Simulation method and system for pellet drop of a hopper

Abstract

The application discloses a kind of simulation method and system of granule of medicine bin, and the application relates to the technical field of simulation method of granule, the falling trajectory of each medicine relative to medicine bin is determined based on the detection of the falling event of each medicine granule, and the simulation picture of medicine granule is determined according to the falling trajectory of each medicine relative to medicine bin and the falling simulation of the monitoring space, guarantee the accuracy of the simulation picture of medicine granule.The therefore, based on the division of the simulation picture of medicine granule is formed multiple flow velocity layers, according to the speed of multiple flow velocity layers and the residual particle amount of multiple flow velocity layers is determined according to the proportion of medicine granule in multiple flow velocity layers, and the posture adjustment of medicine bin is triggered, to avoid the accumulation of medicine bin after each time of discharge, guarantee the accuracy of the residual particle amount of multiple flow velocity layers, and the posture adjustment of medicine bin is triggered, to optimize the residual particle amount of multiple flow velocity layers, avoid the accumulation of medicine bin after each time of discharge.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation method of granular material falling, and particularly relates to a simulation method and system of granular material falling of a medicine bin. BACKGROUND

[0002] With the development of science and technology, medicine bins are gradually applied to people's lives and store multiple medicine particles. The multiple medicine particles are in the same medicine bin and are discharged downward from the discharge outlet of the medicine bin. In the prior art, the multiple medicine particles are discharged downward from the discharge outlet of the medicine bin. However, in each discharge of the medicine bin, there is a large amount of accumulated material in the medicine bin, which affects the subsequent use of the medicine bin. The prior art cannot calculate multiple flow velocity layers of the medicine particles, and thus cannot optimize the residual particle amount of the multiple flow velocity layers. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art, and provides a simulation method and system of granular material falling of a medicine bin.

[0004] The simulation method of granular material falling of a medicine bin provided by the present application comprises the following steps: determining a monitoring space according to the current position of the medicine bin and the falling trajectory of the medicine particles in the past; in the dynamic detection of the monitoring space, determining the falling event of each medicine particle according to the position node, time and specification of the medicine particle in the falling process; determining the falling trajectory of each medicine particle relative to the medicine bin based on the detection of the falling event of each medicine particle, and determining the simulation picture of the granular material falling of the medicine particles according to the falling simulation of the monitoring space and the falling trajectory of each medicine particle relative to the medicine bin; forming multiple flow velocity layers based on the division of the simulation picture of the granular material falling of the medicine particles, wherein the multiple flow velocity layers are respectively a central fast layer, an inner wall slow layer and a transition velocity layer; determining the residual particle amount of the multiple flow velocity layers according to the speed of the multiple flow velocity layers and the proportion of the medicine particles in the multiple flow velocity layers, and triggering the posture adjustment of the medicine bin to avoid the accumulated material condition after each discharge of the medicine bin.

[0005] The simulation system of granular material falling of a medicine bin provided by the present application is applied to the simulation method of granular material falling of a medicine bin described above, and comprises:

[0006] A monitoring space module is configured to determine a monitoring space according to the current position of the medicine bin and the falling trajectory of the medicine particles in the past.

[0007] A falling event module is configured to determine the falling event of each medicine particle in the dynamic detection of the monitoring space according to the position node, time and specification of the medicine particle in the falling process.

[0008] A simulation picture module is configured to determine a falling trajectory of each drug relative to the drug bin based on detection of the falling event of each drug particle, and determine a simulation picture of the drug particle discharge based on the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space;

[0009] A flow rate layer module is configured to form a plurality of flow rate layers based on division of the simulation picture of the drug particle discharge, and the plurality of flow rate layers are respectively a center fast layer, an inner wall slow layer and a transition speed layer;

[0010] A posture adjustment module is configured to determine a residual particle amount of the plurality of flow rate layers according to the speed of the plurality of flow rate layers and the drug particle proportion of the plurality of flow rate layers, and trigger posture adjustment of the drug bin to avoid the accumulation of the drug bin after each discharge.

[0011] Compared with the prior art, the present application has the following beneficial effects:

[0012] In the embodiment of the present application, the falling trajectory of each drug relative to the drug bin is determined based on the detection of the falling event of each drug particle, and the simulation picture of the drug particle discharge is determined based on the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space, which is compatible with the falling trajectory of each drug and the overall consideration of the detection space, and ensures the accuracy of the simulation picture of the drug particle discharge.

[0013] Therefore, the plurality of flow rate layers are formed based on the division of the simulation picture of the drug particle discharge, and the plurality of flow rate layers are respectively a center fast layer, an inner wall slow layer and a transition speed layer; the residual particle amount of the plurality of flow rate layers is determined according to the speed of the plurality of flow rate layers and the drug particle proportion of the plurality of flow rate layers, and the posture adjustment of the drug bin is triggered to avoid the accumulation of the drug bin after each discharge, which is compatible with the overall consideration of the speed of the plurality of flow rate layers and the drug particle proportion of the plurality of flow rate layers, ensures the accuracy of the residual particle amount of the plurality of flow rate layers, and triggers the posture adjustment of the drug bin to optimize the residual particle amount of the plurality of flow rate layers and avoid the accumulation of the drug bin after each discharge. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a flowchart of the simulation method of the particle discharge of the drug bin in the embodiment of the present application;

[0015] Figure 2 is a flowchart of step S11 in the simulation method of the particle discharge of the drug bin in the embodiment of the present application;

[0016] Figure 3 is a flowchart of step S12 in the simulation method of the particle discharge of the drug bin in the embodiment of the present application;

[0017] Figure 41 is a flow chart of step S13 in the simulation method for particle dropping from a medicine bin in an embodiment of the present invention;

[0018] Figure 5 1 is a flow chart of step S14 in the simulation method for particle dropping from a medicine bin in an embodiment of the present invention;

[0019] Figure 6 1 is a flow chart of step S15 in the simulation method for particle dropping from a medicine bin in an embodiment of the present invention;

[0020] Figure 7 It is a schematic diagram of the structural composition of the simulation system for particle dropping from the medicine bin in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0022] See also Figures 1 to 7 A simulation method for particle dropping in a medicine bin includes:

[0023] Step S11: determining the monitoring space according to the current position of the medicine bin and the previous falling trajectory of the medicine particles;

[0024] Step S12: in the dynamic detection of the monitoring space, determining the falling events of each drug particle in the drug bin according to the position nodes, time and specifications of each drug particle during the falling process;

[0025] Step S13: determining the falling trajectory of each drug relative to the drug bin based on the detection of the falling events of each drug particle, and determining a simulation image of the drug particle falling according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space;

[0026] Step S14: forming a plurality of flow velocity layers based on the division of the simulation screen of the drug particle falling, wherein the plurality of flow velocity layers are respectively a central fast layer, an inner wall slow layer and a transitional velocity layer;

[0027] Step S15: determining the amount of residual particles in the multiple flow rate layers according to the speeds of the multiple flow rate layers and the proportions of the drug particles in the multiple flow rate layers, and triggering the posture adjustment of the medicine bin to avoid material accumulation in the medicine bin after each discharge;

[0028] refer to Figure 2 ,In step S11, the monitoring space is determined according to the current position of the medicine bin and the previous falling trajectory of the medicine particles;

[0029] In the specific implementation process of the present invention, the specific steps are:

[0030] S111: In the drug detection room, the camera of the drug detection room is used to detect the position of the drug bin, and the current image of the drug bin is collected. The current position of the drug bin is determined according to the matching of the current image of the drug bin and the indoor distribution map of the drug detection room.

[0031] S112: Based on the surrounding detection of the current position of the drug bin, the corresponding drug particle carrying table is collected, and the relative space between the drug bin and the drug particle carrying table is determined according to the spatial comparison of the drug bin and the drug particle carrying table.

[0032] S113: Based on the current position of the drug bin and the drug bin database, the falling trajectory of the past drug particles is determined, and the monitoring space is determined according to the falling trajectory of the past drug particles and the relative space between the drug bin and the drug particle carrying table.

[0033] In the embodiment of the present application, in the drug detection room, the camera of the drug detection room is used to detect the position of the drug bin, and the current image of the drug bin is collected. The current position of the drug bin is determined according to the matching of the current image of the drug bin and the indoor distribution map of the drug detection room, which ensures the accuracy of the current position of the drug bin.

[0034] At this time, in order to capture the position and state of the drug bin in real time, a high-resolution camera needs to be arranged in the drug detection room; at the same time, the camera should be installed in a position that can fully cover the active area of the drug bin, ensuring that the front, side or top of the drug bin can be clearly photographed; the number, position and angle of the camera should be reasonably planned according to the size and layout of the drug detection room.

[0035] The image captured by the camera is used to detect the real-time position of the drug bin; at this time, the image captured by the camera is transmitted to the computer vision system, which uses image recognition technology (such as edge detection, feature matching, etc.) to recognize the drug bin in the image; by comparing the image features of the drug bin with the template features stored in the database in advance, the position and direction of the drug bin in the image are determined.

[0036] In order to match with the indoor distribution map later, the current high-definition image of the drug bin needs to be collected; at this time, after the camera captures the image of the drug bin, the computer will automatically save the image as the current image, which should contain enough details for subsequent image matching and position determination.

[0037] By matching the current image of the cartridge with the indoor distribution map of the drug detection room, the specific position of the cartridge in the room is determined; at this time, the indoor distribution map is a two-dimensional or three-dimensional image containing information such as room layout and equipment position; the computer vision system will compare the current image of the cartridge with the indoor distribution map, and determine the relative position of the cartridge in the distribution map by finding common feature points or edge contours, etc. This position is usually expressed in the form of coordinates, such as (x, y) or (x, y, z) coordinates.

[0038] Based on the results of image matching, the exact position of the cartridge in the drug detection room is determined; at the same time, once the relative position of the cartridge in the distribution map is determined, the actual position of the cartridge in the room is calculated according to the size and scale of the distribution map, which is used in subsequent analysis and simulation processes.

[0039] Further, based on the peripheral detection of the current position of the cartridge, the corresponding drug particle carrying platform is collected, and the relative space between the cartridge and the drug particle carrying platform is determined according to the spatial comparison of the cartridge and the drug particle carrying platform, which is compatible with the overall consideration of the spatial comparison of the cartridge and the drug particle carrying platform, and ensures the accuracy of the relative space between the cartridge and the drug particle carrying platform.

[0040] At this time, after determining the current position of the cartridge, the environment around the cartridge needs to be detected to identify other equipment or structures related to the cartridge, especially the drug particle carrying platform; at the same time, this usually involves using sensors or cameras to scan or shoot the space around the cartridge; sensors detect physical parameters (such as distance, light, etc.), while cameras capture visual information, which is transmitted to the computer system for subsequent analysis and processing.

[0041] In the results of peripheral detection, the information of the drug particle carrying platform directly related to the cartridge is identified and collected; at this time, the computer system will filter out the data related to the drug particle carrying platform from the results of peripheral detection according to the preset rules or algorithms, which includes the position, size, shape, etc. of the carrying platform, which is crucial for subsequent determination of the relative space between the cartridge and the carrying platform.

[0042] By comparing the spatial information of the cartridge and the drug particle carrying platform, the relative position and spatial relationship between them is determined; at this time, this usually involves using three-dimensional modeling or spatial geometry calculation technology; first, according to the collected information, three-dimensional models or spatial coordinates of the cartridge and the carrying platform are constructed; then, by calculating the relative distance, direction, etc. between these models or coordinates, the relative spatial relationship between them is determined, which is used in subsequent particle dropping simulation to simulate the process of particles falling from the cartridge to the carrying platform.

[0043] Specifically, the medicine bin is installed on a fixed support, and the medicine particle carrier is located at a certain position below the medicine bin; the current position of the medicine bin has been determined through S111 step as (x=500, y=600, z=1000) (assuming it is a three-dimensional coordinate system); in S112 step, the environment around the medicine bin is first scanned using the camera; the scanning result shows that there is a medicine particle carrier that matches the preset rules at a certain position directly below the medicine bin; by further analyzing the scanning result, the position information of the carrier is collected as (x=500, y=600, z=900).

[0044] Next, a three-dimensional model of the medicine bin and the carrier is constructed using three-dimensional modeling technology, and the relative spatial relationship between them is determined according to their position information; in this example, the positions of the medicine bin and the carrier in the x and y directions are the same, but in the z direction, the carrier is 100 units lower than the medicine bin, which means that when the particles fall from the medicine bin, they will fall along the z-axis direction to the carrier by 100 units; through the determination of the relative spatial relationship, accurate spatial parameters are provided for subsequent particle falling simulation to ensure the accuracy and practicality of the simulation; during the simulation process, the particles are simulated to fall from different positions of the medicine bin, and the stacking form and distribution of the particles on the carrier are observed.

[0045] Further, based on the current position of the medicine bin and the medicine bin database, the falling trajectory of the past medicine particles is determined, and the monitoring space is determined according to the falling trajectory of the past medicine particles and the relative space between the medicine bin and the medicine particle carrier, which is compatible with the overall consideration of the falling trajectory of the past medicine particles and the relative space between the medicine bin and the medicine particle carrier, ensuring the accuracy of the monitoring space.

[0046] At this time, the current position information of the medicine bin is used to retrieve relevant historical data in the medicine bin database, especially the falling trajectory of the past medicine particles; at this time, the medicine bin database is a system that stores historical data about the medicine bin and its related operations (such as particle falling, discharging, etc.); after determining the current position of the medicine bin, the system will search for matching or similar records in the database according to this position information, which contains the trajectory data of the particles falling from the medicine bin under different conditions (such as different particle types, different operation parameters, etc.).

[0047] From the retrieved historical data, the most similar or closest drug particle falling trajectory to the current condition is selected; at this time, this usually involves comparing and analyzing the retrieved data; the system will evaluate the similarity of each record to the current condition according to the pre-set rules or algorithms, which take into account particle type, hopper type, operating parameters (such as discharge speed, vibration frequency, etc.) and environmental factors (such as temperature, humidity, etc.); finally, the system will select the most similar or closest falling trajectory to the current condition as a reference.

[0048] According to the previous drug particle falling trajectory and the relative spatial relationship between the hopper and the drug particle carrying table, a monitoring space for monitoring particle discharge is determined; at this time, first, the system will predict the area and range of particle falling under the current conditions according to the falling trajectory data; then, combined with the relative spatial relationship (such as distance, direction, etc.) between the hopper and the carrying table, a monitoring space containing the predicted area is determined, which should be large enough to cover all particle landing points, but not too large to avoid unnecessary computational burden and false positives.

[0049] Specifically, the current position of the hopper has been determined to be (x=500, y=600, z=1000) through S111 and S112 steps, and the position information of the drug particle carrying table directly related to the hopper has been collected as (x=500, y=600, z=900); at the same time, a hopper database containing particle falling trajectory data under multiple conditions has also been established.

[0050] In S113 step, first, according to the current position information of the hopper, the historical data related to it is retrieved in the database; suppose a record very close to the current condition is found, which describes the falling trajectory of particles in the same type of hopper when discharging the same type of particles, the record shows that the particles fall from the outlet of the hopper along the z-axis direction for about 100 units (matching the height difference with the carrying table), and form a specific accumulation pattern on the carrying table; next, combined with the relative spatial relationship between the hopper and the carrying table, a monitoring space for monitoring particle discharge is determined; in this example, the monitoring space is defined as a cylindrical region with the carrying table as the center and a radius R, where R is determined according to the diffusion degree of the particle falling trajectory and the size of the carrying table, this monitoring space will be used in subsequent particle discharge simulation and real-time monitoring to ensure that the particles can accurately fall on the carrying table and avoid the accumulation or leakage of particles.

[0051] In an embodiment of the present application, a falling trajectory parameter matching table is collected to record records similar to the current position in the hopper database and their related parameters; the falling trajectory parameter matching table is shown in Table 1:

[0052] Table 1 Falling trajectory parameter matching table

[0053]

[0054] Reference Figure 3 In step S12, in the dynamic detection of the monitoring space, the falling event of each drug particle is determined according to the position node of each drug particle in the drug cartridge in the falling process, the time, and the specification of the drug particle;

[0055] In the specific implementation of the present application, the specific steps are as follows:

[0056] S121: dynamically detecting the monitoring space, and marking each drug particle discharged through the discharge port of the drug cartridge based on the dynamic detection of the monitoring space, determining the position node of each drug particle in the falling process according to the marked spatial position of each drug particle, so as to collect the position node of each drug particle in the falling process;

[0057] S122: among the drug particles, the predicted trajectory of the drug particle is determined based on the connection of the plurality of position nodes of the drug particle;

[0058] S123: collecting the particle carrying capacity of the drug particle carrying table, and determining the falling event of each drug particle based on the predicted trajectory of the plurality of drug particles, the specification of the plurality of drug particles, and the particle carrying capacity of the drug particle carrying table;

[0059] In the embodiment of the present application, the monitoring space is dynamically detected, and each drug particle discharged through the discharge port of the drug cartridge is marked based on the dynamic detection of the monitoring space, the position node of each drug particle in the falling process is determined according to the marked spatial position of each drug particle, so as to collect the position node of each drug particle in the falling process.

[0060] At this time, the changes in the monitoring space are monitored in real time, especially the movement of the drug particles after being discharged from the discharge port of the drug cartridge; at the same time, this usually involves continuous capturing or scanning of the monitoring space using high-speed cameras, laser scanners or other types of sensors, which can record images or data in the space at a high frequency, thereby capturing the dynamic changes of the drug particles.

[0061] Each drug particle discharged from the discharge port of the drug cartridge is uniquely identified for subsequent tracking and analysis; at this time, after capturing the image or data of the drug particle, image processing techniques (such as edge detection, object recognition, etc.) or sensor data analysis methods are used to mark each particle, which is realized by assigning a unique ID to each particle or distinguishing the particles by some characteristics (such as shape, size, color, etc.).

[0062] Record the key positions of each drug particle during the falling process, these position nodes will be used for subsequent trajectory prediction and analysis; At this time, based on the labeled drug particles, use object tracking algorithms in image processing techniques or time series analysis of sensor data to determine the position of the particles at different time points, these position information is recorded as position nodes, each node contains the spatial coordinates and timestamp of the particle.

[0063] Collect the position node information of all drug particles for subsequent processing and analysis; At this time, the determined position node information is stored in a database or data file, which usually includes the ID of the particle, the spatial coordinates of each position node, the timestamp, etc., so that these data can be accessed at any time for further analysis or visualization.

[0064] Further, among the various drug particles, the predicted trajectory of the drug particle is determined based on the connection of the multiple position nodes of the drug particle, which is compatible with the overall consideration of the connection of the multiple position nodes of the drug particle, and ensures the accuracy of the predicted trajectory of the drug particle.

[0065] At this time, the multiple position node information of each drug particle is obtained from the previous step (such as S121), which is the basis for determining the predicted trajectory of the particle; At this time, the position node information usually contains the ID of the particle, the spatial coordinates (such as x, y, z) of each node and the corresponding timestamp, which are stored in a database or data structure for subsequent processing.

[0066] Select the appropriate trajectory prediction algorithm according to the motion characteristics and accuracy requirements of the drug particles; At this time, the trajectory prediction algorithm includes but is not limited to linear interpolation, polynomial fitting, Bezier curve fitting, Kalman filtering or machine learning algorithms (such as time series analysis, neural networks); The selection of the algorithm should be based on the smoothness, speed change, acceleration of the particle motion, and the demand for prediction accuracy.

[0067] Configure the necessary parameters for the selected trajectory prediction algorithm and initialize it; At this time, this involves setting the number of interpolation points, the order of the polynomial, the noise parameters of the Kalman filter, etc.; In addition, the data structures required by the algorithm need to be initialized, such as matrices, vectors, etc.

[0068] Use the collected position node information to calculate the predicted trajectory of the particle by the trajectory prediction algorithm; At this time, the position node information is input into the algorithm, and the algorithm calculates the predicted position of the particle at different time points according to the spatial coordinates and timestamps of the nodes, and these predicted positions are connected to form the predicted trajectory of the particle.

[0069] The accuracy of the predicted trajectory is evaluated and adjusted as needed; at this time, this is achieved by comparing with the actual observed particle motion trajectory; if there is a significant difference between the predicted trajectory and the actual trajectory, the algorithm parameters need to be adjusted or a more suitable algorithm needs to be selected; in addition, statistical methods (such as mean square error, correlation coefficient, etc.) are also used to quantify the accuracy of the predicted trajectory.

[0070] Specifically, the medicine bin continuously discharges small circular particles; in step S121, the position node information of these particles has been collected through high-speed cameras and image processing technology; now, in step S122, the predicted trajectory of the particles will be determined based on this information; first, extract the position node information of each particle from the database; then, considering that the motion of the particles is generally smooth and the speed change is not large, choose to use quadratic polynomial fitting as the trajectory prediction algorithm.

[0071] Next, configure the parameters of the polynomial fitting, such as the order of the fitting (choose quadratic here) and the number of interpolation points (determined according to the density of the position nodes and the accuracy requirements); then, initialize the data structures required by the algorithm, such as the matrix used to store the fitting coefficients; now, execute the polynomial fitting algorithm; for each particle, input the spatial coordinates and timestamps of the position nodes into the algorithm, which calculates the predicted positions of the particles at different time points, and these predicted positions are connected to form the predicted trajectory of the particles; finally, verify the accuracy of the predicted trajectory; by comparing with the actual observed particle motion trajectory, it is found that the predicted trajectory is very close to the actual trajectory, which indicates that the algorithm selection and parameter configuration are reasonable.

[0072] Therefore, the particle carrying capacity of the medicine particle carrying table is collected, and the falling events of each medicine particle are determined based on the predicted trajectories of multiple medicine particles, the specifications of multiple medicine particles, and the particle carrying capacity of the medicine particle carrying table, which is compatible with the overall consideration of the predicted trajectories of multiple medicine particles, the specifications of multiple medicine particles, and the particle carrying capacity of the medicine particle carrying table, and ensures the accuracy of the falling events of each medicine particle.

[0073] At this time, the number or mass of the particles currently accumulated on the medicine particle carrying table is obtained in real time or periodically to understand the load situation of the carrying table; at this time, this is achieved in various ways, such as using a weight sensor to directly measure the total weight on the carrying table, or calculating the coverage area or number of particles on the carrying table through image processing technology; if the particles are uniformly distributed, and the mass or volume of each particle is known, then the total weight or coverage area is converted into the number or mass of particles.

[0074] The predicted trajectory of each drug particle calculated in the previous step (e.g., S122) is used to analyze the particle's falling behavior; at this point, these predicted trajectories are usually stored in time series, containing the particle's spatial position information at different time points; in order to analyze whether the particle successfully landed on the carrier table, the predicted trajectories need to be compared with the position information of the carrier table.

[0075] The particle's specifications, such as shape, size, and mass, are considered because these factors affect the particle's falling behavior and packing method; at this point, the particle's specifications are usually obtained during production or testing; when analyzing the particle's falling event, these factors need to be considered because they affect the particle's resistance in the air, falling speed, and packing density, etc.

[0076] Based on the carrier table's particle carrying capacity, the particle's predicted trajectory, and the particle's specifications, it is determined whether each particle successfully landed on the carrier table and their packing method; at this point, this is achieved by comparing the predicted trajectory with the position information of the carrier table; if the end point of the predicted trajectory falls within the range of the carrier table, and the carrier table's particle carrying capacity has not reached the maximum value (or the preset threshold), it is considered that the particle has successfully fallen; in addition, the particle's packing is also judged to be uniform, overlapping, or voided, etc., according to the particle's specifications and packing method.

[0077] Specifically, the medicine bin continuously discharges small circular particles, which are collected on a drug particle carrier table; in the S122 step, the predicted trajectory of each particle has been calculated; now, in the S123 step, the particle carrying capacity on the carrier table is first collected by the weight sensor; assuming the maximum carrying capacity of the carrier table is 1000 grams, and the current carrying capacity is 800 grams; then, the predicted trajectory of each particle is obtained and compared with the position information of the carrier table; for example, it is found that the end point of a particle's predicted trajectory falls within the range of the carrier table, and its falling time does not conflict with other particles (i.e., no other particles fall at the same time and block its path).

[0078] Then, the particle's specifications are considered; in this example, all particles are circular particles of the same size and mass, so it is considered that their falling behavior and packing method are similar; finally, the particle's falling event is determined; since the end point of the predicted trajectory falls within the range of the carrier table, and the carrier table's particle carrying capacity has not reached the maximum value, it is determined that the particle has successfully fallen, and it is added to the current carrying capacity of the carrier table (i.e., the carrying capacity is updated to 800 grams + the mass of the particle); through this example, it can be seen that each sub-step in the S123 step is interrelated and interdependent; they together constitute a complete process for determining the drug particle's falling event based on the particle's predicted trajectory, particle specifications, and carrier table carrying capacity.

[0079] In an embodiment of the present application, a falling event matching table is collected, as shown in Table 2:

[0080] Table 2 Falling event matching table

[0081]

[0082] Reference Figure 4 In step S13, the falling trajectory of each drug relative to the drug bin is determined based on the detection of the falling event of each drug particle, and the simulation picture of the drug particle dropping is determined according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space;

[0083] In the specific implementation of the present application, the specific steps are as follows:

[0084] S131: Collect the falling event of each drug particle, and determine the falling trajectory of each drug particle relative to the drug bin according to the falling event of each drug particle and the specification of each drug particle;

[0085] S132: In the monitoring space, the falling trajectory of each drug particle relative to the drug bin is presented in different color trajectory lines;

[0086] S133: Determine the hierarchical image corresponding to each time node based on the multiple trajectory lines and the time node of the monitoring space, and determine the simulation picture of the drug particle dropping according to the each time node, the multiple hierarchical images and the corresponding trajectory lines.

[0087] In the embodiment of the present application, the falling event of each drug particle is collected, and the falling trajectory of each drug particle relative to the drug bin is determined according to the falling event of each drug particle and the specification of each drug particle, which is compatible with the overall consideration of the falling event of each drug particle and the specification of each drug particle, and ensures the accuracy of the falling trajectory of each drug particle relative to the drug bin.

[0088] At this time, the entire process of each drug particle being discharged from the drug bin and falling to the carrier table (or other target position) is recorded, including whether it successfully falls, the falling time, position, and other information; At this time, this usually relies on high-precision sensors or cameras and other monitoring equipment, which can monitor and record the motion state of the particles in real time; For example, a high-speed camera is used to capture the falling process of the particles, or an infrared sensor is used to detect the passing of the particles; The collected falling event data needs to be accurately recorded and stored in a computer system for subsequent analysis and processing.

[0089] Based on the collected falling event data and particle specification information, the complete motion trajectory of each particle from the discharge of the cartridge to the final falling is calculated; at the same time, the particle specification includes the shape, size, density and other physical characteristics of the particle, which will affect the motion state of the particle in the air (such as speed, direction, etc.);

[0090] Trajectory calculation: use physical models (such as Newton's second law, air resistance model, etc.) or machine learning algorithms (such as neural networks, support vector machines, etc.) to calculate the trajectory of the particle, which needs to input the initial state of the particle (such as position, speed), specification information and external environmental parameters (such as gravity acceleration, air density, etc.), and then output the position information of the particle at each time point; the calculated trajectory is usually represented in the form of a series of spatial coordinate points, which are connected to form the falling trajectory of the particle.

[0091] Further, in the monitoring space, the falling trajectory of each drug particle relative to the cartridge is presented in different colored trajectory lines.

[0092] At this time, the presentation range of the particle falling trajectory is clear, which is usually a three-dimensional or two-dimensional space region, including the cartridge, the particle falling path and the landing point (such as the loading table); at this time, the size and shape of the monitoring space should be determined according to the actual production line layout to ensure that the falling trajectories of all particles can be captured completely.

[0093] From the previous step (such as S131), the falling trajectory data of each drug particle relative to the cartridge has been calculated, which is usually a series of spatial coordinate points representing the position of the particle at different time points. At the same time, in order to distinguish different particle trajectories, a unique color needs to be assigned to each particle; the color scheme is based on the gradient color of the rainbow color band, and it is also a fixed set of colors that are used in a cycle; the color should have enough contrast to visually distinguish different trajectories clearly.

[0094] In the monitoring space, the corresponding trajectory lines are drawn according to the falling trajectory data of the particles; at this time, the trajectory line drawing is realized by using graphic drawing software or programming library (such as MATLAB, Python's matplotlib or Plotly, etc.); when drawing, each coordinate point in the trajectory data needs to be connected to form a smooth curve or polyline; according to the color scheme selected in sub-step 3, the trajectory line of each particle is assigned a corresponding color.

[0095] The drawn trajectory lines are presented in the monitoring space for visual analysis and observation; the presentation mode is a static image or a dynamic animation; the animation can more intuitively show the falling process of the particles; according to the needs, interactive functions such as mouse hovering to display trajectory information, zooming in and out to view details, etc.

[0096] Specifically, the medicine bin continuously discharges different specifications of medicine particles; the falling trajectory data of each particle relative to the medicine bin has been calculated through the previous step (such as S131);

[0097] In the S132 step, the monitoring space is first determined, which is a three-dimensional area containing the medicine bin, the particle falling path, and the bearing table; then, the falling trajectory data of the particles are obtained from the S131 step, which contains the spatial coordinates of each particle at different time points; next, a gradient color scheme based on a rainbow color band is selected, and each particle is assigned a unique color, so that even if multiple particle trajectories overlap in space, they can be distinguished by color.

[0098] Then, the matplotlib library of Python is used to draw the trajectory lines; each coordinate point in the trajectory data is connected to form a smooth curve; at the same time, each trajectory line is assigned a corresponding color according to the color scheme; finally, the drawn trajectory lines are presented in the form of a three-dimensional animation; in the animation, different colored trajectory lines are seen falling from the medicine bin opening to the bearing table along different paths; by observing the animation, the falling process of each particle and their relative positional relationship can be intuitively understood.

[0099] Therefore, based on the multiple trajectory lines and the time node of the monitoring space, the hierarchical images corresponding to each time node are determined, and the simulation picture of the medicine particle falling is determined according to each time node, multiple hierarchical images, and corresponding trajectory lines, which is compatible with the overall consideration of each time node, multiple hierarchical images, and corresponding trajectory lines, ensuring the accuracy of the simulation picture of the medicine particle falling, and at the same time, the overall consideration of the falling trajectory of each medicine and the detection space is compatible, ensuring the accuracy of the simulation picture of the medicine particle falling.

[0100] At this time, in order to generate a continuous simulation picture, a series of time nodes need to be determined, which will be used to extract information of corresponding positions from the trajectory lines; at this time, the selection of time nodes should be determined according to the falling speed of particles and the required simulation accuracy; for example, if the particle falling speed is fast and high-precision simulation picture is required, shorter time intervals should be selected; conversely, if the particle falling speed is slow and the simulation accuracy requirement is not high, longer time intervals should be selected.

[0101] At each time node, a two-dimensional or three-dimensional image representing the current position of the particles is generated based on the trajectory lines of all particles. This image is called a level image. At this time, the generation of the level image usually involves converting the position information of the trajectory lines at each time node into pixel points on the image, which is achieved through graphics drawing software or programming libraries such as matplotlib, Plotly, or three-dimensional graphics libraries (such as VTK, OpenGL, etc.) in Python. When generating the image, the size, shape, and color of the particles need to be considered to ensure that the image accurately reflects the actual state of the particles.

[0102] The level images at multiple time nodes are combined in chronological order to form a dynamic simulation picture. At this time, this usually involves converting the level images into video frames and using video editing software or programming libraries (such as FFmpeg, OpenCV, etc.) to combine them into a coherent video. During the combination process, it is necessary to ensure smooth transitions between frames to avoid jumps or stalls.

[0103] In the simulation picture, in addition to the current position of the particles represented by the level image, trajectory lines need to be added to represent the motion path of the particles. At this time, the addition of trajectory lines is achieved by drawing lines on the video frames, which requires calculating the starting and ending points of the lines based on the trajectory data of the particles at each time node, and connecting them using appropriate drawing functions. In order to maintain the continuity of the trajectory, interpolation algorithms (such as linear interpolation, Bezier curve, etc.) are used to smoothly connect the position points at adjacent time nodes.

[0104] The simulation picture is optimized to improve its visual effect and readability, and the final simulation result is output. At this time, optimization includes adjusting image brightness, contrast, color saturation, and other parameters, as well as adding annotations, labels, or scales, and other auxiliary information. The output is in the format of a video file, GIF animation, or a series of static images, depending on application requirements and user preferences.

[0105] Specifically, the medicine warehouse continuously discharges medicine particles of different specifications and colors. The falling trajectory data and color information of the particles have been obtained through previous steps (such as S131 and S132). In the S133 step, the time nodes are first determined, and a sampling rate of 10 frames per second is selected to capture the falling process of the particles, which means that the position information of the particles will be extracted from the trajectory lines at each time node.

[0106] Then, a hierarchy of images is generated for each time node, which are two-dimensional, with each pixel representing the position of a particle at that time node; different colors are used to represent different sizes of particles to ensure that the image can clearly reflect the actual state of the particles; Next, these hierarchical images are combined in chronological order to form a dynamic simulation picture; During the combination process, the transition between frames is smooth to avoid jumping or stuttering phenomenon; In order to more intuitively show the movement path of the particles, trajectory lines are added to the simulation picture, which connect the position points at adjacent time nodes and use the same color as the particles to represent; In order to maintain the continuity of the trajectory, a linear interpolation algorithm is used to smoothly connect these position points; Finally, the simulation picture is optimized, adjusting image brightness, contrast, color saturation and other parameters, and adding scale and annotation and other auxiliary information; Finally, the simulation results are output as a video file for subsequent analysis and display.

[0107] In an embodiment of the present application, first, a series of time nodes need to be determined, and corresponding hierarchical images are generated for each time node, which reflect the positions of all drug particles in the monitoring space at that time point; To simplify the description, a time node matching table is used to record this information; The time node matching table is shown in Table Three:

[0108] Table Three Time Node Matching Table

[0109]

[0110] To more accurately describe the importance of the state and trajectory of each particle at each time node, the concepts of weight and score are introduced; The weight is determined according to the size, speed, color and other attributes of the particle, while the score is calculated according to the weight and the position of the particle at each time node;

[0111] For each particle at each time node, the score is calculated according to its weight and position; For example, if the particle is at a key position of the trajectory (such as the starting point, turning point or end point), the score is higher; The score is calculated by the following formula: Score = Weight × Position Factor (The position factor is determined according to the position of the particle in the trajectory, for example, the factor of the key position is higher).

[0112] With the information of time nodes, hierarchical images, weights and scores, the simulation picture of drug particle dropping is determined; according to the matching table, the corresponding hierarchical image is drawn for each time node; on the hierarchical image, lines are drawn according to the trajectory data of the particles, and different colors or thicknesses are used to represent different weights or scores; the hierarchical images and trajectory lines on multiple time nodes are combined to form a dynamic simulation picture, which is realized through video editing software or programming libraries (such as FFmpeg, OpenCV, etc.).

[0113] Specifically, the final simulation picture is a video file containing the whole process from the initial state to the final stacking shape; at each time node, the trajectory lines of the particles and their positions in space are seen; by adjusting the allocation of weights and scores, the process of falling and stacking of particles of different specifications and types is more accurately simulated.

[0114] Reference Figure 5 In step S14, multiple flow velocity layers are formed based on the division of the simulation picture of drug particle dropping, and the multiple flow velocity layers are respectively a center fast layer, an inner wall slow layer and a transition velocity layer.

[0115] In the specific implementation process of the present application, the specific steps are:

[0116] S141: Collect the simulation picture of drug particle dropping, and mark the speed of each drug particle at different height positions based on the simulation picture of drug particle dropping;

[0117] S142: Form multiple speed ranges according to the classification of the speed of each drug particle at different height positions, which is related to the specifications and height positions of the drug particles;

[0118] S143: Form multiple flow velocity layers based on the multiple speed ranges and the corresponding height positions, and the multiple flow velocity layers are respectively a center fast layer, an inner wall slow layer and a transition velocity layer, the speeds of the center fast layer, the inner wall slow layer and the transition velocity layer are different, and are for different height positions.

[0119] In the embodiments of the present application, the simulation picture of drug particle dropping is collected, and the speed of each drug particle at different height positions is marked based on the simulation picture of drug particle dropping, which introduces the speed of each drug particle at different height positions.

[0120] At this time, simulation pictures containing the dynamic process of drug particle dropping are obtained, which should clearly show the movement state of particles at different height positions; at this time, professional simulation software (such as CFD simulation software, discrete element method (DEM) simulation software, etc.) is used to simulate the dropping process of drug particles; after the simulation is completed, pictures or video files containing particle motion information are exported from the software, which are usually stored in image sequences or video formats; ensure that the quality of the exported pictures is high enough to accurately identify and track particles later.

[0121] In the collected simulation pictures, the speed of each drug particle at different height positions is marked; at this time, image processing techniques (such as edge detection, threshold segmentation, template matching, etc.) are used to identify particles in the picture; track the trajectory of the identified particles, which usually involves matching the position of the particles between consecutive picture frames to form a complete motion trajectory; select different height positions as key points on the trajectory of the particles, and use the position change and time interval between adjacent key points to calculate the instantaneous speed of the particles passing through these key points; associate the calculated speed data with the corresponding height position and particle identification to form a data set, which usually involves superimposing speed markers (such as arrows, digital labels, etc.) on the simulation picture, or using an external data table to record this information.

[0122] Specifically, suppose a circular drug particle is being analyzed in a cylindrical drug bin; the diameter of the particle ranges from 2mm to 5mm, and the height of the drug bin is 1m; DEM simulation software is used to simulate this process and export a series of simulation pictures containing particle motion information; in step S141, the simulation pictures are first imported into the image processing software; then, edge detection and threshold segmentation techniques are used to identify particles in the picture; then, the identified particles are tracked to form complete motion trajectories by matching the positions of the particles in consecutive picture frames; on the basis of trajectory tracking, different height positions in the drug bin (such as 0.2m, 0.5m, 0.8m) are selected as key points; for the instantaneous speed of each particle passing through these key points, the position change and time interval between adjacent key points are used to calculate; finally, the calculated speed data is associated with the corresponding height position and particle identification, and speed arrows are superimposed on the simulation picture to represent the direction and size of the particle speed.

[0123] Further, a plurality of speed ranges are formed according to the classification of the speed of each drug particle at different height positions, which are related to the size of the drug particle and the height position, and a plurality of speed ranges are introduced.

[0124] At this time, the velocity data of each drug particle at different height positions is collected from the previous step (e.g., S141); at this time, the data integrity and accuracy are ensured, including the specifications of the particles (e.g., diameter, shape, etc.), height positions, and corresponding velocity values, which are usually stored in the form of data sets or tables, with each row representing the velocity information of a particle at a certain height position.

[0125] The collected velocity data is preprocessed to eliminate outliers, fill in missing values, etc., to ensure data quality; at this time, statistical methods (such as box plots, Z-scores, etc.) are used to detect and handle abnormal velocity values, which are caused by measurement errors or unstable factors in simulation; for missing velocity data, interpolation is used to fill in the missing values according to the trend of adjacent data points, or other reasonable estimation methods are used.

[0126] According to the specifications and height positions of the drug particles, the velocity data is divided into multiple velocity ranges; at this time, the particles are preliminarily classified according to their specifications (such as diameter size), because particles of different specifications have different velocity characteristics under the same conditions; within each specification category, the velocity is further subdivided according to the height position, because the particles are affected by gravity, air resistance, particle interaction, etc. during the falling process, resulting in a change in velocity with height; statistical methods (such as cluster analysis, histogram analysis, etc.) or empirical rules are used to determine the velocity range; cluster analysis divides the velocity data into naturally formed groups, while histogram analysis helps identify the distribution pattern of the velocity.

[0127] The classified velocity ranges are associated with the specifications and height positions of the drug particles to form a complete velocity classification system; at this time, a table or database is created, with each row representing a velocity range, including the upper and lower limits of the velocity range, the corresponding particle specifications and height position information; by comparing with actual observation data or experimental results, the accuracy and reasonableness of the velocity classification system are verified, and adjustments are made as needed.

[0128] Specifically, suppose that the falling process of a drug particle containing two specifications (large particles and small particles) in a cylindrical drug bin is being analyzed; a large amount of velocity data of particles at different height positions has been collected from the S141 step; in the S142 step, the data is preprocessed to delete abnormal velocity values caused by measurement errors, and a small amount of missing velocity data is filled in using interpolation method; next, the particles are preliminarily classified according to their specifications; for large particles and small particles, the average velocity at different height positions (such as 0.2m, 0.5m, 0.8m) is calculated, and the trend of velocity change with height is observed.

[0129] Then, the velocity data is further subdivided using clustering analysis methods; for each size of particle, according to the natural distribution of velocity values, it is divided into several speed ranges, such as "low speed", "medium speed" and "high speed", the upper and lower limits of these speed ranges are determined according to the clustering results; finally, the association table of speed range and particle size, height position is established; for example, for large particles, at the height position of 0.2m, the speed range is "low speed" (0-1 m / s), "medium speed" (1-2 m / s) and "high speed" (>2 m / s); while at the height position of 0.8m, due to the influence of air resistance and particle interaction, the speed range will be different; through this example, it can be seen that each sub-step in step S142 is interrelated, and they together constitute a complete process for classifying velocity according to the size and height position of the drug particles, and forming multiple speed ranges, which provides important basis for subsequent drug particle dropping analysis and optimization.

[0130] Therefore, based on multiple speed ranges and corresponding height positions, multiple flow velocity layers are formed, and the multiple flow velocity layers are respectively a center fast layer, an inner wall slow layer and a transition speed layer, the speeds of the center fast layer, the inner wall slow layer and the transition speed layer are different, and the center fast layer, the inner wall slow layer and the transition speed layer are introduced for different height positions.

[0131] At this time, the association between the multiple speed ranges determined in step S142 and the corresponding height positions is analyzed in depth, which is the basis for forming the flow velocity layer; at this time, the velocity classification data is reviewed, and the velocity variation trend of particles of different sizes at different heights is noted, as well as how these trends change with the change of particle size and height position.

[0132] Based on the association between the speed range and the height position, three main flow velocity layers are defined: the center fast layer, the inner wall slow layer and the transition speed layer; at this time, the center fast layer: usually located in the center of the flow region, composed of particles with faster speed, these particles have larger size or higher falling potential energy; the inner wall slow layer: close to the inner wall of the flow region, composed of particles with slower speed, these particles are affected by frictional resistance, particle interaction or boundary effect; the transition speed layer: located between the center fast layer and the inner wall slow layer, the particle speed is between the two, which is the area with the most significant speed gradient change.

[0133] The boundaries of each flow velocity layer are determined so that they can be accurately identified and distinguished in simulation pictures or actual experiments. At this time, according to the velocity range, a specific velocity threshold is set for each flow velocity layer. The particles with a velocity higher than a certain threshold belong to the central fast layer, the particles with a velocity lower than another threshold belong to the inner wall slow layer, and the particles with a velocity between the two thresholds belong to the transition velocity layer. Considering the change of velocity with height, the boundaries of the flow velocity layer are not fixed but change with the height position. Therefore, the boundaries of the flow velocity layer need to be determined for each height position.

[0134] By comparing with actual observation data or simulation results, it is verified whether the defined flow velocity layer is reasonable. At this time, the flow velocity layer markers are superimposed in the simulation picture, and whether the actual motion of the particles is consistent with the defined flow velocity layer is observed. The velocity distribution of the particles in the flow velocity layer is statistically analyzed to check whether the velocity distribution is as expected.

[0135] Specifically, it is assumed that a falling process of drug particles containing two specifications (large particles and small particles) in a cylindrical drug bin is being analyzed. In step S142, a plurality of velocity ranges have been determined, and their association with particle specifications and height positions is known. In step S143, the trend of the velocity range with height is first analyzed in depth. It is found that the velocity of large particles in the central region is generally fast, forming a central fast layer. Due to the influence of the boundary effect, the velocity of small particles near the inner wall is slow, forming an inner wall slow layer. The particles between the two form a transition velocity layer.

[0136] Next, specific flow velocity layer boundaries are defined for each height position. For example, at a height position of 0.2 m, particles with a velocity greater than 1.5 m / s are set to belong to the central fast layer, particles with a velocity less than 0.5 m / s are set to belong to the inner wall slow layer, and particles with a velocity between 0.5 m / s and 1.5 m / s belong to the transition velocity layer. These thresholds are determined according to the comprehensive consideration of the velocity range and particle specifications. Then, flow velocity layer markers are superimposed in the simulation picture to verify the reasonableness of the flow velocity layer by visual means. It is found that the actual trajectory of the particles is highly consistent with the defined flow velocity layer. The particles in the central fast layer fall quickly, the particles in the inner wall slow layer have a slow velocity, and the particles in the transition velocity layer have a velocity between the two. Finally, the velocity of the particles in each flow velocity layer is statistically analyzed to further verify the reasonableness of the flow velocity layer. The statistical results show that the velocity distribution of the particles in the central fast layer is relatively concentrated, and the velocity value is high. The velocity distribution of the particles in the inner wall slow layer is relatively dispersed, and the velocity value is low. The velocity of the particles in the transition velocity layer shows a clear gradient change.

[0137] In an embodiment of the present application, a flow velocity layer matching table is collected, which directly shows the correspondence between the velocity range, the height position, and the flow velocity layer. The flow velocity layer matching table is shown in Table Four:

[0138] Table four flow velocity layer matching table

[0139] Height position (m) Velocity range (m / s) Flow rate layer 0.2 >1.5 Central fast layer 0.2 0.5-1.5 Transition velocity layer 0.2 <0.5 Inner wall slow layer 0.5 >1.2 Central fast layer 0.5 0.4-1.2 Transition velocity layer 0.5 <0.4 Inner wall slow layer ... ... ... 0.8 >1.0 Central fast layer 0.8 0.3-1.0 Transition velocity layer 0.8 <0.3 Inner wall slow layer

[0140] In this flow velocity layer matching table, different speed ranges are listed for each height position, and these ranges are matched with the corresponding flow velocity layers; for example, at the 0.2m height position, particles with a speed greater than 1.5m / s are classified as the central fast layer, particles with a speed between 0.5-1.5m / s are classified as the transition speed layer, and particles with a speed less than 0.5m / s are classified as the inner wall slow speed layer.

[0141] Reference Figure 6 In step S15, the residual particle amount of the multiple flow velocity layers is determined according to the speed of the multiple flow velocity layers and the drug particle proportion of the multiple flow velocity layers, and the posture adjustment of the cartridge is triggered to avoid the accumulation of the cartridge after each discharge.

[0142] In the specific implementation process of the present application, the specific steps are as follows:

[0143] S151: In each flow velocity layer, the simulation picture of the flow velocity layer at the preset time point is collected, and the total amount of drug particles is determined according to the traversal of the simulation picture, and the distribution number of each type of drug particle is determined according to the total amount of drug particles and the specifications of drug particles;

[0144] S152: The drug particle proportion of the flow velocity layer is determined based on the comparison of the distribution number of each type of drug particle; the corresponding residual layer is determined based on the comparison of each flow velocity layer and the area of the cartridge, and the drug particle residual image is determined according to the tracing of the residual layer; the residual particle amount of the flow velocity layer is determined based on the detection of the drug particle residual image;

[0145] S153: The residual layer with the maximum residual particle amount is determined according to the residual particle amount of each flow velocity layer and the height position of each flow velocity layer, and the residual position of the drug particles is determined based on the detection of the residual layer with the maximum residual particle amount; the posture adjustment of the cartridge is triggered according to the residual position of the drug particles and the flow velocity of the flow velocity layer corresponding to the current posture of the cartridge, so that the current posture of the cartridge changes, and the accumulation of the drug particles at the residual position of the drug particles is gradually controlled.

[0146] In the embodiments of the present application, in each flow velocity layer, the simulation picture of the flow velocity layer at the preset time point is collected, and the total amount of drug particles is determined according to the traversal of the simulation picture, and the distribution number of each type of drug particle is determined according to the total amount of drug particles and the specifications of drug particles, which is compatible with the overall consideration of the total amount of drug particles and the specifications of drug particles, and ensures the accuracy of the distribution number of each type of drug particle.

[0147] At this time, in each flow velocity layer, the simulation picture at the preset time point is obtained for subsequent analysis; at this time, using simulation software or simulation tools, the picture of the flow velocity layer is captured at the preset time point (such as a period of time after the particle flow is stable); ensure that the picture is clear and can accurately reflect the distribution and quantity of particles; the picture should contain enough details for subsequent identification and counting of particles.

[0148] By traversing the simulation picture, the total quantity of drug particles in the flow velocity layer is calculated; at this time, using image processing techniques such as edge detection, binarization, etc., separate the particles in the picture from the background; traverse the processed picture to identify and count each particle; accumulate the number of all identified particles to obtain the total quantity of particles in the flow velocity layer.

[0149] According to the total quantity and specifications of the particles, determine the distribution quantity of each type of drug particles; at this time, classify the identified particles, and according to the specifications (such as size, shape), classify the particles into different categories; count the particles in each category to obtain the distribution quantity of each type of particle; further analyze the spatial distribution of each type of particle in the flow velocity layer, such as uniformity, aggregation, etc.

[0150] Specifically, assume that a drug bin flow situation containing two types of particles (large particles and small particles) is being analyzed; after the drug bin flow is stable for a period of time, the simulation software captures the pictures of the center fast layer, the transition velocity layer and the inner wall slow layer at the preset time point; the picture is clear and can accurately reflect the distribution and quantity of particles; perform image processing on the captured picture using edge detection and binarization techniques to separate the particles from the background; traverse the processed picture to identify and count each particle; for example, in the center fast layer, 1000 large particles and 800 small particles are identified and counted, so the total quantity of particles in this layer is 1800.

[0151] Classify the identified particles into two categories: large particles and small particles; count the particles in each category to obtain the distribution quantity of each type of particle; for example, in the center fast layer, the distribution quantity of large particles is 1000, and the distribution quantity of small particles is 800; further analysis shows that large particles are uniformly distributed in the center fast layer, while small particles have a certain aggregation, which is of great significance for subsequent drug bin design and optimization; through the above example, it can be seen that each sub-step in S151 is interrelated, and they together constitute a complete process for determining the total quantity and distribution quantity of drug particles in each flow velocity layer, which provides important basic data for subsequent drug bin flow analysis and optimization.

[0152] Further, the proportion of drug particles in the flow rate layer is determined based on the comparison of the distribution quantities of various types of drug particles; the corresponding residual layer is determined based on the comparison of each flow rate layer and the area of the cartridge; and the drug particle residual image is determined according to the tracing of the residual layer; the residual particle quantity of the flow rate layer is determined based on the detection of the drug particle residual image, thereby ensuring the accuracy of the residual particle quantity of the flow rate layer.

[0153] At this time, by comparing the distribution quantities of various types of drug particles, the proportion of each type of particle in a certain flow rate layer is determined; at this time, the distribution quantity data of various types of drug particles in each flow rate layer is collected; the data is normalized, that is, the proportion of the number of each type of particle to the total number of particles in the flow rate layer is calculated;

[0154] The proportion data is analyzed to understand the distribution of particle types in different flow rate layers.

[0155] By comparing each flow rate layer and the overall area of the cartridge, the flow rate layer with the most significant particle accumulation, that is, the residual layer, is identified; at this time, the particle flow situation of each flow rate layer is analyzed, especially the accumulation and retention of particles; in combination with the structural characteristics of the cartridge, the area where particles are prone to accumulate is identified; based on the above information, the position of the residual layer is determined.

[0156] The history simulation picture of the residual layer is traced back to extract the drug particle residual image; at this time, the picture of the residual layer at the key time point is found and extracted in the simulation software; the extracted picture is pre-processed, such as denoising and contrast enhancement, to more clearly display the particle residual situation;

[0157] The processed picture is saved as a drug particle residual image.

[0158] Based on the drug particle residual image, the particle quantity of the residual layer is detected and determined; at this time, the residual image is processed using image processing techniques (such as particle recognition algorithms) to identify and count the residual particles; based on the recognition results of the particles, the total number or total area of the residual particles (depending on whether the particle size is uniform) is calculated; the trend of the residual particle quantity is analyzed to provide a basis for subsequent adjustment and optimization.

[0159] Specifically, suppose a cartridge containing three types of particles (large, medium, and small) is being analyzed for flow situation, and the data collection of step S151 has been completed; the distribution quantity data of various types of particles in the center fast layer, the transition speed layer, and the inner wall slow layer has been collected; for example, in the center fast layer, large particles account for 30%, medium particles account for 40%, and small particles account for 30%; by comparing these data, the distribution of particle types in different flow rate layers is understood.

[0160] In the analysis of the particle flow, it is found that the particle accumulation in the inner wall slow layer is most significant, especially in some corners and bends of the cartridge; combined with the structural characteristics of the cartridge, the inner wall slow layer is determined to be the residual layer; the pictures of the inner wall slow layer at key time points are found and extracted in the simulation software; the extracted pictures are preprocessed to enhance the contrast, so that the particle residual situation can be displayed more clearly; the processed pictures are saved as the drug particle residual images.

[0161] The residual images are processed using a particle recognition algorithm to identify and count the residual particles; for example, in the residual image, 500 large particles, 800 medium particles and 300 small particles are identified; according to the identification results, the total number of residual particles (1600) and the proportion of the number of each type of particle are calculated; by analyzing the change trend of the residual particle amount, the main area and trend of particle accumulation are found, which provides a basis for subsequent adjustment and optimization; for example, the structure of the cartridge needs to be adjusted or the particle feeding method needs to be changed to reduce the accumulation of particles in the inner wall slow layer; as illustrated by the above examples, each sub-step in step S152 is interrelated, and they together constitute a complete process for determining the location of the residual layer, extracting the residual image and detecting the residual particle amount, which provides important basic data for subsequent cartridge flow analysis and optimization.

[0162] Therefore, the residual layer with the maximum residual particle amount is determined according to the residual particle amount of each flow velocity layer and the height position of each flow velocity layer, and the residual position of the drug particles is determined based on the detection of the residual layer with the maximum residual particle amount, and the flow velocity of the flow velocity layer corresponding to the current posture of the cartridge triggers the posture adjustment of the cartridge according to the residual position of the drug particles and the current posture of the cartridge, so that the current posture of the cartridge changes and gradually controls the accumulation of drug particles at the residual position of the drug particles, which is compatible with the overall consideration of the speed of multiple flow velocity layers and the proportion of drug particles in multiple flow velocity layers, ensures the accuracy of the residual particle amount of multiple flow velocity layers, and triggers the posture adjustment of the cartridge to optimize the residual particle amount of multiple flow velocity layers, avoiding the accumulation of the cartridge after each discharge.

[0163] At this time, by comparing the residual particle amounts of each flow velocity layer, the flow velocity layer with the maximum residual particle amount is found; at this time, the residual particle amount data of each flow velocity layer is summarized; by comparing the data, the flow velocity layer with the maximum residual particle amount is found, which is the residual layer that needs to be focused on.

[0164] In the flow velocity layer with the maximum residual particle amount, the specific residual position of the drug particles is determined; at this time, the residual particle image or simulation data of the flow velocity layer is analyzed to identify the area where the particles are aggregated or accumulated; combined with the structural characteristics of the cartridge, the specific position of the particle residual is determined.

[0165] According to the residual position of the drug particles and the flow velocity of the flow velocity layer corresponding to the current posture of the cartridge, the posture of the cartridge is adjusted to change the flow path of the particles; at this time, the flow velocity distribution of each flow velocity layer under the current posture of the cartridge is analyzed; according to the residual position and the flow velocity distribution, the direction and degree of adjusting the posture of the cartridge are determined, such as the inclination angle, the rotation angle, etc.; the posture adjustment mechanism of the cartridge is triggered to change the posture of the cartridge.

[0166] By continuously observing the flow of particles after the posture adjustment of the cartridge, the posture of the cartridge is gradually adjusted to reduce or eliminate the accumulation of drug particles; at this time, after the posture adjustment of the cartridge, the flow of particles is continuously observed; according to the observation results, the posture of the cartridge is gradually fine-tuned until the ideal particle distribution state is reached; the key parameters and effects in the adjustment process are recorded to provide a reference for subsequent cartridge design and optimization.

[0167] Specifically, it is assumed that in the S152 step, the inner wall slow layer is determined to be the flow velocity layer with the largest amount of residual particles, and the residual particle image is extracted; the residual particle amount data of each flow velocity layer is summarized, and it is found that the residual particle amount of the inner wall slow layer is the largest, reaching 1200; therefore, it is determined that the inner wall slow layer is the residual layer that needs to be focused on.

[0168] The residual particle image of the inner wall slow layer is analyzed, and it is found that the particles mainly accumulate in the bottom corners and curved parts of the cartridge; combined with the structural characteristics of the cartridge, the specific position of the particle accumulation is determined. The flow velocity distribution of each flow velocity layer under the current posture of the cartridge is analyzed, and it is found that the flow velocity of the inner wall slow layer is low, and the particles are easy to accumulate; in order to change the flow path of the particles, it is decided to adjust the inclination angle of the cartridge to increase the flow velocity of the inner wall slow layer; the posture adjustment mechanism of the cartridge is triggered to tilt the cartridge to a certain angle on one side.

[0169] After the posture adjustment of the cartridge, the flow of particles is continuously observed; it is found that after the adjustment of the inclination angle, the flow velocity of the particles in the inner wall slow layer has increased, but part of the particles still accumulate in the bottom corners; therefore, the inclination angle and the rotation angle of the cartridge are gradually fine-tuned until the distribution of the particles in the cartridge is more uniform; the key parameters and effects in the adjustment process are recorded, and it is found that when the inclination angle of the cartridge is 15 degrees and the rotation angle is 30 degrees, the accumulation of the particles is significantly improved; through the above example, it is seen that each sub-step in the S153 step is interrelated, and they together constitute a complete process for determining the residual layer, the residual position, triggering the posture adjustment of the cartridge, and gradually controlling the accumulation of particles, which provides an important reference for subsequent cartridge design and optimization.

[0170] In an embodiment of the present application, it is assumed that there are three flow rate layers: A (low height), B (medium height), and C (high height), and the residual particle amount of each flow rate layer has been obtained through the previous steps; a residual particle amount matching table is created, as shown in Table 5:

[0171] Table 5 Residual particle amount matching table

[0172]

[0173] As can be seen from the residual particle amount matching table, the residual particle amount of flow rate layer B is the largest, so layer B is the residual layer that needs attention. Assuming that through residual particle image analysis, it is found that the particles in layer B mainly accumulate in a certain specific area (for example, the bottom corner) of the hopper, and this area is the residual position; according to the flow rate of the flow rate layer corresponding to the residual position and the current posture of the hopper, it is determined to adjust the posture of the hopper; for example, if the hopper is currently horizontal, it is determined to tilt it slightly to increase the flow rate of layer B and help the particles flow; after adjusting the posture of the hopper, the flow of the particles is continuously observed, and the posture of the hopper is gradually fine-tuned as needed until the accumulation of the particles is improved.

[0174] Please refer to Figure 7 , Figure 7 which is a structural composition diagram of a particle discharging simulation system of a hopper in an embodiment of the present application; the particle discharging simulation system of the hopper comprises:

[0175] a monitoring space module 21, configured to determine a monitoring space according to a current position of the hopper and a falling trajectory of a drug particle in the past;

[0176] a falling event module 22, configured to determine a falling event of each drug particle according to a position node, a time, and a specification of the drug particle in a falling process of each drug particle in the hopper in dynamic detection of the monitoring space;

[0177] a simulation picture module 23, configured to determine a falling trajectory of each drug particle relative to the hopper based on detection of the falling event of each drug particle, and determine a simulation picture of the drug particle discharging based on the falling trajectory of each drug particle relative to the hopper and a falling simulation of the monitoring space;

[0178] a flow rate layer module 24, configured to form a plurality of flow rate layers based on division of the simulation picture of the drug particle discharging, and the plurality of flow rate layers are respectively a center fast layer, an inner wall slow layer, and a transition speed layer;

[0179] a posture adjustment module 25, configured to determine a residual particle amount of the plurality of flow rate layers according to a speed of the plurality of flow rate layers and a proportion of the drug particles in the plurality of flow rate layers, and trigger adjustment of a posture of the hopper to avoid accumulation of the hopper after each discharging.

[0180] Any combination of the technical features of the above embodiments is possible, and for the sake of brevity, not all possible combinations are described. However, it is to be understood that any combination of the technical features is possible and within the scope of the disclosure.

Claims

1. A simulation method for particle dropping in a medicine bin, characterized in that: include: Determine the monitoring space based on the current position of the drug warehouse and the previous falling trajectory of the drug particles; In the dynamic detection of the monitoring space, the falling events of each drug particle in the drug bin are determined according to the position node, time and specifications of each drug particle during the falling process; Determining the falling trajectory of each drug relative to the drug bin based on the detection of the falling events of each drug particle, and determining a simulated image of the drug particle falling according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space; Based on the division of the simulation screen of drug particle falling, multiple flow velocity layers are formed, including a central fast layer, an inner wall slow layer and a transition velocity layer; The residual particle amount of multiple flow rate layers is determined according to the speed of multiple flow rate layers and the proportion of drug particles in multiple flow rate layers, and the posture adjustment of the medicine warehouse is triggered to avoid material accumulation in the medicine warehouse after each discharge, including: in each flow rate layer, collecting the simulation picture of the flow rate layer at a preset time point, and determining the total amount of drug particles based on the traversal of the simulation picture, and determining the distribution quantity of each type of drug particles based on the total amount of drug particles and the specifications of the drug particles; determining the proportion of drug particles in the flow rate layer based on the comparison of the distribution quantity of each type of drug particles; determining based on the regional comparison of each flow rate layer and the medicine warehouse The corresponding residual layer is determined, and the residual image of the drug particles is determined based on the tracing of the residual layer, and the residual particle amount of the flow rate layer is determined based on the detection of the residual image of the drug particles; the residual layer with the maximum residual particle amount is determined according to the residual particle amount of each flow rate layer and the height position of each flow rate layer, and the residual position of the drug particles is determined based on the detection of the residual layer with the maximum residual particle amount, and the posture adjustment of the drug warehouse is triggered according to the residual position of the drug particles and the flow velocity of the flow velocity layer corresponding to the current posture of the drug warehouse, so that the current posture of the medicine warehouse is changed, and the accumulation of drug particles at the residual position of the drug particles is gradually regulated.

2. The simulation method for particle dropping of a medicine bin according to claim 1, characterized in that: The method of determining the monitoring space based on the current position of the medicine bin and the previous falling trajectory of the medicine particles includes: In the drug testing room, the drug warehouse is positioned and detected based on the camera in the drug testing room, and the current image of the drug warehouse is collected. The current position of the drug warehouse is determined based on the matching of the current image of the drug warehouse and the indoor distribution map of the drug testing room; Based on the peripheral detection of the current position of the medicine warehouse, the corresponding medicine particle carrying platform is collected, and the relative space between the medicine warehouse and the medicine particle carrying platform is determined based on the spatial comparison between the medicine warehouse and the medicine particle carrying platform; The previous falling trajectory of the drug particles is determined based on the current position of the drug bin and the drug bin database, and the monitoring space is determined according to the previous falling trajectory of the drug particles and the relative space between the drug bin and the drug particle carrying platform.

3. The simulation method for particle dropping of a medicine bin according to claim 1, characterized in that: In the dynamic detection of the monitoring space, the falling events of the respective drug particles in the drug bin are determined according to the position nodes, time and specifications of the drug particles during the falling process, including: Dynamic detection is performed on the monitoring space, and based on the dynamic detection of the monitoring space, each drug particle discharged through the discharge port of the drug bin is marked, and a position node of each drug particle during the falling process is determined according to the spatial position of the mark of each drug particle, so as to collect the position node of each drug particle during the falling process; In each drug particle, a predicted trajectory of the drug particle is determined based on connections of a plurality of position nodes of the drug particle; The particle carrying capacity of the drug particle carrying platform is collected, and the falling event of each drug particle is determined based on the predicted trajectories of the multiple drug particles, the specifications of the multiple drug particles, and the particle carrying capacity of the drug particle carrying platform.

4. The method for simulating particle dropping from a medicine bin according to claim 1, characterized in that: The method of determining the falling trajectory of each drug relative to the drug bin based on the detection of the falling events of each drug particle, and determining the simulation screen of the drug particle falling according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space, includes: The falling events of each drug particle are collected, and the falling trajectory of each drug particle relative to the drug bin is determined according to the falling events of each drug particle and the specifications of each drug particle.

5. The method for simulating particle dropping from a medicine bin according to claim 4, characterized in that: Based on the detection of the falling events of each drug particle, the falling trajectory of each drug relative to the drug bin is determined, and according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space, a simulation picture of the drug particle falling is determined, which also includes: In this monitoring space, the falling trajectory of each drug particle relative to the drug bin is presented as trajectory lines of different colors; Based on multiple trajectory lines and time nodes of the monitoring space, the hierarchical image corresponding to each time node is determined, and the simulation picture of the drug particle falling is determined according to each time node, the multiple hierarchical images and the corresponding trajectory lines.

6. The method for simulating particle dropping from a medicine bin according to claim 1, characterized in that: The division of the simulation screen based on the drug particle falling is used to form multiple flow velocity layers, and the multiple flow velocity layers are respectively a central fast layer, an inner wall slow layer and a transition velocity layer, including: A simulation screen of drug particle falling is collected, and the speed of each drug particle at different height positions is marked based on the simulation screen of drug particle falling.

7. The method for simulating particle dropping from a medicine bin according to claim 6, characterized in that: The method further comprises: forming a plurality of flow velocity layers based on the division of the simulation screen of the drug particle falling, wherein the plurality of flow velocity layers are respectively a central fast layer, an inner wall slow layer and a transitional velocity layer; A plurality of speed ranges are formed according to the classification of the speeds of the individual drug particles at different height positions, wherein the speed ranges are related to the specifications and height positions of the drug particles; Based on multiple speed ranges and corresponding height positions, multiple velocity layers are formed. The multiple velocity layers are a central fast layer, an inner wall slow layer, and a transition velocity layer. The speeds of the central fast layer, the inner wall slow layer, and the transition velocity layer are different and target different height positions.

8. A simulation system for particle dropping in a medicine bin, characterized in that: The simulation system for particle dropping from a medicine bin is applied to the simulation method for particle dropping from a medicine bin as claimed in any one of claims 1 to 7, and the simulation system for particle dropping from a medicine bin comprises: The monitoring space module is used to determine the monitoring space based on the current position of the medicine warehouse and the previous falling trajectory of the medicine particles; A falling event module is used to determine the falling events of each drug particle in the drug bin according to the position node, time and specifications of each drug particle during the falling process in the dynamic detection of the monitoring space; a simulation screen module for determining the falling trajectory of each drug relative to the drug bin based on the detection of the falling events of each drug particle, and determining a simulation screen of the drug particle falling according to the falling trajectory of each drug relative to the drug bin and the falling simulation of the monitoring space; A velocity layer module is used to form multiple velocity layers based on the division of the simulation screen of drug particle falling, and the multiple velocity layers are respectively a central fast layer, an inner wall slow layer and a transition velocity layer; The posture adjustment module is used to determine the amount of residual particles in multiple flow rate layers according to the speed of multiple flow rate layers and the proportion of drug particles in multiple flow rate layers, and trigger the posture adjustment of the medicine warehouse to avoid material accumulation in the medicine warehouse after each discharge, including: in each flow rate layer, collecting the simulation picture of the flow rate layer at a preset time point, and determining the total amount of drug particles based on the traversal of the simulation picture, and determining the distribution number of each type of drug particles based on the total amount of drug particles and the specifications of the drug particles; determining the proportion of drug particles in the flow rate layer based on the comparison of the distribution number of each type of drug particles; based on the area of ​​each flow rate layer and the medicine warehouse The corresponding residual layer is determined by comparison, and the residual image of the drug particles is determined based on the tracing of the residual layer, and the residual particle amount of the flow rate layer is determined based on the detection of the residual image of the drug particles; the residual layer with the maximum residual particle amount is determined according to the residual particle amount of each flow rate layer and the height position of each flow rate layer, and the residual position of the drug particles is determined based on the detection of the residual layer with the maximum residual particle amount, and the posture adjustment of the drug warehouse is triggered according to the residual position of the drug particles and the flow velocity of the flow velocity layer corresponding to the current posture of the medicine warehouse, so that the current posture of the medicine warehouse is changed, and the accumulation of drug particles at the residual position of the drug particles is gradually regulated.

Images