Drug pulverization method and device based on particle size control

Abstract

This invention discloses a drug pulverization method and apparatus based on particle size control, relating to the field of drug pulverization technology. The method includes: acquiring basic pulverization information of the target drug; connecting the target pulverization equipment and collecting first pulverization control parameters and first environmental control information; generating first predicted particle size characteristics and first particle size dispersion characteristics; optimizing pulverization parameters when the first predicted particle size characteristics do not meet the desired particle size constraint range and / or the first particle size dispersion characteristics do not meet the desired particle size dispersion characteristics; and initializing the parameters of the target pulverization equipment according to second pulverization control parameters and second environmental control information. This invention solves the technical problem of existing drug pulverization methods relying on manual experience adjustments, leading to insufficient particle size control accuracy, low production efficiency, and unstable product quality, thus failing to achieve the expected particle size standards and particle size dispersion characteristics. It achieves the technical effect of improving particle size control accuracy, production efficiency, and product quality stability.

Description

Technical Field

[0001] This application relates to the field of pharmaceutical pulverization technology, specifically to a pharmaceutical pulverization method and apparatus based on particle size control. Background Technology

[0002] In modern pharmaceutical manufacturing, particle size control is crucial for ensuring drug efficacy, bioavailability, and stability. Different drugs, due to their physicochemical properties, solubility, and biomembrane permeability, have strict requirements on the particle size and particle size distribution of the final product. Excessively large particle size can affect the drug's dissolution rate and bioabsorption efficiency, while excessively small particle size may increase the drug's surface area, accelerating its degradation or reaction with the surrounding environment, which is also detrimental to the drug's stability and efficacy. Ensuring precise control over the particle size of pulverized drugs has become an important direction for pharmaceutical technology development. However, traditional drug pulverization methods often rely on experience-based adjustments and multiple trials, which are not only inefficient but also make it difficult to guarantee that each production will achieve the expected particle size standard and particle size dispersion characteristics, resulting in a wide range of particle size distribution in the final product, affecting drug efficacy and stability.

[0003] Therefore, current pharmaceutical pulverization technologies suffer from technical problems due to reliance on manual experience for adjustments, which leads to insufficient precision in controlling drug particle size, low production efficiency, and unstable product quality, making it impossible to achieve the expected particle size standards and particle size dispersion characteristics. Summary of the Invention

[0004] This application provides a drug pulverization method and apparatus based on particle size control, which solves the technical problems of existing drug pulverization methods that rely on manual experience for adjustment, resulting in insufficient particle size control accuracy, low production efficiency, and unstable product quality, making it impossible to achieve the expected particle size standard and particle size dispersion characteristics. It achieves the technical effect of improving particle size control accuracy, production efficiency, and product quality stability.

[0005] This application provides a drug pulverization method based on particle size control. The method includes: acquiring basic pulverization information of a target drug, wherein the basic pulverization information includes drug characteristic information, a desired particle size constraint range, and a desired particle size dispersion characteristic; connecting a target pulverization device and collecting first pulverization control parameters and first environmental control information; based on the drug characteristic information, performing pulverization fitting prediction on the first pulverization control parameters and the first environmental control information to generate a first predicted particle size characteristic and a first particle size dispersion characteristic; when the first predicted particle size characteristic does not satisfy the desired particle size constraint range and / or the first particle size dispersion characteristic does not satisfy the desired particle size dispersion characteristic, activating a cyclic optimization constraint module to optimize the pulverization parameters and generate second pulverization control parameters and second environmental control information; and initializing the target pulverization device according to the second pulverization control parameters and the second environmental control information.

[0006] In a possible implementation, when the first predicted particle size feature does not satisfy the desired particle size constraint interval and / or the first particle size dispersion feature does not satisfy the desired particle size dispersion feature, the cyclic optimization constraint module is activated to optimize the crushing parameters, generate second crushing control parameters and second environmental control information, and further perform the following processing: Activate the cyclic optimization constraint module and perform the following steps: Perform multiple random adjustments on the first crushing control parameters and the first environmental control information to generate multiple sets of optimized crushing parameters and multiple sets of optimized environmental parameters, and the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters correspond one-to-one; Perform crushing fitting on the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion features; Calculate multiple first distances between the multiple optimized particle size constraint intervals and the desired particle size constraint interval, and multiple second distances between the multiple optimized particle size dispersion features and the desired particle size dispersion feature; Based on the multiple first distances and the multiple second distances, perform distance minimization iterative optimization to generate the second crushing control parameters and the second environmental control information.

[0007] In a possible implementation, based on the plurality of first distances and the plurality of second distances, with the desired particle size constraint interval as the priority constraint, distance minimization iterative optimization is performed to generate optimal crushing parameters and optimal environmental parameters, as well as the corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics. The following processes are then performed: the plurality of first distances are sorted to generate a first sorting result; the plurality of second distances are sorted to generate a second sorting result; the differences between the solutions of corresponding sorted nodes in the first sorting result and the second sorting result are compared, and solutions with different positional correspondences are deleted to generate a fused optimized sorting result; based on the fused optimized sorting result, multiple sets of optimization spaces are established with solutions at adjacent positions; parameters are randomly generated in the multiple sets of optimization spaces, and it is determined whether a solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics is included. If so, the second crushing control parameters and the second environmental control information are output; if not, iterative optimization is performed.

[0008] In a possible implementation, the target crushing equipment is initialized with parameters according to the second crushing control parameters and the second environmental control information, and the following processes are performed: If the number of iterations reaches a preset number and there is no solution that satisfies the desired particle size constraint range and the desired particle size dispersion feature, the optimal particle size constraint range is taken as the priority constraint, and a candidate solution space is extracted based on the iteration optimization results; the solution with the smallest distance from the desired particle size dispersion feature is selected from the candidate solution space as the optimal crushing control parameters and the optimal environmental control information, and the corresponding optimal particle size dispersion feature is obtained; the optimal particle size dispersion feature is compared with the desired particle size dispersion feature to select the cyclic crushing particle size, and the screening control parameters of the crushing particle screening mechanism are configured with the cyclic crushing particle size; the target crushing equipment is initialized with parameters according to the screening control parameters, the optimal crushing control parameters, and the optimal environmental control information.

[0009] In a possible implementation, based on the drug characteristic information, a crushing fitting prediction is performed on the first crushing control parameter and the first environmental control information to generate a first predicted particle size feature and a first particle size dispersion feature. The following processing is also performed: the drug characteristic information includes drug hardness and drug viscosity; multiple historical crushing records are collected, constrained by the drug hardness, drug viscosity, the first crushing control parameter, and the first environmental control information; after outlier removal from the multiple historical crushing records, the particle size distribution interval is statistically analyzed to generate the first predicted particle size feature; the distribution ratio of the same particle size is statistically analyzed from the multiple historical crushing records after outlier removal to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes multi-level particle size dispersion features.

[0010] In a possible implementation, the following steps are performed: connecting to the target crushing equipment, collecting the first crushing control parameter and the first environmental control information, and then: connecting to the target crushing equipment and obtaining a set of historical crushing record logs; clustering the same crushing control parameters based on the set of historical crushing record logs, and statistically obtaining multiple frequent activation probabilities of multiple historical control parameter combinations based on the clustering results, wherein any set of historical control parameter combinations includes historical crushing control parameters and historical environmental control information; and selecting the set of historical control parameter combinations with the highest probability based on the multiple frequent activation probabilities to generate the first crushing control parameter and the first environmental control information.

[0011] In a possible implementation, the target crushing equipment is initialized with parameters according to the second crushing control parameters and the second environmental control information, and the following processing is also performed: when the first predicted particle size feature meets the desired particle size constraint range and the first particle size dispersion feature meets the desired particle size dispersion feature, the target crushing equipment is initialized with parameters according to the first crushing control parameters and the first environmental control information.

[0012] This application also provides a drug pulverizing device based on particle size control, comprising: a pulverizing basic information acquisition module for acquiring pulverizing basic information of a target drug, wherein the pulverizing basic information includes drug characteristic information, a desired particle size constraint range, and a desired particle size dispersion characteristic; a control parameter information acquisition module for connecting to the target pulverizing equipment and acquiring first pulverizing control parameters and first environmental control information; a pulverizing fitting prediction module for performing pulverizing fitting prediction based on the drug characteristic information, targeting the first pulverizing control parameters and the first environmental control information, to generate a first predicted particle size characteristic and a first particle size dispersion characteristic; a pulverizing parameter optimization module for activating a cyclic optimization constraint module to optimize pulverizing parameters and generate second pulverizing control parameters and second environmental control information when the first predicted particle size characteristic does not meet the desired particle size constraint range and / or the first particle size dispersion characteristic does not meet the desired particle size dispersion characteristic; and a pulverizing equipment parameter initialization module for initializing the parameters of the target pulverizing equipment according to the second pulverizing control parameters and the second environmental control information.

[0013] The proposed method and apparatus for drug pulverization based on particle size control aims to obtain basic information on the pulverization of a target drug; connect the target pulverization equipment and collect first pulverization control parameters and first environmental control information; generate first predicted particle size characteristics and first particle size dispersion characteristics; optimize pulverization parameters when the first predicted particle size characteristics do not meet the desired particle size constraint range and / or the first particle size dispersion characteristics do not meet the desired particle size dispersion characteristics; and initialize the parameters of the target pulverization equipment according to second pulverization control parameters and second environmental control information. This method solves the technical problem of existing drug pulverization methods relying on manual experience adjustments, leading to insufficient particle size control accuracy, low production efficiency, and unstable product quality, thus failing to achieve the expected particle size standards and particle size dispersion characteristics. It achieves the technical effect of improving particle size control accuracy, production efficiency, and product quality stability. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the apparatus according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0015] Figure 1 A schematic diagram of a drug pulverization method based on particle size control provided in an embodiment of this application;

[0016] Figure 2 This is a schematic diagram of a drug pulverizing device based on particle size control, provided in an embodiment of this application.

[0017] Explanation of reference numerals in the attached diagram: 10 for acquiring basic crushing information, 20 for acquiring control parameter information, 30 for crushing fitting and prediction, 40 for crushing parameter optimization, and 50 for initializing crushing equipment parameters. Detailed Implementation

[0018] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application.

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or apparatuses. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0021] This application provides a drug pulverization method based on particle size control, such as... Figure 1 As shown, the method includes:

[0022] Step S100: Obtain basic information on the pulverization of the target drug. This basic information includes drug characteristic information, desired particle size constraint range, and desired particle size dispersion characteristics. Obtaining this information can be achieved by carefully reading the drug's instructions, reviewing relevant scientific literature and research papers, conducting in-depth drug property analysis and pulverization experimental data, or directly consulting the drug manufacturer or supplier to obtain best practices and related information on drug pulverization. Specifically, the drug characteristic information refers to the drug's physicochemical properties (such as melting point, boiling point, density, hardness, brittleness, viscosity, hygroscopicity, and solubility, which directly affect the drug's behavior during pulverization; for example, drugs with high hardness may require stronger pulverization force, while drugs with high viscosity may agglomerate during pulverization), crystal structure (the crystal morphology and internal structure of the drug significantly affect its pulverization effect; drugs with different crystal structures may exhibit different brittleness and fracture behaviors during pulverization), and stability (the drug may degrade due to environmental factors such as temperature, humidity, and light during pulverization). (or denaturation); the desired particle size constraint range refers to the range of particle sizes expected to be achieved after drug pulverization. Different drugs and formulations have different requirements for particle size. For example, some oral formulations may require larger particle sizes to improve taste and swallowability, while injectable formulations may require smaller particle sizes to improve drug solubility and bioavailability. When developing a pulverization strategy, the target particle size range must be clearly defined, and the particle size distribution of the final product should fall within this range as much as possible. In addition to particle size, particle size distribution is also an important indicator for evaluating pulverization effect. Particle size distribution describes the proportion of particles of different sizes in the total, reflecting the uniformity of particle size. The desired particle size dispersion characteristics usually include information such as the width, shape, and symmetry of the particle size distribution. When the particle size of the pulverized drug meets the desired particle size constraint range, the proportion of particles of the same size, such as at least 70% of the particles having the same particle size, and the difference between the particle size of the remaining 30% of the particles and the 70% of the particles should not be too large, is to ensure particle uniformity, which is beneficial for subsequent mixing or tableting.

[0023] Step S200: Connect the target crushing equipment and collect the first crushing control parameters and the first environmental control information.

[0024] Furthermore, step S200 also includes step S210, connecting the target crushing device and obtaining a set of historical crushing record logs; step S220, clustering the same crushing control parameters based on the set of historical crushing record logs, and statistically obtaining multiple frequent activation probabilities of multiple historical control parameter combinations based on the clustering results, wherein any set of historical control parameter combinations includes historical crushing control parameters and historical environmental control information; step S230, selecting the set of historical control parameter combinations with the highest probability based on the multiple frequent activation probabilities, and generating the first crushing control parameter and the first environmental control information.

[0025] Preferably, the system connects to the target crushing equipment to obtain a historical crushing record log set. Specifically, this refers to accessing and downloading the historical records of all crushing tasks performed by the equipment over a past period. These records typically contain detailed information about each crushing task, such as crushing time, control parameters used, environmental conditions (e.g., temperature, humidity), and crushing results (e.g., particle size distribution, output). Clustering based on the historical crushing record log set for the same crushing control parameters involves performing cluster analysis on the historical crushing record log set, dividing the dataset into several groups or clusters. Data points within the same cluster have high similarity, while data points between different clusters have low similarity. This clustering result groups records with the same or similar crushing control parameters and environmental control information into one category. This helps identify which combinations of control parameters and environmental conditions are more common or effective in actual production. Based on the clustering results, multiple frequent activation probabilities for various historical control parameter combinations are statistically obtained. The frequent activation probability refers to the frequency with which a specific control parameter combination (including historical crushing control parameters and historical environmental control information) is used or activated in all historical crushing records. This probability reflects the popularity or effectiveness of the combination in actual production. By statistically analyzing the clustering results... The frequency of activation for each cluster can be used to evaluate the performance of different combinations of control parameters and select the optimal combination. Combinations with high frequency of activation may mean that they can consistently produce compliant pulverization results. Historical pulverization control parameters refer to parameters set and adjusted by operators or automatic control systems during the pulverization process, which directly affect the pulverization effect and quality. Common pulverization control parameters include, but are not limited to, pulverizer speed, pulverization time, feed rate, pulverization chamber pressure, and the selection and dosage of grinding media. In addition to pulverization control parameters, the pulverization process is also affected by the external environment. Historical environmental control information refers to environmental condition data recorded during the execution of pulverization tasks, such as temperature, humidity, air pressure, and vibration. These environmental factors may affect pulverization efficiency, product particle size distribution, and powder flowability. Then, based on the frequency of activation, the optimal combination of control parameters is selected, that is, the most frequently used combination of control parameters is selected, which is likely to represent the best pulverization conditions. Finally, based on the selected optimal combination of control parameters, the first pulverization control parameters (such as speed, pressure, time, etc.) and the first environmental control information (such as temperature, humidity, etc.) are generated and used to guide future pulverization tasks in order to achieve better pulverization results and higher production efficiency.

[0026] Step S300: Based on the drug characteristic information, perform a crushing fitting prediction on the first crushing control parameters and the first environmental control information to generate a first predicted particle size characteristic and a first particle size dispersion characteristic. A simulation model of the crushing process is established based on the drug characteristic information, the first crushing control parameters, and the first environmental control information to simulate and predict the crushing process. This model should be able to reflect the stress on the drug particles, the crushing mechanism, and the changing patterns of particle size and particle size distribution during the crushing process. The first crushing control parameters and the first environmental control information are input into the model as input parameters. The model is used for simulation calculation to predict the crushing effect of the drug under given control parameters and environmental conditions. The simulation calculation will consider the physical properties of the drug, the crushing mechanism, and the influence of environmental factors. After the simulation calculation is completed, the prediction results are output. The prediction results should include the first predicted particle size characteristic and the first particle size dispersion characteristic. The particle size characteristic usually refers to statistical indicators such as the average particle size and median particle size; the particle size dispersion characteristic describes the width and shape of the particle size distribution, such as span and uniformity index.

[0027] In one possible implementation, step S300 further includes step S310, where the drug characteristic information includes drug hardness and drug viscosity; step S320, where multiple historical pulverization records are collected, constrained by the drug hardness, the drug viscosity, the first pulverization control parameters, and the first environmental control information; step S330, where outlier removal is performed on the multiple historical pulverization records, and particle size distribution intervals are statistically analyzed to generate the first predicted particle size feature; step S340, where the distribution ratio of the same particle size is statistically analyzed on the multiple historical pulverization records after outlier removal to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes multi-level particle size dispersion features.

[0028] Preferably, the drug characteristic information includes two important physical properties: drug hardness and drug viscosity. Specifically, drug hardness, especially for solid dosage forms (such as tablets and capsules), mainly refers to its compressive strength or radial breaking force. Hardness is a comprehensive indicator of a material's mechanical properties, including elasticity, plasticity, strength, and toughness. For tablets, hardness directly affects their formability during production, the stability of packaging and transportation, and their disintegration and dissolution during use. Tablets with too low hardness are prone to loosening and cracking, affecting subsequent coating, packaging, and transportation processes, and may even lead to damage during storage or transportation. While tablets with too high hardness are beneficial for maintaining their shape stability, they may cause the drug and excipients to adhere tightly together, making the tablet difficult to disintegrate and preventing the drug components from dissolving effectively, thus affecting the therapeutic effect. Hardness is typically assessed by using a hardness tester, such as the YD-1 type, to randomly select samples from a certain number of tablets and measure the force required to break them by applying pressure. Drug viscosity refers to the resistance of fluid drugs (such as solutions, suspensions, emulsions, etc.) to flow, directly affecting the drug's flowability, stability, and efficacy. The viscosity of a drug directly influences its administration method and effectiveness. For example, liquid drugs with moderate viscosity are easier to administer via syringe or infusion tubing and ensure uniform distribution in the body, while drugs with excessively high or low viscosity may lead to difficulty in administration or uneven drug distribution. Viscometers, such as rotational viscometers and capillary viscometers, are typically used to calculate the viscosity value by measuring the flow rate or required shear stress of the fluid drug under specific conditions.

[0029] Preferably, the process uses drug hardness, drug viscosity, first pulverization control parameters (such as rotation speed and time), and first environmental control information (such as temperature and humidity) as constraints. Multiple pulverization records matching or similar to these conditions are collected from a historical database. These records should contain detailed results for each pulverization task, such as particle size distribution and yield. Since historical data may contain outliers (possibly due to equipment malfunction, operational errors, etc.), which can negatively impact subsequent statistical analysis, statistical methods (such as Z-score and IQR) are needed to identify and remove outliers from the collected historical pulverization records to ensure data accuracy and reliability. Based on the particle size distribution of the statistically processed historical pulverization records, the particle size distribution range after pulverization is predicted under given drug characteristics, pulverization control parameters, and environmental control information. Specifically, statistical analysis of the particle size distribution of the historical pulverization records after outlier removal is performed to calculate the particle size distribution. The first predicted particle size feature consists of statistical measures such as mean, median, and standard deviation, as well as the main intervals of particle size distribution (e.g., minimum particle size, maximum particle size, common particle size range, etc.). In addition to predicting the particle size distribution intervals, it is also necessary to understand the degree of dispersion of particle size distribution, that is, the proportion of particles of different sizes in the total. The distribution proportion of the same particle size is statistically analyzed for historical crushing records after removing outliers. First, the particle size range is divided into multiple levels as needed (e.g., each level is 0.1 mm or 1 μm). Then, the quantity or mass proportion of particles of each size in each level is statistically analyzed. Finally, these proportion data are output as the first particle size dispersion feature. The first particle size dispersion feature includes multi-level particle size dispersion features. Particle size dispersion features usually include multi-level particle size dispersion features, that is, particles are classified according to different particle size ranges (e.g., fine particle size, medium particle size, coarse particle size, etc.), and the proportion of particles of each size level in the total is statistically analyzed. This multi-level classification can describe the dispersion of particle size distribution in more detail.

[0030] Step S400: When the first predicted particle size feature does not meet the expected particle size constraint interval and / or the first particle size dispersion feature does not meet the expected particle size dispersion feature, the cyclic optimization constraint module is activated to optimize the crushing parameters and generate the second crushing control parameters and the second environmental control information. If at least one of the first predicted particle size feature (i.e., the particle size distribution predicted based on the current crushing control parameters and environmental control information) and the first particle size dispersion feature (such as the proportion of each level in the multi-level particle size dispersion feature) does not meet the corresponding expected particle size constraint interval or the expected particle size dispersion feature, that is, when the prediction result does not meet the expectation, the cyclic optimization constraint module needs to be activated to adjust the crushing control parameters and environmental control information in order to obtain a better crushing effect. Specifically, the cyclic optimization constraint module will use a certain optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm, gradient descent method, etc.) to search for better crushing control parameters and environmental control based on the current prediction result and the expected target. Information is combined, new parameter combinations are continuously tried, their prediction results are evaluated, and the parameters are adjusted according to the results until a parameter combination that meets the desired conditions is found. The optimization of crushing parameters includes, but is not limited to, optimizing crushing control parameters such as the speed of the crusher, crushing time, feed rate, and crushing chamber pressure, as well as environmental control information such as temperature and humidity, so that the predicted particle size characteristics fall within the desired particle size constraint range and the predicted particle size dispersion characteristics meet the desired particle size dispersion characteristics. After optimization by the cyclic optimization constraint module, a new set of crushing control parameters (i.e., the second crushing control parameters) and environmental control information (i.e., the second environmental control information) will be generated in order to obtain better crushing effect and product quality.

[0031] In one possible implementation, step S400 further includes activating the cyclic optimization constraint module and performing the following steps: Step S410, randomly adjusting the first crushing control parameter and the first environmental control information multiple times to generate multiple sets of optimized crushing parameters and multiple sets of optimized environmental parameters, wherein the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters correspond one-to-one; Step S420, performing crushing fitting on the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion features; Step S430, calculating multiple first distances between the multiple optimized particle size constraint intervals and the desired particle size constraint interval, and multiple second distances between the multiple optimized particle size dispersion features and the desired particle size dispersion features; Step S440, performing distance minimization iterative optimization based on the multiple first distances and the multiple second distances to generate the second crushing control parameter and the second environmental control information.

[0032] Preferably, after activating the cyclic optimization constraint module, a random number generator or a random search strategy (such as the Monte Carlo method) is used to randomly adjust the first crushing control parameters and the first environmental control information, generating multiple sets of different combinations of optimized crushing parameters and optimized environmental parameters. Each set of optimized crushing parameters corresponds one-to-one with the optimized environmental parameters, serving as candidate solutions for subsequent evaluation. Each set of optimized crushing parameters and optimized environmental parameters is input into the simulation model for simulation calculation, outputting the corresponding optimized particle size constraint intervals and optimized particle size dispersion features, i.e., generating multiple optimized particle size constraint intervals and multiple optimized particle size dispersion features. Multiple first distances between the multiple optimized particle size constraint intervals and the desired particle size constraint interval are calculated, i.e., calculating the distance between each optimized particle size constraint interval and the desired particle size constraint interval, such as calculating the interval overlap, the distance of the center point, or the difference of the entire distribution, etc. Multiple second distances between the multiple optimized particle size dispersion features and the desired particle size dispersion features are calculated, i.e., calculating the distance between each optimized particle size constraint interval and the desired particle size constraint interval, i.e., calculating the distance between each optimized particle size constraint interval and the desired particle size constraint interval, such as calculating the interval overlap, the distance of the center point, or the difference of the entire distribution, etc. The distance between the optimized granularity dispersion feature and the desired granularity dispersion feature is calculated, such as comparing the proportion of different particle size levels or the difference in distribution shape. Based on multiple first distances and multiple second distances, the optimal parameter combination that minimizes the distance is found through iterative optimization. Specifically, based on the comprehensive evaluation of the first and second distances (which may be combined through weighted summation, product, or other methods), the best-performing set of optimization parameters in the current iteration is selected as the candidate optimal solution. Centered on this set of candidate optimal solutions, random adjustment or a more refined search strategy (such as gradient descent, crossover mutation in genetic algorithms, etc.) is continued to generate new combinations of optimization parameters. The above steps are repeated for evaluation and selection. The iterative process continues until a certain convergence condition is met (such as the optimal solution changes very little in multiple consecutive iterations, or the preset maximum number of iterations is reached). Finally, the second crushing control parameters and the second environmental control information that satisfy the desired particle size constraint range and granularity dispersion feature are generated.

[0033] In one possible implementation, step S440 further includes step S441, sorting the plurality of first distances to generate a first sorting result; step S442, sorting the plurality of second distances to generate a second sorting result; step S443, comparing the solutions of corresponding sorted nodes in the first sorting result and the second sorting result, deleting solutions with different positional correspondences, and generating a fused optimized sorting result; step S444, based on the fused optimized sorting result, establishing multiple sets of optimization spaces with solutions at adjacent positions; step S445, continuing to randomly generate parameters in the multiple sets of optimization spaces, determining whether they contain solutions that satisfy the desired particle size constraint interval and the desired particle size dispersion characteristics, and if so, outputting the second crushing control parameters and the second environmental control information; step S446, if not, performing cyclic optimization.

[0034] Preferably, based on multiple first distances (representing the difference between the optimized particle size constraint interval and the desired particle size constraint interval) and multiple second distances (representing the difference between the optimized particle size dispersion characteristics and the desired particle size dispersion characteristics), the desired particle size constraint interval is taken as the priority constraint, and distance minimization iterative optimization is performed to find the optimal grinding parameters and environmental parameters. Specifically, since the particle size constraint interval may have a more critical impact on product quality and performance, setting the desired particle size constraint interval as the priority constraint means that in the optimization process, the first distance will be focused on and minimized as much as possible, that is, ensuring that the optimized particle size constraint interval is as close as possible to or completely contained within the desired particle size constraint interval. In each iteration, the first distance and the second distance are calculated based on the current optimization parameters (grinding parameters and environmental parameters). The effectiveness of the current optimization parameters is evaluated based on the first distance (i.e., the difference in particle size constraint interval), and those parameters that cause a larger first distance are adjusted first. The second distance (i.e., the difference in particle size dispersion characteristics) is also considered, but with a smaller weight or priority when adjusting the parameters, to ensure that the particle size dispersion characteristics are improved as much as possible while satisfying the particle size constraint interval. Through multiple iterations, the optimal solution is gradually approached, that is, a set of optimization parameters is found that can satisfy the desired particle size constraint interval and make the particle size dispersion characteristics close to the desired value. Finally, the optimal pulverization parameters and the optimal environmental parameters are obtained. This set of parameters enables the pulverized drug particles to satisfy the desired particle size constraint interval and have good particle size dispersion characteristics. The corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics are calculated based on this set of optimal parameters.

[0035] Preferably, the first distance (i.e., the difference between the optimized particle size constraint interval and the desired particle size constraint interval) corresponding to all optimization parameter combinations is sorted to generate a first sorting result; the second distance (i.e., the difference between the optimized particle size dispersion feature and the desired particle size dispersion feature) corresponding to all optimization parameter combinations is sorted to generate a second sorting result; the solutions of corresponding sorted nodes in the first and second sorting results are compared, and solutions with different positional correspondences are deleted, that is, only solutions with similar or consistent positions in the two sorting results are retained. These solutions achieve a good balance between the two optimization objectives (particle size and particle size dispersion). The filtered solutions are reordered according to a certain method (such as comprehensive distance, priority, etc.) to generate a fused optimization sorting result; based on the fused optimization sorting result, adjacent... The solution at the location is used as the boundary to establish multiple optimization spaces, representing the parameter range that may contain better solutions. Within each optimization space, parameters are randomly generated to explore potential better solutions. For each newly generated parameter combination, it is determined whether it meets the constraints of the desired particle size constraint range and the desired particle size dispersion characteristics. If a solution that meets the constraints is found, it is output as the second crushing control parameter and the second environmental control information. If no solution that meets the constraints is found after the above steps, iterative optimization is performed, such as readjusting the boundary of the optimization space, changing the strategy of randomly generating parameters, or introducing more complex optimization algorithms (such as genetic algorithms, simulated annealing, etc.), and iteratively until a solution that meets the constraints is found or a preset stopping condition is reached.

[0036] In one possible implementation, step S400 further includes step S450, whereby, when the first predicted particle size feature meets the desired particle size constraint range and the first particle size dispersion feature meets the desired particle size dispersion feature, the target pulverizing equipment is initialized with parameters according to the first pulverizing control parameters and the first environmental control information. If the first predicted particle size feature meets the desired particle size constraint range and the first particle size dispersion feature meets the desired particle size dispersion feature, the target pulverizing equipment is set and adjusted accordingly based on the collected first pulverizing control parameters (such as adjusting the pulverizer's rotation speed, feed rate, and discharge particle size setpoint) and the first environmental control information (such as adjusting the working environment's temperature, humidity, and airflow speed) to ensure that the subsequent pulverizing process can operate stably and efficiently, thereby guaranteeing the drug pulverizing effect.

[0037] Step S500: Initialize the parameters of the target crushing equipment according to the second crushing control parameters and the second environmental control information.

[0038] Further, step S500 also includes step S510: if the number of iterations reaches a preset number and there is no solution that satisfies the desired particle size constraint range and the desired particle size dispersion feature, the optimal particle size constraint range is taken as the priority constraint, and a candidate solution space is extracted based on the iteration optimization result; step S520: the solution with the smallest distance to the desired particle size dispersion feature is selected from the candidate solution space as the optimal crushing control parameter and the optimal environmental control information, and the corresponding optimal particle size dispersion feature is obtained; step S530: the optimal particle size dispersion feature is compared with the desired particle size dispersion feature to select the cyclic crushing particle size, and the screening control parameters of the crushing particle screening mechanism are configured with the cyclic crushing particle size; step S540: the target crushing equipment is initialized with the screening control parameters, the optimal crushing control parameters, and the optimal environmental control information.

[0039] Preferably, if the number of iterations for optimization has reached the preset number, but no solution simultaneously satisfying the desired particle size constraint range and the desired particle size dispersion characteristics has been found during the search process, then satisfying the optimal particle size constraint range is chosen as the primary condition. That is, solutions that make the particle size characteristics closer to the desired particle size constraint range are given priority. Then, in the results of the cyclic optimization, all possible candidate solutions are extracted to obtain the optimal solution space (including all tried combinations of control parameters). Then, among these candidate solutions, the solution with the smallest distance from the desired particle size dispersion characteristics is selected. This solution will be regarded as the combination of the optimal crushing control parameters and the optimal environmental control information, and the corresponding optimal particle size dispersion characteristics are obtained. The optimal particle size dispersion characteristics corresponding to the selected optimal solution are compared with the desired particle size dispersion characteristics to evaluate the difference between the two. Based on the comparison results, cyclic crushing is performed. In particle size selection, specifically, through multiple or continuous crushing operations, the crushing parameters (such as particle size setting value, rotation speed, etc.) are adjusted each time. Then, the crushed particles are screened using a particle screening mechanism to gradually approach the desired particle size distribution characteristics. The configuration of screening control parameters refers to setting its working parameters according to the specific requirements of the screening mechanism and the selected larger particle size range. Finally, the target crushing equipment is comprehensively initialized with the selected optimal screening control parameters, optimal crushing control parameters, and optimal environmental control information. This includes setting the crusher's rotation speed, feed rate, etc., to optimal values, adjusting the temperature and humidity of the working environment to the optimal range, and configuring the screening parameters of the screening mechanism to match the selected particle size range. This allows the screened large particles to be returned to the crushing chamber for further crushing, so as to achieve optimized crushing effect and particle size distribution in actual operation.

[0040] In the above text, refer to Figure 1 A pharmaceutical pulverization method based on particle size control according to embodiments of the present invention has been described in detail. Next, reference will be made to... Figure 2A pharmaceutical pulverizing apparatus based on particle size control according to an embodiment of the present invention is described.

[0041] The pharmaceutical pulverizing device based on particle size control according to embodiments of the present invention addresses the technical problems of existing pharmaceutical pulverizing methods that rely on manual experience for adjustment, leading to insufficient particle size control accuracy, low production efficiency, and unstable product quality, thus failing to achieve the expected particle size standards and particle size dispersion characteristics. The device achieves the technical effect of improving particle size control accuracy, production efficiency, and product quality stability. The pharmaceutical pulverizing device based on particle size control includes: a pulverizing basic information acquisition module 10, a control parameter information acquisition module 20, a pulverizing fitting and prediction module 30, a pulverizing parameter optimization module 40, and a pulverizing equipment parameter initialization module 50.

[0042] The system includes a basic information acquisition module 10 for acquiring basic information about the target drug's pulverization process, including drug characteristic information, a desired particle size constraint range, and a desired particle size dispersion characteristic; a control parameter information acquisition module 20 for connecting to the target pulverization equipment and acquiring first pulverization control parameters and first environmental control information; a pulverization fitting and prediction module 30 for performing pulverization fitting and prediction based on the drug characteristic information, targeting the first pulverization control parameters and the first environmental control information, to generate first predicted particle size characteristics and first particle size dispersion characteristics; a pulverization parameter optimization module 40 for activating a cyclic optimization constraint module to optimize pulverization parameters and generate second pulverization control parameters and second environmental control information when the first predicted particle size characteristics do not meet the desired particle size constraint range and / or the first particle size dispersion characteristics do not meet the desired particle size dispersion characteristics; and a pulverization equipment parameter initialization module 50 for initializing the target pulverization equipment parameters according to the second pulverization control parameters and the second environmental control information.

[0043] The specific configuration of the crushing parameter optimization module 40 will be described in detail below. The crushing parameter optimization module 40 may further include: activating a cyclic optimization constraint module and performing the following steps: randomly adjusting the first crushing control parameter and the first environmental control information multiple times to generate multiple sets of optimized crushing parameters and multiple sets of optimized environmental parameters, wherein the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters correspond one-to-one; performing crushing fitting on the multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion features; calculating multiple first distances between the multiple optimized particle size constraint intervals and the desired particle size constraint interval, and multiple second distances between the multiple optimized particle size dispersion features and the desired particle size dispersion features; and performing distance minimization iterative optimization based on the multiple first distances and the multiple second distances to generate the second crushing control parameter and the second environmental control information.

[0044] The specific configuration of the crushing parameter optimization module 40 will be described in detail below. The crushing parameter optimization module 40, based on the plurality of first distances and the plurality of second distances, prioritizes satisfying the desired particle size constraint interval, performs distance minimization iterative optimization, and generates optimal crushing parameters and optimal environmental parameters, as well as the corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics. It further includes: sorting the plurality of first distances to generate a first sorting result; sorting the plurality of second distances to generate a second sorting result; comparing the solutions of corresponding sorted nodes in the first sorting result and the second sorting result, deleting solutions with different positional correspondences, and generating a fused optimized sorting result; establishing multiple sets of optimization spaces based on the fused optimized sorting result and solutions at adjacent positions; continuing to randomly generate parameters in the multiple sets of optimization spaces, determining whether they contain solutions that satisfy the desired particle size constraint interval and the desired particle size dispersion characteristics; if so, outputting the second crushing control parameters and the second environmental control information; if not, performing iterative optimization.

[0045] The specific configuration of the crushing parameter optimization module 40 will be described in detail below. The crushing parameter optimization module 40 may further include: if the number of iterations reaches a preset number, and no solution satisfies the desired particle size constraint range and the desired particle size dispersion characteristic, the optimal particle size constraint range is taken as the priority constraint; based on the iteration optimization results, a candidate solution space is extracted; the solution with the smallest distance to the desired particle size dispersion characteristic is selected from the candidate solution space as the optimal crushing control parameter and the optimal environmental control information, and the corresponding optimal particle size dispersion characteristic is obtained; the optimal particle size dispersion characteristic is compared with the desired particle size dispersion characteristic to perform cyclic crushing particle size selection, and the screening control parameters of the crushing particle screening mechanism are configured with the cyclic crushing particle size; the target crushing equipment is initialized with the screening control parameters, the optimal crushing control parameters, and the optimal environmental control information.

[0046] The specific configuration of the pulverization fitting prediction module 30 will be described in detail below. The pulverization fitting prediction module 30 may further include: the drug characteristic information including drug hardness and drug viscosity; collecting multiple historical pulverization records constrained by the drug hardness, drug viscosity, the first pulverization control parameter, and the first environmental control information; after removing outliers from the multiple historical pulverization records, statistically analyzing the particle size distribution interval to generate the first predicted particle size feature; and statistically analyzing the distribution ratio of the same particle size among the multiple historical pulverization records after outlier removal to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes multi-level particle size dispersion features.

[0047] The specific configuration of the control parameter information acquisition module 20 will be described in detail below. The control parameter information acquisition module 20 may further include: connecting to the target crushing equipment and acquiring a historical crushing record log set; clustering identical crushing control parameters based on the historical crushing record log set; statistically obtaining multiple frequent activation probabilities for multiple historical control parameter combinations based on the clustering results, wherein any set of historical control parameter combinations includes historical crushing control parameters and historical environmental control information; and selecting the set of historical control parameter combinations with the highest probability based on the multiple frequent activation probabilities to generate the first crushing control parameter and the first environmental control information.

[0048] The specific configuration of the crushing equipment parameter initialization module 50 will be described in detail below. The crushing equipment parameter initialization module 50 may further include: when the first predicted particle size feature meets the desired particle size constraint range and the first particle size dispersion feature meets the desired particle size dispersion feature, the target crushing equipment is initialized with parameters according to the first crushing control parameters and the first environmental control information.

[0049] The particle size control-based drug pulverizing device provided in the embodiments of the present invention can execute the particle size control-based drug pulverizing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0050] Although this application makes various references to certain modules in the apparatus according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not intended to limit the scope of protection of this invention.

[0051] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for pulverizing a pharmaceutical product based on particle size control, characterized by, include: Obtain basic information on the pulverization of the target drug, wherein the basic information on pulverization includes drug characteristic information, desired particle size constraint range, and desired particle size dispersion characteristics; Connect to the target crushing equipment and collect the first crushing control parameters and the first environmental control information; Based on the drug characteristic information, a crushing fitting prediction is performed on the first crushing control parameters and the first environmental control information to generate a first predicted particle size feature and a first particle size dispersion feature. When the first predicted particle size feature does not meet the expected particle size constraint range and / or the first particle size dispersion feature does not meet the expected particle size dispersion feature, the cyclic optimization constraint module is activated to optimize the crushing parameters and generate the second crushing control parameters and the second environmental control information. The target crushing equipment is initialized according to the second crushing control parameters and the second environmental control information; When the first predicted particle size feature does not meet the desired particle size constraint range and / or the first particle size dispersion feature does not meet the desired particle size dispersion feature, the cyclic optimization constraint module is activated to optimize the crushing parameters and generate second crushing control parameters and second environmental control information, including: Activate the cyclic optimization constraint module and perform the following steps: The first crushing control parameter and the first environmental control information are randomly adjusted multiple times to generate multiple sets of optimized crushing parameters and multiple sets of optimized environmental parameters, and the multiple sets of optimized crushing parameters and multiple sets of optimized environmental parameters correspond one-to-one. The multiple sets of optimized crushing parameters and the multiple sets of optimized environmental parameters are subjected to crushing fitting to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion characteristics. Calculate a plurality of first distances between the plurality of optimized particle size constraint intervals and the desired particle size constraint interval, and a plurality of second distances between the plurality of optimized particle size dispersion features and the desired particle size dispersion features; Based on the plurality of first distances and the plurality of second distances, distance minimization iterative optimization is performed to generate the second crushing control parameters and the second environmental control information; Its characteristic is that, based on the plurality of first distances and the plurality of second distances, and taking the desired particle size constraint interval as the priority constraint, iterative optimization is performed to minimize distances, generating optimal crushing parameters and optimal environmental parameters, as well as the corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics, including: Sort the plurality of first distances to generate a first sorting result; The plurality of second distances are sorted to generate a second sorting result; By comparing the solutions for the corresponding sorting nodes in the first sorting result and the second sorting result, solutions with different positional correspondences are deleted, and a fused optimized sorting result is generated. Based on the fusion optimization ranking results, multiple sets of optimization spaces are established using solutions at adjacent positions; Parameters are randomly generated in the multiple optimization spaces. It is determined whether the solution contains a solution that satisfies the desired particle size constraint range and the desired particle size dispersion characteristics. If so, the second crushing control parameter and the second environmental control information are output. If not, perform a loop to find the optimal solution; Connect to the target crushing equipment and collect the first crushing control parameters and the first environmental control information, including: Connect to the target crushing equipment and obtain a collection of historical crushing records; Based on the historical shredding record log set, clustering is performed for the same shredding control parameters. Based on the clustering results, multiple frequent activation probabilities of multiple historical control parameter combinations are obtained. Each set of historical control parameter combinations includes historical shredding control parameters and historical environmental control information. Based on the multiple frequent activation probabilities, the set of historical control parameter combinations with the highest probability is selected to generate the first crushing control parameters and the first environmental control information.

2. The pharmaceutical pulverization method based on particle size control as described in claim 1, characterized in that, include: If the number of iterations reaches the preset number of iterations and there is no solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics, then the optimal particle size constraint interval is taken as the priority constraint, and the candidate solution space is extracted based on the results of the iteration search. The solution with the smallest distance from the desired particle size dispersion feature is selected from the candidate solution space and used as the optimal crushing control parameter and optimal environmental control information, and the corresponding optimal particle size dispersion feature is obtained. By comparing the optimal particle size dispersion characteristics with the desired particle size dispersion characteristics, the cyclic crushing particle size is selected, and the screening control parameters of the crushing particle screening mechanism are configured based on the cyclic crushing particle size. The target crushing equipment is initialized with the screening control parameters, the optimal crushing control parameters, and the optimal environmental control information.

3. The pharmaceutical pulverization method based on particle size control as described in claim 1, characterized in that, Based on the drug characteristic information, a pulverization fitting prediction is performed on the first pulverization control parameters and the first environmental control information to generate a first predicted particle size feature and a first particle size dispersion feature, including: The drug characteristic information includes drug hardness and drug viscosity; Multiple historical pulverization records are collected, constrained by the drug hardness, drug viscosity, the first pulverization control parameter, and the first environmental control information. After removing outliers from the multiple historical crushing records, the particle size distribution range is statistically analyzed to generate the first predicted particle size feature; After removing outliers, the distribution ratio of the same particle size is statistically analyzed for multiple historical crushing records to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes multi-level particle size dispersion features.

4. The pharmaceutical pulverization method based on particle size control as described in claim 1, characterized in that, When the first predicted particle size feature satisfies the desired particle size constraint range, and the first particle size dispersion feature satisfies the desired particle size dispersion feature, the target pulverizing equipment is initialized with parameters according to the first pulverizing control parameters and the first environmental control information.

5. A medicine pulverizing device based on particle size control, characterized by, The apparatus is used to implement the drug pulverization method based on particle size control according to any one of claims 1-4, and the apparatus comprises: The basic information acquisition module for pulverization is used to acquire the basic information of pulverization of the target drug, wherein the basic information of pulverization includes drug characteristic information, expected particle size constraint range and expected particle size dispersion characteristics; The control parameter information acquisition module is used to connect to the target crushing equipment and acquire the first crushing control parameters and the first environmental control information; The pulverization fitting and prediction module is used to perform pulverization fitting and prediction based on the drug characteristic information, targeting the first pulverization control parameters and the first environmental control information, and to generate the first predicted particle size feature and the first particle size dispersion feature. The crushing parameter optimization module is used to activate the cyclic optimization constraint module to optimize the crushing parameters and generate second crushing control parameters and second environmental control information when the first predicted particle size feature does not meet the expected particle size constraint range and / or the first particle size dispersion feature does not meet the expected particle size dispersion feature. The crushing equipment parameter initialization module is used to initialize the parameters of the target crushing equipment according to the second crushing control parameters and the second environmental control information.

Images