Method for constructing and using typical characteristic machining database of aero-engine

Abstract

The invention provides an aero-engine typical feature machining database construction and use method, and relates to the technical field of aero-engine manufacturing, and the method specifically comprises the steps: dividing typical features of aero-engine family parts, carrying out the parametric modeling of the typical features, inputting equipment, tool and clamp information, and carrying out the machining of the typical features; optimized parameters are provided for programming software through physical simulation to generate an optimized numerical control program, typical features are processed, processing results are detected, and detection data are provided for an artificial neural network training model based on big data to obtain process information of the typical features; then the typical feature process information is automatically combined to generate process information of the part, after a database is built, a three-dimensional model with information such as materials and sizes is input, training measurement indexes of quality, efficiency or cost are determined, the database automatically recognizes typical features of the three-dimensional model, the sorted typical feature process information is searched from the database, and the process information of the part is obtained. Or part process information obtained after typical feature process information is combined.

Description

Technical Field

[0001] The present invention relates to the technical field of aero-engine manufacturing, and in particular to a method for constructing and using a typical feature machining database of an aero-engine. Background Art

[0002] There are many common or similar typical features in the parts of the aircraft engine family. The combination of typical feature machining processes can generate the machining process of the parts. At present, there is no database for reference of the machining process of these features. On the one hand, the existing massive process parameters, tools, programming strategies and test results and other basic process data are not utilized. On the other hand, the process routes, equipment, tools, process parameters, tools, programming strategies, etc. in the existing process design are determined by personal experience, lacking data support and guidance and optimization of physical simulation. In addition, discrete knowledge such as expert experience and past machining quality problems cannot be passed on and guide the process design and processing of typical features and parts without omissions, resulting in the inability to automatically generate process information with high quality and efficiency. At the same time, the quality of part machining is unstable, and there is a lot of room for improvement in efficiency and cost. Summary of the invention

[0003] In view of the current situation that there is no database for reference in the existing typical characteristics of aircraft engines, resulting in the fact that a large amount of data is not used, and the process design relies on personal experience, expert experience and other knowledge and cannot fully guide the process design, and finally causes the problems of parts processing quality, efficiency and cost to be improved. The present invention provides a method for constructing and using a typical characteristics of aircraft engines machining database;

[0004] A method for constructing and using a typical feature machining database of an aircraft engine comprises the following steps:

[0005] Step 1: Classify the typical characteristics of aircraft engine family parts;

[0006] The typical features include blade body profile, blade root, edge plate, tenon, flow channel, comb tooth, disk center hole, transition fillet, reinforcement rib, thin-walled ring, boss, groove, hole, mounting edge, web;

[0007] Step 2: Collect processing data, inspection data and knowledge data of typical features;

[0008] The processing data includes part information, cutting parameters, and other processes;

[0009] The part information includes processing part features, processing part diameter, family part type, part material brand, heat treatment status, material hardness, process category, processing part description, shape features, programming features, processing equipment model, tool brand, tool bar brand, cooling method, and whether it has been optimized; the cutting parameters include: cutting speed, feed rate, back cutting, side cutting, spindle speed, feed speed, feed depth, and retract feed speed; the other processes include: whether chip removal is required, one-time feed depth, material removal amount per operation cycle, and cumulative operation cycle;

[0010] The test data include: flank wear, test image number, roughness, test image number, machining force, spindle power, vibration, machining temperature, micromorphology, and residual stress;

[0011] The knowledge data includes: process plan, process route, processing method, process equipment, expert experience, and quality problem description;

[0012] Step 3: Conduct experimental research on typical characteristics and generate experimental data, test data and knowledge data of typical characteristics;

[0013] The experimental study specifically includes: parametric modeling of typical features, inputting selected equipment, tool and fixture information, physically simulating typical features, providing optimized parameters to programming software according to simulation results, and finally processing typical features, and testing processing results to obtain test data;

[0014] The parametric modeling is a secondary development of UG software, which uses dimensional constraints, geometric constraints, topological constraints, service stress and performance knowledge constraints to construct a three-dimensional model.

[0015] Furthermore, the selected equipment, tool and fixture information comes from an equipment information library, a tool information library and a fixture information library.

[0016] Furthermore, physical simulation of typical features is to model the process system, input machining parameters and tool parameters, and realize process parameter setting and contour error compensation through mechanical, thermal, deformation and wear simulation and artificial intelligence technology;

[0017] The test data includes part information, cutting parameters, other processes, part information, and cutting parameters;

[0018] Step 4: Provide the existing data collected in step 2 and the test data generated in step 3 to the artificial neural network training model and genetic algorithm based on big data, train the model with quality, efficiency or cost as the training measurement index, and build a typical feature machining database of aircraft engines based on the trained model, so as to obtain the process information with the best training measurement index;

[0019] The training measurement indicator may be a single training measurement indicator of quality, efficiency or cost, or a comprehensive training measurement indicator with a priority set after combining quality, efficiency and cost;

[0020] After the database is built, the 3D model and training metrics are input, and then the typical features of the 3D model are identified, and the sorted typical feature process information or the part process information after the typical feature process information is combined is found from the database;

[0021] Typical feature process information includes process route, matching equipment, tools, procedures, parameters and knowledge data;

[0022] Step 5: Guide on-site part machining by obtaining typical feature process information and part process information.

[0023] The beneficial effects of adopting the above technical solution are:

[0024] The present invention provides a method for constructing and using a typical feature machining database of an aircraft engine. The basic database of typical feature machining processes of an aircraft engine has the functions of storage, query and recommendation of process information based on big data. After the database is built, only a three-dimensional model and measurement indicators need to be input to automatically output the process information of typical features with high quality and efficiency, or the process information of parts. These process information are process files that can directly guide on-site processing or be called by existing process files. The database can optimize the machining process of existing parts, and can also guide and recommend machining processes for new parts. The use of this database can effectively improve the machining quality and quality stability of parts, and the efficiency and cost are also significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the overall structure of the typical characteristics machine-added database of aircraft engines of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] A method for constructing and using a typical feature machining database of an aircraft engine comprises the following steps:

[0028] Step 1: Classify the typical characteristics of aircraft engine family parts;

[0029] The typical features include blade body profile, blade root, edge plate, tenon, flow channel, comb tooth, disk center hole, transition fillet, reinforcement rib, thin-walled ring, boss, groove, hole, mounting edge, web;

[0030] The user can classify typical features by himself according to the same and similar structures of family parts; in this embodiment, the typical features are classified by taking turbine blades and turbine disks as examples. The typical features of turbine blades include blade body profile, blade root, edge plate, tenon, flow channel, comb teeth, etc. The typical features of turbine disks include tenon, protrusion, web, mounting hole, disk center hole, transition fillet, and lace;

[0031] Step 2: Collect existing and continuously generated processing data, inspection data and knowledge data of typical characteristics;

[0032] The processing data includes part information, cutting parameters, and other processes; the detailed information of the specific processing data form in this embodiment is shown in Table 1.

[0033] Table 1: Collection of existing and continuously generated typical features of massive processing data, detection data and knowledge data

[0034]

[0035]

[0036] The part information includes processing part features, processing part diameter, family component type, part material brand, heat treatment status, material hardness, process category, processing part description, shape features, programming features, processing equipment model, tool brand, tool bar brand, cooling method, and whether it has been optimized; the cutting parameters include: cutting speed, feed rate, back cutting, side cutting, spindle speed, feed speed, feed depth, and retract feed speed; the other processes include: whether chip removal is required, feed depth per time, material removal amount per operation cycle, and cumulative operation cycles; users can delete them according to their needs.

[0037] The test data include: flank wear, test image number, roughness, test image number, machining force, spindle power, vibration, machining temperature, micromorphology, and residual stress;

[0038] The knowledge data include: process plan, process route, processing method, process equipment, expert experience, quality problem description; users can delete it as needed.

[0039] Step 3: Conduct experimental research on typical characteristics and generate experimental data, test data and knowledge data of typical characteristics; the detailed information of the form in this embodiment is shown in Table 2.

[0040] Table 2: Table of typical characteristic test data, detection data and knowledge data

[0041]

[0042]

[0043] The experimental study specifically includes: parametric modeling of typical features, inputting selected equipment, tool and fixture information, physically simulating typical features, providing optimized parameters to programming software according to simulation results, realizing rapid programming of typical features, and finally processing typical features, and detecting processing results to obtain detection data;

[0044] The parametric modeling is a secondary development of UG software, which uses dimensional constraints, geometric constraints, topological constraints, service stress and performance knowledge constraints to construct a three-dimensional model.

[0045] Furthermore, the selected equipment, tool and fixture information comes from an equipment information library, a tool information library and a fixture information library.

[0046] Furthermore, physical simulation of typical features is to model the process system, input machining parameters and tool parameters, and realize process parameter setting and contour error compensation through mechanical, thermal, deformation and wear simulation and artificial intelligence technology;

[0047] The test data includes part information, cutting parameters, other processes, part information, cutting parameters; the user can delete them as needed. In this embodiment, the form style of the equipment information library is detailed in Table 3, the form style of the tool information library is detailed in Table 4, and the form style of the fixture information library is detailed in Table 5.

[0048] Table 3 Equipment information database form

[0049]

[0050]

[0051] Table 4 Tool information library form

[0052] Tool ID Tool name Tool Type Tool material Tool bar material Tool rake angle Tool back angle Tool corner radius Tool length ……

[0053] Table 5 Fixture Information Library Form

[0054] Fixture ID Fixture No. Fixture Type Fixture size ……

[0055] Step 4: Provide the existing data collected in step 2 and the test data generated in step 3 to the artificial neural network training model and genetic algorithm based on big data, train the model with quality, efficiency or cost as the training measurement index, and build a typical feature machining database of aircraft engines based on the trained model, such as Figure 1 As shown, the process information with the best training measurement index is obtained; in this embodiment, the training measurement index is set with the priority of quality first, efficiency second or cost third.

[0056] The training measurement indicator may be a single training measurement indicator of quality, efficiency or cost, or a comprehensive training measurement indicator with a priority set after combining quality, efficiency and cost;

[0057] After the database is built, the 3D model with information such as materials and dimensions and training metrics are input, including a single metric of efficiency or cost or a comprehensive metric with efficiency and cost prioritized. Then, the typical features of the 3D model are identified, and the sorted typical feature process information or the part process information after the typical feature process information is combined is found from the database.

[0058] Typical feature process information includes process route, matching equipment, tools, programs, parameters and knowledge data; part process information is composed of typical feature processes, mainly including the part's process route, matching equipment, tools, programs, parameters and related knowledge data.

[0059] Step 5: Guide on-site part machining by obtaining typical feature process information and part process information.

[0060] 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 constructing and using a typical feature machining database of an aircraft engine, characterized in that: The following steps are involved: Step 1: Classify the typical characteristics of aircraft engine family parts; Step 2: Collect processing data, inspection data and knowledge data of typical features; Step 3: Conduct experimental research on typical characteristics and generate experimental data, test data and knowledge data of typical characteristics; Step 4: Provide the existing data collected in step 2 and the test data generated in step 3 to the artificial neural network training model and genetic algorithm based on big data, train the model with quality, efficiency or cost as the training measurement index, and build a typical feature machining database of aircraft engines based on the trained model, so as to obtain the process information with the best training measurement index; Step 5: Guide on-site part machining by obtaining typical feature process information and part process information.

2. The method for constructing and using a typical feature machining database of an aircraft engine according to claim 1, characterized in that: The typical features described in step 1 include blade body profile, blade root, edge plate, tenon, flow channel, comb teeth, disk center hole, transition fillet, reinforcement rib, thin-walled ring, boss, groove, hole, mounting edge, and web.

3. The method for constructing and using a typical feature machining database of an aircraft engine according to claim 1, characterized in that: The processing data in step 2 includes part information, cutting parameters, and other processes; The part information includes processing part features, processing part diameter, family part type, part material brand, heat treatment status, material hardness, process category, processing part description, shape features, programming features, processing equipment model, tool brand, tool bar brand, cooling method, and whether it has been optimized; the cutting parameters include: cutting speed, feed rate, back cutting, side cutting, spindle speed, feed speed, feed depth, and retract feed speed; the other processes include: whether chip removal is required, one-time feed depth, material removal amount per operation cycle, and cumulative operation cycle; The test data include: flank wear, test image number, roughness, test image number, machining force, spindle power, vibration, machining temperature, micromorphology, and residual stress; The knowledge data includes: process plan, process route, processing method, process equipment, expert experience, and quality problem description.

4. The method for constructing and using a typical feature machining database of an aircraft engine according to claim 1, characterized in that: The experimental study described in step 3 specifically includes: parametric modeling of typical features, input of selected equipment, tool and fixture information, physical simulation of typical features, providing optimized parameters to programming software according to simulation results, and finally processing the typical features, and testing the processing results to obtain test data; The parametric modeling is a secondary development of UG software, which uses size constraints, geometric constraints, topological constraints, service stress and performance knowledge constraints to build a three-dimensional model; The test data includes part information, cutting parameters, other processes, part information, and cutting parameters.

5. The method for constructing and using a typical feature machining database of an aircraft engine according to claim 4, characterized in that: The selected equipment, tool and fixture information comes from the equipment information library, tool information library and fixture information library; Furthermore, physical simulation of typical features is to model the process system, input processing parameters and tool parameters, and realize process parameter setting and contour error compensation through mechanical, thermal, deformation and wear simulation and artificial intelligence technology.

6. The method for constructing and using a typical feature machining database of an aircraft engine according to claim 1, characterized in that: The training measurement indicator in step 4 may be a single training measurement indicator based on quality, efficiency or cost, or a comprehensive training measurement indicator with a priority set after combining quality, efficiency and cost; After the database is built, the 3D model and training metrics are input, and then the typical features of the 3D model are identified, and the sorted typical feature process information or the part process information after the typical feature process information is combined is found from the database; Typical feature process information includes process routes, matching equipment, tools, programs, parameters and knowledge data.

Images