A selective laser melting intelligent process design and simulation optimization method

Abstract

The application relates to a laser selective melting intelligent process design and simulation optimization method, and belongs to the technical field of laser selective melting processing, and solves the problem that the prior art cannot meet the requirements of a new generation of laser selective melting process and rapid response, high efficiency and high quality manufacturing. The method comprises the following steps: constructing a three-dimensional model of an obtained target part and a support structure; obtaining a to-be-processed surface feature of the target part; searching for laser selective melting initial recommended process parameters of the target part; performing finite element analysis on the constructed three-dimensional model and the laser selective melting initial recommended process parameters of the target part; comparing and analyzing the finite element analysis result with technical requirements in a process database; and optimizing laser selective melting process parameter data that does not meet the requirements by using a simulated annealing algorithm. The method can quickly obtain laser selective melting process parameters without relying on manual experience trial and error and manual simulation analysis, and improves the digitalization and intelligent level of process design.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of laser selective melting, and particularly to a laser selective melting intelligent process design and simulation optimization method. BACKGROUND

[0002] At present, the manufacturing process informationization and intelligentization capability of laser selective melting production process is seriously insufficient, and the process design still relies on manual experience trial and error and manual setting simulation analysis process. In order to meet the design index requirements, trial and error iteration needs to be repeatedly performed, resulting in problems such as high cost, long cycle and low quality reliability in product development, which is difficult to meet the needs of rapid response, high efficiency and high quality of new generation laser selective melting process and manufacturing, and the digitalization and intelligentization level of process design needs to be improved. SUMMARY

[0003] In view of the above analysis, the embodiments of the present application aim to provide a laser selective melting intelligent process design and simulation optimization method to solve the problem that the existing process cannot meet the needs of rapid response, high efficiency and high quality of new generation laser selective melting process and manufacturing.

[0004] In one aspect, the embodiments of the present application provide a laser selective melting intelligent process design and simulation optimization method, comprising:

[0005] Step 1: Simplify the forming target part and support structure in the three-dimensional model software, and save it as XT format to build a three-dimensional model of the target part and the support structure;

[0006] Step 2: Identify the straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and other entities and feature relationships in the three-dimensional model to obtain the surface features to be processed of the target part;

[0007] Step 3: Based on the surface features to be processed of the target part, obtain the initial recommended process parameters of laser selective melting of the target part;

[0008] Step 4: Perform finite element analysis on the built three-dimensional model and the initial recommended process parameters of laser selective melting of the target part to obtain the target part forming surface and stress-strain distribution-time data;

[0009] Step 5: Compare and analyze the target part forming surface and stress-strain distribution-time data with the technical requirements in the process database;

[0010] Step 6: Optimize the laser selective melting process parameter data that does not meet the requirements by using simulated annealing algorithm, and return to step 4 until the process parameters that meet the requirements are obtained;

[0011] The optimized modified process parameters include: support structure position and size, cladding path, initial starting point, ambient temperature, laser power, welding gun diameter, and cladding speed.

[0012] Further, the step 3 comprises:

[0013] S31: constructing a process database to store laser selective melting process basic information;

[0014] S32: obtaining the laser selective melting process of the target part based on the laser selective melting process characteristics of the target part;

[0015] S33: obtaining the technical requirements of the target part's surface to be processed accuracy and forming quality based on the laser selective melting process of the target part and the surface to be processed characteristics of the target part;

[0016] S34: based on the surface to be processed characteristics of the target part and the technical requirements of the surface to be processed accuracy and forming quality of the target part, searching for similar laser selective melting process parameters of the target part in the process database to obtain the initial recommended process parameters of the laser selective melting of the target part.

[0017] Further, in the step S31, the laser selective melting process basic information includes: the laser selective melting process based on the laser selective melting process characteristics of the target part, the laser selective melting process parameters based on the technical requirements of the surface to be processed accuracy and forming quality of the target part, and the technical requirements of the surface to be processed accuracy and forming quality based on the surface to be processed characteristics of the target part.

[0018] Further, in the step S32, the laser selective melting process of the target part includes specifying the target part and the support structure, selecting the cladding path and the starting position, and selecting the target part material, including titanium alloy and aluminum alloy.

[0019] Further, the step S34 comprises:

[0020] S341: setting a 3-layer neural network, including an input layer, a hidden layer, and an output layer;

[0021] S342: determining the boundary conditions of the process to construct the process value range of the laser selective melting, the initial input quality requirements, and the material fracture strain value;

[0022] S343: obtaining the initial recommended process parameters of the laser selective melting of the target part based on steps S341 and S342.

[0023] Further, in the step S341, the input layer satisfies:

[0024]

[0025] The hidden layer satisfies:

[0026]

[0027] The output layer satisfies:

[0028]

[0029] Among them, Y (0) Represents the input layer process parameter condition matrix;

[0030] Y (1) represents the output vector of the hidden layer;

[0031] Y (2) A mathematical relationship between model quality and workmanship;

[0032] Among them, the number of nodes in the input layer, hidden layer and output layer are m0, m1 and m2 respectively.

[0033] Furthermore, the hidden layer satisfies:

[0034]

[0035] Among them, f (1) is the activation function. At this time, for the laser selective melting process, we have:

[0036] f(x)=max(xα,x)

[0037] Among them, α is a hyperparameter obtained by data training, net (1) is the weighted amount.

[0038] Furthermore, in S343, the characteristics of the target part's surface to be processed and the technical requirements of the target part's surface to be processed accuracy and forming quality are used as input parameters, and the laser selective melting process parameters of the target part are used as output parameters. After determining the model characteristics and quality requirements, the knowledge base queries the saved model-process-quality relationship to see if it matches the known facts; if it matches, the laser selective melting process parameters of the target part are obtained.

[0039] Furthermore, in step 6, the probability p of the process parameter being accepted when changing from x1 to x2 satisfies:

[0040]

[0041] Where △f=f1-f2, is the difference between the values ​​of the objective functions f(x1) and f(x2);

[0042] f(x) is the mass function, which represents the maximum strain.

[0043] T is a temperature constant.

[0044] Further, in the step 6, the relationship between the iteration number n and the temperature constant T in the optimization process satisfies:

[0045] T(n+1)=K*T(n)

[0046] Wherein, K is a constant less than 1.

[0047] Compared with the prior art, the present application can achieve at least the following beneficial effects:

[0048] The model feature recognition module of the present application automatically acquires the surface feature to be processed of the three-dimensional model of the target part and the support structure, based on the surface feature to be processed and the technical requirements, the initial recommended process parameters of laser selective melting are acquired by searching in the process database through the knowledge base, and the initial process parameters of laser selective melting are analyzed by finite element analysis, so as to realize the optimization of the process parameters of laser selective melting, and the process parameters of laser selective melting meeting the requirements are obtained, thereby, under the condition of ensuring the quality of process design, the efficiency of acquiring the process parameters of laser selective melting is improved, the problem that the process design is too dependent on manual experience and trial and error and manual simulation analysis is overcome, and the efficiency of simulation iteration is improved.

[0049] The above technical solutions can be combined with each other in the present application to realize more preferred combination solutions. Other features and advantages of the present application will be described in the subsequent specification, and some advantages will become apparent from the specification, or will be understood by implementing the present application. The purposes and other advantages of the present application can be realized and obtained from the contents specifically pointed out in the specification and the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0050] The accompanying drawings are included to provide a further understanding of the present application, and are incorporated herein and constitute a part of the detailed description. The drawings illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings:

[0051] Figure 1 The flow chart of the intelligent process design and simulation optimization method of laser selective melting in the present application;

[0052] Figure 2 The structure block diagram of the intelligent process design and simulation optimization platform of laser selective melting in the present application;

[0053] Figure 3 The search and calculation method logic diagram of the knowledge base in the present application. DETAILED DESCRIPTION

[0054] The preferred embodiments of the present application are described below in detail with reference to the accompanying drawings, which form a part of this application, and are used to illustrate the principles of the application, and are not intended to limit the scope of the application.

[0055] The additive structure parts of aerospace and automobile manufacturing industry have the characteristics of complex shape, high precision, and structure and function integration. With the increasing requirements of laser selective melting manufacturing process technology, the laser selective melting target part manufacturing process presents the characteristics of high dispersion, multi-variety, small batch, and short development cycle. The control requirements for the size precision of the component are more and more strict, and the quality and efficiency of the process design directly affect the overall machining quality. Therefore, the high-quality and high-efficiency design of the machining process is extremely critical. However, the informatization and intelligentization ability of the laser selective melting production process is seriously insufficient at present, and the process design still depends on manual experience trial and error and manual setting simulation analysis process. In order to meet the design index requirements, trial and error iteration needs to be repeatedly performed, which leads to the problems of high cost, long cycle and low quality reliability in product development, and it is difficult to meet the requirements of rapid response, high efficiency and high quality of the new generation of laser selective melting process and manufacturing. The digitalization and intelligentization level of process design needs to be improved.

[0056] To solve the above problems, the present application provides a laser selective melting intelligent process design and simulation optimization method, comprising:

[0057] Step 1: Simplify the forming target part and support structure in the three-dimensional model software, and save it as XT format to build a three-dimensional model of the target part and the support structure;

[0058] Step 2: Identify the straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and other entities and feature relationships in the three-dimensional model to obtain the surface features to be machined of the target part;

[0059] Step 3: Based on the surface features to be machined of the target part, obtain the initial recommended process parameters of laser selective melting of the target part;

[0060] Step 4: Perform finite element analysis on the built three-dimensional model and the initial recommended process parameters of laser selective melting of the target part to obtain the target part forming surface and stress-strain distribution-time data;

[0061] Step 5: Compare and analyze the target part forming surface and stress-strain distribution-time data with the technical requirements in the process database;

[0062] Step 6: Optimize the laser selective melting process parameter data that does not meet the requirements by using simulated annealing algorithm, and return to step 4 until the process parameters that meet the requirements are obtained.

[0063] Step 3 comprises:

[0064] S31: Constructing a process database to store laser selective melting process basic information;

[0065] S32: Based on the laser selective melting process characteristics of the target part, the laser selective melting process of the target part is obtained;

[0066] S33: Based on the laser selective melting process of the target part and the surface feature to be processed of the target part, the technical requirements of the surface precision and forming quality of the target part to be processed are obtained;

[0067] S34: Based on the surface feature to be processed of the target part and the technical requirements of the surface precision and forming quality of the target part to be processed, in the process database, the similar laser selective melting process parameters of the target part are searched and obtained to obtain the initial recommended process parameters of the laser selective melting of the target part.

[0068] Among them, the laser selective melting process basic information includes: the laser selective melting process based on the laser selective melting process characteristics of the target part, the laser selective melting process parameters based on the technical requirements of the surface precision and forming quality of the target part to be processed, and the technical requirements of the surface precision and forming quality of the target part to be processed.

[0069] Compared with the prior art, the model feature recognition module is used to automatically obtain the surface feature to be processed of the three-dimensional model of the target part and the support structure, based on the surface feature to be processed and the technical requirements, the initial recommended process parameters of the laser selective melting are obtained by searching in the process database through the knowledge base, and the finite element analysis is carried out on the initial process parameters of the laser selective melting, so as to realize the optimization of the laser selective melting process parameters, and the laser selective melting process parameters meeting the requirements are obtained, so as to ensure the quality of process design, improve the efficiency of obtaining the laser selective melting process parameters, and overcome the problem that the process design is too dependent on manual experience and manual simulation analysis.

[0070] Specifically, in step 2, it includes:

[0071] S21: Constructing a feature library;

[0072] Among them, the feature library parameters include: straight line, round angle, arc surface, hole, plane, stretching and rotation and other entity and feature relationship data.

[0073] S22: Comparing the surface feature to be processed of the identified three-dimensional model with the parameters in the feature library to determine the surface feature to be processed of the target part.

[0074] Among them, the surface feature to be processed is the collinear decision of the coplanar determined by the model feature recognition.

[0075] Specifically, in step 3, comprising:

[0076] S31: constructing a process database to store laser selective melting process basic information;

[0077] Wherein, the process database includes laser selective melting process basic information input by business terminal automatic iteration and process personnel.

[0078] The laser selective melting process basic information includes: laser selective melting process based on the characteristics of the laser selective melting process of the target part, laser selective melting process parameters based on the technical requirements of the precision and forming quality of the surface to be processed of the target part based on the characteristics of the surface to be processed of the target part, and the technical requirements of the precision and forming quality of the surface to be processed of the target part.

[0079] Exemplarily, including ambient temperature, laser power, welding gun diameter and cladding speed.

[0080] S32: based on the characteristics of the laser selective melting process of the target part, obtaining the laser selective melting process of the target part;

[0081] Specifically, the target part and the support structure are specified, the cladding path and the starting position are selected, the target part material is selected, including titanium alloy and aluminum alloy;

[0082] Wherein, the path and the starting position are determined by the collinearity on the coplanar identified by the model characteristics, and the starting and ending points of each path are determined by the shortest path, and the starting and ending points of a single path have no effect.

[0083] Wherein, the material of the target part is selected according to the actual processing part material type.

[0084] S33: based on the laser selective melting process of the target part and the characteristics of the surface to be processed of the target part, obtaining the technical requirements of the precision and forming quality of the surface to be processed of the target part;

[0085] Wherein, the technical requirements of the precision and forming quality of the surface to be processed of the target part are standard parameters stored in the process database.

[0086] S34: based on the characteristics of the surface to be processed of the target part and the technical requirements of the precision and forming quality of the surface to be processed of the target part, searching for similar laser selective melting process parameters of the target part in the process database to obtain the initial recommended process parameters of the laser selective melting of the target part.

[0087] Specifically, according to the model-process-quality relationship prediction model and the related rule base in the knowledge base, search and calculate the initial recommended process parameters;

[0088] The 3-layer neural network is set, including an input layer, a hidden layer and an output layer.

[0089] The number of nodes of the input layer, the hidden layer and the output layer is m0, m1 and m2 respectively.

[0090] The input layer satisfies:

[0091]

[0092] The hidden layer satisfies:

[0093]

[0094] The output layer satisfies:

[0095]

[0096] Y (0) represents an input layer process parameter condition matrix.

[0097] Y (1) represents an output vector of the hidden layer.

[0098] Y (2) represents a mathematical relationship between the model quality and the process.

[0099] For the hidden layer:

[0100]

[0101] wherein f (1) is an activation function, and for the laser selective melting process, f(x) = max(xa, x), wherein a is a hyperparameter obtained by data training, and net (1) is a weighted quantity.

[0102] f(x) = max(xa, x), wherein a is a hyperparameter obtained by data training, and net (1) is a weighted quantity.

[0103] The rule base is a boundary condition of the process, and is used to construct a process value range of the laser selective melting, an initial input quality requirement and a material fracture strain value.

[0104] Specifically, the searching and calculating method is as follows: after the model characteristics and the quality requirement are determined, the knowledge base queries the saved model-process-quality relationship to see whether it matches the known facts.

[0105] After all IF clauses (relationships, i.e. the hidden layer) in the rule are matched, the THEN clause is traced back to enable the rule, and new facts generated by the rule are added to the database, at this time, all facts in the database are the reasoning result, and the reasoning is ended.

[0106] The initial recommended process parameters of the laser selective melting include an ambient temperature, a laser power, a welding gun diameter and a cladding speed.

[0107] Specifically, in step 5, the target part shaped surface and stress-strain distribution-time data are compared and analyzed with the technical requirements in the process database; if the quality technical requirements are met, the comparison is successful, and the final process parameters are obtained; if the quality technical requirements are not met, the comparison is unsuccessful.

[0108] Specifically, in step 6, the laser selective melting process parameter data that do not meet the requirements are optimized by using the simulated annealing algorithm, and the process returns to step 4 until the process parameters that meet the requirements are obtained.

[0109] Specifically, the probability p that the process parameter is accepted from x1 to x2 satisfies:

[0110]

[0111] Wherein, △f = f1-f2, is the difference between the values of the objective functions f(x1), f(x2);

[0112] f(x) is a quality function, representing the maximum strain.

[0113] T is a temperature constant;

[0114] As time decreases, when the temperature is very high, the second probability is high, and as the temperature decreases, the second case is slowly reduced until almost no second case is selected.

[0115] Wherein, the relationship between the iteration number n and the temperature constant T satisfies:

[0116] T(n+1) = K*T(n)

[0117] Wherein, K is a constant less than 1.

[0118] Wherein, the process parameters are laser power, scanning speed, scanning spacing, powder thickness.

[0119] Wherein, the support structure position and size, cladding path, initial starting point, ambient temperature, laser power, welding gun diameter and cladding speed are optimized and modified, and the simulation software is driven for analysis again until the required result is obtained.

[0120] Further, it further includes step 7: saving the process of obtaining the final result and the final result to the process database, and optimizing the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base and the simulated annealing algorithm based on the updated process database.

[0121] In order to realize the laser selective melting process parameters of the target part obtained by the intelligent process design and simulation optimization method of the above laser selective melting, the application further provides a laser selective melting intelligent process design and simulation optimization platform, comprising:

[0122] A three-dimensional model construction module is used for constructing three-dimensional models of the shaped target part and the support structure.

[0123] A model feature recognition module is used for comparing the identified straight lines, round corners, curved surfaces, holes, planes, stretches and rotations and the like entities and feature relationships in the three-dimensional model with the feature parameters in the process database, so as to determine the to-be-processed features of the target part.

[0124] A process database is used for storing laser selective melting process basic information.

[0125] A knowledge base is used for obtaining the laser selective melting process of the target part based on the laser selective melting process characteristics of the target part, obtaining the technical requirements of the to-be-processed surface accuracy and forming quality of the target part based on the laser selective melting process of the target part and the to-be-processed surface features of the target part, and searching for the similar laser selective melting process parameters of the target part in the process database based on the to-be-processed surface features of the target part and the technical requirements of the to-be-processed surface accuracy and forming quality of the target part, so as to obtain the initial recommended laser selective melting process parameters of the target part.

[0126] A simulation interaction module is used for importing the constructed three-dimensional model into a finite element analysis software, driving the finite element analysis software to perform calculation and analysis under different parameter iterations, and extracting the calculation results and transmitting them to the knowledge base for quality result data analysis.

[0127] In the process database, the laser selective melting process based on the laser selective melting process characteristics of the target part, the laser selective melting process parameters based on the technical requirements of the to-be-processed surface accuracy and forming quality of the target part based on the to-be-processed surface features of the target part, and the technical requirements of the to-be-processed surface accuracy and forming quality of the target part based on the to-be-processed surface features of the target part further include the feature parameter data of straight lines, round corners, curved surfaces, holes, planes, stretches and rotations and the like entities and feature relationships.

[0128] That is, by recognizing the constructed three-dimensional model, the straight lines, round corners, curved surfaces, holes, planes, stretches and rotations and the like entities and feature relationships of the target part are obtained, the similar laser selective melting process parameters of the target part are searched in the process data by combining the technical requirements of the to-be-processed surface accuracy and forming quality, and the similar laser selective melting process parameters of the target part are used as the initial recommended laser selective melting process parameters of the target part.

[0129] Wherein, the finite element analysis is carried out on the constructed three-dimensional model and the initial recommended process parameters of laser selective melting to obtain the target part forming surface and stress-strain distribution-time data, and the forming surface and stress-strain distribution-time data are compared with the technical requirements in the process library, if qualified, the final result is output, if not qualified, the laser selective melting process is optimized by using the knowledge base until the process parameters meeting the requirements are obtained.

[0130] Specifically, the three-dimensional model construction module is used to simplify the forming target part and the support structure in the three-dimensional model software, and save it in XT format to construct the three-dimensional model of the target part and the tooling.

[0131] The model feature recognition module is used to compare the identified straight lines, fillets, curved surfaces, holes, planes, stretching and rotation entities and their feature relationships in the three-dimensional model with the feature parameters in the process database to determine the to-be-processed features of the target part.

[0132] The process database is used to store the laser selective melting process basic information input by the business terminal automatic iteration and the process personnel.

[0133] Exemplarily, the laser selective melting process basic information includes: ambient temperature, laser power, welding gun diameter and cladding speed.

[0134] The knowledge base obtains the laser selective melting process of the target part based on the characteristics of the laser selective melting process of the target part, obtains the technical requirements of the to-be-processed surface precision and forming quality of the target part based on the laser selective melting process of the target part and the to-be-processed surface features of the target part, and searches for the similar laser selective melting process parameters of the target part in the process database based on the to-be-processed surface features of the target part and the technical requirements of the to-be-processed surface precision and forming quality of the target part to obtain the initial recommended process parameters of the laser selective melting of the target part.

[0135] Wherein, the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base are set in the knowledge base to search and calculate the initial recommended process parameters of the laser selective melting.

[0136] Specifically, the model-process-quality relationship prediction model sets a 3-layer neural network, including an input layer, a hidden layer and an output layer.

[0137] Wherein, the number of nodes of the input layer, the hidden layer and the output layer is m0, m1 and m2 respectively,

[0138] Wherein, the input layer satisfies:

[0139]

[0140] The hidden layer satisfies:

[0141]

[0142] The output layer satisfies:

[0143]

[0144] where Y (0) represents an input layer process parameter condition matrix;

[0145] Y (1) represents an output vector of the hidden layer;

[0146] Y (2) represents a mathematical relationship between the model quality and the process.

[0147] For the hidden layer:

[0148]

[0149] where f (1) is an activation function, and for the laser selective melting process, f(x) = max(xa, x).

[0150] f(x) = max(xa, x)

[0151] where a is a hyperparameter obtained by data training, and net (1) is a weighted quantity.

[0152] The rule base is a boundary condition of the process, and is used to construct a process value range of the laser selective melting, an initial input quality requirement, and a material fracture strain value.

[0153] Specifically, the searching and calculating method is as follows: after the model characteristics and the quality requirement are determined, the knowledge base queries the saved model-process-quality relationship to see whether it matches the known facts.

[0154] After all IF clauses (relationships, i.e., hidden layers) in the rule match, the THEN clause is traced back to enable the rule, and new facts generated by the rule are added to the database, at which time all the facts in the database are the reasoning results, and the reasoning ends.

[0155] where the initial recommended process parameters of the laser selective melting include: ambient temperature, laser power, welding gun diameter, and cladding speed.

[0156] The simulation interaction module is used to import the constructed three-dimensional model into the finite element analysis software, drive the finite element analysis software to perform calculation and analysis under different parameter iterations, and extract the calculation results for quality result data analysis.

[0157] Specifically, the finite element analysis software is used to perform finite element analysis on the constructed three-dimensional model and the laser selective melting initial recommended process parameters of the target part to obtain the target part forming surface and stress-strain distribution-time data.

[0158] After obtaining the target part forming surface and stress-strain distribution-time data, the obtained data are compared and analyzed with the technical requirements in the process database by using the knowledge base.

[0159] If the comparison meets the requirements, the similar laser selective melting process parameters of the target part are searched and obtained as the final result.

[0160] If the comparison does not meet the requirements, the laser selective melting process is optimized by using the knowledge base until the process parameters meeting the requirements are obtained.

[0161] The simulated annealing optimization model is provided in the knowledge base to optimize the process parameter data that does not meet the requirements until the process parameters meeting the requirements are obtained.

[0162] According to the simulated annealing algorithm, the support structure position and size, the cladding path, the initial starting point, the environmental temperature, the laser power, the welding gun diameter and the cladding speed are optimized and modified, and the simulation software is driven for analysis again until the result meeting the requirements is obtained.

[0163] Specifically, the probability p that the process parameter is accepted from x1 to x2 satisfies:

[0164]

[0165] Wherein, △f = f1-f2, which is the difference between the values of the objective functions f(x1), f(x2);

[0166] f(x) is a quality function, which represents the maximum strain.

[0167] T is a temperature constant.

[0168] As the time decreases, when the temperature is very high, the second probability is high, and as the temperature decreases, the second probability slowly decreases until almost no second probability is selected.

[0169] Wherein, the relationship between the iteration number n and the temperature constant T satisfies:

[0170] T(n+1) = K*T(n)

[0171] Wherein, K is a constant less than 1.

[0172] Therefore, the laser selective melting process parameters are optimized by the simulated annealing optimization model until the laser selective melting process parameters meeting the requirements are obtained, finally, the process of obtaining the final result and the final result are saved to the process database, and the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base and the simulated annealing algorithm are optimized based on the updated process database.

[0173] After the final result is obtained, the process of obtaining the final result and the final result are saved to the process database, and the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base and the simulated annealing algorithm are optimized based on the updated process database.

[0174] Compared with the prior art, the three-dimensional model of the target part and the support structure is automatically obtained by the model feature recognition module, the laser selective melting initial recommended process parameters are obtained by searching in the process database based on the machining surface features and technical requirements, and the laser selective melting initial process parameters are analyzed by the finite element analysis, so that the laser selective melting process parameters are optimized until the laser selective melting process parameters meeting the requirements are obtained, so that the efficiency of obtaining the laser selective melting process parameters is improved under the condition of ensuring the process design quality, the problem that the process design is too dependent on manual experience and manual simulation analysis is overcome, and the efficiency of simulation iteration is improved.

[0175] Embodiment 1

[0176] A laser selective melting intelligent process design and simulation optimization method, comprising:

[0177] Step 1: simplify the forming target part and the support structure in the three-dimensional model software, and save it as XT format to build the three-dimensional model of the target part and the support structure;

[0178] Step 2: identify the straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and other entities and feature relationships in the three-dimensional model to obtain the machining surface features of the target part;

[0179] Specifically, it comprises:

[0180] S21: build a feature library;

[0181] The feature library parameters include: straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and other entities and feature relationship data.

[0182] S22: compare the identified machining surface features of the three-dimensional model with the parameters in the feature library to determine the machining features of the target part.

[0183] Wherein, the to-be-processed surface feature is a collinear decision on a coplanar identified by the model feature.

[0184] Step 3: Based on the to-be-processed surface feature of the target part, obtaining the initial recommended process parameters of the target part for laser selective melting.

[0185] Specifically, it includes:

[0186] S31: Constructing a process database for storing basic information of laser selective melting process;

[0187] Wherein, the process database includes basic information of laser selective melting process automatically iterated by the business terminal and input by the process personnel.

[0188] The basic information of laser selective melting process includes: laser selective melting process based on the characteristics of the laser selective melting process of the target part, laser selective melting process parameters based on the technical requirements of the to-be-processed surface precision and forming quality of the to-be-processed surface feature of the target part, and technical requirements of the to-be-processed surface precision and forming quality of the to-be-processed surface feature of the target part.

[0189] S32: Based on the characteristics of the laser selective melting process of the target part, obtaining the laser selective melting process of the target part;

[0190] Specifically, the target part and the support structure are specified, the cladding path and the starting position are selected, and the target part material is selected, including titanium alloy and aluminum alloy.

[0191] Wherein, the path and the starting position are determined by the collinear decision on the coplanar identified by the model feature, and the starting and ending points of each path are determined by the shortest path, and the starting and ending points have no effect on a single path.

[0192] Wherein, the material of the target part is selected according to the actual processing part material type.

[0193] S33: Based on the laser selective melting process of the target part and the to-be-processed surface feature of the target part, obtaining the technical requirements of the to-be-processed surface precision and forming quality of the target part;

[0194] Wherein, the technical requirements of the to-be-processed surface precision and forming quality of the target part are standard parameters stored in the process database.

[0195] S34: Based on the to-be-processed surface feature of the target part and the technical requirements of the to-be-processed surface precision and forming quality of the target part, searching for similar laser selective melting process parameters of the target part in the process database to obtain the initial recommended process parameters of the target part for laser selective melting.

[0196] Specifically, according to the model-process-quality relationship prediction model and the related rule base in the knowledge base, the initial recommended process parameters are searched and calculated;

[0197] wherein a 3-layer neural network is set, including an input layer, a hidden layer and an output layer;

[0198] wherein the number of nodes of the input layer, the hidden layer and the output layer are m0, m1 and m2 respectively,

[0199] wherein the input layer satisfies:

[0200]

[0201] the hidden layer satisfies:

[0202]

[0203] the output layer satisfies:

[0204]

[0205] wherein Y (0) represents an input layer process parameter condition matrix;

[0206] Y (1) represents an output vector of the hidden layer;

[0207] Y (2) represents a mathematical relationship between the model quality and the process.

[0208] For the hidden layer:

[0209]

[0210] wherein f (1) is an activation function, and for the laser selective melting process, f(x) = max(xa, x).

[0211] f(x) = max(xa, x)

[0212] wherein a is a hyperparameter obtained by data training, and net (1) is a weighted quantity.

[0213] The rule base is a boundary condition of the process, used to construct the process value range of the laser selective melting, the initial input quality requirement and the material fracture strain value.

[0214] Specifically, the searching and calculating method is as follows: after the model characteristics and the quality requirements are determined, the knowledge base queries the saved model-process-quality relationship to see whether it matches the known facts.

[0215] After all IF clauses (relations, i.e., hidden layers) in the rule match, backtracking to the THEN clause enables the rule and adds new facts produced by the rule to the database, and all facts in the database at this time are the inference result, and the inference ends.

[0216] The initial recommended process parameters for laser selective melting include ambient temperature, laser power, welding gun diameter, and cladding speed.

[0217] Step 4: Finite element analysis is performed on the built three-dimensional model and the initial recommended process parameters for laser selective melting of the target part to obtain target part forming profile and stress-strain distribution-time data;

[0218] Step 5: Comparing and analyzing the target part forming profile and stress-strain distribution-time data with the technical requirements in the process database;

[0219] Specifically, if the quality technical requirements are met, the comparison is successful, and the final process parameters are obtained;

[0220] If the quality technical requirements are not met, the comparison is unsuccessful.

[0221] Step 6: Adopting the simulated annealing algorithm to optimize the laser selective melting process parameter data that does not meet the requirements, and returning to step 4 until the process parameters that meet the requirements are obtained.

[0222] Specifically, the probability p that x1 changes to x2 is accepted satisfies:

[0223]

[0224] Where, △f = f1-f2, is the difference between the values of the objective function f(x1), f(x2);

[0225] f(x) is the quality function, representing the maximum strain.

[0226] T is the temperature constant;

[0227] As time slowly decreases, when the temperature is very high, the second probability is high, and as the temperature decreases, the second case slowly decreases until almost no second case is selected.

[0228] Where, the relationship between the number of iterations n and the temperature constant T satisfies:

[0229] T(n+1) = K*T(n)

[0230] Where, K is a constant less than 1.

[0231] Where, the process parameters are laser power, scanning speed, scanning spacing, and powder thickness.

[0232] The support structure position and size, cladding path, initial starting point, ambient temperature, laser power, welding gun diameter and cladding speed are optimized and modified, and the simulation software is driven for analysis again until the required results are obtained.

[0233] Step 7: The process of obtaining the final result and the final result are saved to the process database, and the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base and simulated annealing algorithm are optimized based on the updated process database.

[0234] Embodiment 2

[0235] The laser selective melting intelligent process design and simulation optimization platform comprises:

[0236] A three-dimensional model construction module is configured to construct three-dimensional models of the shaped target part and the support structure.

[0237] The three-dimensional models of the shaped target part and the support structure are simplified in the three-dimensional model software and saved in XT format to construct the three-dimensional models of the target part and the tooling.

[0238] A model feature recognition module is configured to compare the identified straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and the like entities and feature relationships in the three-dimensional model with the feature parameters in the process database to determine the features to be processed of the target part.

[0239] A process database is configured to store the laser selective melting process basic information input by the business terminal automatic iteration and the process personnel.

[0240] The laser selective melting process basic information includes the laser selective melting process based on the laser selective melting process characteristics of the target part, the laser selective melting process parameters based on the technical requirements of the surface precision and forming quality of the features to be processed of the target part, and the feature parameter data of the straight lines, fillets, curved surfaces, holes, planes, stretches and rotations and the like entities and feature relationships.

[0241] For example, the ambient temperature, the laser power, the welding gun diameter and the cladding speed.

[0242] The knowledge base obtains a laser selective melting process of the target part based on characteristics of the laser selective melting process of the target part, obtains technical requirements of a machined surface precision and forming quality of the target part based on the laser selective melting process of the target part and the machined surface characteristics of the target part, searches for similar laser selective melting process parameters of the target part in the process database based on the machined surface characteristics of the target part and the technical requirements of the machined surface precision and forming quality of the target part, and obtains initial recommended laser selective melting process parameters of the target part.

[0243] The model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base are provided in the knowledge base to search and calculate the initial recommended laser selective melting process parameters.

[0244] Specifically, the model-process-quality relationship prediction model is provided with a three-layer neural network, including an input layer, a hidden layer and an output layer.

[0245] The number of nodes of the input layer, the hidden layer and the output layer is m0, m1 and m2 respectively.

[0246] The input layer satisfies:

[0247]

[0248] The hidden layer satisfies:

[0249]

[0250] The output layer satisfies:

[0251]

[0252] Y (0) represents an input layer process parameter condition matrix.

[0253] Y (1) represents an output vector of the hidden layer.

[0254] Y (2) represents a mathematical relationship between model quality and process.

[0255] For the hidden layer:

[0256]

[0257] Y (1) is an activation function, and for the laser selective melting process, the following equation is obtained:

[0258] f(x) = max(xα, x)

[0259] wherein α is a hyperparameter obtained by data training, and net(1) The weighted quantity is added.

[0260] The rule base is the boundary condition of the process, which is used to build the process value range of laser selective melting, the quality requirement of initial input and the material fracture strain value.

[0261] Specifically, the searching and calculating method is that after the model characteristics and quality requirements are determined, the knowledge base queries the saved model-process-quality relationship to see if it matches the known facts.

[0262] After all the IF clauses (relationships, i.e. hidden layers) in the rule match, the THEN clause is traced back to enable the rule, and new facts generated by the rule are added to the database. At this time, all the facts in the database are the reasoning results, and the reasoning ends.

[0263] The initial recommended process parameters of laser selective melting include: ambient temperature, laser power, welding gun diameter and cladding speed.

[0264] The simulation interaction module is used to import the built three-dimensional model into the finite element analysis software, drive the finite element analysis software to perform calculation and analysis under different parameter iterations, and extract the calculation results for quality result data analysis.

[0265] The finite element analysis module performs finite element analysis on the built three-dimensional model and the initial recommended process parameters of laser selective melting of the target part to obtain the target part forming surface and stress-strain distribution-time data.

[0266] After obtaining the target part forming surface and stress-strain distribution-time data, the knowledge base is used to compare and analyze the obtained data with the technical requirements in the process database.

[0267] If the comparison meets the requirements, the similar laser selective melting process parameters of the target part are searched and obtained as the final result.

[0268] If the comparison does not meet the requirements, the knowledge base is used to optimize the laser selective melting process until the process parameters that meet the requirements are obtained.

[0269] The simulated annealing optimization model is provided in the knowledge base to optimize the process parameter data that does not meet the requirements until the process parameters that meet the requirements are obtained.

[0270] According to the simulated annealing algorithm, the support structure position and size, cladding path, initial starting point, ambient temperature, laser power, welding gun diameter and cladding speed are optimized and modified, and the simulation software is driven for analysis again until the required results are obtained.

[0271] Specifically, the probability p that the process parameters are accepted from x1 to x2 satisfies:

[0272]

[0273] Wherein, △f=f1-f2, is the difference between the values of the objective function f(x1), f(x2);

[0274] f(x) is a quality function, indicating the maximum strain.

[0275] T is a temperature constant;

[0276] Slowly reduce with time, when the temperature is very high, take the second probability is high, with the temperature decreases, take the second case slowly reduce, until almost no choice second case.

[0277] Wherein, the relationship between the number of iterations n and the temperature constant T satisfies:

[0278] T(n+1)=K*T(n)

[0279] Wherein, K is a constant less than 1.

[0280] In this way, the laser selective melting process parameters are optimized through the simulated annealing optimization model until the laser selective melting process parameters meeting the requirements are obtained, finally, the process of obtaining the final result and the final result are saved to the process database, and based on the updated process database, the model-process-quality relationship prediction model and the simulated annealing optimization model and the related rule base and the simulated annealing algorithm are optimized.

[0281] It also includes a business terminal for process personnel to operate and interact with the interface;

[0282] Wherein, the business terminal process personnel can query, save, modify, read and use process information on the workstation.

[0283] The management terminal is used for account maintenance and permission setting of system management users, information query and management, statistics and analysis.

[0284] Wherein, the management terminal further includes establishing, querying, saving, modifying process personnel platform use permissions.

[0285] Compared with the traditional process simulation design:

[0286] The traditional process simulation design needs to use orthogonal design when designing parameters, taking the ribbed cylindrical part of the application as an example, the wall thickness is 3mm, the ribs are longitudinal and transverse, arranged every 30mm with a height of 25mm, the cylindrical radius is 200mm, the depth is 400mm, and the process parameters are selected as follows:

[0287] Laser power Scan speed Scan spacing Powder thickness W1 (800 Watts) V1 (0.5 mm / s) T1 (0.05 mm) W1 (0.5 mm) W2 (850 Watts) V2 (1 mm / s) T2 (0.1 mm / s) W1 (1 mm) W3 (900 Watts) V3 (1.5 mm / s) T3 (0.15 mm / s) W3 (1.5 mmG) W4 (950 Watts) V4 (2 mm / s) T4 (0.22 mm / s) W4 (2 mmG)

[0288] According to the parameter in the above, orthogonal design is developed, 4*4*4*4=256 groups of simulation need to be carried out to obtain the relationship between the process parameters and the quality, and the process parameters meeting the quality requirements are still unclear.

[0289] After the first group of simulation is completed, only 3-4 iterations are needed to obtain the required process parameters by using the method of the application, and the design efficiency is greatly improved.

[0290] It can be seen that, compared with the traditional trial-and-error method and manual adjustment of simulation parameters and models, the intelligent process design and simulation optimization method of laser selective melting of the application adopts a database automatic retrieval method, a knowledge base self-driven optimization method, a simulation software automatic calculation method, and a network cloud platform sharing mode, realizes the intelligentization of process design and optimization, the digitization of process knowledge, the self-learning of knowledge base, and greatly improves the laser selective melting process design efficiency and the process test manufacturing cost.

[0291] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. The computer readable storage medium includes a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

[0292] The above is only a preferred specific embodiment of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered within the protection scope of the application.

Claims

1. A laser selective melting intelligent process design and simulation optimization method, characterized in that: include: Step 1: Simplify the target part and support structure in the 3D modeling software and save them in XT format to construct a 3D model of the target part and support structure; Step 2: Identify the straight lines, fillets, arcs, holes, planes, extruded and rotated entities and their feature relationships in the 3D model to obtain the surface features to be machined of the target part; Step 3: Based on the features of the target part's surface to be processed, obtain the initial recommended process parameters for laser selective melting of the target part; Step 4: Perform finite element analysis on the constructed 3D model and the initial recommended process parameters for laser selective melting of the target part to obtain the forming surface and stress-strain distribution-time data of the target part; Step 5: Compare and analyze the target part forming surface and stress-strain distribution-time data with the technical requirements in the process database; Step 6: Use the simulated annealing algorithm to optimize the laser selective melting process parameter data that does not meet the requirements, and return to step 4 until the process parameters that meet the requirements are obtained; Among them, the optimized and modified process parameters include: support structure position and size, cladding path, initial starting point, ambient temperature, laser power, welding gun diameter and cladding speed; In step 6, the probability p of the process parameter being accepted when changing from x1 to x2 satisfies: Where △f=f1-f2, is the difference between the values ​​of the objective functions f(x1) and f(x2); f(x) is the mass function, which represents the maximum strain; T is the temperature constant.

2. The method according to claim 1, characterized in that The step 3 comprises: S31: constructing a process database to store basic information of the selective laser melting process; S32: based on the characteristics of the laser selective melting process of the target part, obtaining the laser selective melting process of the target part; S33: Based on the laser selective melting process of the target part and the characteristics of the target part's surface to be processed, obtain the technical requirements for the target part's surface accuracy and forming quality; S34: Based on the features of the target part's surface to be processed and the technical requirements of the target part's surface accuracy and forming quality, similar laser selective melting process parameters of the target part are searched for in the process database to obtain initial recommended laser selective melting process parameters of the target part.

3. The method according to claim 2, characterized in that In step S31, the basic information of the laser selective melting process includes: the laser selective melting process based on the laser selective melting process characteristics of the target part, the laser selective melting process parameters based on the technical requirements of the precision of the surface to be processed and the forming quality of the surface to be processed based on the characteristics of the surface to be processed of the target part, and the technical requirements of the precision of the surface to be processed and the forming quality based on the characteristics of the surface to be processed of the target part.

4. The method according to claim 3, characterized in that In step S32, the selective laser melting process of the target part includes specifying the target part and the support structure, selecting the cladding path and the starting position, and selecting the target part material, including titanium alloy and aluminum alloy.

5. The method according to claim 3, characterized in that The step S34 includes: S341: Set up a 3-layer neural network, input layer, hidden layer and output layer; S342: Determine the process boundary conditions to establish the process value range for laser selective melting, the quality requirements of the initial input, and the material fracture strain value; S343: Based on steps S341 and S342, initial recommended process parameters for selective laser melting of the target part are obtained.

6. The method according to claim 5, characterized in that: In step S341, the input layer satisfies: The hidden layer satisfies: The output layer satisfies: Among them, Y (0) Represents the input layer process parameter condition matrix; Y (1) represents the output vector of the hidden layer; Y (2) A mathematical relationship between model quality and workmanship; Among them, the number of nodes in the input layer, hidden layer and output layer are m0, m1 and m2 respectively.

7. The method according to claim 6, characterized in that: The hidden layer satisfies: Among them, f (1) is the activation function. At this time, for the laser selective melting process, we have: f(x)=max(xα,x) Among them, α is a hyperparameter obtained by data training, net (1) is the weighted amount.

8. The method according to claim 5, wherein: In S343, the features of the target part's to-be-machined surface and the technical requirements for the target part's to-be-machined surface accuracy and forming quality are used as input parameters, and the laser selective melting process parameters of the target part are used as output parameters. After determining the model features and quality requirements, the knowledge base queries the saved model-process-quality relationship to see if it matches the known facts. If they match, the laser selective melting process parameters of the target part are obtained.

9. The method according to claim 1, wherein: In step 6, during the optimization process, the relationship between the number of iterations n and the temperature constant T satisfies: T(n+1)=K*T(n) Here, K is a constant less than 1.

Images