Mixture mixing uniformity control method, system and equipment, medium and product

Abstract

The invention relates to the technical field of medicine preparation, and discloses a mixture mixing uniformity control method, system and equipment, a medium and a product, and the method comprises the following steps: determining a mixing speed switching condition and a mixing ending condition of a target mixture based on historical qualified monitoring data of the target mixture; obtaining current monitoring parameters of the target mixture, wherein the current monitoring parameters comprise a near infrared spectrum of the target mixture in the mixing process and mixing equipment parameters; determining a preset judgment parameter based on the current monitoring parameter; when the preset judgment parameter meets the mixing speed switching condition, controlling the mixing equipment to switch the stirring speed; and when the preset judgment parameter meets the mixing ending condition, controlling the mixing equipment to stop stirring. According to the method, the relevance between the equipment operation state and the mixing uniformity is fully considered, the raw material batch difference and the equipment state fluctuation can be dynamically adapted, and the mixing uniformity and the batch consistency are improved.

Description

Technical Field

[0001] This invention relates to the field of drug preparation technology, specifically to a method, system, equipment, medium, and product for controlling the uniformity of mixture mixing. Background Technology

[0002] In drug preparation, the uniformity of powder mixing is a core indicator for ensuring the quality of drug formulations, directly affecting their safety, stability, and efficacy. High-shear mixing is a technology that achieves efficient mixing, emulsification, and dispersion of materials through high-speed mechanical action, and it is widely used in the field of drug preparation.

[0003] Although high-shear mixing technology has shown good results in powder mixing, traditional high-shear mixing technology relies on fixed time or a single parameter, such as average particle size distribution, to trigger process switching when mixing powders. This leads to the powder being unable to adapt to fluctuations in raw materials and equipment during the mixing process, thus affecting the batch consistency of powder mixing uniformity. Summary of the Invention

[0004] This invention provides a method, system, device, medium, and product for controlling the uniformity of mixing mixtures, in order to solve the problem in the prior art that powder cannot adapt to fluctuations in raw materials and equipment during the mixing process.

[0005] In a first aspect, the present invention provides a method for controlling the uniformity of mixing of a mixture, the method comprising: Based on historical qualified monitoring data of the target mixture, determine the mixing rate switching conditions and mixing termination conditions of the target mixture; Acquire the current monitoring parameters of the target mixture, including the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment; Based on the current monitoring parameters, determine the preset judgment parameters; When the preset judgment parameters meet the mixing speed switching conditions, the mixing equipment is controlled to switch the stirring speed; when the preset judgment parameters meet the mixing end conditions, the mixing equipment is controlled to stop stirring.

[0006] This invention fully considers the correlation between equipment operating status and mixing uniformity. By combining process switching conditions determined based on historical qualified monitoring data, and real-time monitoring of near-infrared spectroscopy and equipment parameters, it can precisely adjust the stirring speed and control the timing of the mixing process. This data-driven control strategy avoids over- or under-stirring, significantly improves the uniformity of the mixture, reduces energy consumption and production time, and enhances production efficiency and consistency of mixing uniformity across different batches.

[0007] In one optional implementation, the preset judgment parameters include the standard deviation value and the deviation statistic; based on the current monitoring parameters, the preset judgment parameters are determined, including: Based on near-infrared spectroscopy, the standard deviation value was determined using an average moving window model. Based on the standard deviation value and the parameters of the mixed equipment, a principal component analysis model was used to determine the deviation statistics.

[0008] Standard deviation provides a measure of data volatility, effectively monitoring the stability of spectral data and promptly identifying anomalies or deviations, thereby supporting quality control and optimization in the production process. Calculating deviation statistics helps identify abnormal deviations.

[0009] In one optional implementation, when the preset judgment parameters meet the mixing speed switching condition, the mixing device is controlled to switch the stirring speed; when the preset judgment parameters meet the mixing end condition, the mixing device is controlled to stop stirring, including: When the standard deviation value meets the first standard deviation threshold range and the deviation statistic meets the first deviation statistic threshold range, the mixing device is controlled to switch from the preset low speed mode to the preset high speed mode. When the standard deviation value meets the second standard deviation threshold range, and the deviation statistic meets the second deviation statistic threshold range, and this continues for a preset time, the mixing device is controlled to stop stirring. Wherein, the minimum value of the first standard deviation threshold range is less than the maximum value of the second standard deviation threshold range; the minimum value of the first deviation statistic threshold range is less than the maximum value of the second deviation statistic threshold range.

[0010] It can achieve dynamic control of the mixing process, dynamically adapt to batch differences in raw materials and fluctuations in equipment status, and improve mixing uniformity and batch consistency.

[0011] In one optional implementation, based on historical qualified monitoring data of the target mixture, the mixing rate switching conditions and mixing termination conditions of the target mixture are determined, including: Acquire historical qualified monitoring data of the target mixture; historical qualified monitoring data includes the full process monitoring data of different qualified batches of the target mixture, from the start of mixing to the preset low-speed mode, then to the preset high-speed mode, until the end of mixing; Based on historical qualified monitoring data, principal component analysis was performed to determine the target principal components; Determine the target principal component score for each qualified batch of the target mixture in the historical qualified monitoring data; Based on the principal component scores, the initial deviation statistics of the target mixture for each qualified batch are determined during the mixing speed switching stage and the mixing end stage. Based on the initial deviation statistics, the threshold ranges for the first and second deviation statistics of the target mixture are determined.

[0012] In this embodiment, based on data-driven MSPC technology, continuous multi-batch data collected during the production process is reorganized, and the three-dimensional data composed of samples, variables, and batches is expanded into two-dimensional data. Principal component analysis (PCA) is used to project the high-dimensional variable data onto a low-dimensional feature space, establishing a multivariate statistical process control (MSPC) model to obtain the principal component scores and T values ​​of normal batch data. 2 Values ​​are set, and control lines are established. The monitoring data of the new batch is projected onto the established statistical model. By comparing it with the control lines of the normal batch data, the controlled status of the current batch of products is determined. Based on the online detection indicators and the control model, real-time process feedback control strategies are provided, which can dynamically adapt to the differences between raw material batches and the fluctuations in equipment status, thereby improving the mixing uniformity and batch consistency.

[0013] In one optional implementation, the first standard deviation threshold range is: (1.5 × 10⁻⁶) -5 1.9×10 -5 The threshold range for the first deviation statistic is: (μ1+0.5σ1, μ1+1.5σ1). The second standard deviation threshold range is: (0, 1.5 × 10⁻⁶) -5 The threshold range for the second deviation statistic is [0, μ1 + 0.5σ1]. Wherein, μ1 and σ1 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing speed switching stage, respectively; μ2 and σ2 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing end stage, respectively.

[0014] In one alternative implementation, prior to acquiring historical compliance monitoring data for the target mixture, the following steps are included: Obtain the original historical qualified monitoring data of the target mixture; Outlier removal was performed on the original historical qualified monitoring data; Standardize the historical qualified monitoring data after removing outliers; The standardized historical qualified monitoring data is time-aligned to obtain the historical qualified monitoring data.

[0015] It can effectively remove abnormal data, eliminate differences in units, synchronize the time axis, and ensure the standardization of subsequent data processing.

[0016] In a second aspect, the present invention provides a mixture mixing uniformity control system, the system comprising: The module is designed to determine the mixing rate switching conditions and mixing termination conditions of the target mixture based on historical qualified monitoring data of the target mixture. The acquisition module is used to acquire the current monitoring parameters of the target mixture, including the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment. The determination module is used to determine preset judgment parameters based on the current monitoring parameters; The control module is used to control the mixing equipment to switch the stirring speed when the preset judgment parameters meet the mixing speed switching conditions; and to control the mixing equipment to stop stirring when the preset judgment parameters meet the mixing end conditions.

[0017] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the mixture mixing uniformity control method of the first aspect or any corresponding embodiment described above.

[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the mixture mixing uniformity control method of the first aspect or any corresponding embodiment described above.

[0019] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the mixture mixing uniformity control method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the first process of a method for controlling the uniformity of mixing of a mixture according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a stirring device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the standard deviation according to an embodiment of the present invention; Figure 4 This is a structural block diagram of a mixture mixing uniformity control system according to an embodiment of the present invention; Figure 5This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] Currently, powder mixing relies solely on fixed time or a single parameter, neglecting the correlation between equipment operating conditions (torque, current) and mixing uniformity. This results in a single threshold setting and poor threshold adaptability. Furthermore, high-shear mixing equipment relies on manual judgment or fixed procedures for high-speed / low-speed switching, failing to capture dynamic changes in the mixing system through multi-parameter collaborative analysis. This makes it difficult to cope with fluctuations caused by batch variations in raw materials (particle size, density) and equipment wear. Additionally, in stratified feeding, for example, with low concentrations and low densities of caffeine and chlorpheniramine maleate, insufficient mixing at low speeds can lead to their floating and agglomeration at high speeds, exacerbating uneven mixing.

[0026] In view of this, according to an embodiment of the present invention, a method for controlling the uniformity of mixing of a mixture is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] This embodiment provides a method for controlling the uniformity of mixture mixing, which can be used in servers, terminals, and mobile terminals such as mobile phones and tablets. Figure 1 This is a flowchart of a method for controlling the uniformity of mixing according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Based on the historical qualified monitoring data of the target mixture, determine the mixing speed switching conditions and mixing termination conditions of the target mixture.

[0028] In this embodiment, the target mixture is taken as an example of the drug components required to prepare cold medicine granules. During the preparation of cold medicine granules, the mixture is added to the mixing equipment in the order of "50% acetaminophen - full amount of caffeine plus chlorpheniramine maleate - remaining 50% acetaminophen" to ensure that the low content components (caffeine, chlorpheniramine maleate) are initially coated by the main drug (acetaminophen).

[0029] Historical qualified monitoring data consists of monitoring data collected from multiple qualified batches of the target mixture during the drug mixing process. The monitoring data for each batch includes MBSD (Moving Block Standard Deviation) values, torque, current timing data, etc., for the entire process from "low speed to high speed to endpoint".

[0030] The mixing speed can be switched when the mixing uniformity and equipment parameters reach the corresponding preset threshold; similarly, the mixing can be stopped when the mixing uniformity and equipment parameters reach the corresponding preset threshold.

[0031] In this embodiment, the mixing speed switching conditions and mixing termination conditions are preferably determined based on the standard deviation value and the deviation statistic. The standard deviation value is determined using a moving window model based on near-infrared spectroscopy; the deviation statistic is determined using a principal component analysis model based on the standard deviation value and mixing equipment parameters. The standard deviation value refers to the MBSD (Moving Block Standard Deviation) value, which is crucial for calculating the standard deviation of data blocks by sliding along a "window," helping to capture the degree of data variation within a local range. The deviation statistic refers to Hotelling's T-squared statistic (also known as T...). 2 Statistic), T 2 Statistics can be used to measure the deviation of a sample from its mean, effectively capturing the correlation between variables and enabling more complex analyses.

[0032] Step S102: Obtain the current monitoring parameters of the target mixture. These parameters include the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment. The mixing equipment parameters include the stirring shaft torque and the motor current. The stirring shaft torque reflects material resistance, while the motor current reflects energy consumption and load.

[0033] The target mixture in this step is the mixture currently being stirred by the equipment, and its monitoring parameters are obtained in real time. The near-infrared spectrum can be obtained by a near-infrared spectrometer installed on the top cover of the mixing equipment (at 1 / 3 of its height from the bottom); the stirring shaft torque can be obtained by a torque sensor integrated into the stirring shaft; the motor current can be obtained by a current sensor connected in series in the motor power supply circuit; the sampling frequency is 1 Hz for all parameters. The preferred wavelength for the near-infrared spectrum is 900 nm-1700 nm.

[0034] Step S103: Determine preset judgment parameters based on the current monitoring parameters.

[0035] In this embodiment, the preset judgment parameters are preferably the standard deviation value and the deviation statistics, or the mixing uniformity and equipment parameters can be used as preset judgment parameters.

[0036] Step S104: When the preset judgment parameters meet the mixing speed switching conditions, control the mixing equipment to switch the stirring speed; when the preset judgment parameters meet the mixing end conditions, control the mixing equipment to stop stirring.

[0037] For example, when the preset judgment parameters meet the first preset threshold range, the mixing speed of the mixing device is controlled to switch from low speed to high speed; when the preset judgment parameters meet the second preset threshold range, the mixing device is controlled to stop mixing. (Mixing device reference) Figure 2 As shown, the material is the mixture in this embodiment, and the paddle is used to stir the mixture.

[0038] In this embodiment, the correlation between equipment operating status and mixing uniformity is fully considered. Combined with process switching conditions determined based on historical qualified monitoring data, and real-time monitoring of near-infrared spectroscopy and equipment parameters, the stirring speed can be precisely adjusted and the timing of the mixing process's termination can be controlled. This data-driven control strategy avoids over- or under-stirring, significantly improving the uniformity of the mixture while reducing energy consumption and production time, and increasing production efficiency and consistency of mixing uniformity across different batches.

[0039] This embodiment provides a method for controlling the uniformity of mixture mixing, which can be used in servers, terminals, and mobile terminals such as mobile phones and tablets. The method includes the following steps: Step S201: Obtain the original historical qualified monitoring data of the target mixture. The historical qualified monitoring data includes the full process monitoring data of different qualified batches of the target mixture, from the start of mixing to the preset low-speed mode, then to the preset high-speed mode, and finally to the end of mixing.

[0040] In this embodiment, the target mixture is still the drug components required for preparing cold medicine granules. During the preparation of cold medicine granules, the components are added to the mixing equipment in the following order: "50% acetaminophen - full amount of caffeine plus chlorpheniramine maleate - remaining 50% acetaminophen" to ensure that the low content components (caffeine, chlorpheniramine maleate) are initially coated by the main drug (acetaminophen).

[0041] Historical qualified monitoring data consists of raw monitoring data collected from multiple qualified batches of the target mixture during the drug mixing process. Each batch's raw monitoring data includes the maximum mean squared deviation (MBSD) value for the entire process from low speed to high speed to endpoint, as well as stirring shaft torque and motor current timing data. The MBSD value is calculated using an average moving window model (a sliding window-based model) based on the near-infrared spectrum from the historical qualified monitoring data.

[0042] In this embodiment, taking at least 50 production batches with qualified mixing uniformity (offline component RSD ≤ 2.0%) as an example, multi-source data are collected for each batch throughout the entire process of "preset low-speed mode - preset high-speed mode - mixing end", with a sampling frequency of 1 Hz. Each batch contains ≥300 data sets, and the data dimensions include: MBSD value (denoted as X1), stirring shaft torque (denoted as X2, unit: N). m), motor current (denoted as X3, unit: A). In this embodiment, the preset low-speed mode corresponds to a low-speed stirring frequency of 30 Hz, which is used to prevent caffeine and chlorpheniramine maleate from floating due to their low density; the preset high-speed mode corresponds to a high-speed stirring frequency of 50 Hz, which is used to achieve deep mixing of materials.

[0043] Step S202 involves preprocessing the original historical qualified monitoring data; specifically, this includes removing outliers from the original historical qualified monitoring data; standardizing the historical qualified monitoring data after removing outliers; and aligning the standardized historical qualified monitoring data by time to obtain the historical qualified monitoring data.

[0044] Outlier removal can be achieved using the 3σ criterion, by calculating the mean μ for each of the univariate X1, X2, and X3. i With standard deviation σ i (i=1,2,3), remove those that satisfy |x-μ i |>3σ i The dataset is processed to remove outliers; the dataset after removing outliers is standardized to eliminate differences in units; and then, based on the device runtime sequence, the three types of parameters are synchronized to a unified time axis.

[0045] Step S203: Based on the historical qualified monitoring data of the target mixture, determine the mixing speed switching conditions and mixing termination conditions of the target mixture.

[0046] Specifically, step S203 includes: Step S2031: Obtain historical qualified monitoring data of the target mixture.

[0047] Step S2032: Based on historical qualified monitoring data, perform principal component analysis (PCA) to determine the target principal components.

[0048] Specifically, this step includes the following dimensions: MBSD value (denoted as X1), and stirring shaft torque (denoted as X2, unit: N). Taking the motor current (denoted as X3, unit: A) as an example, m) is used.

[0049] Based on historical qualified monitoring data, a standardized data matrix Z is constructed; the dimension of the standardized data matrix Z is m×n (still with m as the number of samples and n=3 as the number of variables).

[0050] Calculate the covariance matrix C based on the standardized data matrix Z; that is, calculate the covariance matrix C based on the standardized data matrix Z according to the formula. Calculate the 3×3 covariance matrix.

[0051] Based on the covariance matrix C, solve for the eigenvalues ​​and eigenvectors; perform eigenvalue decomposition on the covariance matrix C to obtain three eigenvalues ​​λ1≥λ2≥λ3 and the corresponding eigenvectors p1, p2, p3 (unit orthogonal vectors).

[0052] Calculate the variance contribution rate of each eigenvalue. : Select the top k principal components with a cumulative variance contribution rate ≥ 85% (usually k=2, the top 2 principal components of the three dependent variables can cover most of the information), denoted as PC1 and PC2.

[0053] Step S2033: Determine the target principal component score for each qualified batch of the target mixture in the historical qualified monitoring data.

[0054] For each qualified batch of the target mixture, i.e., the standardized sample Z j (1×3 vector), calculate the score t of the first k target principal components. jk :t jk =Z jpk (j=1~m, k=1~2).

[0055] Step S2034: Based on the principal component scores, determine the initial deviation statistics of the target mixture for each qualified batch during the mixing speed switching stage and the mixing end stage.

[0056] In this embodiment, initial deviation statistics are preferentially calculated only during the critical stages, namely the mixing speed switching stage and the mixing end stage. This can be done using the formula... Calculate the initial bias statistic for each standardized sample, i.e., Hotelling T. 2 Statistic, abbreviated as T 2 The value of T 2 The value represents the overall fluctuation state of a multivariable system.

[0057] Step S2035: Based on the initial deviation statistics, determine the first deviation statistics threshold range and the second deviation statistics threshold range for the target mixture. The minimum value of the first deviation statistics threshold range is less than the maximum value of the second deviation statistics threshold range.

[0058] Specifically, the mean and standard deviation of the initial deviation statistic for each qualified batch of target mixture during the mixing speed switching phase can be calculated, and the judgment threshold can be determined based on the mean and standard deviation of the initial deviation statistic during the mixing speed switching phase; the mean and standard deviation of the initial deviation statistic for each qualified batch of target mixture during the mixing end phase can also be calculated, and the judgment threshold can be determined based on the mean and standard deviation of the initial deviation statistic during the mixing end phase.

[0059] Step S2036: Based on the MBSD values ​​in the historical qualified monitoring data, determine the first standard deviation threshold range and the second standard deviation threshold range for the target mixture. The minimum value of the first standard deviation threshold range is less than the maximum value of the second standard deviation threshold range.

[0060] In this embodiment, when mixing the required drug components for cold medicine granules, the first standard deviation threshold range is determined to be: (1.5 × 10⁻⁶). -5 1.9×10 -5 The threshold range for the first deviation statistic is (μ1+0.5σ1, μ1+1.5σ1); ensuring that the light components are sufficiently dispersed and do not float significantly.

[0061] The second standard deviation threshold range is: (0, 1.5 × 10⁻⁶) -5 The threshold range for the second deviation statistic is [0, μ1 + 0.5σ1]; ensuring stable uniformity. See the diagram for a schematic of the standard deviation. Figure 3 As shown.

[0062] Wherein, μ1 and σ1 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing speed switching stage, respectively; μ2 and σ2 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing end stage, respectively.

[0063] Step S204: Obtain the current monitoring parameters of the target mixture. These parameters include the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0064] Step S205: Based on the current monitoring parameters, determine the preset judgment parameters. The preset judgment parameters include the standard deviation value and the deviation statistic.

[0065] Specifically, step S205 includes: Step S2051: Based on near-infrared spectroscopy, the standard deviation value is determined using an average moving window model.

[0066] A suitable sliding window size can be selected as needed. Then, by calculating the average value of the near-infrared spectral data within the window at each time step, and further calculating the standard deviation of the data within that window, short-term fluctuations in the spectral data are smoothed, and changes in long-term trends are identified. This standard deviation value provides a measure of data volatility, effectively monitoring the stability of the spectral data, and promptly detecting anomalies or deviations, thereby supporting quality control and optimization of the production process.

[0067] Step S2052: Based on the standard deviation value and the parameters of the mixed equipment, a principal component analysis model is used to determine the deviation statistics.

[0068] The equipment parameters (such as agitator shaft torque and motor current) and standard deviation values ​​are standardized to ensure uniformity of measurement for different parameters. Next, PCA is used to reduce the dimensionality of the multidimensional data, extracting the main variability components and constructing a principal component score matrix. Then, the deviation statistic T is calculated. 2 This value helps identify abnormal deviations.

[0069] Step S206: When the preset judgment parameters meet the mixing speed switching conditions, control the mixing equipment to switch the stirring speed; when the preset judgment parameters meet the mixing end conditions, control the mixing equipment to stop stirring.

[0070] Specifically, when the standard deviation value meets the first standard deviation threshold range and the deviation statistic meets the first deviation statistic threshold range, the mixing device is controlled to switch from the preset low-speed mode to the preset high-speed mode. When the standard deviation value meets the second standard deviation threshold range, and the deviation statistic meets the second deviation statistic threshold range, and this condition persists for a preset time, the mixing device is controlled to stop stirring. In this embodiment, while determining whether the standard deviation value meets the second standard deviation threshold range and whether the deviation statistic meets the second deviation statistic threshold range, it is preferable to further determine whether the time for meeting the mixing end condition persists for a preset time, such as 30 seconds, to ensure that the uniformity is stably met.

[0071] Specifically, during the low-speed dispersion stage, low-speed stirring (30 Hz) is initiated to prevent light components from floating by utilizing low shear force. MBSD values, stirring shaft torque, and current are collected in real time, and deviation statistics are calculated and compared with the first deviation statistics threshold range. When the real-time parameters meet the first deviation statistics threshold range, the control system automatically switches the speed to high speed (50 Hz) to enhance the mixing effect. During the high-speed stage, multiple parameters are continuously monitored, and deviation statistics are calculated and compared with the second deviation statistics threshold range. When the second deviation statistics threshold range is met and maintained for 30 seconds, the system determines that mixing is complete and automatically stops stirring, thereby achieving dynamic control of the mixing process.

[0072] In this embodiment, based on data-driven MSPC (Multivariate Statistical Process Control), continuous multi-batch data (process data, near-infrared spectral data, etc.) collected during the production process are reorganized, expanding the three-dimensional data composed of samples, variables, and batches into two-dimensional data. Principal component analysis is used to project the high-dimensional variable data onto a low-dimensional feature space, establishing a multivariate statistical process control MSPC model to obtain the principal component scores and Hotelling's T values ​​for normal batch data. 2 Values ​​are set, and control lines are established. The monitoring data of the new batch is projected onto the established statistical model. The control status of the current batch of products is determined by comparing it with the control lines of the normal batch data. Based on the online detection indicators and the control model, real-time process feedback control strategies (such as switching time points and mixed endpoints) are provided.

[0073] In this embodiment, a multi-parameter online monitoring system is built to collect near-infrared spectra (for calculating MBSD values), stirring shaft torque, and motor current signals during the mixing process, enabling simultaneous acquisition and preprocessing of multi-source data. A statistical model is constructed using historical batch data, and principal component analysis is employed to extract characteristic variables for MBSD values, stirring shaft torque, and motor current. Based on multivariate statistical process analysis, key threshold ranges are determined, enabling dynamic adaptation to batch differences in raw materials and fluctuations in equipment status, thereby improving mixing uniformity and batch consistency.

[0074] In this embodiment, by integrating quality and equipment parameters through multivariate statistical analysis, the threshold setting is more in line with the actual state of the mixing system, effectively overcoming the limitations of a single parameter. It can dynamically adapt to batch differences in raw materials and fluctuations in equipment status, achieving a mixing uniformity RSD ≤ 2.0% and improving batch consistency by 20%. It effectively realizes a closed loop of "monitoring-analysis-decision-control" without the need for manual intervention, and significantly improves production efficiency.

[0075] In this embodiment, multivariate statistical process analysis (MSPC) can identify process anomalies and critical nodes by fusing multi-source parameters (such as quality indicators and equipment parameters), and combine the MBSD value of near-infrared spectroscopy to quantify uniformity, providing a new path for the precise control of the mixing process.

[0076] The following is a specific example: The near-infrared spectrometer uses a MicroNIR Pro spectrometer (900~1700 nm) with a diffuse reflection extended probe; The sensors used are a torque sensor (range 0~50 N·m, accuracy ±0.5%) and a current sensor (range 0~10A, accuracy ±0.2%). The mixing equipment uses a GHL-600 high-shear mixer (with automatic control support); The control system uses a PLC and an industrial computer, integrating data acquisition and control algorithms.

[0077] When determining the conditions for switching and ending the mixing speed, historical data statistics were first performed. In 50 batches of data, the statistical values ​​of the deviation during the mixing speed switching stage were μ1=2.8 and σ1=0.6; the statistical values ​​of the deviation during the mixing end stage were μ2=1.2 and σ2=0.3. Hybrid speed switching condition: 1.2 + 0.5 × 0.3 = 1.35 < T 2 ≤2.8 + 1.5 × 0.6 = 3.7, and 1.5 × 10 -5 <MBSD≤1.9×10 -5 ; Mixing termination condition: 0 < T 2 ≤1.2+0.5×0.3=1.35, and 0<MBSD≤1.5×10 -5 It lasts for 30 seconds.

[0078] Production control process: Feeding: 50% acetaminophen (93.96 kg) - caffeine (3.758 kg) + chlorpheniramine maleate (3.758 kg) - remaining 50% acetaminophen (93.96 kg); Low-speed stage: stirring at 30 Hz, real-time monitoring showed that MBSD increased from 3.8 × 10⁻⁶. -4Up to 1.85×10 -5 The stirring shaft torque increased from 15 N·m to 18 N·m, and the current increased from 4.2 A to 4.5 A. 2 =3.6 (≤3.7), triggering high-speed switching; High-speed stage: stirring at 50 Hz, after 120 s, the MBSD was measured to be 1.35 × 10⁻⁶. -5 The stirring shaft torque is 28 N·m, and the current is 6.8 A. 2 =1.2 (≤1.35), automatically shut down after 30 seconds; Verification: HPLC analysis of samples showed that the RSD of acetaminophen was 1.5%, the RSD of caffeine was 1.8%, and the RSD of chlorpheniramine maleate was 2.0%, all of which met the requirements.

[0079] This embodiment discloses an intelligent control method for the premixing uniformity of cold medicine granules based on multivariate statistical process analysis. This method collects MBSD values, torque, and current signals during the mixing process in real time, uses multivariate statistical process analysis to determine key thresholds for high-speed / low-speed switching and the mixing endpoint, and constructs a closed-loop feedback control system to achieve dynamic regulation of the high-shear mixing equipment. This solves the problem that traditional fixed processes cannot adapt to fluctuations in raw materials and equipment, significantly improving batch consistency and production efficiency of mixing uniformity, and providing a data-driven intelligent control solution for the premixing process of cold medicine granules.

[0080] This embodiment also provides a mixture mixing uniformity control system, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0081] This embodiment provides a mixture mixing uniformity control system, such as... Figure 4 As shown, it includes: The module is designed to determine the mixing rate switching conditions and mixing termination conditions of the target mixture based on historical qualified monitoring data of the target mixture. The acquisition module is used to acquire the current monitoring parameters of the target mixture, including the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment. The determination module is used to determine preset judgment parameters based on the current monitoring parameters; the preset judgment parameters include the standard deviation value and the deviation statistics; The control module is used to control the mixing equipment to switch the stirring speed when the preset judgment parameters meet the mixing speed switching conditions; and to control the mixing equipment to stop stirring when the preset judgment parameters meet the mixing end conditions.

[0082] In one alternative implementation, the determining module is specifically used for: Based on near-infrared spectroscopy, the standard deviation value was determined using an average moving window model. Based on the standard deviation value and the parameters of the mixed equipment, a principal component analysis model was used to determine the deviation statistics.

[0083] In one alternative implementation, the control module is specifically used for: When the standard deviation value meets the first standard deviation threshold range and the deviation statistic meets the first deviation statistic threshold range, the mixing device is controlled to switch from the preset low speed mode to the preset high speed mode. When the standard deviation value meets the second standard deviation threshold range, and the deviation statistic meets the second deviation statistic threshold range, and this continues for a preset time, the mixing device is controlled to stop stirring. Wherein, the minimum value of the first standard deviation threshold range is less than the maximum value of the second standard deviation threshold range; the minimum value of the first deviation statistic threshold range is less than the maximum value of the second deviation statistic threshold range.

[0084] In one alternative implementation, the building module is specifically used for: Acquire historical qualified monitoring data of the target mixture; historical qualified monitoring data includes the full process monitoring data of different qualified batches of the target mixture, from the start of mixing to the preset low-speed mode, then to the preset high-speed mode, until the end of mixing; Based on historical qualified monitoring data, principal component analysis was performed to determine the target principal components; Determine the target principal component score for each qualified batch of the target mixture in the historical qualified monitoring data; Based on the principal component scores, the initial deviation statistics of the target mixture for each qualified batch are determined during the mixing speed switching stage and the mixing end stage. Based on the initial deviation statistics, the threshold ranges for the first and second deviation statistics of the target mixture are determined.

[0085] In one optional implementation, the first standard deviation threshold range is: (1.5 × 10⁻⁶) -5 1.9×10 -5 The threshold range for the first deviation statistic is: (μ1+0.5σ1, μ1+1.5σ1). The second standard deviation threshold range is: (0, 1.5 × 10⁻⁶) -5The threshold range for the second deviation statistic is [0, μ1 + 0.5σ1]. Wherein, μ1 and σ1 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing speed switching stage, respectively; μ2 and σ2 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing end stage, respectively.

[0086] In one optional implementation, the system further includes a preprocessing module, specifically used for: Obtain the original historical qualified monitoring data of the target mixture; Outlier removal was performed on the original historical qualified monitoring data; Standardize the historical qualified monitoring data after removing outliers; The standardized historical qualified monitoring data is time-aligned to obtain the historical qualified monitoring data.

[0087] The mixture mixing uniformity control system provided in this embodiment of the invention can execute the mixture mixing uniformity control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0088] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0089] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0090] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0091] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the mixture mixing uniformity control method of the embodiments of the present invention.

[0092] Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0093] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the mixture mixing uniformity control method shown in the above embodiments is implemented.

[0094] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0095] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling the uniformity of mixing in a mixture, characterized in that, The method includes: Based on historical qualified monitoring data of the target mixture, determine the mixing speed switching conditions and mixing termination conditions of the target mixture; Obtain the current monitoring parameters of the target mixture, including the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment; Based on the current monitoring parameters, determine the preset judgment parameters; When the preset judgment parameters meet the mixing speed switching condition, the mixing device is controlled to switch the stirring speed; when the preset judgment parameters meet the mixing end condition, the mixing device is controlled to stop stirring.

2. The method according to claim 1, characterized in that, The preset judgment parameters include standard deviation values ​​and deviation statistics; determining the preset judgment parameters based on the current monitoring parameters includes: Based on the near-infrared spectrum, the standard deviation value was determined using an average moving window model; Based on the standard deviation value and the parameters of the mixing equipment, the deviation statistic is determined using a principal component analysis model.

3. The method according to claim 2, characterized in that, The step of controlling the mixing device to switch stirring speed when the preset judgment parameter meets the mixing speed switching condition, and controlling the mixing device to stop stirring when the preset judgment parameter meets the mixing end condition, includes: When the standard deviation value meets the first standard deviation threshold range and the deviation statistic meets the first deviation statistic threshold range, the mixing device is controlled to switch from a preset low-speed mode to a preset high-speed mode. When the standard deviation value meets the second standard deviation threshold range, and the deviation statistic meets the second deviation statistic threshold range, and this continues for a preset time, the mixing device is controlled to stop stirring. Wherein, the minimum value of the first standard deviation threshold range is less than the maximum value of the second standard deviation threshold range; and the minimum value of the first deviation statistic threshold range is less than the maximum value of the second deviation statistic threshold range.

4. The method according to claim 3, characterized in that, The determination of the mixing rate switching conditions and mixing termination conditions for the target mixture based on historical qualified monitoring data of the target mixture includes: Acquire the historical qualified monitoring data of the target mixture; the historical qualified monitoring data includes the full process monitoring data of different qualified batches of the target mixture, from the start of mixing to the preset low-speed mode, then to the preset high-speed mode, until the end of mixing; Based on the aforementioned historical qualified monitoring data, principal component analysis was performed to determine the target principal components; Determine the target principal component score for each qualified batch of the target mixture in the historical qualified monitoring data; Based on the principal component scores, the initial deviation statistics of the target mixture for each qualified batch are determined during the mixing speed switching stage and the mixing end stage. Based on the initial deviation statistics, the threshold range of the first deviation statistics and the threshold range of the second deviation statistics for the target mixture are determined.

5. The method according to claim 4, characterized in that, The first standard deviation threshold range is: (1.5 × 10⁻⁶) -5 1.9×10 -5 The threshold range for the first deviation statistic is (μ1+0.5σ1, μ1+1.5σ1). The second standard deviation threshold range is: (0, 1.5 × 10⁻⁶) -5 The threshold range for the second deviation statistic is [0, μ1 + 0.5σ1]. Wherein, μ1 and σ1 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing speed switching stage, respectively; μ2 and σ2 are the mean and standard deviation of the initial deviation statistics of the target mixture in each qualified batch during the mixing end stage, respectively.

6. The method according to claim 4, characterized in that, Before obtaining the historical qualified monitoring data of the target mixture, the following steps are included: Obtain the original historical qualified monitoring data of the target mixture; Outlier removal is performed on the original historical qualified monitoring data; The historical qualified monitoring data, after removing outliers, are standardized. The historical qualified monitoring data is obtained by time alignment of the standardized historical qualified monitoring data.

7. A mixture mixing uniformity control system, characterized in that, The system includes: A construction module is used to determine the mixing speed switching conditions and mixing termination conditions of the target mixture based on historical qualified monitoring data of the target mixture; The acquisition module is used to acquire the current monitoring parameters of the target mixture, including the near-infrared spectrum of the target mixture during the mixing process and the parameters of the mixing equipment; The determination module is used to determine preset judgment parameters based on the current monitoring parameters; The control module is used to control the mixing device to switch the stirring speed when the preset judgment parameters meet the mixing speed switching condition; and to control the mixing device to stop stirring when the preset judgment parameters meet the mixing end condition.

8. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the mixture mixing uniformity control method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the mixture mixing uniformity control method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the mixture mixing uniformity control method according to any one of claims 1 to 6.

Images