Intelligent enteric capsule forming system based on computer real-time monitoring and control

Abstract

The invention relates to the technical field of general control systems, in particular to an enteric capsule intelligent forming system based on computer real-time monitoring and control, which performs pellet detection and tracking in video data in a diffusion chamber in each coating process to obtain pellet detection and tracking results, according to the pellet detection tracking result in the real-time coating process, in combination with the temperature and humidity data in the fluidized bed diffusion chamber at each moment, determining the wind pressure tending to be high strength of the real-time coating process, and in combination with the difference between the pellet detection tracking result in the real-time coating process and the pellet detection tracking result in all historical coating processes, determining the wind pressure tending to be high strength of the real-time coating process. And determining the wind pressure demand index of the real-time coating process, and finally performing wind pressure control on the next coating process in the future by combining the pressure data of the guide cylinder distribution plate at all moments in all the coating processes. According to the invention, the real-time monitoring control efficiency of the computer on the enteric capsule forming process is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the general control system technical field, specifically relates to the computer real-time monitoring control based on intelligent forming system of enteric capsule. BACKGROUND

[0002] The enteric capsule is a kind of capsule made by special process, its outer layer is wrapped with enteric coating, to ensure that the drug does not dissolve in gastric acid environment, and only when it enters the intestinal alkaline environment, it will disintegrate and release, to fully exert the efficacy of the drug.The enteric micro-pellet coating technology is an important process in the preparation process of enteric capsule, and the precision of coating process directly affects the drug dissolution characteristics.

[0003] The traditional fluidized bed bottom spray micro-pellet coating technology is often used for enteric micro-pellet coating, and in the micro-pellet coating process, the micro-pellets made of medicinal materials make reciprocating fluidized motion in the fluidized bed, and the micro-pellets are mixed with the coating liquid sprayed from the bottom nozzle in each fluidized motion process, and then the coating film is generated on the surface of the enteric micro-pellets through multi-process fluidized motion, to realize the micro-pellet coating process, and the whole coating forming process is monitored and controlled by computer in real time.

[0004] The existing problem is that in the running process of the traditional computer monitoring and control based on fluidized bed bottom spray micro-pellet coating machine, the fan pressure of fluidized bed is often selected as a constant value, while in actual scene, the particle size and morphology of micro-pellets are different, the atomization pressure, temperature and humidity in the diffusion chamber of fluidized bed are different, so that the demand for fan pressure is different in each fluidized process, if the fan pressure is too high, the micro-pellets may flow faster, and then the contact time with coating liquid is short, and the drug loading is insufficient, if the fan pressure is too low, the adhesion rate between micro-pellets and coating unevenness may be increased, so the traditional coating method using constant fan pressure is difficult to adapt to the coating requirements of enteric micro-pellets, and the monitoring and control efficiency of computer on intelligent forming process of enteric capsule is reduced. SUMMARY

[0005] The present application provides a computer real-time monitoring control based on intelligent forming system of enteric capsule to solve the existing problems.

[0006] The computer real-time monitoring control based on intelligent forming system of enteric capsule provided by the present application adopts the following technical scheme: One embodiment of the present application provides a computer real-time monitoring control based on intelligent forming system of enteric capsule, which comprises the following modules: An enteric micro-pellet coating data acquisition module is configured to acquire video data in a diffusion chamber in each coating process, and temperature and humidity data in the diffusion chamber of the fluidized bed and pressure data of a distribution plate of a draft tube at each time during an enteric micro-pellet coating process in a fluidized bed. The coating process includes a real-time coating process and a plurality of historical coating processes. Micro-pellet detection and tracking are performed on the video data in the diffusion chamber in each coating process to obtain micro-pellet detection and tracking results. A wind pressure trend high intensity analysis module is configured to determine a wind pressure trend high intensity of the real-time coating process according to the micro-pellet detection and tracking results in the real-time coating process and the temperature and humidity data in the diffusion chamber of the fluidized bed at each time. A wind pressure demand index analysis module is configured to determine a wind pressure demand index of the real-time coating process according to a difference between the micro-pellet detection and tracking results in the real-time coating process and all historical coating processes, and the wind pressure trend high intensity. A wind pressure control module is configured to control wind pressure of a future next coating process according to the wind pressure demand index of the real-time coating process and the pressure data of the distribution plate of the draft tube at all times in all coating processes.

[0007] Further, the determination of the wind pressure trend high intensity of the real-time coating process includes: The micro-pellet detection and tracking results include a maximum fluidization height, a fluidization movement speed, and a complete fluidization termination time of each complete fluidization micro-pellet, and a plurality of micro-pellets selected from all complete fluidization micro-pellets and having adhesion during fluidization. A coating uniformity degradation index of the real-time coating process is determined according to the maximum fluidization height, the fluidization movement speed, and the complete fluidization termination time of each complete fluidization micro-pellet in the real-time coating process. A wind pressure adhesion influence degree of the real-time coating process is determined according to the number of all complete fluidization micro-pellets, the number of all micro-pellets selected from all complete fluidization micro-pellets and having adhesion during fluidization, and the temperature and humidity data in the diffusion chamber of the fluidized bed at all times. The wind pressure trend high intensity of the real-time coating process is determined according to the coating uniformity degradation index and the wind pressure adhesion influence degree of the real-time coating process.

[0008] Further, the determination of the coating uniformity degradation index of the real-time coating process includes: An average of an inverse proportional normalized value of the maximum fluidization height and an inverse proportional normalized value of the fluidization movement speed of each complete fluidization micro-pellet in the real-time coating process is obtained, and is recorded as a particle size degree factor of each complete fluidization micro-pellet. In the real-time coating process, a complete fluidization micro-pellet with a particle size degree factor greater than or equal to a preset particle size threshold is recorded as a large particle size micro-pellet. The real-time coating process is divided into a front time period and a rear time period, the number of large-diameter pellets in the front time period at the time when the complete fluidization is terminated is counted and recorded as a first number value, the number of large-diameter pellets in the rear time period at the time when the complete fluidization is terminated is counted and recorded as a second number value, the ratio of the second number value to the first number value is recorded as a coating uniformity deterioration index of the real-time coating process.

[0009] Further, the determination of the wind pressure adhesion influence degree of the real-time coating process comprises: The ratio of the number of all the pellets that exist adhesion in the fluidization process to the number of all the complete fluidization pellets in all the complete fluidization pellets in the real-time coating process is recorded as a material adhesion rate of the real-time coating process; In the real-time coating process, the mean value of the temperature data in the diffusion chamber of the fluidized bed at all time points is recorded as a temperature characteristic value, the mean value of the humidity data in the diffusion chamber of the fluidized bed at all time points is recorded as a humidity characteristic value, the mean value of the inverse proportional normalized value of the temperature characteristic value and the inverse proportional normalized value of the humidity characteristic value is recorded as an influence weight, and the product of the influence weight and the material adhesion rate of the real-time coating process is recorded as a wind pressure adhesion influence degree of the real-time coating process.

[0010] Further, the determination of the wind pressure adhesion influence degree of the real-time coating process comprises: The inverse proportional normalized value of the product of the coating uniformity deterioration index and the wind pressure adhesion influence degree of the real-time coating process is recorded as a wind pressure high-trend strength of the real-time coating process.

[0011] Further, the determination of the wind pressure demand index of the real-time coating process comprises: The pellet detection and tracking result comprises: the pellet area of each complete fluidization pellet in the continuous video frame, and the motion trajectory line of each complete fluidization pellet; The coating liquid dyeing effect of each coating process is determined according to the color change of the pellet area of each complete fluidization pellet in the continuous video frame in each coating process; The mean value of the coating liquid dyeing effects of all the historical coating processes is recorded as a historical coating liquid dyeing effect, and the normalized value of the difference between the coating liquid dyeing effect of the real-time coating process and the historical coating liquid dyeing effect is recorded as a pellet drug placement degree of the real-time coating process; The atomization matching degree of the real-time coating process is determined according to the curvature of the trajectory point on the motion trajectory line of each complete fluidization pellet in each coating process; The wind pressure strong coefficient of the real-time coating process is determined according to the pellet drug placement degree and the atomization matching degree of the real-time coating process; The normalized value of the sum of the average of the inverse proportional value of the wind pressure trend high intensity and the inverse proportional value of the wind pressure strong coefficient in the real-time coating process and the preset constant is recorded as the wind pressure demand index of the real-time coating process.

[0012] Further, the determination of the coating liquid dyeing effect of each coating process comprises: The LAB color space is constructed, and in each coating process, the average of the numerical values of all pixel points in the pellet area of each complete fluidized pellet in each frame of the continuous video frame in the LAB color channel is obtained, the pellet point position of the pellet area of each complete fluidized pellet in each frame of the continuous video frame in the LAB color space is determined, the Euclidean distance between the pellet point positions of the pellet area of each complete fluidized pellet in the first frame and the last frame of the continuous video frame in the LAB color space is obtained, and the color difference before and after fluidization of each complete fluidized pellet is recorded. The average of the color difference before and after fluidization of all complete fluidized pellets in each coating process is obtained as the coating liquid dyeing effect of each coating process.

[0013] Further, the determination of the atomization matching degree of the real-time coating process comprises: In each coating process, the average of the curvatures of all trajectory points on the motion trajectory line of each complete fluidized pellet is obtained as the coating liquid wrapping effect of each complete fluidized pellet. The maximum value of the coating liquid wrapping effect of all complete fluidized pellets in all coating processes is obtained, and is recorded as the maximum coating liquid wrapping effect. The ratio of the average of the coating liquid wrapping effect of all complete fluidized pellets in the real-time historical coating process to the maximum coating liquid wrapping effect is obtained, and is recorded as the atomization matching degree of the real-time coating process.

[0014] Further, the determination of the wind pressure strong coefficient of the real-time coating process comprises: The average of the inverse proportional value of the pellet drug placement degree and the inverse proportional value of the atomization matching degree in the real-time coating process is obtained, and is recorded as the wind pressure strong coefficient of the real-time coating process.

[0015] Further, the wind pressure control on the future next coating process comprises: The default proportional gain coefficient of the PID controller is obtained by tuning method. The product of the wind pressure demand index of the real-time coating process and the default proportional gain coefficient is recorded as the adjusted proportional gain value. According to the adjusted proportional gain value, the pressure data of the distribution plate of the draft tube at all times in all coating processes are input into the PID controller, and the wind pressure control signal of the future next coating process is output.

[0016] The beneficial effects of the technical scheme of the present application are: first, the coating process is divided, then the particle size sphericity factor of each pellet is obtained according to the maximum fluidization height and fluidization speed of the pellets in the real-time coating process, then the coating uniformity degradation index of the real-time coating process is evaluated according to the distribution performance of different sphericity pellets, then the wind pressure trend strength of the real-time process is obtained in combination with the material adhesion performance, then the wind pressure strong coefficient is obtained by synergistically analyzing the matching degree of the medicine on the pellets and the fluidization and atomization pressure of the pellets on the basis of the wind pressure trend strength, and the wind pressure demand index is obtained in combination with the input performance of the draft tube pellets, so that the gain parameter adjustment of the PID control is carried out according to the real-time wind pressure demand index. Compared with the method of using constant fan wind pressure in the whole process of traditional coating, the present application can obtain more accurate coating fluidized bed fan wind pressure control results in combination with the particle size distribution performance of the pellets, the medicine on the pellets and the matching performance of the atomization pressure in the actual scene, and the real-time monitoring and control efficiency of the computer on the enteric capsule forming process is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laborious work.

[0018] Figure 1 The module flow chart of the enteric capsule intelligent forming system based on computer real-time monitoring and control of the present application; Figure 2 The structure schematic diagram of the fluidized bed bottom spraying coating machine. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the enteric capsule intelligent forming system based on computer real-time monitoring and control according to the present application, its specific implementation, structure, features and effects will be described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0021] The specific scheme of the enteric capsule intelligent forming system based on computer real-time monitoring and control provided by the present application will be specifically described below with reference to the drawings.

[0022] Please refer toFigure 1 which shows a module flow chart of the computer real-time monitoring and control based enteric capsule intelligent forming system provided by an embodiment of the present application, the system comprises the following modules: Module 101: enteric micro-pellet coating data acquisition module.

[0023] The module is used to acquire video data in the diffusion chamber in each coating process, and temperature and humidity data in the diffusion chamber of the fluidized bed and pressure data of the distribution plate of the draft tube at each moment during the fluidized bed enteric micro-pellet coating process; the coating process includes a real-time coating process and a plurality of historical coating processes; micro-pellet detection and tracking are performed in the video data in the diffusion chamber in each coating process, and micro-pellet detection and tracking results are acquired.

[0024] It is to be noted that: enteric micro-pellet coating technology is an important forming process for enteric capsule preparation, which is usually realized by a fluidized bed bottom-spraying micro-pellet coating machine, the whole process is monitored and controlled by a computer in real time, a film can be wrapped on the outside of the micro-pellet to make the drug not dissolved in the stomach and fully dissolved in the intestine to fully exert the drug effect, and the coating thickness of the micro-pellet is controllable. The structure of the fluidized bed bottom-spraying coating machine is shown in Figure 2 . The fluidized bed bottom-spraying coating machine in Figure 2 includes a draft tube, a diffusion chamber, a material container, an airflow distribution plate, a spray gun, and air is introduced from the bottom. The process of enteric micro-pellet coating is as follows: first, all the enteric micro-pellets to be coated are poured into the material container of the coating machine, the coating machine is turned on, the airflow distribution plate applies fan pressure to blow the micro-pellets into a “fountain type” fluidized state (ascending in the draft tube and descending outside the draft tube), the spray gun sprays coating liquid droplets, the micro-pellets contact the droplets when ascending in the draft tube, a film is formed on the surface of the micro-pellets, and then the micro-pellets fall to the external drying area to complete one “spraying to drying” cycle, and the process is repeated until the micro-pellet population reaches the target value of the coating time.

[0025] It is further to be noted that: it is difficult to adapt the coating requirements of the micro-pellets by using a constant fan pressure in the traditional micro-pellet coating process, therefore, in the embodiment, the computer monitoring and control results of the fan pressure of the coating fluidized bed are obtained by combining the actual scene micro-pellet size distribution performance, the micro-pellet drug loading situation, and the matching performance of the atomization pressure.

[0026] The preset single-coating process duration is 3 seconds, which is taken as an example for description.

[0027] During the fluidized bed enteric micro-pellet coating process, video data in the diffusion chamber in each coating process, and temperature and humidity data in the diffusion chamber of the fluidized bed and pressure data of the distribution plate of the draft tube at each moment are acquired.

[0028] In time sequence, the last coating process is recorded as a real-time coating process, and other coating processes except the real-time coating process are recorded as historical coating processes.

[0029] It should be noted that in this embodiment, the fan pressure is constant within a single coating process, and the fan pressure is adaptively changed at the transition time between adjacent coating processes, that is, the automatic regulation of the fan pressure is performed every 3 seconds, so there is no case that the coating process does not meet 3 seconds in the regulation analysis. Among them, the real-time temperature and humidity data in the fluidized bed diffusion chamber are read through the temperature and humidity monitoring module, the real-time pressure data of the guide cylinder distribution plate are read through the pressure sensing module on the side of the guide cylinder distribution plate, and the collection frequency of the temperature and humidity data and the pressure data is 12 times per second. Then the video data of the front perspective surface in the diffusion chamber is collected by the industrial camera, and the video collection frequency is 24 frames per second. Then all the read data are preprocessed, and finally the preprocessed data are uploaded to the computer monitoring module for subsequent analysis.

[0030] It should be further noted that the purpose of this embodiment is to monitor and control the fan pressure at the bottom of the fluidized bed during the enteric micro-pellet coating process, so it is necessary to judge the wind pressure demand of each coating process. First, the particle size of each micro-pellet in the real-time coating process is evaluated, and then the coating uniformity degradation index of the real-time process is obtained through the distribution of different size micro-pellets, and then the wind pressure trend intensity is obtained by combining the adhesion of the micro-pellets in the fluidization process. On the basis of the wind pressure trend intensity, the wind pressure intensity coefficient is obtained by analyzing the matching degree of the drug effect on the micro-pellets and the fluidization and atomization pressure of the micro-pellets, and then the real-time wind pressure demand index is obtained by combining the micro-pellet input performance of the guide cylinder. The wind pressure demand index is input into the PID control module of the computer to adjust the gain parameter, so as to control the fan pressure during the micro-pellet coating process.

[0031] Micro-pellet detection and tracking are performed in the video data in the diffusion chamber in each coating process to obtain micro-pellet detection and tracking results. The micro-pellet detection and tracking results include: the micro-pellet area of each complete fluidized micro-pellet in the continuous video frame, and the motion trajectory line, maximum fluidization height, fluidization motion speed, and complete fluidization termination time of each complete fluidized micro-pellet. A number of micro-pellets that exist in the adhesion during the fluidization process are selected from all complete fluidized micro-pellets.

[0032] It is required to be explained: in this embodiment, YOLOv5 and DeepSORT are used respectively to detect and track pellets in the video data in each coating process in the diffusion chamber, wherein YOLOv5 is a target detection algorithm based on the YOLO (You Only Look Once) series, and DeepSORT (Deep Learning based SORT) is a target tracking algorithm combined with deep learning, both of which are known technologies, and the specific method is not introduced here. Among them, YOLOv5 is used to identify and locate multiple targets (pellets) in the video, and then combined with the Mask R-CNN algorithm to obtain the pellet area in the video frame, wherein Mask R-CNN is a classic instance segmentation algorithm used to obtain the connected domain of the target (pellet), which is a known technology and the specific method is not introduced here. DeepSORT is used to track the motion trajectory of the pellets in the video. In this embodiment, the process of the pellets being sprayed out of the flow guide cylinder to the highest point and then falling into the outside material container is recorded as a single complete fluidization round, and DeepSORT can be used to extract all complete fluidization pellets that complete a single complete fluidization round in the coating process, and DeepSORT can be used to judge whether there is adhesion between the complete fluidization pellets in the fluidization process, wherein the adhesion judgment condition is that the motion trajectory lines of different complete fluidization pellets at the same time appear to be mixed, and the trajectory changes tend to be consistent after the mixing.

[0033] It is further required to be explained: in this embodiment, the top of the lower left corner of the video frame is taken as the origin, the horizontal right is taken as the horizontal positive direction, and the vertical up is taken as the vertical positive direction to construct a plane coordinate system. The center point of the pellet area of each complete fluidization pellet in the continuous video frame is taken as the trajectory point, and the time when the last trajectory point is located in the video frame is recorded as the complete fluidization termination time of each complete fluidization pellet. In the plane coordinate system, the position coordinates of all trajectory points of each complete fluidization pellet in the continuous video frame are curve fitted using the least square method to obtain the motion trajectory line of each complete fluidization pellet. Since the video data of the front view surface of the diffusion chamber is collected by an industrial camera in this embodiment, the vertical axis direction in the plane coordinate system is the height direction of the pellet motion trajectory, that is, the maximum vertical axis coordinate on the motion trajectory line of each complete fluidization pellet is the maximum fluidization height of each complete fluidization pellet. In the motion trajectory line of each complete fluidization pellet, the ratio of the Euclidean distance between the trajectory points corresponding to adjacent video frames to the time interval between adjacent video frames is taken as the pellet motion speed between adjacent video frames, and the mean value of all pellet motion speeds between adjacent video frames is taken as the fluidization motion speed of each complete fluidization pellet. The least square method is a known technology and the specific method is not introduced here.

[0034] Module 102: Wind pressure tends to high intensity analysis module.

[0035] This module is used to determine the wind pressure rise intensity of the real-time coating process based on the microparticle detection and tracking results during the real-time coating process, combined with the temperature and humidity data in the fluidized bed diffusion chamber at each moment.

[0036] It should be noted that during the fluidized bed bottom spray micro-pellet coating process, the particle size of each micro-pellet may vary due to differences in manufacturing process precision. Different particle sizes will exhibit different effects under the same air pressure. Therefore, it is necessary to evaluate the particle size distribution to distinguish between large and small particle sizes. When the air pressure is too low, large-diameter micro-pellets have a shorter fluidization path, while small-diameter micro-pellets diffuse further, leading to uneven drug coating. Therefore, an analysis of the distribution of micro-pellets of different sizes is used to obtain an index of coating uniformity degradation during the coating process. For a single micro-pellet, under the same air pressure, a higher maximum fluidization height and faster fluidization velocity indicate a higher probability of it being a small-diameter micro-pellet, and vice versa.

[0037] Preferably, in one embodiment of the present invention, the method for obtaining the wind pressure intensity of the real-time coating process includes: During the real-time coating process, the maximum fluidization height of each complete fluidized pellet is obtained. The inversely proportional normalized value and fluidization velocity The mean of the inverse proportional normalized values ​​is denoted as the particle size factor for each intact fluidized pellet.

[0038] It should be noted that in this embodiment, the following is used: and These are respectively used as the maximum fluidization height With fluidization velocity The inverse proportional normalized value, where, This is a linear normalization function used to normalize data values ​​to a range of 0 to 1. In other words, the higher the maximum fluidization height of the microsphere and the faster the fluidization velocity (i.e., the smaller the particle size factor), the higher the probability that the microsphere is a small-sized microsphere; conversely, the lower the probability that the microsphere is a large-sized microsphere.

[0039] The preset particle size threshold is 0.52, and this will be used as an example for explanation.

[0040] In the real-time coating process, complete fluidized pellets with a particle size factor greater than or equal to a preset particle size threshold are denoted as large-size pellets, and complete fluidized pellets with a particle size factor less than a preset particle size threshold are denoted as small-size pellets.

[0041] It is required to be explained that due to the subtle differences in the morphology of the pellets, it is difficult to determine the details of each orientation in the video data, so in this embodiment, the trajectory after the positioning of the pellets is analyzed to determine the particle size. When the wind pressure is too low, the large particle size pellets are difficult to pass through the high-intensity fluidization movement to the two sides of the diffusion chamber, resulting in the possibility of large particle size pellets falling to the proximal end of the flow guide cylinder and being repeatedly fluidized to take medicine, while small particle size pellets are difficult to enter the flow guide cylinder to take medicine, which may cause the uniformity of the medicine between the pellets to decrease. Therefore, the real-time coating process can be divided into two time periods according to the time length, and if the number of large particle size pellets in the latter time period is significantly more than that in the former time period, it indicates that the wind pressure of the real-time coating process may be too low, causing the fluidization uniformity of different particle sizes to deteriorate.

[0042] The real-time coating process is equally divided into a front time period and a rear time period, the number of large particle size pellets in the front time period at the complete fluidization termination time is counted and recorded as a first number value, the number of large particle size pellets in the rear time period at the complete fluidization termination time is counted and recorded as a second number value, and the ratio of the second data value to the first number value is recorded as a coating uniformity deterioration index of the real-time coating process.

[0043] It is required to be explained that when the number of large particle size pellets in the rear time period is more than that in the front time period in the real-time coating process, it indicates that the possibility of large particle size pellets being repeatedly taken medicine due to low wind pressure is higher, and the coating uniformity is worse. Moreover, the medicine taking of the coating liquid mainly changes the weight of the pellets, and the surface coating film formed by the medicine taking is relatively thin, which has little effect on the morphology of the pellets, so the effect of the medicine taking on the particle size of the pellets is not considered.

[0044] It is further required to be explained that when the wind pressure is too low, the vertical movement of the pellets is weakened, resulting in some pellets staying in the coating area for a long time, excessively absorbing the coating liquid, increasing the surface moisture, and increasing the probability of adhesion. Therefore, the wind pressure tends to be high in strength by combining the coating uniformity and the adhesion of the pellets. At the same time, too high wind pressure will cause the trajectory of the pellets to directly pass through the atomization layer of the coating liquid, thereby shortening the contact time between the pellets and the coating liquid, reducing the medicine taking efficiency, and the wind pressure of the high-adaptation fan should make the residence time of the pellets on the distribution plate of the flow guide cylinder shorter to help them quickly enter the fluidization state. Therefore, the wind pressure demand index of the real-time coating process is obtained by analyzing the medicine taking effect, the atomization matching performance, and the flow guide cylinder adaptation on the basis of the wind pressure tending to be high in strength.

[0045] In the real-time coating process, the ratio of the number of all pellets that exist adhesion in the fluidization process to the number of all complete fluidization pellets is recorded as the material adhesion rate of the real-time coating process.

[0046] It should be noted that in addition to the fan wind pressure, the temperature and humidity in the fluidized bed diffusion chamber itself also affect the adhesion between the pellets. For example, if the temperature and humidity in the chamber are high, then the fan wind pressure has a lower impact on the adhesion of the pellets.

[0047] In the real-time coating process, the average value of the temperature data in the fluidized bed diffusion chamber at all times is obtained, denoted as the temperature characteristic value, the average value of the humidity data in the fluidized bed diffusion chamber at all times is obtained, denoted as the humidity characteristic value, the average value of the inverse proportional normalized value of the temperature characteristic value and the inverse proportional normalized value of the humidity characteristic value is obtained, denoted as the impact weight, and the product of the impact weight and the material adhesion rate of the real-time coating process is obtained, denoted as the wind pressure adhesion influence degree of the real-time coating process.

[0048] It should be noted that in this embodiment, the and the are used as the inverse proportional normalized value of the temperature characteristic value and the humidity characteristic value respectively. The lower the temperature and humidity in the fluidized bed diffusion chamber in the real-time coating process, the higher the impact of the fan wind pressure on the adhesion of the pellets.

[0049] It should be further noted that the smaller the coating uniformity degradation index of the real-time coating process, the higher the wind pressure intensity is sufficient to make different particle size pellets uniformly coated, that is, the higher the wind pressure intensity, and the lower the wind pressure adhesion influence degree, which indicates that the adhesion phenomenon caused by the wind pressure is less, and further indicates that the wind pressure intensity is higher.

[0050] The product of the coating uniformity degradation index of the real-time coating process and the inverse proportional normalized value of the wind pressure adhesion influence degree of the real-time coating process is denoted as the wind pressure trend intensity of the real-time coating process.

[0051] In this embodiment, the is used as the inverse proportional normalized value of .

[0052] Module 103: Wind pressure demand index analysis module.

[0053] This module is used to determine the wind pressure demand index of the real-time coating process according to the difference between the real-time coating process and the pellet detection tracking results in all historical coating processes, in combination with the wind pressure trend intensity.

[0054] It is required to be explained that in the process of coating medicine on the micro-pellets, the coating liquid often has different color performance with the micro-pellets, that is, when the micro-pellets are in the circulating fluidized motion to be coated by the coating liquid, the surface color of the micro-pellets will gradually be consistent with the coating liquid. For each coating process, each micro-pellet sprayed by the wind pressure of the guide cylinder in the video frame is located by the existing positioning tracking algorithm, and then the detailed micro-pellet area is obtained by the connected domain extraction technology. If the color difference between the color of each complete fluidized micro-pellet in the real-time coating process in the micro-pellet area in the final frame and the color in the initial frame is larger, it means that the coating effect of the micro-pellets under the wind pressure in the real-time coating process is better.

[0055] Preferably, in one embodiment of the present application, the method for obtaining the wind pressure requirement index of the real-time coating process comprises: LAB color space is constructed. In each coating process, the average value of all pixel points in the micro-pellet area of each complete fluidized micro-pellet in each frame of the continuous video frame in the LAB color channel is obtained, and the micro-pellet point position of the micro-pellet area of each complete fluidized micro-pellet in each frame of the continuous video frame in the LAB color space is determined.

[0056] Wherein, the construction of LAB color space is a known technology, and the specific method is not introduced here.

[0057] In each coating process, the Euclidean distance between the micro-pellet point position of the micro-pellet area of each complete fluidized micro-pellet in the first frame and the last frame of the continuous video frame in the LAB color space is obtained, which is recorded as the color difference before and after the fluidization of each complete fluidized micro-pellet.

[0058] The average value of the color difference before and after the fluidization of all complete fluidized micro-pellets in each coating process is obtained as the coating liquid immersion effect of each coating process.

[0059] The average value of the coating liquid immersion effects of all historical coating processes is obtained, which is recorded as the historical coating liquid immersion effect. The difference between the coating liquid immersion effect of the real-time coating process and the historical coating liquid immersion effect is normalized as the micro-pellet medicine placement degree of the real-time coating process.

[0060] It is required to be explained that in the present embodiment, is the normalized value of When the coating liquid immersion effect of the real-time coating process is larger than that of the historical coating process, it means that the medicine immersion effect of the micro-pellets under the wind pressure of the real-time coating process is better, and vice versa, which means that the wind pressure is too high, the contact time between the coating liquid and the micro-pellets is short, and the medicine effect is not good.

[0061] ​It is further needed to be explained that when the wind pressure is at the adaptive wind pressure, the movement speed of the micro-pellets is slow, and when the micro-pellets contact the coating liquid atomization layer, the micro-pellets will be wrapped by the coating liquid, the coating liquid atomization layer gives the micro-pellets a transverse force, changes the original movement track of the micro-pellets, and the micro-pellets are sprayed out from the edge of the coating liquid atomization layer, and the curvature of the movement track increases, and in the process, the micro-pellets are in full contact with the coating liquid, which reflects that the adaptability of the wind pressure is higher, and if the wind pressure is too high, the movement speed of the micro-pellets is too fast, and the micro-pellets can directly break through the coating liquid atomization layer and fly out from the side of the center of the flow guide cylinder, and at this time, the interaction time between the micro-pellets and the coating liquid is short, and the coating efficiency is low. Therefore, by positioning the movement track of each micro-pellet sprayed by the flow guide cylinder wind pressure in the video frame through the existing positioning tracking algorithm, if the curvature of the movement track of the sprayed micro-pellets in the coating process is small, the micro-pellets tend to directly break through the coating liquid atomization layer, which reflects that the wind pressure is too high, and vice versa, which indicates that the matching effect of the wind pressure and the atomization layer is better.

[0062] In each coating process, the average value of the curvatures of all the track points on the movement track line of each complete fluidized micro-pellet is obtained as the coating liquid wrapping effect of each complete fluidized micro-pellet.

[0063] The maximum value of the coating liquid wrapping effects of all the complete fluidized micro-pellets in all the coating processes is obtained as the maximum coating liquid wrapping effect.

[0064] The ratio of the average value of the coating liquid wrapping effects of all the complete fluidized micro-pellets in the real-time historical coating process to the maximum coating liquid wrapping effect is obtained as the atomization matching degree of the real-time coating process.

[0065] It is needed to be explained that the smaller the curvature level of the movement track of the micro-pellet in the real-time coating process is, the more likely it is that the micro-pellet breaks through the coating liquid atomization layer due to the too large wind pressure, which indicates that the wind pressure is too high, and vice versa, which indicates that the matching degree of the wind pressure and the atomization layer in the real-time coating process is higher.

[0066] It is further needed to be explained that the lower the matching degree of the wind pressure and the atomization layer in the real-time coating process is, the more intense the real-time wind pressure is, and the lower the micro-pellet fluidization speed is, which further indicates that the micro-pellet fluidization speed is too fast, and which indicates that the wind pressure intensity is too strong at this time.

[0067] The average value of the inverse proportional value of the micro-pellet fluidization speed in the real-time coating process and the inverse proportional value of the atomization matching degree of the real-time coating process is obtained as the wind pressure intensity coefficient of the real-time coating process.

[0068] It is needed to be explained that in the embodiment, 1 minus the difference value of the micro-pellet fluidization speed in the real-time coating process is taken as the inverse proportional value of the micro-pellet fluidization speed in the real-time coating process, and 1 minus the difference value of the atomization matching degree of the real-time coating process is taken as the inverse proportional value of the atomization matching degree of the real-time coating process.

[0069] It is further needed to be explained that: if the wind pressure trend intensity of the real-time coating process is lower, and the wind pressure intensity coefficient is lower, it reflects that the wind pressure demand is higher.

[0070] The preset constant is 1, and this is described as an example.

[0071] The normalized value of the average of the inverse value of the wind pressure trend intensity of the real-time coating process and the inverse value of the wind pressure intensity coefficient of the real-time coating process and the preset constant is recorded as the wind pressure demand index of the real-time coating process.

[0072] It is needed to be explained that: in this embodiment, the difference between 1 and the wind pressure trend intensity of the real-time coating process is taken as the inverse value of the wind pressure trend intensity of the real-time coating process, the difference between 1 and the wind pressure intensity coefficient of the real-time coating process is taken as the inverse value of the wind pressure intensity coefficient of the real-time coating process, and is taken as the normalized value of , wherein is a hyperbolic tangent function, which is used to normalize the data value to-1 to 1. The lower the wind pressure trend intensity and the wind pressure intensity coefficient, the higher the wind pressure demand.

[0073] Module 104: wind pressure control module.

[0074] This module is used to control the wind pressure of the future next coating process according to the wind pressure demand index of the real-time coating process and the pressure data of the flow guide cylinder distribution plate at all times in all coating processes.

[0075] Preferably, in an embodiment of the present application, the method for obtaining the wind pressure control signal of the future next coating process comprises: The default proportional gain coefficient of the PID controller is obtained by using the tuning method, wherein the tuning method is a method for obtaining the parameters of the PID controller, which is a known technology, and the specific method is not introduced here. The PID controller is a very common and known controller type, which is used to control industrial processes, mechanical systems and other various systems. PID represents proportional (Proportional), integral (Integral) and derivative (Derivative), which respectively represent the three main parts of the controller.

[0076] The product of the wind pressure demand index of the real-time coating process and the default proportional gain coefficient is recorded as the adjusted proportional gain value.

[0077] According to the adjusted proportional gain value, the pressure data of the flow guide cylinder distribution plate at all times in all coating processes is input into the PID controller, and the wind pressure control signal of the future next coating process is output.

[0078] It is required to be explained: in this embodiment, the real-time adjusted parameters are continuously input into the PID control chip in the above-mentioned manner, and the control output obtained by calculation is converted into actual control signals for fan pressure control. Thus, the parameters of the PID controller are dynamically updated in the continuous monitoring process of the pellets, ensuring the stability of the fan pressure control of the pellets in the fluidized bed during the processing. Finally, after the control cycle ends, the control effect of the system is evaluated to determine whether there is overshoot or oscillation. According to the actual feedback results, the related parameters can be fine-tuned and optimized to improve the efficiency and system performance in the subsequent forming process.

[0079] It is further required to be explained: the complete process of the intelligent forming of the enteric capsule based on computer real-time monitoring control is as follows: first, the coating process of the current batch of pellets is completed under the action of the computer self-adaptive fan pressure monitoring control result. The coated pellets are sieved through the mold to remove oversized, undersized or non-conforming particles, ensuring that the particle size distribution of the pellets meets the design requirements. The sieved coated pellets are subjected to quality detection, including but not limited to: (1) particle size distribution: detected by sieving method or laser particle size analyzer to ensure uniform pellet size. (2) moisture content: detected by Karl Fischer method to ensure that the moisture content meets the requirements and avoid capsule moisture absorption and deterioration. (3) coating weight gain: detected by weight method to ensure that the enteric layer weight gain meets the design requirements to ensure the enteric effect. The qualified pellets are filled into the capsule shell to form the final enteric capsule. In the intelligent production line, the dispensing link usually uses automatic equipment (such as capsule filling machine) to ensure accurate filling and good capsule sealing. Finally, each batch of pellets is processed in the above-mentioned manner, thereby realizing the intelligent forming method of the enteric capsule based on computer real-time monitoring control.

[0080] Thus, the present application is completed.

[0081] In summary, in the embodiment of the present application, pellet detection and tracking are performed in the video data in the diffusion chamber in each coating process, the pellet detection and tracking results are obtained, the wind pressure trend in the real-time coating process is determined according to the pellet detection and tracking results in the real-time coating process, combined with the temperature and humidity data in the fluidized bed diffusion chamber at each time, the wind pressure demand index of the real-time coating process is determined by combining the differences between the pellet detection and tracking results in the real-time coating process and all historical coating processes, and finally the wind pressure control is performed on the next coating process in the future by combining the pressure data of the guide cylinder distribution plate at all times in all coating processes. The present application improves the real-time monitoring control efficiency of the computer on the enteric capsule forming process.

[0082] The above only describes the preferred embodiments of the present application and should not be used to limit the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A computer real-time monitoring control based enteric capsule intelligent forming system, characterized in that, The system comprises the following modules: An enteric micro-pellet coating data acquisition module: used for acquiring video data in a diffusion chamber in each coating process, and temperature and humidity data in the diffusion chamber of the fluidized bed and pressure data of the distribution plate of the diffusion tube at each time during the fluidized bed enteric micro-pellet coating process; the coating process includes a real-time coating process and a plurality of historical coating processes; micro-pellet detection and tracking are performed on the video data in the diffusion chamber in each coating process to obtain micro-pellet detection and tracking results; A wind pressure trend high-intensity analysis module: used for determining the wind pressure trend high-intensity of the real-time coating process according to the micro-pellet detection and tracking results in the real-time coating process and the temperature and humidity data in the diffusion chamber of the fluidized bed at each time; A wind pressure demand index analysis module: used for determining the wind pressure demand index of the real-time coating process according to the difference between the micro-pellet detection and tracking results in the real-time coating process and all historical coating processes and the wind pressure trend high-intensity; A wind pressure control module: used for performing wind pressure control on the next coating process in the future according to the wind pressure demand index of the real-time coating process and the pressure data of the distribution plate of the diffusion tube at all times in all coating processes.

2. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 1, characterized in that, The determination of the wind pressure trend high-intensity of the real-time coating process comprises: The micro-pellet detection and tracking results include: the maximum fluidization height, the fluidization movement speed, and the complete fluidization termination time of each complete fluidized micro-pellet, and a plurality of micro-pellets selected from all complete fluidized micro-pellets that have adhesion during the fluidization process; Determination of a coating uniformity degradation index of the real-time coating process according to the maximum fluidization height, the fluidization movement speed, and the complete fluidization termination time of each complete fluidized micro-pellet in the real-time coating process; Determination of a wind pressure adhesion influence degree of the real-time coating process according to the number of all complete fluidized micro-pellets, the number of all micro-pellets selected from all complete fluidized micro-pellets that have adhesion during the fluidization process, and the temperature and humidity data in the diffusion chamber of the fluidized bed at all times; Determination of the wind pressure trend high-intensity of the real-time coating process according to the coating uniformity degradation index and the wind pressure adhesion influence degree of the real-time coating process.

3. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 2, characterized in that, The determination of the coating uniformity degradation index of the real-time coating process comprises: Obtaining the average value of the inverse proportional normalized value of the maximum fluidization height and the inverse proportional normalized value of the fluidization movement speed of each complete fluidized micro-pellet in the real-time coating process, denoted as the particle size degree factor of each complete fluidized micro-pellet; In the real-time coating process, the complete fluidized micro-pellets with a particle size degree factor greater than or equal to a preset particle size threshold are denoted as large-particle-size micro-pellets; The real-time coating process is equally divided into a front time period and a rear time period, the number of large-particle-size micro-pellets with the complete fluidization termination time in the front time period is denoted as a first number value, the number of large-particle-size micro-pellets with the complete fluidization termination time in the rear time period is denoted as a second number value, and the ratio of the second number value to the first number value is denoted as the coating uniformity degradation index of the real-time coating process.

4. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 2, wherein, The determination of the wind pressure adhesion influence degree of the real-time coating process comprises: Obtaining a ratio of a number of all the micro-pellets selected in the screening of all the complete fluidized micro-pellets in the real-time coating process and a number of all the complete fluidized micro-pellets in the fluidization process, and denoted as a material adhesion rate of the real-time coating process; In the real-time coating process, obtaining a mean value of temperature data in the diffusion chamber of the fluidized bed at all times, denoted as a temperature characteristic value, obtaining a mean value of humidity data in the diffusion chamber of the fluidized bed at all times, denoted as a humidity characteristic value, obtaining a mean value of an inverse proportional normalized value of the temperature characteristic value and an inverse proportional normalized value of the humidity characteristic value, denoted as an influence weight, and obtaining a product of the influence weight and the material adhesion rate of the real-time coating process, denoted as a wind pressure adhesion influence degree of the real-time coating process.

5. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 2, wherein, The wind pressure adhesion influence degree of the real-time coating process is determined according to the coating uniformity deterioration index and the wind pressure adhesion influence degree of the real-time coating process, and the wind pressure trend high strength of the real-time coating process includes: An inverse proportional normalized value of a product of the coating uniformity deterioration index and the wind pressure adhesion influence degree of the real-time coating process is denoted as the wind pressure trend high strength of the real-time coating process.

6. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 1, wherein, The wind pressure demand index of the real-time coating process is determined, and the micro-pellet detection and tracking result includes: The micro-pellet detection and tracking result includes: a micro-pellet area of each complete fluidized micro-pellet in the continuous video frames, and a motion trajectory line of each complete fluidized micro-pellet; According to a color change of the micro-pellet area of each complete fluidized micro-pellet in the continuous video frames in each coating process, a coating liquid dyeing effect of each coating process is determined; A mean value of the coating liquid dyeing effects of all the historical coating processes is obtained, denoted as a historical coating liquid dyeing effect, and a normalized value of a difference between the coating liquid dyeing effect of the real-time coating process and the historical coating liquid dyeing effect is denoted as a micro-pellet drug placement degree of the real-time coating process; According to a curvature of a trajectory point on the motion trajectory line of each complete fluidized micro-pellet in each coating process, an atomization matching degree of the real-time coating process is determined; According to the micro-pellet drug placement degree and the atomization matching degree of the real-time coating process, a wind pressure strong coefficient of the real-time coating process is determined; A normalized value of a sum of a mean value of inverse proportional values of the wind pressure trend high strength and the wind pressure strong coefficient of the real-time coating process and a preset constant is denoted as the wind pressure demand index of the real-time coating process.

7. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 6, characterized in that, The coating liquid dyeing effect of each coating process is determined, and the LAB color space is constructed. In each coating process, a mean value of values of all the pixel points in the micro-pellet area of each complete fluidized micro-pellet in each frame of the continuous video frames in the LAB color channel is obtained, a micro-pellet point position of the micro-pellet area of each complete fluidized micro-pellet in each frame of the continuous video frames in the LAB color space is determined, a Euclidean distance between the micro-pellet point positions of each complete fluidized micro-pellet in the first frame and the last frame of the continuous video frames in the LAB color space is obtained, and denoted as a color difference before and after fluidization of each complete fluidized micro-pellet; A mean value of the color differences before and after fluidization of all the complete fluidized micro-pellets in each coating process is obtained as the coating liquid dyeing effect of each coating process.

8. The computer-based real-time monitoring control system for enteric capsule intelligent molding system according to claim 6, wherein, The atomization matching degree of the real-time coating process is determined, and the LAB color space is constructed. In each coating process, the average of curvatures of all trajectory points on the trajectory line of each complete fluidized pellet is obtained as the coating liquid wrapping effect of each complete fluidized pellet; The maximum value of the coating liquid wrapping effect of all complete fluidized pellets in all coating processes is obtained, denoted as the maximum coating liquid wrapping effect; The ratio of the average of the coating liquid wrapping effect of all complete fluidized pellets in the real-time historical coating process to the maximum coating liquid wrapping effect is obtained, denoted as the atomization matching degree of the real-time coating process.

9. The computer-based real-time monitoring control system for enteric capsule intelligent molding system according to claim 6, wherein, The determination of the wind pressure strong coefficient of the real-time coating process comprises: The average of the inverse proportion value of the pellet medicine placing degree of the real-time coating process and the inverse proportion value of the atomization matching degree is obtained, denoted as the wind pressure strong coefficient of the real-time coating process.

10. The computer real-time monitoring control based enteric capsule intelligent forming system according to claim 1, wherein, The wind pressure control of the future next coating process comprises: The default proportional gain coefficient of the PID controller is obtained by using the setting method; The product of the wind pressure demand index of the real-time coating process and the default proportional gain coefficient is denoted as the adjusted proportional gain value; According to the adjusted proportional gain value, the pressure data of the distribution plate of the draft tube at all times in all coating processes is input into the PID controller, and the wind pressure control signal of the future next coating process is output.

Images