3D printing mold cooling method and device based on dynamic visual feedback

Abstract

The invention provides a 3D printing mold cooling method and device based on dynamic visual feedback. The method comprises the steps that the initial cooling condition in the cooling process is determined; the 3D printing mold in the printing process is primarily cooled based on the initial cooling condition; performing feature analysis on a first mold surface image acquired based on visual camera equipment to obtain a first image analysis result; if the surface temperature does not reach the preset target surface temperature, adjusting the initial cooling condition based on the first image analysis result and the preset target surface temperature to obtain an optimized cooling condition, and cooling again based on the optimized cooling condition; and a second mold surface image of the 3D printing mold in the re-cooling process is collected based on the visual camera equipment, and the optimized cooling condition is adjusted according to a second image analysis result of the second mold surface image till the surface temperature is cooled to the preset target surface temperature. The production quality and the production efficiency of the mold are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a 3D printing mold cooling method and device based on dynamic visual feedback. Background Art

[0002] In the manufacturing process of 3D printing molds, the cooling process is crucial to ensure mold quality and production efficiency. The existing 3D printing mold cooling method usually achieves cooling by setting fixed cooling pipes around the mold and using circulating coolant to take away the heat of the mold.

[0003] However, the existing 3D printing mold cooling methods are difficult to ensure uniform cooling. Since mold shapes are often complex and diverse, fixed cooling pipes may be too far away from the mold surface in some parts, resulting in low cooling efficiency, and in some parts, stress concentration may occur due to excessive cooling, affecting the overall performance and service life of the mold. This uneven cooling problem is particularly prominent when printing large and complex molds. It not only affects the production quality of the mold, but also greatly limits the application of 3D printing molds in the field of high-end manufacturing and affects the production efficiency of the mold. Summary of the invention

[0004] The present invention provides a 3D printing mold cooling method and device based on dynamic visual feedback, which are used to improve the production quality and production efficiency of the mold.

[0005] In a first aspect, the present invention provides a 3D printing mold cooling method based on dynamic visual feedback, wherein a plurality of visual camera devices are evenly arranged around the mold printing position in the printing working area of ​​the 3D printing device; the 3D printing mold cooling method based on dynamic visual feedback comprises:

[0006] Determine the initial cooling condition of the 3D printed mold during the cooling process based on the parameter information obtained from the design drawing of the 3D printed mold and the thermophysical properties of the 3D printed material;

[0007] In response to a printing start instruction of the 3D printing mold, preliminarily cooling the 3D printing mold during the printing process based on the initial cooling condition;

[0008] Capturing a first mold surface image of the 3D printed mold during the preliminary cooling process based on a visual camera device, and performing feature analysis on the first mold surface image to obtain a first image analysis result;

[0009] If it is determined based on the first image analysis result that the surface temperature of the 3D printing mold has not reached the preset target surface temperature, then the initial cooling condition is adjusted based on the first image analysis result and the preset target surface temperature to obtain an optimized cooling condition, and the 3D printing mold during the printing process is cooled again based on the optimized cooling condition;

[0010] Based on the vision camera device, the second mold surface image of the 3D printing mold during the re-cooling process is collected, and the optimized cooling condition is adjusted according to the second image analysis result of the second mold surface image until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0011] In a second aspect, the present invention further provides a 3D printing mold cooling device based on dynamic vision feedback, which is applied to the 3D printing mold cooling method based on dynamic vision feedback as described in the first aspect. In the printing working area of the 3D printing device, a plurality of vision camera devices are evenly arranged around the mold printing position; the 3D printing mold cooling device based on dynamic vision feedback includes:

[0012] An initialization module, configured to determine the initial cooling condition of the 3D printing mold during the cooling process by combining the parameter information obtained from the design drawing of the 3D printing mold with the thermophysical properties of the 3D printing material;

[0013] A mold preliminary cooling module, configured to respond to the printing start instruction of the 3D printing mold and preliminarily cool the 3D printing mold during the printing process based on the initial cooling condition;

[0014] A dynamic vision feedback module, configured to collect the first mold surface image of the 3D printing mold during the preliminary cooling process based on the vision camera device, and perform feature analysis on the first mold surface image to obtain a first image analysis result;

[0015] A mold re-cooling module, configured to if it is determined based on the first image analysis result that the surface temperature of the 3D printing mold has not reached the preset target surface temperature, then adjust the initial cooling condition based on the first image analysis result and the preset target surface temperature to obtain an optimized cooling condition, and re-cool the 3D printing mold during the printing process based on the optimized cooling condition;

[0016] A dynamic feedback cooling module, configured to collect the second mold surface image of the 3D printing mold during the re-cooling process based on the vision camera device, and adjust the optimized cooling condition according to the second image analysis result of the second mold surface image until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0017] In a third aspect, the present invention further provides an electronic device, including: a memory for storing a computer software program; and a processor for reading and executing the computer software program to implement the 3D printing mold cooling method based on dynamic vision feedback as described in any one of the above.

[0018] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium storing a computer software program, which when executed by a processor implements the 3D printing mold cooling method based on dynamic vision feedback as described in any one of the above.

[0019] In a fifth aspect, the present invention provides a computer program product including a computer program, which when executed by a processor implements the 3D printing mold cooling method based on dynamic vision feedback as described in any one of the above.

[0020] The 3D printing mold cooling method based on dynamic vision feedback provided by the embodiments of the present invention collects the mold surface image of the 3D printing mold in real time through a vision camera device. Therefore, no matter how complex the structure of the 3D printing mold is, the temperature distribution of the mold surface of the 3D printing mold can be intuitively obtained. By combining the image analysis result of the mold surface image with the preset target surface temperature, the optimized cooling conditions for each part of the mold surface of the 3D printing mold can be dynamically generated, enabling each part of the mold surface of the 3D printing mold to be cooled evenly, effectively solving the disadvantage of uneven cooling, improving the overall performance and service life. At the same time, continuous monitoring and optimization are carried out throughout the process to ensure that the temperature of each part of the mold surface is always within a suitable range until it is cooled to the preset target surface temperature, avoiding the problems of overcooling or undercooling and improving the cooling efficiency. Therefore, the embodiments of the present invention improve the mold quality and production efficiency. Description of the Drawings

[0021] Figure 1 is a flowchart of the 3D printing mold cooling method based on dynamic vision feedback provided by the embodiments of the present invention;

[0022] Figure 2 is a structural diagram of the 3D printing mold cooling device based on dynamic vision feedback provided by the embodiments of the present invention;

[0023] Figure 3 is an embodiment diagram of the electronic device provided by the embodiments of the present invention;

[0024] Figure 4 is an embodiment diagram of the computer-readable storage medium provided by the embodiments of the present invention. Detailed Embodiments

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

[0026] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0027] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0028] Optionally, refer to Figure 1 as shown Figure 1 is a flowchart of the 3D printing mold cooling method based on dynamic visual feedback provided by the present invention. In the embodiments of the present invention, the execution subject of the 3D printing mold cooling method based on dynamic visual feedback is a mold cooling device. Optionally, in the printing working area of the 3D printing device, a plurality of visual camera devices are evenly arranged around the mold printing position. Therefore, the 3D printing mold cooling method based on dynamic visual feedback includes:

[0029] Step 10, combining the parameter information obtained from the design drawings of the 3D printing mold with the thermophysical properties of the 3D printing material to determine the initial cooling conditions of the 3D printing mold during the cooling process.

[0030] Optionally, the design drawings of the 3D printing mold and the thermophysical properties of various 3D printing materials are pre-stored in the mold cooling device, or when performing 3D printing, technicians output the design drawings of the 3D printing mold and the thermophysical properties of various 3D printing materials in the mold cooling device.

[0031] Therefore, the mold cooling device analyzes the design drawing of the 3D printing mold to obtain the parameter information of the 3D printing mold. Among them, the parameter information includes the size, shape, etc. of the 3D printing mold. At the same time, the thermophysical properties of the 3D printing material used are obtained, including thermal conductivity, specific heat capacity, thermal diffusivity, etc.

[0032] Furthermore, the mold cooling device determines the initial cooling conditions of the 3D printing mold at the beginning of the cooling process according to the parameter information of the 3D printing mold combined with the thermophysical properties of the 3D printing material, as specifically described in steps 101 to 104. Among them, the initial cooling conditions include the initial cooling temperature, initial cooling flow rate, initial cooling flow of the coolant in the cooling system, etc.

[0033] Step 20: In response to the printing start instruction of the 3D printing mold, the 3D printing mold during the printing process is preliminarily cooled based on the initial cooling conditions.

[0034] Furthermore, the mold cooling device responds to the printing start instruction of the 3D printing mold, starts the cooling system according to the initial cooling conditions, and the cooling medium in the cooling system starts to preliminarily cool the 3D printing mold during the printing process according to the initial cooling conditions, taking away the heat generated by the 3D printing mold during the printing process to prevent the 3D printing mold from deforming or affecting the printing quality due to overheating. Among them, during the cooling process, the mold surface temperature distribution prediction model is established as:

[0035]

[0036] Among them, T represents the mold surface temperature, t represents time, x and y represent the coordinates of the mold surface, and α mod represents the corrected thermal diffusivity, h represents the convective heat transfer coefficient, and k mod represents the corrected material thermal conductivity, and T coolant0 represents the initial cooling temperature.

[0037] Step 30: Based on the visual camera device, collect the first mold surface image of the 3D printing mold during the preliminary cooling process, and perform feature analysis on the first mold surface image to obtain the first image analysis result.

[0038] Further, the mold cooling device invokes a vision camera device to collect images of the 3D printed mold during the initial cooling process, obtaining a first mold surface image of the 3D printed mold during the initial cooling process. After collecting the image, the mold cooling device uses a built-in image analysis algorithm to analyze the features of the first mold surface image, identify the features in the first mold surface image, such as the color distribution features and texture features on the mold surface, and infer the temperature distribution of the mold surface of the 3D printed mold through the features in the first mold surface image, obtaining a first image analysis result, specifically as described in steps 301 to 304.

[0039] In one embodiment, the vision camera device takes pictures of the mold surface of the 3D printed mold being initially cooled every 1 minute. At the 5th minute after the start of printing, a first mold surface image is collected. The mold cooling device uses an image analysis algorithm based on the principle of thermal radiation to process this image. By analyzing the color brightness of different regions in the image and according to the correspondence between color and temperature, it is identified that the temperature of most regions on the mold surface is between 50 and 60 degrees Celsius, but the temperature of a thin-walled region reaches 70 degrees Celsius, obtaining a first image analysis result.

[0040] Step 40, if it is determined based on the first image analysis result that the surface temperature of the 3D printed mold has not reached the preset target surface temperature, then the initial cooling conditions are adjusted based on the first image analysis result and the preset target surface temperature to obtain optimized cooling conditions, and the 3D printed mold during the printing process is cooled again based on the optimized cooling conditions.

[0041] Further, the mold cooling device determines whether the surface temperature of the 3D printed mold has reached the preset target surface temperature according to the first image analysis result, where the preset target surface temperature is set in advance by technicians in the mold cooling device. If the surface temperature of the 3D printed mold has not reached the preset target surface temperature, the mold cooling device combines the temperature distribution in the first image analysis result and the preset target surface temperature, and optimizes the initial cooling conditions by adjusting parameters such as the temperature, flow rate, and flow volume of the cooling medium, obtaining optimized cooling conditions, specifically as described in steps 401 to 404.

[0042] Further, the mold cooling device restarts the cooling system to cool the 3D printed mold during the printing process through the optimized cooling conditions.

[0043] In one embodiment, the preset target surface temperature is 40 degrees Celsius. According to the first image analysis result, the mold surface temperature of the 3D printing mold is determined to be 48 degrees Celsius. At this time, the mold surface temperature of the 3D printing mold is greater than the preset target surface temperature. Therefore, the mold cooling device adjusts the algorithm, such as reducing the temperature of the cooling medium water to 18 degrees Celsius, increasing the flow rate to 0.6 cubic meters per hour, and increasing the flow rate to 6 liters per minute, so as to obtain the optimized cooling conditions. Then, according to the optimized conditions, the cooling system is turned on again to cool the mold, and the mold temperature change is continuously monitored within the next 5 minutes.

[0044] Step 50: Based on the visual camera device, collect the second mold surface image of the 3D printing mold during the re-cooling process, and adjust the optimized cooling conditions according to the second image analysis result of the second mold surface image until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0045] Further, during the re-cooling process, the mold cooling device calls the visual camera device to continue collecting the second mold surface image of the 3D printing mold, and analyzes the second mold surface image to obtain the second image analysis result. Further, the mold cooling device judges again whether the mold surface temperature reaches the preset target surface temperature according to the second image analysis result. If it still does not reach, continue to adjust the optimized cooling conditions, such as further changing the cooling medium parameters, etc., and then cool again. This cycle continues until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0046] Continuing the above embodiment, after re-cooling for 3 minutes according to the optimized cooling conditions, the visual camera device collects the second mold surface image. After analysis, the overall mold surface temperature has dropped to 43 degrees Celsius, but still does not reach the target temperature of 40 degrees Celsius. The mold cooling device further reduces the temperature of the cooling medium water to 16 degrees Celsius and increases the flow rate to 0.7 cubic meters per hour. After adjusting the cooling conditions again, continue to cool. After multiple such image collections, analyses, and cooling condition adjustments, finally, at the 20th minute after the start of printing, the mold surface temperature is successfully cooled to the preset target surface temperature of 40 degrees Celsius.

[0047] In an embodiment of the present invention, the mold surface image of the 3D printing mold is collected in real time by a vision camera device. Therefore, no matter how complex the structure of the 3D printing mold is, the temperature distribution on the mold surface of the 3D printing mold can be intuitively obtained. By combining the image analysis result of the mold surface image with the preset target surface temperature, the optimized cooling conditions for each part of the mold surface of the 3D printing mold can be dynamically generated, enabling uniform cooling of each part of the mold surface of the 3D printing mold, effectively solving the drawback of uneven cooling, improving the overall performance and service life. At the same time, continuous monitoring and optimization are carried out throughout the process to ensure that the temperature of each part of the mold surface is always within an appropriate range until it is cooled to the preset target surface temperature, avoiding the problems of overcooling or undercooling, improving the cooling efficiency, and thus enhancing the mold quality and production efficiency.

[0048] In one embodiment, the descriptions of steps 101 to 104 are as follows:

[0049] Step 101: Modify the original thermal diffusivity of the 3D printing material based on the thermophysical properties of the 3D printing material to obtain the modified thermal diffusivity of the 3D printing material.

[0050] Optionally, the mold cooling device obtains the internal void volume and the total volume of the 3D printing mold, and considering the influence of the complex internal structure of the 3D printing mold on heat conduction, obtains a structure influence factor according to the mold structure complexity of the 3D printing mold combined with expert experience.

[0051] Furthermore, the mold cooling device modifies the original thermal diffusivity of the 3D printing material based on the thermophysical properties of the 3D printing material combined with the internal void volume, the total volume of the 3D printing mold, and the structure influence factor to obtain the modified thermal diffusivity of the 3D printing material. The specific formula is:

[0052]

[0053] Among them, α mod represents the modified thermal diffusivity, α 0 represents the original thermal diffusivity, β represents the structure influence factor, V void represents the internal void volume of the mold, and V total represents the total volume of the mold.

[0054] Step 102: Estimate the heat flux based on the mold size and mold shape of the 3D printing mold combined with the modified thermal diffusivity to obtain the initial heat flux on the mold surface of the 3D printing mold.

[0055] Optionally, in the embodiment of the present invention, the mold surface of the 3D printing mold is a uniform heat dissipation surface. Therefore, the mold cooling device obtains the mold size and mold shape of the 3D printing mold, as well as the corrected material thermal conductivity related to the corrected thermal diffusivity, and determines the mold surface area S of the 3D printing mold according to the mold shape. surface Further, the mold cooling device determines the equivalent heat conduction length L according to the mold surface area and the total mold volume of the 3D printing mold. eff , and the specific formula is: L eff = V total / S surface .

[0056] Further, the mold cooling device obtains the current ambient temperature and the preset target surface temperature of the 3D printing mold when printing is completed, wherein the preset target surface temperature is set in advance according to the actual situation.

[0057] Further, the mold cooling device estimates the heat flux according to the corrected material thermal conductivity, the current ambient temperature, the equivalent heat conduction length, and the preset target surface temperature, and obtains the initial heat flux of the mold surface of the 3D printing mold. The specific formula is:

[0058] q pre = [k mod *(T target - T amb )] / L eff .

[0059] Wherein, q pre represents the initial heat flux, k mod represents the corrected material thermal conductivity, T target represents the preset target surface temperature, and T amb represents the current ambient temperature.

[0060] Step 103: Determine the convective heat transfer coefficient between the coolant in the cooling system and the mold surface of the 3D printing mold based on the pipe structure of the cooling system and the flow characteristics of the coolant in the cooling system.

[0061] Further, the mold cooling device obtains the pipe structure of the cooling system and the flow characteristics of the coolant in the cooling system. In the embodiment of the present invention, the pipe structure is the hydraulic diameter, and the flow characteristic is the thermal conductivity.

[0062] Further, the mold cooling device calculates the convective heat transfer coefficient between the coolant in the cooling system and the mold surface of the 3D printing mold according to the hydraulic diameter of the cooling system and the thermal conductivity of the coolant in the cooling system. The specific formula is:

[0063] h = (N u * k fluid ) / Dhyd 。

[0064] Among them, h represents the convective heat transfer coefficient, N u represents the Nusselt number, k fluid represents the thermal conductivity of the coolant, D hyd represents the hydraulic diameter. Among them, the specific formula for the Nusselt number is:

[0065]

[0066] R e =(ρ fluid *v*D hyd ) / μ fluid 。

[0067] Among them, C 1 , C 2 , C 3 , C 4 are constants obtained by fitting experimental data. R e represents the Reynolds number, P r represents the Prandtl number, ∈ represents the pipe wall roughness of the cooling system, ρ fluid represents the density of the coolant, v represents the flow rate of the coolant, μ fluid represents the dynamic viscosity of the coolant.

[0068] Step 104: Determine the initial cooling conditions based on the initial heat flux and the convective heat transfer coefficient.

[0069] Furthermore, the mold cooling device determines the initial cooling conditions according to the initial heat flux and the convective heat transfer coefficient, specifically as described in Steps 1041 to 1043. Among them, the initial cooling conditions include the initial cooling temperature and the initial cooling flow rate of the coolant in the cooling system.

[0070] The embodiment of the present invention can formulate the most suitable initial cooling conditions according to the specific characteristics of the 3D printing mold and the material, as well as the actual situation of the cooling system, thereby reducing problems such as deformation and internal stress concentration of the mold caused by improper cooling, improving the yield rate of 3D printed products, and effectively improving the production quality and production efficiency of the 3D printing mold cooling process.

[0071] In one embodiment, the descriptions of Steps 1041 to 1043 are as follows:

[0072] Step 1041: Predict the energy transfer based on the initial heat flux, the convective heat transfer coefficient, the mass of the 3D printing mold, the specific heat capacity of the mold material, and the contact surface area between the coolant in the cooling system and the mold surface of the 3D printing mold to obtain the heat reduction amount.

[0073] Optionally, the mold cooling device obtains the mold quality of the 3D printed mold, the specific heat capacity of the mold material, and the contact surface area between the coolant in the cooling system and the mold surface of the 3D printed mold.

[0074] Furthermore, the mold cooling device predicts energy transfer based on the initial heat flux, the convective heat transfer coefficient, and the contact surface area between the coolant in the cooling system and the mold surface of the 3D printed mold, and combines the principle of conservation of energy to obtain the heat reduction amount. The specific formula is as follows:

[0075] where, W q represents the heat reduction amount, S cool represents the contact surface area, c mold represents the specific heat capacity of the mold material, m mold represents the mold quality.

[0076] Step 1042: Determine the initial cooling temperature of the coolant in the cooling system based on the heat reduction amount and the preset target surface temperature of the 3D printed mold.

[0077] Furthermore, the mold cooling device determines the initial cooling temperature T coolant0 of the coolant in the cooling system according to the heat reduction amount and the preset target surface temperature of the 3D printed mold. The specific formula is:

[0078] T coolant0 = T target + W q .

[0079] Step 1043: Predict the flow rate based on the initial heat flux, the convective heat transfer coefficient, the preset target surface temperature, the initial cooling temperature, and combine the density, cooling rate, and specific heat capacity at constant pressure of the coolant in the cooling system to obtain the initial cooling flow rate of the coolant in the cooling system.

[0080] Furthermore, the mold cooling device obtains the density, cooling rate, and specific heat capacity at constant pressure of the coolant in the cooling system, where the cooling rate represents the volume flow rate of the coolant in the cooling pipe per unit time.

[0081] Furthermore, the mold cooling device predicts the flow rate based on the initial heat flux, the convective heat transfer coefficient, the preset target surface temperature, the initial cooling temperature, and combines the density, cooling rate, and specific heat capacity at constant pressure of the coolant in the cooling system to obtain the initial cooling flow rate of the coolant in the cooling system. The specific formula is:

[0082] v 0 =(q pre * S cool ) / [ρ fluid * c p，fluid *(T target-T coolant0 )*V flow .

[0083] Among them, v 0 represents the initial cooling flow rate, ρ fluid represents the density of the coolant, c p，fluid represents the specific heat capacity at constant pressure of the coolant, V flow represents the cooling rate of the coolant.

[0084] The embodiment of the present invention realizes precise regulation of the cooling conditions, can optimize the initial temperature and flow rate of the coolant according to the actual situation of the 3D printing mold, thereby improving the cooling efficiency, ensuring that the temperature of the 3D printing mold drops evenly during the cooling process, reducing defects such as deformation and cracking of the mold caused by uneven cooling, and effectively improving the production quality and production efficiency of the cooling process of the 3D printing mold.

[0085] In one embodiment, the descriptions of steps 301 to 304 are as follows:

[0086] Step 301, divide the mold surface of the 3D printing mold into multiple thermal zones, and perform a thermal field distribution difference analysis on each thermal zone based on the temperature data in the first image analysis result to obtain the temperature difference coefficient between each thermal zone and the preset target surface temperature.

[0087] Optionally, the mold cooling device processes the first mold surface image, divides the mold surface of the 3D printing mold into multiple thermal zones according to factors such as shape and structure. Among them, the division of the thermal zones aims to more carefully analyze the temperature distribution of different regions on the mold surface. Then, obtain the temperature data corresponding to each thermal zone from the first image analysis result. For each thermal zone, compare its average temperature with the preset target surface temperature, and calculate the ratio of the difference between the two to the preset target surface temperature to obtain the temperature difference coefficient between the thermal zone and the preset target surface temperature.

[0088] In one embodiment, the 3D printing mold is a complex mechanical part mold, and the mold cooling device divides its surface into 5 thermal zones. It is known from the first image analysis result that the average temperature of thermal zone 1 is 60 degrees Celsius, and the preset target surface temperature is 50 degrees Celsius. Then the temperature difference coefficient of thermal zone 1 is |60 - 50| / 50 = 0.2. Similarly, calculate the temperature difference coefficients of other thermal zones.

[0089] Step 302, according to the temperature difference coefficients of each thermal zone and the corresponding mold volume of each thermal zone, combined with the heat exchange principle between the mold and the coolant, calculate the heat capacity adjustment amount corresponding to the coolant in each thermal zone.

[0090] Optionally, heat transfer is related to factors such as the mold volume, temperature change, and specific heat capacity of the material. Therefore, the mold cooling device obtains the specific heat capacity of the mold material, the mold volume corresponding to each hot zone, and the specific heat capacity of the coolant flowing through each hot zone, and calculates the heat capacity adjustment amount of the coolant corresponding to each hot zone based on the specific heat capacity of the mold material, the temperature difference coefficient of each hot zone, the mold volume corresponding to each hot zone, and the specific heat capacity of the coolant flowing through each hot zone, in combination with the heat exchange principle between the mold and the coolant. Therefore, for each hot zone, by using the specific heat capacity of the mold material, its temperature difference coefficient, and the mold volume, and combining with the heat exchange formula Q = ρVcΔTα for derivation, the amount of heat change that needs to be absorbed or released due to temperature difference in each hot zone is obtained, where Q represents heat, ρ represents the density of the mold material, V represents the mold volume, c represents the specific heat capacity of the mold material, ΔT represents the temperature change, and α represents the temperature difference coefficient.

[0091] Further, the mold cooling device calculates the ratio of the heat change amount of each hot zone to the specific heat capacity of the coolant flowing through each hot zone to obtain the heat capacity adjustment amount of the coolant corresponding to each hot zone, that is, heat capacity adjustment amount = heat change amount / specific heat capacity of the coolant.

[0092] Step 303: Based on the coolant mass and the specific heat capacity of the coolant flowing through each hot zone, and in combination with the heat capacity adjustment amount of the coolant corresponding to each hot zone, determine the initial temperature adjustment value of the coolant in each hot zone.

[0093] Further, the mold cooling device obtains the coolant mass of the coolant flowing through each hot zone, and multiplies the coolant mass of the coolant flowing through each hot zone by the specific heat capacity of the coolant to obtain the heat capacity of the coolant flowing through each hot zone. Further, the mold cooling device calculates the ratio of the heat capacity of the coolant flowing through each hot zone to the heat capacity adjustment amount of the coolant corresponding to each hot zone to obtain the initial temperature adjustment value of the coolant in each hot zone, that is, initial temperature adjustment value = heat capacity adjustment amount / heat capacity.

[0094] Step 304: Adjust the initial cooling conditions based on the temperature difference coefficient and the initial temperature adjustment value of each hot zone to obtain the optimized cooling conditions.

[0095] Further, the mold cooling device adjusts the initial cooling conditions according to the temperature difference coefficient and the initial temperature adjustment value of each hot zone to obtain the optimized cooling conditions, as specifically described in Steps 3041 to 3044.

[0096] The embodiments of the present invention can achieve fine adjustment of the cooling conditions according to the temperature distribution in different regions of the mold surface. Therefore, it can effectively improve the uniformity of mold cooling, avoid problems such as mold deformation and internal stress concentration caused by local overheating or overcooling, improve the quality and service life of 3D printing molds, and effectively improve the production quality and production efficiency of the 3D printing mold cooling process.

[0097] In one embodiment, the descriptions of steps 3041 to 3044 are as follows:

[0098] Step 3041: Adjust the initial temperature adjustment values of each hot zone based on the temperature difference coefficients of each hot zone to obtain the target temperature adjustment values of each hot zone.

[0099] Optionally, for each hot zone, the mold cooling device obtains the correction factor corresponding to the temperature difference coefficient in the preset mapping table according to the temperature difference coefficient, where the preset mapping table is an association relationship table established in advance according to the temperature difference coefficient and its corresponding correction factor. In one embodiment, in the preset mapping table, when α = 0.2, the correction factor is 1.5; when α = 0.1, the correction factor is 1.2.

[0100] Further, the mold cooling device adjusts the initial temperature adjustment values of each hot zone according to the correction factor corresponding to the temperature difference coefficient of each hot zone to obtain the target temperature adjustment values of each hot zone. The specific formula is: T tn = T ti * exp(1 + α t ). Wherein, T tn represents the target temperature adjustment value, T ti represents the initial temperature adjustment value; α t represents the correction factor corresponding to the temperature difference coefficient α.

[0101] Step 3042: Adjust the initial cooling flow rate of the coolant in each hot zone based on the target temperature adjustment values of each hot zone to obtain the optimized flow rate of the coolant in each hot zone.

[0102] Further, the mold cooling device adjusts the initial cooling flow rate of the coolant according to the target temperature adjustment values of each hot zone. Among them, the larger the target temperature adjustment value, it means that the hot zone needs the coolant to take away more or less heat (depending on whether the temperature is higher or lower than the preset target surface temperature). Therefore, it is necessary to increase or decrease the coolant flow rate accordingly. According to the heat transfer principle, the heat taken away by the coolant is related to the flow rate. The optimized flow rate is calculated by establishing a functional relationship between the flow rate and the temperature adjustment value. Generally, a linear or non-linear function model can be adopted, such as: optimized flow rate = initial cooling flow rate + target temperature adjustment value * flow rate adjustment coefficient, where the flow rate adjustment coefficient is determined according to factors such as coolant characteristics and mold structure.

[0103] Step 3043: Determine the flow rate adjustment amount of the coolant for each hot zone based on the optimized flow rate of each hot zone and the cross-sectional area of the cooling channel corresponding to each hot zone.

[0104] Furthermore, the mold cooling device obtains the cross-sectional area information of the cooling channels corresponding to each hot zone. For each hot zone, according to the principle of fluid mechanics, the flow rate is equal to the flow velocity multiplied by the cross-sectional area. First, calculate the flow rate corresponding to the optimized flow velocity of each hot zone, and then compare it with the flow rate corresponding to the initial flow velocity to determine the flow rate adjustment amount. The flow rate adjustment amount = optimized flow velocity * cross-sectional area - initial flow velocity * cross-sectional area.

[0105] Step 3044: Determine the optimized cooling conditions by taking the optimized flow velocity and the flow rate adjustment amount of the coolant for each hot zone.

[0106] Furthermore, the mold cooling device determines the optimized cooling conditions by taking the optimized flow velocity and the flow rate adjustment amount of the coolant for each hot zone.

[0107] The embodiments of the present invention can achieve precise and differential adjustment of the cooling conditions, improve the uniformity and efficiency of mold cooling, reduce problems such as deformation and internal stress concentration caused by local overheating or overcooling of the mold, and thus improve the quality and service life of the 3D printing mold, effectively improving the production quality and production efficiency of the 3D printing mold cooling process.

[0108] In one embodiment, the descriptions of steps 401 to 404 are as follows:

[0109] Step 401: Convert the first mold surface image from a color image to a grayscale image.

[0110] Optionally, the mold cooling device obtains a color image of the first mold surface. Generally, a color image consists of three color channels: red (R), green (G), and blue (B), and each pixel contains color information of the three channels. Furthermore, the mold cooling device converts the color image to a grayscale image. In a grayscale image, each pixel has only one brightness value, representing the gray level of that point, and the value range is generally from 0 (black) to 255 (white). Common grayscale conversion methods include the weighted average method. For example, calculate the gray value of each pixel through the formula Gray = 0.299R + 0.587G + 0.114B, and convert each pixel in the color image to the corresponding gray value according to this formula to obtain a complete grayscale image.

[0111] Step 402: Divide the grayscale image into multiple sub-regions, and perform edge detection on each sub-region to obtain the edge features of each sub-region.

[0112] Further, the mold cooling device divides the grayscale image into multiple sub-regions according to certain rules. Among them, the division method can be uniform division. For example, the image can be divided into square or rectangular sub-regions of equal size, or it can be adaptively divided according to the structural characteristics of the mold.

[0113] Further, after the division is completed, the mold cooling device performs edge detection on each sub-region to obtain the edge features of each sub-region. Among them, edge detection aims to identify the regions in the image where the grayscale values change drastically. These regions usually correspond to the edges of objects or the boundaries of different temperature regions. Commonly used edge detection algorithms include the Canny algorithm, the Sobel algorithm, etc. Taking the Canny algorithm as an example, the image is filtered by Gaussian filtering to remove noise, the gradient magnitude and direction of the image are calculated, then non-maximum suppression is performed to refine the edges, and finally the final edges are determined through double-threshold detection and edge connection.

[0114] In an embodiment, the mold cooling device evenly divides the grayscale image into 100 square sub-regions with a size of 10*10 pixels. For one of the sub-regions, the Canny algorithm is used for edge detection. The sub-region is filtered by a Gaussian filter. For example, the Gaussian kernel size is 3*3 and the standard deviation is 1.4. After filtering, the sub-region image becomes smoother and the noise is suppressed. Then the gradient magnitude and direction of the sub-region image are calculated. For example, at a certain pixel point, the calculated gradient magnitude is 20 and the direction is 45 degrees. Then non-maximum suppression is performed to remove the pixel points that are not local gradient maxima and refine the edges. Finally, by setting double thresholds (for example, the low threshold is 50 and the high threshold is 150) for edge detection and connection, the edge features of the sub-region are obtained, which are manifested as a series of connected edge pixel points.

[0115] Step 403, construct a temperature correlation matrix for each sub-region based on the edge features of each sub-region.

[0116] Further, for each sub-region, the mold cooling device constructs a temperature correlation matrix according to its edge features. Since the edge features reflect the change of grayscale values between different positions within the sub-region, and the grayscale value is related to temperature (under the principle of thermal imaging, different temperatures correspond to different grayscale values), therefore, the matrix elements in the temperature correlation matrix represent the temperature correlation degree between different positions within the sub-region based on the edge features. The method of constructing the temperature correlation matrix can be based on factors such as spatial distance and edge strength. For example, for two pixel points P i and P j , if the distance between pixel points P i and P j is relatively close and the edge strength on the path connecting pixel points P i and Pj is weak (indicating a relatively gentle temperature change), then pixel point Pi and P j If the corresponding element value in the temperature correlation matrix is large, it indicates a high degree of temperature correlation; conversely, if the distance is far and the edge intensity on the path is strong (large temperature change), the corresponding element value is small. The size of the matrix is related to the number of pixel points in the sub-region, generally N*N, where N is the number of pixel points in the sub-region.

[0117] In one embodiment, there are 100 pixel points in a certain sub-region. For pixel points P 1 and P 20 , if the pixel points P 1 and P 20 are close in spatial distance within the sub-region, and the edge intensity obtained by edge detection on the path connecting the pixel points P 1 and P 20 is weak (few edge pixel points), then the element T 1，20 (representing the temperature correlation degree between the pixel points P 1 and P 20 ) is set to 0.8 (the value range is 0 - 1, and the larger the value, the higher the correlation degree). For pixel points P 5 and P 90 with a far distance and a strong edge intensity on the path, the value of the element T 5，90 is set to 0.2. And so on, a complete 100*100 temperature correlation matrix for this sub-region is constructed.

[0118] Step 404, perform fusion analysis based on the edge features and temperature correlation matrix of each sub-region to obtain the first image analysis result.

[0119] Furthermore, the mold cooling device performs fusion analysis based on the edge features and temperature correlation matrix of each sub-region to obtain the first image analysis result, as specifically described in Steps 4041 to 4044.

[0120] The embodiments of the present invention can perform in-depth analysis on the first mold surface image, obtain more accurate temperature distribution information, can more accurately judge the difference between the mold surface temperature and the preset target surface temperature, provide a reliable basis for adjusting the initial cooling conditions based on this, thereby improving the pertinence and effectiveness of the cooling process, better ensuring the quality of the 3D printing mold, reducing problems such as mold deformation and internal defects caused by improper temperature control, and effectively improving the production quality and production efficiency of the 3D printing mold cooling process.

[0121] In one embodiment, the descriptions of Steps 4041 to 4044 are as follows:

[0122] Step 4041, fuse the edge features and temperature correlation matrix within each sub-region to obtain the temperature feature representation of each sub-region.

[0123] Optionally, for each sub-region, the mold cooling device fuses its edge feature and temperature correlation matrix. Among them, the edge feature contains information about the temperature change boundary within the sub-region, such as the positions of edge pixel points, the trend of the edge, etc.; the temperature correlation matrix reflects the temperature-based correlation degree between different positions within the sub-region. There are various fusion methods, such as vector splicing. The edge feature and the temperature correlation matrix are respectively transformed into vector forms, and then spliced together in sequence to form a new vector, which is the temperature feature representation of the sub-region. It is also possible to use the method of weighted summation, assign weights according to the importance of the edge feature and the temperature correlation matrix to the temperature feature, and perform weighted summation on the corresponding elements of the two to obtain a new matrix or vector as the temperature feature representation.

[0124] Step 4042: Integrate the temperature feature representations of the sub-regions to obtain the global temperature feature representation.

[0125] Furthermore, the mold cooling device collects the temperature feature representations of all sub-regions. Since the temperature feature representations of each sub-region have the same dimension, these temperature feature representations of the sub-regions can be arranged or combined in a certain order to form a larger matrix or vector as the global temperature feature representation. For example, the temperature feature representation vectors of all sub-regions can be sequentially spliced into a long vector, or they can be arranged into a two-dimensional matrix, where each row of the matrix represents the temperature feature representation of a sub-region. In this way, the global temperature feature representation contains the temperature-related feature information of each sub-region on the entire mold surface.

[0126] Step 4043: Perform clustering analysis on the global temperature feature representation to cluster the sub-regions with similar temperature features into the same class and obtain the clustering result.

[0127] Furthermore, the mold cooling device performs clustering analysis on the global temperature feature representation. The purpose of clustering analysis is to divide the sub-regions with similar temperature features into the same class. Common clustering algorithms include the K-Means algorithm, DBSCAN algorithm, etc. Taking the K-Means algorithm as an example, first, the number of clustering classes K needs to be determined (which can be determined according to experience or experiments). Then, randomly select K points as the initial clustering centers, calculate the distances (such as Euclidean distances) between the temperature feature representation vectors of each sub-region and these K clustering centers, and assign each sub-region to the class where the nearest clustering center is located. Then, recalculate the clustering centers of each class, that is, the mean vector of the temperature feature representation vectors of all sub-regions in the class. Continuously repeat the above process until the clustering centers no longer change significantly or reach the preset number of iterations, and finally obtain the clustering result, that is, the class label to which each sub-region belongs.

[0128] Step 4044: Map the clustering result to the first mold surface image, representing different temperature feature categories with different colors to obtain the first image analysis result.

[0129] Furthermore, the mold cooling device maps the clustering result back to the first mold surface image. Different colors are assigned to each sub-region according to the category it belongs to. For example, the sub-regions belonging to category 1 are shown in red in the image, those of category 2 are shown in blue, and those of category 3 are shown in green. In this way, on the first mold surface image, the regions of different temperature feature categories are visually presented in different colors. At the same time, the temperature range corresponding to each category or other relevant temperature feature information can also be marked on the image, thus obtaining a comprehensive and intuitive first image analysis result.

[0130] In one embodiment, on the first mold surface image, the color values of the pixel points of all sub-regions marked as category 1 are modified to red (such as RGB value (255, 0, 0)), those of category 2 are modified to blue (such as RGB value (0, 0, 255)), and those of category 3 are modified to green (such as RGB value (0, 255, 0)). Then, in the corner or blank area of the image, it is marked that the temperature range of the red area is 50 - 60 degrees Celsius, the blue area is 60 - 70 degrees Celsius, and the green area is 70 - 80 degrees Celsius, forming a complete first image analysis result image.

[0131] The embodiments of the present invention can systematically and intuitively analyze the temperature distribution on the mold surface. Therefore, it can quickly and accurately identify the differences in the temperature distribution on the mold surface, providing an intuitive and reliable basis for adjusting the initial cooling conditions, helping to improve the accuracy and effectiveness of the cooling process, reducing the quality problems of the mold caused by uneven temperature, and effectively improving the production quality and production efficiency of the 3D printing mold cooling process.

[0132] Furthermore, the 3D printing mold cooling device based on dynamic visual feedback provided by the present invention is described below. The 3D printing mold cooling device based on dynamic visual feedback described below can be mutually referred to with the 3D printing mold cooling method based on dynamic visual feedback described above.

[0133] Optionally, referring to Figure 2 , Figure 2 is the structural diagram of the 3D printing mold cooling device based on dynamic visual feedback provided by the present invention. The 3D printing mold cooling device based on dynamic visual feedback includes:

[0134] An initialization module 210, configured to determine the initial cooling conditions of the 3D printing mold during the cooling process by combining the parameter information obtained from the design drawing of the 3D printing mold with the thermophysical properties of the 3D printing material.

[0135] The preliminary mold cooling module 220 is configured to respond to a printing start instruction of a 3D printing mold and perform preliminary cooling on the 3D printing mold during the printing process based on initial cooling conditions;

[0136] The dynamic vision feedback module 230 is configured to collect a first mold surface image of the 3D printing mold during the preliminary cooling process based on a vision imaging device, and perform feature analysis on the first mold surface image to obtain a first image analysis result;

[0137] The mold re-cooling module 240 is configured to, if it is determined based on the first image analysis result that the surface temperature of the 3D printing mold has not reached a preset target surface temperature, adjust the initial cooling conditions based on the first image analysis result and the preset target surface temperature to obtain optimized cooling conditions, and perform re-cooling on the 3D printing mold during the printing process based on the optimized cooling conditions;

[0138] The dynamic feedback cooling module 250 collects a second mold surface image of the 3D printing mold during the re-cooling process based on the vision imaging device, and adjusts the optimized cooling conditions according to a second image analysis result of the second mold surface image until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0139] In the embodiment of the present invention, the mold surface image of the 3D printing mold is collected in real time through the vision imaging device. Therefore, no matter how complex the structure of the 3D printing mold is, the temperature distribution on the mold surface of the 3D printing mold can be intuitively obtained. By combining the image analysis result of the mold surface image with the preset target surface temperature, the optimized cooling conditions for each part of the mold surface of the 3D printing mold can be dynamically generated, enabling each part of the mold surface of the 3D printing mold to be cooled evenly, effectively solving the drawback of uneven cooling, improving the overall performance and service life. At the same time, continuous monitoring and optimization are carried out throughout the process to ensure that the temperature of each part of the mold surface is always within a suitable range until it is cooled to the preset target surface temperature, avoiding the problems of over-cooling or under-cooling, improving the cooling efficiency, and thus enhancing the mold quality and production efficiency.

[0140] Please refer to Figure 3 , Figure 3 which is the embodiment diagram of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0141] Based on the parameter information obtained from the design drawings of the 3D printing mold and combined with the thermophysical properties of the 3D printing material, determine the initial cooling conditions of the 3D printing mold during the cooling process;

[0142] In response to the printing start instruction of the 3D printing mold, based on the initial cooling conditions, preliminarily cool the 3D printing mold during the printing process;

[0143] Based on the visual camera device, collect the first mold surface image of the 3D printing mold during the preliminary cooling process, and perform feature analysis on the first mold surface image to obtain the first image analysis result;

[0144] If it is determined based on the first image analysis result that the surface temperature of the 3D printing mold has not reached the preset target surface temperature, then adjust the initial cooling conditions based on the first image analysis result and the preset target surface temperature to obtain the optimized cooling conditions, and based on the optimized cooling conditions, cool the 3D printing mold during the printing process again;

[0145] Based on the visual camera device, collect the second mold surface image of the 3D printing mold during the re-cooling process, and adjust the optimized cooling conditions according to the second image analysis result of the second mold surface image until the surface temperature of the 3D printing mold is cooled to the preset target surface temperature.

[0146] Please refer to Figure 4 , Figure 4 which is the embodiment diagram of the computer-readable storage medium provided by the embodiment of the present invention. As Figure 4 shown, this embodiment provides a computer-readable storage medium 400, on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0147] Based on the parameter information obtained from the design drawings of the 3D printing mold and combined with the thermophysical properties of the 3D printing material, determine the initial cooling conditions of the 3D printing mold during the cooling process;

[0148] In response to the printing start instruction of the 3D printing mold, based on the initial cooling conditions, preliminarily cool the 3D printing mold during the printing process;

[0149] Based on the visual camera device, collect the first mold surface image of the 3D printing mold during the preliminary cooling process, and perform feature analysis on the first mold surface image to obtain the first image analysis result;

[0150] If it is determined based on the first image analysis result that the surface temperature of the 3D printing mold has not reached the preset target surface temperature, then adjust the initial cooling conditions based on the first image analysis result and the preset target surface temperature to obtain the optimized cooling conditions, and based on the optimized cooling conditions, cool the 3D printing mold during the printing process again;

[0151] Based on the second die surface image of the 3D printing die collected by the vision camera device during the re-cooling process, the optimized cooling conditions are adjusted according to the second image analysis result of the second die surface image until the surface temperature of the 3D printing die is cooled to the preset target surface temperature.

[0152] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the 3D printing die cooling method based on dynamic vision feedback provided by the above-mentioned various methods. The method includes:

[0153] Based on the parameter information obtained from the design drawing of the 3D printing die and combined with the thermophysical properties of the 3D printing material, determine the initial cooling conditions of the 3D printing die during the cooling process;

[0154] In response to the printing start instruction of the 3D printing die, initially cool the 3D printing die during the printing process based on the initial cooling conditions;

[0155] Based on the vision camera device, collect the first die surface image of the 3D printing die during the initial cooling process, and perform feature analysis on the first die surface image to obtain the first image analysis result;

[0156] If it is determined based on the first image analysis result that the surface temperature of the 3D printing die has not reached the preset target surface temperature, then adjust the initial cooling conditions based on the first image analysis result and the preset target surface temperature to obtain the optimized cooling conditions, and re-cool the 3D printing die during the printing process based on the optimized cooling conditions;

[0157] Based on the vision camera device, collect the second die surface image of the 3D printing die during the re-cooling process, and adjust the optimized cooling conditions according to the second image analysis result of the second die surface image until the surface temperature of the 3D printing die is cooled to the preset target surface temperature.

[0158] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0159] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A 3D printing mold cooling method based on dynamic visual feedback, characterized in that: In the printing working area of ​​the 3D printing device, a plurality of visual camera devices are evenly arranged around the mold printing position; the 3D printing mold cooling method based on dynamic visual feedback includes: Determine the initial cooling condition of the 3D printed mold during the cooling process based on the parameter information obtained from the design drawing of the 3D printed mold and the thermophysical properties of the 3D printed material; In response to a printing start instruction of the 3D printing mold, preliminarily cooling the 3D printing mold during the printing process based on the initial cooling condition; Capturing a first mold surface image of the 3D printed mold during the preliminary cooling process based on a visual camera device, and performing feature analysis on the first mold surface image to obtain a first image analysis result; If it is determined based on the first image analysis result that the surface temperature of the 3D printing mold does not reach a preset target surface temperature, the initial cooling condition is adjusted based on the first image analysis result and the preset target surface temperature to obtain an optimized cooling condition, and the 3D printing mold in the printing process is cooled again based on the optimized cooling condition; Based on the visual camera device, a second mold surface image of the 3D printed mold is collected during the re-cooling process, and the optimized cooling condition is adjusted according to the second image analysis result of the second mold surface image until the surface temperature of the 3D printed mold is cooled to the preset target surface temperature.

2. The 3D printing mold cooling method based on dynamic visual feedback according to claim 1 is characterized in that: The adjusting the initial cooling condition based on the first image analysis result and the target surface temperature to obtain the optimized cooling condition includes: Dividing the mold surface of the 3D printed mold into a plurality of hot zones, and performing a thermal field distribution difference analysis on each hot zone based on the temperature data in the first image analysis result to obtain a temperature difference coefficient between each hot zone and the preset target surface temperature; According to the temperature difference coefficient of each hot zone and the mold volume corresponding to each hot zone, combined with the heat exchange principle between the mold and the coolant, the heat capacity adjustment amount of the coolant corresponding to each hot zone is calculated; Based on the coolant mass and specific heat capacity of the coolant flowing through each hot zone, combined with the heat capacity adjustment amount corresponding to the coolant in each hot zone, determine the initial temperature adjustment value of the coolant in each hot zone; The initial cooling condition is adjusted based on the temperature difference coefficient of each hot zone and the initial temperature adjustment value to obtain the optimized cooling condition.

3. The 3D printing mold cooling method based on dynamic visual feedback according to claim 2 is characterized in that: The adjusting the initial cooling condition based on the temperature difference coefficient of each hot zone and the initial temperature adjustment value to obtain the optimized cooling condition includes: Adjusting the initial temperature adjustment value of each hot zone based on the temperature difference coefficient of each hot zone to obtain the target temperature adjustment value of each hot zone; Adjusting the initial cooling flow rate of the coolant in each hot zone based on the target temperature adjustment value of each hot zone to obtain the optimized flow rate of the coolant in each hot zone; Determine the flow adjustment amount of the coolant in each hot zone based on the optimized flow velocity of each hot zone and the cross-sectional area of ​​the cooling channel corresponding to each hot zone; The optimized flow rate and flow adjustment amount of the coolant in each hot zone are determined as the optimized cooling conditions.

4. The 3D printing mold cooling method based on dynamic visual feedback according to claim 1, characterized in that: The parameter information includes size and shape; the parameter information obtained based on the design drawing of the 3D printing mold is combined with the thermophysical properties of the 3D printing material to determine the initial cooling conditions of the 3D printing mold during the cooling process, including: Correcting the original thermal diffusion coefficient of the 3D printing material based on the thermophysical properties of the 3D printing material to obtain a corrected thermal diffusion coefficient of the 3D printing material; The heat flux is estimated based on the mold size and mold shape of the 3D printed mold combined with the corrected thermal diffusion coefficient to obtain the initial heat flux of the mold surface of the 3D printed mold; the mold surface of the 3D printed mold is a uniform heat dissipation surface; Determining a convection heat transfer coefficient between the coolant in the cooling system and the mold surface of the 3D printing mold based on a pipeline structure of the cooling system and flow characteristics of the coolant in the cooling system; The initial cooling condition is determined based on the initial heat flux and the convection heat transfer coefficient; the initial cooling condition includes an initial cooling temperature and an initial cooling flow rate of the coolant in the cooling system.

5. The 3D printing mold cooling method based on dynamic visual feedback according to claim 4 is characterized in that: The determining the initial cooling condition based on the initial heat flux and the convection heat transfer coefficient comprises: Based on the initial heat flux, the convection heat transfer coefficient, the mold mass of the 3D printed mold and the specific heat capacity of the mold material, and the contact surface area between the coolant in the cooling system and the mold surface of the 3D printed mold, an energy transfer prediction is performed to obtain a heat reduction amount; Determining an initial cooling temperature of the coolant in the cooling system based on the heat reduction and a preset target surface temperature of the 3D printed mold; Based on the initial heat flux, the convective heat transfer coefficient, the preset target surface temperature, and the initial cooling temperature, the flow rate is predicted in combination with the density, cooling rate, and constant-pressure specific heat capacity of the coolant in the cooling system to obtain the initial cooling flow rate of the coolant in the cooling system.

6. The 3D printing mold cooling method based on dynamic visual feedback according to any one of claims 1 to 5, characterized in that: The performing feature analysis on the first mold surface image to obtain a first image analysis result includes: converting the first mold surface image from a color image to a grayscale image; Dividing the grayscale image into a plurality of sub-regions, and performing edge detection on each sub-region to obtain edge features of each sub-region; Based on the edge features of each sub-region, a temperature correlation matrix of each sub-region is constructed, and the matrix elements in the temperature correlation matrix represent the degree of temperature correlation between different positions in the sub-region based on the edge features; A fusion analysis is performed based on the edge features and temperature correlation matrix of each sub-region to obtain the first image analysis result.

7. The 3D printing mold cooling method based on dynamic visual feedback according to claim 6, characterized in that: The performing fusion analysis based on the edge features of each sub-region and the temperature correlation matrix to obtain the first image analysis result includes: The edge features and temperature correlation matrix in each sub-region are fused to obtain the temperature feature representation of each sub-region; Integrate the temperature feature representation of each sub-region to obtain the global temperature feature representation; Performing cluster analysis on the global temperature feature representation to cluster sub-regions with similar temperature features into the same category to obtain a clustering result; The clustering result is mapped to the first mold surface image, and different temperature feature categories are represented by different colors to obtain the first image analysis result.

8. A 3D printing mold cooling device based on dynamic visual feedback, characterized in that: Applied to the 3D printing mold cooling method based on dynamic visual feedback as claimed in any one of claims 1 to 8, a plurality of visual camera devices are evenly arranged around the mold printing position in the printing working area of ​​the 3D printing device; the 3D printing mold cooling device based on dynamic visual feedback comprises: An initialization module, used to determine the initial cooling conditions of the 3D printing mold during the cooling process based on the parameter information obtained from the design drawing of the 3D printing mold and the thermophysical properties of the 3D printing material; A mold preliminary cooling module, used to respond to a printing start instruction of the 3D printing mold and perform preliminary cooling on the 3D printing mold during the printing process based on the initial cooling condition; A dynamic visual feedback module, used for collecting a first mold surface image of the 3D printed mold during the preliminary cooling process based on a visual camera device, and performing feature analysis on the first mold surface image to obtain a first image analysis result; A mold re-cooling module, configured to adjust the initial cooling condition based on the first image analysis result and the preset target surface temperature to obtain an optimized cooling condition if it is determined based on the first image analysis result that the surface temperature of the 3D printing mold does not reach a preset target surface temperature, and re-cool the 3D printing mold in the printing process based on the optimized cooling condition; A dynamic feedback cooling module is used to collect a second mold surface image of the 3D printed mold during the re-cooling process based on a visual camera device, and adjust the optimized cooling conditions according to a second image analysis result of the second mold surface image until the surface temperature of the 3D printed mold is cooled to the preset target surface temperature.

9. An electronic device, comprising: Memory for storing computer software programs; A processor, used to read and execute the computer software program, characterized in that when the computer software program is executed by the processor, the 3D printing mold cooling method based on dynamic visual feedback as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer software program stored therein, characterized in that: When the computer software program is executed by a processor, the 3D printing mold cooling method based on dynamic visual feedback as described in any one of claims 1 to 7 is implemented.

Images