Drug crushing method and device based on particle size control

Abstract

The invention discloses a drug crushing method and device based on particle size control, and relates to the technical field of drug crushing, and the method comprises the following steps: obtaining crushing basic information of a target drug; connecting target crushing equipment, and collecting a first crushing control parameter and first environment control information; generating a first predicted particle size characteristic and a first particle size dispersion characteristic; when the first predicted particle size characteristic does not meet the expected particle size constraint interval and / or the first particle size dispersion characteristic does not meet the expected particle size dispersion characteristic, crushing parameter optimization is carried out; and performing parameter initialization on the target crushing equipment according to the second crushing control parameter and the second environment control information. The technical problems that due to the fact that existing medicine smashing depends on manual experience adjustment, medicine particle size control precision is insufficient, production efficiency is low, product quality is unstable, and expected particle size standards and particle size dispersion characteristics cannot be achieved are solved. The technical effects of improving the particle size control precision, the production efficiency and the product quality stability are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of drug pulverization, and in particular to a drug pulverization method and device based on particle size control. Background Art

[0002] In the modern pharmaceutical industry, drug particle size control is a crucial link to ensure drug efficacy, bioavailability and stability. Different drugs have strict requirements on the particle size and particle size distribution of the final product due to their physical and chemical properties, solubility, biomembrane permeability and other characteristics. Too large a particle size will affect the dissolution rate and bioabsorption efficiency of the drug, while too small a particle size may increase the surface area of ​​the drug, accelerate its degradation or reaction with the surrounding environment, which is also not conducive to the stability and efficacy of the drug. How to ensure precise control of the particle size of drug crushing has become an important direction for the development of pharmaceutical technology. However, traditional drug crushing methods often rely on empirical adjustments and multiple tests, which are not only inefficient, but also difficult to ensure that each production can achieve the expected particle size standard and particle size dispersion characteristics, resulting in a wide range of particle size distribution of the final product, affecting drug efficacy and stability.

[0003] Therefore, at the current stage, there is a technical problem in the technology related to pharmaceutical crushing that relies on manual experience adjustment, which leads to insufficient precision in drug particle size control, low production efficiency, unstable product quality, and failure to achieve the expected particle size standard and particle size dispersion characteristics. Summary of the invention

[0004] The present application provides a drug pulverization method and device based on particle size control, thereby solving the technical problems existing in the existing drug pulverization, which rely on manual experience adjustment, resulting in insufficient drug particle size control accuracy, low production efficiency, unstable product quality, and failure to achieve the expected particle size standard and particle size dispersion characteristics, thereby achieving the technical effect of improving particle size control accuracy, production efficiency and product quality stability.

[0005] The present application provides a drug pulverization method based on particle size control, the method comprising: obtaining basic pulverization information of a target drug, wherein the basic pulverization information comprises drug characteristic information, an expected particle size constraint interval and an expected particle size dispersion characteristic; connecting a target pulverization device and collecting a first pulverization control parameter and a first environmental control information; based on the drug characteristic information, performing pulverization fitting prediction for the first pulverization control parameter 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 expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic, activating a cyclic optimization constraint module, performing pulverization parameter optimization, and generating a second pulverization control parameter and a second environmental control information; and initializing parameters of the target pulverization device according to the second pulverization control parameter and the second environmental control information.

[0006] In a possible implementation, when the first predicted particle size characteristic does not satisfy the expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic, the loop optimization constraint module is activated to optimize the crushing parameters, generate the second crushing control parameters and the second environmental control information, and also perform the following processing: activate the loop 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 groups of optimized crushing parameters and multiple groups of optimized environmental parameters, and the multiple groups of optimized crushing parameters and the multiple groups of optimized environmental parameters correspond one to one; perform crushing fitting on the multiple groups of optimized crushing parameters and the multiple groups of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion characteristics; calculate multiple first distances between the multiple optimized particle size constraint intervals and the expected particle size constraint intervals, and multiple second distances between the multiple optimized particle size dispersion characteristics and the expected particle size dispersion characteristics; 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 multiple first distances and the multiple second distances, with satisfying the expected particle size constraint interval as a priority constraint, an iterative optimization search for distance minimization is performed to generate optimal crushing parameters and optimal environmental parameters, as well as corresponding optimal particle size constraint intervals and optimal particle size dispersion characteristics, and the following processing is performed: sorting the multiple first distances to generate a first sorting result; sorting the multiple second distances to generate a second sorting result; comparing the similarities and differences between the solutions of the corresponding sorting nodes in the first sorting result and the second sorting result, deleting solutions with different position correspondences, and generating a fusion optimization sorting result; based on the fusion optimization sorting result, establishing multiple groups of optimization spaces with solutions at adjacent positions; continuing to randomly generate parameters in the multiple groups of optimization spaces to determine whether they contain solutions that satisfy the expected particle size constraint interval and the expected particle size dispersion characteristics, and if so, outputting the second crushing control parameters and the second environmental control information; if not, performing a cyclic optimization search.

[0008] In a possible implementation, the parameters of the target pulverizing equipment are initialized according to the second pulverizing control parameters and the second environmental control information, and the following processing is performed: if the number of cyclic optimization reaches a preset number of iterations, and there is no solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics, the optimal particle size constraint interval is taken as a priority constraint, and according to the cyclic optimization result, a candidate solution space is extracted; the solution with the smallest distance to the desired particle size dispersion characteristics is screened in the candidate solution space as the optimal pulverizing control parameters and the optimal environmental control information, and the corresponding optimal particle size dispersion characteristics are obtained; the optimal particle size dispersion characteristics are compared with the expected particle size dispersion characteristics, and a cyclic pulverizing particle size is selected, and the screening control parameters of the pulverizing particle screening mechanism are configured according to the cyclic pulverizing particle size; the parameters of the target pulverizing equipment are initialized with the screening control parameters, the optimal pulverizing control parameters and the optimal environmental control information.

[0009] In a possible implementation, based on the drug characteristic information, a pulverization fitting prediction is performed for the first pulverization control parameter and the first environmental control information to generate a first predicted particle size characteristic and a first particle size dispersion characteristic, and the following processing is also performed: the drug characteristic information includes drug hardness and drug viscosity; with the drug hardness, the drug viscosity, the first pulverization control parameter and the first environmental control information as constraints, multiple historical pulverization records are collected; after outliers are removed from the multiple historical pulverization records, the particle size distribution interval is statistically calculated to generate the first predicted particle size characteristic; the distribution percentage of the same particle size is statistically calculated for the multiple historical pulverization records after outliers are removed to generate the first particle size dispersion characteristic, wherein the first particle size dispersion characteristic includes a multi-level particle size dispersion characteristic.

[0010] In a possible implementation, the target comminution device is connected, the first comminution control parameter and the first environmental control information are collected, and the following processing is also performed: the target comminution device is connected to obtain a set of historical comminution record logs; the same comminution control parameters are clustered based on the historical comminution record log set, and multiple frequent activation probabilities of multiple historical control parameter combinations are obtained according to the clustering results, wherein any group of historical control parameter combinations includes historical comminution control parameters and historical environmental control information; according to the multiple frequent activation probabilities, a group of historical control parameter combinations with the largest probability is selected to generate the first comminution control parameters and the first environmental control information.

[0011] In a possible implementation, the parameters of the target crushing equipment are initialized 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 characteristic meets the expected particle size constraint interval, and the first particle size dispersion characteristic meets the expected particle size dispersion characteristic, the parameters of the target crushing equipment are initialized according to the first crushing control parameters and the first environmental control information.

[0012] The present application also provides a drug pulverizing device based on particle size control, including: a pulverizing basic information acquisition module, used to obtain the pulverizing basic information of the target drug, wherein the pulverizing basic information includes drug characteristic information, expected particle size constraint interval and expected particle size dispersion characteristics; a control parameter information acquisition module, used to connect to the target pulverizing equipment, and collect the first pulverizing control parameter and the first environmental control information; a pulverizing fitting prediction module, used to perform pulverizing fitting prediction for the first pulverizing control parameter and the first environmental control information based on the drug characteristic information, and generate a first predicted particle size characteristic and a first particle size dispersion characteristic; a pulverizing parameter optimization module, used to activate the cyclic optimization constraint module when the first predicted particle size characteristic does not meet the expected particle size constraint interval and / or the first particle size dispersion characteristic does not meet the expected particle size dispersion characteristic, and perform pulverizing parameter optimization to generate a second pulverizing control parameter and a second environmental control information; a pulverizing equipment parameter initialization module, used to perform parameter initialization of the target pulverizing equipment according to the second pulverizing control parameter and the second environmental control information.

[0013] The invention proposes to obtain the basic information of the target drug pulverization through the drug pulverization method and device based on particle size control proposed in this application; connect the target pulverization equipment, collect the first pulverization control parameter and the first environmental control information; generate the first predicted particle size characteristic and the first particle size dispersion characteristic; when the first predicted particle size characteristic does not meet the expected particle size constraint interval and / or the first particle size dispersion characteristic does not meet the expected particle size dispersion characteristic, optimize the pulverization parameters; initialize the parameters of the target pulverization equipment according to the second pulverization control parameter and the second environmental control information. The invention solves the technical problem that the existing drug pulverization relies on manual experience adjustment, which leads to insufficient drug particle size control accuracy, low production efficiency, unstable product quality, and the inability to achieve the expected particle size standard and particle size dispersion characteristics, and achieves the technical effect of improving particle size control accuracy, production efficiency and product quality stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations 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 the present application; Figure 2 A schematic diagram of the structure of a drug pulverizing device based on particle size control provided in an embodiment of the present application.

[0016] Explanation of the reference numerals: crushing basic information acquisition module 10 , control parameter information acquisition module 20 , crushing fitting prediction module 30 , crushing parameter optimization module 40 , crushing equipment parameter initialization module 50 . DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application provides a method for pulverizing a drug based on particle size control, such as Figure 1 As shown, the method includes: Step S100, obtaining basic information on the crushing of the target drug, wherein the basic information on the crushing includes drug characteristic information, expected particle size constraint interval, and expected particle size dispersion characteristics. The basic information on the crushing of the target drug is obtained, for example, by reading the instructions of the drug in detail, consulting relevant scientific literature and research papers, conducting a more in-depth analysis of the drug properties and crushing experimental data, or directly consulting the drug manufacturer or supplier to obtain the best practices and related information on drug crushing, wherein the basic information on the crushing includes drug characteristic information, expected particle size constraint interval, and expected particle size dispersion characteristics. Specifically, the drug characteristic information refers to the physical and chemical properties of the drug (such as the melting point, boiling point, density, hardness, brittleness, viscosity, hygroscopicity, solubility, etc. of the drug, which directly affects the behavior of the drug during the crushing process, such as drugs with high hardness may require stronger crushing force, while drugs with high viscosity may produce agglomeration during the crushing process), crystal structure (the crystal morphology and internal structure of the drug have a significant impact on its crushing effect, and drugs with different crystal structures may show different brittleness and fracture behaviors during crushing) and stability (drugs may be affected by environmental factors such as temperature, humidity, and light during the crushing process and degraded). or denaturation); the expected particle size constraint range refers to the particle size range expected to be achieved after the drug is crushed. Different drugs and preparations have different requirements for particle size. For example, some oral preparations may require a larger particle size to improve taste and swallowing, while injectable preparations may require a smaller particle size to improve drug solubility and bioavailability. When formulating a crushing strategy, the target particle size range must be clearly defined, and the particle size distribution of the final product must fall within this range as much as possible; in addition to particle size, particle size distribution is also an important indicator for evaluating the crushing effect. Particle size distribution describes the proportion of particles of different sizes in the total, reflecting the uniformity of particle size. The expected 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 crushed drug meets the expected particle size constraint range, the proportion of the same particle size, such as at least 70% of the particles have the same particle size, and the difference between the particle size of the remaining 30% of the particles and the particle size of 70% of the particles cannot be too large, is to ensure the uniformity of the particles, which is convenient for subsequent mixing or tableting.

[0021] Step S200, connecting to a target crushing device, and collecting first crushing control parameters and first environmental control information.

[0022] Furthermore, step S200 also includes step S210, connecting to the target shredding device and obtaining a set of historical shredding record logs; step S220, clustering the same shredding control parameters based on the set of historical shredding record logs, and obtaining multiple frequent activation probabilities of multiple historical control parameter combinations based on the clustering results, wherein any group of historical control parameter combinations includes historical shredding control parameters and historical environmental control information; step S230, selecting a group of historical control parameter combinations with the highest probability based on the multiple frequent activation probabilities to generate the first shredding control parameters and the first environmental control information.

[0023] Preferably, a connection is made with the target crushing device to obtain a set of historical crushing record logs, specifically referring to accessing and downloading the historical records of all crushing tasks performed by the device in the past period of time. These records usually contain detailed information of each crushing task, such as crushing time, control parameters used, environmental conditions (such as temperature, humidity), crushing results (such as particle size distribution, output, etc.), etc.; clustering the same crushing control parameters based on the historical crushing record log set refers to clustering the historical crushing record log set, dividing the data set into several groups or clusters, so that the similarity of data points in the same cluster is high, while the similarity of data points between different clusters is low, and obtaining clustering results, that is, classifying records with the same or similar crushing control parameters and environmental control information into one category, which helps to identify which control parameter combinations and environmental condition combinations are more common or effective in actual production, and obtaining multiple frequent activation probabilities of multiple historical control parameter combinations based on the clustering results, wherein 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 frequent activation probability of each cluster can evaluate the performance of different control parameter combinations and select the optimal combination. Combinations with high frequent activation probability may mean that they can stably produce crushing results that meet the requirements. Historical crushing control parameters refer to parameters set and adjusted by operators or automatic control systems during the crushing process, which directly affect the crushing effect and quality. Common crushing control parameters include but are not limited to the speed of the crusher, crushing time, feed rate, crushing chamber pressure, selection and dosage of grinding media, etc. In addition to crushing control parameters, the crushing process is also affected by the external environment. Historical environmental control information refers to environmental condition data recorded during the execution of the crushing task, such as temperature, humidity, air pressure, vibration, etc. These environmental factors may affect the crushing efficiency, product particle size distribution, powder fluidity, etc.; then the optimal control parameter combination is selected based on the high or low frequent activation probability, that is, the most frequently used control parameter combination is selected, which is likely to represent the best crushing conditions. Finally, according to the selected optimal control parameter combination, the first crushing control parameter (such as speed, pressure, time, etc.) and the first environmental control information (such as temperature, humidity, etc.) are generated, which are used to guide future crushing tasks in order to achieve better crushing effects and higher production efficiency.

[0024] Step S300, based on the drug characteristic information, a pulverization fitting prediction is performed for the first pulverization control parameter and the first environmental control information to generate a first predicted particle size characteristic and a first particle size dispersion characteristic. According to the drug characteristic information, the first pulverization control parameter and the first environmental control information, a simulation model of the pulverization process is established to simulate and predict the pulverization process. The model should be able to reflect the stress conditions, crushing mechanism and change rules of particle size and particle size distribution of drug particles during the pulverization process. The first pulverization control parameter and the first environmental control information are input into the model as input parameters, and the model is used to perform simulation calculations to predict the pulverization 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 result is output, and the prediction result 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 of the particles; the particle size dispersion characteristic describes the width and shape of the particle size distribution, such as the span and uniformity index.

[0025] In a possible implementation, step S300 further includes step S310, wherein the drug characteristic information includes drug hardness and drug viscosity; step S320, collecting multiple historical crushing records with the drug hardness, the drug viscosity, the first crushing control parameter and the first environmental control information as constraints; step S330, after removing outliers from the multiple historical crushing records, statistically analyzing the particle size distribution interval to generate the first predicted particle size feature; step S340, statistically analyzing the distribution ratio of the same particle size for the multiple historical crushing records after the outliers are removed to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes a multi-level particle size dispersion feature.

[0026] Preferably, the drug characteristic information includes two important physical properties: drug hardness and drug viscosity. Specifically, drug hardness, especially for solid preparations (such as tablets, capsules, etc.), mainly refers to its compressive strength or radial crushing force. Hardness is a comprehensive indicator of mechanical properties such as material elasticity, plasticity, strength and toughness. For tablets, hardness directly affects its formability during production, stability during packaging and transportation, and disintegration and solubility during use. Tablets with too low hardness are prone to loose tablets, cracks, etc., affecting subsequent coating, packaging and transportation processes, and may even cause damage to the drug during storage or transportation. Although tablets with too high hardness are conducive to maintaining their morphological stability, they may cause the drug and excipients to adhere tightly together, making it difficult for the tablet to disintegrate and the drug ingredients to be effectively dissolved, thereby affecting the therapeutic effect. To evaluate the hardness of a drug, a hardness tester, such as the YD-1 hardness tester, is usually used. Samples are randomly selected from a certain number of tablets, and the force required to break them is measured by applying pressure to evaluate their hardness. The viscosity of a drug refers to the resistance of a fluid drug (such as a solution, suspension, emulsion, etc.) to flow, which directly affects the fluidity, stability, and drug administration effect of the drug. The viscosity of the drug directly affects its administration method and use effect. For example, liquid drugs with moderate viscosity are easier to administer through a syringe or infusion tube, and can ensure uniform distribution of the drug in the body. Drugs with too high or too low viscosity may cause difficulty in administration or uneven drug distribution. Viscosities are usually measured, such as rotational viscometers, capillary viscometers, etc., by measuring the flow velocity or required shear stress of fluid drugs under specific conditions to calculate their viscosity values.

[0027] Preferably, with drug hardness, drug viscosity, first pulverization control parameters (such as rotation speed, time, etc.) and first environmental control information (such as temperature, humidity, etc.) as constraints, multiple pulverization records matching or similar to these conditions are collected from the historical database. These records should contain detailed results of each pulverization task, such as particle size distribution, output, etc. Since there may be abnormal values ​​or outliers in the historical data (which may be caused by equipment failure, operational errors, etc.), these values ​​will have an adverse effect on subsequent statistical analysis. Therefore, it is necessary to use statistical methods (such as Z-score, IQR, etc.) to identify and eliminate outliers in the collected historical pulverization records to ensure the accuracy and reliability of the data; through the particle size distribution of the historical pulverization records after statistical processing, the particle size distribution range of the drug after pulverization is predicted under given drug characteristic information, pulverization control parameters and environmental control information. Specifically, the particle size distribution of the historical pulverization records after eliminating outliers is statistically analyzed to calculate the particle size. The statistical quantities such as mean, median, standard deviation, and the main intervals of particle size distribution (such as minimum particle size, maximum particle size, common particle size range, etc.) constitute the first predicted particle size feature. In addition to predicting the particle size distribution interval, it is also necessary to understand the dispersion of the particle size distribution, that is, the proportion of particles of different particle sizes in the total. The distribution proportion of the same particle size is statistically analyzed for the historical crushing records after removing outliers. First, the particle size range is divided into multiple levels as needed (such as one level for every 0.1 mm or 1 μm); then, the number or mass proportion of particles of each size in each level is counted; finally, these proportion data are output as the first particle size dispersion feature, wherein the first particle size dispersion feature includes a multi-level particle size dispersion feature, and the particle size dispersion feature usually includes a multi-level particle size dispersion feature, that is, the particles are classified according to different particle size ranges (such as fine particle size, medium particle size, coarse particle size, etc.), and the proportion of particles of each particle size in the total is counted. This multi-level classification can describe the dispersion of the particle size distribution in more detail.

[0028] Step S400, when the first predicted particle size characteristic does not satisfy the expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic, activate the loop optimization constraint module, 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 characteristic (i.e., the particle size distribution predicted based on the current crushing control parameters and environmental control information) and the first particle size dispersion characteristic (such as the proportion of each level in the multi-level particle size dispersion characteristic) does not satisfy the corresponding expected particle size constraint interval and the expected particle size dispersion characteristic, that is, when the prediction result does not meet the expectation, it is necessary to activate the loop optimization constraint module, adjust the crushing control parameters and environmental control information, in order to obtain a better crushing effect. Specifically, the loop 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 goal. Information combination, constantly try new parameter combinations, evaluate their prediction results, and adjust parameters according to the results until a parameter combination that meets the expected conditions is found. The crushing parameter optimization includes but is not limited to optimizing the crushing control parameters such as the crusher's rotation speed, crushing time, feed rate, crushing chamber pressure, and environmental control information such as temperature and humidity, so that the predicted particle size characteristics fall within the expected particle size constraint range, and the predicted particle size dispersion characteristics meet the expected 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.

[0029] In a possible implementation, step S400 further includes activating a loop optimization constraint module and executing the following steps: step S410, performing multiple random adjustments on the first crushing control parameters and the first environmental control information to generate multiple groups of optimized crushing parameters and multiple groups of optimized environmental parameters, and the multiple groups of optimized crushing parameters and the multiple groups of optimized environmental parameters correspond one to one; step S420, performing crushing fitting on the multiple groups of optimized crushing parameters and the multiple groups of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion characteristics; step S430, calculating multiple first distances between the multiple optimized particle size constraint intervals and the expected particle size constraint intervals, and multiple second distances between the multiple optimized particle size dispersion characteristics and the expected particle size dispersion characteristics; step S440, performing distance minimization iterative optimization based on the multiple first distances and the multiple second distances to generate the second crushing control parameters and the second environmental control information.

[0030] 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 parameter and the first environmental control information to generate multiple groups of different optimized crushing parameter and optimized environmental parameter combinations, each group of optimized crushing parameters corresponds to the optimized environmental parameters one by one, as candidate solutions for subsequent evaluation; each group of optimized crushing parameters and optimized environmental parameters is input into the simulation model, simulated and calculated, and the corresponding optimized particle size constraint interval and optimized particle size dispersion characteristics are output, that is, multiple optimized particle size constraint intervals and multiple optimized particle size dispersion characteristics are generated; multiple first distances between multiple optimized particle size constraint intervals and expected particle size constraint intervals are calculated, that is, the distance between each optimized particle size constraint interval and the expected particle size constraint interval is calculated, such as calculating the interval overlap, the distance between the center point or the difference of the entire distribution; multiple second distances between multiple optimized particle size dispersion characteristics and the expected particle size dispersion characteristics are calculated, that is, each The distance between an optimized particle size dispersion feature and an expected particle size dispersion feature, such as comparing the differences in the proportions or distribution shapes of different particle size levels; based on multiple first distances and multiple second distances, find the optimal parameter combination that minimizes the distance through iterative optimization. Specifically, according to the comprehensive evaluation of the first distance and the second distance (which may be combined by weighted summation, product or other methods), select a set of optimization parameters with the best performance in the current iteration as the candidate optimal solution, and with this set of candidate optimal solutions as the center, continue to perform random adjustments or adopt more sophisticated search strategies (such as gradient descent, crossover mutation in genetic algorithms, etc.) to generate a new optimization parameter combination, and repeat the above steps for evaluation and selection. The iterative process will continue until a certain convergence condition is met (such as the optimal solution of multiple consecutive iterations changes very little, reaching a preset maximum number of iterations, etc.), and finally generate the second comminution control parameters and second environmental control information that meet the expected particle size constraint interval and particle size dispersion characteristics.

[0031] In a possible implementation, step S440 further includes step S441, sorting the multiple first distances to generate a first sorting result; step S442, sorting the multiple second distances to generate a second sorting result; step S443, comparing the similarities and differences between the solutions of the corresponding sorting nodes in the first sorting result and the second sorting result, deleting the solutions with different position correspondences, and generating a fusion optimization sorting result; step S444, based on the fusion optimization sorting result, establishing multiple groups of optimization spaces with solutions at adjacent positions; step S445, continuing to randomly generate parameters in the multiple groups of optimization spaces, judging whether they contain solutions that satisfy the expected particle size constraint interval and the expected particle size dispersion characteristics, and if so, outputting the second crushing control parameters and the second environmental control information; step S446, if not, executing a loop optimization search.

[0032] Preferably, based on multiple first distances (representing the difference between the optimized particle size constraint interval and the expected particle size constraint interval) and multiple second distances (representing the difference between the optimized particle size dispersion characteristics and the expected particle size dispersion characteristics), satisfying the expected particle size constraint interval is taken as a priority constraint, and distance minimization iterative optimization is performed to find the optimal crushing parameters and environmental parameters. Specifically, since the particle size constraint interval may have a more critical impact on product quality and performance, satisfying the expected particle size constraint interval is set as a priority constraint, which means that in the optimization process, the first distance will be paid attention to and minimized as much as possible, that is, to ensure that the optimized particle size constraint interval is as close as possible to or completely contained in the expected particle size constraint interval; in each iteration, the first distance and the second distance are calculated according to the current optimization parameters (crushing parameters and environmental parameters), and the optimal parameters are calculated based on the particle size constraint interval. The effect of the current optimization parameters is evaluated based on the first distance (i.e., the difference in the particle size constraint interval), and the parameters that lead to a larger first distance are adjusted first, while the second distance (i.e., the difference in particle size dispersion characteristics) is considered. However, when adjusting the parameters, a smaller weight or priority is given 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 that can satisfy the expected particle size constraint interval and make the particle size dispersion characteristics close to the expected value is found, and finally the optimal crushing parameters and optimal environmental parameters are obtained. This set of parameters can make the crushed drug particles satisfy the expected particle size constraint interval and have good particle size dispersion characteristics, and the corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics calculated according to this set of optimal parameters are obtained.

[0033] Preferably, the first distances corresponding to all optimization parameter combinations (i.e., the difference between the optimized particle size constraint interval and the expected particle size constraint interval) are sorted to generate a first sorting result; the second distances corresponding to all optimization parameter combinations (i.e., the difference between the optimized particle size dispersion characteristics and the expected particle size dispersion characteristics) are sorted to generate a second sorting result; the solutions corresponding to the sorting nodes in the first sorting result and the second sorting result are compared, and the solutions with different position correspondence are deleted, that is, only the solutions with similar or consistent positions in the two sorting results are retained, and these solutions have achieved a good balance between the two optimization objectives (particle size and particle size dispersion), and the screened solutions are re-sorted in a certain way (such as comprehensive distance, priority, etc.) to generate a fusion optimization sorting result; based on the fusion optimization sorting result, the adjacent solutions are sorted. The solution of the position is used as the boundary, and multiple groups of optimization spaces are established, representing the parameter range that may contain a better solution. Random generation of parameters continues in each optimization space to explore the potential better solution in the space; for each newly generated parameter combination, it is determined whether it satisfies the constraints of the expected particle size constraint interval and the expected particle size dispersion characteristics. If a solution that satisfies the constraints is found, the solution is output as the second crushing control parameter and the second environmental control information; if a solution that satisfies the constraints is still not found after the above steps, a cyclic optimization search is performed, such as readjusting the boundaries of the optimization space, changing the strategy of randomly generating parameters, introducing more complex optimization algorithms (such as genetic algorithms, simulated annealing, etc.), etc., and the iteration is performed until a solution that satisfies the constraints is found or the preset stop condition is reached.

[0034] In a possible implementation, step S400 further includes step S450, when the first predicted particle size characteristic satisfies the expected particle size constraint interval, and the first particle size dispersion characteristic satisfies the expected particle size dispersion characteristic, the target pulverizing device is initialized according to the first pulverizing control parameter and the first environmental control information. If the first predicted particle size characteristic satisfies the expected particle size constraint interval, and the first particle size dispersion characteristic satisfies the expected particle size dispersion characteristic, the target pulverizing device is set and adjusted accordingly according to the collected first pulverizing control parameter (such as adjusting the rotation speed, feed rate, and discharge particle size setting value of the pulverizer) and the first environmental control information (such as adjusting the temperature, humidity, and air flow velocity of the working environment), so as to ensure that the subsequent pulverizing process can run stably and efficiently, thereby ensuring the pulverizing effect of the medicine.

[0035] Step S500: initializing parameters of the target pulverizing device according to the second pulverizing control parameters and the second environmental control information.

[0036] Furthermore, step S500 also includes step S510, if the number of cyclic optimization reaches a preset number of iterations, and there is no solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics, satisfying the optimal particle size constraint interval is prioritized, and according to the cyclic optimization result, a candidate solution space is extracted; step S520, the solution with the smallest distance from the desired particle size dispersion characteristics is screened in the candidate solution space as the optimal crushing control parameter and the optimal environmental control information, and the corresponding optimal particle size dispersion characteristics are obtained; step S530, the optimal particle size dispersion characteristics are compared with the expected particle size dispersion characteristics, and a cyclic crushing particle size is selected, and the screening control parameters of the crushing particle screening mechanism are configured with the cyclic crushing particle size; step S540, the parameters of the target crushing equipment are initialized with the screening control parameters, the optimal crushing control parameters and the optimal environmental control information.

[0037] Preferably, if the number of cyclic optimization has reached a preset number of iterations, but no solution that satisfies both the expected particle size constraint interval and the expected particle size dispersion characteristics is found during the search process, then satisfying the optimal particle size constraint interval is selected as the primary condition, that is, priority is given to those solutions that can make the particle size characteristics closer to the expected particle size constraint interval, and then all possible candidate solutions are extracted from the cyclic optimization results to obtain the optimal solution space (including all tried control parameter combinations), and then a solution with the smallest distance to the expected particle size dispersion characteristics is screened out from these candidate solutions. This solution will be regarded as a combination of optimal crushing control parameters and optimal environmental control information, and the corresponding optimal particle size dispersion characteristics will be obtained; the optimal particle size dispersion characteristics corresponding to the screened optimal solution will be compared with the expected particle size dispersion characteristics to evaluate the difference between the two, and the cyclic crushing and particle size dispersion will be performed according to the comparison results. Diameter selection, specifically, through multiple or continuous crushing operations, each time the crushing parameters (such as particle size setting value, rotation speed, etc.) are adjusted, and then the crushed particles are screened using a screening particle screening mechanism to gradually approach the desired particle size dispersion characteristics, wherein the configuration of the 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, and finally, the target crushing equipment is fully initialized with the screened optimal screening control parameters, optimal crushing control parameters and optimal environmental control information, including setting the speed and feed rate of the crusher to the optimal value, 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, so as to return the screened large particles to the crushing chamber for crushing, so as to achieve optimized crushing effect and particle size distribution in actual operation.

[0038] In the above, refer to Figure 1 The pharmaceutical pulverization method based on particle size control according to an embodiment of the present invention is described in detail. Figure 2A medicine pulverizing device based on particle size control according to an embodiment of the present invention is described.

[0039] The drug pulverizing device based on particle size control according to the embodiment of the present invention is used to solve the technical problems of existing drug pulverizing that rely on manual experience adjustment, which leads to insufficient drug particle size control accuracy, low production efficiency, unstable product quality, and failure to achieve the expected particle size standard and particle size dispersion characteristics, thereby achieving the technical effect of improving particle size control accuracy, production efficiency and product quality stability. The drug 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 prediction module 30, a pulverizing parameter optimization module 40, and a pulverizing equipment parameter initialization module 50.

[0040] A pulverization basic information acquisition module 10 is used to obtain the pulverization basic information of the target drug, wherein the pulverization basic information includes drug characteristic information, expected particle size constraint interval and expected particle size dispersion characteristics; a control parameter information acquisition module 20 is used to connect to the target pulverization equipment and collect the first pulverization control parameter and the first environmental control information; a pulverization fitting prediction module 30 is used to perform pulverization fitting prediction for the first pulverization control parameter and the first environmental control information based on the drug characteristic information, and generate a first predicted particle size characteristic and a first particle size dispersion characteristic; a pulverization parameter optimization module 40 is used to activate the cyclic optimization constraint module when the first predicted particle size characteristic does not meet the expected particle size constraint interval and / or the first particle size dispersion characteristic does not meet the expected particle size dispersion characteristic, perform pulverization parameter optimization, and generate a second pulverization control parameter and a second environmental control information; a pulverization equipment parameter initialization module 50 is used to initialize the parameters of the target pulverization equipment according to the second pulverization control parameter and the second environmental control information.

[0041] 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 the cyclic optimization constraint module, and executing the following steps: performing multiple random adjustments on the first crushing control parameter 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 to each other one by 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 characteristics; calculating multiple first distances between the multiple optimized particle size constraint intervals and the desired particle size constraint intervals, and multiple second distances between the multiple optimized particle size dispersion characteristics and the desired particle size dispersion characteristics; 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.

[0042] The specific configuration of the crushing parameter optimization module 40 will be described in detail below. The crushing parameter optimization module 40 is based on the multiple first distances and the multiple second distances, and takes the desired particle size constraint interval as the priority constraint to perform distance minimization iterative optimization, generate optimal crushing parameters and optimal environmental parameters, and the corresponding optimal particle size constraint interval and optimal particle size dispersion characteristics, and further includes: sorting the multiple first distances to generate a first sorting result; sorting the multiple second distances to generate a second sorting result; comparing the similarities and differences between the solutions of the corresponding sorting nodes in the first sorting result and the second sorting result, deleting the solutions with different position correspondences, and generating a fusion optimization sorting result; based on the fusion optimization sorting result, establishing multiple groups of optimization spaces with solutions at adjacent positions; continuing to randomly generate parameters in the multiple groups of optimization spaces to determine whether a solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics is included, and if so, outputting the second crushing control parameter and the second environmental control information; if not, performing a cyclic optimization search.

[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: if the number of cyclic optimization reaches a preset number of iterations, and there is no solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics, taking the optimal particle size constraint interval as a priority constraint, extracting a candidate solution space according to the cyclic optimization result; screening the solution with the smallest distance from the desired particle size dispersion characteristics in the candidate solution space as the optimal crushing control parameter and the optimal environmental control information, and obtaining the corresponding optimal particle size dispersion characteristics; comparing the optimal particle size dispersion characteristics with the desired particle size dispersion characteristics, performing cyclic crushing particle size selection, and configuring the screening control parameters of the crushing particle screening mechanism with the cyclic crushing particle size; initializing the parameters of the target crushing equipment with the screening control parameters, the optimal crushing control parameters and the optimal environmental control information.

[0044] 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 feature information includes drug hardness and drug viscosity; taking the drug hardness, the drug viscosity, the first pulverization control parameter and the first environmental control information as constraints, collecting multiple historical pulverization records; after removing outliers from the multiple historical pulverization records, statistically analyzing the particle size distribution interval to generate the first predicted particle size feature; performing statistics on the distribution ratio of the same particle size for the multiple historical pulverization records after removing outliers to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes a multi-level particle size dispersion feature.

[0045] 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 shredding device to obtain a set of historical shredding record logs; clustering the same shredding control parameters based on the set of historical shredding record logs, and obtaining multiple frequent activation probabilities of multiple historical control parameter combinations according to the clustering results, wherein any set of historical control parameter combinations includes historical shredding control parameters and historical environmental control information; and selecting a set of historical control parameter combinations with the largest probability according to the multiple frequent activation probabilities to generate the first shredding control parameters and the first environmental control information.

[0046] The specific configuration of the pulverizing device parameter initialization module 50 will be described in detail below. The pulverizing device parameter initialization module 50 may further include: when the first predicted particle size characteristic satisfies the expected particle size constraint interval, and the first particle size dispersion characteristic satisfies the expected particle size dispersion characteristic, initializing the parameters of the target pulverizing device according to the first pulverizing control parameter and the first environmental control information.

[0047] The drug pulverizing device based on particle size control provided in the embodiment of the present invention can execute the drug pulverizing method based on particle size control provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0048] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and 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 the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0049] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art 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 in the protection scope of this application.

Claims

1. A drug pulverization method based on particle size control, characterized in that: include: Obtaining basic information of crushing of the target drug, wherein the basic information includes drug characteristic information, expected particle size constraint interval and expected particle size dispersion characteristics; Connecting to a target crushing device and collecting a first crushing control parameter and a first environmental control information; Based on the drug characteristic information, a pulverization fitting prediction is performed for the first pulverization control parameter 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 expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic, activating the cyclic optimization constraint module, optimizing the crushing parameters, and generating the second crushing control parameters and the second environmental control information; Parameters of the target pulverizing device are initialized according to the second pulverizing control parameters and the second environmental control information.

2. The drug pulverization method based on particle size control according to claim 1, characterized in that: When the first predicted particle size characteristic does not satisfy the expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic, activating the cyclic optimization constraint module, optimizing the crushing parameters, and generating the second crushing control parameters and the second environmental control information, including: Activate the loop 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 groups of optimized crushing parameters and multiple groups of optimized environmental parameters, and the multiple groups of optimized crushing parameters and the multiple groups of optimized environmental parameters correspond to each other one by one; Performing pulverization fitting on the multiple groups of optimized pulverization parameters and the multiple groups of optimized environmental parameters to generate multiple optimized particle size constraint intervals and multiple optimized particle size dispersion characteristics; Calculating 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 multiple first distances and the multiple second distances, distance minimization iterative optimization is performed to generate the second pulverization control parameter and the second environmental control information.

3. The drug pulverization method based on particle size control according to claim 2, characterized in that: Based on the multiple first distances and the multiple second distances, taking the desired particle size constraint interval as a priority constraint, performing distance minimization iterative optimization, generating optimal crushing parameters and optimal environmental parameters, as well as corresponding optimal particle size constraint intervals and optimal particle size dispersion characteristics, including: Sorting the multiple first distances to generate a first sorting result; Sorting the multiple second distances to generate a second sorting result; Comparing the similarities and differences between the solutions of the corresponding sorting nodes in the first sorting result and the second sorting result, deleting the solutions with different position correspondences, and generating a fusion optimization sorting result; Based on the fusion optimization sorting results, multiple groups of optimization spaces are established with solutions at adjacent positions; Continue to randomly generate parameters in the multiple groups of optimization spaces to determine whether a solution that satisfies the desired particle size constraint interval and the desired particle size dispersion characteristics is included, and if so, output the second pulverization control parameter and the second environmental control information; If not, perform a loop optimization.

4. The drug pulverization method based on particle size control according to claim 3, characterized in that: include: If the number of cyclic optimization 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, the candidate solution space is extracted according to the cyclic optimization result, with satisfying the optimal particle size constraint interval as the priority constraint; Screening the solution with the smallest distance from the desired particle size dispersion feature in the candidate solution space as the optimal crushing control parameter and optimal environmental control information, and obtaining the corresponding optimal particle size dispersion feature; Comparing the optimal particle size dispersion characteristics with the expected particle size dispersion characteristics, selecting a cyclic crushing particle size, and configuring screening control parameters of a crushing particle screening mechanism according to the cyclic crushing particle size; The target pulverizing device is initialized with the screening control parameter, the optimal pulverizing control parameter and the optimal environmental control information.

5. The drug pulverization method based on particle size control according to claim 1, characterized in that: Based on the drug characteristic information, a pulverization fitting prediction is performed for the first pulverization control parameter and the first environmental control information to generate a first predicted particle size characteristic and a first particle size dispersion characteristic, including: The drug characteristic information includes drug hardness and drug viscosity; Collecting a plurality of historical pulverization records based on the drug hardness, the drug viscosity, the first pulverization control parameter, and the first environmental control information as constraints; After removing outliers from the plurality of historical comminution records, the particle size distribution interval is counted to generate the first predicted particle size feature; The distribution ratio of the same particle size is statistically performed on the multiple historical crushing records after outliers are removed to generate the first particle size dispersion feature, wherein the first particle size dispersion feature includes a multi-level particle size dispersion feature.

6. The drug pulverization method based on particle size control according to claim 1, characterized in that: Connecting to the target crushing equipment, collecting the first crushing control parameter and the first environmental control information, including: Connect to the target shredding device and obtain the historical shredding record log set; Clustering the same shredding control parameters based on the historical shredding record log set, and obtaining multiple frequent activation probabilities of multiple historical control parameter combinations according to the clustering results, wherein any group of historical control parameter combinations includes historical shredding control parameters and historical environmental control information; According to the multiple frequent activation probabilities, a group of historical control parameter combinations with the largest probability is selected to generate the first pulverizing control parameter and the first environmental control information.

7. The drug pulverization method based on particle size control according to claim 1, characterized in that: When the first predicted particle size characteristic satisfies the expected particle size constraint interval, and the first particle size dispersion characteristic satisfies the expected particle size dispersion characteristic, parameters of the target pulverizing device are initialized according to the first pulverizing control parameter and the first environmental control information.

8. A drug pulverizing device based on particle size control, characterized in that: The device is used to implement the drug pulverization method based on particle size control according to any one of claims 1 to 7, and the device comprises: A pulverization basic information acquisition module is used to obtain pulverization basic information of a target drug, wherein the pulverization basic information includes drug characteristic information, a desired particle size constraint interval, and desired particle size dispersion characteristics; A control parameter information acquisition module, used to connect to the target crushing equipment and acquire the first crushing control parameter and the first environmental control information; A pulverization fitting prediction module, used for performing pulverization fitting prediction on the first pulverization control parameter and the first environmental control information based on the drug characteristic information, and generating a first predicted particle size characteristic and a first particle size dispersion characteristic; A comminution parameter optimization module, for activating a cyclic optimization constraint module to optimize comminution parameters and generate second comminution control parameters and second environmental control information when the first predicted particle size characteristic does not satisfy the expected particle size constraint interval and / or the first particle size dispersion characteristic does not satisfy the expected particle size dispersion characteristic; A pulverizing device parameter initialization module is used to initialize the parameters of the target pulverizing device according to the second pulverizing control parameters and the second environmental control information.

Images