Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an artificial intelligence-based additive manufacturing process optimization method and system, which can effectively solve the problems related to the background art.
The invention provides an artificial intelligence-based additive manufacturing flow optimization method, which comprises the steps of obtaining material characteristic parameters of additive manufacturing, evaluating material thermophysical properties and material photophysical properties through the material characteristic parameters, and comprehensively analyzing to obtain material characteristic evaluation parameters.
Monitoring the additive manufacturing process, analyzing to obtain an additive manufacturing component porosity abnormal change evaluation value and an additive manufacturing component temperature abnormal change evaluation value, matching according to material characteristic evaluation parameters to obtain an additive manufacturing component porosity abnormal change evaluation threshold and an additive manufacturing component temperature abnormal change evaluation threshold, and comprehensively analyzing to obtain an additive manufacturing component abnormal degree evaluation index.
And adjusting the additive manufacturing process parameters according to the additive manufacturing component abnormality degree evaluation index.
According to the material characteristic parameters including viscosity, heat conductivity and thermal expansion coefficient of various metal materials and absorptivity and reflectivity of various metal materials, extracting critical viscosity of the metal materials, reference standard heat conductivity of the metal materials, critical thermal expansion coefficient of the metal materials, critical absorptivity and critical reflectivity of the metal materials from an additive manufacturing database, and processing to obtain material thermophysical property evaluation parameters and material photophysical property evaluation parameters respectively.
And comprehensively analyzing according to the material thermophysical property evaluation parameters and the material photophysical property evaluation parameters to obtain the material characteristic evaluation parameters.
The method comprises the steps of deploying a plurality of time monitoring points, collecting the porosity of the additive manufacturing part at each time monitoring point, extracting critical porosity and critical porosity growth rate of the additive manufacturing part from an additive manufacturing database, and processing to obtain the abnormal change evaluation value of the porosity of the additive manufacturing part.
And monitoring the temperature of each printing layer of the additive manufacturing component, collecting the temperature of each printing layer of each time monitoring point, extracting the reference standard cooling rate of the printing layer and the reference standard interlayer temperature difference from an additive manufacturing database, and processing to obtain an abnormal change evaluation value of the temperature of the additive manufacturing component.
As a further method, the porosity anomaly change evaluation threshold value and the temperature anomaly change evaluation threshold value of the additive manufactured part are obtained according to the matching of the material characteristic evaluation parameters, the anomaly degree evaluation index of the additive manufactured part is obtained through comprehensive analysis, and the specific analysis process is as follows: matching the material characteristic evaluation parameters with the abnormal change evaluation threshold value of the porosity of the additive manufacturing part and the abnormal change evaluation threshold value of the temperature of the additive manufacturing part, which correspond to each material characteristic evaluation parameter interval stored in the additive manufacturing database, to obtain the abnormal change evaluation threshold value of the porosity of the additive manufacturing part and the abnormal change evaluation threshold value of the temperature of the additive manufacturing part, and comprehensively analyzing to obtain the abnormal degree evaluation index of the additive manufacturing part according to the abnormal change evaluation value of the porosity of the additive manufacturing part and the abnormal change evaluation value of the temperature of the additive manufacturing part.
The method comprises the steps of matching the abnormality degree evaluation index of the additive manufacturing component with laser power and printing layer thickness corresponding to each abnormality degree evaluation index interval of the additive manufacturing component stored in an additive manufacturing database to obtain proper laser power and proper printing layer thickness of the additive manufacturing component, and adjusting the laser power and printing layer thickness of the additive manufacturing component in real time according to the proper laser power and the proper printing layer thickness.
As a further method, the material characteristic evaluation parameter is a quantitative evaluation index obtained by analyzing the material thermophysical property evaluation parameter and the material photophysical property evaluation parameter, and is used for quantitatively evaluating the suitability of the material characteristic for additive manufacturing.
As a further method, the abnormality degree evaluation index of the additive manufactured part is a quantization index obtained by comprehensively analyzing the abnormal change of the porosity and the abnormal change of the temperature of the additive manufactured part, and is used for evaluating the abnormality degree of the additive manufactured part.
As a further method, the material characteristic evaluation parameter has a specific numerical expression:
Wherein, gamma represents a material characteristic evaluation parameter, e represents a natural constant, betaR represents a material thermophysical property evaluation parameter, betaG represents a material photophysical property evaluation parameter, omega1 represents a material characteristic evaluation influence factor corresponding to the set material thermophysical property evaluation parameter, and omega2 represents a material characteristic evaluation influence factor corresponding to the set material photophysical property evaluation parameter.
As a further method, the additive manufactured part abnormality degree evaluation index has a specific numerical expression of:
Where δ represents an additive manufacturing part abnormality degree evaluation index, e represents a natural constant, εK represents an additive manufacturing part porosity abnormality change evaluation value, εW represents an additive manufacturing part temperature abnormality change evaluation value, εK0 represents an additive manufacturing part porosity abnormality change evaluation threshold, εW0 represents an additive manufacturing part temperature abnormality change evaluation threshold, ψ1 represents an additive manufacturing part abnormality degree influence factor corresponding to the set additive manufacturing part porosity abnormality change evaluation value, and ψ2 represents an additive manufacturing part abnormality degree influence factor corresponding to the set additive manufacturing part temperature abnormality change evaluation value.
The invention provides an artificial intelligence-based additive manufacturing flow optimization system, which comprises a material characteristic analysis module, a material characteristic analysis module and a material characteristic analysis module, wherein the material characteristic analysis module is used for acquiring material characteristic parameters of additive manufacturing, evaluating material thermophysical properties and material photophysical properties through the material characteristic parameters, and comprehensively analyzing to obtain material characteristic evaluation parameters.
The additive manufacturing monitoring module is used for monitoring the additive manufacturing process, analyzing to obtain an additive manufacturing part porosity abnormal change evaluation value and an additive manufacturing part temperature abnormal change evaluation value, matching according to material characteristic evaluation parameters to obtain an additive manufacturing part porosity abnormal change evaluation threshold value and an additive manufacturing part temperature abnormal change evaluation threshold value, and comprehensively analyzing to obtain an additive manufacturing part abnormality degree evaluation index.
And the process parameter adjusting module is used for adjusting the additive manufacturing process parameters according to the additive manufacturing component abnormality degree evaluation index.
The additive manufacturing database is used for storing additive manufacturing related data, and comprises a metal material critical viscosity, a metal material reference standard thermal conductivity, a metal material critical thermal expansion coefficient, a metal material critical absorptivity, a metal material critical reflectivity, an additive manufacturing part critical porosity and a critical porosity growth rate, a printing layer reference standard cooling rate and a reference standard interlayer temperature difference, an additive manufacturing part porosity abnormal change evaluation threshold value and an additive manufacturing part temperature abnormal change evaluation threshold value corresponding to each material characteristic evaluation parameter interval, and laser power and printing layer thickness corresponding to each additive manufacturing part abnormal degree evaluation index interval.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
(1) According to the method and the system for optimizing the additive manufacturing flow based on artificial intelligence, the material characteristics of the additive manufacturing component are analyzed, the porosity and the temperature of the additive manufacturing component in the additive manufacturing process are monitored, the automatic control and decision of the additive manufacturing flow are realized, the artificial intervention burden is reduced, the production efficiency is improved, the process parameters are regulated and controlled in real time according to the material characteristics, the porosity and the temperature of the additive manufacturing component, the stability of part forming is ensured, and the post-treatment workload is reduced.
(2) According to the invention, through analyzing the material characteristics of the additive manufacturing part, the accurate setting of the technological parameters of the additive manufacturing is facilitated, the proper technological parameters can ensure that the material is uniformly melted and well solidified in the forming process, the generation of defects is reduced, the compactness and the overall performance of the part are improved, and meanwhile, the material characteristics can assist in optimizing the technological parameters in the additive manufacturing process, so that the overall optimization of the additive manufacturing is realized, and the quality and the reliability of the product are improved.
(3) According to the invention, the porosity and the temperature of the additive manufacturing component in the additive manufacturing process are monitored, the abnormal changes of the porosity and the temperature are analyzed, the occurrence probability of defects is reduced, the manufactured component is ensured to meet the specified requirements, and meanwhile, the monitoring of the porosity and the temperature is beneficial to timely feedback adjustment of technological parameters, so that the production efficiency of a product is improved.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present invention are included in the protection scope of the present invention.
Referring to fig. 1, a first aspect of the present invention provides an artificial intelligence-based additive manufacturing process optimization method, which includes obtaining material characteristic parameters of additive manufacturing, evaluating material thermophysical properties and material photophysical properties through the material characteristic parameters, and comprehensively analyzing to obtain material characteristic evaluation parameters.
The material characteristic evaluation parameters are obtained through comprehensive analysis, wherein the specific analysis process is that according to the material characteristic parameters, including the viscosity, the heat conductivity and the thermal expansion coefficient of various metal materials and the absorptivity and the reflectivity of various metal materials, the critical viscosity, the standard heat conductivity, the critical thermal expansion coefficient, the critical absorptivity and the critical reflectivity of the metal materials are extracted from an additive manufacturing database, and the material thermophysical property evaluation parameters and the material photophysical property evaluation parameters are respectively obtained through processing.
It should be understood that the material thermophysical property evaluation parameter in this embodiment is a quantization index obtained by comprehensively analyzing the viscosity, the thermal conductivity and the thermal expansion coefficient of the additive manufacturing metal material, and is used for quantitatively evaluating the additive manufacturing adaptability level of the thermophysical property of the additive manufacturing metal material, so as to provide a data basis for material characteristic evaluation.
In a specific embodiment, the material thermophysical property evaluation parameter is expressed as:
Wherein βR denotes a material thermophysical property evaluation parameter, e denotes a natural constant, NDi denotes a viscosity of an i-th metal material, RDi denotes a thermal conductivity of the i-th metal material, RPi denotes a coefficient of thermal expansion of the i-th metal material, ND0 denotes a critical viscosity of the metal material, RD0 denotes a standard thermal conductivity of the metal material, RP0 denotes a critical coefficient of thermal expansion of the metal material, Δrd denotes a set allowable deviation of the thermal conductivity of the metal material, χ1 denotes a thermophysical property fitness influencing factor corresponding to the set viscosity, χ2 denotes a thermophysical property fitness influencing factor corresponding to the set thermal conductivity, χ3 denotes a thermophysical property fitness influencing factor corresponding to the set coefficient of thermal expansion, i denotes the number of each metal material, i=1, 2,3, n, n denotes the total number of classes of the metal material.
In a specific embodiment, the thermophysical property evaluation parameters of the material can be obtained through the calculation mode, can also be obtained through computer simulation, can be used for predicting the thermophysical behavior of the material in the additive manufacturing process by adopting methods such as Finite Element Analysis (FEA), molecular dynamics simulation and the like, and comprises the phenomena of temperature distribution, thermal stress formation, phase change and the like, and can also be obtained through consulting the existing material databases (such as MatWeb, ASM Alloy Center and the like) to obtain the thermophysical property data of the material verified through experiments, wherein the data can be directly used for primarily evaluating the additive manufacturing adaptability of the material, and can be quantized to obtain the thermophysical property evaluation parameters of the material.
It should be understood that the material photophysical property evaluation parameter in this embodiment is a quantization index obtained by analyzing the absorptivity and reflectivity of the additive manufacturing metal material, and is used to quantitatively evaluate the additive manufacturing adaptability level of the photophysical property of the additive manufacturing metal material, so as to provide a data basis for material characteristic evaluation.
In a specific embodiment, the material photophysical property evaluation parameter has the following specific numerical expression:
Wherein βG represents a material photophysical property evaluation parameter, XSi represents an absorptivity of an i-th metal material, FSi represents a reflectivity of the i-th metal material, XS0 represents a critical absorptivity of the metal material, FS0 represents a critical reflectivity of the metal material, Φ1 represents a photophysical property fitness influencing factor corresponding to the set absorptivity of the metal material, and Φ2 represents a photophysical property fitness influencing factor corresponding to the set reflectivity of the metal material.
In a specific embodiment, the photophysical property evaluation parameters of the material can be obtained not only through the above calculation mode, but also through consulting literature data such as academic papers, technical reports, patents and the like, knowing the photophysical behaviors of the known material in the additive manufacturing process, such as light absorption, scattering, fluorescence, nonlinear optical response and the like, and the influence of the known material on the forming process, theoretically analyzing the interaction mechanism between the photophysical property of the material and the additive manufacturing process parameters (such as laser power, scanning speed, layer thickness and the like), predicting the influence of the photophysical property of the material on the forming quality (such as precision, surface roughness, internal microstructure) and the final product functions (such as optical transparency, color stability, photocatalytic activity and the like), and further through simulating the propagation path, focusing effect and light intensity distribution of the laser in a multilayer structure and complex geometry sample by using a light propagation model (such as a fresnel integral, a maxwell as a maxwell equation solver), evaluating the utilization rate of the laser energy and possible optical non-uniformity problem of the material, and comprehensively analyzing to obtain the photophysical property evaluation parameters of the material.
It should be understood that the viscosity in this example describes the flow resistance of the metallic material in the molten state, i.e. the ability of the liquid metal to resist shear deformation. In additive manufacturing processes, metal powders are heated above the melting point to form a liquid state where viscosity determines the fluidity, spreadability, and ability to fill complex geometries of the molten metal bath. The low viscosity is beneficial to the rapid and uniform filling of the printing layer by the molten metal, so that good metallurgical bonding is formed, and the forming efficiency and precision are improved. High viscosity can lead to poor melt pool fluidity, uneven spreading, or difficult filling, thereby affecting print quality.
It should be understood that the thermal conductivity in this embodiment is a measure of the ability of a metallic material to transfer heat per unit time, per unit area, per unit temperature gradient. During additive manufacturing, the thermal conductivity directly affects the heat distribution of the molten metal bath, the cooling rate, and the heat exchange between the molten region and the solid substrate. High thermal conductivity metallic materials can rapidly dissipate heat, allowing the puddle to solidify quickly, helping to reduce the heat affected zone, but can lead to difficult puddle temperature control, and can require higher power energy input to maintain the molten state. Conversely, a bath of low thermal conductivity material cools slowly, which is beneficial for prolonging metallurgical reaction times in the molten state, but may increase the heat affected zone and increase the risk of residual stress and deformation. Suitable thermal management strategies, including adjusting laser power, scan speed, and path planning, often require consideration of the thermal conductivity characteristics of the metallic material.
It should be understood that the thermal expansion coefficient (generally referred to as a linear thermal expansion coefficient) in this embodiment means a proportion in which the length of a metal material increases linearly with an increase in temperature in a certain direction when the temperature is changed. Standard thermal expansion coefficient data of various metal materials can be obtained by inquiring in professional books such as materials handbook, metal materials handbook and the like, and the data are verified based on a large number of experimental measurements and industrial practices. During the printing process, internal stress is generated when the metal layer is cooled and contracted, and if the thermal expansion coefficients of all layers are not matched or the cooling rate is uneven, larger thermal stress accumulation can be caused, so that the part is deformed or cracked. Therefore, a reasonable design of the cooling strategy, selection of a combination of materials with similar coefficients of thermal expansion, and post-treatment (e.g., heat treatment) for stress relief are critical to reducing thermal stresses.
It should be understood that the reflectivity and absorptivity of various metal materials are detected by the spectrometer device in this embodiment. Reflectivity refers to the percentage of light energy reflected back by a surface as the laser beam impinges on the surface of a metallic material. Metals generally have high reflectivity, especially for lasers of specific wavelengths, which depends on factors such as the type of metal, the wavelength of the laser, the surface state (e.g., roughness, oxide layer, coating, etc.), and the angle of incidence. High reflectivity means that most of the laser energy is not absorbed by the material, but is reflected back into the system or scattered into the environment, which is detrimental to the laser machining process. The absorptivity refers to the proportion of the light energy absorbed by the material and converted into heat energy after the laser beam is incident on the surface of the metal material. In additive manufacturing, the ideal metallic material should have a high absorptivity to ensure that the laser is able to quickly and efficiently melt or heat the target area. The reflectivity and absorptivity of metal materials in additive manufacturing are key indicators for measuring the response of the metal materials to laser energy, and directly influence the processing efficiency, the forming quality and the process stability. By reasonably selecting materials, adjusting laser parameters and optimizing surface conditions, the utilization rate of laser energy can be effectively improved, and the generation of high-quality additive manufacturing components is promoted.
And comprehensively analyzing according to the material thermophysical property evaluation parameters and the material photophysical property evaluation parameters to obtain the material characteristic evaluation parameters.
Specifically, the material characteristic evaluation parameter is a quantitative evaluation index obtained by analyzing the material thermophysical property evaluation parameter and the material photophysical property evaluation parameter, and is used for quantitatively evaluating the suitability of the material characteristic for additive manufacturing and providing a data basis for adjusting the additive manufacturing process parameters.
Further, the material characteristic evaluation parameters have the following specific numerical expressions:
Wherein, gamma represents a material characteristic evaluation parameter, e represents a natural constant, betaR represents a material thermophysical property evaluation parameter, betaG represents a material photophysical property evaluation parameter, omega1 represents a material characteristic evaluation influence factor corresponding to the set material thermophysical property evaluation parameter, and omega2 represents a material characteristic evaluation influence factor corresponding to the set material photophysical property evaluation parameter.
In a specific embodiment, the material characteristic evaluation parameter can be obtained not only through the above calculation mode, but also through using a specially designed software tool, a user can judge in a plurality of dimensions such as preset materials and processes, structures and features, performances and functions, production and cost and the like according to product information and material characteristics, a system can automatically calculate and generate an evaluation report to give an adaptability grade or grade of the material to additive manufacturing, and laboratory tests can be performed according to a program specified by a standard, so that performance data of the material under the additive manufacturing processes such as fused deposition, laser sintering, electron beam melting and the like can be obtained, and the adaptability of the material can be further quantified, so that the material characteristic evaluation parameter can be obtained.
In a specific embodiment, by analyzing the material characteristics of the additive manufacturing component, the method is beneficial to accurately setting the technological parameters of the additive manufacturing, the proper technological parameters can ensure that the material is uniformly melted and well solidified in the forming process, the defects are reduced, the density and the overall performance of the part are improved, and meanwhile, the material characteristics can assist in optimizing the technological parameters in the additive manufacturing process, so that the overall optimization of the additive manufacturing is realized, and the quality and the reliability of the product are improved.
Monitoring the additive manufacturing process, analyzing to obtain an additive manufacturing component porosity abnormal change evaluation value and an additive manufacturing component temperature abnormal change evaluation value, matching according to material characteristic evaluation parameters to obtain an additive manufacturing component porosity abnormal change evaluation threshold and an additive manufacturing component temperature abnormal change evaluation threshold, and comprehensively analyzing to obtain an additive manufacturing component abnormal degree evaluation index.
The method comprises the steps of disposing a plurality of time monitoring points, collecting the porosity of the additive manufacturing component at each time monitoring point, extracting critical porosity and critical porosity growth rate of the additive manufacturing component from an additive manufacturing database, and processing to obtain an additive manufacturing component porosity abnormal change evaluation value.
It should be understood that the abnormal change evaluation value of the porosity of the additive manufactured part in this embodiment is a quantization index obtained by analyzing the porosity and the change rate of the porosity in the printing process of the additive manufactured part, and is used for quantitatively evaluating the abnormal degree of the porosity change of the additive manufactured part, so as to provide a data basis for evaluating the abnormal degree of the additive manufactured part.
In a specific embodiment, the porosity of the additive manufacturing component adjacent to two time monitoring points is obtained, the interval duration of the time monitoring points is extracted, and the abnormal change evaluation value of the porosity of the additive manufacturing component is obtained through comprehensive analysis, wherein the specific numerical expression is as follows:
Wherein εK represents an abnormal change in additive manufacturing part porosity evaluation value, Kj represents an abnormal change in porosity of an additive manufacturing part at a j-th time monitoring point, K0 represents a critical porosity of the additive manufacturing part, Km represents a porosity of the additive manufacturing part at an m-th time monitoring point, Km-1 represents a porosity of the additive manufacturing part at an m-1-th time monitoring point, T represents an interval duration of the time monitoring points, K (V)0 represents a critical porosity growth rate, V represents a porosity abnormal change influence factor corresponding to the set porosity, j represents a number of each time monitoring point, j=1, 2, 3.
In a specific embodiment, the abnormal change in porosity of the additive manufacturing part is estimated by not only the above calculation, but also installing pressure, temperature or strain sensors during printing, collecting process parameter data, predicting or diagnosing the abnormal porosity in real time by combining a machine learning algorithm, and further monitoring the form and cooling rate of a molten pool during printing, wherein abnormal thermal behaviors possibly indicate the formation of pores, and comprehensively analyzing to obtain the abnormal change in porosity of the additive manufacturing part.
It should be appreciated that in this embodiment, the printed article is scanned three-dimensionally and nondestructively by X-rays to generate a high resolution image of the internal structure. The software algorithm can perform three-dimensional reconstruction and pore analysis on the CT data, and accurately measure the number, size, shape and distribution of the pores, thereby obtaining the porosity of the additive manufactured part. As the number of layers increases, the heat accumulation effect may cause the heat affected zone to expand, and the difference in thermal expansion between the molten metal and the solidified layer may cause stress concentrations, inducing microcracks or voids. In addition, repeated heating and cooling of the powder bed may also cause thermal stress variations between powder particles, causing periodic fluctuations in porosity between different layers. By monitoring the porosity of the additive manufactured part during the additive manufacturing process, it may help optimize process parameters and improve the final quality of the additive manufactured part.
And monitoring the temperature of each printing layer of the additive manufacturing component, collecting the temperature of each printing layer of each time monitoring point, extracting the reference standard cooling rate of the printing layer and the reference standard interlayer temperature difference from an additive manufacturing database, and processing to obtain an abnormal change evaluation value of the temperature of the additive manufacturing component.
It should be understood that, the abnormal temperature change evaluation value of the additive manufacturing component in this embodiment is a quantization index obtained by analyzing the temperature change condition of each printed layer, and is used for quantitatively evaluating the abnormal degree of the temperature change of the additive manufacturing component, and providing a data basis for evaluating the abnormal degree of the additive manufacturing component.
In a specific embodiment, the temperature of each printing layer adjacent to the time monitoring point is obtained, and the abnormal change evaluation value of the temperature of the additive manufacturing component is obtained through comprehensive analysis, wherein the specific numerical expression is as follows:
where εW represents an evaluation value of abnormal change in temperature of the additive manufactured part, W (V)r represents a cooling rate of the r-th printed layer,Wr→m denotes the temperature of the r-th print layer at the m-th time monitoring point, Wr→m-1 denotes the temperature of the r-th print layer at the m-1 th time monitoring point, W (V)0 denotes the print layer reference standard cooling rate, Wr+1 denotes the temperature of the r+1-th print layer adjacent to the time monitoring point, Wr denotes the temperature of the r-th print layer adjacent to the time monitoring point, W0 denotes the reference standard interlayer temperature difference, Δw denotes the set interlayer temperature difference allowable deviation value, τ1 denotes the temperature abnormality change influence factor corresponding to the set interlayer temperature difference, τ2 denotes the temperature abnormality change influence factor corresponding to the set cooling rate, r denotes the number of each print layer, r=1, 2, 3.
In a specific embodiment, the evaluation value of abnormal temperature change of the additive manufacturing component can be obtained through the calculation mode, the influence of the evaluation value on temperature can be analyzed by continuously tracking the change of technological parameters such as laser power, a scanning path, layer thickness, cooling conditions and the like, when the parameters deviate from a set range, the risk of temperature abnormality can exist, a machine learning model (such as a neural network, a support vector machine and the like) can be trained by combining historical data with real-time monitoring data to predict the trend of temperature change, possible abnormal temperature is early warned in advance, and the evaluation value of abnormal temperature change of the additive manufacturing component is obtained through analysis.
It should be understood that the print layer in this embodiment is a basic unit for building an object in a three-dimensional printing process, which is stacked from bottom to top according to a design model. Each layer represents a two-dimensional projection of a three-dimensional model onto a certain height section, the thickness of which is one of the additive manufacturing process parameters, and can be accurately set according to actual requirements and equipment capacity.
It should be appreciated that the temperature of each printed layer of the additive manufactured part is monitored by infrared thermal imaging in this embodiment. The cooling rate of each printed layer can have an effect on the quality of the additive manufactured part, and if the printed layer cools too fast (e.g., the cooling air speed is too high, the ambient temperature is too low, the thermal conductivity of the material is high), a large temperature gradient can be generated inside and around the molten pool, high thermal stress can be formed, and the risk of cracking or warping of the part can be increased. Rapid cooling may also result in insufficient microstructuring, affecting material properties. Conversely, if the cooling rate is too slow (e.g., poor heat dissipation conditions, large heat capacity of the material, excessive heat build-up between layers), the melt pool remains high Wen Shijian too long, which may result in too large a heat affected zone between adjacent layers, affect the inter-layer metallurgical bonding, and may also promote element diffusion, changing the alloy composition distribution. Meanwhile, abnormal thermal gradients of the printing layers can also affect the quality of the additive manufacturing component, uneven thermal expansion force can be generated in the printing process due to the fact that different metal materials or the thermal expansion coefficient difference of the same material in different directions, deformation of the component is caused, and the accumulated thermal stress can lead to warping, twisting or integral deformation of the component along with the increase of the number of printing layers.
In a specific embodiment, the porosity and the temperature of the additive manufactured part in the additive manufacturing process are monitored, abnormal changes of the porosity and the temperature are analyzed, the occurrence probability of defects is reduced, the manufactured part is ensured to meet the specified requirements, and meanwhile, the monitoring of the porosity and the temperature is beneficial to timely feedback adjustment of technological parameters, so that the production efficiency of a product is improved.
The method comprises the steps of matching the material characteristic evaluation parameters with the abnormal change evaluation threshold of the porosity of the additive manufacturing part and the abnormal change evaluation threshold of the temperature of the additive manufacturing part corresponding to each material characteristic evaluation parameter interval stored in an additive manufacturing database, obtaining the abnormal change evaluation threshold of the porosity of the additive manufacturing part and the abnormal change evaluation threshold of the temperature of the additive manufacturing part, and comprehensively analyzing to obtain the abnormal degree evaluation index of the additive manufacturing part according to the abnormal change evaluation value of the porosity of the additive manufacturing part and the abnormal change evaluation value of the temperature of the additive manufacturing part.
Specifically, the abnormal degree evaluation index of the additive manufactured part is a quantitative index obtained by comprehensively analyzing the abnormal change of the porosity and the abnormal change of the temperature of the additive manufactured part, is used for evaluating the abnormal degree of the additive manufactured part, and provides a data basis for adjusting the technological parameters of the additive manufacturing.
Further, the additive manufacturing component abnormality degree evaluation index has a specific numerical expression:
Where δ represents an additive manufacturing part abnormality degree evaluation index, e represents a natural constant, εK represents an additive manufacturing part porosity abnormality change evaluation value, εW represents an additive manufacturing part temperature abnormality change evaluation value, εK0 represents an additive manufacturing part porosity abnormality change evaluation threshold, εW0 represents an additive manufacturing part temperature abnormality change evaluation threshold, ψ1 represents an additive manufacturing part abnormality degree influence factor corresponding to the set additive manufacturing part porosity abnormality change evaluation value, and ψ2 represents an additive manufacturing part abnormality degree influence factor corresponding to the set additive manufacturing part temperature abnormality change evaluation value.
In a specific embodiment, the evaluation index of the degree of abnormality of the additive manufactured part can be obtained not only by the above calculation method, but also by using advanced simulation software of the additive manufacturing process (such as ANSYS ADDITIVE Suite, exaSIM, etc.), performing numerical simulation on the whole forming process before printing, predicting possible defects (such as deformation caused by thermal stress, holes caused by insufficient melting, poor interlayer bonding caused by uneven powder bed, etc.), providing an expected evaluation value of the degree of abnormality as a reference in the actual manufacturing process, and further by performing real-time or near-real-time internal defect detection on the formed part during printing by using nondestructive detection technology (such as ultrasonic detection, X-ray Computed Tomography (CT), magnetic powder inspection, eddy current detection, etc.), which can reveal hidden defects such as voids, cracks, inclusions, etc., and quantifying the degree of abnormality of the part by information such as number, size, position, type, etc. of the defects, so as to obtain the evaluation index of the degree of abnormality of the additive manufactured part.
And adjusting the additive manufacturing process parameters according to the additive manufacturing component abnormality degree evaluation index.
The method comprises the steps of adjusting additive manufacturing process parameters according to an additive manufacturing component abnormality degree evaluation index, wherein the specific analysis process comprises the steps of matching the additive manufacturing component abnormality degree evaluation index with laser power and printing layer thickness corresponding to each additive manufacturing component abnormality degree evaluation index interval stored in an additive manufacturing database to obtain proper laser power and proper printing layer thickness of the additive manufacturing component, and adjusting the laser power and printing layer thickness of additive manufacturing in real time according to the proper laser power and the proper printing layer thickness.
It should be appreciated that the laser power of the additive manufacturing is adjusted in this embodiment, which directly affects whether the metal powder is sufficiently melted and the melting rate. Higher power can heat and melt the powder faster, improving the forming efficiency, but excessive power can lead to problems of excessive melting, splashing, increased air holes, etc. Proper power adjustment helps to form the desired melt pool size and shape (e.g., depth, width, and shape) to ensure good fusion and solidification.
It will be appreciated that the thickness of the printed layers of additive manufacturing is adjusted in this embodiment, and the thickness of each layer of powder deposit is set in the device software, typically in microns. This thickness is determined by the metal powder layer that the powder placement system uniformly spreads onto the melted layer before each layer is built up. The print layer thickness should be matched to the laser scanning strategy (e.g., scan speed, scan pitch, fill pattern, etc.) and laser power to ensure that each layer melts sufficiently and bonds well to the next layer. Smaller layer thicknesses can improve the surface quality and dimensional accuracy of the molded part because thinner layers allow the laser to mold more finely the details and contours, reducing the step effect. However, too thin a layer may result in a significant increase in manufacturing time.
Referring to FIG. 2, a second aspect of the present invention provides an artificial intelligence based additive manufacturing process optimization system comprising a material property analysis module, an additive manufacturing monitoring module, a process parameter adjustment module, and an additive manufacturing database.
The material characteristic analysis module is used for acquiring material characteristic parameters of additive manufacturing, evaluating the thermophysical properties and the photophysical properties of the material through the material characteristic parameters, and comprehensively analyzing to obtain material characteristic evaluation parameters.
The additive manufacturing monitoring module is used for monitoring the additive manufacturing process, analyzing to obtain an additive manufacturing part porosity abnormal change evaluation value and an additive manufacturing part temperature abnormal change evaluation value, matching according to material characteristic evaluation parameters to obtain an additive manufacturing part porosity abnormal change evaluation threshold value and an additive manufacturing part temperature abnormal change evaluation threshold value, and comprehensively analyzing to obtain an additive manufacturing part abnormality degree evaluation index.
The process parameter adjusting module is used for adjusting the process parameters of the additive manufacturing according to the abnormal degree evaluation index of the additive manufacturing component.
The additive manufacturing database is used for storing additive manufacturing related data, and comprises a metal material critical viscosity, a metal material reference standard thermal conductivity, a metal material critical thermal expansion coefficient, a metal material critical absorptivity, a metal material critical reflectivity, an additive manufacturing part critical porosity and a critical porosity growth rate, a printing layer reference standard cooling rate and a reference standard interlayer temperature difference, an additive manufacturing part porosity abnormal change evaluation threshold value and an additive manufacturing part temperature abnormal change evaluation threshold value corresponding to each material characteristic evaluation parameter interval, and laser power and a printing layer thickness corresponding to each additive manufacturing part abnormal degree evaluation index interval.
In a specific embodiment, the invention provides the artificial intelligence-based additive manufacturing process optimization method and system, which are used for analyzing the material characteristics of the additive manufacturing components, monitoring the porosity and the temperature of the additive manufacturing components in the additive manufacturing process, realizing the automatic control and decision of the additive manufacturing process, reducing the burden of manual intervention, improving the production efficiency, regulating and controlling the process parameters in real time according to the material characteristics, the porosity and the temperature of the additive manufacturing components, ensuring the stability of part forming and reducing the post-processing workload.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.