Aero-engine part feature process parameter design evaluation method and related device

Abstract

The application discloses an aero-engine part feature process parameter design evaluation method and a related device, relates to the aero-engine part process parameter evaluation field, and the method comprises the following steps: according to the machining feature type, the machining material and the machining feature type input by a user, similar cases are searched, and the similar cases are obtained; the similar cases are rewritten for cutting parameters, and rewritten cases are obtained; according to a parameter optimization model, a particle swarm algorithm is applied to optimize the cutting parameters, and optimization cases are obtained; the rewritten cases and the optimization cases are evaluated, and the scores of the cases are obtained. The present application can quickly determine the process parameters that meet the user input requirements and the process parameters from the existing process parameter cases and the cases optimized by applying the optimization algorithm, can shorten the design cycle of the aero-engine part feature machining process scheme, and improve the efficiency of process parameter selection.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of aero-engine part process parameter evaluation, in particular to an aero-engine part feature process parameter design evaluation method and related device. BACKGROUND

[0002] Aero-engine is a typical difficult-to-machine component in the field of aerospace, which contains various typical difficult-to-machine parts, such as blades, blisks, casings, etc. The typical difficult-to-machine parts of aero-engine also contain various typical difficult-to-machine features, such as blade profiles, stiffeners, flow channels, etc. Due to the lack of systematic analysis, induction and evaluation of related machining data knowledge, the incomplete data knowledge reuse reasoning and rapid programming tools, the program applied to feature machining is different for different people, resulting in the lack of stability and consistency of typical part machining, which brings challenges to the stability of batch production type product manufacturing and the promotion progress of research type product.

[0003] At present, the hierarchical process data knowledge modeling method and system design of aero-engine manufacturing have not formed an effective data processing method from different levels of materials to features and parts, which is insufficient to support the high-quality manufacturing of engines. Specifically, the basic data and expert knowledge data of typical machining features of aero-engine are large in volume, various in structure and complex in association rules. In order to effectively organize and manage these data, related technical research needs to be carried out, a scientific data knowledge expression model needs to be established, and then the design of machining expert system for typical features of difficult-to-machine parts of aero-engine is completed. Taking the invention “numerical control machining process program compilation quality evaluation method, device, equipment and medium” (application number 202210695676.1) as an example, the optimization theme of this evaluation method is the part, which does not start from the features of the part, and the evaluation subject is the numerical control machining process quality, which is not the more detailed machining process parameters, so it cannot optimize the process parameters at the feature level. Taking the invention “a green evaluation method for mechanical part cold cutting machining process” (application number 201610905656.7) as an example, this invention only targets single cold cutting machining and evaluates and optimizes the process route for green machining.

[0004] For the process parameter design of typical part features, if the traditional feature process parameter planning is adopted, it is necessary to rely on the experience of process development personnel, and the machining quality is difficult to guarantee, which is easy to cause various machining defects, resulting in poor product consistency, low machining quality and other problems, as shown in the following table. Figure 1

[0005] In order to realize the efficient and precise machining of typical features of difficult-to-machine parts of aero-engine, optimize the manufacturing of complex parts, shorten the process design cycle, reduce the process design cost, and finally achieve the goal of comprehensively improving the process design capability, the present application provides an aero-engine part feature process parameter design evaluation method and related device.​ SUMMARY

[0006] The purpose of the present application is to provide an aero-engine part feature process parameter design evaluation method and related device, which can quickly determine the process parameters that meet the user's input requirements from the existing process parameter cases and the cases optimized by the application optimization algorithm, shorten the design cycle of aero-engine part feature process parameters, and improve the efficiency of process parameter design.

[0007] To achieve the above purpose, the present application provides the following solutions:

[0008] In a first aspect, the present application provides an aero-engine part feature process parameter design evaluation method, comprising:

[0009] According to the machining feature type and machining material input by the user or the machining feature type, machining material and machining target, similar cases are searched from the historical actual machining cases stored in the database and the rewritten cases stored in the case library, to obtain similar cases; the machining feature type refers to the type of each component part of the aero-engine; the historical actual machining cases and the rewritten cases include machining feature type, machining material, machine tool information, tool information, working condition information, cutting parameters and machining results;

[0010] The similar cases are rewritten for cutting parameters to obtain rewritten cases;

[0011] According to the parameter optimization model, the particle swarm algorithm is applied to optimize the cutting parameters to obtain the cutting parameter optimization result; the parameter optimization model is determined according to the machining feature type and the machining material or the machining feature type, the machining material and the machining target; the parameter optimization model includes a surface machining quality model and a machining efficiency model; the expressions of the surface machining quality model and the machining efficiency model include cutting parameters;

[0012] The rewritten cases and the optimization cases are evaluated to obtain the case scores of the rewritten cases and the optimization cases to show the rewritten cases and the optimization cases and the corresponding case scores to the user; the optimization cases include the cutting parameter optimization result, the machining feature type and the machining material and machining result; when the user's input includes the machining target, the machining result is determined according to the machining target; when the user's input does not include the machining target, the machining result is determined according to the default machining target parameters in the parameter optimization model; the default machining target parameters in the parameter optimization model include tool wear weight, cutting force weight and surface roughness weight.

[0013] In a second aspect, the present application provides an aero-engine part feature process parameter design evaluation device, comprising:

[0014] Database, used to store historical actual processing cases;

[0015] A case library for storing rewritten cases; the historical actual processing cases and the rewritten cases include processing feature types, processing materials, machine tool information, tool information, working condition information, cutting parameters and processing results;

[0016] A similar case retrieval module is used to retrieve similar cases from historical actual processing cases stored in the database and rewritten cases stored in the case library based on the processing feature type and processing material or processing feature type, processing material and processing target input by the user, to obtain similar cases; the processing feature type refers to the type of each component of the aircraft engine;

[0017] A similar case rewriting module is used to rewrite the cutting parameters of the similar case to obtain a rewritten case;

[0018] an optimization module, configured to apply a particle swarm algorithm to optimize cutting parameters according to a parameter optimization model, and obtain a cutting parameter optimization result; the parameter optimization model is determined based on the processing feature type and the processing material or the processing feature type, the processing material, and the processing target; the parameter optimization model includes a surface processing quality model and a processing efficiency model; and the expressions of the surface processing quality model and the processing efficiency model include cutting parameters;

[0019] A case evaluation module is used to perform case evaluation on the rewriting case and the optimization case, and obtain the case scores of the rewriting case and the optimization case to display the rewriting case and the optimization case and the corresponding case scores to the user; the optimization case includes the cutting parameter optimization result, the processing feature type and the processing material and processing result; when the user input includes the processing target, the processing result is determined according to the processing target; when the user input does not include the processing target, the processing result is determined according to the default processing target parameters in the parameter optimization model; the default processing target parameters in the parameter optimization model include tool wear weight, cutting force weight and surface roughness weight.

[0020] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for designing and evaluating characteristic process parameters of aircraft engine parts.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for designing and evaluating characteristic process parameters of aircraft engine parts.

[0022] According to the specific embodiments provided in the present application, the present application discloses the following technical effects:

[0023] The present application provides an aero-engine part feature process parameter design evaluation method and related device, on the one hand, the similar cases that meet the user input requirements (processing feature type, processing material and processing target) are retrieved from the existing cases in the database and case library, and the process parameters (i.e. cutting parameters) are rewritten on the basis of the similar cases to meet the user input requirements; on the other hand, based on the input requirements of the user, the optimization algorithm is used to optimize the process parameters, and the optimized case that meets the user input requirements is obtained. Then the rewritten case and the optimized case are further evaluated, and the scores of each case are obtained. Subsequently, the user can refer to the required process parameters according to the scores of each case to manufacture the related part features. Obviously, the present application can quickly determine the process parameters that meet the user input requirements from the existing process parameter cases and the cases optimized by the optimization algorithm, which can shorten the design cycle of aero-engine part feature process parameters and improve the efficiency of process parameter design. In addition, the optimization target of the present application can be diversified, which can be divided into two aspects of processing efficiency and surface processing quality, so as to realize the optimization target requirements in multiple aspects on the basis of shortening the process design cycle. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0025] Figure 1 Aero-engine blade airfoil milling chatter schematic diagram;

[0026] Figure 2 An application environment diagram of an aero-engine part feature process parameter design evaluation method in an embodiment of the present application;

[0027] Figure 3 A flowchart schematic diagram of an aero-engine part feature process parameter design evaluation method provided in an embodiment of the present application;

[0028] Figure 4 A technical route schematic diagram of an aero-engine part feature process parameter design evaluation method provided in an embodiment of the present application;

[0029] Figure 5 An E-R diagram of a database provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of a case search process provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of a case optimization process provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of weight settings for a parameter optimization model provided in one embodiment of the present application;

[0033] Figure 9 A schematic diagram of particle swarm optimization provided in one embodiment of the present application;

[0034] Figure 10 A schematic diagram of the functional modules of a device for designing and evaluating characteristic process parameters of aircraft engine parts provided by another embodiment of the present application;

[0035] Figure 11 A diagram of a database front-end interface provided for another embodiment of the present application;

[0036] Figure 12 This is a diagram of the case retrieval and rewriting front-end interface provided in another embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0038] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0039] The design and evaluation method of characteristic process parameters of aircraft engine parts provided in the embodiment of the present application can be applied to Figure 2In the application environment shown. The terminal communicates with the expert system through the network. The data server set can store the data that the expert system needs to process. The data server set can be set up separately, integrated into the expert system, or placed on the cloud or other expert systems. The terminal can send the processing feature type and processing material or processing feature type, processing material and processing target input by the user to the expert system. After the expert system receives the processing feature type and processing material or processing feature type, processing material and processing target input by the user, the expert system searches for similar cases from the historical actual processing cases stored in the database and the rewritten cases stored in the case library based on the processing feature type and processing material or processing feature type, processing material and processing target input by the user, and obtains similar cases; rewrites the cutting parameters of the similar cases to obtain rewritten cases; applies the particle swarm algorithm to optimize the cutting parameters according to the parameter optimization model to obtain the cutting parameter optimization results; performs case evaluation on the rewritten cases and optimized cases to obtain case scores of the rewritten cases and the optimized cases to display the rewritten cases and the optimized cases and the corresponding case scores to the user. The expert system may feed back the obtained rewriting cases and optimization cases and corresponding scores to the terminal.

[0040] The terminals may be, but are not limited to, various desktop computers, laptops, smart phones, tablet computers, and portable IoT devices.

[0041] In an exemplary embodiment, Figure 3 and Figure 4 As shown, a method for designing and evaluating characteristic process parameters of aircraft engine parts is provided. The method is executed by a computer device, specifically an expert system or other computer device. In the embodiment of the present application, the method is applied to Figure 2 The expert system in is used as an example to illustrate, including the following steps 101 to 104.

[0042] Step 101, based on the processing feature type and processing material or the processing feature type, processing material and processing target input by the user, similar cases are retrieved from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain similar cases; the processing feature type refers to the type of each component of the aircraft engine; the historical actual processing case and the rewritten case include the processing feature type, processing material, machine tool information, tool information, working condition information, cutting parameters and processing results.

[0043] The storage information in the database can be in the form of ER diagram (entity-relationship diagram), such as Figure 5As shown, the database field information entity includes feature information, process method, machine tool information, tool information, working condition information, cutting parameter and machining result; the machining feature information includes machining feature name (type) and machining material; there are 20 types of machining feature types of typical parts of an aero-engine, such as boss, thin-walled ring, blade profile, etc.; the process method includes turning, milling, planing, grinding and drilling; the machine tool information includes machine tool model, machine tool type, spindle speed, spindle maximum power, etc.; the tool information includes tool name, tool model, tool type, tool diameter, tool R angle, etc.; the working condition information includes rough machining, semi-finish machining and finish machining; the cutting parameter includes cutting speed v c , axial depth of cut a p , radial depth of cut a e and feed per tooth f z ; the machining result includes surface roughness R a , tool wear VB, cutting force F and machining deformation, etc. Among them, the cutting parameter affects the machining result; the appropriate process method, tool, machine tool and cutting parameter are selected according to the machining feature information and the working condition information; the machine tool information and the tool information must match the process method to ensure that the equipment used meets the method requirements; the cutting parameter must match the machine tool information to ensure that the machine tool performance meets the machining requirements.

[0044] Step 102, rewriting the cutting parameter of the similar case to obtain a rewritten case.

[0045] Step 103, applying a particle swarm algorithm to optimize the cutting parameter according to a parameter optimization model to obtain a cutting parameter optimization result; the parameter optimization model is determined according to the machining feature type and the machining material or the machining feature type, the machining material and the machining target; the parameter optimization model includes a surface machining quality model and a machining efficiency model; the expressions of the surface machining quality model and the machining efficiency model include the cutting parameter.

[0046] Step 104, evaluating the rewritten case and the optimized case to obtain the case scores of the rewritten case and the optimized case to show the rewritten case and the optimized case and the corresponding case scores to the user; the optimized case includes the cutting parameter optimization result, the machining feature type and the machining material and the machining result; when the input of the user includes the machining target, the machining result is determined according to the machining target; when the input of the user does not include the machining target, the machining result is determined according to the default machining target parameter in the parameter optimization model; the default machining target parameter in the parameter optimization model includes tool wear weight, cutting force weight and surface roughness weight.

[0047] By implementing steps 101 to 104, the present invention retrieves similar cases that meet the user's input requirements (processing feature type, processing material, and processing target) from existing cases in the database and case library. Based on these similar cases, process parameters (i.e., cutting parameters) are rewritten to meet the user's input requirements. By constructing a database and case library to retrieve similar cases, the existing cases can be used as a basis for rewriting cases that better meet the user's requirements, thereby improving the efficiency of process parameter design. Furthermore, to ensure the number of cases to be evaluated, a process parameter optimization model is constructed based on the user's input. The process parameters are optimized using an optimization algorithm to obtain optimized cases that meet the user's input requirements. The rewritten and optimized cases are then evaluated to obtain a score for each case. Subsequently, the user can use the scores of each case as a reference to determine the required process parameters for manufacturing the relevant part features. Clearly, the present invention can quickly determine process parameters that meet the user's input requirements from existing process parameter cases and cases optimized using the optimization algorithm, shortening the design cycle of process parameters for aircraft engine part features and improving the efficiency of process parameter design. In addition, the optimization objectives of the present invention can be diversified and divided into two aspects: processing efficiency and surface processing quality. This can achieve the goal of achieving multiple optimization requirements on the basis of shortening the process design cycle.

[0048] In an exemplary embodiment of the present application, for similar case retrieval in step 101, if the user input only includes the processing feature type and processing material, then based on the processing feature type and processing material input by the user, a search is performed from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain similar cases, specifically including:

[0049] (a1) According to the processing feature type input by the user, cases with the same processing feature type are screened from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain a number of first screened cases.

[0050] (a2) Screening out cases having the same or similar material mechanical properties as the processing material input by the user from the first screening cases, and obtaining a plurality of second screening cases.

[0051] (a3) Filtering out cases with the same material mechanical properties or with a material mechanical property similarity greater than a preset similarity value from the second screening cases to obtain the similar cases.

[0052] In another exemplary embodiment of the present application, for the similar case search in step 101, as shown in FIG. Figure 6As shown, the user's input includes the machining feature type, the machining material, and the machining target, the same feature data is extracted one by one from the database and the case library, the material mechanical property parameters such as material hardness and material tensile strength, and the machining target parameters such as surface roughness and machining efficiency are calculated for local similarity, and the above attributes (material mechanical property parameters and machining target parameters) are assigned weights through the attribute importance scoring matrix completed by the expert in advance, so as to calculate the global similarity. The data with global similarity reaching the threshold requirement (for example, 90%) is sorted and output according to size. Therefore, as another optional embodiment, step 101, according to the machining feature type, the machining material, and the machining target input by the user, the similar cases are searched from the historical actual machining cases stored in the database and the rewritten cases stored in the case library, and the similar cases are obtained, which specifically includes:

[0053] (b1) According to the machining feature type input by the user, the cases with the same machining feature type are screened from the historical actual machining cases stored in the database and the rewritten cases stored in the case library, and a plurality of third screening cases are obtained.

[0054] (b2) From the third screening cases, the cases with the same or similar material mechanical properties of the machining material input by the user are screened, and a plurality of fourth screening cases are obtained.

[0055] (b3) From the third screening cases, the cases with the same or similar machining target are screened, and a plurality of fifth screening cases are obtained.

[0056] (b4) The global similarity of the machining material and the machining target in the fourth screening case is calculated.

[0057] (b5) The global similarity of the machining material and the machining target in the fifth screening case is calculated.

[0058] When calculating the global similarity, according to the preset weight values of the machining material and the machining target, the respective local similarities are combined for weighted summation to obtain the global similarity.

[0059] (b6) From the fourth screening cases and the fifth screening cases, the cases with global similarity greater than the preset global similarity are screened, and the similar cases are obtained.

[0060] It should be noted that when the cases in the case library and the database are searched, if the same case is searched, it can be directly used, and if the same case is not found, the similar case is searched.

[0061] In another exemplary embodiment of the present application, for the case rewriting in step 102, the similar cases are rewritten for cutting parameters to obtain rewritten cases, which specifically includes:

[0062] (1) For each similar case, calculate the material similarity between the processed material in the similar case and the processed material input by the user.

[0063] (2) Determine the similarity of the feed per tooth between the similar case and the rewritten case based on the material similarity.

[0064] (3) Determining the cutting speed similarity between the similar case and the rewritten case based on the thermal conductivity ratio between the processing material in the similar case and the processing material input by the user; the cutting speed similarity is equal to the cutting depth similarity between the similar case and the rewritten case.

[0065] (4) Rewriting the cutting parameters in the similar case according to the similarity of the feed per tooth, the similarity of the cutting speed, and the similarity of the cutting depth to obtain the rewritten case; the cutting parameters include cutting speed, feed per tooth, axial cutting depth, and radial cutting depth.

[0066] Taking the blade surface characteristics TC4 titanium alloy processing data rewritten into TC17 titanium alloy processing data as an example, the relevant performance parameters of the two materials are shown in Tables 1 and 2 below.

[0067] Table 1 Mechanical properties of TC4 titanium alloy materials

[0068]

[0069] Table 2 TC4 milling cutting parameter data

[0070] Cutting speed v c ]]> <![CDATA[每齿进给量f z ]]> <![CDATA[轴向切深a p ]]> <![CDATA[径向切深a e ]]> 44m / min 0.027 mm / z 0.5mm 0.5mm

[0071] The material similarity m can be obtained by the following formula: m , similarity of feed per tooth m fz , cutting speed similarity m v , cutting depth similarity m a :

[0072]

[0073] m v =m a

[0074] Among them, cutting speed similarity m v is the ratio of the thermal conductivity of the two materials.

[0075] Where m1 is the heat generation ratio, m2 is the tensile strength ratio, m3 is the elastic modulus ratio, m4 is the aluminum content ratio, and k is the material correction factor (this value is 1.05). The calculation results are:

[0076] mm ≈0.86, m v ≈0.52. The TC17 rewritten case data (rewritten cutting parameters) can be obtained through parameter similarity calculation as shown in Table 3.

[0077] Table 3 Cutting parameters in the TC17 rewriting case

[0078] <![CDATA[切削速度v c ]]> <![CDATA[每齿进给量f z ]]> <![CDATA[轴向切深a p ]]> <![CDATA[径向切深a e ]]> 84.6m / min 0.023mm / z 1mm 1mm

[0079] It should be noted that when there is no data in the database or case library that meets the similarity requirements, case rewriting cannot be performed. Instead, the rule inference engine will be used to infer a reasonable range of processing parameters. For example, there is a rough parameter range for cutting aluminum alloy materials. The main purpose is to avoid the problem of no data output due to insufficient similarity and to provide users with a reasonable parameter range reference. When the search continuously returns similar cases, case evaluation will not be performed, and the inferred processing parameter range will be displayed to the user for reference.

[0080] In another exemplary embodiment of the present application, for the process parameter optimization process in step 103, as shown in FIG. Figure 7 As shown in the figure, experimental data were obtained through a four-factor, five-level orthogonal experiment (referring to milling force measurement, surface quality measurement, and machining deformation measurement under changes in four cutting parameters). For each machining feature type, two process parameter optimization models were constructed using the response surface methodology: a surface machining quality model and a machining efficiency model. Taking the machining efficiency model and surface machining quality model of the impeller blade surface feature as an example, the formulas for the machining efficiency model and surface machining quality model are as follows:

[0081]

[0082] in,

[0083]

[0084] The formula of the surface processing quality model is:

[0085]

[0086] in,

[0087]

[0088] Where: v c is the cutting speed, f z is the feed per tooth, a eis the radial cutting depth, β1 is the tool wear weight, β2 is the material weight, β3 is the cutting force weight, β4 is the surface roughness weight, g i (x) is the penalty function of each unknown in the blade profile machining efficiency model, t function is the cutting time function, d is the tool diameter, A is the milling area, t c is the tool change time, T is the tool durability, Ra is the surface roughness, Fy is the y-direction cutting force, c i (x) represents the penalty function for each unknown in the blade airfoil surface quality model, and the F function represents the main milling force function for the blade airfoil surface. The material weight β2 is adjusted based on the processing material input by the user. When the user input includes a machining target, the weights of the parameters related to the machining target (machining result): tool wear weight β1, cutting force weight β3, and surface roughness weight β4, are adjusted based on the machining target. If the user does not enter a machining target, the weights of the parameters related to the machining target (machining result) are set to the standard values.

[0089] After determining the expression of the parameter optimization model, different weight coefficients of the surface quality model and the processing efficiency model are calculated according to the multiple processing targets input by the user; Figure 8 As shown in the figure, when the user subjectively assigns values ​​to the four weights according to the actual situation. The boundary conditions of the parameter optimization model are determined according to the multiple processing goals input by the user; the parameter optimization model is rewritten according to the calculated weight coefficients and the input boundary conditions (referring to the penalty function in the above formula); according to the parameter optimization model, the program's embedded PSO particle swarm optimization algorithm is used to optimize the cutting parameters, and finally the optimal solution for the cutting parameters is obtained. Figure 9 Schematic diagram of particle swarm optimization. Figure 9 Represents an iterative optimization process of the particle swarm algorithm.

[0090] Therefore, in step 103, based on the parameter optimization model, the particle swarm algorithm is applied to optimize the cutting parameters to obtain the cutting parameter optimization results, which specifically include:

[0091] (1) determining a parameter optimization model based on the processing feature type and the processing material or the processing feature type, the processing material, and the processing target; when the user input includes the processing feature type and the processing material, the material weight parameter in the parameter optimization model is determined based on the processing material input by the user, and the weight of the default processing target parameter in the parameter optimization model is selected from a preset weight value; when the user input also includes the processing target, the weight of the default processing target parameter in the parameter optimization model is determined based on the processing target input by the user;

[0092] (2) The particle fitness is calculated using the parameter optimization model, and the particle swarm algorithm is applied to optimize the cutting parameters to obtain the cutting parameter optimization results; in the particle swarm algorithm, one particle is a numerical combination of a group of cutting parameters.

[0093] In another exemplary embodiment of the present application, the case evaluation in step 104 adopts a grey correlation analysis method:

[0094] (1) Establishment and standardization of evaluation index matrix.

[0095] a. Establish an evaluation indicator matrix:

[0096] Let U={u1,u2,...,u i ,...,u m} is a set of processing plans, where u i represents the i-th processing plan, and m represents the number of plans in the processing plan set. Let V = {v1, v2, ..., v i ,...,v n} is the evaluation index set, where v i Represents the result corresponding to the i-th evaluation index, and n is the total number of evaluation results, for example, v1: surface roughness Ra; v2: dimensional accuracy D i ; v3: tool flank wear VB. v1, v2 represent the processing quality, v3 represents the tool life. The element pair (u i , v j ) constitutes a Cartesian product set, stipulating that the element pair (u i , v j ) is f ij , then m×n f ij Construct the finishing evaluation index matrix F=(f ij ) m×n .

[0097] b. Standardization of evaluation indicators

[0098] Different evaluation indicators usually have different dimensions and orders of magnitude. In order to eliminate the influence and ensure the accuracy and reliability of the results, different methods are used to normalize different types of evaluation indicators.

[0099] (2) Establishment of the solution decision model

[0100] a. Grey relational degree of the scheme

[0101] According to the grey correlation decision theory, the order of the processing schemes can be judged by comparing the correlation between each evaluation index vector and the evaluation index vector of the relatively optimal processing scheme. The larger the correlation, the closer it is to the optimal. Let the relatively optimal processing scheme be u0=(f 01 , f 02 ,…,f 0n ), after normalization, we have u0=(1, 1, …, 1), and the processing plan u i Evaluation index v j The evaluation index v of the relatively optimal processing solution u0 j The grey correlation degree between them is:

[0102]

[0103] Where ξ∈(0,1) is the resolution coefficient, whose value is difficult to quantify and usually depends on experience, and is generally taken as 0.5, i=1,2,…,m; j=1,2,…,n.

[0104] b. Determine the indicator weight

[0105] c. Decision model

[0106] From the above analysis, we can see that the grey correlation matrix of the processing scheme can be expressed as:

[0107]

[0108] The weight vector of n evaluation indicators can be expressed as W = (w1, w2, ..., w n ), based on the grey correlation matrix and weight vector, the processing scheme u i The weighted correlation γ between the relative optimal processing solution u0 i Form the correlation vector γ′.

[0109] γ′=γW=(γ1,γ2,...,γ i ,..,γ m );

[0110] in, Weighted correlation γ i The larger the solution u is, the i The closer it is to the relatively optimal solution u0.

[0111] Therefore, step 104 is to perform case evaluation on the rewritten case and the optimized case to obtain case scores for the rewritten case and the optimized case, specifically including:

[0112] (1) constructing a processing evaluation index matrix according to the rewriting cases and the optimization cases and respective corresponding processing targets; elements in the processing evaluation index matrix are element pairs formed by any collocation of the to-be-evaluated schemes and evaluation indexes; the to-be-evaluated schemes refer to the rewriting cases and the optimization cases; the evaluation indexes are determined according to the processing targets.

[0113] (2) performing standardization processing on the processing evaluation index matrix to obtain a pre-processed processing evaluation index matrix.

[0114] (3) calculating a grey correlation degree between an evaluation index of each to-be-evaluated scheme and an evaluation index of a relatively optimal processing scheme according to the processing evaluation index matrix and the evaluation index corresponding to the relatively optimal processing scheme; the grey correlation degrees corresponding to each to-be-evaluated scheme form a grey correlation degree matrix of the to-be-evaluated schemes; the relatively optimal processing scheme is predefined.

[0115] (4) determining weight values of the evaluation indexes corresponding to the to-be-evaluated schemes.

[0116] (5) calculating a weighted correlation degree between each to-be-evaluated scheme and the relatively optimal scheme according to the weight values and the grey correlation degree matrix; the weighted correlation degree corresponding to each to-be-evaluated scheme is a case score.

[0117] In another exemplary embodiment of the present application, after the cases are evaluated, the rewriting cases and the optimization cases with scores ranking in the front are further stored into a case library. Therefore, after the step 104 "performing case evaluation on the rewriting cases and the optimization cases to obtain scores of the rewriting cases and the optimization cases" is executed, the aero-engine part feature process parameter design evaluation method further comprises:

[0118] (1) performing sorting of the case scores from large to small.

[0119] (2) selecting multiple cases with scores ranking in the front to store into the case library.

[0120] The present application also provides an application scenario which applies the aero-engine part feature process parameter design evaluation method described above. Specifically, the aero-engine part feature process parameter design evaluation method provided in the embodiment is mainly applied to the compilation of a new aero-engine process specification to provide suitable process parameter references for existing processing procedures. The scenario includes the following links: analyzing a part drawing, drafting a process route, determining a processing equipment, determining a processing allowance, determining a process parameter, and compiling and approving. The video label processing method provided in the embodiment belongs to the link of determining a process parameter.

[0121] Based on the same inventive concept, the embodiment of the present application also provides a device for implementing the above-mentioned aero-engine part feature process parameter design evaluation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above-mentioned method, so the specific limitations in one or more aero-engine part feature process parameter design evaluation device embodiments provided below can be referred to the limitations of the aero-engine part feature process parameter design evaluation method in the above, which will not be described here again.

[0122] In one exemplary embodiment, as shown in Figure 10 An aero-engine part feature process parameter design evaluation device is provided, comprising:

[0123] A database M1 is configured to store historical actual machining cases. As shown in Figure 11 The front-end interface of the database is shown, and the functions of adding, deleting, modifying and querying the database data can be realized.

[0124] A case library M2 is configured to store rewritten cases; the historical actual machining cases and the rewritten cases include machining feature types, machining materials, machine tool information, tool information, working condition information, cutting parameters and machining results.

[0125] A similar case retrieval module M3 is configured to retrieve similar cases from the historical actual machining cases stored in the database and the rewritten cases stored in the case library according to the machining feature types and the machining materials input by a user or the machining feature types, the machining materials and a machining target, to obtain similar cases; the machining feature types refer to the types of various constituent parts of an aero-engine. As shown in Figure 12 The front-end interface of the similar case retrieval is shown.

[0126] A similar case rewriting module M4 is configured to rewrite the cutting parameters of the similar cases to obtain rewritten cases. As shown in Figure 12 The front-end interface of the rewritten cases is shown.

[0127] An optimization module M5 is configured to apply a particle swarm algorithm to optimize the cutting parameters according to a parameter optimization model to obtain a cutting parameter optimization result; the parameter optimization model is determined according to the machining feature types and the machining materials or the machining feature types, the machining materials and the machining target; the parameter optimization model includes a surface machining quality model and a machining efficiency model; the expressions of the surface machining quality model and the machining efficiency model include the cutting parameters.

[0128] The case evaluation module M6 is used to perform case evaluation on the rewritten case and the optimized case to obtain the case scores of the rewritten case and the optimized case; the optimized case includes the cutting parameter optimization result, the processing feature type and the processing material and processing result; when the user input includes the processing target, the processing result is determined according to the processing target; when the user input does not include the processing target, the processing result is determined according to the default processing target parameters in the parameter optimization model; the default processing target parameters in the parameter optimization model include tool wear weight, cutting force weight and surface roughness weight.

[0129] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is configured to store rewriting cases and optimization cases and corresponding evaluation scores for each case. The I / O interface of the computer device is configured to exchange information between the processor and an external device. The communication interface of the computer device is configured to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a method for designing and evaluating characteristic process parameters of aircraft engine parts.

[0130] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0132] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. The databases involved in the embodiments provided in this application may include relational databases. The technical features of the above embodiments can be arbitrarily combined. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for designing and evaluating characteristic process parameters of aircraft engine parts, characterized in that: The method for designing and evaluating characteristic process parameters of aircraft engine parts includes: Based on the processing feature type and processing material or the processing feature type, processing material and processing target input by the user, similar cases are retrieved from historical actual processing cases stored in the database and rewritten cases stored in the case library to obtain similar cases; the processing feature type refers to the type of each component of the aircraft engine; the historical actual processing case and the rewritten case include the processing feature type, processing material, machine tool information, tool information, working condition information, cutting parameters and processing results; rewriting the cutting parameters of the similar case to obtain a rewritten case; According to the parameter optimization model, a particle swarm algorithm is applied to optimize the cutting parameters to obtain a cutting parameter optimization result; the parameter optimization model is determined according to the processing feature type and the processing material or the processing feature type, the processing material and the processing target; the parameter optimization model includes a surface processing quality model and a processing efficiency model; the expressions of the surface processing quality model and the processing efficiency model include cutting parameters; A case evaluation is performed on the rewritten case and the optimized case, and case scores of the rewritten case and the optimized case are obtained to display the rewritten case and the optimized case and the corresponding case scores to the user; the optimized case includes the cutting parameter optimization result, the processing feature type, the processing material and the processing result; when the user input includes a processing target, the processing result is determined according to the processing target; when the user input does not include a processing target, the processing result is determined according to the default processing target parameters in the parameter optimization model; the default processing target parameters in the parameter optimization model include a tool wear weight, a cutting force weight and a surface roughness weight; Among them, according to the parameter optimization model, the particle swarm algorithm is applied to optimize the cutting parameters, and the cutting parameter optimization results are obtained, which specifically include: A parameter optimization model is determined based on the processing feature type and the processing material or the processing feature type, the processing material, and the processing target; when the user input includes the processing feature type and the processing material, the material weight parameter in the parameter optimization model is a weight value determined based on the processing material input by the user, and the weight of the default processing target parameter in the parameter optimization model is a preset weight value; when the user input also includes the processing target, the weight of the default processing target parameter in the parameter optimization model is determined based on the processing target input by the user; The particle fitness is calculated using the parameter optimization model, and a particle swarm algorithm is applied to optimize the cutting parameters to obtain a cutting parameter optimization result; in the particle swarm algorithm, one particle is a numerical combination of a group of cutting parameters; The rewriting case and the optimization case are evaluated to obtain case scores for the rewriting case and the optimization case, specifically including: A processing evaluation index matrix is ​​constructed based on the rewriting case and the optimization case and their corresponding processing objectives; the elements in the processing evaluation index matrix are element pairs formed by any combination of each scheme to be evaluated and an evaluation index; the scheme to be evaluated refers to the rewriting case and the optimization case; and the evaluation index is determined based on the processing objectives; Standardizing the processing evaluation index matrix to obtain a pre-processed processing evaluation index matrix; Calculating the grey correlation between the evaluation index of each scheme to be evaluated and the evaluation index of the relatively optimal processing scheme based on the processing evaluation index matrix and the evaluation index corresponding to the relatively optimal processing scheme; the grey correlation corresponding to each scheme to be evaluated constitutes a grey correlation matrix of each scheme to be evaluated; the relatively optimal processing scheme is predefined; Determine the weight value of each evaluation indicator corresponding to the scheme to be evaluated; The weighted correlation between each of the schemes to be evaluated and the relatively optimal scheme is calculated according to the weight value and the grey correlation matrix; the weighted correlation corresponding to each of the schemes to be evaluated is the case score.

2. The method for designing and evaluating characteristic process parameters of aircraft engine parts according to claim 1, characterized in that: Based on the processing feature type and processing material input by the user, similar cases are retrieved from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain similar cases, including: According to the processing feature type input by the user, cases with the same processing feature type are screened from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain a number of first screened cases; Screening out cases having the same or similar material mechanical properties as the processing material input by the user from the first screening cases, and obtaining a plurality of second screening cases; From the second screening cases, cases with the same material mechanical properties or with a material mechanical property similarity greater than a preset similarity value are screened out to obtain the similar cases.

3. The method for designing and evaluating characteristic process parameters of aircraft engine parts according to claim 1, characterized in that: Based on the processing feature type, processing material and processing target input by the user, similar cases are retrieved from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain similar cases, including: According to the processing feature type input by the user, cases with the same processing feature type are screened out from the historical actual processing cases stored in the database and the rewritten cases stored in the case library to obtain a plurality of third screened cases; Screening out cases having the same or similar material mechanical properties as the processing material input by the user from the third screening cases, and obtaining a plurality of fourth screening cases; Screening out cases that are identical or similar to the processing target input by the user from the third screening cases to obtain a plurality of fifth screening cases; calculating the global similarity between the processing material and the processing target in the fourth screening case; calculating the global similarity between the processing material and the processing target in the fifth screening case; From the fourth screening cases and the fifth screening cases, cases having a global similarity greater than a preset global similarity are screened out to obtain the similar cases.

4. The method for designing and evaluating characteristic process parameters of aircraft engine parts according to claim 1, wherein: Rewriting the cutting parameters of the similar case to obtain a rewritten case, specifically including: For each similar case, calculating the material similarity between the processed material in the similar case and the processed material input by the user; determining a similarity in feed per tooth between the similar case and the rewritten case based on material similarity; Determining a cutting speed similarity between the similar case and the rewritten case based on a thermal conductivity ratio between a processing material in the similar case and a processing material input by a user; the cutting speed similarity is equal to a cutting depth similarity between the similar case and the rewritten case; The cutting parameters in the similar case are rewritten according to the similarity of the feed per tooth, the similarity of the cutting speed, and the similarity of the cutting depth to obtain the rewritten case; the cutting parameters include cutting speed, feed per tooth, axial cutting depth, and radial cutting depth.

5. The method for designing and evaluating characteristic process parameters of aircraft engine parts according to claim 1, wherein: After executing the step of "performing case evaluation on the rewritten case and the optimized case to obtain case scores for the rewritten case and the optimized case", the method for evaluating characteristic process parameter design of aircraft engine parts further includes: Sort the case scores from largest to smallest; Select multiple cases with high case scores and store them in the case library.

6. A device for designing and evaluating characteristic process parameters of aircraft engine parts, characterized in that: The aircraft engine part characteristic process parameter design and evaluation device comprises: Database, used to store historical actual processing cases; A case library for storing rewritten cases; the historical actual processing cases and the rewritten cases include processing feature types, processing materials, machine tool information, tool information, working condition information, cutting parameters and processing results; A similar case retrieval module is used to retrieve similar cases from historical actual processing cases stored in the database and rewritten cases stored in the case library based on the processing feature type and processing material or processing feature type, processing material and processing target input by the user, to obtain similar cases; the processing feature type refers to the type of each component of the aircraft engine; A similar case rewriting module is used to rewrite the cutting parameters of the similar case to obtain a rewritten case; an optimization module, configured to apply a particle swarm algorithm to optimize cutting parameters according to a parameter optimization model, and obtain a cutting parameter optimization result; the parameter optimization model is determined based on the processing feature type and the processing material or the processing feature type, the processing material, and the processing target; the parameter optimization model includes a surface processing quality model and a processing efficiency model; and the expressions of the surface processing quality model and the processing efficiency model include cutting parameters; Among them, according to the parameter optimization model, the particle swarm algorithm is applied to optimize the cutting parameters, and the cutting parameter optimization results are obtained, which specifically include: A parameter optimization model is determined based on the processing feature type and the processing material or the processing feature type, the processing material, and the processing target; when the user input includes the processing feature type and the processing material, the material weight parameter in the parameter optimization model is determined based on the processing material input by the user, and the weight of the default processing target parameter in the parameter optimization model is selected from a preset weight value; when the user input also includes the processing target, the weight of the default processing target parameter in the parameter optimization model is determined based on the processing target input by the user; The particle fitness is calculated using the parameter optimization model, and a particle swarm algorithm is applied to optimize the cutting parameters to obtain a cutting parameter optimization result; in the particle swarm algorithm, one particle is a numerical combination of a group of cutting parameters; a case evaluation module for performing case evaluation on the rewriting case and the optimization case, obtaining case scores for the rewriting case and the optimization case, and displaying the rewriting case and the optimization case and the corresponding case scores to the user; the optimization case includes the cutting parameter optimization result, the processing feature type, the processing material, and the processing result; when the user input includes a processing target, the processing result is determined according to the processing target; when the user input does not include a processing target, the processing result is determined according to the default processing target parameters in the parameter optimization model; the default processing target parameters in the parameter optimization model include tool wear weight, cutting force weight, and surface roughness weight; The rewriting case and the optimization case are evaluated to obtain case scores for the rewriting case and the optimization case, specifically including: A processing evaluation index matrix is ​​constructed based on the rewriting case and the optimization case and their corresponding processing objectives; the elements in the processing evaluation index matrix are element pairs formed by any combination of each scheme to be evaluated and an evaluation index; the scheme to be evaluated refers to the rewriting case and the optimization case; and the evaluation index is determined based on the processing objectives; Standardizing the processing evaluation index matrix to obtain a pre-processed processing evaluation index matrix; Calculating the grey correlation between the evaluation index of each scheme to be evaluated and the evaluation index of the relatively optimal processing scheme based on the processing evaluation index matrix and the evaluation index corresponding to the relatively optimal processing scheme; the grey correlation corresponding to each scheme to be evaluated constitutes a grey correlation matrix of each scheme to be evaluated; the relatively optimal processing scheme is predefined; Determine the weight value of each evaluation indicator corresponding to the scheme to be evaluated; The weighted correlation between each of the schemes to be evaluated and the relatively optimal scheme is calculated according to the weight value and the grey correlation matrix; the weighted correlation corresponding to each of the schemes to be evaluated is the case score.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for designing and evaluating characteristic process parameters of aircraft engine parts according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for designing and evaluating characteristic process parameters of aircraft engine parts according to any one of claims 1 to 5 is implemented.

Images