Parameter optimization method and device for traditional Chinese medicine mask forming process and medium

Abstract

The invention discloses a parameter optimization method and device for a traditional Chinese medicine mask forming process and a medium, and relates to the technical field of continuous production of traditional Chinese medicine preparations. The parameter optimization method comprises the steps that the torque value of a stirring shaft is collected, apparent viscosity is calculated, the particle size value of particles is detected, the rotating speed is dynamically adjusted according to the particle size value of the particles, and a high-dispersion traditional Chinese medicine extracting solution is generated; starting a coating machine for spraying based on the initial coating parameter set, capturing a quantum dot fluorescence signal in real time, and generating a quantum dot fluorescence intensity distribution image; according to the quantum dot fluorescence intensity distribution image, the average penetration depth value and the transverse diffusion uniformity value of the liquid medicine are calculated, the coating parameters are dynamically adjusted according to the average penetration depth value and the transverse diffusion uniformity value of the liquid medicine, and an optimized coating parameter set is generated. According to the invention, the online closed-loop optimization of the permeation-diffusion behavior of the film layer is realized, the three-dimensional uniform distribution of the liquid medicine in the base cloth is ensured, and the precise control of the functional gradient of the film layer and the consistency of drug effect release are enhanced.

Description

Technical Field

[0001] This invention relates to the field of continuous production technology of traditional Chinese medicine preparations, and in particular to a method, equipment and medium for optimizing parameters in a traditional Chinese medicine facial mask forming process. Background Technology

[0002] In the industrial production of traditional Chinese medicine facial masks, conventional processes employ segmented parameter control: the herbal extraction stage uses constant-speed stirring to achieve solid-liquid mixing, while the coating stage is based on preset speed and tension parameters. The industry generally relies on offline detection methods (such as high-performance liquid chromatography) to sample active ingredients, combined with manual adjustment of coating parameters to ensure quality. Existing technologies have achieved basic automated control, such as adjusting the stirring rate using viscosity sensors or monitoring coating uniformity using image processing. These methods offer stability advantages in large-scale production, comply with GMP requirements, and are the mainstream application solution in the industry.

[0003] However, conventional methods have limitations in terms of process linkage and real-time control: First, the particle dispersion control and coating parameter settings in the extraction stage are independent of each other, resulting in insufficient matching between the rheological properties of the drug solution and the coating equipment, which affects the uniformity of the film layer; Second, quality monitoring relies on terminal sampling and testing, and parameter adjustment lags behind the production process, making it difficult to achieve online closed-loop optimization of penetration depth and diffusion uniformity. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a parameter optimization method for the molding process of traditional Chinese medicine facial masks to solve the problems of parameter fragmentation and monitoring lag in the production of traditional Chinese medicine facial masks.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a parameter optimization method for the forming process of a traditional Chinese medicine facial mask, comprising: collecting the torque value of the stirring shaft to calculate the apparent viscosity and detecting the particle size value; dynamically adjusting the rotation speed according to the particle size value to generate a highly dispersed traditional Chinese medicine extract; conveying the highly dispersed traditional Chinese medicine extract to a coating mixing tank and setting the initial coating parameters according to the apparent viscosity to obtain an initial coating parameter set; starting the coating machine to perform spraying based on the initial coating parameter set and capturing quantum dot fluorescence signals in real time to generate a quantum dot fluorescence intensity distribution image; calculating the average penetration depth value and the lateral diffusion uniformity value of the medicinal solution based on the quantum dot fluorescence intensity distribution image, and dynamically adjusting the coating parameters according to the average penetration depth value and the lateral diffusion uniformity value of the medicinal solution to generate an optimized coating parameter set; starting the coating machine again to perform spraying based on the optimized coating parameter set to generate an optimized wet facial mask substrate, and detecting the content of lycolic acid and the diameter of the antibacterial zone on the wet facial mask substrate, while generating a process parameter optimization report in conjunction with the optimized coating parameter set.

[0008] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for generating the highly dispersed traditional Chinese medicine extract are as follows:

[0009] The torque value of the stirring shaft is collected in real time, and the apparent viscosity of the extract is calculated by combining it with the blade geometry.

[0010] The apparent viscosity is compared with the viscosity control threshold to generate a viscosity over-limit signal, and the temperature of the extract is adjusted according to the viscosity over-limit signal.

[0011] The particle size of the extract is detected and compared with the particle size control threshold to generate a particle size exceedance signal. At the same time, the stirring speed is adjusted according to the particle size exceedance signal to generate a highly dispersed Chinese herbal extract.

[0012] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for obtaining the initial coating parameter set are as follows:

[0013] The highly dispersed Chinese herbal extract is transported to the coating mixing tank, and biocompatible ZnAgInS quantum dots are added to generate a quantum dot Chinese herbal coating solution.

[0014] The initial coating speed and initial substrate tension are calculated based on the apparent viscosity to generate an initial coating parameter set.

[0015] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for generating the quantum dot fluorescence intensity distribution image are as follows:

[0016] Based on the initial coating parameter set, the coating machine is started to spray quantum dot traditional Chinese medicine coating liquid to generate fluorescent wet film substrate;

[0017] Based on the fluorescent wet film substrate, the quantum dot luminescence signal is captured by a high-speed fluorescence camera and digital grayscale value conversion is performed to generate the original fluorescence image;

[0018] The original fluorescence image is subjected to real-time noise reduction and contrast enhancement, and the continuous frame fluorescence image data is integrated to generate a quantum dot fluorescence intensity distribution image.

[0019] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for calculating the average penetration depth and lateral diffusion uniformity of the medicinal solution are as follows:

[0020] Based on the quantum dot fluorescence intensity distribution image, the coordinates of the longitudinal fluorescence intensity front position are extracted, and the average penetration depth of the drug solution is calculated.

[0021] The pixel grayscale values ​​in the horizontal direction of the quantum dot fluorescence intensity distribution image were analyzed, and the uniformity of the drug diffusion in the horizontal direction was calculated by the image grayscale variation coefficient analysis method.

[0022] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for generating the optimized coating parameter set are as follows:

[0023] The average penetration depth of the drug solution is compared with the maximum allowable penetration depth threshold to generate a penetration error signal. The coating speed is then adjusted based on the penetration error signal to obtain an optimized coating speed.

[0024] The lateral diffusion uniformity value of the drug solution is compared with the lateral diffusion uniformity threshold to generate a diffusion non-uniformity signal. The base fabric tension is then adjusted based on the diffusion non-uniformity signal to obtain the optimized base fabric tension.

[0025] By integrating and optimizing coating speed and substrate tension, an optimized coating parameter set is generated.

[0026] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the generation of the optimized wet facial mask substrate refers to starting the coating machine to re-spray the quantum dot traditional Chinese medicine coating liquid evenly according to the optimized coating parameter set, thereby generating the optimized wet facial mask substrate.

[0027] As a preferred embodiment of the parameter optimization method for the traditional Chinese medicine facial mask forming process described in this invention, the steps for generating the process parameter optimization report are as follows:

[0028] Standardized films were cut from optimized wet mask substrates, and the content of lycolic acid was detected by HPLC. Simultaneously, the films were applied to agar plates inoculated with bacteria, and the diameter of the inhibition zone was measured to obtain a drug efficacy-component correlation dataset.

[0029] Integrate and optimize the coating parameter set and the efficacy-component correlation dataset to generate a process parameter optimization report.

[0030] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the parameter optimization method for the traditional Chinese medicine facial mask forming process as described in the first aspect of the present invention.

[0031] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the parameter optimization method for the traditional Chinese medicine facial mask forming process as described in the first aspect of the present invention.

[0032] The beneficial effects of this invention are as follows: by generating highly dispersed traditional Chinese medicine extracts, the rheological properties of the extracts and the particle dispersion are synergistically controlled, ensuring the uniformity and stability of the extracts and improving the dispersion and coating compatibility of highly active ingredients; by dynamically adjusting the coating parameters, the online closed-loop optimization of the membrane layer's permeation-diffusion behavior is achieved, ensuring the three-dimensional uniform distribution of the extracts in the substrate and strengthening the precise control of the membrane layer's functional gradient and the consistency of drug release. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of a parameter optimization method for the molding process of traditional Chinese medicine facial masks.

[0035] Figure 2 This is a flowchart for generating highly dispersed traditional Chinese medicine extracts.

[0036] Figure 3 A flowchart for enhancing the contrast of fluorescence images.

[0037] Figure 4 A flowchart for terminal detection and report generation. Detailed Implementation

[0038] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0039] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0041] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for optimizing the parameters of a traditional Chinese medicine facial mask forming process, comprising the following steps:

[0042] S1. Collect the torque value of the stirring shaft to calculate the apparent viscosity, and detect the particle size value. Adjust the rotation speed dynamically according to the particle size value to generate a highly dispersed Chinese herbal extract.

[0043] The torque value of the stirring shaft is collected in real time, and the apparent viscosity of the extract is calculated by combining it with the blade geometry.

[0044] Furthermore, the rotational resistance signal of the stirring shaft is collected in real time by a strain gauge torque sensor at the bottom of the mixing tank: when the bearing is subjected to shear stress, the deformation of the metal strain gauge in the sensor causes the bridge to become unbalanced, and outputs a raw torque analog voltage value that is proportional to the torque; the raw torque analog voltage value is converted into a digital torque value through high-precision analog-to-digital conversion; a servo motor encoder is used to collect the real-time rotational speed, and combined with the digital torque value and the blade geometry, the apparent viscosity of the extract is calculated using rotational rheology formulas;

[0045] The expression for calculating the apparent viscosity of the extract is: ;

[0046] in, It is the apparent viscosity of the extract; This is the torque value of the stirring shaft; These are the blade geometry coefficients; It is the real-time rotational speed;

[0047] It should be noted that the blade geometry coefficients are dimensionless constants related to the blade shape / size, which are determined in advance through fluid dynamics simulation combined with Newtonian fluid calibration experiments. An exemplary range of values ​​is 0.012~0.025.

[0048] The apparent viscosity is compared with the viscosity control threshold to generate a viscosity over-limit signal, and the temperature of the extract is adjusted according to the viscosity over-limit signal.

[0049] Furthermore, the apparent viscosity is compared with the viscosity control threshold: when the apparent viscosity exceeds the viscosity control threshold, a high-level viscosity over-limit signal is generated; based on the high-level viscosity over-limit signal, the solid-state relay is triggered to close, energizing the heater (3kW quartz tube) to perform the heating operation: the heater converts electrical energy into heat energy, which heats the extract through a stainless steel heat exchange plate; at the same time, the temperature of the extract is monitored in real time by a wall-mounted PT100 temperature sensor. When the temperature of the extract is lower than the viscosity control target temperature threshold, the drive circuit maintains the heater in the energized state; when the temperature of the extract exceeds the viscosity control target temperature threshold, the drive circuit disconnects the solid-state relay to stop heating, thus completing the dynamic control of the extract temperature.

[0050] It should be noted that the viscosity control threshold is a rheological safety boundary value set based on particle dispersion stability experiments, with an exemplary range of 1.2 to 1.8; the viscosity control target temperature threshold is a thermal control optimization target value set through thermogravimetric-rheological combined testing, with an exemplary range of 48 to 52°C.

[0051] The particle size of the extract is detected and compared with the particle size control threshold to generate a particle size exceedance signal. At the same time, the stirring speed is adjusted according to the particle size exceedance signal to generate a highly dispersed Chinese herbal extract.

[0052] Furthermore, the particle size distribution of the extract is detected in real time using an online laser particle size analyzer to obtain particle size values. These particle size values ​​are then compared with the particle size control threshold in real time. When the particle size value exceeds the particle size control threshold, a high-level particle size exceedance signal is output. Based on this high-level signal, the stirring motor is driven to increase the stirring speed from the reference value (determined through torque-power balance experiments and the optimal initial energy consumption value set by the fluid flow pattern transition point) to the target speed value (the critical speed value for agglomeration and breakup set based on flow field CFD simulation and cavitation synergistic experiments). Simultaneously, the ultrasonic pulse generator is driven to trigger the pulse cavitation effect. Finally, the particle size value is rechecked in real time. When the continuously detected particle size value is within the dispersion threshold, the particle size exceedance signal is reset to a low level, the stirring speed is restored to the reference value, and the ultrasonic generator is turned off, resulting in a highly dispersed herbal extract.

[0053] It should be noted that the particle size control threshold is a control trigger critical value set based on particle dispersion stability experiments, with an exemplary range of 15~25μm; the dispersion compliance threshold is a process acceptance standard value set through online detection by a laser particle size analyzer and skin penetration experiments, with an exemplary range of 5~10μm; the pulse cavitation effect refers to the technical mechanism of periodically generating and collapsing microbubbles in a liquid by intermittently emitting high-frequency ultrasonic waves, and using the high-energy microjets and shock waves released at the moment of bubble collapse to physically pulverize particle agglomerates.

[0054] S2. The highly dispersed Chinese herbal extract is transported to the coating mixing tank, and the initial coating parameters are set according to the apparent viscosity to obtain the initial coating parameter set.

[0055] The highly dispersed Chinese herbal extract is transported to the coating mixing tank, and biocompatible ZnAgInS quantum dots are added to generate a quantum dot Chinese herbal coating solution.

[0056] Furthermore, the highly dispersed traditional Chinese medicine extract is transported to the coating tank through sterile pipelines, and the liquid level in the coating tank is monitored in real time. Based on the liquid level in the coating tank, biocompatible ZnAgInS quantum dots are precisely added at a fixed ratio, and a quantum dot feeding completion signal is output. Based on the quantum dot feeding completion signal, a magnetic stirrer is started, and the stirring torque value is monitored in real time. When the stirring torque value fluctuation is lower than the torque stability judgment threshold, a torque stability signal is output. Based on the torque stability signal, an online fluorescence spectrometer is activated to scan fixed detection points in the coating tank, collect the raw fluorescence intensity values ​​of each point, and calculate the average fluorescence intensity and fluorescence intensity standard deviation based on the raw fluorescence intensity values ​​of each point. The fluorescence intensity fluctuation rate is obtained based on the ratio of the average fluorescence intensity and the fluorescence intensity standard deviation. If the fluorescence intensity fluctuation rate exceeds the quantum dot dispersion tolerance threshold, a high-speed homogenizer is triggered to run, and the quantum dot traditional Chinese medicine coating solution is dispersed a second time until the fluorescence intensity fluctuation rate is retested within the quantum dot dispersion tolerance threshold, and a quantum dot traditional Chinese medicine coating solution with uniform quantum dot distribution is output.

[0057] The expression for calculating the fluorescence intensity fluctuation rate is:

[0058] ;

[0059] in, It is the fluorescence intensity fluctuation rate; It is the average fluorescence intensity; It is the standard deviation of fluorescence intensity;

[0060] It should be noted that the biocompatible ZnAgInS quantum dots are quaternary alloy fluorescent nanoprobes with a surface-modified silica-chitosan composite layer, specifically designed for real-time tracking of the three-dimensional penetration behavior of traditional Chinese medicine coating liquid in the mask base fabric; the torque stability judgment threshold is a critical value for judging mixing uniformity set through fluid dynamics experiments, with an exemplary value range of 3~8%; the quantum dot dispersion tolerance threshold is the maximum permissible deviation value for quantum dot distribution uniformity set through film formation monitoring error inversion experiments, with an exemplary value range of 2~5%.

[0061] Calculate the initial coating speed and initial base fabric tension based on the apparent viscosity to generate an initial coating parameter set;

[0062] Furthermore, the apparent viscosity of the highly dispersed Chinese herbal extract is read in real time, and the initial coating speed is calculated based on the apparent viscosity using the rheology-coating speed conversion formula. At the same time, the initial value of the base fabric tension is calculated using the viscosity-tension compensation formula. The initial coating speed and the initial value of the base fabric tension are integrated into a structured data set to generate an initial coating parameter set.

[0063] The expressions for calculating the initial coating velocity and the initial tension of the base fabric are as follows:

[0064] ;

[0065] in, It is the initial velocity of the coating; It is the rheology-velocity conversion factor (representing the inhibition factor of viscosity on coating speed, set through coating stacking critical test, with an exemplary value range of 1.3~1.7).

[0066] ;

[0067] in, This is the initial value of the base fabric tension; It is the viscosity-tension gain coefficient (representing the mechanical enhancement factor of viscosity on tension, set based on the elastic modulus of the base fabric and wrinkle elimination experiments, with an exemplary value range of 0.35~0.45).

[0068] S3. Start the coating machine to spray based on the initial coating parameter set, and capture the quantum dot fluorescence signal in real time to generate a quantum dot fluorescence intensity distribution image;

[0069] Based on the initial coating parameter set, the coating machine is started to spray quantum dot traditional Chinese medicine coating liquid to generate fluorescent wet film substrate;

[0070] Furthermore, the initial coating speed and initial substrate tension are analyzed from the initial coating parameter set. The coating roller speed is set according to the rheology-coating speed conversion formula based on the initial coating speed. Simultaneously, the pressure of the pneumatic cylinder is obtained through the tension-pressure balance formula based on the initial substrate tension. The tension roller is driven to stretch the substrate based on the coating roller speed and the pneumatic cylinder pressure. The substrate passes through the coating head at a uniform speed under the initial substrate tension value, and the quantum dot herbal coating liquid is sprayed by the ultrasonic atomizing nozzle to form a uniformly wetted substrate. The unit area mass of the uniformly wetted substrate is monitored in real time by an online weighing sensor. If the unit area mass deviates from the coating weight gain target value, the initial coating speed is dynamically fine-tuned until the weight gain reaches the target, and a weight gain target signal is output. Based on the weight gain target signal, the UV curing lamp is triggered to irradiate the uniformly wetted substrate, activating the fluorescence properties of the quantum dots and outputting a fluorescent wet film substrate.

[0071] It should be noted that the target value for coating weight gain is the mass of coating liquid per unit area set based on the minimum effective dose of the active ingredient in the prescription and the liquid absorption saturation point of the base fabric. An exemplary range is 3.0~4.0 mg / cm².

[0072] Based on the fluorescent wet film substrate, the quantum dot luminescence signal is captured by a high-speed fluorescence camera and digital grayscale value conversion is performed to generate the original fluorescence image;

[0073] Furthermore, the fluorescent wet film substrate is placed on a high-speed conveyor belt. The linear speed of the conveyor belt is precisely controlled by a servo motor to synchronize with the initial coating speed, triggering the high-speed fluorescence camera to start shooting. The high-speed fluorescence camera focuses the light emission signal of the quantum dots on the substrate surface through an optical filter. The light emission signal is then emitted by photons bombarded by the photomultiplier tube cathode (cesium gallium nitride material). Simultaneously, the signal is amplified by a second-order dynamo and output as a photon flow analog signal. The photodiode in the photon flow analog signal generates a charge signal array under the drive of the gate voltage. A reference voltage is applied to the charge signal array, and the instantaneous voltage value is locked by a sample-and-hold circuit. The instantaneous voltage value is converted into a discrete digital value within a fixed range by an analog-to-digital converter. The discrete digital value is then mapped to a grayscale range and filled into the corresponding coordinate positions according to the physical pixel arrangement of the photoelectric sensor, outputting a digital grayscale matrix. The Bayer filtering algorithm is applied to the digital grayscale matrix: the odd row and odd column pixel values ​​are taken as the R channel, the even row and even column pixel values ​​as the B channel, and the average value of adjacent pixels is taken as the G channel. Artifacts are eliminated by bilinear interpolation to generate the original fluorescence image.

[0074] It should be noted that the RGGB array is the standard arrangement pattern of Bayer filters, which refers to the color filter pattern that is periodically arranged in 2×2 pixel units on the surface of an image sensor (such as CCD / CMOS).

[0075] The original fluorescence image is subjected to real-time noise reduction and contrast enhancement, and the continuous frame fluorescence image data is integrated to generate a quantum dot fluorescence intensity distribution image;

[0076] Furthermore, the original fluorescence image is segmented into 8×8 pixel blocks, similar block groups are searched and 3D transformation is performed (combining Haar wavelet and discrete cosine transform), while hard thresholding is applied to the transform coefficients (preserving significant signal components). After inverse transformation reconstruction, a denoised fluorescence image is output. The denoised fluorescence image is then divided into 64×64 pixel blocks, and the gray values ​​of all pixels within each block are extracted to form a gray value set. The mean and standard deviation of the gray values ​​in each pixel block's gray value set are calculated to generate a local histogram for each block. Using the mean gray value as the center point and the standard deviation of the gray value as the fluctuation range benchmark, a judgment boundary for abnormal pixels is dynamically generated. Pixels outside the judgment boundary are judged as abnormal pixels (overly bright / overly dark areas). The gray values ​​of abnormal pixels are redistributed through histogram equalization to generate a contrast-enhanced fluorescence image. Based on the contrast-enhanced fluorescence image, multiple frames of fluorescence data are continuously acquired and processed by light... The flow method identifies the displacement of each pixel in the XY direction, removes outliers, and outputs valid motion trajectory data. Based on the valid motion trajectory data, the affine transformation parameters are directly solved using the least squares method: the initial coordinates of each pixel are associated with the coordinates after displacement, the sum of squared residuals between the predicted and actual displacements is minimized, and the affine transformation matrix is ​​output after residual verification. Based on the affine transformation matrix, an inverse geometric transformation is performed on the original fluorescence image, and the pixel gray values ​​are resampled to generate a displacement-compensated fluorescence image. The displacement-compensated fluorescence image is then assigned decreasing weights according to the time series (the first frame has the highest weight), and the fluorescence data from multiple frames are superimposed by a weighted average pixel-by-pixel to generate a time-integrated fluorescence image. Based on the time-integrated fluorescence image, the spatial coordinates and gray values ​​of each pixel are extracted, a high-resolution matrix (rows and columns map to the physical location of the substrate) is constructed, and the gray values ​​are linearly mapped to the standard intensity range to finally generate a quantum dot fluorescence intensity distribution image.

[0077] It should be noted that the transform coefficients are the frequency component values ​​obtained by decomposing the image patch in the 3D transform domain (such as Haar wavelet + discrete cosine transform), and are set by the hard threshold shrinkage method. The exemplary value range is the entire real number domain (concentrated in the interval of -1 to 1 after normalization). The standard intensity range refers to the pixel gray values ​​of the original fluorescence image being transformed to the normalized interval through linear mapping. The minimum and maximum gray values ​​are dynamically determined by scanning the full-frame pixels of the quantum dot fluorescence intensity distribution image. The exemplary value range is 0~255.

[0078] S4. Based on the quantum dot fluorescence intensity distribution image, calculate the average penetration depth and lateral diffusion uniformity of the drug solution, and dynamically adjust the coating parameters according to the average penetration depth and lateral diffusion uniformity of the drug solution to generate an optimized coating parameter set.

[0079] Based on the quantum dot fluorescence intensity distribution image, the coordinates of the longitudinal fluorescence intensity front position are extracted, and the average penetration depth of the drug solution is calculated.

[0080] Furthermore, based on the quantum dot fluorescence intensity distribution image, the pixels are scanned column by column along the thickness direction of the base fabric (Y-axis), and the fluorescence intensity profile data of each column is output. Based on the intensity profile data of each column, the fluorescence intensity gradient value is obtained by the central difference method. At the same time, the position of the maximum gradient point is identified according to the fluorescence intensity gradient value, and the longitudinal fluorescence intensity front position coordinates are generated. The longitudinal fluorescence intensity front position coordinates are subtracted from the preset base fabric surface reference coordinates to identify the single column penetration depth. The arithmetic mean of all single column penetration depths is taken to output the average penetration depth value of the drug solution.

[0081] The expression for calculating the average penetration depth of the drug solution is:

[0082] ;

[0083] in, It is the average penetration depth of the drug solution; It is the physical size of the pixel; It is the column index number in the width direction of the base fabric; It is the total number of valid columns included in the statistics; It is a weighting factor (generated directly through the position determination rule, with an exemplary value range of 0~1), representing the weight for suppressing edge errors; These are the pixel coordinates of the front, representing the first... The Y-axis position of the drug penetration front; These are the base coordinates, representing the first... The Y-axis reference position of the base fabric surface;

[0084] It should be noted that the reference coordinates of the base fabric surface are generated by pre-scanning the dried base fabric sample, detecting the Y-axis position of the point where the fluorescence intensity of the dried base fabric sample drops sharply, and linearly adjusting the coordinate values ​​of each column according to the tilt of the base fabric.

[0085] The pixel gray values ​​in the horizontal direction of the quantum dot fluorescence intensity distribution image were analyzed, and the uniformity of the horizontal diffusion of the drug solution was calculated by the image gray value variation coefficient analysis method.

[0086] Furthermore, based on the quantum dot fluorescence intensity distribution image, the data is scanned row by row along the width direction (X-axis) of the base fabric to extract the gray values ​​of all pixels in each row. The arithmetic mean of the gray values ​​of all pixels in each row is then calculated to generate the row average gray value. Based on the gray values ​​of all pixels in each row and the row average gray value, the standard deviation is calculated to generate the row gray standard deviation. The row gray coefficient of variation is obtained according to the ratio between the row average gray value and the row gray standard deviation. Finally, the arithmetic mean of the row gray coefficients of variation for all rows is calculated to obtain the lateral diffusion uniformity value of the drug solution.

[0087] The expression for calculating the lateral diffusion uniformity of the drug solution is:

[0088] ;

[0089] in, It is the value of the uniformity of the lateral diffusion of the drug solution; It is the standard deviation of grayscale in a single row, representing the first line. The fluctuation of grayscale values ​​across all pixels; It is the average gray value of a single row, representing the first line. The arithmetic mean of the grayscale values ​​of all pixels in the row;

[0090] The average penetration depth of the drug solution is compared with the maximum allowable penetration depth threshold to generate a penetration error signal. The coating speed is then adjusted based on the penetration error signal to obtain an optimized coating speed.

[0091] Furthermore, the average penetration depth of the chemical solution is compared with the maximum allowable penetration depth threshold. If the average penetration depth exceeds the maximum allowable penetration depth threshold, a high-level penetration error signal is generated; if the average penetration depth is below the maximum allowable penetration depth threshold, a low-level signal is maintained. Based on the penetration error signal, a coating speed command is triggered: a high level reduces the coating speed, while a low level maintains the original speed. The coating speed command is converted into a pulse width modulation (PWM) signal to drive the servo motor, adjusting the coating roller speed according to the speed conversion formula to obtain a new coating roller speed. Finally, the coating machine runs at the new coating roller speed and re-measures the average penetration depth of the chemical solution. When the re-measured average penetration depth is below the maximum allowable penetration depth threshold, the penetration error signal is reset to a low-level signal, ultimately obtaining the optimized coating speed.

[0092] It should be noted that the maximum allowable penetration depth threshold is a value proportional to the thickness of the base fabric determined by an experiment on the balance of capillary adsorption force and gravity, with an exemplary range of 0.3 to 0.35.

[0093] The lateral diffusion uniformity value of the drug solution is compared with the lateral diffusion uniformity threshold to generate a diffusion non-uniformity signal. The base fabric tension is then adjusted based on the diffusion non-uniformity signal to obtain the optimized base fabric tension.

[0094] Furthermore, the lateral diffusion uniformity value of the drug solution is compared with the lateral diffusion uniformity threshold. If the lateral diffusion uniformity value exceeds the threshold, a high-level diffusion non-uniformity signal is generated; if the value is below the threshold, a low-level signal is maintained. Based on the diffusion non-uniformity signal, a base fabric tension adjustment command is triggered: a high level increases the tension (e.g., +0.1 MPa, verified by numerous wrinkle elimination experiments), while a low level maintains the original base fabric tension. The base fabric tension adjustment command is then converted into a pneumatic control signal using a linear conversion formula, and based on this signal, the pneumatic cylinder is driven to output a pressure increment. The pneumatic cylinder receives the pressure increment, pushes the piston to generate thrust, and converts the linear thrust into the angular displacement of the tension roller via a linkage mechanism. This angular displacement increases the base fabric tension. Simultaneously, the lateral diffusion uniformity value of the drug solution is retested. If the retested value is below the threshold, the diffusion non-uniformity signal is reset to a low level, ultimately obtaining the optimized base fabric tension.

[0095] It should be noted that the transverse diffusion uniformity threshold is a benchmark value determined through extensive coating tests and dynamically fine-tuned based on the characteristics of the base fabric (non-woven fabric / silk). An exemplary value range is 4.5%~5.5%.

[0096] Integrate and optimize coating speed and base fabric tension to generate an optimized coating parameter set;

[0097] Furthermore, the system reads the optimized coating speed updated in real time and verifies it against the process safety speed range threshold. If the optimized coating speed exceeds the process safety speed range threshold, it is forcibly limited to the boundary value (set through a balance experiment between the surface tension of the coating liquid and the capillary adsorption force of the base fabric), and outputs the valid coating speed that has passed the verification. Simultaneously, the system reads the optimized base fabric tension updated in real time and verifies it against the base fabric breakage safety threshold. If the tension exceeds the base fabric breakage safety threshold, it is forcibly limited to the upper limit value (set through a critical experiment of liquid splashing), and outputs the valid base fabric tension that has passed the verification. The system integrates and encapsulates the valid coating speed and the valid base fabric tension to generate an optimized coating parameter set.

[0098] It should be noted that the process safety speed range threshold is a coating speed safety boundary value set by verifying the balance between coating coverage and splash prevention through thousands of coating tests, with an exemplary range of 0.5~2.0m / min; the base fabric breakage safety threshold is a tension safety boundary value set based on the yield strength test of the base fabric material, with an exemplary range of 0.4~0.48MPa.

[0099] S5. Based on the optimized coating parameter set, start the coating machine to re-spray, generate an optimized wet film substrate, and test the content of Lulutong acid and the diameter of the antibacterial ring on the optimized wet film substrate. At the same time, generate a process parameter optimization report based on the optimized coating parameter set.

[0100] Based on the optimized coating parameter set, the coating machine is started to re-spray the quantum dot traditional Chinese medicine coating liquid evenly to generate an optimized wet film substrate.

[0101] Furthermore, the optimal coating speed is analyzed and optimized from the coating parameter set. A rheology-coating speed conversion formula is used to drive a servo motor to set the coating roller speed. Simultaneously, the base fabric tension is optimized, and a pressure cylinder is controlled according to a pressure conversion formula to output pressure. Based on the coating roller speed and the pressure cylinder, a tension roller is driven to stretch the base fabric to the optimized tension. Under the optimized tension, the base fabric passes through the coating head at a uniform speed, and an ultrasonic atomizing nozzle is activated to atomize the quantum dot herbal coating liquid into droplets and spray them evenly onto the coating surface. An online weighing sensor monitors the unit area of ​​the coating in real time. If the mass per unit area deviates from the target weight gain value for coating, the nozzle flow rate is dynamically adjusted until the weight gain meets the target. At this point, a continuous wet film layer is formed on the surface of the base fabric, and a weight gain target signal is output. Based on the weight gain target signal, a UV curing lamp is triggered to irradiate the coating to activate the fluorescence properties of quantum dots, generating a wet film substrate with a stable fluorescent label. Finally, the thickness of the wet film layer of the wet film substrate is scanned by a laser thickness gauge. If the fluctuation of the wet film layer thickness exceeds the wet film thickness tolerance threshold, the coating parameters are recalculated. If the fluctuation of the wet film layer thickness is lower than the wet film thickness tolerance threshold, a qualified optimized wet film substrate is output.

[0102] It should be noted that the wet film thickness tolerance threshold is set through a dual-critical experiment verifying film cracking and drug release, with an exemplary range of ±5%.

[0103] Standardized films were cut from optimized wet mask substrates, and the content of lycolic acid was detected by HPLC. Simultaneously, the films were applied to agar plates inoculated with bacteria, and the diameter of the inhibition zone was measured to obtain a drug efficacy-component correlation dataset.

[0104] Furthermore, two standardized membrane sheets were cut from the optimized wet mask substrate, outputting test sample A and test sample B with positioning coordinates. Test sample A was dehydrated using a freeze dryer and then ground into powder, outputting a uniformly dried test powder. The test powder was accurately weighed and added to a methanol solution, then ultrasonically extracted and centrifuged to obtain the supernatant, outputting the Lulutong acid test solution. The Lulutong acid test solution was filtered through an organic phase filter membrane and injected into a high-performance liquid chromatograph for elution. The chromatographic peak with retention time was captured at a specific wavelength. The peak area was obtained using the external standard method and compared with the standard curve to obtain the content of lycolytic acid. Simultaneously, sample B was applied to agar plates inoculated with Staphylococcus epidermidis and Propionibacterium acnes for culture, and plates with inhibition zones were output. The diameter of the inhibition zone in the plate was measured with calipers, and the mean diameter of the inhibition zone for Staphylococcus epidermidis and Propionibacterium acnes was identified respectively. The lycolytic acid content and the mean diameter of the inhibition zone of all samples were integrated to construct a two-dimensional data pair, and finally, the efficacy-component correlation dataset was output.

[0105] It should be noted that the standard curve is a linear calibration curve plotted by high performance liquid chromatography (HPLC) with concentration as the x-axis and peak area as the y-axis, which is used to convert the peak area of ​​the sample to be tested into the content of luciferase.

[0106] Integrate and optimize the coating parameter set and the efficacy-component correlation dataset to generate a process parameter optimization report;

[0107] Furthermore, the optimized coating speed and optimized substrate tension are extracted from the optimized coating parameter set. Film thickness data is obtained by real-time scanning of the wet film substrate using a laser thickness gauge, and film thickness fluctuation is identified based on the film thickness data. The film thickness fluctuation is then compared with the wet film thickness tolerance threshold. If the film thickness fluctuation is lower than the wet film thickness tolerance threshold, the process performance is deemed satisfactory; if the film thickness fluctuation exceeds the wet film thickness tolerance threshold, the process performance is deemed unsatisfactory, and the process performance evaluation result is output. Simultaneously, the content of lycolic acid and the average diameter of the inhibition zone are extracted from the efficacy-component association dataset, and a dual threshold judgment rule is applied: if the lycolic acid content is lower than the threshold, the process performance is deemed unsatisfactory. If the content of Luffa cylindrica acid is greater than the threshold value and the average diameter of the inhibition zone is greater than the threshold value, the efficacy is considered to meet the standard. If the content of Luffa cylindrica acid is less than the threshold value and the average diameter of the inhibition zone is less than the threshold value, or if the content of Luffa cylindrica acid is less than the threshold value but the average diameter of the inhibition zone is greater than the threshold value, or if the content of Luffa cylindrica acid is greater than the threshold value but the average diameter of the inhibition zone is less than the threshold value, the efficacy is considered to not meet the standard, and the efficacy evaluation result is output. The process performance evaluation result and the efficacy performance evaluation result are integrated to generate a process parameter optimization report.

[0108] It should be noted that the dual threshold judgment rule is a collaborative judgment rule used to verify the efficacy status. It is set based on the data of the minimum effective dose experiment of active ingredient and the bacterial inhibition experiment, including the threshold of lycopene acid content and the threshold of inhibition zone diameter.

[0109] It should be noted that the threshold value of Lulutong acid content is set based on the minimum effective dose of the active ingredient in the in vitro transdermal release experiment, and the exemplary range is 1.15~1.25mg / g; the threshold value of inhibition zone diameter is set based on the critical inhibition experiment of Staphylococcus epidermidis and Propionibacterium acnes inoculated by the agar diffusion method, and the exemplary range is 15.5~16.5mm.

[0110] This embodiment also provides a computer device applicable to the parameter optimization method for the traditional Chinese medicine facial mask forming process, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the parameter optimization method for the traditional Chinese medicine facial mask forming process proposed in the above embodiment.

[0111] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0112] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the parameter optimization method for the traditional Chinese medicine facial mask forming process proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0113] In summary, this invention achieves synergistic regulation of the rheological properties of the extract and the particle dispersion by generating a highly dispersed traditional Chinese medicine extract, ensuring the uniformity and stability of the extract and improving the dispersion and coating compatibility of highly active ingredients; and achieves online closed-loop optimization of the membrane layer's permeation-diffusion behavior by dynamically adjusting the coating parameters, ensuring the three-dimensional uniform distribution of the extract in the substrate and strengthening the precise control of the membrane layer's functional gradient and the consistency of drug release.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing parameters in the molding process of a traditional Chinese medicine facial mask, characterized in that: Comprising, Collect the stirring shaft torque value to calculate the apparent viscosity, detect the particle size value, dynamically adjust the rotating speed according to the particle size value, and generate a highly dispersed traditional Chinese medicine extract; Transport the highly dispersed traditional Chinese medicine extract to the coating ingredient tank, set the initial coating parameters according to the apparent viscosity, and obtain an initial coating parameter set; Start the coating machine to spray based on the initial coating parameter set, capture the quantum dot fluorescence signal in real time, and generate a quantum dot fluorescence intensity distribution image; Calculate the average penetration depth value and the liquid lateral diffusion uniformity value of the medicine liquid according to the quantum dot fluorescence intensity distribution image, dynamically adjust the coating parameters according to the average penetration depth value and the liquid lateral diffusion uniformity value of the medicine liquid, and generate an optimized coating parameter set; Start the coating machine to spray again based on the optimized coating parameter set, generate an optimized wet film base material, and detect the content of the road acid and the diameter of the bacteriostatic circle of the optimized wet film base material, and generate a process parameter optimization report combining the optimized coating parameter set.

2. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. The highly dispersed traditional Chinese medicine extract is generated by the following steps, Collect the stirring shaft torque value in real time, calculate the apparent viscosity of the extract in combination with the paddle geometric coefficient, compare the apparent viscosity with the viscosity control threshold value, generate a viscosity overrun signal, and control the temperature of the extract according to the viscosity overrun signal; Detect the particle size value of the extract, compare it with the particle size control threshold value, generate a particle size overrun signal, and adjust the stirring speed according to the particle size overrun signal to generate a highly dispersed traditional Chinese medicine extract. The initial coating parameter set is obtained by the following steps, 3. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. Transport the highly dispersed traditional Chinese medicine extract to the coating ingredient tank, add biocompatible ZnAgInS quantum dots to generate quantum dot traditional Chinese medicine coating liquid, and calculate the initial coating speed and the initial value of the base fabric tension according to the apparent viscosity to generate the initial coating parameter set. The quantum dot fluorescence intensity distribution image is generated by the following steps, Start the coating machine to spray the quantum dot traditional Chinese medicine coating liquid based on the initial coating parameter set to generate a fluorescent wet film base material, capture the quantum dot luminescence signal through a high-speed fluorescence camera according to the fluorescent wet film base material, perform digital gray value conversion to generate an original fluorescence image, perform real-time noise reduction and contrast enhancement processing on the original fluorescence image, and integrate continuous frame fluorescence image data to generate a quantum dot fluorescence intensity distribution image.

4. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. The average penetration depth value and the liquid lateral diffusion uniformity value of the medicine liquid are calculated by the following steps, Extract the longitudinal fluorescence intensity front position coordinates from the quantum dot fluorescence intensity distribution image to calculate the average penetration depth value of the medicine liquid, analyze the pixel gray value in the transverse direction of the quantum dot fluorescence intensity distribution image, and calculate the liquid lateral diffusion uniformity value through an image gray scale variation coefficient analysis method. The optimized coating parameter set is generated by the following steps, Compare the average penetration depth value of the medicine liquid with the maximum allowed penetration depth threshold value to generate a penetration out-of-tolerance signal, adjust the coating speed according to the penetration out-of-tolerance signal, and obtain an optimized coating speed, compare the liquid lateral diffusion uniformity value with the lateral diffusion uniformity threshold value to generate a diffusion unevenness signal, adjust the base fabric tension according to the diffusion unevenness signal, and obtain an optimized base fabric tension, and integrate the optimized coating speed and the optimized base fabric tension to generate the optimized coating parameter set.

5. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. ​ ​ ​ 6. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. ​ ​ ​ ​ 7. The method of claim 1, wherein the parameters of the Chinese medicine mask forming process are optimized. The generating the optimized wet mask substrate refers to starting the coating machine to re-uniformly spray the quantum dot traditional Chinese medicine coating liquid according to the optimized coating parameter set, and generating the optimized wet mask substrate. 8.The method of claim 1, wherein the parameters of the process are optimized by using a computer program. The generating the process parameter optimization report has the following steps, A standardized film piece is cut from the optimized wet mask substrate, the content of linalool is detected by using an HPLC method, meanwhile, the film piece is pasted to an agar plate inoculated with bacteria, the diameter of the bacteriostatic circle is measured, and a pharmacodynamic-ingredient correlation data set is obtained; The optimized coating parameter set and the pharmacodynamic-ingredient correlation data set are integrated to generate the process parameter optimization report. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the parameter optimization method of the traditional Chinese medicine mask forming process according to any one of claims 1-8.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the parameter optimization method of the traditional Chinese medicine mask forming process according to any one of claims 1-8.

Images