A method, apparatus, and medium for performance tuning of an additive manufacturing product

Abstract

The embodiment of the application discloses a kind of additive manufacturing product performance regulation methods, equipment and medium.It includes, based on the characteristics of multiple pre-set parts, construct the performance prediction model set of additive manufacturing product based on inclination radian;Based on the basic information of current test part, determine the feature information corresponding to current test part;The feature information corresponding to current test part is matched with multiple pre-set part characteristics, to determine the reference prediction model that meets the demand of test part in the performance prediction model set of additive manufacturing product based on inclination radian;Based on reference prediction model, deformation prediction and / or roughness prediction is carried out to test part;Based on the prediction result, the inclination radian of test part is adjusted, so that the deformation and roughness of test part meet the requirements;Through the above method, improve the cost of additive manufacturing product performance regulation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of workpiece measurement, and particularly relates to a performance regulation method and device of an additive manufacturing product and a medium. BACKGROUND

[0002] Laser additive manufacturing (LAM) is a material accumulation manufacturing method from bottom to top, layer by layer, and incrementally, which integrates advanced manufacturing technologies of material, equipment, program control and other multidisciplinary "shape and property" integration.

[0003] Selective laser melting (SLM) is a technology that selects laser as an energy source, performs layer-by-layer scanning on a metal powder bed according to a planned path in a three-dimensional CAD slicing model, and the scanned metal powder is melted and solidified to achieve a metallurgical bonding effect, and finally a metal part designed by the model is obtained.

[0004] In the prior art, process supports are used in the region where the local inclination angle of the metal additive part product is designed to be too large, so as to reduce the deformation and roughness, and to realize the feasibility of additive manufacturing. However, too many and too large process supports are designed, which on the one hand easily leads to damage to the product size in the process of manual removal of the process supports, and on the other hand, too many and too large process supports lead to a reduction in process yield and an increase in production cost. SUMMARY

[0005] The embodiments of the present application provide a performance regulation method and device of an additive manufacturing product and a medium, which are used to solve the following technical problem: in the prior art, too many process supports are used in the region where the local inclination angle of the metal additive part product is designed to be too large, which leads to a reduction in process yield and an increase in production cost.

[0006] The embodiments of the present application adopt the following technical solutions:

[0007] The embodiment of the application provides a kind of additive manufacturing product performance regulation method.The method comprises: constructing a set of additive manufacturing product performance prediction models based on inclination radian based on a plurality of pre-set component features;Wherein, the additive manufacturing product performance prediction model based on inclination radian includes a deformation prediction model and a roughness prediction model;Determine the feature information corresponding to the current component to be tested based on the basic information of the current component to be tested;Match the feature information corresponding to the current component to be tested with a plurality of pre-set component features to determine the reference prediction model that meets the requirements of the component to be tested in the set of additive manufacturing product performance prediction models based on inclination radian;Based on the reference prediction model, deformation prediction and / or roughness prediction is carried out on the component to be tested;Based on the prediction result, the inclination radian of the component to be tested is adjusted to make the deformation and roughness of the component to be tested meet the requirements;Wherein, the inclination radian is related to the angle between the component and the horizontal line.

[0008] The embodiment of the application can improve the speed and accuracy of product deformation and roughness detection by constructing a deformation and roughness prediction model based on metal additive manufacturing components and detecting the rationality of the inclination design of the local structure of the product through the model.Secondly, the embodiment of the application can quickly screen the prediction model that meets the characteristics of the current component to be tested by matching the feature information corresponding to the current component to be tested with a plurality of pre-set component features, so that the accuracy of the prediction model is higher.In addition, the embodiment of the application adjusts the inclination radian of the component to be tested based on the prediction result, optimizes the product structure design, provides technical support for realizing additive manufacturing without process support or with less support, improves process yield, and reduces production cost.

[0009] In one implementation of the application, a set of additive manufacturing product performance prediction models based on inclination radian is constructed based on a plurality of pre-set component features, specifically including: determining a plurality of pre-set component features currently required;Wherein, the pre-set component feature is related to the size data of the component;Different product performance prediction model templates are constructed based on the combination of different pre-set component features;A set of additive manufacturing product performance prediction models based on inclination radian is constructed based on different pre-set component feature parameters and product performance prediction model templates.

[0010] In one implementation of the application, different product performance prediction model templates are constructed based on different pre-set component feature combinations, specifically including: constructing a function

[0011] f D (x)=Aln x +B

[0012] constructing a part deformation prediction model template; wherein, x is the local structure inclination angle radian of the part; A and B are obtained by fitting the radian-deformation change data corresponding to parts of different sizes; and based on the function

[0013] f R (x)=Hx E

[0014] constructing a part roughness prediction model template; wherein, x is the local structure inclination angle radian of the part; H and E are obtained by fitting the radian-roughness change data corresponding to parts of different sizes.

[0015] In an implementation manner of the present application, based on different preset part characteristic parameters, a product performance prediction model set based on inclination angle radian is constructed by using a product performance prediction model template, and specifically includes: determining a reference preset part characteristic parameter to be used for model construction; determining a corresponding reference product performance prediction model based on part characteristics corresponding to the reference preset part characteristic parameter; inputting the reference preset part characteristic parameter into the reference product performance prediction model template to construct a product performance prediction model corresponding to the reference preset part characteristic parameter; and assembling the product performance prediction model set based on inclination angle radian by using product performance prediction models corresponding to different reference preset part characteristic parameters.

[0016] In an implementation manner of the present application, based on basic information of a part to be measured, characteristic information corresponding to the part to be measured is determined, and specifically includes: determining basic information of the part to be measured; wherein, the basic information at least includes one of a name of the part to be measured, size information of the part to be measured, structure information of the part to be measured, and process parameter information of the part to be measured; finding matched characteristic information in a preset characteristic information database based on the basic information; wherein, the characteristic information at least includes one of part inclination angle radian, part thickness, and part width; wherein, the preset characteristic information database includes multiple basic information and characteristic information corresponding to the multiple basic information.

[0017] In an implementation manner of the present application, the characteristic information corresponding to the part to be measured is matched with multiple preset part characteristics to determine a reference prediction model meeting the requirements of the part to be measured in the product performance prediction model set based on inclination angle radian, and specifically includes: determining a characteristic keyword corresponding to the characteristic information corresponding to the part to be measured; querying multiple reference part characteristics matching the characteristic keyword in the multiple preset part characteristics; taking the multiple reference part characteristics as a characteristic set; and determining a reference prediction model matching the characteristic set in the product performance prediction model set based on inclination angle radian based on the characteristic set.

[0018] In an implementation form of the present application, the deformation and / or roughness of the to-be-tested part is predicted based on the reference prediction model, specifically including: inputting the inclination radian of the current to-be-tested part into the reference deformation prediction model to obtain the predicted deformation of the part on the down-sloping surface corresponding to the to-be-tested part; and / or inputting the inclination radian of the current to-be-tested part into the reference roughness prediction model to obtain the predicted roughness of the part on the down-sloping surface corresponding to the to-be-tested part.

[0019] In an implementation form of the present application, the inclination radian of the to-be-tested part is adjusted based on the prediction result to make the deformation and roughness of the to-be-tested part meet the requirements, specifically including: adjusting the inclination radian in the case that the predicted deformation of the part on the down-sloping surface is not less than the first preset deformation threshold; or adjusting the inclination radian in the case that the predicted roughness of the part on the down-sloping surface is not less than the preset roughness threshold.

[0020] The embodiment of the present application provides a kind of additive manufacturing product performance regulation equipment, including: at least one processor;And, at least one processor communication connection of memory;Wherein, memory stores the instruction that can be executed by at least one processor, instruction is executed by at least one processor, to enable at least one processor can:based on multiple preset part features, construct the inclination radian-based additive manufacturing product performance prediction model set;Wherein, inclination radian-based additive manufacturing product performance prediction model includes, deformation prediction model and roughness prediction model;Based on the basic information of current to-be-tested part, the feature information corresponding to current to-be-tested part is determined;Current to-be-tested part corresponding feature information is matched with multiple preset part features, to determine the reference prediction model that meets the demand of to-be-tested part in inclination radian-based additive manufacturing product performance prediction model set;Based on reference prediction model, deformation and / or roughness of to-be-tested part is predicted;Based on prediction result, the inclination radian of to-be-tested part is adjusted, to make the deformation and roughness of to-be-tested part meet the requirements;Wherein, inclination radian is related to the angle between part and horizontal line.

[0021] The nonvolatile computer storage medium provided by the embodiment of the application stores computer executable instructions, and the computer executable instructions are configured to: based on a plurality of preset part features, construct a set of additive manufacturing product performance prediction models based on an inclination angle radian; wherein the additive manufacturing product performance prediction model based on the inclination angle radian includes a deformation amount prediction model and a roughness prediction model; based on basic information of a current part to be tested, determine feature information corresponding to the current part to be tested; match the feature information corresponding to the current part to be tested with the plurality of preset part features, so as to determine a reference prediction model meeting the requirements of the part to be tested from the set of additive manufacturing product performance prediction models based on the inclination angle radian; based on the reference prediction model, perform deformation amount prediction and / or roughness prediction on the part to be tested; and based on the prediction result, adjust the inclination angle radian of the part to be tested, so that the deformation amount and the roughness of the part to be tested meet the requirements; wherein the inclination angle radian is related to an angle between the part and a horizontal line.

[0022] The above at least one technical solution adopted by the embodiment of the application can achieve the following beneficial effects: by constructing a metal additive manufacturing part deformation amount and roughness prediction model, the embodiment of the application can improve the speed and accuracy of product deformation amount and roughness detection by detecting the rationality of the product local structure inclination angle design through the model. Secondly, by matching the feature information corresponding to the current part to be tested with the plurality of preset part features, the embodiment of the application can quickly screen out a prediction model meeting the feature of the current part to be tested, so that the accuracy of the prediction model is higher. In addition, the embodiment of the application adjusts the inclination angle radian of the part to be tested based on the prediction result, optimizes the product structure design, provides technical support for realizing process support-free or less support additive manufacturing, improves the process yield, and reduces the production cost. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0024] Figure 1 A flow chart of an additive manufacturing product performance regulation method is provided for the embodiment of the present application;

[0025] Figure 2 A process flow of metal additive product deformation amount and roughness prediction and structure optimization based on an inclination angle radian is provided for the embodiment of the present application;

[0026] Figure 3A schematic diagram of an additive manufacturing deformation amount prediction model provided for an embodiment of the present application is shown in FIG. 1.

[0027] Figure 4 A schematic diagram of an additive manufacturing roughness prediction model provided for an embodiment of the present application is shown in FIG. 2.

[0028] Figure 5 A structural schematic diagram of an additive manufacturing product performance regulation device provided for an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0029] An additive manufacturing product performance regulation method, device and medium are provided in the embodiments of the present application.

[0030] In order to enable persons skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0031] The technical solutions proposed in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0032] Figure 1 A flowchart of an additive manufacturing product performance regulation method provided for an embodiment of the present application is shown in FIG. 4. As shown in FIG. 4, the additive manufacturing product performance regulation method comprises the following steps: Figure 1

[0033] S101, based on a plurality of preset component features, an additive manufacturing product performance prediction model set based on inclination radian is constructed.

[0034] In an embodiment of the present application, the additive manufacturing product performance prediction model based on inclination radian comprises a deformation amount prediction model and a roughness prediction model.

[0035] In an embodiment of the present application, a plurality of preset component features required at present are determined, wherein the preset component features are related to size data of the component. Different product performance prediction model templates are constructed based on combination of different preset component features. The additive manufacturing product performance prediction model set based on inclination radian is constructed based on different preset component feature parameters and the product performance prediction model template.

[0036] ​Specifically, according to product requirements, feature extraction is performed on different to-be-tested parts to obtain a plurality of preset part features corresponding to different parts respectively. The plurality of preset part features at least include one or more of an inclination angle of the part, a thickness of the part, and a width of the part.

[0037] It should be noted that in the application, the required part features can be increased or reduced according to actual needs, and the embodiments of the present application do not limit this.

[0038] Further, different preset part features are combined, for example, the inclination angle and the thickness are combined, or the inclination angle and the width are combined, to obtain a product performance prediction model template corresponding to each feature combination. Different product performance prediction models can be constructed by inputting different preset part feature parameters into the corresponding product performance prediction model template, thereby obtaining the additive manufacturing product performance prediction model set based on the inclination angle radian.

[0039] In an embodiment of the present application, based on the function

[0040] f D (x) = Aln x +B

[0041] A deformation prediction model template of the part is constructed. Wherein, x is the local structure inclination angle radian of the part; A and B are obtained by fitting the radian-deformation change data corresponding to parts of different sizes.

[0042] And, based on the function

[0043] f R (x) = Hx E

[0044] A part roughness prediction model template is constructed. Wherein, x is the local structure inclination angle radian of the part; H and E are obtained by fitting the radian-roughness change data corresponding to parts of different sizes.

[0045] Specifically, based on different model templates, data analysis is performed to obtain trend change graphs between the radian and the deformation amount corresponding to different model templates, and to obtain a trend change graph between the radian and the deformation amount. For example, a model template corresponding to a feature of a part composed of an inclination angle and a thickness is given corresponding parameters of the inclination angle and the thickness, and a corresponding trend change graph between the radian and the deformation amount and a trend change graph between the radian and the roughness can be obtained. According to the drawn change graph, a prediction correlation mathematical model of the metal additive manufacturing part deformation amount and the roughness of the local structure inclination angle radian of the part can be fitted to obtain the corresponding prediction model under the parameter. The corresponding correlation mathematical model of the thickness is changed, and part of the data of the corresponding correlation mathematical model is changed accordingly. Through the law, the change rule of the mathematical model with the change of the thickness can be obtained, so that the corresponding correlation mathematical model under the thickness parameter can be directly calculated based on the corresponding model template according to the law under the condition of obtaining different thickness parameters.

[0046] In an embodiment of the present application, a reference preset part feature parameter to be currently constructed is determined. Based on the reference preset part feature corresponding to the reference preset part feature parameter, a corresponding reference product performance prediction model template is determined. The reference preset part feature parameter is input into the reference product performance prediction model template to construct a product performance prediction model corresponding to the reference preset part feature parameter. Through the product performance prediction models respectively corresponding to different reference preset part feature parameters, an additive manufacturing product performance prediction model set based on inclination angle radian is established.

[0047] Specifically, based on the characteristics of the product to be tested, the reference preset part feature needed is determined, and the reference preset part feature parameter respectively corresponding to the reference preset part feature is determined. Based on the reference preset part feature, a corresponding reference product performance prediction model template is determined. The reference preset part feature parameter is input into the reference product performance prediction model template to obtain the product performance prediction model corresponding to the reference preset part feature parameter. Through different product performance prediction models respectively corresponding to different parameters, the additive manufacturing product performance prediction model set based on inclination angle radian can be established.

[0048] S102, based on the basic information of the current part to be tested, the feature information corresponding to the current part to be tested is determined.

[0049] In an embodiment of the present application, the basic information of the current to-be-tested part is determined, wherein the basic information at least includes one of the name of the to-be-tested part, the size information of the to-be-tested part, the structure information of the to-be-tested part, and the process parameter information of the to-be-tested part. Based on the basic information, the matching feature information is found in the preset feature information database, wherein the feature information at least includes one of the part inclination radian, the part thickness, and the part width. The preset feature information database includes a plurality of basic information, and also includes the feature information corresponding to each basic information.

[0050] Specifically, the basic information of the current to-be-tested part is determined, that is, the name, size information, structure information, and process parameter of the to-be-tested part are determined, and different information can be used to determine the to-be-tested part. Further, based on the basic information, the matching feature information can be found in the preset feature information database, that is, the feature information consistent with the basic information of the current to-be-tested part is found in the feature information database. The preset feature information database includes a plurality of basic information, and also includes the feature information corresponding to each basic information.

[0051] S103, the feature information corresponding to the current to-be-tested part is matched with a plurality of preset part features to determine the reference prediction model meeting the demand of the to-be-tested part in the set of additive manufacturing product performance prediction models based on inclination radian.

[0052] In an embodiment of the present application, the feature keyword corresponding to the feature information of the current to-be-tested part is determined. In a plurality of preset part features, a plurality of reference part features matching the feature keyword are found. The plurality of reference part features are taken as a feature set. Based on the feature set, the reference prediction model matching the feature set is determined in the set of additive manufacturing product performance prediction models based on inclination radian.

[0053] Specifically, the feature keyword corresponding to the feature information of the current to-be-tested part is determined, which can be an angle, a width, and a thickness in the feature information. In the preset part feature, a plurality of reference part features corresponding to the feature keyword are found, and the found reference part features are marked. The marked reference part features are taken as a feature set. Based on the plurality of features in the feature set, the product performance prediction model consistent with the current feature set is determined in the set of additive manufacturing product performance prediction models based on inclination radian, and is taken as the reference prediction model matching the feature set.

[0054] S104, based on the reference prediction model, the deformation amount prediction and / or the roughness prediction of the to-be-tested part are performed.

[0055] In an embodiment of the present application, the inclination radian of the current to-be-tested part is input into the reference deformation prediction model to obtain the part down-slope surface predicted deformation of the to-be-tested part. And / or the inclination radian of the current to-be-tested part is input into the reference roughness prediction model to obtain the part down-slope surface predicted roughness of the to-be-tested part.

[0056] Specifically, the obtained reference prediction model includes the reference deformation prediction model and the reference roughness prediction model. The inclination radian of the current to-be-tested part is input into the reference deformation prediction model, and the corresponding predicted deformation can be output through the reference deformation prediction model. The inclination radian of the current to-be-tested part is input into the reference roughness prediction model, and the corresponding predicted roughness can be output through the reference roughness prediction model.

[0057] S105, based on the prediction result, adjusting the inclination radian of the to-be-tested part to make the deformation and roughness of the to-be-tested part meet the requirements; wherein the inclination radian is related to the angle between the part and the horizontal line.

[0058] In an embodiment of the present application, the inclination radian is adjusted when the part down-slope surface predicted deformation is not less than the first preset deformation threshold. Or the inclination radian is adjusted when the part down-slope surface predicted roughness is not less than the preset roughness threshold.

[0059] For example, when the inclination radian ≥ 0.7, the inclination ≥ 40°, the deformation ≥ 150 μm, the deformation is large; when the inclination radian ≥ 0.7, the inclination ≥ 40°, the roughness ≥ 75 μm, the roughness is large. At this time, the inclination radian can be adjusted downward to make the deformation and roughness meet the requirements.

[0060] Figure 2 A metal additive product deformation and roughness prediction and structure optimization process based on inclination radian is provided for the embodiments of the present application. As shown in Figure 2

[0061] Structure design: develop product structure design for additive manufacturing. Product design includes topology optimization design, meso-structure design, and part integration design. Topology optimization design can find the best material distribution scheme in the design space of part material, thereby improving material utilization to reduce weight. Meso-structure refers to a unit cell with a feature size of 0.1-10 mm arranged in a specific way, which not only has a high strength-to-mass ratio or stiffness-to-mass ratio, but also has energy absorption, heat dissipation, sound insulation. Part integration design and manufacturing provides an optimized space for part design.

[0062] ​Process arrangement: arrange the number and placement direction of parts in the additive manufacturing forming cavity, focus on the inclination area not to design process support, and realize free state to achieve process support structure design without process support.

[0063] Process parameter design: carry out process parameter design such as laser power, laser speed, scanning interval, printing layer thickness, scanning strategy, substrate preheating temperature, etc.

[0064] Process simulation: for the designed additive manufacturing (SLM) model. First, according to the product structure characteristics, set the arrangement direction and inclination angle of the parts; then design the process support, and design the dendritic support and zigzag support according to the product structure characteristics. Finally, considering the product material types and additive printing machine types, design the process parameters such as laser power, laser speed, scanning interval, printing layer thickness, scanning strategy, substrate preheating temperature, etc. Finally, process simulation is carried out, and the deformation distribution is obtained, and the quantitative record is analyzed, the deformation result Total displacement is analyzed, the deformation value of the concerned area is displayed on the deformation result interface of the part surface by using the dotting method, and the mathematical relationship model of the inclination radian and the deformation is analyzed by using the statistical method.

[0065] Through the constructed model, the deformation and roughness are analyzed to adjust the product to meet the product delivery specifications.

[0066] Figure 3 A kind of additive manufacturing deformation prediction model provided in the embodiment of the application is shown in the schematic diagram of the application. Figure 3 As shown, the abscissa is radian, and the ordinate is deformation. Based on different radian, the deformation is different. Figure 4 A kind of additive manufacturing roughness prediction model provided in the embodiment of the application is shown in the schematic diagram of the application. Figure 4 As shown, the abscissa is radian, and the ordinate is roughness. Based on different radian, the roughness is different. Table 1 is the deformation data statistical situation of the verification embodiment:

[0067] Angle of inclination (°) 50 45 40 35 30 Angle of inclination (rad) 0.87 0.79 0.70 0.61 0.52 Amount of deformation (pm) 110 140 150 170 190

[0068] Table 1

[0069] Table 2 is the roughness data statistical situation of the verification embodiment:

[0070] Serial number Angle (°) Angle (rad) Roughness measurement (pm) 1 180 3.14 28.62 2 50 0.87 45.7 3 45 0.79 60.88 4 40 0.70 75.23 5 35 0.61 98.4 6 30 0.52 310.89 7 25 0.44 333.78 8 20 0.35 346.03 9 0 0.00 399.99

[0071] Table 2

[0072] From the data in Figure 3 and Figure 4 , the prediction correlation mathematical model of the metal additive manufacturing part deformation and roughness based on the local structure inclination radian of the part can be obtained:

[0073] f D (x) = -145.6ln x + 97.276 R 2 = 0.9633;

[0074] f R (x) = 73.099x -1.249 R 2 = 0.723;

[0075] In the formula:

[0076] x: local structure inclination angle of the part, rad;

[0077] f D (x): deformation of the downward-inclined surface of the part, μm;

[0078] f R (x): roughness of the downward-inclined surface of the part, μm;

[0079] When x: inclination angle rad≥0.7, inclination angle≥40°, f D (x)≥150μm, the deformation is large;

[0080] When x: inclination angle rad≥0.7, inclination angle≥40°, f R (x)≥75μm, the roughness is large;

[0081] Therefore: to control the deformation and roughness, the inclination angle rad needs to be controlled to be≤0.7, and the inclination angle≤40°.

[0082] Figure 5 A structural schematic diagram of an additive manufacturing product performance regulation device provided by the embodiment is shown in FIG. 1. Figure 5As shown, the additive manufacturing product performance regulation device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: based on a plurality of preset part features, construct a set of additive manufacturing product performance prediction models based on inclination radian; wherein the additive manufacturing product performance prediction model based on inclination radian comprises a deformation prediction model and a roughness prediction model; based on the basic information of the current to-be-tested part, determine the feature information corresponding to the current to-be-tested part; match the feature information corresponding to the current to-be-tested part with the plurality of preset part features, to determine a reference prediction model meeting the requirements of the to-be-tested part in the set of additive manufacturing product performance prediction models based on inclination radian; based on the reference prediction model, perform deformation prediction and / or roughness prediction on the to-be-tested part; based on the prediction result, adjust the inclination radian of the to-be-tested part, so that the deformation and roughness of the to-be-tested part meet the requirements; wherein the inclination radian is related to the angle between the part and the horizontal line.

[0083] The embodiments of the present application also provide a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured to: based on a plurality of preset part features, construct a set of additive manufacturing product performance prediction models based on inclination radian; wherein the additive manufacturing product performance prediction model based on inclination radian comprises a deformation prediction model and a roughness prediction model; based on the basic information of the current to-be-tested part, determine the feature information corresponding to the current to-be-tested part; match the feature information corresponding to the current to-be-tested part with the plurality of preset part features, to determine a reference prediction model meeting the requirements of the to-be-tested part in the set of additive manufacturing product performance prediction models based on inclination radian; based on the reference prediction model, perform deformation prediction and / or roughness prediction on the to-be-tested part; based on the prediction result, adjust the inclination radian of the to-be-tested part, so that the deformation and roughness of the to-be-tested part meet the requirements; wherein the inclination radian is related to the angle between the part and the horizontal line.

[0084] Each of the embodiments in the present application is described in a progressive manner, and the same and similar parts of each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0085] The above merely describes the embodiments of the present application, and is not intended to limit the present application. The embodiments of the present application can be variously changed and modified by those skilled in the art. Any modification or replacement does not cause the corresponding technical solution to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of performance tuning of an additively manufactured product, characterized in that, The method comprises: Based on a plurality of pre-set component characteristics, a set of additive manufacturing product performance prediction models based on inclination radian is constructed; wherein the additive manufacturing product performance prediction model based on inclination radian comprises a deformation prediction model and a roughness prediction model; Based on the basic information of the current component to be tested, the characteristic information corresponding to the current component to be tested is determined; The characteristic information corresponding to the current component to be tested is matched with the plurality of pre-set component characteristics to determine the reference prediction model that meets the requirements of the component to be tested in the set of additive manufacturing product performance prediction models based on inclination radian; Based on the reference prediction model, the deformation and / or roughness of the component to be tested is predicted; Based on the prediction result, the inclination radian of the component to be tested is adjusted to make the deformation and roughness of the component to be tested meet the requirements; wherein the inclination radian is related to the angle between the component and the horizontal line.

2. The method of claim 1, wherein, The set of additive manufacturing product performance prediction models based on inclination radian is constructed based on a plurality of pre-set component characteristics, specifically comprising: A plurality of pre-set component characteristics required at present are determined; wherein the pre-set component characteristics are related to the size data of the component; Different product performance prediction model templates are constructed based on the combination of different pre-set component characteristics; Based on different pre-set component characteristic parameters, the set of additive manufacturing product performance prediction models based on inclination radian is constructed with the product performance prediction model template.

3. The method of claim 2, wherein, The different product performance prediction model templates are constructed based on the combination of different pre-set component characteristics, specifically comprising: Based on the function f D (x) = Aln x +B A component deformation prediction model template is constructed; wherein x is the local structure inclination radian of the component; A and B are fitted from the radian-deformation change data corresponding to different sizes of components; and Based on the function f R (x) = Hx E A component roughness prediction model template is constructed; wherein x is the local structure inclination radian of the component; H and E are fitted from the radian-roughness change data corresponding to different sizes of components.

4. The method of claim 3, wherein, The set of additive manufacturing product performance prediction models based on inclination radian is constructed based on different pre-set component characteristic parameters and the product performance prediction model template, specifically comprising: The reference pre-set component characteristic parameters for model construction at present are determined; Based on the component characteristics corresponding to the reference pre-set component characteristic parameters, the corresponding reference product performance prediction model template is determined; The reference pre-set component characteristic parameters are input into the reference product performance prediction model template to construct the product performance prediction model corresponding to the reference pre-set component characteristic parameters; The set of additive manufacturing product performance prediction models based on inclination radian is constructed through the product performance prediction models corresponding to different reference pre-set component characteristic parameters respectively.

5. The method of claim 1, wherein, The characteristic information corresponding to the current component to be tested is determined based on the basic information of the current component to be tested, specifically comprising: Determine the basic information of the current to-be-tested part; wherein the basic information at least includes one of the name of the to-be-tested part, the size information of the to-be-tested part, the structure information of the to-be-tested part and the process parameter information of the to-be-tested part; Based on the basic information, find the matching feature information in the preset feature information database; wherein the feature information at least includes one of the part inclination angle radian, the part thickness and the part width; Wherein, the preset feature information database includes a plurality of basic information, and also includes the feature information corresponding to the plurality of basic information respectively.

6. The method of claim 1, wherein, The feature information corresponding to the current to-be-tested part is matched with the plurality of preset part features to determine the reference prediction model meeting the demand of the to-be-tested part in the inclination angle radian-based additive manufacturing product performance prediction model set, specifically including: Determine the feature keywords corresponding to the feature information of the current to-be-tested part; In the plurality of preset part features, a plurality of reference part features matching the feature keywords are queried; The plurality of reference part features are taken as a feature set; Based on the feature set, a reference prediction model matching the feature set is determined in the inclination angle radian-based additive manufacturing product performance prediction model set.

7. The method of claim 1, wherein, The reference prediction model is used to predict the deformation and / or roughness of the to-be-tested part, specifically including: The inclination angle radian of the current to-be-tested part is input into the reference deformation prediction model to obtain the part downward inclination surface predicted deformation of the to-be-tested part; and / or The inclination angle radian of the current to-be-tested part is input into the reference roughness prediction model to obtain the part downward inclination surface predicted roughness of the to-be-tested part.

8. The method of claim 1, wherein, Based on the prediction result, the inclination angle radian of the to-be-tested part is adjusted to make the deformation and roughness of the to-be-tested part meet the requirements, specifically including: In the case that the part downward inclination surface predicted deformation is not less than the first preset deformation threshold, the inclination angle radian is adjusted; or In the case that the part downward inclination surface predicted roughness is not less than the preset roughness threshold, the inclination angle radian is adjusted.

9. An additive manufacturing product performance regulation device, comprising: at least one processor; and, a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: based on a plurality of preset part features, construct an inclination angle radian-based additive manufacturing product performance prediction model set; wherein the inclination angle radian-based additive manufacturing product performance prediction model includes a deformation prediction model and a roughness prediction model; based on the basic information of the current to-be-tested part, determine the feature information corresponding to the current to-be-tested part; The characteristic information corresponding to the current to-be-tested part is matched with the plurality of preset part characteristics to determine a reference prediction model meeting the requirements of the to-be-tested part from the set of the inclination radian-based additive manufacturing product performance prediction models; Based on the reference prediction model, deformation and / or roughness of the to-be-tested part is predicted; Based on the prediction result, the inclination radian of the to-be-tested part is adjusted so that the deformation and the roughness of the to-be-tested part meet the requirements; wherein the inclination radian is related to the angle between the part and the horizontal line. 10.A non-volatile computer storage medium storing computer executable instructions, the computer executable instructions being configured to: Based on a plurality of pre-set component characteristics, a set of performance prediction models for additive manufacturing products based on the inclination radian is constructed; wherein, The inclination radian-based additive manufacturing product performance prediction model comprises a deformation prediction model and a roughness prediction model; Based on the basic information of the current to-be-tested part, the characteristic information corresponding to the current to-be-tested part is determined; The characteristic information corresponding to the current to-be-tested part is matched with the plurality of preset part characteristics to determine a reference prediction model meeting the requirements of the to-be-tested part from the set of the inclination radian-based additive manufacturing product performance prediction models; Based on the reference prediction model, deformation and / or roughness of the to-be-tested part is predicted; Based on the prediction result, the inclination radian of the to-be-tested part is adjusted so that the deformation and the roughness of the to-be-tested part meet the requirements; wherein the inclination radian is related to the angle between the part and the horizontal line.

Images