Process compensation method and system for characteristic evolution of additive manufacturing recovery powder

Abstract

The invention relates to a process compensation method and system for characteristic evolution of recycled powder in additive manufacturing, and the method comprises the steps: carrying out component forming on powder with different recycling times and new powder proportions, carrying out characteristic detection on the recycled powder and a formed component, and building a decay relation between the recycling times and powder characteristic parameters; calculating a fluidity attenuation coefficient, a heat absorption attenuation rate and a satellite powder proportion amplification coefficient according to the decay relationship, and constructing a compensation strategy of a scanning task; in the process of executing the additive manufacturing scanning task, a compensation strategy is triggered every preset layer number, compensation process parameters are generated based on the current recycling times, and meanwhile the optimal new powder proportion is predicted through a machine learning decision model; and the compensation parameters and the new powder proportion are input into additive manufacturing equipment to be executed. The powder characteristic decay rule can be accurately quantified under the powder recycling condition, and a dynamic matching compensation mechanism with the process parameters is established, so that the forming quality is effectively guaranteed, defects are reduced, and the utilization rate of recycled powder is increased.

Description

Technical Field

[0001] This application relates to the field of additive manufacturing technology, and more specifically to a process compensation method and system for the evolution of properties of recycled powder in additive manufacturing. Background Technology

[0002] In recent years, with the rapid increase in demand for integrated and lightweight manufacturing of high-performance complex components in new-generation aerospace equipment, powder bed fusion (PBF) technology has become increasingly widely used in the integrated and lightweight manufacturing of high-end aerospace equipment due to its ability to achieve high-performance forming of highly complex components. However, due to the dynamic powder spreading and local rapid solidification of powder layers, the characteristics of powder raw materials and their process compatibility are particularly important for improving the process effect and product quality of PBF technology. In particular, powder characteristics such as particle flowability, particle morphology, and surface properties significantly affect heat and mass transfer processes such as powder bed laying and molten pool metallurgical solidification and cooling.

[0003] Currently, in actual production, metal powders typically need to be recycled multiple times. However, with the increase in the number of recycling cycles, the oxide film on the powder surface gradually thickens, the proportion of satellite powder and the hollow powder ratio increase, leading to decreased powder flowability (manifested as an increase in Hall flow rate), reduced thermal absorption rate, and insufficient density. These deterioration effects not only affect the powder bed quality but also exacerbate the risk of insufficient or over-melting energy input to the laser molten pool, ultimately resulting in a decline in the quality of the formed components. Summary of the Invention

[0004] This application provides a process compensation method and system for the evolution of the properties of recycled powder in additive manufacturing. It can accurately quantify the decay law of powder properties with the number of recycling cycles under cyclic use conditions, and then establish a dynamic matching compensation mechanism between the decay law and process parameters, thereby ensuring the forming quality of the formed components and improving the utilization rate of recycled powder.

[0005] In a first aspect, this application provides a process compensation method for the evolution of characteristics of recycled powder in additive manufacturing. The method includes: forming components from powder with different recycling times and new powder ratios, and performing characteristic testing on the recycled powder and components after forming, establishing a decay relationship between the recycling times and powder characteristic parameters; calculating the decay coefficient of the powder based on the decay relationship between the recycling times and powder characteristic parameters, and constructing a compensation strategy for the scanning task based on the decay coefficient, wherein the decay coefficient includes a flowability decay coefficient, a thermal absorption decay rate, and a satellite powder ratio amplification coefficient; during the execution of the additive manufacturing scanning task, triggering the compensation strategy every preset number of scanning layers to generate compensation process parameters based on the current recycling times, and simultaneously using a machine learning decision model to predict the new powder ratio corresponding to the optimal forming quality index for the current recycling times; and inputting the compensation process parameters and the new powder ratio into the additive manufacturing equipment for execution.

[0006] In one alternative of the first aspect, the characteristic testing of the recycled powder and components after molding includes: testing the flowability parameters of the powder using a Hall flowmeter test and a dynamic angle of repose test; testing the oxide film thickness and oxygen content parameters of the powder using X-ray photoelectron spectroscopy; measuring the surface roughness of the cladding layer of the component using a non-contact three-dimensional profilometer and measuring the density of the component using the water displacement method.

[0007] In one alternative embodiment of the first aspect, calculating the decay coefficient of the powder based on the decay relationship includes: calculating the flowability attenuation coefficient of the powder based on the decay relationship. ,in The number of recycling cycles; the thermal absorption decay rate of the powder is calculated based on the decay relationship: ,in, The energy beam absorption rate for the Nth recovery cycle. The energy beam absorptivity of the new powder; the satellite powder ratio amplification factor of the powder is calculated based on the decay relationship: ,in The proportion of satellite powder recovered in the Nth recovery cycle. This refers to the ratio of satellite powder to new powder.

[0008] In one alternative embodiment of the first aspect, the step of constructing a compensation strategy for the scanning task based on the decay coefficient includes: constructing a powder layer thickness increase strategy based on the fluidity decay coefficient, wherein the adjustment range formula for the powder layer thickness increase strategy is: ,in To increase the thickness of the powder layer, This is the liquidity decay coefficient. The powder layer thickness is used as a reference; an energy beam power enhancement strategy is constructed based on the aforementioned thermal absorption attenuation rate, and the adjustment range formula for the energy beam power enhancement strategy is as follows: ,in, To increase the power of the energy beam, The thermal absorption attenuation rate, The baseline energy beam power is used; a dust-spreading speed reduction strategy is constructed based on the satellite dust ratio amplification coefficient, and the adjustment range formula for the dust-spreading speed reduction strategy is as follows: ,in, To reduce the speed of powder application, This is the coefficient for increasing the proportion of satellite powder. The base powder spreading speed.

[0009] In one alternative of the first aspect, after constructing a compensation strategy for the scanning task based on the decay coefficient, the method includes: setting an adjustment threshold range of ±10μm in a powder layer thickness increase strategy; setting an adjustment threshold range of ±30W in an energy beam power increase strategy; and setting an adjustment threshold range of ±50mm / s in a powder layer speed reduction strategy.

[0010] In one alternative of the first aspect, when the compensation strategy is triggered, the method includes: dividing the forming area of ​​the additively manufactured component into sub-regions according to the scanning path of the scanning task to form multiple partitions; obtaining the number of powder recycling times for each partition and independently calculating the flowability attenuation coefficient, thermal absorption attenuation rate, and satellite powder ratio amplification coefficient of the powder in each partition; and independently executing a corresponding powder layer thickness increase strategy and / or energy beam power increase strategy and / or powder layer speed reduction strategy for each partition.

[0011] In one alternative of the first aspect, when constructing the compensation strategy for the scanning task, the method further includes: collecting a first preset number of sample parameters such as the number of recycling attempts, the proportion of new powder, powder characteristic parameters, and the surface roughness and density of the corresponding components, and constructing a dataset; using machine learning methods to iteratively train the dataset to construct a machine learning decision model, wherein the iterative training process includes: taking the number of recycling attempts and powder characteristic parameters as inputs, taking the forming quality index and the proportion of new powder as outputs, and setting constraints.

[0012] In one alternative of the first aspect, the construction of the dataset includes: generating a second preset number of new sample parameters for two adjacent sample parameters; using linear interpolation to calculate the proportion of new powder, the surface roughness and density of the corresponding components for the new sample parameters, while adding small-amplitude Gaussian noise to simulate experimental measurement errors, and constructing enhanced sample parameters; adding the constructed enhanced sample parameters to the dataset to form an enhanced dataset, and dividing the dataset into a training set and a test set according to a preset ratio using a random shuffling indexing method.

[0013] In one alternative of the first aspect, the construction of the machine learning decision model includes: using an input data standardization method to eliminate dimensional differences in the enhanced dataset; setting the kernel function of the machine learning decision model as a radial basis function; and setting the constraint condition as maximizing the proportion of recycled powder while ensuring that the surface roughness of the component cladding layer does not exceed a preset value.

[0014] Secondly, this application provides a process compensation method system for the evolution of characteristics of recycled powder in additive manufacturing using the method according to any one of the first aspects, comprising: a decay construction module for forming components from powder with different recycling times and new powder ratios, and performing characteristic detection on the recycled powder and components after forming, and establishing a decay relationship between the recycling times and powder characteristic parameters; a strategy construction module for calculating the decay coefficient of the powder based on the decay relationship between the recycling times and powder characteristic parameters, and constructing a compensation strategy for the scanning task based on the decay coefficient, wherein the decay coefficient includes a flowability decay coefficient, a thermal absorption decay rate, and a satellite powder ratio amplification coefficient; a process compensation module for triggering the compensation strategy every preset number of scanning layers during the execution of the additive manufacturing scanning task, so as to generate compensation process parameters based on the current recycling times; a machine learning module for constructing a machine learning decision model and using the machine learning decision model to predict the optimal recycled powder ratio corresponding to the current recycling times; and an execution control module for inputting the compensation process parameters and the optimal recycled powder ratio into the additive manufacturing equipment for execution.

[0015] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0016] The accompanying drawings, which are incorporated herein and form part of this specification, illustrate one or more embodiments of the present application and, together with the description, serve to explain the principles of the present application and to enable those skilled in the art to make and use the present application.

[0017] Figure 1 This is a schematic flowchart of an exemplary additive manufacturing process for compensating for the evolution of characteristics of recycled powder, according to some embodiments of this application.

[0018] Figure 2 This is a schematic diagram of the structure of an exemplary three-dimensional profilometer according to some embodiments of this application.

[0019] Figure 3 This is a schematic flowchart of an exemplary method for calculating the decay coefficient of powder according to some embodiments of this application.

[0020] Figure 4 This is a flowchart illustrating an exemplary SVM model construction method according to some embodiments of this application.

[0021] Figure 5 This is a schematic diagram of the optimization graph of an exemplary SVM model according to some embodiments of this application.

[0022] Figure 6 This is an exemplary schematic diagram of the surface cladding quality of uncompensated recycled powder with different number of cycles according to some embodiments of this application, wherein (a) to (j) represent 1 to 10 cycles, respectively.

[0023] Figure 7 This is an exemplary schematic diagram of the surface cladding quality of 40% of the compensated recycled powder with different number of cycles according to some embodiments of this application, wherein (a) to (j) represent the number of cycles 1 to 10, respectively.

[0024] Figure 8 This is an exemplary schematic diagram of the surface cladding quality of the compensated recycled powder with different number of cycles according to some embodiments of this application, wherein (a) to (j) represent the number of cycles from 1 to 10, respectively.

[0025] Figure 9 This is an exemplary schematic diagram of the surface cladding quality of 60% of the compensated recycled powder with different number of cycles according to some embodiments of this application, wherein (a) to (j) represent 1 to 10 cycles respectively.

[0026] Figure 10 This is an electron microscope schematic diagram of the powder particle morphology from uncompensated recovered powder to 60% compensated recovered powder at different cycles, according to some embodiments of this application.

[0027] Figure 11 This is an exemplary schematic diagram of the morphology of a component sample measured by a three-dimensional optical profilometer according to some embodiments of this application; wherein, (a) is the boundary between the substrate and the cladding layer, (b) is the surface profile in the X direction, and (c) is the surface profile in the Y direction.

[0028] Figure 12 This is a schematic flowchart of an exemplary partition compensation method according to some embodiments of this application.

[0029] Figure 13 This is a schematic diagram of the module connections of an exemplary additive manufacturing process compensation system for the evolution of characteristics of recycled powder, according to some embodiments of this application.

[0030] Figure 14 This is a schematic diagram of the connection of an exemplary electronic device according to some embodiments of this application. Detailed Implementation

[0031] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, the description of these embodiments is intended to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to provide a deeper understanding of embodiments of this application.

[0032] Powder bed fusion (PBF) is an additive manufacturing technology driven by energy beams such as laser beams or electron beams. It selectively melts metal or polymer powder materials layer by layer to create three-dimensional solid parts with complex geometries. PBF technology is particularly suitable for preparing metal components with high density, high precision, and complex structures, and is widely used in fields with extremely high performance requirements, such as aerospace, biomedicine, and energy.

[0033] Currently, depending on the energy source used, powder bed melting technology is mainly divided into several types, including Selective Laser Melting (SLM), Laser Powder Bed Fusion (L-PBF), Electron Beam Melting (EBM), and Selective Laser Sintering (SLS). The process flow of powder bed melting technology typically includes powder laying, energy beam scanning and melting, interlayer lifting, and post-processing. Specifically, a powder laying mechanism lays a layer of powder material with a thickness of tens to hundreds of μm on a forming platform to form a uniform powder bed. Then, based on the slicing data of the 3D component model, a laser beam or electron beam selectively scans, melts, and solidifies the current powder layer according to a pre-set scanning path, forming a solid cross-section. After scanning one layer, the forming platform descends by one layer thickness unit, laying the next layer of powder. This process is repeated to build layer by layer until the entire 3D component is completed. Once the component is finished, it is removed and undergoes post-processing steps such as heat treatment, support removal, and surface treatment to obtain the final product. The performance and quality of powder bed melting technology are affected by a variety of parameters, including energy beam power, scanning speed, scanning spacing, layer thickness, scanning strategy, and powder characteristics.

[0034] Powder properties affect the energy transfer mechanism of particle groups (powder beds) under the action of laser heat sources, thereby altering the cladding quality. The thermophysical properties of PBF powder layers, such as energy absorption rate and thermal conductivity, change with variations in powder layer packing density, specific surface area, and particle surface properties. Currently, numerical modeling techniques have been used to model and analyze the energy absorption and heat transfer behavior in PBF powder layers, providing a key theoretical foundation and excellent demonstration for revealing the interaction mechanism between high-energy beam heat sources and powders. However, most research discussions on powder properties are mainly limited to powder particle size distribution, thus their views still have certain limitations. In addition, after the powder melts under heat, it forms a highly dynamic moving molten pool, and its defect formation tendency changes with powder properties, resulting in different processing window ranges. Furthermore, the convective heat and mass transfer within the molten pool affects the temperature field at the solidification interface and influences solidification conditions (temperature gradient and solidification rate), thereby altering the final solidification microstructure characteristics. However, due to the difficulty in evaluating the thermal properties of powder beds and obtaining information on the cladding process, there is still a lack of in-depth understanding of the differences in energy transfer and phase transformation behavior of powder beds composed of powders with different properties under laser thermal interaction.

[0035] A uniform, dense, and continuous powder bed is an important prerequisite for ensuring the quality of PBF forming. Therefore, this application clarifies the control factors related to powder flow and dynamic powder spreading process stability, and establishes a correlation mechanism between powder characteristics such as particle flowability, particle morphology, and surface properties and powder recycling times and the proportion of new powder, providing an important reference for process parameter compensation.

[0036] Figure 1 This document illustrates a schematic flowchart of an exemplary process compensation method 10 for the evolution of properties of recycled additive manufacturing powder, based on some embodiments of this application. (Refer to...) Figure 1 The provided process compensation method 10 has the following steps 11 to 14.

[0037] 11: Components were formed from powders with different recycling times and new powder ratios, and the characteristics of the recycled powder and components were tested to establish the decay relationship between the recycling times and powder characteristic parameters.

[0038] In this application, metal powder is selected as the experimental material. Then, it is mixed with recycled powder according to a preset ratio of new powder to recycled powder (i.e., the proportion of new powder, such as 40%, 50%, and 60%), and additive manufacturing components are formed under different recycling times (N=1 to 10). Then, the recycled powder and the formed components are subjected to characteristic tests in sequence. Based on the experimental test results, the decay law between the number of recycling times and the powder characteristic parameters is established, including the relationship between powder flowability, energy absorption rate, satellite powder ratio, oxide film thickness and oxygen content, as well as the surface roughness and density of the component cladding layer, and the number of recycling times.

[0039] Specifically, in step 11, the characteristic detection includes detecting the powder's flowability parameters, oxide film thickness, oxygen content parameters, and the surface roughness and density of the component cladding layer.

[0040] Specifically, when testing the flowability parameters of the powder, a Hall effect flowmeter test and a dynamic angle of repose test are used. The specific implementation process of the Hall effect flowmeter is as follows.

[0041] (1) Place the Hall flow meter on a stable experimental platform and keep it horizontal. Then check whether the instrument funnel, nozzle and powder receiving tube are clean and free of residual powder, and confirm that the nozzle orifice diameter meets the standard (usually φ2.5mm±0.05mm).

[0042] (2) Take the powder sample to be tested (usually 50g); the powder sample to be tested should be dried at 105℃ for 1 hour and then cooled to room temperature, and then large impurities should be removed by using a standard sieve to ensure uniform powder particle size.

[0043] (3) Zero the weighing balance, prepare to record the time when the powder sample to be tested flows out, and confirm that the stopwatch can be used normally.

[0044] (4) Place the powder receiving tube below the funnel and ensure that it is centered. Then quickly pour the weighed powder sample into the funnel and start the stopwatch at the same time. After the powder flows out freely until it is completely finished, stop the timer and record the time taken (unit: seconds).

[0045] (5) Calculate the Hall flow velocity based on this. Where 50 represents the sample mass (g). The outflow time is in seconds.

[0046] The specific implementation process of this dynamic angle of repose test is as follows.

[0047] (1) Use a dynamic angle of repose measuring instrument, take 40g of the powder sample to be tested, and ensure that the powder sample to be tested is dry, free of lumps and impurities; if the powder sample to be tested is easily affected by static electricity, it should be operated in a dry environment.

[0048] (2) For a rotary dynamic angle of repose measuring instrument, set the cylinder rotation speed (exemplary, reference 25 rpm); for a vibrating device, set the vibration frequency and amplitude (exemplary, vibration frequency reference 50 Hz, amplitude reference 2 mm).

[0049] (3) Set the accumulation angle of the powder sample to be tested to be collected once per second; the accumulation angle of the powder sample to be tested can also be collected according to the sampling frequency required by the instrument.

[0050] (4) Pour the powder sample to be tested evenly into the measuring container or cylinder and gently shake the container to make the surface of the powder sample flat and avoid the initial tilt affecting the measurement; during the measurement process, ensure that the container is stable to prevent it from sliding or tipping over during the test.

[0051] (5) Start the running program of the dynamic angle of repose measuring instrument to make the powder sample to be tested gradually form a natural flow and accumulation state. The dynamic angle of repose measuring instrument records the change of the tilt angle formed by the accumulation of the powder sample to be tested over time through a sensor or high-speed camera system, thereby collecting and recording the accumulation angle of the powder sample to be tested during the dynamic angle of repose stabilization period.

[0052] (6) Take the average value of the angle of repose of the powder sample under steady flow as the dynamic angle of repose; wherein, each powder sample is repeated at least 3 times, the average value is taken and the standard deviation is calculated.

[0053] Specifically, when detecting the oxide film thickness and oxygen content parameters of the powder, X-ray photoelectron spectroscopy (XPS) is used to test the oxide film thickness and oxygen content parameters of the powder; the process of X-ray photoelectron spectroscopy testing of oxide film thickness and oxygen content is as follows.

[0054] (1) Select a representative powder sample to be tested and spread it gently on the conductive tape to ensure that the powder is evenly distributed and to minimize agglomeration; in order to avoid the powder sample to be tested from adsorbing moisture and organic pollution, the powder sample to be tested is pretreated in a vacuum drying oven before testing (for example, vacuum drying at 60°C for 0.5 to 3 hours).

[0055] (2) Test in ultra-high vacuum (~ The experiment was conducted in an environment of mbar, using monochromatic Al Kα rays (1486.6 eV) as the excitation source, with the spot diameter controlled at around 400 μm and the energy resolution set at 0.1 eV to ensure the resolution of fine spectral peaks.

[0056] (3) First, a full spectrum (Survey Scan) is performed to obtain the types and relative contents of the main elements on the surface of the powder sample to be tested. Then, high-resolution spectral (High-resolution Scan) tests are performed on the characteristic energy level regions such as O 1s, Ti 2p, and Ni 2p, and the oxygen in different valence states (such as lattice oxygen, hydroxyl oxygen, and adsorbed oxygen) are distinguished by peak fitting.

[0057] (4) Using the ratio of the peak intensity of the substrate metal to its oxide in XPS, combined with the corresponding electronic mean free path (IMFP) and geometric correction factor, the oxide film thickness is quantitatively estimated using an improved film thickness calculation model (such as the Tougaard or Beer–Lambert attenuation model).

[0058] (5) By integrating the O 1s spectrum peak and combining the sensitivity factor and relative correction factor, the oxygen element is quantitatively analyzed, thereby obtaining the average oxygen content of the oxide film on the surface of the powder sample to be tested.

[0059] (6) To improve accuracy, the C 1s peak (284.8 eV) was used as the binding energy calibration standard. At the same time, the background was subtracted by the Shirley method to eliminate secondary electron background interference. Thus, the thickness range of the oxide film and its oxygen content were finally obtained.

[0060] Specifically, when detecting the surface roughness and density of the cladding layer of a component, a non-contact three-dimensional profilometer is used to measure the surface roughness of the cladding layer, and the density of the component is measured using the drainage method; the style of the three-dimensional profilometer is referenced. Figure 2 As shown, Figure 2 A schematic diagram of the structure of an exemplary three-dimensional profilometer according to some embodiments of this application is shown.

[0061] The process of measuring the surface roughness of the cladding layer of a component using this non-contact three-dimensional profilometer is as follows.

[0062] (1) Select a non-contact 3D profilometer, such as a 3D optical profilometer.

[0063] (2) Perform horizontal calibration and height calibration of the non-contact three-dimensional profilometer according to the instrument instruction manual, and use standard roughness sample block or standard plate for measurement verification to ensure that the accuracy of the non-contact three-dimensional profilometer meets the experimental requirements.

[0064] (3) Wipe the surface of the component sample with a lint-free cloth and alcohol to remove surface oil, dust and particulate impurities.

[0065] (4) Place the component sample on the sample stage and fix it with a clamp or vacuum adsorption to ensure that it does not move during the measurement process.

[0066] (5) Set the maximum measurement field of view to 2.5×2mm, the Z-direction measurement range to 10nm~10mm, and to ensure measurement accuracy, select different areas of each component sample to measure its surface roughness 3 times.

[0067] (6) Start the scanning program of the non-contact three-dimensional profilometer. The non-contact three-dimensional profilometer acquires the three-dimensional height information of the component sample surface along the specified path. Confirm that there are no obvious missing or abnormal points during the scanning process, and repeat the scan if necessary.

[0068] (7) Select the appropriate filter length according to the standard (e.g., ISO 4287 / 4288) to separate roughness and ripple.

[0069] (8) Calculate the surface roughness parameters of the component sample. Based on the three-dimensional height information of the component sample surface, calculate the average roughness of the entire component sample surface, calculate the root mean square value of the height of the entire component sample surface, and calculate the height difference between the highest and lowest points of the entire component sample surface. Then, perform three measurements and calculations on different areas of each component sample and calculate the average value and standard deviation of the three measurement results. Record the final surface roughness parameters of the component sample in this way.

[0070] The density of each component sample was determined by measuring it five times using the water displacement method and taking the average value as the density of the component sample.

[0071] In the actual implementation process, this application also uses scanning electron microscopy (SEM) to observe the surface morphology of powder particles and to count the proportion of satellite powder and hollow powder in the powder sample to be tested.

[0072] 12: Calculate the decay coefficient of the powder based on the decay relationship and construct a compensation strategy for the scanning task based on the decay coefficient, where the decay coefficient includes the flowability decay coefficient, the thermal absorption decay rate and the satellite powder ratio amplification coefficient.

[0073] Specifically, in step 12, the decay coefficient of the powder is calculated based on the decay relationship, including the following steps 12A-12C, with reference to... Figure 3 As shown, Figure 3 A schematic flowchart illustrating an exemplary method for calculating the decay coefficient of powder according to some embodiments of this application is shown.

[0074] 12A: Based on the decay relationship in step 11, define and calculate the powder flowability decay coefficient:

[0075] ,

[0076] in The coefficient represents the number of recycling cycles. This coefficient reflects the decrease in powder flowability as the number of recycling cycles increases. The larger the value of the flowability decay coefficient, the more obvious the flowability decline.

[0077] 12B: Based on the decay relationship in step 11, define and calculate the thermal absorption decay rate of the powder:

[0078] ,

[0079] in, The energy beam absorption rate for the Nth recovery cycle. The energy beam absorptivity of the new powder; this coefficient represents the decrease in effective laser energy absorption due to oxide film thickening and compositional changes.

[0080] 12C: Based on the decay relationship in step 11, define and calculate the satellite powder ratio amplification factor of the powder:

[0081] ,

[0082] in The proportion of satellite powder recovered in the Nth recovery cycle. The ratio of satellite powder to new powder; this coefficient represents the increase in the proportion of small particles attached to the surface of recycled powder particles, reflecting the degree of deterioration in powder morphology.

[0083] Therefore, the aforementioned liquidity decay coefficient Thermal absorption attenuation rate And satellite powder ratio increase coefficient The coefficient is used to construct an adaptive compensation strategy for the scanning task's process parameters. For example, when this fluidity attenuation coefficient... When the value increases, it indicates a decrease in flowability parameters and a reduction in the uniformity of powder spreading on the powder bed. This decrease in flowability can be offset by increasing the thickness of the powder spreading layer. The specific adjustment formula is as follows: ,in This refers to the increased thickness of the powder coating layer, i.e., the increase in the thickness of the powder coating layer. This is the liquidity decay coefficient. The base powder layer thickness is used; the compensated powder layer thickness is updated as follows: .

[0084] When the heat absorption attenuation rate When the value increases, it indicates an increase in the thickness of the surface oxide film, which leads to a decrease in the thermal absorption rate of the effective energy beam. To ensure sufficient input energy for the molten pool, an energy beam power enhancement strategy is constructed to compensate for the insufficient effective energy input. The adjustment formula is as follows: ,in, The increase in energy beam power, i.e., the amount of energy beam power increase; The thermal absorption attenuation rate, The reference energy beam power is used; the compensated energy beam power is updated as follows: .

[0085] When the satellite powder ratio increases by a factor An increase in the speed indicates an increase in the number of satellite powders adhering to the surface of the recycled powder particles, leading to insufficient powder bed packing density or the formation of voids. Therefore, a strategy of reducing the powder spreading rate can be implemented to improve powder bed density or reduce voids. The adjustment formula is as follows: ,in, The amount by which the powder spreading speed is reduced; This is the coefficient for increasing the proportion of satellite powder. The base powder spreading speed is used; the compensated powder spreading speed is updated as follows: .

[0086] In some examples of this application, after constructing a compensation strategy for the scanning task based on the decay coefficient, in order to avoid excessive deviation of the compensation process parameters leading to instability in the additive manufacturing process, this application sets a corresponding compensation threshold range in each of the above compensation strategies.

[0087] Specifically, in the strategy of increasing the powder layer thickness, the adjustment threshold range is set to ±10μm; in the strategy of increasing the energy beam power, the adjustment threshold range is set to ±30W; in the strategy of decreasing the powder spreading speed, the adjustment threshold range is set to ±50mm / s; when the calculated... , or When the value exceeds the set threshold range, the maximum or minimum value within that range is taken as the actual compensation value.

[0088] Therefore, based on the above steps, a powder decay relationship model is constructed.

[0089] 13: During the execution of additive manufacturing scanning tasks, a compensation strategy is triggered every preset number of scanning layers (for example, the preset number of scanning layers can be 1 to 20 layers, which can be adjusted according to equipment characteristics and powder decay rate) to generate compensation process parameters based on the current number of recycling cycles. At the same time, a machine learning decision model is used to predict the proportion of new powder corresponding to the optimal forming quality index for the current recycling cycle.

[0090] Specifically, when the compensation strategy is triggered, the number of powder recovery cycles corresponding to the current scan layer is input into the constructed powder decay relationship model, and the corresponding flowability decay coefficient is calculated by combining the powder characteristic parameters corresponding to the number of recovery cycles. Thermal absorption attenuation rate And satellite powder ratio increase coefficient Then, based on the liquidity decay coefficient Thermal absorption attenuation rate And satellite powder ratio increase coefficient The system calls a compensation strategy to calculate the corresponding process parameter compensation amount and applies a threshold constraint to the compensation amount to automatically trim compensation values ​​exceeding the set threshold range to the maximum or minimum threshold. Finally, the compensated process parameters are input into the additive manufacturing equipment. Simultaneously, the corresponding number of recycling cycles for the current scanning layer and the powder characteristic parameters corresponding to that recycling cycle are input into the machine learning decision model. The machine learning decision model is then used to predict the optimal forming quality index and its corresponding proportion of new powder at that recycling cycle. This achieves dual adaptive control of process parameters and powder supply.

[0091] The machine learning decision model can employ one of the following: Support Vector Machine (SVM), Logistic Regression, Decision Tree, Random Forest, etc. In this application, the machine learning decision model adopts the SVM model, for example... Figure 4 and Figure 5 As shown, Figure 4 The diagram illustrates a flowchart of an exemplary SVM model construction method according to some embodiments of this application. Figure 5 The diagram illustrates an optimization graph of an exemplary SVM model according to some embodiments of this application. The construction process of the SVM model consists of the following steps 13A to 13D.

[0092] 13A: Collect a first preset number of sample parameters, including the number of recycling cycles, the proportion of new powder, powder characteristic parameters, and the surface roughness and density of the corresponding components, to construct a dataset; wherein, the first preset number of sample parameters can be set by the debugging personnel according to actual needs, or the experimental data generated in step 11 can be directly used as sample parameters.

[0093] 13B: Based on the sample parameters, an interpolation and noise addition method is used to construct enhanced sample parameters. In the process of constructing enhanced sample parameters, a preset number (exemplary num_augments=3) of new sample parameters are generated for two adjacent samples. Then, linear interpolation is used to calculate the proportion of new powder, the surface roughness and density of the corresponding components of the new sample parameters. At the same time, a small amount of Gaussian noise (exemplary noise_level=0.03) is added to the interpolation results to simulate experimental measurement errors. The enhanced sample parameters constructed in this way can increase the data density while maintaining the original distribution characteristics.

[0094] 13C: Add the constructed enhanced sample parameters to the dataset to form an enhanced dataset and divide the enhanced dataset into a training set and a test set according to a preset ratio (exemplary 80%:20%) using a random shuffling indexing method (fixed random seed rng(42)); wherein the training set is used for model fitting and the test set is used to evaluate the model's generalization ability.

[0095] 13D: The input data standardization method (Standardize=true) is adopted to eliminate the dimensional differences of the augmented dataset, and the kernel function of the machine learning decision model is set as the radial basis function (RBF) to capture the nonlinear relationship between the number of recycling times, the proportion of new powder and the forming quality index, thereby generating and training the SVM model. At the same time, the constraint condition of the SVM model is set to ensure that the surface roughness of the component cladding layer does not exceed the preset value (surface roughness less than or equal to 10μm) while maximizing the proportion of recycled powder (greater than or equal to 60%). The mean square error (MSE) is used as the performance evaluation index to compare the predicted values ​​of the test set with the true values, thereby evaluating the predictive performance of the SVM model.

[0096] 14: Input the compensation process parameters and the proportion of new powder into the additive manufacturing equipment for execution.

[0097] By adopting the above technical solution, and by detecting and analyzing the evolution of powder characteristics after different recycling cycles and establishing the decay relationship between flowability, heat absorption rate, and satellite powder ratio, the decay trend of powder can be identified. This allows for adaptive compensation of process parameters during additive manufacturing, ensuring that recycled powder maintains high forming quality even after multiple cycles, thus achieving efficient utilization of powder resources. Furthermore, by using a machine learning decision model to predict the optimal proportion of new powder for the current recycling cycle, the proportion of recycled powder can be maximized while ensuring component forming quality, reducing new powder consumption, decreasing production costs, and optimizing economic benefits and material utilization.

[0098] Therefore, in some examples of this application, the law of change of powder properties with the number of cycles was obtained based on experimental data. The specific results are shown in Tables 1 to 4 below:

[0099] Table 1: Decay Law of Key Performance Parameters of Recovered Powder (Uncompensated Recovered Powder)

[0100]

[0101] Table 2: Decay law of key performance parameters of recovered powder (40% recovered powder after compensation)

[0102]

[0103] Table 3: Decay law of key performance parameters of recovered powder (50% of recovered powder after compensation)

[0104]

[0105] Table 4: Decay law of key performance parameters of recovered powder (60% recovered powder after compensation)

[0106]

[0107] Therefore, the surface roughness measurement data of this application are referenced Figures 6 to 9 As shown, Figure 6 This invention illustrates an exemplary schematic diagram of the surface cladding quality of uncompensated recycled powder with different cycle numbers according to some embodiments of this application, wherein... Figure 6 (a) to Figure 6 (j) represents the number of iterations from 1 to 10; Figure 7 This application illustrates an exemplary schematic diagram of 40% surface cladding quality of compensated recycled powder with different cycle numbers, according to some embodiments of this application. Figure 7 (a) to Figure 7 (j) represents the number of iterations from 1 to 10; Figure 8 This illustration shows an exemplary schematic diagram of 50% surface cladding quality of compensated recycled powder with different cycle numbers according to some embodiments of this application, wherein... Figure 8 (a) to Figure 8 (j) represents the number of iterations from 1 to 10; Figure 9 This invention illustrates an exemplary schematic diagram of 60% surface cladding quality of compensated recycled powder with different cycle numbers according to some embodiments of this application, wherein... Figure 9 (a) to Figure 9 The (j) values ​​represent the number of iterations from 1 to 10.

[0108] Therefore, the density measurement data of this application are shown in Table 5 below:

[0109] Table 5: Packing density at different cycle numbers

[0110]

[0111] In this application, scanning electron microscopy was used to photograph and characterize the powder morphology, and the specific morphology of the powder particles is as follows: Figure 10 As shown, Figure 10 The diagram shows an exemplary electron microscope image of the particle morphology of uncompensated recovered powder to 60% compensated recovered powder at different cycle counts according to some embodiments of this application.

[0112] In this application, a three-dimensional optical profilometer is used to measure and characterize the morphology of the component, and the specific morphology of the component is as follows: Figure 11 As shown, Figure 11 The illustration shows a schematic diagram of the morphology of a component sample measured by an exemplary three-dimensional optical profilometer according to some embodiments of this application, wherein, Figure 11 (a) represents the boundary between the substrate and the cladding layer. Figure 11 (b) is the surface profile in the X direction. Figure 11 (c) is the surface profile in the Y direction.

[0113] refer to Figure 12 As shown, Figure 12 A schematic flowchart of an exemplary partition compensation method according to some embodiments of this application is shown. In some embodiments of this application, when the compensation strategy is triggered, the method (specifically step 13) further includes steps 13E to 13G.

[0114] 13E: The forming area of ​​the additive manufacturing equipment is divided into sub-regions according to the scanning path of the scanning task, forming multiple partitions.

[0115] Specifically, in step 13E, the scanning area of ​​the additive manufacturing equipment is divided according to the scanning task path to form multiple sub-regions (partitions), each partition corresponding to a certain number of scanning trajectories or scanning grid units; wherein, the division of sub-regions can be determined according to the scanning path, component geometry and energy beam working area of ​​the additive manufacturing equipment, ensuring that the powder layup and energy beam cladding process of each partition is independently controllable; and the current scanning layer number and the cumulative number of powder recovery times of each layer are recorded in each partition, the number of powder recovery times can be obtained through the powder conveying system data of the additive manufacturing equipment or historical scanning records.

[0116] For example, the XY plane of the forming area can be divided into several squares of 10mm × 10mm, with each square being a partition; or, a linear partition can be formed according to each scanning trajectory of the scanning path.

[0117] 13F: Obtain the number of powder recycling cycles for each zone and independently calculate the flowability decay coefficient, thermal absorption decay rate, and satellite powder proportion increase coefficient for each zone.

[0118] Specifically, in step 13F, for the powder in each partition, the flowability decay coefficient is calculated independently based on its cumulative number of recoveries. Thermal absorption attenuation rate And satellite powder ratio increase coefficient Furthermore, based on the liquidity decay coefficient of each partition... Thermal absorption attenuation rate And satellite powder ratio increase coefficient Calculate the corresponding increase in powder layer thickness Energy beam power increase And the amount of powder spreading speed reduction At the same time, the amount of increase in the thickness of the powder layer Energy beam power increase And the amount of powder spreading speed reduction Apply threshold constraints to ensure that the compensation value does not exceed the set maximum / minimum range.

[0119] 13G: Execute the corresponding powder layer thickness increase strategy and / or energy beam power increase strategy and / or powder layer speed reduction strategy independently for each partition.

[0120] Specifically, in step 13G, the calculated increase in the powder layer thickness is... Energy beam power increase And the amount of powder spreading speed reduction The baseline process parameters for each partition are added to generate the compensated process parameters for each partition. The compensated process parameters for each partition are then input into the control system of the additive manufacturing equipment, and adjustments are made accordingly when the scanning task reaches that partition.

[0121] In actual implementation, after each preset number of scanning layers is completed, steps 13E to 13G are triggered again to re-count and update the number of powder recovery times for each zone. , , and compensation amount , , ; Repeat the process until the scanning task is completely finished.

[0122] By employing the above technical solutions to locally compensate for powder in different zones, it is possible to regulate powder areas with poor flowability, ensuring uniform powder distribution and preventing localized sparse or accumulated powder layers; it is possible to regulate powder areas with low heat absorption rates, improving powder melting sufficiency and preventing localized over-melting or under-melting; and it is possible to regulate powder areas with increased satellite powder quantity, improving the quality of the formed surface.

[0123] In some embodiments of this application, reference is made to Figure 13 As shown, Figure 13 The diagram illustrates a modular connection of an exemplary additive manufacturing process compensation system 20 for the evolution of characteristics of recycled powder, according to some embodiments of this application. The process compensation system 20 is configured to have a decay building module 201, a strategy building module 202, a process compensation module 203, a machine learning module 204, and an execution control module 205.

[0124] The decay construction module 201 is configured to form components from powders with different recycling times and new powder ratios, and to perform characteristic testing on the recycled powder and components after forming, thereby establishing a decay relationship between the recycling times and powder characteristic parameters.

[0125] The strategy construction module 202 is configured to calculate the decay coefficient of the powder based on the decay relationship and construct a compensation strategy for the scanning task based on the decay coefficient, wherein the decay coefficient includes the flowability decay coefficient, the thermal absorption decay rate and the satellite powder ratio amplification coefficient.

[0126] The process compensation module 203 is configured to trigger a compensation strategy every preset number of scan layers during the execution of an additive manufacturing scanning task, so as to generate compensation process parameters based on the current number of recycling cycles.

[0127] The machine learning module 204 is configured to build a machine learning decision model and use the machine learning decision model to predict the optimal powder recovery ratio corresponding to the current recovery cycle.

[0128] The execution control module 205 is configured to input compensation process parameters and optimal recycled powder ratio into the additive manufacturing equipment for execution.

[0129] In some embodiments, reference Figure 14 As shown, Figure 14 A connection diagram of an electronic device used to implement embodiments of this application is shown. The electronic device 30 includes a memory 301 and a processor 302. The memory 301 stores a computer program that can run on the processor 302. When the processor 302 executes the computer program, it implements the methods described in the above embodiments. The number of memories 301 and processors 302 can be one or more.

[0130] The electronic device 30 also includes a communication interface 303 for communicating with external devices and exchanging and transmitting data.

[0131] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the memory 301, processor 302, and communication interface 303 can be interconnected through a bus and complete communication between them.

[0132] This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 14 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0133] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0134] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor 302, implements the method provided in this application.

[0135] This application also provides a chip, which includes a processor 302 for calling and running instructions stored in a memory 301, causing a communication device equipped with the chip to execute the method provided in this application.

[0136] This application also provides a chip, including: an input interface, an output interface, a processor 302 and a memory 301. The input interface, the output interface, the processor 302 and the memory 301 are connected through an internal connection path. The processor 302 is used to execute code in the memory 301. When the code is executed, the processor 302 is used to execute the method provided in the application embodiment.

[0137] It should be understood that the processor 302 mentioned above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that processor 302 can be a processor supporting the Advanced Reduced Instruction Set Computing (ARM) architecture.

[0138] Furthermore, the aforementioned memory 301 may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory 301 may be volatile memory or non-volatile memory, or may include both. The non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0139] Other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A process compensation method for the evolution of properties of recycled powder in additive manufacturing, characterized in that, The method includes: Components were formed from powders with different recycling times and the proportion of new powder, and the characteristics of the recycled powder and components were tested to establish the decay relationship between the recycling times and powder characteristic parameters. The decay coefficient of the powder is calculated based on the decay relationship between the number of recycling cycles and the powder characteristic parameters, and a compensation strategy for the scanning task is constructed based on the decay coefficient, wherein the decay coefficient includes the flowability decay coefficient, the thermal absorption decay rate, and the satellite powder ratio amplification coefficient. During the additive manufacturing scanning task, the compensation strategy is triggered every preset number of scanning layers to generate compensation process parameters based on the current number of recycling cycles. Simultaneously, a machine learning decision model is used to predict the proportion of new powder corresponding to the optimal forming quality index for the current recycling cycle; and... The compensation process parameters and the proportion of new powder are input into the additive manufacturing equipment for execution.

2. The method according to claim 1, characterized in that, The characteristic testing of the recovered powder and components after molding includes: The flowability parameters of the powder were determined using a Hall effect flowmeter test and a dynamic angle of repose test. The oxide film thickness and oxygen content parameters of the powder were measured using X-ray photoelectron spectroscopy. The surface roughness of the cladding layer of the component was measured using a non-contact three-dimensional profilometer, and the density of the component was measured using the drainage method.

3. The method according to claim 1 or 2, characterized in that, The calculation of the decay coefficient of the powder based on the decay relationship includes: Calculate the powder's flowability decay coefficient based on the decay relationship: ,in For the number of times the item is recycled; Calculate the thermal absorption decay rate of the powder based on the decay relationship: ,in, The energy beam absorption rate for the Nth recovery cycle. The energy beam absorption rate of the new powder; Calculate the satellite powder ratio amplification factor based on the decay relationship: ,in The proportion of satellite powder recovered in the Nth recovery cycle. This refers to the ratio of satellite powder to new powder.

4. The method according to claim 3, characterized in that, The compensation strategy for constructing the scanning task based on the decay coefficient includes: A strategy for increasing the powder coating thickness is constructed based on the aforementioned fluidity decay coefficient. The adjustment formula for the powder coating thickness increase strategy is as follows: ,in To increase the thickness of the powder layer, This is the liquidity decay coefficient. Based on the thickness of the powder layer; An energy beam power enhancement strategy is constructed based on the aforementioned thermal absorption attenuation rate. The adjustment range formula for the energy beam power enhancement strategy is as follows: ,in, To increase the power of the energy beam, The thermal absorption attenuation rate, The reference energy beam power; A strategy to reduce the powder spreading speed is constructed based on the aforementioned satellite powder ratio amplification coefficient. The adjustment range formula for the powder spreading speed reduction strategy is as follows: ,in, To reduce the speed of powder application, This is the coefficient for increasing the proportion of satellite powder. The base powder spreading speed.

5. The method according to claim 4, characterized in that, After constructing a compensation strategy for the scanning task based on the decay coefficient, the method includes: In the strategy of increasing the thickness of the powder layer, the adjustment threshold range is set to ±10μm; In the energy beam power enhancement strategy, the adjustment threshold range is set to ±30W; In the strategy to reduce powder spreading speed, the adjustment threshold range is set to ±50mm / s.

6. The method according to claim 1 or 5, characterized in that, When the compensation strategy is triggered, the method further includes: The forming area of ​​the additive manufacturing component is divided into sub-regions according to the scanning path of the scanning task, forming multiple partitions; Obtain the number of powder recycling cycles for each zone and independently calculate the flowability decay coefficient, thermal absorption decay rate, and satellite powder proportion increase coefficient for each zone. For each partition, implement the corresponding strategies for increasing the powder layer thickness and / or increasing the energy beam power and / or reducing the powder spreading speed independently.

7. The method according to claim 1, characterized in that, When constructing the compensation strategy for the scanning task, the method further includes: Collect a first preset number of sample parameters, including the number of recycling cycles, the proportion of new powder, powder characteristic parameters, and the surface roughness and density of the corresponding components, and construct a dataset. The dataset is iteratively trained using machine learning methods to construct a machine learning decision model. The iterative training process includes taking the number of recycling times and powder characteristic parameters as inputs, taking the forming quality index and the proportion of new powder as outputs, and setting constraints.

8. The method according to claim 7, characterized in that, The constructed dataset includes: Generate a second preset number of new sample parameters for two adjacent sample parameters; The proportion of new powder, the surface roughness and density of the corresponding components are calculated using linear interpolation. At the same time, a small amount of Gaussian noise is added to simulate the experimental measurement error, thereby constructing enhanced sample parameters. The constructed enhanced sample parameters are added to the dataset to form an enhanced dataset, and the dataset is divided into a training set and a test set according to a preset ratio using a random shuffling indexing method.

9. The method according to claim 7 or 8, characterized in that, The construction of the machine learning decision model includes: Input data standardization methods are used to eliminate dimensional differences in the augmented dataset; Set the kernel function of the machine learning decision model as a radial basis function; The constraint condition is to ensure that the surface roughness of the component cladding layer does not exceed the preset value while maximizing the proportion of recycled powder.

10. A process compensation system for the evolution of additive manufacturing recycled powder characteristics using the method according to any one of claims 1-9, characterized in that, include: The decay construction module is used to form components from powders with different recycling times and new powder ratios, and to perform characteristic testing on the recycled powder and components after forming, thereby establishing the decay relationship between the recycling times and powder characteristic parameters. The strategy construction module calculates the decay coefficient of the powder based on the decay relationship between the number of recycling cycles and the powder characteristic parameters, and constructs a compensation strategy for the scanning task based on the decay coefficient, wherein the decay coefficient includes the flowability decay coefficient, the thermal absorption decay rate, and the satellite powder ratio amplification coefficient. The process compensation module triggers the compensation strategy every preset number of scanning layers during the execution of the additive manufacturing scanning task, so as to generate compensation process parameters based on the current number of recycling cycles. The machine learning module is used to build machine learning decision models and use these models to predict the proportion of new powder corresponding to the optimal forming quality index for the current recycling cycle. The execution control module is used to input the compensation process parameters and the proportion of new powder into the additive manufacturing equipment for execution.

Images