CN115659688B - Process determination method for improving reliability of additive aluminum alloy and composite material thereof - Google Patents
Process determination method for improving reliability of additive aluminum alloy and composite material thereof Download PDFInfo
- Publication number
- CN115659688B CN115659688B CN202211384918.1A CN202211384918A CN115659688B CN 115659688 B CN115659688 B CN 115659688B CN 202211384918 A CN202211384918 A CN 202211384918A CN 115659688 B CN115659688 B CN 115659688B
- Authority
- CN
- China
- Prior art keywords
- temperature
- additive manufacturing
- composite material
- aluminum alloy
- additive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Landscapes
- Powder Metallurgy (AREA)
Abstract
The invention provides a process determination method for improving the reliability of an additive aluminum alloy and a composite material thereof. The method comprises the steps of carrying out post-treatment on an additive manufacturing aluminum alloy and a composite material workpiece thereof in a mode of electric field assisted deep-cooling isostatic pressing and solid solution aging, quantitatively predicting influence rules of additive manufacturing process parameters and electric field assisted deep-cooling isostatic pressing and solid solution aging process parameters on static mechanical properties and dynamic mechanical properties of the additive manufacturing workpiece of the aluminum alloy and the composite material thereof based on a support vector machine algorithm, taking an average value and anisotropy weighted combination of all index predicted values as unified control optimization targets, and finally determining an optimal process scheme for improving service reliability of the workpiece by utilizing an improved whale optimization algorithm, thereby having great significance for serial production application of novel post-treatment process in additive manufacturing and popularization and application of promotion of additive manufacturing technology.
Description
Technical Field
The patent relates to the technical field of additive manufacturing reliability improvement, in particular to a process determination method for improving the reliability of an additive aluminum alloy and a composite material thereof.
Background
Additive manufacturing techniques not only can manufacture complex parts, but also can construct stronger, lighter parts, reduce material consumption, and facilitate the integrated manufacture of assembly components in a variety of applications. With the leap development of manufacturing technology, more and more industries nowadays begin to relate to the technology of additive manufacturing, in particular to the fields of aerospace, military, medical, mould and the like.
However, for the additive manufacturing forming part, especially the aluminum alloy and the composite forming part thereof, after finishing, many defects such as pores, cracks, deformation, spheroidization and thermal stress, gap defects, physical property defects of the material, and the like exist, and the practical performance problems of excessive internal stress, insufficient hardness, low plasticity, short service life and the like of the product are caused. Thus, the formed part can reach the application stage only after the defect problem of the product is solved by the post-treatment. The post-treatment technology of the additive formed parts plays a decisive role in the service performance and service life of the additive formed parts, and is an indispensable procedure in the serial production process of additive manufacturing.
Compared with hot isostatic pressing (hot isostatic pressing, HIP), cold isostatic pressing (cold isostatic pressing, CIP) is an isostatic pressing treatment process at normal temperature, a new process, namely deep isostatic pressing (deep cryogenic isostatic pressing, DCIP), is proposed based on cold isostatic pressing, is used for carrying out high-pressure treatment on materials below minus 130 ℃, belongs to the latest material toughening treatment process, and the materials are uniformly pressed in all directions under the combined action of low temperature and high pressure, so that the workpiece has high compactness, good uniformity and excellent performance, the mechanical property and the service life of the additive manufactured formed piece can be effectively improved, the size is stabilized, the uniformity is improved, the deformation is reduced, the operation is simple and convenient, the workpiece is not damaged, the pollution is avoided, the cost is low, and the method has positive application prospect and development space.
The electric field is a special physical field, and by changing the states or environments of atoms, electrons, defects and the like in the material, the energy density of electrons in the system and the metal is changed, and the electric field is used for treating the electric field energy to introduce the material, so that the diffusion, phase change and other processes occurring in the material are influenced, and further, one or more properties of the material are improved. The electric field increases the vacancy concentration of the alloy and accelerates the movement of vacancies within the alloy, promoting the formation of a plurality of supersaturated vacancy clusters wherein a portion of the vacancy clusters collapse upon quenching to form a plurality of mobile dislocations. Under the coupling action of the force field and the temperature field, the dislocations start to move in a thermal activation mode and interact with impurities, precipitated phases, defects and the like in the matrix in the movement process, so that the movement of the dislocations is blocked, and finally the dislocation tends to be stable, namely stress relaxation phenomenon.
Based on the idea of the composite treatment process, the treatment method for applying the electric field while the deep isostatic pressing is performed is provided, and compared with the single deep isostatic pressing, the movable dislocation density can be improved due to the increase of the electric field strength, so that the generated stress relaxation is more obvious, the microstructure of the alloy can be remarkably improved, and the mechanical property and the service life of the alloy are further improved. Meanwhile, more vacancies and dislocation are provided for the solid solution and aging process under the action of the subsequent electric field, so that nucleation of the precipitated phase is promoted, refinement and dispersion of the precipitated phase are facilitated, uniformity of the material is improved, and anisotropy of a workpiece is reduced.
As a brand new compound post-treatment process, the existing evaluation and optimization method cannot be fully adopted to check the effect of electric field assisted deep-cooling isostatic pressing and solid solution aging on the manufacturability, service performance, safety and reliability of the additive manufacturing material. Therefore, establishing an evaluation standard and a process parameter determination method under a novel structural form according to the characteristics of additive manufacturing and post-treatment processes is a key core problem for realizing engineering application of the additive manufacturing technology of aluminum alloy and composite materials thereof.
Disclosure of Invention
The invention aims to provide a process determination method for improving the reliability of an additive aluminum alloy and a composite material thereof. The method comprises the steps of carrying out post-treatment on an additive manufacturing aluminum alloy and a composite material workpiece thereof in a mode of electric field assisted deep-cooling isostatic pressing and solid solution aging, quantitatively researching the action mechanism and influence rules of additive manufacturing process parameters and electric field assisted deep-cooling isostatic pressing and solid solution aging process parameters on the static mechanical properties (yield strength, elongation) and dynamic mechanical properties (impact properties and fatigue life) of the aluminum alloy and the composite material additive manufacturing workpiece thereof based on a support vector machine algorithm, taking the average value and anisotropy weighted combination of all index predicted values as unified control optimization targets, scientifically, efficiently and accurately searching for the optimal process combination by utilizing an improved whale optimization algorithm, and finally determining a process scheme for improving service reliability of the additive manufacturing aluminum alloy and the composite material workpiece thereof.
In order to achieve the above object, the present invention adopts the following technical scheme:
the process determination method for improving the reliability of the additive aluminum alloy and the composite material thereof comprises the following steps:
(a) The method comprises the following steps of performing deep isostatic pressing and solid solution aging treatment on the additive manufacturing aluminum alloy and the composite material thereof under the action of an electrostatic field, wherein the main contents comprise: carrying out solution quenching and artificial aging on an aluminum alloy or aluminum-based composite material workpiece formed by printing in an additive manufacturing way after carrying out low-temperature high-pressure treatment for a certain time in a specific container, and applying an electrostatic field with a certain intensity to the workpiece in the process all the time, so that the compactness of the material of the workpiece manufactured by the additive manufacturing way is improved, the effective precipitation and uniform distribution of a second phase are promoted, the internal defects of the material are eliminated, the anisotropism of the workpiece is reduced, and the dynamic and static mechanical properties of the material are greatly improved; finally, the yield strength, the elongation, the impact toughness and the fatigue life of the material in the scanning direction X, the direction Y and the height direction Z of the additive manufacturing workpiece are obtained through various detection means and data analysis;
(b) Repeating the step (a) on the premise of ensuring the reliability and the effectiveness of test results, designing a process test scheme for improving the service reliability of the additive manufacturing aluminum alloy and the composite material thereof according to a support vector machine algorithm based on a process parameter constraint range, wherein input data are respectively the temperature T during deep isostatic pressing HIP Pressure P HIP Cooling rate v T Rate of temperature rise v' T Boost rate v P Pressure relief rate v' P Time t of heat preservation T Dwell time t P Difference delta t between temperature and pressure start loading time TP Electric field strength E of cryogenic isostatic pressing HIP And a solid solution temperature T S Time t of solid solution S Field strength E of solid solution electric field S Quenching rate v Q Aging temperature T A Time of aging t A Field strength E of aging electric field A The output data is the yield strength of the additive manufacturing aluminum alloy and the composite material workpiece along a specific direction i
Elongation delta i Impact toughness->
Fatigue life->
Processing, correcting and removing irregular data, carrying out normalization or standardization treatment, dividing the data according to the ratio of 3:1:1 to generate a training set, a verification set and a test set, selecting proper kernel functions and parameters, finding out the optimal function relation between input and output by utilizing the steps of sample training, sample inspection and the like, and finally establishing a prediction model of yield strength, elongation, impact toughness and fatigue life of the additive manufactured workpiece based on a support vector machine;
further, the process parameter constraint range refers to the maximum and minimum values of the following parameters: temperature T at cryogenic isostatic pressing HIP Pressure P HIP Cooling rate v T Rate of temperature rise v' T Boost rate v P Pressure relief rate v' P Time t of heat preservation T Dwell time t P Difference delta t between temperature and pressure start loading time TP Electric field strength E of cryogenic isostatic pressing HIP And a solid solution temperature T S Time t of solid solution S Field strength E of solid solution electric field S Quenching rate v Q Aging temperature T A Time of aging t A Field strength E of aging electric field A 。
Further, the difference delta t between the temperature and the pressure at the beginning of loading TP : if delta t TP =0, then synchronous loading, i.e. temperature and pressure start loading simultaneously; if delta t TP Not equal to 0, then asynchronous loading, where, when Δt TP When the temperature is greater than 0, the temperature is loaded first and then the pressure is loaded, and when deltat is TP When the pressure is less than 0, loading the pressure and then loading the temperature; Δt is generally preferred TP And > 0, i.e. loading temperature and then pressure.
Further, the kernel functions mainly include a linear kernel function, a polynomial kernel function, a Gaussian/radial basis function, a Sigmoid kernel function, a string kernel function, a fourier kernel function, a spline kernel function, wherein a Gaussian/radial basis function is preferable.
Further, the kernel function is selected mainly by a priori knowledge, cross validation and mixed kernel functions.
(c) Recording the maximum value sigma of yield strength of the additive manufactured aluminum alloy and the composite material thereof in all test results in the step (b) smax And a minimum value sigma smin Maximum value delta of elongation max And a minimum value delta min Maximum value of impact toughness a kmax And a minimum value a kmin Maximum fatigue strength N fmax And a minimum value N fmin ；
(d) The improved whale optimization algorithm is utilized to seek the optimal technological scheme combination, the service reliability of the aluminum alloy for additive manufacturing and the composite material workpiece thereof is improved, a unified target evaluation function F (X) of each index (namely output data) is established as an fitness function to evaluate the advantages and disadvantages of the corresponding solutions of the variables, the smaller the value is, the better the corresponding solutions of the variables are indicated, and the expression is:
wherein X-argument, X= [ T ] HIP ,P HIP ,v T ,v′ T ,v P ,v′ P ,t T ,t P ,Δt TP ,E HIP ,T S ,t S ,E S ,v Q ,T A ,t A ,E A ]；
ψ 1 ,ψ 2 ,ψ 3 ,λ,η,
Xi-weighting coefficient, the value range is 0 to 1, and each value can be adjusted in the (0, 1) range according to different requirements on each index parameter;
mid () —the intermediate value after removal of the maximum and minimum values;
in the formula (1), G 1 For (X)At the average level of static mechanical properties of the evaluation material, G 2 (X) degree of anisotropy for evaluating static mechanical properties of Material, G 3 (X) average value level for evaluating dynamic mechanical properties of materials, G 4 (X) the degree of anisotropy for evaluating the dynamic mechanical properties of the material;
(e) Initializing, determining the population size m of whales, and randomly generating the positions X of m whales in a search domain determined by the process parameter constraint conditions in the step (b) j As the initial position of the population, the maximum iteration number k max As optimizing termination condition, let current iteration number be k=0;
further, the value range of the population size m is 20-100.
Further, the maximum number of iterations k max The value range is 200-1000.
(f) Evaluating the fitness value of m whale individuals in the step (e), calculating the fitness value of each whale, sorting according to the fitness value, comparing, and finding out the globally optimal whale individual and the position X thereof * ；
(g) Updating whale individual positions using formula (2):
wherein, w is an inertia weight;
c-a constant;
b-a constant defining a logarithmic spiral shape;
a random number between l < -1 >, 1 >;
X * (k) rand -a whale individual position vector randomly selected from the current population;
(h) Judging whether the iteration condition k of the algorithm is less than k max If yes, making k=k+1, turning to the step (f), continuing algorithm iteration, otherwise, directly turning to the step (i);
(i) Outputting the optimal whale individual, and ending iteration, namely finding out a global optimal solution X by an algorithm y And finally, determining the optimal technological parameter combination for improving the service reliability of the additive manufacturing aluminum alloy and the composite material thereof.
Compared with the prior art, the invention has the following advantages and effects:
compared with the prior art, the invention realizes a process parameter determination method for improving and improving the static mechanical properties (yield strength, elongation) and the dynamic mechanical properties (impact property, fatigue life) of the aluminum alloy and the composite material additive manufacturing workpiece thereof, and mainly has the following advantages: (1) The new method for deep-cooling isostatic pressing is provided, electric field treatment and deep-cooling isostatic pressing and traditional solution-quenching-aging cooperative coupling are applied to an aluminum alloy and composite material additive manufacturing post-treatment process thereof, and an evaluation method for the effect of technological parameters of the new process on the static and dynamic mechanical properties of a workpiece is determined, so that the problem of the lack of current evaluation standards is solved, and an important reference basis is provided for enriching and perfecting an additive manufacturing standard system; (2) Compared with the conventional whale optimization algorithm, the improved whale optimization algorithm can quickly converge on a global optimal value by improving the inertia weight w and the parameter A, balance the development and exploration capacity of the algorithm, improve the overall performance of the algorithm, enhance the global and local searching capacity of the algorithm, improve the convergence precision and accelerate the convergence speed, and introduce a calculation control factor c-c (k/k) max ) The search range of the cosine cos (2 pi l) local development area is controlled, and furthermore, the sine term sin (X (k)) is introduced to play a role of [ -1,1]The method has the advantages that interference and auxiliary effects are provided in the range, the convergence precision can be improved, the opportunity that the population is quickly gathered together in later searching is effectively reduced, the result is prevented from being trapped into local optimum, and the conventional whale optimization algorithm has better properties; (3) Based on an improved intelligent optimization algorithm, the strength and plasticity of the workpiece manufactured by the additive manufacturing of the aluminum alloy and the composite material thereof are improved, the dimensional accuracy of the workpiece is ensured, the impact toughness of the workpiece is improved, the fatigue strength and service life are improved, the internal stress distribution is improved, the anisotropism of the workpiece is reduced, the service reliability of the workpiece is comprehensively improved, a key process optimization method is provided for the precise and stable control of the post-treatment processes of the electric field assisted deep-cooling isostatic pressing and the solid solution aging of the additive manufacturing of the complex component of the aluminum alloy and the composite material thereof, and the key process optimization method is provided for the post-treatment processThe method has important theoretical and practical significance in serial production application of additive manufacturing and promotion of popularization and application of additive manufacturing technology.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it being understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope, and that other related drawings can be obtained from these drawings without inventive effort to a person of ordinary skill in the art.
FIG. 1 is a general flow chart of a process determination method for improving the reliability of an additive aluminum alloy and a composite material thereof;
FIG. 2 is a graph of laser cladding deposition additive manufacturing 10wt% TiC in an example p Carrying out deep isostatic pressing and solid solution aging treatment process schematic diagram on the AlSi10Mg composite material forming piece under the action of an electrostatic field;
wherein: 1-an auxiliary electric field; 2-a workpiece; 3-deep cooling high pressure container.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, but the present invention may be implemented in many different forms, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention, rather, these embodiments are provided so that this disclosure will be more thorough and complete. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The portions of the following examples, which are not specifically described, are well known to those skilled in the art and are not described herein.
This example selects laser cladding deposition additive to make 10wt% TiC p AlSi10Mg composite shaped bodies were used as test subjects. AlSi10Mg spherical powder is prepared by a rotary electrode method, the powder granularity is 45-150 mu m, tiC powder granularity is 5-25 mu m, the powder is ball-milled and mixed, the mixed powder is dried, the mixed powder is conveyed to a coaxial powder conveying head by a powder conveying device under the bearing of argon, and a forming substrate is 6061 aluminum alloy.
The process determination method for improving the reliability of the additive aluminum alloy and the composite material thereof comprises the following steps (the total flow chart is shown in figure 1):
(a) The method comprises the following steps of performing deep isostatic pressing and solid solution aging treatment on the additive manufacturing aluminum alloy and the composite material thereof under the action of an electrostatic field, wherein the main contents comprise: as shown in fig. 2, 10wt% tic printed for laser cladding deposition additive manufacturing p Carrying out solution quenching and artificial aging on an AlSi10Mg composite material workpiece 2 after carrying out low-temperature high-pressure treatment for a certain time in a specific cryogenic high-pressure container 3, and applying an electrostatic field with a certain intensity to the workpiece by using an auxiliary electrode 1 all the time in the process, so as to improve the compactness of the workpiece material for additive manufacturing, promote the effective precipitation and uniform distribution of a second phase, eliminate the internal defects of the material, reduce the anisotropy of the workpiece and greatly improve the dynamic and static mechanical properties of the material; finally, the yield strength, the elongation, the impact toughness and the fatigue life of the material in the scanning direction X, the direction Y and the height direction Z of the additive manufacturing workpiece are obtained through various detection means and data analysis;
(b) Repeating the step (a) on the premise of ensuring the reliability and the effectiveness of test results, and improving the laser cladding deposition additive manufacturing 10wt% TiC according to the algorithm design of the support vector machine based on the constraint range of the technological parameters p Technological test scheme of service reliability of AlSi10Mg composite material forming part, and input data are respectively temperature T during deep isostatic pressing HIP Pressure P HIP Cooling rate v T Rate of temperature rise v' T Boost rate v P Pressure relief rate v' P Time t of heat preservation T Dwell time t P Difference delta t between temperature and pressure start loading time TP More than 0, namely, loading temperature and pressure, and deep isostatic pressing electric field intensity E HIP And a solid solution temperature T S Time t of solid solution S Field strength E of solid solution electric field S Quenching rate v Q Aging temperature T A Time of aging t A Field strength E of aging electric field A The output data is the yield strength of the additive manufacturing aluminum alloy and the composite material workpiece along a specific direction i
Elongation delta i Impact toughness->
Fatigue life->
Processing, correcting and removing irregular data, carrying out normalization or standardization treatment, dividing the data according to the ratio of 3:1:1 to generate a training set, a verification set and a test set, selecting a Gaussian/radial basis function as a kernel function and parameters by using a mixed kernel function method, finding out the optimal function relation between input and output by using the steps of sample training, sample inspection and the like, and finally establishing 10wt% TiC manufactured by using laser cladding deposition additive based on a support vector machine p Predictive models of AlSi10Mg composite formed part yield strength, elongation, impact toughness, fatigue life;
(c) Recording laser cladding deposition additive manufacturing of 10wt% TiC in all test results in step (b) p AlSi10Mg composite formed article yield strength maximum sigma smax And a minimum value sigma smin Maximum value delta of elongation max And a minimum value delta min Maximum value of impact toughness a kmax And a minimum value a kmin Maximum fatigue strength N fmax And a minimum value N fmin ；
(d) Optimal technological scheme combination is sought by utilizing improved whale optimization algorithm, and 10wt% TiC is manufactured by laser cladding deposition additive material p Service reliability of AlSi10Mg composite material forming piece is improved, a unified target evaluation function F (X) of each index (namely output data) is established as a fitness function according to a formula (1), wherein psi is 1 ＝ψ 2 ＝ψ 3 ＝0.25，λ＝0.5，η＝0.5，
ζ=0.5 while establishing corresponding constraint conditions;
(e) Initializing, determining population size m=80 of whales, randomly generating positions X of 80 whales in a search field determined by process parameter constraints in step (b) j As the initial position of the population, the maximum iteration number k max =800 as the optimization termination condition, and let the current iteration number be k=0;
(f) Evaluating the fitness values of 80 whale individuals in the step (e), calculating the fitness value of each whale, sorting according to the fitness values, comparing, and finding out the globally optimal whale individual and the position X thereof * ；
(g) Updating the individual whale position using formula (2);
(h) Judging whether the iteration condition k of the algorithm is smaller than 800, if yes, enabling k=k+1 to go to the step (f), continuing algorithm iteration, otherwise, directly going to the step (i);
(i) Outputting the optimal whale individual, and ending iteration, namely finding out a global optimal solution X by an algorithm y After that, the additive manufacturing of 10wt% TiC by lifting laser cladding deposition is finally determined p The optimal technological parameter combination of the service reliability of the AlSi10Mg composite material forming piece mainly comprises the following parameters: temperature T at cryogenic isostatic pressing HIPy = -190 ℃ and pressure P HIPy =90 MPa, cooling rate v Ty = -5 ℃/min and heating rate v' Ty =4deg.C/min, boost rate v Py =2.7 MPa/min, pressure relief rate v' Py =1.7 MPa/min, heat preservationTime t Ty =5h, dwell time t Py =4h, difference Δt between the temperature and pressure start loading TPy =1h, field strength E of cryogenic isostatic pressing electric field HIPy =19 kV/cm, solid solution temperature T Sy =535 ℃, solid solution time t Sy =4h, solid solution field strength E Sy =8kv/cm, quench rate v Qy =40 ℃/s, aging temperature T Ay Time of aging t at 180 =180% Ay 12h, aging field strength E Ay ＝12kV/cm。
The optimized technological parameters of the invention are temperature, pressure, cooling rate, heating rate, boosting rate, pressure relief rate, heat preservation time, pressure maintaining time, temperature and pressure starting loading time difference, deep isostatic pressing electric field intensity, solid solution temperature, solid solution time, solid solution electric field intensity, quenching rate, aging temperature, aging time and aging electric field intensity, and in order to quickly and effectively realize the technological parameter determination method for improving the service reliability of the additive manufacturing aluminum alloy and the composite material thereof, certain or some technological parameters can be added or subtracted appropriately according to actual requirements, and only the invention provides an optimization model.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (7)
1. The process determination method for improving the reliability of the additive aluminum alloy and the composite material thereof is characterized by comprising the following steps of: the method comprises the following steps:
(a) The method comprises the following steps of performing deep isostatic pressing and solid solution aging treatment on the additive manufacturing aluminum alloy and the composite material thereof under the action of an electrostatic field: for the printing-formed aluminum alloy or aluminum-based composite material workpiece in additive manufacturing, carrying out solution quenching and artificial aging after carrying out low-temperature high-pressure treatment for a certain time in a container, always applying a static electric field with a certain intensity to the workpiece in the processes of low-temperature high-pressure treatment, solution quenching and artificial aging, improving the compactness of the material of the workpiece in additive manufacturing, promoting the effective precipitation and uniform distribution of a second phase, eliminating the internal defects of the material, reducing the anisotropism of the workpiece and greatly improving the dynamic and static mechanical properties of the material; finally, the yield strength, the elongation, the impact toughness and the fatigue life of the material in the scanning direction X, the direction Y and the height direction Z of the additive manufacturing workpiece are obtained through various detection means and data analysis;
the deep isostatic pressing refers to the high-pressure treatment of the material at the same time below-130 ℃;
(b) Repeating the step (a) on the premise of ensuring the reliability and the effectiveness of test results, designing a process test scheme for improving the service reliability of the additive manufacturing aluminum alloy and the composite material thereof according to a support vector machine algorithm based on a process parameter constraint range, wherein input data are respectively the temperature T during deep isostatic pressing HIP Pressure P HIP Cooling rate v T Rate of temperature rise v' T Boost rate v P Pressure relief rate v' P Time t of heat preservation T Dwell time t P Difference delta t between temperature and pressure start loading time TP Electric field strength E of cryogenic isostatic pressing HIP And a solid solution temperature T S Time t of solid solution S Field strength E of solid solution electric field S Quenching rate v Q Aging temperature T A Time of aging t A Field strength E of aging electric field A The output data is the yield strength of the additive manufacturing aluminum alloy and the composite material workpiece along a specific direction i
Elongation delta i Impact toughness->
Fatigue life->
Processing, correcting and removing irregular data, carrying out normalization or standardization treatment, dividing the data according to the ratio of 3:1:1 to generate a training set, a verification set and a test set, selecting proper kernel functions and parameters, finding out the optimal function relation between input and output by utilizing the steps of sample training, sample inspection and the like, and finally establishing a prediction model of yield strength, elongation, impact toughness and fatigue life of the additive manufactured workpiece based on a support vector machine;
(c) Recording the maximum value sigma of yield strength of the additive manufactured aluminum alloy and the composite material thereof in all test results in the step (b) smax And a minimum value sigma smin Maximum value delta of elongation max And a minimum value delta min Maximum value of impact toughness a kmax And a minimum value a kmin Maximum fatigue strength N fmax And a minimum value N fmin ；
(d) The improved whale optimization algorithm is utilized to seek the optimal technological scheme combination, the service reliability of the aluminum alloy for additive manufacturing and the composite material workpiece thereof is improved, the unified target evaluation function F (X) of each index, namely output data, is established as an fitness function to evaluate the merits of the corresponding solutions of the variables, the smaller the value, the better the corresponding solutions of the variables are indicated, and the expression is:
wherein X-argument, X= [ T ] HIP ,P HIP ,v T ,v′ T ,v P ,v′ P ,t T ,t P ,Δt TP ,E HIP ,T S ,t S ,E S ,v Q ,T A ,t A ,E A ]；
ψ 1 ,ψ 2 ,ψ 3 ,λ,η,
Xi-weighting coefficient, the value range is 0 to 1, and the value can be within (0) according to different requirements on various index parameters1) adjusting within the range;
mid () —the intermediate value after removal of the maximum and minimum values;
in the formula (1), G 1 (X) average value level for evaluating static mechanical properties of materials, G 2 (X) degree of anisotropy for evaluating static mechanical properties of Material, G 3 (X) average value level for evaluating dynamic mechanical properties of materials, G 4 (X) the degree of anisotropy for evaluating the dynamic mechanical properties of the material;
(e) Initializing, determining the population size m of whales, and randomly generating the positions X of m whales in a search domain determined by the process parameter constraint conditions in the step (b) j As the initial position of the population, the maximum iteration number k max As optimizing termination condition, let current iteration number be k=0;
(f) Evaluating the fitness value of m whale individuals in the step (e), calculating the fitness value of each whale, sorting according to the fitness value, comparing, and finding out the globally optimal whale individual and the position X thereof * ；
(g) Updating whale individual positions using formula (2):
wherein, w is an inertia weight;
c-a constant;
b-a constant defining a logarithmic spiral shape;
a random number between l < -1 >, 1 >;
X * (k) rand -a whale individual position vector randomly selected from the current population;
(h) Judging whether the iteration condition k of the algorithm is less than k max If yes, making k=k+1, turning to the step (f), continuing algorithm iteration, otherwise, directly turning to the step (i);
(i) Outputting the optimal whale individual, and ending iteration, namely finding out a global optimal solution X by an algorithm y After the end of the process, the process is finished,and finally, determining the optimal technological parameter combination for improving the service reliability of the additive manufacturing aluminum alloy and the composite material thereof.
2. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: the process parameter constraint limits described in step (b) refer to the maximum and minimum values of the following parameters: temperature T at cryogenic isostatic pressing HIP Pressure P HIP Cooling rate v T Rate of temperature rise v' T Boost rate v P Pressure relief rate v' P Time t of heat preservation T Dwell time t P Difference delta t between temperature and pressure start loading time TP Electric field strength E of cryogenic isostatic pressing HIP And a solid solution temperature T S Time t of solid solution S Field strength E of solid solution electric field S Quenching rate v Q Aging temperature T A Time of aging t A Field strength E of aging electric field A 。
3. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: for the temperature and pressure start loading time difference Δt described in step (b) TP : if delta t TP =0, then synchronous loading, i.e. temperature and pressure start loading simultaneously; if delta t TP Not equal to 0, then asynchronous loading, where, when Δt TP When the temperature is greater than 0, the temperature is loaded first and then the pressure is loaded, and when deltat is TP And when the pressure is less than 0, loading pressure and then loading temperature.
4. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: the kernel functions described in step (b) include linear kernel functions, polynomial kernel functions, gaussian/radial basis kernel functions, sigmoid kernel functions, string kernel functions, fourier kernel functions, spline kernel functions.
5. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: the kernel function is selected in step (b) in a manner that includes a priori knowledge, cross-validation, and blending of the kernel functions.
6. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: and (3) the value range of the population size m in the step (e) is 20-100.
7. The process determination method for improving the reliability of additive aluminum alloys and composites thereof according to claim 1, wherein: for the maximum number of iterations k of step (e) max The value range is 200-1000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384918.1A CN115659688B (en) | 2022-11-07 | 2022-11-07 | Process determination method for improving reliability of additive aluminum alloy and composite material thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211384918.1A CN115659688B (en) | 2022-11-07 | 2022-11-07 | Process determination method for improving reliability of additive aluminum alloy and composite material thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115659688A CN115659688A (en) | 2023-01-31 |
| CN115659688B true CN115659688B (en) | 2023-05-09 |
Family
ID=85016777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211384918.1A Active CN115659688B (en) | 2022-11-07 | 2022-11-07 | Process determination method for improving reliability of additive aluminum alloy and composite material thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115659688B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2566084C (en) * | 2004-06-07 | 2014-01-21 | Syngenta Participations Ag | Methods of reducing nematode damage |
| US11915105B2 (en) * | 2019-02-05 | 2024-02-27 | Imagars Llc | Machine learning to accelerate alloy design |
| CN110523997B (en) * | 2019-08-19 | 2022-05-20 | 江苏大学 | High-entropy alloy particle reinforced subzero treatment aluminum-based composite material and preparation method thereof |
| CN112155796B (en) * | 2020-10-30 | 2024-04-09 | 嘉思特医疗器材(天津)股份有限公司 | Titanium alloy partition bone small Liang Rengong acetabular cup manufactured by additive and preparation method |
| CN113361170B (en) * | 2021-06-11 | 2023-05-12 | 金陵科技学院 | Unsaturated soil hydraulic characteristic parameter numerical inversion method based on evaporation process |
| CN113627071B (en) * | 2021-06-26 | 2023-06-20 | 西安科技大学 | Coal-fired boiler NO based on whale algorithm optimization long-short-term memory network X Soft measurement method |
-
2022
- 2022-11-07 CN CN202211384918.1A patent/CN115659688B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115659688A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jie et al. | Flow behavior of Al–6.2 Zn–0.70 Mg–0.30 Mn–0.17 Zr alloy during hot compressive deformation based on Arrhenius and ANN models | |
| Wang et al. | Prediction of dynamic globularization of Ti-17 titanium alloy with initial lamellar microstructure during hot compression | |
| CN112487683B (en) | Structural member high-cycle fatigue life prediction method considering residual stress influence | |
| Nicoletto | Smooth and notch fatigue behavior of selectively laser melted Inconel 718 with as-built surfaces | |
| Chemkhi et al. | Effects of mechanical post-treatments on additive manufactured 17-4PH stainless steel produced by bound powder extrusion | |
| CN107937842B (en) | A kind of heat treatment method of Al-Zn-Mg-Cu aluminium alloy | |
| CN111286599A (en) | Alloy heat treatment process optimization method based on machine learning | |
| Yang et al. | Prediction of mechanical properties of A357 alloy using artificial neural network | |
| Sun et al. | Microstructure evolution modeling and simulation for dynamic recrystallization of Cr12MoV die steel during hot compression based on real metallographic image | |
| CN115659688B (en) | Process determination method for improving reliability of additive aluminum alloy and composite material thereof | |
| Afroz et al. | Fatigue behaviour of laser powder bed fusion (L-PBF) Ti–6Al–4V, Al–Si–Mg and stainless steels: a brief overview | |
| CN108062583A (en) | A kind of heating furnace technique parameter optimization method towards energy-saving and emission-reduction | |
| Zhang et al. | Influence of variable loading path pattern on deformation and grain size in large-scale electric upsetting process of Nimonic superalloy | |
| CN111933221B (en) | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel | |
| CN111861041B (en) | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel | |
| CN116611322A (en) | Reverse design method of additive manufacturing process parameters of titanium-based part based on near-spherical powder | |
| Wei et al. | High-cycle fatigue SN curve prediction of steels based on a transfer learning-guided convolutional neural network | |
| Gao et al. | Prediction of tri-modal microstructure under complex thermomechanical processing history in isothermal local loading forming of titanium alloy | |
| CN110442953B (en) | Q & P steel design method based on machine learning under guidance of physical metallurgy | |
| CN112877621A (en) | Cold bulging method for regulating residual stress of aluminum alloy ring piece and improving mechanical property | |
| Yanhui et al. | Microstructure homogeneity evaluation for TC11 blisk forging using loss function based on Taguchi method | |
| Arimoto et al. | Explanation of the origin of quench distortion and residual stress in specimens using computer simulation | |
| Roy et al. | A machine learning based approach for cold spray deposition porosity prediction from processing parameters | |
| DK2764127T3 (en) | A method for improving the fatigue strength of micro-alloy steels, forged parts made by the method and apparatus for carrying out the method | |
| Wang et al. | Machine Learning Design of Aluminum-Lithium Alloys with High Strength. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |