Fig.14 It can be clearly seen that these data points are scattered across y = xOn both sides of this line, most data points fall within the ±5% error band, and a small number of data points fall on the boundary of the error band or outside the error band. This situation shows that the prediction accuracy of the BP neural network agent model based on double hidden layers established in this example can reach 95%, which basically meets the requirements of engineering applications.

[0072] Fig.15 The relative error frequency distribution histogram of all sample data points in the test set is given. The horizontal axis of the figure represents the error of the predicted value relative to the true value, and the vertical axis represents the error distribution density. The curve in the figure is the normal distribution fitting curve of the relative error data. Fig.15 It can be seen that about 15% of the sample data in the test set has an absolute value of relative error exceeding 5%. This indicator seems high, but in fact, combined with Fig.15 From the scattering of sample points in the ±5% relative error band, it can be seen that the relative errors of these data points exceeding 5% are only slightly more than 5%, not much more than 5%. Although there are a lot of sample points with absolute relative errors exceeding 5%, the absolute relative errors are small, around 5%, and not more than 6%, so this situation is completely acceptable. It can also be clearly seen from the frequency distribution histogram that the number of sample points with a relative error less than -5% is about twice the number of sample points with a relative error greater than +5%. Another thing we can see intuitively is that the number of sample points with a relative error in the range of (-2.5%, 2.5%) accounts for about 55% of the number of sample points in the test set, while the number of sample points with a relative error in the range of (-5%, 5%) accounts for as much as 85%. These situations further indicate that the prediction accuracy of the proxy model established based on the BP neural network in this example is fully up to standard and can effectively characterize the quantitative relationship between the key blade error and the total pressure loss coefficient.

[0073] Based on the constructed proxy model, the maximum thickness tolerance, leading edge profile tolerance and torsion angle tolerance are optimized according to the method from step S4 to step S5. Among them, the optimization results are compared with the original tolerance band as shown in Table 1. The left column of Table 1 gives the optimization results of the sparrow search algorithm under the condition that the total pressure loss coefficient does not increase, the middle column gives the original tolerance range of the three errors, and the right column gives the optimization results under the condition that the total pressure loss coefficient of the blade increases by 0.005. It can be seen from Table 1 that under the condition that the total pressure loss coefficient does not increase, the optimization result of the lower limit deviation of the maximum thickness is -0.215mm, which is 0.065mm smaller than the original lower limit deviation; the optimization result of the upper limit deviation is +0.183mm, which is 0.033mm larger than the original upper limit deviation. Under the condition that the total pressure loss coefficient does not increase, the optimization result of the lower limit deviation of the leading edge profile tolerance is -0.046mm, which is 0.016mm smaller than the original lower limit deviation, and the optimization result of the upper limit deviation is 0.043mm, which is 0.013mm larger than the original upper limit deviation. Under the condition that the total pressure loss coefficient does not increase, the optimization result of the lower limit deviation of the torsion angle is -0.272°, which is 0.022° smaller than the original lower limit deviation, and the optimization result of the upper limit deviation of the torsion angle is 0.419°, which is 0.169° larger than the original upper limit deviation. In this embodiment, when establishing the key processing error of the blade-aerodynamic performance proxy model, since the leading edge profile error belongs to the profile error, and the maximum thickness error and the torsion angle error belong to the characteristic parameter error, the input related to the leading edge profile error in the proxy model is the upper limit deviation and the lower limit deviation of the leading edge profile, which represents the profile error range of the leading edge of the two-dimensional profile of the blade. When optimizing blade tolerances, we also mentioned the relationship between the three optimization variables and the four inputs of the proxy model for the optimization of upper and lower limit deviations. Therefore, for the leading edge profile tolerance, the optimization result should be the smaller absolute value of the optimization result of the upper limit deviation and the optimization result of the lower limit deviation of the leading edge profile. Therefore, under the condition that the total pressure loss coefficient does not increase, the tolerance optimization result of the leading edge profile error should be [-0.043mm, +0.043mm].

[0074] Table 1

[0075] In order to more intuitively compare the optimization effects of the three tolerance ranges, Figure 16-18 The comparison between the original tolerance range and the optimized tolerance range is given. Fig.16It can be seen that in the maximum thickness error data of the cross section of the 38 blades measured in this paper with a spanwise blade height of 352.742 mm, 10 data points fell outside the original tolerance range, of which 6 exceeded the original upper limit deviation and 4 exceeded the lower limit deviation. If the maximum thickness tolerance optimization results of this paper without losing aerodynamic performance are used as a reference, then only 4 data points fall outside the optimization tolerance range, that is, only 4 blades will fail due to the maximum thickness error exceeding the tolerance, and the tolerance rate of the maximum thickness error of the blade has dropped by 15.77%. In addition, it can be intuitively seen that the optimization effect of the lower limit deviation of the maximum thickness is better than that of the upper limit deviation. After further investigation, this embodiment believes that it is still related to the influence trend of the maximum thickness error on the total pressure loss coefficient of the blade. Combined with the optimization results under the condition of a total pressure loss coefficient increase of 0.005 given in the rightmost column of Table 1 and Fig.16 Judging from the distribution of sample data points, if an increase of 0.005 in the total pressure loss coefficient is acceptable, then at least 80% of the maximum thickness error problem can be solved, that is, among all 10 out-of-tolerance data points, at least 8 blades will be transformed from unqualified to qualified due to the relaxation of the maximum thickness tolerance range.

[0076] The optimization results of the leading edge profile tolerance are analyzed from the same perspective. Fig.17 It can be seen that when the original leading edge profile tolerance range is used to constrain the 38 leading edge profile error maximum measurement data points, 21 leading edge profile error maximum data points fall outside the original tolerance range. Fig.18 It can be seen that when the original leading edge profile tolerance range is used to constrain the 38 leading edge profile error minimum data points, 16 leading edge profile error minimum data points fall outside the original tolerance range. The resulting deviation rates are 55.26% and 42.11%, respectively. If the optimization result of the leading edge profile tolerance [-0.043mm, +0.043mm] under the condition that the total pressure loss coefficient does not increase is used as the evaluation standard, then the deviation rates are 23.68% and 15.79%, respectively, which are reduced by 31.58% and 26.32%, respectively. Fig.17 and 18 It can also be seen that, taking the optimized tolerance range as the evaluation index, among the data points with the maximum value of the leading edge profile error, only one data point is smaller than the lower limit deviation of the leading edge profile, and among the data points with the minimum value of the leading edge profile error, only one data point is larger than the lower limit deviation of the leading edge profile.

[0077] Fig.19 The optimization results of the torsion angle tolerance without loss of aerodynamic performance are given in this paper. Fig.19It can be clearly seen that among the 38 torsion angle error data points, 13 data points are scattered outside the original torsion angle tolerance range, of which 7 data points exceed the original upper limit deviation, and 6 exceed the original lower limit deviation. Taking the optimized tolerance range as the upper and lower constraint limits, only 7 error data points are out of tolerance, of which two exceed the optimized upper limit deviation and 5 are lower than the lower limit deviation. This shows that the optimization result of this embodiment is more effective in solving the problem of upper limit deviation out of tolerance. The reason for this phenomenon may be related to the changing trend that the total pressure loss coefficient of the blade decreases with the increase of the torsion angle error. Overall, the optimized torsion angle tolerance range under the condition that the total pressure loss coefficient does not increase can reduce the excess rate from 34.21% to 18.42%, and the excess rate has decreased by 15.79%. Combined with the optimization results of the torsion angle tolerance under the condition that the total pressure loss coefficient increases by 0.005 given in Table 1 and Fig.19 Judging from the distribution of the mean error data, if an increase of 0.005 in the total pressure loss coefficient is acceptable, the deviation rate can be reduced to 7.89%.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing the critical tolerance of an aero-engine compressor blade, characterized in that: include: Obtaining machining error data of key machining errors of compressor blades, and obtaining a maximum tolerance deviation coefficient corresponding to each tolerance according to a distribution range of the machining error data of each key machining error and a corresponding original tolerance range; Based on the complete factor method, all machining error combinations of all key machining error types are designed and the error blade profiles of the corresponding error combinations are constructed. At the same time, CFD numerical simulation is performed to obtain the total pressure loss coefficient value of the error blade profile of all key machining error types under each machining error combination. A neural network is constructed, each combination of all kinds of key machining errors is used as the input of the neural network, the total pressure loss coefficient value of the error blade corresponding to each machining error combination is used as the output of the neural network, and the neural network is trained to obtain a trained machining error-aerodynamic performance proxy model; The out-of-tolerance range is obtained according to the error range and tolerance range of the machining error number of each key machining error, a target data is randomly selected from each out-of-tolerance range to form the target input data, and the target input data is input into the proxy model to obtain the target aerodynamic loss coefficient value; each data is selected from the original tolerance range of each key machining error to form a group of original data, and the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data is obtained by using the proxy model; the constraint violation function is obtained according to the target aerodynamic loss coefficient value and the maximum aerodynamic loss coefficient value, and the fitness function is constructed based on the constraint violation function, the maximum tolerance offset coefficient corresponding to each tolerance, and the target input data; Taking the target input data as the optimization target, the target input data is optimized based on the fitness function and the sparrow search algorithm until the fitness function value is minimum. The final tolerance range of each key machining error is obtained according to the target input data corresponding to the minimum fitness function value.

2. The method for optimizing critical tolerances of aeroengine compressor blades according to claim 1, characterized in that: The key processing errors include: maximum thickness error, maximum leading edge profile error, minimum leading edge profile error and torsion angle error.

3. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 1, characterized in that: The steps to obtain the maximum tolerance deviation coefficient corresponding to each tolerance are: The ratio of the maximum limit value of the distribution range of the machining error data of each key machining error to the maximum limit value of the corresponding tolerance range is taken as a first ratio; The ratio of the minimum limit value of the distribution range of the machining error data of each key machining error to the minimum limit value of the corresponding tolerance range is used as a second ratio; The maximum value of the absolute value of the first ratio and the absolute value of the second ratio is taken as the maximum tolerance deviation coefficient.

4. The method for optimizing critical tolerances of aeroengine compressor blades according to claim 2, characterized in that: Based on the complete factor method, all machining error combinations of all kinds of key machining errors are designed and the error blade profiles of the corresponding error combinations are constructed. At the same time, CFD numerical simulation is performed to obtain the total pressure loss coefficient value of the error blade profile of all key machining error types under each machining error combination. The steps are as follows: Setting error sampling values ​​of different types of key machining errors according to the distribution range of error data; The original design blade profile is constructed using the NURBS method and the contour curve is discretized. The error value of each type of key processing error is inserted into the discrete points of the corresponding area. Then, the discrete points are fitted using the NURBS method to obtain the error blade profile. By performing CFD numerical simulation on the error blade profile, the total pressure loss coefficient of the error blade profile under different error sampling value combinations of all key machining error types is obtained.

5. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 4, characterized in that: The steps of inserting the error sampling values ​​corresponding to each type of key processing error into the original design blade profile to fit the error blade profile are as follows: Discretize the contour curve of the maximum thickness area of ​​the original designed blade to obtain discrete points; Determine the error value at the maximum thickness position, use the Hanning window function as a weight function to weight the error value, and insert the weighted error value into discrete points on both sides of the maximum thickness position in the maximum thickness area; The distribution range of the error data of the leading edge profile is from the minimum value of the leading edge profile to the maximum value of the leading edge profile; Generate random error data that obeys normal distribution within the distribution range of error data of leading edge contour according to the number of discrete points in the leading edge contour area; The generated random error data are sequentially added to the discrete point positions corresponding to the leading edge contour area; After inserting the maximum thickness error and leading edge profile error at the discrete points in the corresponding area, the insertion of the torsion angle error can be achieved by changing the angle of attack of the blade, and thus the contour curve of the error blade is obtained by fitting the NURBS method.

6. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 5, characterized in that: The chord length areas before and after the maximum thickness position are taken as the maximum thickness area.

7. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 1, characterized in that: The steps to obtain the out-of-tolerance range based on the error range and tolerance range of the machining error number of each key machining error are as follows: The maximum limit value of the tolerance range to the maximum limit value of the error range is taken as the maximum limit value deviation range; The minimum limit value of the error range to the minimum limit value of the tolerance range is taken as the minimum limit value deviation range.

8. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 1, characterized in that: The expression of constraint violation function is: In the formula, Represents the constraint violation function value; Indicates that the target input data is The target aerodynamic loss coefficient value output by the proxy model when It means that one data is selected from the original tolerance range of each key processing error to form a group of original data, and the agent model is used to obtain the maximum aerodynamic loss coefficient value among the aerodynamic loss coefficient values ​​corresponding to all groups of original data.

9. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 1, characterized in that: The expression of the fitness function is: In the formula, Represents the fitness function value; The maximum tolerance deviation factor indicating the maximum thickness error; The maximum tolerance deviation factor representing the leading edge profile error; The maximum tolerance deviation factor indicating the torsion angle error; The target data representing the maximum thickness error out-of-tolerance range selection; Target data representing the selection of the tolerance range of the leading edge profile error; Indicates target data for selecting the tolerance range of the torsion angle error; Expressed as a penalty factor; represents the constraint violation function value, Indicates taking the absolute value.

10. The method for optimizing critical tolerances of aero-engine compressor blades according to claim 9, characterized in that: The steps to obtain the final tolerance range based on the target input data corresponding to the minimum fitness function value are: According to the target data corresponding to the tolerance range of the maximum thickness error in the target input data corresponding to the minimum fitness function value, the final tolerance range of the maximum thickness tolerance is obtained; The target data corresponding to the tolerance range of the leading edge profile error in the target input data corresponding to the minimum fitness function value is used to obtain the final tolerance range of the leading edge profile tolerance; The target data corresponding to the excess tolerance range of the torsion angle error in the target input data corresponding to the minimum fitness function value is used to obtain the final tolerance range of the torsion angle tolerance.

Images