Method for evaluating machining process performance of structural characteristics of typical parts of aero-engine

Abstract

The invention discloses an aero-engine typical part structural feature machining process performance evaluation method, and relates to the field of aero-engine part process parameter evaluation, and the method comprises the steps: carrying out the retrieval of similar cases according to a machining feature type, a machining material and a machining feature type inputted by a user, and obtaining the similar cases; rewriting cutting parameters of the similar cases to obtain rewritten cases; according to the parameter optimization model, optimizing cutting parameters by using a particle swarm algorithm to obtain an optimization case; and performing case evaluation on the rewritten cases and the optimized cases to obtain scores of the cases. According to the method, the technological parameters meeting the user input requirements can be rapidly determined from the existing technological parameter cases and the cases optimized by applying the optimization algorithm, the design period of the aero-engine part feature machining technological scheme can be shortened, and the technological parameter selection efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of process parameter evaluation of aero-engine parts, and particularly to a method for evaluating the machining process performance of the structural features of typical parts of an aero-engine. Background Art

[0002] An aero-engine is a typical difficult-to-machine component in the field of aerospace, which contains a variety of typical difficult-to-machine parts, such as blades, blisks, casings, etc. The typical difficult-to-machine parts of an aero-engine also contain a variety of typical difficult-to-machine features, such as blade profiles, stiffeners, flow channels, etc. Due to the lack of systematic sorting, induction and evaluation of relevant machining data knowledge, and the incompleteness of enabling tools such as data knowledge reuse reasoning and rapid programming, the programs applied to feature machining vary from person to person, resulting in the lack of stability and consistency in the machining of typical parts, which poses challenges to the stability of mass-produced model products and the progress of research and development model propulsion.

[0003] At present, in the aspect of the hierarchical process data knowledge modeling method and system design for aero-engine manufacturing, there is no 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-engines are huge in volume, diverse in structure, and complex in association rules. In order to effectively organize and manage these data, it is necessary to carry out research on relevant technologies, establish a scientific data knowledge expression model, and then complete the design of an expert system for machining typical features of difficult-to-machine parts of aero-engines. Taking the invention "Numerical control machining process programming quality evaluation method, device, equipment and medium" (application number 202210695676.1) as an example, the optimization theme of this evaluation method is parts, which does not start from the refined features of parts, and the evaluation object is the quality of numerical control machining process rather than more refined machining process parameters, and it cannot perform targeted optimization of process parameters at the feature level; taking the invention "A greenness evaluation method for the cold cutting process of mechanical parts" (application number 201610905656.7) as an example, this invention only targets single cold cutting machining, and takes green machining as the goal to evaluate and optimize the process route.

[0004] For the process parameter design of typical part features, if traditional feature process parameter planning is adopted, it must rely on the experience of process planners, and it is difficult to guarantee the machining quality, and various machining defects are likely to occur, resulting in problems such as poor product consistency and low machining quality, as Figure 1 shown.

[0005] In order to achieve the high-efficiency and precision machining of typical features of difficult-to-machine parts of aero-engines, optimize the manufacturing of complex parts, shorten the process design cycle, reduce the process design cost, and further achieve the goal of comprehensively improving the process design ability. The present invention provides a method for evaluating the machining process performance of the structural features of typical parts of an aero-engine. Summary of the Invention

[0006] The object of the present application is to provide a method for evaluating the processing performance of the structural characteristics of typical parts of an aero-engine, 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 applying optimization algorithms, shorten the design cycle of the process parameters of aero-engine part features, and improve the efficiency of process parameter design.

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

[0008] In a first aspect, the present application provides a method for designing and evaluating process parameters of aero-engine part features, including:

[0009] Retrieve similar cases from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to the processing feature type and processing material or processing feature type, processing material and processing target input by the user; the processing feature type refers to the types of various components of the aero-engine; the historical actual processing cases and the rewritten cases include processing feature type, processing material, machine tool information, tool information, working condition information, cutting parameters and processing results;

[0010] Rewrite the cutting parameters of the similar cases to obtain rewritten cases;

[0011] According to the parameter optimization model, apply the particle swarm algorithm to optimize the cutting parameters to obtain the optimization result of the cutting parameters; 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;

[0012] Evaluate the rewritten cases and the optimized cases to obtain the case scores of the rewritten cases and the optimized cases to display the rewritten cases, the optimized cases and the corresponding case scores to the user; the optimized cases include the optimization result of the cutting parameters, the processing feature type, the processing material and the processing result; when the user's input includes a processing target, the processing result is determined according to the processing target; when the user's 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.

[0013] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0014] The present application provides a method for evaluating the processing technological performance of typical part structures of aero-engines. On the one hand, similar cases that match the user's input requirements (processing feature type, processing material, and processing target) are retrieved from the existing cases in the database and the case library, and the process parameters (i.e., cutting parameters) are rewritten based on the similar cases to meet the user's input requirements. On the other hand, based on the user's input requirements, an optimization algorithm is used to optimize the process parameters to obtain an optimized case that meets the user's input requirements. Subsequently, the rewritten case and the optimized case are further evaluated to obtain the scores of each case. Subsequently, the user can refer to the process parameters according to the scores of each case to manufacture the relevant part features. Obviously, the present invention can quickly determine the process parameters that meet the user's input requirements from the existing process parameter cases and the cases optimized by applying the optimization algorithm, which can shorten the design cycle of the process parameters of aero-engine part features and improve the efficiency of process parameter design. In addition, the optimization objectives of the present invention can be selected diversely, divided into two aspects: processing efficiency and surface processing quality, which can achieve multiple optimization objective requirements on the basis of shortening the process design cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a schematic diagram of milling chatter of the blade body profile of an aero-engine;

[0017] Figure 2 It is an application environment diagram of a method for designing and evaluating process parameters of aero-engine part features in an embodiment of the present application;

[0018] Figure 3 It is a schematic flowchart of a method for designing and evaluating process parameters of aero-engine part features provided in an embodiment of the present application;

[0019] Figure 4 It is a schematic technical route diagram of a method for designing and evaluating process parameters of aero-engine part features provided in an embodiment of the present application;

[0020] Figure 5 It is an E-R diagram of the database provided in an embodiment of the present application;

[0021] Figure 6 It is a schematic flowchart of case retrieval provided in an embodiment of the present application;

[0022] Figure 7Schematic diagram of the case optimization process provided by an embodiment of the present application;

[0023] Figure 8 Schematic diagram of the weight setting of the parameter optimization model provided by an embodiment of the present application;

[0024] Figure 9 Schematic diagram of particle swarm optimization provided by an embodiment of the present application;

[0025] Figure 10 Front-end interface diagram of the database provided by another embodiment of the present application;

[0026] Figure 11 Front-end interface diagram of case retrieval and rewriting provided by another embodiment of the present application. Detailed implementation manners

[0027] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0028] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0029] The method for designing and evaluating the characteristic process parameters of aero-engine parts provided by the embodiments of the present application can be applied to, for example Figure 2In the application environment shown. Among them, 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 separately, integrated on the expert system, placed on the cloud or other expert systems. The terminal can send the machining feature type, machining material or machining feature type, machining material and machining target input by the user to the expert system. After receiving the machining feature type, machining material or machining feature type, machining material and machining target input by the user, the expert system retrieves similar cases from the historical actual machining cases stored in the database and the rewritten cases stored in the case library based on the machining feature type, machining material or machining feature type, machining material and machining target input by the user, and obtains similar cases; rewrite the cutting parameters of the similar cases to obtain rewritten cases; according to the parameter optimization model, apply the particle swarm algorithm to optimize the cutting parameters, and obtain the cutting parameter optimization result; evaluate the rewritten cases and the optimized cases to obtain the case scores of the rewritten cases and the optimized cases to display the rewritten cases, the optimized cases and the corresponding case scores to the user. The expert system can feedback the obtained rewritten cases, optimized cases and corresponding scores to the terminal.

[0030] Among them, the terminal can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers and portable Internet of Things devices.

[0031] In an exemplary embodiment, as Figure 3 and Figure 4 shown, a method for designing and evaluating process parameters of an aero-engine part feature is provided. This method is executed by a computer device, specifically, it can be executed by a computer device such as an expert system. In the embodiment of the present application, taking this method applied to Figure 2 the expert system in it as an example for illustration, it includes the following steps 101 to step 104.

[0032] Step 101, 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 type, machining material or machining feature type, machining material and machining target input by the user, and obtain similar cases; the machining feature type refers to the types of various components 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.

[0033] For the stored information in the database, the form of an E-R diagram (entity-relationship diagram) can be adopted, such as Figure 5As shown in the figure, the database field information entity includes: feature information, processing methods, machine tool information, cutting tool information, working conditions information, cutting parameters, and machining results; the machining feature information includes the machining feature name (type) and the machining material; there are 20 types of machining feature types for typical parts of aero-engines, such as bosses, thin-walled rings, blade profiles, etc.; the processing methods include turning, milling, planing, grinding, and drilling; the machine tool information includes the machine tool brand, machine tool type, spindle speed, maximum spindle power, etc.; the cutting tool information includes the cutting tool name, cutting tool brand, cutting tool type, cutting tool diameter, cutting tool R angle, etc.; the working conditions information includes rough machining, semi-finishing, and finishing; the cutting parameters include the cutting speed v c , the axial depth of cut a p , the radial depth of cut a e and the feed per tooth f z ; the machining results include the surface roughness R a , the tool wear VB, the cutting force F, and the machining deformation amount, etc. Among them, the cutting parameters affect the machining results; appropriate processing methods, cutting tools, machine tools, and cutting parameters are selected according to the machining feature information and the working conditions information; the machine tool information and the cutting tool information must match the processing method to ensure that the equipment used meets the method requirements; the cutting parameters must match the machine tool information to ensure that the machine tool performance meets the machining requirements.

[0034] Step 102: Rewrite the cutting parameters of the similar case to obtain a rewritten case.

[0035] Step 103: According to the parameter optimization model, apply the particle swarm optimization algorithm to optimize the cutting parameters and 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.

[0036] Step 104: Evaluate the rewritten case and the optimized case to obtain the case scores of the rewritten case and the optimized case to display the rewritten case, the optimized case, and the corresponding case scores to the user; the optimized case includes the cutting parameter optimization result, the machining feature type, the machining material, and the machining result; when the user's input includes a machining target, the machining result is determined according to the machining target; when the user's input does not include a 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 the tool wear weight, the cutting force weight, and the surface roughness weight.

[0037] By implementing the above steps 101 to 104, on the one hand, the present invention retrieves similar cases that match the user's input requirements (processing feature type, processing material, and processing target) from the existing cases in the database and the case library, and rewrites the process parameters (i.e., cutting parameters) based on the similar cases to meet the user's input requirements. By constructing the database and the case library for similar case retrieval, case rewriting that is more in line with the user's needs can be carried out based on the existing cases, improving the efficiency of process parameter design. On the other hand, to ensure the number of cases to be evaluated, further based on the user's input, a process parameter optimization model is constructed, and an optimization algorithm is used to optimize the process parameters to obtain optimized cases of process parameters that meet the user's input requirements. Then, the rewritten cases and the optimized cases are further evaluated to obtain the scores of each case. Subsequently, the user can refer to the required process parameters according to the scores of each case for the manufacturing of relevant part features. Obviously, the present invention can quickly determine the process parameters that meet the user's input requirements from the existing process parameter cases and the cases optimized by applying the optimization algorithm, which can shorten the design cycle of the process parameters of aeroengine part features and improve the efficiency of process parameter design. In addition, the optimization objectives of the present invention can be selected diversely, divided into two aspects: processing efficiency and surface processing quality, and on the basis of shortening the process design cycle, the requirements of multiple optimization objectives can be completed.

[0038] In an exemplary embodiment of the present application, for the similar case retrieval in step 101, if the user input only includes the processing feature type and the processing material, then according to the processing feature type and the 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, and the obtained similar cases specifically include:

[0039] (a1) 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, and a number of first-screened cases are obtained.

[0040] (a2) From the first-screened cases, cases with the same or similar material mechanical properties as the processing material input by the user are screened out to obtain a number of second-screened cases.

[0041] (a3) From the second-screened cases, cases with the same material mechanical properties or a material mechanical property similarity greater than a preset similarity value are screened out to obtain the similar cases.

[0042] In another exemplary embodiment of the present application, for the similar case retrieval in step 101, as Figure 6As shown, the user's input includes the machining feature type, machining material, and machining target. The same feature data is extracted one by one from the database and the case library, and local similarity calculations are performed on material mechanical property parameters such as material hardness and material tensile strength, and machining target parameters such as surface roughness and machining efficiency. Weight values are assigned to the above attributes (material mechanical property parameters and machining target parameters) through the attribute importance scoring matrix pre-completed by experts, so as to calculate the global similarity. The data with the global similarity reaching the threshold requirement (for example, 90%) is sorted and output according to size. Therefore, as another alternative implementation, in step 101, according to the machining feature type, machining material, and machining target input by the user, similar cases are retrieved 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, specifically including:

[0043] (b1) According to the machining feature type input by the user, cases with the same machining feature type are screened out from the historical actual machining cases stored in the database and the rewritten cases stored in the case library, and several third-screened cases are obtained.

[0044] (b2) From the third-screened cases, cases with the same or similar material mechanical properties of the machining material input by the user are screened out, and several fourth-screened cases are obtained.

[0045] (b3) From the third-screened cases, cases with the same or similar machining target as the machining target input by the user are screened out, and several fifth-screened cases are obtained.

[0046] (b4) Calculate the global similarity of the machining material and the machining target in the fourth-screened cases.

[0047] (b5) Calculate the global similarity of the machining material and the machining target in the fifth-screened cases.

[0048] When calculating the global similarity, according to the preset weight values of the machining material and the machining target, the global similarity is obtained by weighted summation in combination with their respective corresponding local similarities.

[0049] (b6) From the fourth-screened cases and the fifth-screened cases, cases with a global similarity greater than the preset global similarity are screened out, and the similar cases are obtained.

[0050] It should be noted that when performing case retrieval according to the cases in the case library and the database, if the same case is retrieved, it can be directly used. In the case where the same case is not found, similar case retrieval is performed.

[0051] In another exemplary embodiment of the present application, for the case rewriting in step 102, the cutting parameters of the similar cases are rewritten to obtain rewritten cases, specifically including:

[0052] (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.

[0053] (2) Determine the feed per tooth similarity between the similar case and the rewritten case according to the material similarity.

[0054] (3) Determine the cutting speed similarity between the similar case and the rewritten case according to the ratio of the thermal conductivity of the processed material in the similar case and the processed material input by the user; the cutting speed similarity is equal to the depth of cut similarity between the similar case and the rewritten case.

[0055] (4) Rewrite the cutting parameters in the similar case according to the feed per tooth similarity, the cutting speed similarity and the depth of cut similarity to obtain the rewritten case; the cutting parameters include cutting speed, feed per tooth, axial depth of cut and radial depth of cut.

[0056] Taking the example of rewriting the machining data of the blade profile feature TC4 titanium alloy into the machining data of TC17 titanium alloy, the relevant performance parameters of the two materials are shown in Tables 1 and 2 below.

[0057] Table 1 Mechanical property parameters of TC4 titanium alloy material

[0058]

[0059] Table 2 Milling cutting parameter data of TC4

[0060] <![CDATA[Cutting speed v c > <![CDATA[Feed per tooth f z > <![CDATA[Axial depth of cut a p > <![CDATA[Radial depth of cut a e > 44 m / min 0.027 mm / z 0.5 mm 0.5 mm

[0061] Thus, the material similarity m m , the feed per tooth similarity m fz , the cutting speed similarity m v , and the depth of cut similarity m a can be obtained by the following formula:

[0062]

[0063] m v = m a

[0064] where the cutting speed similarity m v is the ratio of the thermal conductivity of the two materials.

[0065] In the formula, m1 is the heat generation ratio, m2 is the tensile strength ratio, m3 is the elastic modulus ratio, m4 is the material aluminum content ratio, and k is the material correction coefficient (the value taken this time is 1.05); the calculation shows that:

[0066] mm ≈0.86, m v ≈0.52. The data of the TC17 rewriting cases (rewritten cutting parameters) can be obtained through parameter similarity calculation as shown in Table 3.

[0067] Table 3 Cutting Parameters in TC17 Rewriting Cases

[0068] <![CDATA[Cutting speed v c > <![CDATA[Feed per tooth f z > <![CDATA[Axial depth of cut a p > <![CDATA[Radial depth of cut a e > 84.6 m / min 0.023 mm / z 1 mm 1 mm

[0069] It should be noted that when there is no data in the database and case base whose similarity meets the conditions, case rewriting cannot be performed, and the rule inference engine will be used for rule inference work to infer a reasonable range of machining process parameters. For example, there will be a rough parameter range for machining aluminum alloy materials. The main purpose is to avoid the problem of no data output due to insufficient similarity and provide a reasonable parameter range reference for users. When similar cases are continuously retrieved, case evaluation will no longer be performed, and the inferred range of machining process parameters will be shown to the user for reference.

[0070] In another exemplary embodiment of the present application, for the process parameter optimization process in step 103, as Figure 7 shown, experimental data are obtained through a four-factor five-level orthogonal experiment (which refers to the measurement of milling force, surface quality, and machining deformation under the change of four cutting parameters). For each machining feature type, two process parameter optimization models are constructed through the response surface method: the surface machining quality model and the machining efficiency model. Taking the machining efficiency model and the surface machining quality model of the blade profile feature of the impeller part as an example, the formulas of its machining efficiency model and surface machining quality model are:

[0071]

[0072] Among them,

[0073]

[0074] The formula of the surface machining quality model is:

[0075]

[0076] Among them,

[0077] In the formula: v c is the cutting speed, f z is the feed per tooth, a eis the radial depth of cut, β1 is the weight of tool wear, β2 is the material weight, β3 is the cutting force weight, β4 is the surface roughness weight, and g i (x) is the penalty function of each unknown in the blade profile machining efficiency model, the t function is the cutting machining time function, d is the tool diameter, A is the milling area, and t c is the tool change time for one time, T is the tool durability, Ra is the surface roughness, Fy is the cutting force in the y direction, and c i (x) is the penalty function of each unknown in the blade profile surface quality model, and the F function is the main milling force function of the blade profile. Among them, the material weight β2 adjusts the specific value according to the machining material input by the user. When the user's input includes the machining target, the specific weight values of the parameters related to the machining target (machining result): the tool wear weight β1, the cutting force weight β3, and the surface roughness weight β4 are adjusted according to the machining target. If the user does not input the machining target, the weight values of the parameters related to the machining target (machining result) are selected as the conventional set values.

[0078] After determining the expression of the parameter optimization model, calculate the different weight coefficients of the surface quality model and the machining efficiency model according to multiple machining targets input by the user; as Figure 8 shown, when the user subjectively assigns values to the 4 weights according to the actual situation. Determine the boundary conditions of the parameter optimization model according to multiple machining targets input by the user; rewrite the parameter optimization model 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, use the PSO particle swarm optimization algorithm embedded in the program to optimize the cutting parameters, and finally obtain the optimal solution of the cutting parameters. As Figure 9 is the schematic diagram of particle swarm optimization. Figure 9 represents an iterative optimization process of a particle swarm algorithm.

[0079] Therefore, it can be obtained that in step 103, according to the parameter optimization model, apply the particle swarm algorithm to optimize the cutting parameters, and obtain the cutting parameter optimization result, which specifically includes:

[0080] (1) Determine the parameter optimization model according to the machining feature type and the machining material or the machining feature type, the machining material and the machining target; when the user's input includes the machining feature type and the machining material, the material weight parameter in the parameter optimization model determines the weight value according to the machining material input by the user, and the weight of the default machining target parameter in the parameter optimization model selects the preset weight value; when the user's input further includes the machining target, the weight of the default machining target parameter in the parameter optimization model determines the weight value according to the machining target input by the user;

[0081] (2) Calculate the particle fitness using the parameter optimization model, and apply the particle swarm algorithm to optimize the cutting parameters to obtain the optimization result of the cutting parameters; in the particle swarm algorithm, a particle is a numerical combination of a set of cutting parameters.

[0082] In another exemplary embodiment of the present application, the case evaluation in step 104 uses the grey relational analysis method:

[0083] (1) Establishment and normalization of the evaluation index matrix.

[0084] a. Establish the evaluation index matrix:

[0085] Let U = {u1, u2,..., u i ,..., u m} be the set of machining plans, where u i represents the i-th machining plan, and m represents the number of plans in the machining plan set. Let V = {v1, v2,..., v i ,..., v n} be 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: flank wear VB of the tool. v1 and v2 represent machining quality, and v3 represents tool life. Then, the element pairs (u i , v j ) formed by any combination of elements from the machining plan set U and the machining evaluation index set V constitute the Cartesian product set. It is stipulated that the element pair (u i , v j ) is f ij . Then, m × n f ij constitute the finishing evaluation index matrix F = (f ij ) m×n .

[0086] b. Normalization of the evaluation index

[0087] Different evaluation indexes usually have different dimensions and orders of magnitude. To eliminate the influence and ensure the accuracy and reliability of the results, different methods are used to normalize different types of evaluation indexes.

[0088] (2) Establishment of the scheme decision model

[0089] a. Grey relational degree of the scheme

[0090] According to the grey relational decision-making theory, the quality order of processing plans can be judged by comparing the relational degrees between each evaluation index vector and the evaluation index vector of the relatively optimal processing plan. The larger the relational degree, the closer it is to the optimum. Let the relatively optimal processing plan be u0 = (f 01 , f 02 , …, f 0n ). After normalization, u0 = (1, 1, …, 1). The grey relational degree between the evaluation index v i of the processing plan u j and the evaluation index v j of the relatively optimal processing plan u0 is as follows:

[0091]

[0092] In the formula, ξ ∈ (0, 1) is the resolution coefficient, and its value is difficult to quantify and usually depends on experience. Generally, it is taken as 0.5, i = 1, 2, …, m; j = 1, 2, …, n.

[0093] b. Determine the index weight

[0094] c. Decision-making model

[0095] From the above analysis, the grey relational degree matrix of the processing plan can be expressed as:

[0096]

[0097] The weight vector of n evaluation indexes can be expressed as W = (w1, w2, …, w n ). Based on the grey relational degree matrix and the weight vector, the weighted relational degree γ i between the processing plan u i and the relatively optimal processing plan u0 can be used to form the relational vector γ′.

[0098] γ′ = γW = (γ1, γ2, ..., γ i ,.., γ m );

[0099] Among them, The larger the weighted relational degree γ i , the closer the plan u i is to the relatively optimal plan u0.

[0100] Therefore, in step 104, case evaluation is performed on the rewritten case and the optimized case to obtain the case scores of the rewritten case and the optimized case, which specifically includes:

[0101] (1) Construct a processing evaluation index matrix based on the rewritten case, the optimized case, and their respective corresponding processing objectives; the elements in the processing evaluation index matrix are element pairs formed by arbitrarily matching each evaluation scheme with the evaluation indexes; the evaluation schemes refer to the rewritten case and the optimized case; the evaluation indexes are determined according to the processing objectives.

[0102] (2) Perform standardization processing on the processing evaluation index matrix to obtain the preprocessed processing evaluation index matrix.

[0103] (3) Calculate the grey relational degree between the evaluation index of each evaluation scheme and the evaluation index of the relatively optimal processing scheme according to the processing evaluation index matrix and the evaluation indexes corresponding to the relatively optimal processing scheme; the grey relational degrees corresponding to each evaluation scheme form the grey relational degree matrix of each evaluation scheme; the relatively optimal processing scheme is predefined.

[0104] (4) Determine the weight values of the evaluation indexes corresponding to the evaluation schemes.

[0105] (5) Calculate the weighted relational degree between each evaluation scheme and the relatively optimal scheme according to the weight values and the grey relational degree matrix; the weighted relational degree corresponding to each evaluation scheme is the case score.

[0106] In another exemplary embodiment of the present application, after evaluating the cases, several cases with higher scores in the rewritten case and the optimized case are further stored in the case library. Therefore, after performing step 104 "evaluate the rewritten case and the optimized case to obtain the scores of the rewritten case and the optimized case", the method for evaluating the characteristic process parameters design of aero-engine parts further includes:

[0107] (1) Sort the case scores from largest to smallest.

[0108] (2) Select multiple cases with higher case scores and store them in the case library.

[0109] The present application also provides an application scenario that applies the above method for evaluating the characteristic process parameters design of aero-engine parts. Specifically: The method for evaluating the characteristic process parameters design of aero-engine parts provided in this embodiment is mainly applied to the compilation of the process specifications of new aero-engines, providing suitable process parameter references for existing processing procedures. This scenario includes the following links: analyzing part drawings, formulating process routes, determining processing equipment, determining machining allowances, determining process parameters, and preparing for approval. The method for processing video tags provided in this embodiment belongs to the link of determining process parameters.

[0110] 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 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 need to comply with relevant regulations.

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. The databases involved in the embodiments provided in this application can include relational databases. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0112] Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for designing and evaluating characteristic process parameters of an aero-engine part, characterized in that, The method for designing and evaluating characteristic process parameters of aero-engine parts includes: Retrieving similar cases from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to 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 types of the components of the aero-engine; the historical actual processing cases and the rewritten cases include 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 cases to obtain rewritten cases; Optimizing the cutting parameters by applying the particle swarm algorithm according to the parameter optimization model to obtain the optimization result of the cutting parameters; 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; Evaluating the rewritten cases and the optimized cases to obtain the case scores of the rewritten cases and the optimized cases to display the rewritten cases, the optimized cases and the corresponding case scores to the user; the optimized cases include the optimization result of the cutting parameters, the processing feature type, the processing material and the processing result; when the user's input includes a processing target, the processing result is determined according to the processing target; when the user's 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.

2. The design evaluation method for the characteristic process parameters of the aero-engine parts according to claim 1, wherein, Retrieving similar cases from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to the processing feature type and processing material input by the user, to obtain similar cases, specifically including: Screening out cases with the same processing feature type from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to the processing feature type input by the user, to obtain a number of first screened cases; Screening out cases with the same or similar material mechanical properties as the processing material input by the user from the first screened cases, to obtain a number of second screened cases; Screening out cases with the same material mechanical properties or a material mechanical property similarity greater than a preset similarity value from the second screened cases to obtain the similar cases.

3. The method for designing and evaluating the characteristic process parameters of an aero-engine part according to claim 1, wherein Retrieving similar cases from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to the processing feature type, processing material and processing target input by the user, to obtain similar cases, specifically including: Screening out cases with the same processing feature type from the historical actual processing cases stored in the database and the rewritten cases stored in the case library according to the processing feature type input by the user, to obtain a number of third screened cases; From the third screening cases, screen out the cases with the same or similar material mechanical properties as the processing material input by the user to obtain several fourth screening cases; From the third screening cases, screen out the cases with the same or similar processing objectives as the processing objective input by the user to obtain several fifth screening cases; Calculate the global similarity of the processing materials and processing objectives in the fourth screening cases; Calculate the global similarity of the processing materials and processing objectives in the fifth screening cases; From the fourth screening cases and the fifth screening cases, screen out the cases with a global similarity greater than the preset global similarity to obtain the similar cases; 4. The method for designing and evaluating the characteristic process parameters of an aero-engine part according to claim 1, wherein Rewrite the cutting parameters of the similar cases to obtain rewritten cases, specifically including: For each similar case, calculate the material similarity between the processing material in the similar case and the processing material input by the user; Determine the feed per tooth similarity between the similar case and the rewritten case according to the material similarity; Determine the cutting speed similarity between the similar case and the rewritten case according to the ratio of the thermal conductivity of the processing material in the similar case to the processing material input by the user; the cutting speed similarity is equal to the depth of cut similarity between the similar case and the rewritten case; Rewrite the cutting parameters in the similar case according to the feed per tooth similarity, the cutting speed similarity and the depth of cut similarity to obtain the rewritten case; the cutting parameters include cutting speed, feed per tooth, axial depth of cut and radial depth of cut.

5. The method for designing and evaluating the characteristic process parameters of an aero-engine part according to claim 1, characterized in that, According to the parameter optimization model, apply the particle swarm algorithm to optimize the cutting parameters to obtain the optimization result of the cutting parameters, specifically including: Determine the parameter optimization model according to the processing feature type and the processing material or the processing feature type, the processing material and the processing objective; when the user input includes the processing feature type and the processing material, the material weight parameter in the parameter optimization model determines the weight value according to the processing material input by the user, and the weight of the default processing objective parameter in the parameter optimization model selects the preset weight value; when the user input further includes the processing objective, the weight of the default processing objective parameter in the parameter optimization model determines the weight value according to the processing objective input by the user; Calculate the particle fitness with the parameter optimization model, and apply the particle swarm algorithm to optimize the cutting parameters to obtain the optimization result of the cutting parameters; in the particle swarm algorithm, a particle is a numerical combination of a set of cutting parameters.

6. The method for designing and evaluating the characteristic process parameters of an aero-engine part according to claim 1, characterized in that Conduct case evaluation on the rewritten cases and the optimized cases to obtain the case scores of the rewritten cases and the optimized cases, specifically including: Construct a processing evaluation index matrix according to the rewritten cases and the optimized cases and their respective corresponding processing objectives; the elements in the processing evaluation index matrix are element pairs formed by arbitrarily matching each evaluation scheme with the evaluation index; the evaluation schemes refer to the rewritten cases and the optimized cases; the evaluation index is determined according to the processing objective; Perform standardization processing on the processing evaluation index matrix to obtain the preprocessed processing evaluation index matrix; Calculate the grey relational degree between the evaluation index of each to-be-evaluated solution and the evaluation index of the relatively optimal processing solution according to the processing evaluation index matrix and the evaluation index corresponding to the relatively optimal processing solution; the grey relational degrees corresponding to each to-be-evaluated solution constitute the grey relational degree matrix of each to-be-evaluated solution; the relatively optimal processing solution is predefined; Determine the weight values of the evaluation indexes corresponding to the to-be-evaluated solution; Calculate the weighted relational degree between each to-be-evaluated solution and the relatively optimal solution according to the weight values and the grey relational degree matrix; the weighted relational degree corresponding to each to-be-evaluated solution is the case score.

7. The method for designing and evaluating the characteristic process parameters of an aero-engine part according to claim 1, characterized in that, After performing the step of "conducting case evaluation on the rewritten case and the optimized case to obtain the case scores of the rewritten case and the optimized case", the method for evaluating the process parameter design of the aero-engine part features further includes: Sort the case scores from large to small; Select multiple cases with higher case scores and store them in the case library.

Images