A method of closed loop injection molding control for thermoplastic elastomer pharmaceutical combination gaskets

Abstract

The present application relates to the technical field of pharmaceutical pad injection molding control, and particularly relates to a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical combination pad, comprising obtaining pad solid particle samples in combination pad raw materials for melting, obtaining compression resilience coefficient and temperature distribution coefficient of double-layer pad in the pressure maintaining stage to generate simulation finished product index to determine whether the injection molding of double-layer pad is qualified, clustering pad solid particles to determine defect risk of pad solid particles and injection molding into alternative pads, respectively obtaining defect characteristic parameters of strong defect risk pad and weak defect risk pad, matching generation of three-layer pad based on pad after thinning treatment and medium defect risk pad, and statistics of matching qualified rate of alternative pads within a preset time to determine adjustment of defect coincidence threshold or update corresponding fingerprint data reference table. The present application improves the control precision of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical combination pad.

Description

Technical Field

[0001] This invention relates to the field of pharmaceutical gasket injection molding control technology, and in particular to a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets. Background Technology

[0002] The injection molding quality of thermoplastic elastomer pharmaceutical composite gaskets directly affects the sealing and safety of the drugs. When processing the gasket solid granule raw materials, there are significant differences in molecular weight distribution, thermal stability, melt flow rate, and geometry among the gasket solid particles of different components, resulting in inconsistent melting behavior and mass decay characteristics. Especially for double-layer composite gaskets, if they are not graded according to the real-time melting characteristics and structural features of the raw materials, problems such as viscosity fluctuations, pressure instability, and overlapping interlayer defects are likely to occur. Therefore, there is an urgent need for a dynamic grading control method based on raw material fingerprint recognition and defect overlap assessment to achieve timely online updates of gasket process parameters, while improving the finished product qualification rate and material utilization rate.

[0003] Chinese Patent Application Publication No. CN121290727A discloses an optimal setpoint tracking control method for an injection molding system based on output feedback, relating to the field of automatic control technology for injection molding systems. The method includes: establishing a discrete-time state-space equation for the injection molding system, which at least includes a state vector and an output vector; subtracting the corresponding setpoint in the reference trajectory from the output vector to obtain the tracking error, and constructing an augmented system based on the state vector and the tracking error; constructing an infinite-domain cost function based on the augmented system; obtaining a non-minimum state vector based on the augmented system using a state parameterization method, and defining an output feedback Q function based on this vector; collecting input and output data of the injection molding system to design a deadbeat controller, and using this controller as an initial stable control strategy to execute an output feedback strategy Q-learning algorithm, iteratively solving to converge the output feedback Q function, thereby obtaining the optimal output feedback control strategy that minimizes the infinite-domain cost function and improving control accuracy.

[0004] However, the existing technology still has the following problems: the existing technology does not take into account the difference in the melting characteristics of raw materials to set up graded injection molding lines, does not use the gaskets for combinations of different number of gaskets according to the defect risk of the gaskets, and does not adjust the control behavior in a timely manner based on the gasket matching results, resulting in a single control strategy and insufficient system adaptability. Summary of the Invention

[0005] To address these issues, the present invention provides a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets. This method overcomes the problems in the prior art, such as failing to consider the specific setting of graded injection molding lines based on the differences in the melting characteristics of raw materials, failing to consider the defect risks of the gaskets when combining gaskets with different numbers of layers, and failing to adjust the control behavior in a timely manner based on the gasket matching results, resulting in a single control strategy and insufficient system adaptability.

[0006] To achieve the above objectives, the present invention provides a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets, comprising: A gasket solid particle sample is obtained from the combined gasket raw material for melting. The viscosity decay rate and pressure fluctuation coefficient of the gasket solid particle sample are collected during the melting process to generate a melt index to determine whether a graded injection molding strategy should be adopted for the gasket solid particles. The spectral and geometric characteristic parameters of the remaining gasket solid particles in the combined gasket raw material are calculated, and several fingerprint differences are generated by referring to several preset fingerprint data tables to determine the graded injection molding line of the gasket solid particles. In response to the application of the first stage injection molding line, the compression rebound coefficient and temperature distribution coefficient of the double-layer gasket in the holding pressure stage are obtained to generate a simulated finished product index to determine whether the double-layer gasket injection molding is qualified. In response to the double-layer gasket injection molding being unqualified, the double-layer gasket is thinned. In response to the application of a second-level injection molding line, the gasket solid particles are clustered to determine the defect risk of the gasket solid particles and injection molded as alternative gaskets. Defect feature parameters of high-defect-risk gaskets and low-defect-risk gaskets are obtained respectively, and defect overlap is generated based on the defect feature parameters to determine whether the candidate gaskets can be matched. The unmatched candidate gaskets are thinned, and a three-layer gasket is generated by matching the thinned gaskets with the medium-defect risk gaskets. The matching pass rate of the candidate gaskets within a preset time is calculated to determine the adjustment of the defect overlap threshold or to update the corresponding fingerprint data reference table.

[0007] Furthermore, the process of generating a melt index includes, The viscosity factor is determined as the ratio of the viscosity decay rate to the reference viscosity decay rate. The ratio of the pressure fluctuation coefficient to the reference pressure fluctuation coefficient is determined as the pressure factor; The arithmetic square root of the product of the viscosity factor and the pressure factor is determined as the melt flow index.

[0008] Furthermore, the process of determining whether to employ a graded injection molding strategy for the gasket solid particles includes, If the melt flow index is greater than the melt flow index threshold, then a graded injection molding strategy is determined for the gasket solid particles.

[0009] Furthermore, the process of generating several fingerprint differences includes, The first absorption peak factor, the first absorbance factor, the second absorption peak factor, and the second absorbance factor are determined based on the spectral characteristic parameters and several fingerprint data reference tables, respectively. The first particle size factor, the first chromaticity factor, the second particle size factor, and the second chromaticity factor are determined based on the geometric feature parameters and several fingerprint data reference tables, respectively. The sum of the first absorption peak factor, the first absorbance factor, the first particle size factor, and the first chromaticity factor is determined to be the first fingerprint difference. The sum of the second absorption peak factor, the second absorbance factor, the second particle size factor, and the second chromaticity factor is determined to be the second fingerprint difference.

[0010] Furthermore, the process of determining the graded injection molding path of the gasket solid particles includes, If the first fingerprint difference is less than or equal to the second fingerprint difference, then the graded injection molding line of the gasket solid particles is determined to be the first graded injection molding line. If the first fingerprint difference is greater than the second fingerprint difference, then the graded injection molding line of the gasket solid particles is determined to be the second graded injection molding line.

[0011] Furthermore, the process of generating the simulated product index includes, Several monitoring points are set on each gasket. The gasket is compressed to obtain the compression rebound factor of each monitoring point and the temperature value of each monitoring point is collected. The standard deviation of several of the compression rebound factors is determined as the compression rebound coefficient; The standard deviation of a number of the temperature values ​​is determined as the temperature distribution coefficient; The arithmetic square root of the product of the compression rebound coefficient and the temperature distribution coefficient is determined as the simulated finished product index; If the simulated finished product index is greater than the simulated finished product index threshold, the double-layer gasket injection molding is deemed unqualified.

[0012] Furthermore, the process of determining the defect risk of the gasket solid particles includes, The gasket solid particles are divided into several components, and the surface gloss, backlight translucency and impact sound main frequency of each component gasket solid particles are obtained respectively. Based on clustering algorithms, surface gloss, backlight translucency, and impact sound dominant frequency, the defect risk of the gasket solid particles is determined to be either a high-defect-risk gasket, a medium-defect-risk gasket, or a low-defect-risk gasket.

[0013] Furthermore, the process of generating defect overlap includes, Obtain the center coordinates and radius of action of each defect in the strong defect risk pad and the weak defect risk pad respectively; The defect area is determined based on the center coordinates and the radius of action. The overlapping area is determined based on the defect area of ​​the strong defect risk pad and the defect area of ​​the weak defect risk pad, and the ratio of the overlapping area to the benchmark overlapping area is calculated to obtain the defect overlap degree.

[0014] Furthermore, the process of determining whether the candidate gaskets are compatible includes, If the defect overlap is less than or equal to the defect overlap threshold, then the candidate gasket is determined to be a match. If the degree of defect overlap is greater than the defect overlap threshold, then the candidate gasket is determined to be unmatched.

[0015] Furthermore, the process of determining the adjustment defect overlap threshold or updating the corresponding fingerprint data reference table includes, The matching qualification rate is determined based on the total number of candidate gaskets, the total number of double-layer gaskets, and the total number of triple-layer gaskets in the second-level injection molding line; If the matching success rate is less than the matching success threshold, then the corresponding fingerprint data reference table will be updated. If the matching pass rate is greater than or equal to the matching pass threshold, then the defect overlap threshold is adjusted to be smaller.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains the viscosity decay rate and pressure fluctuation coefficient of the gasket solid particle sample during the melting process to generate a melt index that characterizes the stability of the melting behavior, reflects the thermal shear sensitivity of the material in the heating section, and determines whether to enable a graded injection molding strategy for the gasket solid particles. Based on the actual melting response characteristics of the gasket solid particles, the corresponding process path is determined, realizing the ability of the injection molding system to adapt and adjust to the fluctuation of raw material quality, thereby further improving the control accuracy of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets.

[0017] Furthermore, this invention synchronously acquires the spectral and geometric characteristic parameters of the gasket solid particles using a vision device, and performs similarity calculations with several preset fingerprint data reference tables to generate several fingerprint difference scores. Based on the comparison results of the first and second fingerprint difference scores, it determines whether the gasket solid particles should enter the first or second stage injection molding line. By decoupling and jointly comparing the chemical composition characteristics and physical morphological characteristics of the raw materials, it achieves micro-level flow and path allocation for particles with different characteristics, reducing the risk of process deviations caused by raw material inconsistencies, thereby further improving the control accuracy of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets.

[0018] Furthermore, in the second-level injection molding process, the present invention first clusters the gasket solid particles and then injects them into the gaskets, classifying them into high-risk, medium-risk, and low-risk gaskets. Then, based on a vision device, the defect feature parameters of each type of gasket are extracted. The defect overlap rate between the high-risk and low-risk gaskets is calculated. When the defect overlap rate is lower than a preset defect overlap threshold, the combined defect risk of the high-risk and low-risk gaskets is deemed acceptable, and the process is permitted. The gaskets are directly combined into a double-layer gasket. When the defect overlap is higher than the preset defect overlap threshold, the gaskets with high defect risk and those with low defect risk are transferred to a buffer zone to wait for matching. In the buffer zone, the matching is optimized based on the defect distribution characteristics until a matching object with a defect overlap that meets the requirements is found. This effectively avoids sealing failure, stress concentration or leakage channel formation caused by the superposition of interlayer defects in the same spatial position, improves the finished product qualification rate and material utilization efficiency, and further improves the control accuracy of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets.

[0019] Furthermore, this invention monitors the matching pass rate of gaskets within a preset time frame during the production process. When the matching pass rate is greater than or equal to a preset matching pass threshold, the defect overlap threshold can be appropriately reduced to improve the screening standard and thus improve the quality of the gaskets. When the matching pass rate does not exceed the preset matching pass threshold, the system triggers an update operation on the fingerprint data reference table. By using the spectral and geometric characteristic parameters of the gasket solid particles collected in the current production cycle as new samples to improve the fingerprint data reference table, the consistency and stability of the gasket injection molding quality are ensured, thereby further improving the control accuracy of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets. Attached Figure Description

[0020] Figure 1 This is a flowchart of a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to an embodiment of the present invention; Figure 2A logic decision diagram for determining the graded injection molding circuit of the gasket solid particles in an embodiment of the present invention; Figure 3 This is a logic diagram for determining whether the injection molding of a double-layer gasket is qualified according to an embodiment of the present invention; Figure 4 This is a logic decision diagram for determining the adjustment defect overlap threshold or updating the corresponding fingerprint data reference table in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0022] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0024] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] Please see Figure 1 The diagram shows a flowchart of a closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to an embodiment of the present invention. The method of this embodiment includes: Step S1: Obtain a gasket solid particle sample for melting, collect the viscosity decay rate and pressure fluctuation coefficient during the melting process to generate a melt index, and determine whether to adopt a graded injection molding strategy for the gasket solid particles based on the melt index. Step S2: Based on the vision device, collect the spectral and geometric feature parameters of several gasket solid particles, and generate several fingerprint differences based on the spectral and geometric feature parameters and several preset fingerprint data reference tables to determine the graded injection molding line of the gasket solid particles. Step S3: In response to the application of the first stage injection molding circuit, the compression rebound coefficient and temperature distribution coefficient of the double-layer gasket in the pressure holding stage are obtained to generate a simulated finished product index to determine whether the double-layer gasket injection molding is qualified; in response to the double-layer gasket injection molding being unqualified, the double-layer gasket is thinned. Step S4, in response to the application of the second-level injection molding line, cluster the gasket solid particles to determine the defect risk of the gasket solid particles and injection mold them as alternative gaskets. Step S5: Obtain the defect feature parameters of the high-defect-risk gasket and the low-defect-risk gasket respectively, and generate the defect overlap degree based on the defect feature parameters to determine whether the candidate gasket can be matched. Step S6: Thin the unmatched candidate gaskets, generate a three-layer gasket based on the thinned gaskets and the medium-defect risk gaskets, and calculate the matching pass rate of the candidate gaskets within a preset time to determine the adjustment defect overlap threshold or update the corresponding fingerprint data reference table.

[0026] In this embodiment, the process of generating the melt flow index includes, The viscosity factor is determined by the ratio of the viscosity decay rate to the reference viscosity decay rate. The pressure factor is determined as the ratio of the pressure fluctuation coefficient to the reference pressure fluctuation coefficient. The arithmetic square root of the product of the viscosity factor and the pressure factor is determined as the melt index.

[0027] Specifically, the viscosity decay rate is the rate at which the apparent viscosity of a melt decreases over time under constant temperature and constant shear rate. It is calculated by collecting the apparent viscosity at any two moments and determining the viscosity decay rate as the ratio of the difference between the two apparent viscosities to the difference between the two moments. Specifically, the pressure fluctuation coefficient is used in the extrusion production stage to reflect the degree of fluctuation and dispersion between the actual pressure and the average pressure in the melt cavity. It is calculated by continuously collecting pressure values ​​at different times to calculate the average pressure and the standard deviation of pressure. The pressure fluctuation coefficient is determined as the ratio of the standard deviation of pressure to the average pressure. Specifically, the baseline viscosity decay rate is the average of several viscosity decay rates recorded in historical data under operating conditions where a graded injection molding strategy was not used for the gasket solid particles, and the baseline pressure fluctuation coefficient is the average of several pressure fluctuation coefficients recorded in historical data under operating conditions where a graded injection molding strategy was not used for the gasket solid particles.

[0028] Please see Figure 2As shown, this is a logic diagram for determining the graded injection molding circuit of the gasket solid particles in an embodiment of the present invention. The process of determining whether to adopt a graded injection molding strategy for the gasket solid particles includes: If the melt flow index is greater than the melt flow index threshold, then a graded injection molding strategy is adopted for the gasket solid particles; If the melt flow index is less than or equal to the melt flow index threshold, then a graded injection molding strategy will not be used for the gasket solid particles.

[0029] Understandably, when the melt flow index does not exceed the melt flow index threshold, the melting characteristics, viscosity decay characteristics, and injection pressure fluctuations of the gasket solid particles are all within the excellent and qualified range. This indicates that the plasticizing rate of the gasket solid particles matches the temperature, screw speed, injection pressure, and injection speed parameters of conventional injection molding. The particles melt fully and uniformly, without obvious viscosity decay abnormalities or large pressure fluctuations. The parts will not have defects such as shrinkage, bubbles, or excessive internal stress. Therefore, there is no need to adopt a graded injection molding strategy for the gasket solid particles, and the conventional injection molding process can be used directly to meet the production quality requirements.

[0030] Specifically, when determining the melt flow index threshold, the melt flow index of solid particles from each batch of gaskets within at least one complete production cycle under the same operating conditions is collected, and the statistical distribution of all historical melt flow indices is calculated. The upper quantile of the historical melt flow index, such as the 75th percentile or the 90th percentile, is determined, and the melt flow index corresponding to the upper quantile is directly used as the melt flow index threshold.

[0031] It should be noted that the upper percentile represents a higher level within the historical normal fluctuation range. When the melt index exceeds the melt index threshold, it indicates that the current batch melt state has deviated from the historical normal fluctuation range, and a graded injection molding strategy needs to be triggered. The 75% percentile is suitable for scenarios with high requirements for graded trigger sensitivity, while the 90% percentile is suitable for scenarios with higher requirements for stability and allowance for a certain degree of fluctuation tolerance.

[0032] Specifically, this invention generates a melt index that characterizes the stability of melting behavior by obtaining the viscosity decay rate and pressure fluctuation coefficient of gasket solid particle samples during the melting process. This reflects the thermal shear sensitivity of the material in the heating section and determines whether to enable a graded injection molding strategy for the gasket solid particles. Based on the actual melting response characteristics of the gasket solid particles, the corresponding process path is determined, thereby realizing the ability of the injection molding system to adapt and adjust to fluctuations in raw material quality.

[0033] In this embodiment, the process of generating several fingerprint differences includes, The first absorption peak factor, the first absorbance factor, the second absorption peak factor, and the second absorbance factor are determined based on the spectral characteristic parameters and several fingerprint data reference tables, respectively. Based on geometric feature parameters and several fingerprint data reference tables, the first particle size factor, the first chromaticity factor, the second particle size factor, and the second chromaticity factor are determined respectively, wherein, The difference between the absorption peak ratio and the first absorption peak ratio is compared with the first absorption peak ratio to obtain the first absorption peak factor; The difference between the absorbance ratio and the first absorbance ratio is compared with the first absorbance ratio to obtain the first absorbance factor; The difference between the average particle size and the first average particle size is compared with the first average particle size to obtain the first particle size factor; The difference between the chromaticity of the gasket solid particles and the chromaticity of the first gasket solid particles is compared with the chromaticity of the first gasket solid particles to obtain the first chromaticity factor; The difference between the absorption peak ratio and the second absorption peak ratio is compared with the second absorption peak ratio to obtain the second absorption peak factor; The difference between the absorbance ratio and the second absorbance ratio is compared with the second absorbance ratio to obtain the second absorbance factor; The difference between the average particle size and the second average particle size is compared with the second average particle size to obtain the second particle size factor; The difference between the chromaticity of the gasket solid particles and the chromaticity of the second gasket solid particles is compared with the chromaticity of the second gasket solid particles to obtain the second chromaticity factor; The sum of the first absorption peak factor, the first absorbance factor, the first particle size factor, and the first color factor is determined as the first fingerprint difference. The sum of the second absorption peak factor, the second absorbance factor, the second particle size factor, and the second chromaticity factor is determined to be the second fingerprint difference. The spectral characteristic parameters include the absorption peak ratio and the absorbance ratio; the geometric characteristic parameters include the average particle size and the chromaticity of the gasket solid particles; and the fingerprint data reference table includes a first fingerprint data reference table and a second fingerprint data reference table. The first fingerprint data reference table includes the first absorption peak ratio, the first absorbance ratio, the first average particle size, and the first gasket solid particle chromaticity, while the second fingerprint data reference table includes the second absorption peak ratio, the second absorbance ratio, the second average particle size, and the second gasket solid particle chromaticity.

[0034] Specifically, when determining the absorption peak ratio, the gasket solid particles are first irradiated with an infrared spectrometer, two characteristic absorption peaks are selected, and the ratio of the intensity of the main absorption peak to the intensity of the secondary absorption peak is calculated as the absorption peak ratio to characterize the chemical composition and functional group structure of the particles. When determining the absorbance ratio, the absorbance at two wavelength points on the spectrum is selected as the ratio to reflect the differences in component concentration and surface structure of the gasket solid particles. Specifically, when determining the average particle size, a laser particle size analyzer is used to output the D50 average particle size and the volume average particle size of the gasket solid particles using a wet method. The ratio of the D50 average particle size to the volume average particle size is calculated as the average particle size. When determining the color of the gasket solid particles, a whiteness meter is used to lay the gasket solid particles flat for testing and output the whiteness value. The whiteness value is then determined as the color of the gasket solid particles. Specifically, in this embodiment, the first absorption peak ratio, the first absorbance ratio, the first average particle size, and the first gasket solid particle color are all the average values ​​calculated after multiple tests of qualified gasket solid particle samples that meet the melting characteristics and injection molding quality standards under the same historical conditions of double-layer gasket injection molding, according to the corresponding determination method; the second absorption peak ratio, the second absorbance ratio, the second average particle size, and the second gasket solid particle color are all the average values ​​calculated after multiple tests of critical gasket solid particle samples that are close to the melting characteristic threshold and are prone to injection molding defects under the same historical conditions of multi-layer gasket injection molding, according to the corresponding determination method. Specifically, the first fingerprint data reference table contains two horizontal rows, namely the comparison parameters and the reference values; the vertical columns corresponding to the comparison parameter horizontal row contain the first absorption peak ratio, the first absorbance ratio, the first average particle size and the first gasket solid particle color, and the vertical columns corresponding to the reference value horizontal row contain the test average values ​​of the above four comparison parameters respectively. Specifically, the second fingerprint data reference table contains two rows, namely the comparison parameters and the reference values; the vertical columns corresponding to the comparison parameters row include the second absorption peak ratio, the second absorbance ratio, the second average particle size, and the second pad solid particle color; and the vertical columns corresponding to the reference values ​​row are the test average values ​​of the above four comparison parameters respectively. Specifically, in implementation, the first absorption peak factor is determined as follows: The difference between the collected absorption peak ratio and the first absorption peak ratio is calculated, the absolute value of which is then divided by the first absorption peak ratio. The result is the first absorption peak factor. The first absorbance factor is determined as follows: The difference between the collected absorbance ratio and the first absorbance ratio is calculated, the absolute value of which is then divided by the first absorbance ratio. The result is the first absorbance factor. The first particle size factor is determined as follows: The difference between the collected average particle size and the first average particle size is calculated, the absolute value of which is then divided by the first average particle size. The result is the first particle size factor. The first chromaticity factor is determined as follows: The difference between the collected chromaticity of the gasket solid particles and the first chromaticity of the gasket solid particles is calculated, the absolute value of which is then divided by the chromaticity of the first gasket solid particles. The result is the first chromaticity factor.

[0035] Among them, the collected absorption peak ratio, absorbance ratio, average particle size, and gasket solid particle color are the spectral and geometric characteristic parameters of the gasket solid particles; the first absorption peak ratio, first absorbance ratio, first average particle size, and first gasket solid particle color are the corresponding parameters in the preset first fingerprint data reference table.

[0036] The second absorption peak factor is determined as follows: The difference between the collected absorption peak ratio and the second absorption peak ratio is calculated, the absolute value of which is then divided by the second absorption peak ratio. The second absorbance factor is determined as follows: The difference between the collected absorbance ratio and the second absorbance ratio is calculated, the absolute value of which is then divided by the second absorbance ratio. The second particle size factor is determined as follows: The difference between the collected average particle size and the second average particle size is calculated, the absolute value of which is then divided by the second average particle size. The second chromaticity factor is determined as follows: The difference between the collected chromaticity of the gasket solid particles and the second chromaticity of the gasket solid particles is calculated, the absolute value of which is then divided by the chromaticity of the second gasket solid particles.

[0037] Among them, the second absorption peak ratio, the second absorbance ratio, the second average particle size, and the second gasket solid particle color are the corresponding parameters in the preset second fingerprint data reference table.

[0038] In this embodiment, the process of determining the graded injection molding path of the gasket solid particles includes, If the difference in the first fingerprint is less than or equal to the difference in the second fingerprint, then the graded injection molding line of the gasket solid particles is determined to be the first graded injection molding line. If the difference between the first fingerprint and the second fingerprint is greater, then the graded injection molding line of the gasket solid particles is determined to be the second graded injection molding line.

[0039] Specifically, the first-stage injection molding line is a double-layer gasket injection molding line, which has a simple flow channel structure, smooth flow, mild shearing action, and small flow channel pressure fluctuations. It is suitable for gasket solid particles with ordinary melt characteristics and uniform particle size and color. The second-stage injection molding line is a double-layer gasket injection molding line or a triple-layer gasket injection molding line, which adopts a double-layer gasket composite flow channel structure. It has the functions of forced homogenization, step-by-step pressure stabilization, and moderately enhanced shearing. It can compensate for particles with melt fluctuations and deviations in particle size uniformity.

[0040] Please see Figure 3 As shown, this is a logic diagram for determining whether the injection molding of a double-layer gasket is qualified according to an embodiment of the present invention. The process of generating the simulated finished product index includes: Several monitoring points are set on each gasket. The gasket is compressed to obtain the compression rebound factor of each monitoring point and the temperature value of each monitoring point is collected. The standard deviation of several compression rebound factors is determined as the compression rebound coefficient. The standard deviation of a number of temperature values ​​is defined as the temperature distribution coefficient. The arithmetic square root of the product of the compression rebound coefficient and the temperature distribution coefficient is determined as the simulated finished product index; If the simulated finished product index is greater than the simulated finished product index threshold, the double-layer gasket injection molding is deemed unqualified. If the simulated finished product index is less than or equal to the simulated finished product index threshold, the double-layer gasket injection molding is deemed qualified.

[0041] Specifically, when determining the compression rebound factor, several fixed monitoring points are evenly distributed on the surface of the single-layer gasket. An injection molding machine is used to simulate the mold closing compression condition. A set rated compression load is applied to the gasket, and the compression deformation and rebound recovery deformation at each monitoring point are collected. The compression rebound factor is determined to be the ratio of the rebound recovery deformation to the compression deformation. When determining the temperature value, a high-definition infrared thermal imager is used to target all monitoring points on the gasket. Under the condition of the gasket being compressed to simulate injection molding shear and melt heat exchange, the temperature value at each point is collected. Specifically, when determining the simulated finished product index threshold, the simulated finished product index of verified qualified double-layer gasket samples in historical data under the same working conditions is collected, and the statistical distribution of the simulated finished product index of all qualified samples is calculated; the upper quantile of the simulated finished product index of qualified samples is determined, such as the 85th percentile or the 95th percentile, and the simulated finished product index corresponding to the upper quantile is directly used as the simulated finished product index threshold.

[0042] It should be noted that the upper quantile represents the upper limit of normal fluctuation in the compression rebound uniformity and temperature distribution uniformity of a qualified double-layer gasket. When the simulated finished product index exceeds the simulated finished product index threshold, it indicates that the current double-layer gasket's compression rebound dispersion or temperature distribution dispersion has exceeded the normal fluctuation range of a qualified sample, and it is judged as unqualified. The 85% quantile is suitable for scenarios with moderate uniformity requirements and allowing for some process fluctuations; the 95% quantile is suitable for scenarios with stringent requirements for gasket sealing performance and strict control of dispersion.

[0043] Specifically, this invention uses a vision device to simultaneously acquire the spectral and geometric feature parameters of the gasket solid particles, and performs similarity calculations with several preset fingerprint data reference tables to generate several fingerprint difference scores. Based on the comparison results of the first fingerprint difference score and the second fingerprint difference score, it determines whether the gasket solid particles should enter the first or second grade injection molding line. By decoupling and jointly comparing the chemical composition characteristics and physical morphological characteristics of the raw materials, it realizes the micro-flow and path allocation of particles with different characteristics, reducing the risk of process deviation caused by the unevenness of raw materials.

[0044] In this embodiment, the process of determining the defect risk of the gasket solid particles includes, The gasket solid particles were divided into several components, and the surface gloss, backlight translucency and impact sound frequency of each component gasket solid particles were obtained. Based on clustering algorithms, surface gloss, backlight translucency, and impact sound dominant frequency, the defect risk of the solid particles in the gasket is determined to be either a high-risk gasket, a medium-risk gasket, or a low-risk gasket.

[0045] Specifically, when determining the surface gloss, a gloss meter is used to perform multi-point optical detection on the flat surface of each component gasket solid particle under the same light source and incident angle. The gloss value of the particle surface reflection is directly read, and the average value is taken as the surface gloss of the component gasket solid particle. When determining the backlight translucency, each component gasket solid particle is evenly laid between the backlight source and the high-definition image acquisition device. The backlight transmission image is acquired through the visual imaging system. The backlight transmission degree of the gasket solid particle is obtained by using image grayscale analysis and transmittance calculation algorithm. The backlight translucency is obtained by solving the backlight transmission degree of the gasket solid particle. When determining the impact sound main frequency, each component gasket solid particle is freely impacted with a fixed drop onto a rigid reference surface. The impact instantaneous sound wave signal is acquired by a high-precision acoustic sensor. Fourier transform spectrum analysis is performed on the acquired sound wave signal, and the characteristic frequency with the largest energy amplitude in the spectrum is extracted, which is the impact sound main frequency of the component gasket solid particle. Specifically, in implementation, for each component of the gasket solid particles after division, a corresponding three-dimensional feature dataset is generated based on three sets of feature parameters: surface gloss, backlight translucency, and impact sound dominant frequency. The three-dimensional feature datasets of all component gasket solid particles are input into the clustering algorithm model, and unsupervised clustering is used to perform similarity clustering on multiple groups of particle features to obtain three cluster groups of gasket solid particles with obvious feature differences. The specific iteration rules, distance measurement methods, and cluster center update methods of the clustering algorithm are existing technologies and will not be elaborated here. It is understood that, based on the requirements of high appearance, high transparency, and material uniformity for the outer layer semi-finished product of the double-layer gasket, and the performance difference of the inner layer semi-finished product which emphasizes structural density and mechanical stability, this invention classifies a type of gasket solid particles with superior appearance and optical characteristics after clustering as materials for preparing the outer layer semi-finished product of the double-layer gasket, and classifies another type of gasket solid particles with acoustic impact characteristics and internal structural density that are more suitable for bearing and buffering requirements as materials for preparing the inner layer semi-finished product of the double-layer gasket.

[0046] In this embodiment, the center coordinates and radius of action of each defect in the strong defect risk pad and the weak defect risk pad are obtained respectively; The defect area is determined based on the center coordinates and the radius of action. The overlapping area is determined based on the defect area of ​​the strong defect risk gasket and the defect area of ​​the weak defect risk gasket, and the ratio of the overlapping area to the benchmark overlapping area is calculated to obtain the defect overlap degree. The defect characteristic parameters include the center coordinates and the radius of effect.

[0047] In implementation, full-domain high-definition images of both high-risk and low-risk gaskets are acquired. Through image thresholding, edge detection, and defect contour extraction algorithms, the contour boundary of each defect is identified. The centroid of the defect contour is calculated, and the center coordinates of each defect are obtained by referring to the preset reference coordinate system of the semi-finished product. Based on the extracted defect contour edges, the distance from each edge point on the contour to the center is calculated with the center coordinates as the reference. The arithmetic mean of several distances is taken as the radius of action. Specifically, the area of ​​defects can be determined based on the formula for the area of ​​a circle; Specifically, when determining the defect overlap, first match defects corresponding to the same location, and extract the center coordinates and radius of action of the strong defect risk pad and the weak defect risk pad respectively; based on the geometric algorithm of two intersecting circles, calculate the ratio of the overlapping area between the areas of each defect to the reference overlapping area as the defect overlap. When there are multiple defects in the strong defect risk pad and the weak defect risk pad, match and pair the defects according to their spatial location; calculate the overlapping area of ​​each set of matched defects, accumulate and sum the overlapping areas of all matched defects to obtain the total overlapping area, and use the ratio of the total overlapping area to the reference overlapping area as the final defect overlap. The reference overlapping area is the total area of ​​the candidate pads.

[0048] Understandably, the larger the overlapping area, the higher the degree of spatial overlap between the high-defect-risk gasket and the low-defect-risk gasket, and the greater the overall molding defect risk of the double-layer gasket.

[0049] In this embodiment, the process of determining whether the candidate gasket is a match includes, If the defect overlap is less than or equal to the defect overlap threshold, the candidate gasket is determined to be a match. If the defect overlap is greater than the defect overlap threshold, the candidate gasket is determined to be unmatched.

[0050] Specifically, in order to simultaneously adapt to the production of double-layer gaskets with high precision and high appearance requirements as well as production under normal working conditions, at least one qualified candidate gasket sample that has been verified within a complete production cycle is collected, the defect overlap degree of each qualified sample is calculated, and the maximum value of the defect overlap degree among all qualified samples is determined as the defect overlap threshold.

[0051] Specifically, when a candidate gasket fails to match, the gaskets with high defect risk and those with low defect risk are moved to the buffer zone to wait for matching.

[0052] Specifically, the buffer is a dedicated buffer silo for temporarily storing high-defect-risk gaskets and low-defect-risk gaskets that do not yet meet the pairing requirements. It has the functions of partitioned storage, orderly queuing, and stable temperature and humidity maintenance. The waiting-to-matching process involves temporarily storing high-defect-risk gaskets and low-defect-risk gaskets with defect overlap exceeding the defect overlap threshold in the buffer, without immediately performing combination and pressing. Subsequently, according to the first-in-first-out rule, in subsequent production batches, feature matching and defect overlap calculation are performed again with newly produced high-defect-risk gaskets and low-defect-risk gaskets until a pairing object with defect overlap meeting the defect overlap threshold requirement is found, and then the double-layer gaskets are combined and formed.

[0053] Specifically, the thinning process of the present invention is to uniformly thin the unmatched alternative gaskets according to the gasket assembly thickness reference requirements, and control the thinning amount within the assembly allowable tolerance range. This satisfies the thickness matching and assembly fit requirements of the three-layer gasket stack, without changing the original defect characteristic parameters of the gasket, and retaining its original defect attributes.

[0054] Specifically, when assembling the three-layer gaskets, the inner and outer layers use thinned gaskets, while the middle layer uses a gasket with medium defect risk. During matching, the defect areas of the gaskets used in the inner, middle, and outer layers are obtained respectively. The union area of ​​the three defect regions is calculated using a three-circle intersection geometric algorithm to determine the sum of the overlapping areas of the three defect regions. This sum is then subtracted from twice the area of ​​the common overlapping area of ​​the three circles to obtain the final overlapping area. The ratio of the final overlapping area to the standard overlapping area is used as the defect overlap degree. If the defect overlap degree is less than or equal to the defect overlap threshold, the three-layer gaskets are considered to be able to match. If the defect overlap degree is greater than the defect overlap threshold, the three-layer gaskets are considered not to match. The standard overlapping area is the sum of the defect areas of the inner layer, the middle layer, and the outer layer.

[0055] Specifically, when determining whether the three circles have a common overlapping area, the distances between the center of the inner defect circle and the center of the middle defect circle, the distances between the center of the inner defect circle and the center of the outer defect circle, and the distances between the center of the middle defect circle and the center of the outer defect circle are calculated respectively. If all three distances are less than the sum of the radii of their respective two circles, and there are points within the triangle formed by the three circle centers whose distances to the three circle centers are all less than the radii of their respective circles, then the three circles are determined to have a common overlapping area; otherwise, the three circles are determined not to have a common overlapping area, and the final overlapping area is directly taken as the sum of the overlapping areas of the three defect areas intersecting pairwise.

[0056] Specifically, when calculating the area of ​​the overlapping region of the three circles, an analytical geometry method is used: determine the coordinates of the six intersection points where the three circles intersect pairwise, and select the three valid boundary intersection points that are simultaneously located inside the three circles; decompose the overlapping region of the three circles into three sector regions with the three circle centers as vertices and the three valid boundary intersection points as arc endpoints, and a central triangle region with the three valid boundary intersection points as vertices; calculate the area of ​​the three sector regions and the area of ​​the central triangle region respectively, and sum them to obtain the area of ​​the overlapping region of the three circles.

[0057] Specifically, this invention first clusters the gasket solid particles in the second-stage injection molding line, classifying them into two types of materials used to prepare the outer or inner semi-finished product in a double-layer gasket. Then, based on a vision device, it extracts the defect feature parameters of the completed outer and inner semi-finished products, and calculates the defect overlap between the two through spatial coordinate registration. When the defect overlap is lower than a preset defect overlap threshold, it is determined that the risk of defect superposition after the inner and outer layers are combined is acceptable, and direct combination into a double-layer gasket is allowed. When the defect overlap is higher than the preset defect overlap threshold, the outer or inner semi-finished product is transferred to a buffer zone for waiting for matching. In the buffer zone, optimized matching is performed based on defect distribution characteristics until a matching object with satisfactory defect overlap is found. This effectively avoids sealing failure, stress concentration, or leakage channel formation caused by the superposition of interlayer defects in the same spatial position, improves the finished product qualification rate and material utilization efficiency, and further improves the control accuracy of the closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets.

[0058] Please see Figure 4 As shown, this is a logic decision diagram for determining whether to adjust the defect overlap threshold or update the corresponding fingerprint data reference table according to an embodiment of the present invention. The process of determining whether to adjust the defect overlap threshold or update the corresponding fingerprint data reference table includes, The matching qualification rate is determined based on the total number of candidate gaskets, the total number of double-layer gaskets, and the total number of triple-layer gaskets in the second-level injection molding line; If the matching success rate is less than the matching success threshold, then the corresponding fingerprint data reference table will be updated. If the matching pass rate is greater than or equal to the matching pass threshold, then the defect overlap threshold is adjusted to be smaller.

[0059] Specifically, in order to ensure that the fingerprint data reference table is updated in a timely manner, avoid excessive monitoring frequency causing redundant system calculations, balance monitoring real-time performance and system computing efficiency, and adapt to the continuous production of solid particle injection molded gaskets, in this embodiment, the preset time is set to 60 minutes.

[0060] Specifically, the matching pass rate is the ratio of the sum of the total number of double-layer gaskets and the total number of triple-layer gaskets to the total number of candidate gaskets. Specifically, when determining the matching qualification threshold, the percentage of qualified double-layer gasket injection molding in step S3 within the same statistical period is obtained, that is, the ratio of the number of qualified double-layer gaskets to the total number of double-layer gaskets entering the pressure holding stage; the double-layer gasket qualification rate is multiplied by the preset production line balance coefficient, and the result is used as the matching qualification threshold.

[0061] The production line balance coefficient is determined based on the design capacity ratio of the first-stage injection molding line and the second-stage injection molding line. To ensure that the qualified output efficiency of the second-stage injection molding line matches the qualified output efficiency of the double-layer gasket of the first line, and to avoid overproduction of double-layer gaskets and insufficient supply of triple-layer gaskets, the value is usually between 0.75 and 0.95.

[0062] Specifically, when updating the fingerprint data reference table, the spectral and geometric characteristic parameters corresponding to the qualified and paired gasket solid particles of the current batch are collected; the second absorption peak ratio, second absorbance ratio, second average particle size, and second gasket solid particle color corresponding to the second fingerprint data reference table are recalculated to replace the original test average value.

[0063] Specifically, when reducing the defect overlap threshold, if the single reduction percentage is less than 3%, the convergence speed of the defect overlap threshold is too slow. This causes the system to fail to tighten the judgment standard to an effective level within multiple preset time periods, such as 60 minutes. High-risk defective gaskets are continuously misjudged as qualified for a long time, flowing into the downstream three-layer gasket matching stage, causing potential quality risks in the finished product. Therefore, using 3% as the lower limit of the single reduction percentage ensures that under typical operating conditions, the defect overlap threshold can approach a reasonable convergence range after 3 to 5 adjustment cycles.

[0064] If the single reduction ratio of the defect overlap threshold is higher than 5%, the defect overlap threshold will decrease too much in a single cycle, which may cause the judgment standard to change drastically from relatively lenient to excessively strict, misjudging a batch of qualified alternative gaskets as unqualified, resulting in a sudden increase in the thinning process, a sudden jump in equipment load, and material waste. Therefore, 5% is set as the upper limit of the single reduction ratio to ensure that the single adjustment range is controllable and the system operates smoothly. In summary, the range of the single reduction ratio of the defect overlap threshold is set as [3%, 5%].

[0065] It should be noted that, in order to avoid the defect overlap threshold being excessively reduced, resulting in extremely strict judgment criteria, such as preventing the defect feature parameters of high-defect-risk gaskets and low-defect-risk gaskets from only slightly overlapping and being judged as mismatched, and causing a large number of slightly defective gaskets that could be absorbed by the three-layer gasket structure to be forcibly thinned, resulting in a significant decrease in material utilization and violating the original design intention of the graded injection molding strategy, this embodiment sets the defect overlap threshold to be less than or equal to 50% and will not be reduced.

[0066] Specifically, this invention monitors the matching pass rate of gaskets within a preset time period during the production process. When the matching pass rate is greater than or equal to a preset matching pass threshold, the defect overlap threshold can be reduced to improve the screening standard and thus improve the quality of the gaskets. When the matching pass rate does not exceed the preset matching pass threshold, the system triggers an update operation on the fingerprint data reference table. By using the spectral and geometric feature parameters of the gasket solid particles collected in the current production cycle as new samples to improve the fingerprint data reference table, the consistency and stability of the gasket injection molding quality are ensured.

[0067] All technologies not mentioned in the above embodiments are existing technologies. During monitoring, several thresholds in this embodiment are set as dynamically adjustable configurable parameters according to on-site requirements.

[0068] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets, characterized in that, include: A gasket solid particle sample is obtained from the combined gasket raw material for melting. The viscosity decay rate and pressure fluctuation coefficient of the gasket solid particle sample are collected during the melting process to generate a melt index to determine whether a graded injection molding strategy should be adopted for the gasket solid particles. The spectral and geometric characteristic parameters of the remaining gasket solid particles in the combined gasket raw material are calculated, and several fingerprint differences are generated by referring to several preset fingerprint data tables to determine the graded injection molding line of the gasket solid particles. In response to the application of the first stage injection molding line, the compression rebound coefficient and temperature distribution coefficient of the double-layer gasket in the holding pressure stage are obtained to generate a simulated finished product index to determine whether the double-layer gasket injection molding is qualified. In response to the double-layer gasket injection molding being unqualified, the double-layer gasket is thinned. In response to the application of a second-level injection molding line, the gasket solid particles are clustered to determine the defect risk of the gasket solid particles and injection molded as alternative gaskets. Defect feature parameters of high-defect-risk gaskets and low-defect-risk gaskets are obtained respectively, and defect overlap is generated based on the defect feature parameters to determine whether the candidate gaskets can be matched. The unmatched candidate gaskets are thinned, and a three-layer gasket is generated by matching the thinned gaskets with the medium-defect risk gaskets. The matching pass rate of the candidate gaskets within a preset time is calculated to determine the adjustment of the defect overlap threshold or to update the corresponding fingerprint data reference table.

2. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 1, characterized in that, The process of generating a melt index includes, The viscosity factor is determined as the ratio of the viscosity decay rate to the reference viscosity decay rate. The ratio of the pressure fluctuation coefficient to the reference pressure fluctuation coefficient is determined as the pressure factor; The arithmetic square root of the product of the viscosity factor and the pressure factor is determined as the melt flow index.

3. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 2, characterized in that, The process of determining whether to use a graded injection molding strategy for the gasket solid particles includes, If the melt flow index is greater than the melt flow index threshold, then a graded injection molding strategy is determined for the gasket solid particles.

4. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 3, characterized in that, The process of generating several fingerprint differences includes, The first absorption peak factor, the first absorbance factor, the second absorption peak factor, and the second absorbance factor are determined based on the spectral characteristic parameters and several fingerprint data reference tables, respectively. The first particle size factor, the first chromaticity factor, the second particle size factor, and the second chromaticity factor are determined based on the geometric feature parameters and several fingerprint data reference tables, respectively. The sum of the first absorption peak factor, the first absorbance factor, the first particle size factor, and the first chromaticity factor is determined to be the first fingerprint difference. The sum of the second absorption peak factor, the second absorbance factor, the second particle size factor, and the second chromaticity factor is determined to be the second fingerprint difference.

5. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 4, characterized in that, The process of determining the graded injection molding path of the gasket solid particles includes, If the first fingerprint difference is less than or equal to the second fingerprint difference, then the graded injection molding line of the gasket solid particles is determined to be the first graded injection molding line. If the first fingerprint difference is greater than the second fingerprint difference, then the graded injection molding line of the gasket solid particles is determined to be the second graded injection molding line.

6. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 5, characterized in that, The process of generating the simulated product index includes, Several monitoring points are set on each gasket. The gasket is compressed to obtain the compression rebound factor of each monitoring point and the temperature value of each monitoring point is collected. The standard deviation of several of the compression rebound factors is determined as the compression rebound coefficient; The standard deviation of a number of the temperature values ​​is determined as the temperature distribution coefficient; The arithmetic square root of the product of the compression rebound coefficient and the temperature distribution coefficient is determined as the simulated finished product index; If the simulated finished product index is greater than the simulated finished product index threshold, the double-layer gasket injection molding is deemed unqualified.

7. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 6, characterized in that, The process of determining the defect risk of the gasket solid particles includes, The gasket solid particles are divided into several components, and the surface gloss, backlight translucency and impact sound main frequency of each component gasket solid particles are obtained respectively. Based on clustering algorithms, surface gloss, backlight translucency, and impact sound dominant frequency, the defect risk of the gasket solid particles is determined to be either a high-defect-risk gasket, a medium-defect-risk gasket, or a low-defect-risk gasket.

8. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 7, characterized in that, The process of generating defect overlap includes, Obtain the center coordinates and radius of action of each defect in the strong defect risk pad and the weak defect risk pad respectively; The defect area is determined based on the center coordinates and the radius of action. The overlapping area is determined based on the defect area of ​​the strong defect risk pad and the defect area of ​​the weak defect risk pad, and the ratio of the overlapping area to the benchmark overlapping area is calculated to obtain the defect overlap degree.

9. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 8, characterized in that, The process of determining whether the candidate gaskets are compatible includes, If the defect overlap is less than or equal to the defect overlap threshold, then the candidate gasket is determined to be a match. If the degree of defect overlap is greater than the defect overlap threshold, then the candidate gasket is determined to be unmatched.

10. The closed-loop injection molding control method for thermoplastic elastomer pharmaceutical composite gaskets according to claim 9, characterized in that, The process of determining the adjustment defect overlap threshold or updating the corresponding fingerprint data reference table includes, The matching qualification rate is determined based on the total number of candidate gaskets, the total number of double-layer gaskets, and the total number of triple-layer gaskets in the second-level injection molding line; If the matching success rate is less than the matching success threshold, then the corresponding fingerprint data reference table will be updated. If the matching pass rate is greater than or equal to the matching pass threshold, then the defect overlap threshold is adjusted to be smaller.

Images