3D printing product quality evaluation system

Abstract

The invention provides a 3D printing product quality evaluation system, and the system comprises a pre-printing self-diagnosis module which is used for classifying the data of each subunit of 3D printing equipment, calculating the health degree Si of each type of data, and carrying out the weighted summation of each type of health degree Si, so as to obtain a health score S1 of the pre-printing self-diagnosis module; the in-printing key part fault diagnosis module is used for diagnosing the health degree Sj of each driving part in the printing process of the 3D printing equipment and performing weighted summation on the health degree Sj of each driving part to obtain a health score S2 of the in-printing key part fault diagnosis module; the printing process key parameter monitoring module is used for monitoring the health score Sk of each parameter in the printing process and performing weighted summation on each health score Sk to obtain a health score S3 of the key parameter monitoring module in the printing process; the printing process powder laying and ink jetting quality monitoring module is used for calculating the ink jetting abnormal rate delta l and the powder laying defect area alpha in the printing process and calculating the health score S4 of the printing process powder laying quality monitoring module according to the ink jetting abnormal rate delta l and the powder laying defect area alpha; and the comprehensive evaluation module performs weighted summation on the health squares S1, S2, S3 and S4 of the modules to obtain a comprehensive health score S. The system can timely stop defects which are difficult to repair in the product printing process and is convenient for tracing product quality problems.

Description

Technical Field

[0001] The present invention relates to the field of binder jetting 3D printing, and in particular, to a 3D printing product quality assessment system. Background Art

[0002] Binder jet 3D printing is an additive manufacturing method that uses a binder to bond material powder layer by layer to achieve product stacking and forming. The advantage of this method is that it has high printing efficiency and can be applied in batches. In the actual production process, the quality of printed products will be affected by many factors. First, the binder will undergo a certain chemical reaction after being sprayed onto the material powder plane, so the temperature and humidity of the printing site and the material powder will affect the curing of the product; secondly, during the printing process, the material powder will be evenly spread on the working plane according to a certain thickness, so the uniformity and flatness of the material powder laying will directly affect the density and integrity of the printed product; then, the print head will spray out the preset pattern layer by layer to bond the material powder, and the integrity of the printed pattern will directly affect whether the material is successfully bonded and firm and reliable. The above processes will have a direct impact on the quality of the printed product. In addition, the stability of each system during the operation of the equipment will also affect the product quality, such as whether the communication connection between the equipment systems is normal, whether the printer hardware such as the motor and module are normal, and whether the pressure control of the ink system is normal; in summary, any system failure during the binder jet 3D printing process may affect the final product quality.

[0003] At present, the quality problems of printed products can only be fully exposed after printing is completed or even sintering is completed. The industry lacks the means and solutions to evaluate the quality of the final product using the monitoring data of the production process. When irreparable defects occur during the printing process and are not stopped in time, the time, raw materials, and manpower invested from the occurrence of the defect to the end of printing are all invalid costs. Secondly, the current way of evaluating product quality in the industry only focuses on judging the appearance by the naked eye or testing the final product through instruments, and lacks the establishment of a mapping exploration from the various data monitoring of the production process to the quality of the final printed product. As a result, it is difficult to trace the quality problems of the product back to the production process after sintering or putting it into use, resulting in a lack of data support for the analysis of the causes of quality problems. Summary of the invention

[0004] Based on this, it is necessary to provide a 3D printing product quality assessment system to address the problems in the prior art that difficult-to-repair defects cannot be stopped in time during the printing process and that quality problems of printed products are difficult to trace. The system can stop difficult-to-repair defects in time during the product printing process and facilitate the tracing of product quality problems.

[0005] A 3D printing product quality assessment system, the 3D printing product quality assessment system comprising:

[0006] The pre-printing self-diagnosis module is used to classify the data of each subunit of the 3D printing equipment and calculate the health level S of each type of data. i , and for each type of health S i The health score S1 of the pre-printing self-diagnosis module is obtained after weighted summation;

[0007] The fault diagnosis module for key components in printing is used to diagnose the health of each drive component during the printing process of 3D printing equipment. j , and the health of each drive component S j The health score S2 of the fault diagnosis module of key components in printing is obtained by weighted summation;

[0008] Printing process key parameter monitoring module, used to monitor the health score S of each parameter during the printing process k , and give each health score S k Perform weighted summation to obtain the health score S3 of the key parameter monitoring module during printing;

[0009] The printing process powder laying inkjet quality monitoring module is used to calculate the inkjet abnormality rate δ during the printing process l and the powder spreading defect area α, and according to the inkjet abnormality rate δ l The health score S4 of the powder spreading quality monitoring module during the printing process is calculated with the powder spreading defect area α;

[0010] The comprehensive evaluation module obtains the comprehensive health score S by weighted summing up the health scores S1, S2, S3, and S4 of the above modules.

[0011] Furthermore, the 3D printing product quality assessment system also includes:

[0012] The report generation module is used to generate a health report of the 3D printing device, which includes the health score S1 of the self-diagnosis module before printing, the health score S2 of the key component fault diagnosis module during printing, the health score S3 of the key parameter monitoring module during printing, and the health score S4 of the powder quality monitoring module during printing. 4、 Comprehensive health score S.

[0013] Furthermore, the health report also includes the health level S of each subunit. i , Health of each drive component S j , health score S of each parameter k 、Inkjet abnormality rateδ l And the defect area α of the powdering surface.

[0014] Furthermore, in the pre-printing self-diagnosis module, the data of each subunit is classified into Boolean data, continuous data, error judgment data and continuous periodic data, and the score S of each type of data is calculated according to the following formula: i ,

[0015]

[0016] Where X i is the detection value, is to set the threshold, α is the proportional weight of the score when the parameter is not in the completely safe interval, and β is to control the distribution of the completely safe parameter interval.

[0017] Furthermore, in the fault diagnosis module for key components in printing, the health status S of each driving component j The calculation formula is as follows:

[0018]

[0019] In the above formula, N is a printing cycle T divided into N time periods. The number of safe operation periods for the drive.

[0020] Furthermore, the operation of each of the driving components is divided into a safety domain [0, μ j ], alert domain [μ j ,v j ], shutdown domain [v j ,1], For each driver in the safety domain [0,μ j ] time periods.

[0021] Furthermore, the health score S of each parameter in the printing process key parameter monitoring module is k The calculation formula is as follows:

[0022]

[0023] In the above formula, σ is the variance of each parameter in a monitoring period. is the standard deviation of each parameter; μ is the mean value of each parameter in a monitoring period, is the standard mean of the parameter; ρ is the extreme value of each parameter in a monitoring period; N s N is the number of times each parameter monitoring value exceeds the safe fluctuation range. w The number of times each parameter monitoring value exceeds the warning zone.

[0024] Furthermore, the powder spreading defect area α includes the powder shortage area Powder pile area Scratch area

[0025] Furthermore, in the printing process powder spreading inkjet quality monitoring module, the powder spreading quality monitoring module health score S4 calculation formula is as follows:

[0026]

[0027] In the above formula, η l is the abnormal area of ​​inkjet; w e ,w p ,w s ,w δ ,w η Respectively represent the sensitivity coefficient of each layer score to the powder shortage area, powder pile area, scratch area, inkjet abnormality rate and inkjet abnormality area, N l Indicates the total number of layers.

[0028] Furthermore, the weighted summation calculation formula of the comprehensive health score S is as follows:

[0029] S=w1S1+w2S2+w3S3+w4S4, where w1, w2, w3, w4 are the weights of the health scores of each module.

[0030] The present invention provides a 3D printing product quality assessment system, which constructs a 3D printing product quality assessment system from four dimensions: pre-printing diagnosis, health status of key components in printing, health status of key parameters in printing, and defects in powdering and inkjet during printing. The system not only pays attention to the health status of the equipment, environmental conditions, etc., but also uses artificial intelligence methods to intelligently detect defects and faults that may occur during the printing process. The evaluation score output by the system and all the data recorded in the process will be associated with the quality problems that may occur after the product is delivered, providing a traceability basis for quality problems generated during the use of the product, and providing data support for equipment design and process improvement. In addition, the 3D printing quality assessment system provided by the present invention can monitor the printing quality of 3D printing equipment in a full process and in an all-round manner. When quality problems occur during the application of 3D printing products, the health report can be compared to quickly find out which link or which parameter or which component in the 3D printing process has problems, so that the staff can repair and adjust them in time; in addition, when important parameters related to the quality of the printed product have problems during the printing process, the system can issue an alarm to remind the staff to shut down the machine for emergency repairs to avoid greater losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is the pre-printing self-diagnosis module of the present invention;

[0032] Figure 2 It is a powder spreading and inkjet quality monitoring module for the printing process of the present invention;

[0033] Figure 3This is a flow chart of the 3D printing product quality assessment system of the present invention. DETAILED DESCRIPTION

[0034] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly understood.

[0035] It should be noted that when an element is referred to as being "disposed on" another element, it may be directly on the other element or there may be a centered element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a centered element at the same time. The terms "vertical", "horizontal", "left", "right", "top", "bottom", "bottom end", "top end" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0037] The present invention provides a 3D printing product quality assessment system, the 3D printing product quality assessment system comprising:

[0038] The pre-printing self-diagnosis module is used to classify the data of each subunit of the 3D printing equipment and calculate the health level S of each type of data. i , and for each type of health S i The health score S1 of the pre-printing self-diagnosis module is obtained after weighted summation;

[0039] The fault diagnosis module for key components in printing is used to diagnose the health of each drive component during the printing process of 3D printing equipment. j , and the health of each drive component S j The health score S2 of the fault diagnosis module of key components in printing is obtained by weighted summation;

[0040] Printing process key parameter monitoring module, used to monitor the health score S of each parameter during the printing process k , and perform weighted summation of each health score Sk to obtain the health score S3 of the key parameter monitoring module during the printing process;

[0041] The printing process powder laying inkjet quality monitoring module is used to calculate the inkjet abnormality rate δ during the printing process l and the powder spreading defect area α, and according to the inkjet abnormality rate δ l The health score S4 of the powder spreading quality monitoring module during the printing process is calculated with the powder spreading defect area α;

[0042] The comprehensive evaluation module obtains the comprehensive health score S by weighted summing up the health squares S1, S2, S3, and S4 of the above modules.

[0043] The present invention provides a 3D printing product quality evaluation system, which evaluates the entire printing process from four dimensions: the health of the 3D printing equipment before printing, the health of key components during printing, the health of key parameters during printing, and the health of powder and inkjet during printing. Each evaluation module will calculate and score each evaluation object involved in the module, and the scores of each evaluation object are weighted and summed according to importance to obtain the health score of the module. The health scores of each module are then weighted and summed according to the importance of each module to obtain the health score of the final 3D printed product. The score comprehensively determines the quality of the final printed product through the static and dynamic health of the printing equipment, the health of the equipment parameters, and the health of the layer-by-layer printing tasks, and quantitatively evaluates it through the health score, so that the quality of the printed product is associated and mapped with the production process, solving the problem that the quality of the printed product was difficult to trace back to the printing process in the past. The system helps to trace the process of printing product quality problems, and then helps design and development personnel to improve the production process in a targeted manner.

[0044] The 3D printing product quality assessment system is described below in conjunction with specific embodiments to further understand the inventive concept of the 3D printing product quality assessment system.

[0045] In one embodiment, if Figure 1-3 As shown, a 3D printing product quality assessment system includes: a pre-printing self-diagnosis module, a key component fault diagnosis module during printing, a printing process key parameter monitoring module, a printing process powder laying and inkjet quality monitoring module and a comprehensive evaluation module.

[0046] The pre-printing self-diagnosis module is used to classify the data of each subunit of the 3D printing equipment and calculate the health level S of each type of data. i , and for each type of health S i The health score S1 of the pre-printing self-diagnosis module is obtained after weighted summation; specifically, Figure 1As shown in FIG. 1 , the pre-printing self-diagnosis module performs a comprehensive inspection of each subunit involved in the operation of the 3D printing device before the device starts printing. The subunits to be inspected include the software unit, the communication unit, the sand mixing unit, the liquid material unit, the inkjet unit, the lifting unit, the sand laying unit, and the environmental data. The above subunits involve different types of data. The data of the above subunits are classified according to the data type, and finally the health level S of each type of data is calculated. i , and for each type of health S i The health score S1 of the pre-printing self-diagnosis module is obtained by weighted summation. The calculation formula of the health score S1 is as follows:

[0047]

[0048] In the above formula, S i is the health of each type of data, w i is the importance weight corresponding to this type of data, which is used to control the contribution of this type of data to the health score S1 of the module.

[0049] The fault diagnosis module for key components in printing is used to diagnose the health of each drive component during the printing process of 3D printing equipment. j , and the health of each drive component S j The health score S2 of the fault diagnosis module of key components in printing is obtained by weighted summation. There are many motion mechanisms in the 3D printing equipment, and these motion mechanisms are driven by corresponding drivers such as motors, such as sanding devices, print heads, and work box lifting mechanisms. The health of the above motion mechanisms is directly related to whether the printing task can be executed. If a sudden failure occurs in the motion mechanism during printing, the current printing task will be forced to be interrupted, and the semi-finished products printed before will also become waste. Therefore, before the failure occurs, the impending failure is warned, so that maintenance personnel can prepare to repair the failure in advance, or prepare for unrepairable failures in advance, which can effectively deal with unplanned downtime and the resulting waste, and improve the operation efficiency of the equipment. The fault diagnosis module of key components in printing realizes fault diagnosis and warning by monitoring the stable operation data and fault operation data of the key motors of the 3D printing equipment. The type of data collected is selected according to the specific situation of the motor, such as the current, load or vibration data of the motor. The real-time monitoring data will be sent to the algorithm model to diagnose the potential fault type and output the probability of a certain fault. It should be noted that, for example, methods such as self-organizing map neural network algorithms and deep learning can be used to issue early warnings some time before a fault occurs and diagnose the type of equipment failure. The calculation formula for the health score S2 is as follows:

[0050]

[0051] In the above formula, w j is the importance weight of the j-th motor to the overall printing task of the device.

[0052] Printing process key parameter monitoring module, used to monitor the health score S of each parameter during the printing process k , and give each health score S k The weighted sum is performed to obtain the health score S3 of the key parameter monitoring module during the printing process. 3D printing involves multiple sub-units. During the printing process, each system protects some parameters that need to be maintained within a certain range at all times. Once the parameter exceeds the predetermined standard range, the quality of the printed product will be directly affected. Therefore, it is necessary to monitor and count the various parameters directly related to product quality during the printing process. The monitored parameters mainly include temperature and humidity, such as the temperature and humidity of the printing room, the temperature of the sand before and after sand mixing, the temperature of the sand surface, the temperature and humidity of the workshop, the temperature of the liquid material, etc., which will affect the temperature and humidity parameters of the bonding reaction; they also include pressure values, such as circulating negative pressure, ink cartridge negative pressure, and other parameter values ​​that affect the supply of liquid materials. In addition, the following error, load fluctuation, and liquid material consumption of the motion system should also be counted. The above parameters should be fully collected throughout the entire printing cycle. Each parameter has a safe fluctuation domain, and on this basis there is also a warning domain. For example, the range of the safe fluctuation domain is (x1, y1) and the range of the warning domain is (x, y), where x<x1<y1<y, when <x and / or When , it means that the parameter fluctuates abnormally and may affect the printing task. When the printing task is completed, each monitoring parameter in the entire cycle is statistically calculated, and the variance σ, mean μ, extreme value ρ, and the number of times N that the parameter exceeds the safe fluctuation range are output. s , the number of times exceeding the alert zone is N w . The health score S of each parameter is calculated by the algorithm k ,Finally, the health score S3 calculation formula of the key parameter monitoring module of the printing process is as follows:

[0053]

[0054] The printing process powder spreading quality monitoring module is used to calculate the inkjet abnormality rate δ during the printing process l and the powder spreading defect area α, and according to the inkjet abnormality rate δ l The health score S4 of the printing process powder spreading quality monitoring module is calculated with the powder spreading defect area α. Figure 2 As shown in the figure, the module uses a visual sensor to collect the powder bed's powder laying result image and inkjet result image in real time, and uses a deep neural network algorithm to monitor the defects on the printing plane in real time. The defect information output by this module is shown in Table 1:

[0055] Table 1 Output information of the visual monitoring system for the powder laying and inkjet quality of the printer process

[0056]

[0057]

[0058] According to the above information, when the defect index of a layer exceeds the safety threshold during printing, an alarm should be sounded immediately to stop the machine and notify the operator to intervene and repair it, because the inkjet abnormality rate δ l , Abnormal inkjet area η l The defect area of ​​the powder spreading surface is directly related to the printing quality. When the above indicators exceed the safety threshold, the printed product will have defects. The health of the powder spreading quality monitoring module during the printing process can be calculated through the above indicators S4.

[0059] like Figure 3 As shown, the comprehensive evaluation module obtains the comprehensive health score S by weighted summing up the health scores S1, S2, S3, and S4 of the above modules. The weighted summing algorithm is as follows:

[0060] S=w1S1+w2S2+w3S3+w4S4

[0061] Where w1, w2, w3, and w4 are the weights of the health scores of each module.

[0062] In another embodiment, in the pre-printing self-diagnosis module, the data of each subunit is classified according to the characteristics of the data of each subunit. After statistics, each subunit may involve 4 different types of data, which are specifically divided into Boolean data, continuous data, error judgment data and continuous periodic data. The health judgment method of different types of data is different, among which the Boolean data judgment method is binary, that is, normal / abnormal. For example, whether the communication between the upper and lower computers of the printer is normal, when the communication is normal, True is returned, otherwise False is returned; continuous data counts whether the value is within the standard range within a period of time before the power-on, such as whether the temperature of the printing room is maintained within a certain range. Error judgment data calculates the deviation between the instruction data and the actual execution data, and judges whether the current data is normal based on whether the deviation is less than the specified threshold. For example, let the printer X-axis move 100mm, and measure whether the deviation between the actual stop position and 100mm is less than the specified error. Continuous periodic data determines its health status by recording whether the fluctuation of data in a single cycle is within the normal range. The pre-printing self-diagnosis module detects the relevant parameters of each subunit, and after statistically classifying the parameter types of each subunit according to data classification, the score S of each type of data is calculated according to the following formula: i ,

[0063]

[0064] Where X i is the detection value, is to set the threshold, α is the proportional weight of the score when the parameter is not in the completely safe interval, and β is to control the distribution of the completely safe parameter interval. It should be noted that for Boolean data, Δ=1, α=1, β=0 in the above formula.

[0065] In another embodiment, in the fault diagnosis module for key components in printing, when the printing task starts, the module starts to collect data and predict the probability of failure. First, the interval [0,1] is divided into a safety domain Warning Zone And the shutdown domain Where 0<μ j <ν j <1. When the probability of the Jth motor failure is greater than v j When the printing task is successfully completed, the distribution of the probability of failure in the entire printing cycle is counted, and the health of the motor components is evaluated using the distribution statistics. Specifically, the entire printing cycle T is evenly divided into N time periods, and the time occupied by each time period is T / N. The distribution of the fault warning probability value output by the model in each time period is counted. When the fault probability at a certain moment in the current time period appears in the alert domain, the fault warning probability value is generated. If the failure probability in this period is within the safety domain, the period is marked as a warning period. Finally, the number of safe periods is calculated. The proportion of the total time period, and the proportion is multiplied by 100 as the health score of the j-th motor, that is, Finally, according to the previous formula, the health scores of all motors are weighted and summed to obtain the health score of the fault diagnosis module of key components of the printing equipment.

[0066] In another embodiment, the calculation formula of the health score Sk of each parameter in the printing process key parameter monitoring module is as follows:

[0067]

[0068] In the above formula, w σ , w μ , w ρ , w s , w w They are all greater than 0 and less than 1, representing the importance weight of the corresponding item; represents the score assigned to the kth parameter, and Where N3 represents the number of detection parameters; σ is the variance of each parameter in a monitoring period, is the standard deviation of each parameter; μ is the mean value of each parameter in a monitoring period, is the standard mean of the parameter; ρ is the extreme value of each parameter in a monitoring period; N s N is the number of times each parameter monitoring value exceeds the safe fluctuation range. w The number of times each parameter monitoring value exceeds the warning domain; These are the standard deviations and standard extreme values ​​of each parameter under normal printing conditions of the 3D printing equipment.

[0069] In another embodiment, the powder spreading defect area α includes a powder shortage area Powder pile area Scratch area In the printing process powder spreading and inkjet quality monitoring module, the powder spreading quality monitoring module health score S4 calculation formula is as follows:

[0070]

[0071] In the above formula, η l is the abnormal area of ​​inkjet; w e ,w p ,w s ,w δ ,w η Respectively represent the sensitivity coefficient of each layer score to the powder shortage area, powder pile area, scratch area, inkjet abnormality rate and inkjet abnormality area, N l Indicates the total number of layers.

[0072] In another embodiment, the 3D printing product quality assessment system further includes a report generation module, which is used to generate a health report of the 3D printing device, wherein the health report includes a health score S1 of the self-diagnosis module before printing, a health score S2 of the key component fault diagnosis module during printing, a health score S3 of the key parameter monitoring module during printing, and a health score S4 of the powder quality monitoring module during printing. 4、 The comprehensive health score S. Furthermore, the health report also includes the health level S of each subunit. i , Health of each motor S j , health score S of each parameter k 、Inkjet abnormality rateδ l And the defect area α of the powdering surface.

[0073] In this embodiment, after the 3D printed product is completed, if there is a quality problem when it is applied, the cause of the problem can be traced in the health report, so that the staff can repair the 3D printing equipment in time to prevent the same problem from recurring in the printed product. For example, for 3D printed sand molds, the sand mold is used for casting. After the casting is completed, the casting is quality inspected. When the casting is found to be defective, the health report generated by the quality assessment system when printing the corresponding sand mold can be compared. First, it can be determined which module has a lower health score, and then it can be determined that the module may contribute more to the occurrence of the problem, that is, it can be determined at which link in the process of printing the sand mold that caused the sand mold quality problem; then look at the health degree or related parameters in the module to determine which subunit, running motor or which parameter or powder spreading problem or inkjet problem caused the sand mold quality problem when printing the screen sand mold, so as to help the staff quickly find and repair the problem of the 3D printing equipment. Therefore, the 3D printing quality evaluation system provided by the present invention can monitor the printing quality of 3D printing equipment in the whole process and in an all-round manner. When more serious problems occur during the printing process, such as in the key component fault diagnosis module, when the failure rate appears in the shutdown domain, Or in the key parameter monitoring module of the printing process, when the inkjet abnormality rate δ l , Abnormal inkjet area η l When the defect area α of the powder paving surface exceeds the safety threshold, the quality assessment system can send an alarm signal to the staff, reminding them to shut down the machine urgently, repair the fault and prevent greater losses.

[0074] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A 3D printing product quality assessment system, characterized in that: The 3D printing product quality assessment system comprises: The pre-printing self-diagnosis module is used to classify the data of each subunit of the 3D printing equipment and calculate the health level S of each type of data. i , and for each type of health S i The health score S1 of the pre-printing self-diagnosis module is obtained after weighted summation; The fault diagnosis module for key components in printing is used to diagnose the health of each drive component during the printing process of 3D printing equipment. j , and the health of each drive component S j The health score S2 of the fault diagnosis module of key components in printing is obtained by weighted summation; Printing process key parameter monitoring module, used to monitor the health score S of each parameter during the printing process k , and give each health score S k Perform weighted summation to obtain the health score S3 of the key parameter monitoring module during printing; The printing process powder laying inkjet quality monitoring module is used to calculate the inkjet abnormality rate δ during the printing process l and the powder spreading defect area α, and according to the inkjet abnormality rate δ l The health score S4 of the powder spreading quality monitoring module during the printing process is calculated with the powder spreading defect area α; The comprehensive evaluation module obtains the comprehensive health score S by weighted summing up the health scores S1, S2, S3, and S4 of the above modules.

2. A 3D printing product quality assessment system according to claim 1, characterized in that: The 3D printing product quality assessment system also includes: The report generation module is used to generate a health report of the 3D printing device, and the health report includes the health score S1 of the self-diagnosis module before printing, the health score S2 of the key component fault diagnosis module during printing, the health score S3 of the key parameter monitoring module during printing, the health score S4 of the powder quality monitoring module during printing, and the comprehensive health score S.

3. A 3D printing product quality assessment system according to claim 2, characterized in that: The health report also includes the health level S of each subunit i , Health of each drive component S j , health score S of each parameter k 、Inkjet abnormality rateδ l And the defect area α of the powdering surface.

4. A 3D printing product quality assessment system according to claim 1, characterized in that: In the pre-printing self-diagnosis module, the data of each subunit is classified into Boolean data, continuous data, error judgment data and continuous periodic data, and the score S of each type of data is calculated according to the following formula: i , Where X i is the detection value, is to set the threshold, α is the proportional weight of the score when the parameter is not in the completely safe interval, and β is to control the distribution of the completely safe parameter interval.

5. A 3D printing product quality assessment system according to claim 1, characterized in that: In the fault diagnosis module of key components in printing, the health of each driving component S j The calculation formula is as follows: In the above formula, N is the N time periods divided into a printing cycle T. j s The number of safe operation periods for the drive.

6. A 3D printing product quality assessment system according to claim 5, characterized in that: The operation of each drive element is divided into a safety domain [0, μ j ], alert domain [μ j ,v j ], shutdown domain [v j ,1],N j s For each driver in the safety domain [0,μ j ] time periods.

7. A 3D printing product quality assessment system according to claim 1, characterized in that: The health score S of each parameter in the key parameter monitoring module of the printing process k The calculation formula is as follows: In the above formula, σ is the variance of each parameter in a monitoring period. is the standard deviation of each parameter; μ is the mean value of each parameter in a monitoring period, is the standard mean of the parameter; ρ is the extreme value of each parameter in a monitoring period; N s N is the number of times each parameter monitoring value exceeds the safe fluctuation range. w The number of times the monitoring value of each parameter exceeds the warning zone.

8. A 3D printing product quality assessment system according to claim 1, characterized in that: The powder spreading defect area α includes the powder shortage area Powder pile area Scratch area 9. A 3D printing product quality assessment system according to claim 8, characterized in that: In the printing process powder spreading and inkjet quality monitoring module, the powder spreading quality monitoring module health score S4 calculation formula is as follows: In the above formula, η l is the abnormal area of ​​inkjet; w e ,w p ,w s ,w δ ,w η Respectively represent the sensitivity coefficient of each layer score to the powder shortage area, powder pile area, scratch area, inkjet abnormality rate and inkjet abnormality area, N l Indicates the total number of layers.

10. According to the 3D printing product quality assessment system of claim 1, the weighted summation calculation formula of the comprehensive health score S is as follows: S=w1S1+w2S2+w3S3+w4S4, where w1, w2, w3, w4 are the weights of the health scores of each module.

Images