Method and system for additive manufacturing of porous bioceramic artificial bone

Abstract

The application discloses a porous bioceramic artificial bone additive manufacturing method and system, relates to the technical field of additive manufacturing, monitors a sintering process and acquires sintering state data, constructs a deviation value of the sintering process after deviation analysis, controls sintering parameters by using a trained sintering parameter control model if the deviation value exceeds expectation, acquires quality data of sintered materials after testing the sintered materials after annealing treatment, evaluates the quality of the sintered materials by using a trained quality identification model, and distinguishes the sintered materials according to the acquired quality score; printing parameters are monitored in real time, a fault value is generated from continuously acquired abnormal data if the printing parameters are abnormal, and printing control parameters are optimized if the acquired fault value exceeds expectation; the cooling speed of the sintered materials is adapted to actual environmental conditions, the influence of the environmental conditions on the sintering process is reduced, and the sintering effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of additive manufacturing, in particular to a porous bioceramic artificial bone additive manufacturing method and system. BACKGROUND

[0002] The additive manufacturing of porous bioceramic artificial bone combines the biocompatibility of bioceramic materials and the precision of additive manufacturing. Through 3D printing technology, artificial bones with complex porous structures can be personalized manufactured, these pores not only simulate the microenvironment of natural bone tissue, but also promote cell growth and vascular ingrowth, accelerating the bone healing process. It shortens the manufacturing cycle, reduces the cost, and also provides a more precise and effective solution for the treatment of bone diseases such as fractures and bone defects.

[0003] In the Chinese invention patent with the authorization announcement number CN108437472B, an additive manufacturing device and an additive manufacturing method are disclosed, wherein the additive manufacturing device includes a ray generating device, the ray generating device includes: a cathode that can emit electrons after being heated; a laser for generating laser, the laser is used for heating the cathode; a grid for converging the electrons to form an electron beam; an anode located below the cathode and arranged to be grounded, a hole is opened in the middle of the anode, and a potential difference for the electron beam to pass through the hole is formed between the anode and the cathode. The present application generates laser by laser, and heats the cathode by laser, so that the cathode generates electrons and forms an electron beam. Compared with the existing technology of electrically heating the cathode, it does not need to heat with large current, avoids the influence of the distribution of electrons caused by the magnetic field generated by the current, improves the service life of the cathode, and also improves the quality of the beam spot during additive manufacturing and the quality and efficiency of additive manufacturing.

[0004] Combining the above application and the content in the prior art:

[0005] When additive manufacturing is performed, a series of processes need to be gone through, such as adjustment of sintering environment, proportioning of sintering materials, control of sintering process, and control of printing process, etc. Any one of the above processes has a fault or an abnormality, which will cause a certain influence on the quality of the final target product.

[0006] In the existing additive manufacturing method of porous bioceramic artificial bone, when improving the quality of the bioceramic product, the main focus is on the quality control of the raw materials, such as adjusting the composition and proportion of the raw materials. However, starting from adjusting the combination of raw materials alone cannot completely guarantee the quality of the porous bioceramic, for example, when there are certain abnormalities in the environmental conditions in the sintering area, especially when there are large fluctuations in temperature and humidity data, and there are many particles in the air, the entire additive manufacturing process will be affected to a certain extent, and the quality of the bioceramic product obtained finally will be affected.

[0007] To this end, the application provides a porous bioceramic artificial bone additive manufacturing method and system. SUMMARY

[0008] (I) Technical problems solved

[0009] In view of the deficiencies in the prior art, the application provides a porous bioceramic artificial bone additive manufacturing method and system, which controls the sintering parameters by using a trained sintering parameter control model, tests the sintered material after annealing treatment to obtain quality data of the sintered material, evaluates the quality of the sintered material using a trained quality identification model, and distinguishes the sintered material according to the obtained quality score; real-time monitoring of the printing parameters, if the printing parameters are abnormal, generating a fault value from the continuously obtained abnormal data, if the obtained fault value exceeds the expectation, optimizing the printing control parameters; the cooling rate of the sintered material is adapted to the actual environmental conditions, reducing the influence of environmental conditions on the sintering process, and improving the sintering effect; thereby solving the technical problems recorded in the background art.

[0010] (II) Technical solutions

[0011] To achieve the above purpose, the application is implemented by the following technical solutions:

[0012] The porous bioceramic artificial bone additive manufacturing method comprises monitoring the environmental conditions in the sintering area, if the current conditions are abnormal, obtaining an abnormal value according to the abnormal environmental condition data analysis, if the abnormal value exceeds the expectation, adjusting the environmental conditions in the sintering area;

[0013] Monitoring the sintering process and obtaining sintering state data, constructing a deviation value of the sintering process after deviation analysis, if the deviation value exceeds the expectation, issuing a parameter optimization instruction to the outside;

[0014] Using a trained sintering parameter control model to control the sintering parameters, and constraining the temperature drop rate when the sintered material is cooled;

[0015] Testing the sintered material after annealing treatment to obtain quality data of the sintered material, evaluating the quality of the sintered material using a trained quality identification model, and distinguishing the sintered material according to the quality score;

[0016] Real-time monitoring of the printing parameters, if the printing parameters are abnormal, generating a fault value from the continuously obtained abnormal data, if the obtained fault value exceeds the expectation, optimizing the printing control parameters.

[0017] Further, the environmental conditions in the sintering area are monitored in real time, and corresponding environmental condition data is obtained. The trained abnormal environment recognition model is used for recognition by taking the environmental condition data as input, to identify whether the current environmental condition is abnormal. If there is an abnormality, an abnormality reminding instruction is sent to the outside;

[0018] The time node when the abnormality instruction is received is recorded, and the corresponding time node is taken as an abnormal node. If the number of abnormal nodes in the pre-set monitoring period exceeds the expectation, the abnormal value is obtained from the environmental abnormality data in the monitoring period.

[0019] Further, after receiving the sintering instruction, the target sintering structure is designed through software, and after selecting the sintering material, the sintering process is expanded and monitored. After summarizing the sintering data obtained in the continuous monitoring period, the sintering state data set is obtained. The sintering state data obtained by monitoring and the reference data value are analyzed for deviation, and the deviation value of the sintering process is constructed from the deviation analysis data.

[0020] Further, after receiving the optimization instruction, the trained sintering parameter control model is used to control the sintering parameters;

[0021] The sintering stage is divided into a pre-sintering stage and a main sintering stage, and the deviation value of the sintering process is taken as the optimization target. The pre-trained genetic algorithm is used to optimize the time length ratio between the pre-sintering stage and the main sintering stage, and the optimized sintering time length ratio is obtained.

[0022] Further, after sintering is completed, the sintering material is cooled, and the temperature drop speed is constrained;

[0023] The sintering material is cooled at a cooling speed that meets the constraint condition until the sintering material is annealed at a pre-set annealing temperature.

[0024] Further, the performance of the sintered material after annealing is tested, and corresponding test data is obtained;

[0025] The microstructure and pore distribution of the material are observed using a scanning electron microscope and a transmission electron microscope, and corresponding material structure data is obtained. The mechanical property data and material structure data obtained are summarized to generate a quality data set of the sintered material.

[0026] Further, the quality data of the sintered material is taken as input, and the trained quality recognition model is used to evaluate the quality of the sintered material, to obtain the quality score of the sintered sample.

[0027] If the quality score obtained is lower than the quality threshold, it is taken as unqualified product, and otherwise it is taken as qualified product. If the proportion of unqualified products exceeds the expectation, the sintering process is optimized.

[0028] Further, the qualified sintering material is used for printing, and the printing process is monitored in real time to obtain corresponding printing control parameters; the trained abnormal data recognition model is used for abnormal recognition with the real-time printing state parameters as input, and if there is an abnormality, the abnormality proportion of the printing state parameters and the corresponding abnormal nodes are obtained; the abnormality proportion of the control parameters and the abnormal nodes are used as abnormal data to generate a printing abnormal data set.

[0029] Further, the fault value is generated from the abnormal data in the printing abnormal data set, and if the obtained fault value exceeds the fault threshold, the abnormal value of the printing control parameter is reduced as an optimization target, and the trained multi-objective optimization algorithm is used to optimize the printing control parameter.

[0030] The porous bioceramic artificial bone additive manufacturing system comprises an environment adjusting unit, which monitors the environmental conditions in the sintering area, and if the current conditions are abnormal, the abnormal value is obtained according to the abnormal environmental condition data analysis, and if the abnormal value exceeds the expectation, the environmental conditions in the sintering area are adjusted.

[0031] The deviation analysis unit monitors the sintering process and obtains sintering state data, and constructs the deviation value of the sintering process after deviation analysis, and if the deviation value exceeds the expectation, a parameter optimization instruction is sent to the outside.

[0032] The temperature control unit uses the trained sintering parameter control model to control the sintering parameters, and constrains the temperature drop speed when the sintering material is cooled.

[0033] The quality recognition unit tests the sintering material after annealing treatment to obtain the quality data of the sintering material, uses the trained quality recognition model to evaluate the quality of the sintering material, and distinguishes the sintering material according to the quality.

[0034] The fault analysis unit monitors the printing parameters in real time, and if the printing parameters are abnormal, the fault value is generated from the continuously obtained abnormal data, and if the obtained fault value exceeds the expectation, the printing control parameter is optimized.

[0035] (Three) beneficial effects

[0036] The present application provides a porous bioceramic artificial bone additive manufacturing method and system, which has the following beneficial effects:

[0037] 1. The abnormal degree of the environmental conditions in the sintering area is judged and evaluated according to the abnormal value, and if the current abnormal degree is large, the environmental conditions are adaptively controlled and adjusted, which can reduce the influence of the environmental conditions on the sintering process and realize the guarantee of the sintering quality.

[0038] 2. By using the deviation value, abnormal values ​​in the sintering process can be judged to determine whether there is an abnormality in the current sintering state. If the sintering state is inconsistent with the expectation and the difference is large, the sintering can be interrupted or adjusted in time to ensure the sintering quality.

[0039] 3. To achieve rapid response and control, reduce the impact of manual delays on sintering results, avoid frequent misjudgments and erroneous operations, and improve sintering efficiency; to constrain the cooling rate by using abnormal environmental conditions, so that the cooling rate of the sintering material is adapted to the actual environmental conditions, reduce the impact of environmental conditions on the sintering process, and improve the sintering effect.

[0040] 4. Based on the obtained test data, the trained quality recognition model is used to evaluate the quality of sintered materials, which is more objective and comprehensive, avoiding incorrect evaluation and material waste. When the current sintering quality fails to meet expectations, the current sintering process is optimized to ensure the sintering quality in subsequent sintering processes.

[0041] 5. Based on the fault values, it is possible to determine whether there is a fault in the current printing process, maintain the printing equipment, or optimize the control parameters in real time, thereby ensuring the quality of additive manufacturing and preventing the failure to handle printing equipment faults in a timely manner. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the process for manufacturing porous bioceramic artificial bone additives according to the present invention;

[0043] Figure 2 This is a schematic diagram of the porous bioceramic artificial bone additive manufacturing system of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Please see Figure 1 This invention provides a method for manufacturing porous bioceramic artificial bone additives, comprising,

[0046] Step 1: Monitor the environmental conditions within the sintering area. If the current conditions are abnormal, analyze the abnormal environmental conditions data to obtain the abnormal values. If the abnormal values ​​exceed expectations, adjust the environmental conditions within the sintering area.

[0047] The step one includes the following contents:

[0048] Step 101, after determining the sintering area of the printing material, the environmental conditions in the sintering area are monitored in real time, and corresponding environmental condition data such as temperature, humidity, and particulate matter concentration are obtained, which are summarized to generate a sintering environment data set;

[0049] The convolutional neural network is trained by the labeled sample data to obtain a trained abnormal environment recognition model. The environmental condition data is used as input to identify whether the current environmental condition is abnormal using the trained abnormal environment recognition model. If there is an abnormality, an abnormality reminding instruction is sent to the outside;

[0050] In use, considering that the environmental condition parameters will cause certain influence and interference to the printing process, by monitoring and identifying the abnormality of the environmental condition in real time, the abnormality of the environmental condition in the sintering area can be perceived and handled in time;

[0051] Step 102, record the time node when the abnormality instruction is received, and take the corresponding time node as an abnormality node;

[0052] If the number of abnormality nodes in the pre-set monitoring period exceeds the expectation, the abnormal value is obtained from the environmental abnormality data in the monitoring period under the dimensionless condition, in the following way: In the formula: is the abnormality degree of the i-th abnormal parameter, is the abnormal value, is the parameter mean, is the standard deviation of the parameter ; is the abnormality occurrence time node of the i-th abnormal parameter, is the time weighting function, , is the decay coefficient, is the total time length, which is the time span from the first abnormality occurrence to the last abnormality occurrence, is the Dirac delta function, which is used to represent the abnormality at time ;

[0053] According to the historical data and the management expectation of the environmental condition, the abnormality threshold value is pre-set;

[0054] If the abnormal value exceeds the abnormality threshold value, it means that the abnormality degree of the environmental condition in the sintering area exceeds the expectation, which may affect the sintering process and the sintering quality. At this time, the environmental condition in the sintering area is adaptively adjusted, for example, the air is filtered;

[0055] In use, the contents in steps 101 and 102 are combined:

[0056] In real-time monitoring of environmental conditions, based on the acquired monitoring data, abnormal values are constructed from the monitoring data, and the abnormal degree of the environmental conditions in the sintering area is judged and evaluated according to the abnormal values. If the current abnormal degree is large, adaptive control and adjustment of the environmental conditions can reduce the influence of the environmental conditions on the sintering process, and realize the guarantee of the sintering quality.

[0057] In combination with the above application and the contents in the prior art:

[0058] When additive manufacturing is performed, a series of processes need to be performed, such as adjustment of the sintering environment, proportioning of the sintering material, control of the sintering process, and control of the printing process. Any one of the above processes has a fault or an abnormality, which will cause a certain influence on the quality of the final target product.

[0059] In the existing porous bioceramic artificial bone additive manufacturing method, when improving the quality of the bioceramic product, the quality control of the raw material is mainly focused on, such as adjusting the composition and proportion of the raw material. However, starting from adjusting the combination of the raw material alone cannot completely realize the quality guarantee of the porous bioceramic, for example, when there is a certain abnormality in the environmental conditions in the sintering area, especially when the temperature and humidity data have large fluctuations, and there are many particles in the air, the entire additive manufacturing process will be affected to a certain extent, and the quality of the finally obtained bioceramic product will be affected.

[0060] Step two, monitoring the sintering process and acquiring sintering state data, constructing the deviation value of the sintering process after deviation analysis, and issuing parameter optimization instructions to the outside if the deviation value exceeds the expectation;

[0061] The step two includes the following contents:

[0062] Step 201, after receiving the sintering instruction, a porous structure is designed by software, the behavior of the porous structure under mechanical load is simulated by FEA, and the target sintering structure is obtained after optimizing the pore size and porosity distribution;

[0063] Selecting sintering materials, such as selecting high-purity ceramic powder with uniform particle size distribution, after surface modification, slurry preparation, adding adhesive and solvent, and high-shear mixing of the configured material, issuing a sintering instruction to the outside;

[0064] Step 202, after receiving the sintering instruction, the sintering process is carried out and monitored, including using differential thermal analysis and thermogravimetric analysis to monitor the thermal behavior data and mass change data in the sintering process, using an optical microscope or an infrared thermal imager to monitor the temperature distribution state and material change data in the sintering process; after collecting the sintering data in a plurality of continuous monitoring periods, the sintering state data set is obtained;

[0065] In use, by detecting and monitoring the sintering process, the current material sintering state can be understood in real time, and intervention can be made in time when the sintering state is abnormal.

[0066] Step 203, after setting the reference data values of each stage and each parameter of the sintering process, deviation analysis is performed on the sintering state data and the reference data values obtained by monitoring, and the deviation value of the sintering process is constructed from the deviation analysis data, as follows: In the formula: is the diagonal matrix of the standard deviation; For each time node , the deviation value vector of the monitoring parameter, wherein is the actual value vector at time ; is the reference vector value; , wherein represents the norm of the standardized deviation value vector, and the norm (i.e. Euclidean norm) is usually selected; is the total number of monitoring parameters, is the total length of time; , is the attenuation coefficient, is the component in the standardized deviation value vector;

[0067] According to historical data and management expectations of sintering progress and sintering state, a deviation threshold is set in advance; if the deviation value exceeds the pre-set deviation threshold, it means that the sintering state of the current stage may be poor, and the control parameters of the sintering process need to be adjusted and optimized in time, at which time a parameter optimization instruction is sent to the outside;

[0068] In use, in combination with the contents in steps 201 to 203:

[0069] After continuously obtaining a plurality of sets of sintering state data, the qualified values of each parameter are set in advance, and on this basis, the deviation value is constructed from the comparison data, the abnormal value of the sintering process can be judged through the deviation value, whether the current sintering state is abnormal is determined, if the sintering state and the expectation are inconsistent and the gap is large, the sintering can be interrupted or adjusted in time, and the sintering quality is guaranteed.

[0070] Step three, using the trained sintering parameter control model to control the sintering parameters, and restricting the temperature drop speed when the sintering material is cooled;

[0071] The step three includes the following contents:

[0072] Step 301, training a machine learning algorithm from the labeled sample data to obtain a trained sintering parameter control model; setting a corresponding target range for each sintering parameter, and after receiving an optimization instruction, using the trained sintering parameter control model to control the sintering parameters;

[0073] The sintering stage is divided into a pre-sintering stage and a main sintering stage, and the deviation value of the sintering process is reduced as an optimization target, and the pre-trained genetic algorithm is used to optimize the time length ratio between the pre-sintering stage and the main sintering stage to obtain an optimized sintering time length ratio;

[0074] In use, through automatic control of the sintering control parameters, on the basis of real-time automatic identification of the sintering parameters, rapid response and response can be realized, the influence of manual lag operation on the sintering effect is reduced, and frequent occurrence of incorrect judgment and incorrect operation is avoided, and the sintering efficiency is improved.

[0075] Step 302, after sintering is completed, the sintering material is cooled, and the temperature drop speed is constrained, and the constraint method is as follows: The weight coefficient, , n is the number of cooling stages, is the time interval from the i th cooling stage to the j th cooling stage, is the average value of the time interval between the cooling stages;

[0076] The sintering material is cooled at a cooling speed that meets the constraint condition until the sintering material is annealed at a preset annealing temperature;

[0077] In use, in combination with the contents in steps 301 to 302:

[0078] Considering that the environmental conditions in the sintering area may be abnormal, on the basis of the environmental condition data in each stage, the abnormal value of the environmental condition is used to constrain the cooling speed, so that the cooling speed of the sintering material is adapted to the actual environmental condition, the influence of the environmental condition on the sintering process is reduced, and the sintering effect is improved.

[0079] Step four, after annealing treatment, test the sintered material to obtain the quality data of the sintered material, use the trained quality identification model to evaluate the quality of the sintered material, and distinguish the sintered material according to the quality score;

[0080] The step four includes the following contents:

[0081] Step 401, test the sintered material after annealing treatment for performance, and obtain the corresponding test data, including mechanical property data such as compressive strength, bending strength and fatigue strength;

[0082] Use scanning electron microscope and transmission electron microscope to observe the microstructure and pore distribution of the material, and obtain the corresponding material structure data; The mechanical property data and material structure data are summarized to generate the quality data set of the sintered material;

[0083] Step 402, train the convolutional neural network from the labeled sample data, obtain the trained quality identification model; Use the trained quality identification model to evaluate the quality of the sintered material with the quality data of the sintered material as input, obtain the quality score of the sintered sample, and label the sintered material with the obtained quality score;

[0084] According to the management expectation of sintering quality, the quality threshold is set in advance. If the obtained quality score is lower than the quality threshold, it means that the current sintering quality is poor and may not meet the use conditions, then it is regarded as unqualified product, on the contrary, it is regarded as qualified product;

[0085] If the proportion of unqualified products exceeds the expectation, optimize the sintering process, for example, adjust the environmental conditions in the sintering area, the component ratio of the sintered material and the sintering temperature, etc;

[0086] In use, combined with the contents in steps 401 and 402:

[0087] After completing the sintering process, by testing and detecting the sintered material, based on the obtained detection data, using the trained quality identification model to evaluate the quality of the sintered material, compared with artificial evaluation, the objectivity and comprehensiveness are better, compared with artificial screening, it can also avoid wrong evaluation and material waste; As a further content, when the current sintering quality fails to meet the expectation, by optimizing the current sintering process, in the subsequent sintering process, the sintering quality is guaranteed.

[0088] Step five, real-time monitoring of printing parameters, if the printing parameters are abnormal, generate fault value from the continuously obtained abnormal data, if the obtained fault value exceeds the expectation, optimize the printing control parameters;

[0089] The step five includes the following contents:

[0090] Step 501, using qualified sintered material for printing and monitoring the printing process in real time, obtaining corresponding printing control parameters such as printing speed, layer thickness and laser power, etc.; training a convolutional neural network from the labeled sample data to obtain a trained abnormal data recognition model;

[0091] Using real-time printing state parameters as input, using the trained abnormal data recognition model for abnormal recognition, if there is an abnormality, obtaining the abnormality proportion of the corresponding printing state parameter and the corresponding abnormal node; using the abnormality proportion of the control parameter and the abnormal node as abnormal data to generate a printing abnormal data set;

[0092] Step 502, under dimensionless conditions, generating a fault value from the abnormal data in the printing abnormal data set, in the following manner: In the formula: is a vector weight, each element represents the weight of the i-th parameter, is the number of abnormal nodes, represents each element represents whether the i-th parameter is abnormal at time , represents abnormality, represents normality, is the transpose of the weight vector ;

[0093] According to historical data and management expectations of printing quality, a fault threshold is set in advance;

[0094] If the obtained fault value exceeds the fault threshold, it means that the current printing process may have faults or abnormalities, which needs to be adjusted or optimized. At this time, an adjustment instruction is sent to the outside;

[0095] Step 503, after receiving the adjustment instruction, taking the abnormal value of the printing control parameter as the optimization target, using the trained multi-objective optimization algorithm to optimize the printing control parameter, such as adjusting the printing speed, layer thickness, laser power and other parameters, etc., executing the optimized printing control parameter until the printing process is completed;

[0096] In use, the contents in steps 501 to 503 are combined:

[0097] When entering the additive manufacturing stage and starting printing, the printing process parameters are monitored, the fault value is generated according to the change and abnormality degree of the printing parameters, and whether the current printing process exists fault can be judged according to the fault value, at this time, after investigation, if the printing equipment exists fault, the printing equipment can be maintained, if the printing equipment currently does not exist fault, the control parameters and printing process may exist defects, the control parameters are optimized in real time, the additive manufacturing quality is guaranteed, and the printing equipment can be processed in time when the printing equipment fails.

[0098] Please refer to Figure 2 The application provides a porous bioceramic artificial bone additive manufacturing system, comprising,

[0099] An environment adjusting unit is arranged to monitor the environmental conditions in the sintering area, and if the current conditions are abnormal, an abnormal value is obtained according to the abnormal environmental condition data analysis, and if the abnormal value exceeds the expectation, the environmental conditions in the sintering area are adjusted.

[0100] A deviation analysis unit is arranged to monitor the sintering process and obtain sintering state data, and after deviation analysis, a deviation value of the sintering process is constructed, and if the deviation value exceeds the expectation, a parameter optimization instruction is sent to the outside.

[0101] A temperature control unit is arranged to control the sintering parameters using the trained sintering parameter control model, and constrain the temperature drop speed when the sintering material is cooled.

[0102] A quality identification unit is arranged to test the sintering material after annealing treatment and obtain the quality data of the sintering material, evaluate the sintering material quality using the trained quality identification model, and distinguish the sintering materials according to the quality.

[0103] A fault analysis unit is arranged to monitor the printing parameters in real time, if the printing parameters are abnormal, a fault value is generated from the continuously obtained abnormal data, and if the obtained fault value exceeds the expectation, the printing control parameters are optimized.

[0104] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0105] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device, and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0107] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices, or units, which can be electrical, mechanical, or other forms.

[0108] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0109] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0110] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for manufacturing porous bioceramic artificial bone additives, characterized in that: include, Monitor the environmental conditions within the sintering area. If the current conditions are abnormal, analyze the abnormal environmental condition data to obtain abnormal values. If the abnormal values ​​exceed expectations, adjust the environmental conditions within the sintering area. The sintering process is monitored and sintering state data is acquired. After deviation analysis, the deviation value of the sintering process is constructed. If the deviation value exceeds the expectation, a parameter optimization command is sent to the outside. The sintering parameters are controlled using a trained sintering parameter control model, and the rate of temperature decrease is constrained when the sintered material is cooled. After testing the annealed sintered material, the quality data of the sintered material is obtained. The trained quality recognition model is used to evaluate the quality of the sintered material and the sintered material is distinguished according to the quality score. Real-time monitoring of printing parameters; if abnormalities are found in the printing parameters, a fault value is generated from the continuously acquired abnormal data; if the acquired fault value exceeds expectations, the printing control parameters are optimized. The environmental conditions within the sintering area are monitored in real time to obtain relevant environmental condition data. Using the environmental condition data as input, the trained abnormal environment recognition model is used to identify whether the current environmental conditions are abnormal. If an abnormality is found, an abnormality alert command is sent to the outside. Record the time node when the abnormal command is received, and take the corresponding time node as the abnormal node; if the number of abnormal nodes in the pre-set monitoring period exceeds the expectation, obtain the abnormal value from the analysis of environmental abnormal data in the monitoring period. Upon receiving the sintering instruction, the target sintering structure is designed through software. After selecting the sintering material, the sintering process is initiated and monitored. The sintering data acquired over several consecutive monitoring periods are summarized to obtain a set of sintering state data. Deviation analysis is performed on the acquired sintering state data and reference data values, and the deviation values ​​of the sintering process are constructed from the deviation analysis data. Upon receiving the optimization instruction, the trained sintering parameter control model is used to control the sintering parameters; The sintering stage is divided into a pre-sintering stage and a main sintering stage. With the goal of reducing the deviation value of the sintering process, a pre-trained genetic algorithm is used to optimize the time ratio between the pre-sintering stage and the main sintering stage to obtain the optimized sintering time ratio. Use qualified sintering materials for printing and monitor the printing process in real time to obtain the corresponding printing control parameters; Using real-time printing status parameters as input, an anomaly identification model is used to identify anomalies. If an anomaly is found, the anomaly ratio of the corresponding printing status parameters and the corresponding anomaly nodes are obtained. The anomaly ratio of the control parameters and the anomaly nodes are then used as anomaly data to generate a printing anomaly data set. Fault values ​​are generated from the abnormal data in the print anomaly dataset. If the obtained fault value exceeds the fault threshold, the print control parameters are optimized using a trained multi-objective optimization algorithm with the goal of reducing the abnormal values ​​of the print control parameters.

2. The method for manufacturing porous bioceramic artificial bone additives according to claim 1, characterized in that: After sintering, the sintered material is cooled down, and the rate of temperature drop is constrained. The sintered material is cooled at a rate that meets the constraints until it reaches the preset annealing temperature, at which point the sintered material is annealed.

3. The method for manufacturing porous bioceramic artificial bone additives according to claim 2, characterized in that: The performance of the annealed sintered material was tested, and the corresponding test data were obtained. The microstructure and pore distribution of the material are observed using scanning electron microscopy and transmission electron microscopy to obtain the corresponding material structure data; the obtained mechanical property data and material structure data are summarized to generate a quality data set of sintered materials.

4. The method for manufacturing porous bioceramic artificial bone additives according to claim 3, characterized in that: Using the quality data of sintered materials as input, the trained quality recognition model is used to evaluate the quality of the sintered materials and obtain the quality score of the sintered samples. If the obtained quality score is lower than the quality threshold, it is regarded as a defective product; otherwise, it is regarded as a qualified product. If the proportion of defective products exceeds the expectation, the sintering process is optimized.

5. A porous bioceramic artificial bone additive manufacturing system, using the method according to any one of claims 1 to 4, characterized in that: include, The environmental control unit monitors the environmental conditions within the sintering area. If the current conditions are abnormal, it analyzes the abnormal environmental condition data to obtain abnormal values. If the abnormal values ​​exceed expectations, it adjusts the environmental conditions within the sintering area. The deviation analysis unit monitors the sintering process and acquires sintering state data. After performing deviation analysis, it constructs the deviation value of the sintering process. If the deviation value exceeds the expectation, it sends parameter optimization instructions to the outside. The temperature control unit uses a trained sintering parameter control model to control the sintering parameters and constrains the rate of temperature drop when the sintered material is cooled. The quality identification unit tests the annealed sintered material to obtain the quality data of the sintered material, uses the trained quality identification model to evaluate the quality of the sintered material, and distinguishes the sintered material according to the quality score. The fault analysis unit monitors printing parameters in real time. If there are abnormalities in the printing parameters, it generates fault values ​​from the continuously acquired abnormal data. If the acquired fault values ​​exceed expectations, it optimizes the printing control parameters.

Images