Aero-engine typical material cutting and grinding basic database building and using method

Abstract

The invention provides an aero-engine typical material cutting and grinding basic database building and using method, relates to the technical field of aerospace machining, and aims at materials such as high-temperature alloy, titanium alloy and intermetallic compounds related to aero-engine typical components and a conventional machining method to build a cutting and grinding basic database. Based on the cutting and grinding basic database, a cutting force model, a temperature field model, a surface roughness prediction model, a residual stress prediction model and a microhardness prediction model are trained, so that the cutting and grinding basic database can effectively support application scenes such as typical component manufacturing process optimization and machining surface integrity prediction; and the stability and the consistency of the component machining quality are ensured. The technology can be applied to the machining process design process of the typical material component of the aero-engine, the actual test machining test number and test period of the component can be effectively reduced through surface integrity and fatigue performance prediction, and the test cost is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of aerospace machining technology, and in particular to a method for building and using a basic database for cutting and grinding typical materials of aircraft engines. Background Art

[0002] At present, a large amount of data is generated in the test and production process of aircraft engine components. However, due to the large number of scattered data sources, poor reliability and standardization, incomplete data accumulation and mining methods, insufficient basic processing performance data, and the lack of systematic sorting, summarization and evaluation of existing data knowledge, the enabling tools such as data knowledge reuse reasoning are incomplete, and intelligent push, parameter optimization, and surface integrity prediction cannot be achieved. Data is a static resource, and the parameters ultimately used in parts processing are mostly based on experience, resulting in low stability and consistency in the processing of typical parts of aircraft engines. The data has not achieved high utilization value and cannot meet the actual use needs of the production site. In addition, the existing process design and processing parameter design optimization mostly rely on experiments and personal experience, lacking the support of key material cutting / grinding basic processing performance data in the process, and the quality of parts processing mostly relies on post-testing. The overall cycle is long, the cost is high, and the actual product quality stability is poor. This patent invents a method for building and using a basic database for cutting and grinding of typical materials of aircraft engines. By developing a basic database for cutting / grinding of key materials, it provides basic data support for key material processing performance for the establishment of a basic data knowledge platform for mechanical processing technology, and provides reference and reference for subsequent part trial production process parameter optimization and surface integrity prediction. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to propose a method for building and using a basic database for cutting and grinding of typical materials for aircraft engines, including:

[0004] Step 1: Obtain parameters of the pre-tested piece and parameters of the pre-tested piece in the actual processing process to obtain parameters to be predicted, wherein the parameters to be predicted include material properties of the pre-tested piece, specimen size of the pre-tested piece, processing tool parameters and processing process parameters, and the material of the pre-tested piece is a typical material of an aerospace engine, and the typical material of an aerospace engine is a metal material of an aerospace engine;

[0005] Step 2: Based on the pre-built cutting and grinding basic database, verify the validity of the parameters to be predicted to obtain a validity verification result. If the validity verification result indicates that the verification has been passed, output a prompt message of parameter error; if the validity verification result indicates that the verification has been passed, preprocess and format convert the parameters to be predicted in turn to obtain the parameters to be predicted after format conversion;

[0006] Step 3: Search in the basic cutting and grinding database according to the parameters to be predicted after format conversion. If the prediction results corresponding to the parameters to be predicted after format conversion are found in the basic cutting and grinding database, the prediction results are cutting force, or temperature, or surface roughness, or residual stress, or microhardness, and the prediction results are output through visualization technology. If the prediction results corresponding to the parameters to be predicted after format conversion are not found in the basic cutting and grinding database, execute step 4;

[0007] Step 4: Obtain the indicators that need to be predicted for the parameters to be predicted after format conversion. According to the indicators that need to be predicted for the parameters to be predicted after format conversion, select the target model from the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model, input the parameters to be predicted after format conversion into the target model, obtain the prediction results, and output the prediction results through visualization technology.

[0008] Among them, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are obtained by model training based on the pre-built cutting and grinding basic database.

[0009] Optionally, the cutting and grinding basic database is constructed by the following steps:

[0010] Step A1: constructing a framework of a cutting and grinding basic database. Specifically, designing a data table in the cutting and grinding basic database, selecting fields in the data table, and creating an index of the cutting and grinding basic database to obtain a framework of the cutting and grinding basic database.

[0011] Step A2: for a test piece made of typical aerospace engine materials, obtaining test parameters during a cutting and grinding test using a single-edged tool, wherein the test parameters include: material properties of the test piece, test piece dimensions, machining tool parameters, machining process parameters, test process monitoring data, and detection data;

[0012] Step A3: Based on the framework of the cutting and grinding basic database and the test parameters, a cutting and grinding basic database for typical aero-engine materials is constructed.

[0013] Optionally, the material properties include material type, grade, heat treatment state, density, tensile strength, elastic modulus, Poisson's ratio, specific heat capacity, thermal conductivity, and linear expansion coefficient;

[0014] The specimen size includes the length, width, height, and appearance of the specimen;

[0015] Machining tool parameters include tool type and tool size;

[0016] Processing parameters include cutting speed, feed rate, back cutting amount, and cutting depth;

[0017] The monitoring data during the test process include cutting and grinding sound, cutting and grinding force, and cutting and grinding temperature;

[0018] The test data includes surface integrity test data, tool grinding tool test data, and fatigue performance test data;

[0019] Wherein, the surface integrity detection data includes surface morphology, workpiece surface, residual stress, macro-microstructure, and microhardness; wherein, the surface morphology includes surface roughness Ra, Rz, Ry, surface morphology stress concentration coefficient Kst, and three-dimensional morphology pictures; white light pictures of the workpiece surface at different detection magnifications, super depth of field pictures at different detection magnifications, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, residual stress includes surface residual stress δ, residual stress influence layer depth, maximum residual stress depth, and surface residual stress distribution curve; wherein, macro-microstructure plastic deformation layer depth, white layer thickness, wrinkle depth, cracks, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, microhardness surface microhardness value, microhardness influence layer depth, and surface microhardness distribution curve;

[0020] Among them, the tool grinding tool detection data includes wear value and wear morphology picture;

[0021] Among them, the fatigue performance test data include the amplitude, frequency, temperature, stress, time, and fracture pictures of vibration fatigue, the amplitude, frequency, temperature, stress, time, and fracture pictures of micro-motion fatigue, and the amplitude, frequency, temperature, stress, time, and fracture pictures of thermal fatigue.

[0022] Optionally, the cutting force model is obtained by model training based on a first training sample, the first training sample comprising a first input sample and a first output sample, the first input sample being the material properties, specimen size, machining tool parameters and machining process parameters of the specimen in the cutting and grinding basic database, and the first output sample being the cutting force exerted on the specimen during the test in the cutting and grinding basic database.

[0023] Optionally, the temperature field model is obtained by model training based on a second training sample, the second training sample includes a second input sample and a second output sample, the second input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the second output sample is the temperature of the specimen during the test in the cutting and grinding basic database.

[0024] Optionally, the surface roughness prediction model is obtained by model training based on a third training sample, the third training sample includes a third input sample and a third output sample, the third input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the third output sample is the surface roughness of the specimen after the test in the cutting and grinding basic database.

[0025] Optionally, the residual stress prediction model is obtained by model training based on a fourth training sample, and the fourth training sample includes a fourth input sample and a fourth output sample. The fourth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fourth output sample is the residual stress of the surface or surface layer of the specimen after the test in the cutting and grinding basic database.

[0026] Optionally, the microhardness prediction model is obtained by model training based on a fifth training sample, the fifth training sample including a fifth input sample and a fourth output sample, the fifth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fifth output sample is the microhardness of the specimen surface after the test in the cutting and grinding basic database.

[0027] Optionally, when the indicator to be predicted for the parameter to be predicted after format conversion is cutting force, the target model is a cutting force model, and the prediction result is the cutting force to which the predicted test piece is subjected during the actual machining process;

[0028] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is temperature, the target model is a temperature field model, and the prediction result is the temperature of the piece to be predicted during the actual processing;

[0029] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is surface roughness, the target model is a surface roughness prediction model, and the prediction result is the surface roughness of the workpiece to be predicted after actual processing;

[0030] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is residual stress, the target model is a residual stress prediction model, and the prediction result is the residual stress of the surface or surface layer of the to-be-predicted piece after actual processing;

[0031] When the indicator to be predicted for the parameter to be predicted after format conversion is microhardness, the target model is a microhardness prediction model, and the prediction result is the microhardness of the surface to be tested of the actual processed piece to be tested.

[0032] Optionally, also include:

[0033] The cutting and grinding basic database is updated according to the prediction results, and then based on the updated cutting and grinding basic database, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are updated.

[0034] The beneficial effects of adopting the above technical solution are:

[0035] The present invention aims at the high-temperature alloys, titanium alloys, intermetallic compounds and other materials involved in typical aircraft engine components and conventional machining methods, builds a basic cutting and grinding database, and based on the basic cutting and grinding database, trains cutting force models, temperature field models, surface roughness prediction models, residual stress prediction models and microhardness prediction models, so that the basic cutting and grinding database can effectively support typical component manufacturing process optimization and machining surface integrity prediction and other application scenarios, ensuring the stability and consistency of component machining quality. This technology can be applied to the mechanical machining process design process of typical aircraft engine material components. The surface integrity and fatigue performance prediction achieved by it can effectively reduce the number of actual component test processing tests and test cycles, and effectively reduce the test cost.

[0036] In addition, the materials and manufacturing methods involved in the database are highly versatile and practical in typical components of aircraft engines and gas turbines. With the increasing demand for product quantity and quality of new engines, the economic and social benefits are enormous. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a process for establishing and using a basic database for cutting and grinding of typical materials for aircraft engines in an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a process for establishing and using another basic database for cutting and grinding of typical aero-engine materials in an embodiment of the present invention;

[0039] Figure 3 It is a schematic diagram of the simulation process of the construction and use of a basic database for cutting and grinding of typical materials for aircraft engines in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0041] In view of the high-temperature alloys, titanium alloys, intermetallic compounds and other materials involved in typical aircraft engine components and conventional mechanical processing methods, the present invention proposes a method for building and using a basic database for cutting and grinding of typical aircraft engine materials. By building a basic database framework for typical material cutting and grinding, clarifying attribute items, standardizing the test process, data collection requirements, and expression forms, and establishing logical relationships between data, the database can effectively support application scenarios such as typical component manufacturing process optimization and processing surface integrity prediction, thereby ensuring the stability and consistency of component processing quality.

[0042] Specifically, the present invention provides a method for building and using a basic database for cutting and grinding of typical materials for aircraft engines. Figure 1 , which may include the following steps:

[0043] Step 1: Obtain parameters of the pre-tested piece and parameters of the pre-tested piece in the actual processing process to obtain parameters to be predicted, wherein the parameters to be predicted include material properties of the pre-tested piece, specimen size of the pre-tested piece, processing tool parameters and processing process parameters, and the material of the pre-tested piece is a typical material of an aerospace engine, and the typical material of an aerospace engine is a metal material of an aerospace engine;

[0044] The parameters of the pre-tested piece and the parameters of the pre-tested piece during the actual processing may be input by a staff member, or may be transmitted through other systems.

[0045] Step 2: Based on the pre-built cutting and grinding basic database, verify the validity of the parameters to be predicted to obtain a validity verification result. If the validity verification result indicates that the verification has been passed, output a prompt message of parameter error; if the validity verification result indicates that the verification has been passed, preprocess and format convert the parameters to be predicted in turn to obtain the parameters to be predicted after format conversion;

[0046] The cutting and grinding basic database is specifically constructed by the following steps:

[0047] Step A1: constructing a framework of a cutting and grinding basic database. Specifically, designing a data table in the cutting and grinding basic database, selecting fields in the data table, and creating an index of the cutting and grinding basic database to obtain a framework of the cutting and grinding basic database.

[0048] In the specific implementation, the existing typical materials, namely the cutting and grinding characteristics and processing experience of aviation engine metal materials, and the database usage requirements, complete the preliminary construction of the basic database framework for cutting and grinding, including the design of data tables, the selection of fields, and the creation of indexes. This ensures that the database can efficiently store and manage process data.

[0049] Step A2: for a test piece made of typical aerospace engine materials, obtaining test parameters during a cutting and grinding test using a single-edged tool, wherein the test parameters include: material properties of the test piece, test piece dimensions, machining tool parameters, machining process parameters, test process monitoring data, and detection data;

[0050] Specifically, according to the standard test methods and requirements pre-designed in the present invention, cutting and grinding simulation tests are developed based on single-factor, orthogonal tests and response surfaces for key materials, preliminary tool materials, parameters and process parameter ranges. The basic cutting parameters are obtained by basic cutting tests using single-edged tools on different materials. The test requirements for surface integrity indicators and fatigue performance indicators and the expression form of test results are determined to obtain the test parameters.

[0051] The material properties include material type, grade, heat treatment state, density, tensile strength, elastic modulus, Poisson's ratio, specific heat capacity, thermal conductivity, and linear expansion coefficient; wherein the density, tensile strength, elastic modulus, Poisson's ratio, specific heat capacity, thermal conductivity, and linear expansion coefficient can be obtained from an existing material library;

[0052] The specimen size includes the length, width, height, and appearance of the specimen;

[0053] The processing tool parameters include tool type and tool size; wherein the tool size can be obtained from an existing tool library;

[0054] Processing parameters include cutting speed, feed rate, back cutting amount, and cutting depth;

[0055] The monitoring data during the test process include cutting and grinding sound, cutting and grinding force, and cutting and grinding temperature;

[0056] The test data includes surface integrity test data, tool grinding tool test data, and fatigue performance test data;

[0057] Wherein, the surface integrity detection data includes surface morphology, workpiece surface, residual stress, macro-microstructure, and microhardness; wherein, the surface morphology includes surface roughness Ra, Rz, Ry, surface morphology stress concentration coefficient Kst, and three-dimensional morphology pictures; white light pictures of the workpiece surface at different detection magnifications, super depth of field pictures at different detection magnifications, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, residual stress includes surface residual stress δ, residual stress influence layer depth, maximum residual stress depth, and surface residual stress distribution curve; wherein, macro-microstructure plastic deformation layer depth, white layer thickness, wrinkle depth, cracks, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, microhardness surface microhardness value, microhardness influence layer depth, and surface microhardness distribution curve;

[0058] Among them, the tool grinding tool detection data includes wear value and wear morphology picture;

[0059] Among them, the fatigue performance test data include the amplitude, frequency, temperature, stress, time, and fracture pictures of vibration fatigue, the amplitude, frequency, temperature, stress, time, and fracture pictures of micro-motion fatigue, and the amplitude, frequency, temperature, stress, time, and fracture pictures of thermal fatigue.

[0060] Step A3: Based on the framework of the cutting and grinding basic database and the test parameters, a cutting and grinding basic database for typical aero-engine materials is constructed.

[0061] Among them, in order to ensure the quality of data in the cutting and grinding basic database, there must be a mechanism for testing data quality, which mainly includes data correctness review and metadata management. To ensure data visualization, different viewing requirements such as data overview, data list and data details must be realized.

[0062] In order to ensure the quality of data, the present invention will conduct a correctness review on the data in the cutting and grinding basic database.

[0063] Among them, the prediction parameters are preprocessed and format converted in sequence, including:

[0064] Clean the parameters to be predicted and remove redundant or erroneous information, such as parameters whose values ​​far exceed the threshold range, to ensure their integrity and validity and provide accurate input for the subsequent operation. The format conversion is to convert the cleaned parameters to be predicted into the format required by the target model in step 3.

[0065] Step 3: Search in the basic cutting and grinding database according to the parameters to be predicted after format conversion. If the prediction results corresponding to the parameters to be predicted after format conversion are found in the basic cutting and grinding database, the prediction results are cutting force, or temperature, or surface roughness, or residual stress, or microhardness, and the prediction results are output through visualization technology. If the prediction results corresponding to the parameters to be predicted after format conversion are not found in the basic cutting and grinding database, execute step 4;

[0066] Among them, in the process of searching in the cutting and grinding basic database, the present invention can construct an optimized query statement to efficiently extract relevant data from the database, such as the mechanical and thermal properties of the material, that is, the prediction result.

[0067] Among them, according to user needs, the prediction results can also be multiple parameters including cutting force, temperature, surface roughness, residual stress, and microhardness.

[0068] Based on the above-mentioned basic database of cutting and grinding, when predicting indicators, based on existing data such as materials, processing, test values, graphics, curves, and charts, a combination of cutting / grinding tests and physical simulation is used to obtain the constitutive parameters of materials under high temperature and high strain rate conditions during cutting / grinding. A cross-scale simulation model of the processing process is established based on methods such as crystal plasticity finite element and cellular automaton, and the relationship between various processing data of cutting and grinding and processing quality, surface integrity, and fatigue performance test data is established. Through general simulation analysis software, empirical formulas, mathematical algorithms, etc., special training models, parameter optimization, surface quality processing result prediction, service performance prediction and other formulas and algorithms are formed. Based on the above ideas, when the prediction results corresponding to the parameters to be predicted after format conversion are not found in the basic database of cutting and grinding, the content in step 4 is designed.

[0069] Step 4: Obtain the indicators that need to be predicted for the parameters to be predicted after format conversion, select the target model from the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model according to the indicators that need to be predicted for the parameters to be predicted after format conversion, input the parameters to be predicted after format conversion into the target model, obtain the prediction results, and output the prediction results through visualization technology;

[0070] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is cutting force, the target model is a cutting force model, and the prediction result is the cutting force to which the predicted test piece is subjected during the actual machining process;

[0071] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is temperature, the target model is a temperature field model, and the prediction result is the temperature of the piece to be predicted during the actual processing;

[0072] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is surface roughness, the target model is a surface roughness prediction model, and the prediction result is the surface roughness of the workpiece to be predicted after actual processing;

[0073] In the case where the indicator to be predicted for the parameter to be predicted after format conversion is residual stress, the target model is a residual stress prediction model, and the prediction result is the residual stress of the surface or surface layer of the to-be-predicted piece after actual processing;

[0074] When the indicator to be predicted for the parameter to be predicted after format conversion is microhardness, the target model is a microhardness prediction model, and the prediction result is the microhardness of the surface to be tested of the actual processed piece to be tested.

[0075] Among them, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are obtained by model training based on the pre-built cutting and grinding basic database, and are all stored in the cutting and grinding basic database in the form of plug-ins. When in use, the plug-ins are called from the cutting and grinding basic database for use.

[0076] The cutting force model is obtained by model training based on a first training sample, wherein the first training sample includes a first input sample and a first output sample, wherein the first input sample is the material properties, specimen size, machining tool parameters and machining process parameters of the specimen in the cutting and grinding basic database, and the first output sample is the cutting force exerted on the specimen during the test in the cutting and grinding basic database.

[0077] Among them, the cutting force model and the cutting force model of finite element analysis can predict the cutting force under different cutting conditions. This model takes into account factors such as the physical properties of the material, the geometry of the tool, and the cutting parameters, providing an important basis for optimizing process parameters.

[0078] The temperature field model is obtained by model training based on the second training sample, the second training sample includes a second input sample and a second output sample, the second input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the second output sample is the temperature of the specimen in the cutting and grinding basic database during the test.

[0079] Among them, the temperature field model based on the temperature field model of heat conduction theory can predict the temperature distribution during the machining process. This model takes into account factors such as cutting heat, coolant circulation, and thermal properties of the workpiece material, and is of great significance for controlling thermal deformation and surface quality during machining.

[0080] The surface roughness prediction model is obtained by model training based on the third training sample, and the third training sample includes a third input sample and a third output sample. The third input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the third output sample is the surface roughness of the specimen after the test in the cutting and grinding basic database.

[0081] Among them, the surface roughness prediction model based on regression analysis or neural network can predict the roughness of the machined surface according to the input information such as material, cutting parameters and tool type. These models are obtained by training a large amount of experimental data and have high prediction accuracy and generalization ability.

[0082] The residual stress prediction model is obtained by model training based on the fourth training sample, and the fourth training sample includes a fourth input sample and a fourth output sample. The fourth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fourth output sample is the residual stress of the surface or surface layer of the specimen after the test in the cutting and grinding basic database.

[0083] The microhardness prediction model is obtained by model training based on the fifth training sample, and the fifth training sample includes a fifth input sample and a fourth output sample. The fifth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fifth output sample is the microhardness of the specimen surface after the test in the cutting and grinding basic database.

[0084] It should be noted that when the parameters of the pre-tested piece and the parameters of the pre-tested piece during actual processing are transmitted through other systems, the prediction results may need to be returned to the other systems.

[0085] Combination Figure 2 As for the above steps, when implemented by a programming language, the present invention can obtain the parameters of the pre-tested piece and the parameters of the pre-tested piece in the actual processing process, that is, the parameters transmitted by other systems, through the user's choice to read the database or parameter matrix file, read the read data or parameter matrix file, and report an error and return when the reading fails. When the reading is successful, the python program is called, that is, the target model is selected in the cutting and grinding basic database; when the user inputs parameters from the interface, that is, the staff inputs them, the present invention needs to determine whether the input parameters are comprehensive and compliant. When the input parameters are incomplete or non-compliant, an error is reported and returned. For example, if the input parameters far exceed the preset threshold range, it means that there may be an input error. When the parameters are complete and compliant, the python program is called.

[0086] If the Python program reports an error, it will report an error and return. If the Python program runs successfully, it will show that the running is completed. The user can read the file, that is, the user clicks the link to view the result file, or the user can input from the interface, that is, the user clicks to enter the result interface to view the result. Figure 2 The prediction of machining quality and efficiency is to predict one or more parameters including cutting force, temperature, surface roughness, residual stress and microhardness.

[0087] The cutting and grinding basic database is updated according to the prediction results, and then based on the updated cutting and grinding basic database, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are updated, wherein the prediction results are of great significance for evaluating processing quality, optimizing process parameters and improving production efficiency.

[0088] The solution provided by the present invention needs to be managed during the implementation process, with a focus on algorithm model management and data security management. Algorithm model management mainly manages the corresponding data of the algorithm model formed by research, including model name, model development language, model common interface, model purpose, usage rules, input parameter template, output parameter template and other data, and query and display the input and output historical data. Data security management includes user access rights, data resource authority management, auditing, etc.

[0089] Based on the above scheme, the present invention obtains the parameters of the pre-tested piece and the parameters of the pre-tested piece during the simulation process through physical simulation, and obtains the prediction results through program simulation. Specifically, Figure 3 The present invention obtains the process parameters of the component processing method from the geometric simulation database, obtains data from the cutting and grinding basic database, material library and tool library, and then performs the parameters of PM physical simulation, and then performs physical simulation to obtain simulation data, and inputs the simulation data and the data before the simulation into the CAE software, that is, the parameters of the pre-tested piece and the parameters of the pre-tested piece during the simulation processing are input into the CAE software, and then the program simulation is performed in the operating environment to obtain the prediction results, and a detailed report containing a simulation overview, performance analysis and optimization suggestions is generated, and the simulation results are displayed using visualization techniques such as charts, curves and animations, so that users can understand and analyze the physical performance of the processing process. Based on the prediction results, the cutting and grinding basic database can also be updated, and further, the physical simulation or program simulation program can be optimized, and the optimized program is stored in the cutting and grinding basic database.

[0090] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) to form a technical solution.

Claims

1. A method for building and using a basic database for cutting and grinding of typical materials for aircraft engines, characterized in that: include: Step 1: Obtain parameters of the pre-tested piece and parameters of the pre-tested piece in the actual processing process to obtain parameters to be predicted, wherein the parameters to be predicted include material properties of the pre-tested piece, specimen size of the pre-tested piece, processing tool parameters and processing process parameters, and the material of the pre-tested piece is a typical material of an aerospace engine, and the typical material of an aerospace engine is a metal material of an aerospace engine; Step 2: Based on the pre-built cutting and grinding basic database, verify the validity of the parameters to be predicted to obtain a validity verification result. If the validity verification result indicates that the verification has been passed, output a prompt message of parameter error; if the validity verification result indicates that the verification has been passed, preprocess and format convert the parameters to be predicted in turn to obtain the parameters to be predicted after format conversion; Step 3: Search in the basic cutting and grinding database according to the parameters to be predicted after format conversion. If the prediction results corresponding to the parameters to be predicted after format conversion are found in the basic cutting and grinding database, the prediction results are cutting force, or temperature, or surface roughness, or residual stress, or microhardness, and the prediction results are output through visualization technology. If the prediction results corresponding to the parameters to be predicted after format conversion are not found in the basic cutting and grinding database, execute step 4; Step 4: Obtain the indicators that need to be predicted for the parameters to be predicted after format conversion. According to the indicators that need to be predicted for the parameters to be predicted after format conversion, select the target model from the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model, input the parameters to be predicted after format conversion into the target model, obtain the prediction results, and output the prediction results through visualization technology. Among them, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are obtained by model training based on the pre-built cutting and grinding basic database.

2. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1 is characterized in that: The cutting and grinding basic database is specifically constructed by the following steps: Step A1: constructing a framework of a cutting and grinding basic database. Specifically, designing a data table in the cutting and grinding basic database, selecting fields in the data table, and creating an index of the cutting and grinding basic database to obtain a framework of the cutting and grinding basic database. Step A2: for a test piece made of typical aerospace engine materials, obtaining test parameters during a cutting and grinding test using a single-edged tool, wherein the test parameters include: material properties of the test piece, test piece dimensions, machining tool parameters, machining process parameters, test process monitoring data, and detection data; Step A3: Based on the framework of the cutting and grinding basic database and the test parameters, a cutting and grinding basic database for typical aero-engine materials is constructed.

3. The method for building and using a basic database for cutting and grinding of typical materials for aircraft engines according to claim 2 is characterized in that: The material properties include material type, grade, heat treatment state, density, tensile strength, elastic modulus, Poisson's ratio, specific heat capacity, thermal conductivity, and linear expansion coefficient; The specimen size includes the length, width, height, and appearance of the specimen; Machining tool parameters include tool type and tool size; Processing parameters include cutting speed, feed rate, back cutting amount, and cutting depth; The monitoring data during the test process include cutting and grinding sound, cutting and grinding force, and cutting and grinding temperature; The test data includes surface integrity test data, tool grinding tool test data, and fatigue performance test data; Wherein, the surface integrity detection data includes surface morphology, workpiece surface, residual stress, macro-microstructure, and microhardness; wherein, the surface morphology includes surface roughness Ra, Rz, Ry, surface morphology stress concentration coefficient Kst, and three-dimensional morphology pictures; white light pictures of the workpiece surface at different detection magnifications, super depth of field pictures at different detection magnifications, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, residual stress includes surface residual stress δ, residual stress influence layer depth, maximum residual stress depth, and surface residual stress distribution curve; wherein, macro-microstructure plastic deformation layer depth, white layer thickness, wrinkle depth, cracks, metallographic pictures at different detection magnifications, and SEM pictures at different detection magnifications; wherein, microhardness surface microhardness value, microhardness influence layer depth, and surface microhardness distribution curve; Among them, the tool grinding tool detection data includes wear value and wear morphology picture; Among them, the fatigue performance test data include the amplitude, frequency, temperature, stress, time, and fracture pictures of vibration fatigue, the amplitude, frequency, temperature, stress, time, and fracture pictures of micro-motion fatigue, and the amplitude, frequency, temperature, stress, time, and fracture pictures of thermal fatigue.

4. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: The cutting force model is obtained by model training based on a first training sample, wherein the first training sample includes a first input sample and a first output sample, wherein the first input sample is the material properties, specimen size, machining tool parameters and machining process parameters of the specimen in the cutting and grinding basic database, and the first output sample is the cutting force exerted on the specimen during the test in the cutting and grinding basic database.

5. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: The temperature field model is obtained by model training based on the second training sample, the second training sample includes a second input sample and a second output sample, the second input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the second output sample is the temperature of the specimen in the cutting and grinding basic database during the test.

6. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: The surface roughness prediction model is obtained by model training based on the third training sample, and the third training sample includes a third input sample and a third output sample. The third input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the third output sample is the surface roughness of the specimen after the test in the cutting and grinding basic database.

7. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: The residual stress prediction model is obtained by model training based on the fourth training sample, and the fourth training sample includes a fourth input sample and a fourth output sample. The fourth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fourth output sample is the residual stress of the surface or surface layer of the specimen after the test in the cutting and grinding basic database.

8. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: The microhardness prediction model is obtained by model training based on the fifth training sample, and the fifth training sample includes a fifth input sample and a fourth output sample. The fifth input sample is the material properties, specimen size, processing tool parameters and processing process parameters of the specimen in the cutting and grinding basic database, and the fifth output sample is the microhardness of the specimen surface after the test in the cutting and grinding basic database.

9. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: In the case where the indicator to be predicted for the parameter to be predicted after format conversion is cutting force, the target model is a cutting force model, and the prediction result is the cutting force to which the predicted test piece is subjected during the actual machining process; In the case where the indicator to be predicted for the parameter to be predicted after format conversion is temperature, the target model is a temperature field model, and the prediction result is the temperature of the piece to be predicted during the actual processing; In the case where the indicator to be predicted for the parameter to be predicted after format conversion is surface roughness, the target model is a surface roughness prediction model, and the prediction result is the surface roughness of the workpiece to be predicted after actual processing; In the case where the indicator to be predicted for the parameter to be predicted after format conversion is residual stress, the target model is a residual stress prediction model, and the prediction result is the residual stress of the surface or surface layer of the to-be-predicted piece after actual processing; When the indicator to be predicted for the parameter to be predicted after format conversion is microhardness, the target model is a microhardness prediction model, and the prediction result is the microhardness of the surface to be tested of the actual processed piece to be tested.

10. The method for building and using a basic database for cutting and grinding of typical aero-engine materials according to claim 1, characterized in that: Also includes: The cutting and grinding basic database is updated according to the prediction results, and then based on the updated cutting and grinding basic database, the cutting force model, temperature field model, surface roughness prediction model, residual stress prediction model and microhardness prediction model are updated.

Images