Low-temperature soft capsule low-temperature filling production process and intelligent control system

Abstract

The present application relates to the technical field of temperature control, in particular to a low-temperature soft capsule low-temperature filling production process and an intelligent control system. First, based on the low-temperature soft capsule low-temperature filling production process, when the number of soft capsules in the filling partition changes under normal circumstances, the weight data of the soft capsules will change accordingly based on the size of the change in the number of soft capsules. First, the counting and weighing delay duration is determined. Then, based on the feature that the adhesion of soft capsules will cause the stability between the weight data of soft capsules and the particle count value to be destroyed, the first weight deviation parameter and the second weight deviation parameter are determined in turn, and further combined with the average weight fluctuation of soft capsules to determine a more accurate temperature anomaly probability and further determine the guide plate correction temperature, so that the accuracy of low-temperature soft capsule low-temperature filling production temperature control according to the guide plate correction temperature is higher.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of temperature control, in particular to a low-temperature soft capsule low-temperature filling production process and an intelligent control system. BACKGROUND

[0002] Low-temperature filling mainly refers to a process of filling contents into a bottle at a temperature lower than the conventional production temperature, and the process is mainly used for temperature-sensitive products. Soft capsules are usually composed of gelatin, glycerol and water, and can ensure the stability of chemical substances in a low-temperature environment. Therefore, low-temperature filling technology is usually used for soft capsules. However, due to the composition of the soft capsules (containing water), the soft capsules will stick together at a very low temperature, so that multiple soft capsules cannot be separated during the filling process and are filled as a larger capsule, which will block the discharge port, affect the filling efficiency, and even terminate the filling process, thereby affecting the stability of the filling process. Therefore, the temperature control of the filling process is crucial to the low-temperature filling production of low-temperature soft capsules.

[0003] The prior art usually uses an infrared imaging method to image the filling partition to determine whether there is a soft capsule sticking situation, and controls the temperature of the low-temperature soft capsule low-temperature filling production according to the number of soft capsule sticking when the soft capsule sticking situation exists. However, due to the different drug compositions at different positions inside the soft capsule and the different thicknesses of the soft capsule, the accuracy of the infrared imaging method is affected, thereby indirectly reducing the accuracy of the temperature control of the low-temperature soft capsule low-temperature filling production according to the number of soft capsule sticking. SUMMARY

[0004] In order to solve the technical problem of low accuracy of the prior art in controlling the temperature of the low-temperature soft capsule low-temperature filling production by using the infrared imaging method, the purpose of the present application is to provide a low-temperature soft capsule low-temperature filling production process and an intelligent control system, and the technical solution is as follows:

[0005] The first aspect of the present application provides a low-temperature soft capsule low-temperature filling production process, comprising:

[0006] At each sampling time in the low-temperature soft capsule low-temperature filling production process, the particle count value of each filling partition and the soft capsule weight data in the temporary storage box corresponding to each filling partition are collected;

[0007] According to the delay change correlation between the soft capsule weight data and the particle count value in time sequence, a count and weighing delay duration is determined; according to the count and weighing delay duration and the time when the particle count value changes, all sampling times are divided into at least two weight stable time periods; according to the standard deviation of the soft capsule weight data in each weight stable time period, a first weight deviation parameter is determined;

[0008] determine a second weight deviation parameter of each weight stabilization time period according to the relative change of the soft capsule weight data between the weight stabilization time periods which are sequentially adjacent; determine a temperature abnormality probability of the soft capsule production at the current temperature regulation moment according to the first weight deviation parameter, the second weight deviation parameter of each weight stabilization time period before the current temperature regulation moment, and the average weight fluctuation of the soft capsule;

[0009] correct the temperature of the guide plate at the current temperature regulation moment according to the first weight deviation parameter, the second weight deviation parameter of the weight stabilization time period in which the current temperature regulation moment is located, and the temperature abnormality, to determine a corrected temperature of the guide plate; and perform the low-temperature filling production of the soft capsule according to the corrected temperature of the guide plate.

[0010] Further, the obtaining process of the counting and weighing delay duration includes:

[0011] traverse the preset time delay window with a preset traversal step to determine a reference delay duration obtained each time; sequentially take each reference delay duration as a target delay duration; take the moment when the particle count value of the filling partition changes as a particle count change moment; determine a corresponding reference interval moment after each particle count change moment is delayed by the target delay duration in time sequence; divide all sampling moments into at least two reference stabilization time periods with the reference moments as intervals;

[0012] determine the delay matching degree of the target delay duration according to the time length of all reference stabilization time periods and the weight data stabilization of the soft capsule; and take the reference delay duration with the largest delay matching degree as the counting and weighing delay duration.

[0013] Further, the obtaining process of the delay matching degree includes:

[0014] arrange the soft capsule weight data of all sampling moments in time sequence and perform curve fitting to obtain a soft capsule weight time sequence curve under the target delay duration; take the average of the tangent slopes of all sampling moments in each reference stabilization time period as the corresponding fluctuation significance on the soft capsule weight time sequence curve; wherein the reference stabilization time period does not include the reference interval moment; and determine the corresponding confidence degree according to the normalized value of the time length of each reference stabilization time period.

[0015] determine the local matching degree of each reference stabilization time period according to the product between the negative correlation mapping value of the fluctuation significance and the confidence degree; and determine the delay matching degree of the target delay duration according to the cumulative value of the local matching degrees of all reference stabilization time periods.

[0016] Further, the obtaining process of the weight stabilization time period includes:

[0017] In terms of time sequence, the corresponding weight change time is determined by delaying the counting and weighing delay time for each particle number change time; all sampling times are divided into at least two weight stability time periods with the weight change time periods as the interval; the weight stability time periods do not include the weight change time periods.

[0018] Furthermore, the process of obtaining the first weight deviation parameter includes:

[0019] Determine the reference particle count for each weight stabilization period; determine the corresponding reference particle count based on the particle count value after the change in particle count at each weight temperature time period.

[0020] During each weight stabilization period, the average weight of the soft capsules is determined by the ratio between the soft capsule weight data at each sampling time and the number of reference particles. The reference standard ratio at each sampling time is determined by the ratio between the average weight of the soft capsules and the standard weight of the soft capsules. The mean of the reference standard ratios corresponding to all sampling times during each weight stabilization period is positively correlated to determine the corresponding first weight deviation parameter.

[0021] Furthermore, the process of obtaining the number of reference particles includes:

[0022] The particle count value at the next sampling time after each particle number change is taken as the changed quantity; the changed quantity of the particle number at the corresponding weight change time is taken as the reference particle number for the first weight stabilization period after each weight change time.

[0023] Furthermore, the process of obtaining the second weight deviation parameter includes:

[0024] The average weight of the soft capsules at all sampling times during each weight stabilization period is taken as the corresponding overall weight data value.

[0025] The difference between the overall weight data value of each weight stabilization period and the overall weight data value of the previous weight stabilization period is taken as the weight change value of each weight stabilization period.

[0026] By positively mapping the ratio between the weight change value and the standard weight of the soft capsule, a second weight deviation parameter is determined for each weight stabilization period.

[0027] Furthermore, the process of obtaining the probability of temperature anomalies includes:

[0028] The total number of weight stabilization periods in which the corresponding first weight deviation parameter is greater than the preset first parameter threshold is taken as the first reference number; the total number of weight stabilization periods in which the corresponding second weight deviation parameter is greater than the preset second parameter threshold is taken as the second reference number; the sum of the first reference number and the second reference number is normalized to determine the abnormal frequency reference value.

[0029] The mean of the average weight values ​​of soft capsules at all sampling times during each weight stabilization period is taken as the corresponding relative weight value of the soft capsule; the standard deviation of the relative weight values ​​of soft capsules during all weight stabilization periods is taken as the true weight fluctuation value.

[0030] The product between the abnormal frequency reference value and the actual weight fluctuation value is normalized to determine the probability of temperature anomaly in soft capsule production at the current temperature control time.

[0031] Furthermore, the process of controlling the temperature during the low-temperature filling production of soft capsules based on the probability of temperature anomalies includes:

[0032] Obtain the initial temperature of the guide plate before the current temperature control adjustment, as well as the highest temperature that the guide plate can control.

[0033] When the temperature anomaly probability is less than or equal to the preset anomaly threshold, the initial temperature is used as the corrected temperature of the guide plate after adjustment at the current temperature control moment.

[0034] When the probability of temperature anomaly exceeds a preset anomaly threshold, the sum of the accumulated values ​​of the first weight deviation parameters over all weight stabilization periods and the accumulated values ​​of the second weight deviation parameters over all weight stabilization periods is taken as the temperature demand level at the current temperature control moment. The product of the temperature demand level and the probability of temperature anomaly is normalized to determine the temperature adjustment range. The temperature control base value is determined based on the difference between the highest temperature and the initial temperature. The final temperature adjustment value is determined based on the product of the temperature adjustment range and the temperature control base value. The corrected temperature of the guide plate after adjustment at the current temperature control moment is determined based on the sum of the initial temperature and the final temperature adjustment value.

[0035] Secondly, this application provides an intelligent control system for low-temperature soft capsule filling production, the system comprising:

[0036] The data acquisition module is used to collect the particle count value of each filling zone and the soft capsule weight data in the temporary storage box corresponding to each filling zone at each sampling time during the low-temperature soft capsule filling process.

[0037] The first determining module is used to determine the counting and weighing delay time based on the correlation between the delay changes in soft capsule weight data and particle count values ​​in chronological order; to divide all sampling times into at least two weight stability time periods based on the counting and weighing delay time and the time when the particle count values ​​change; and to determine the first weight deviation parameter based on the standard deviation of the soft capsule weight data in each weight stability time period.

[0038] The second determining module is used to determine the second weight deviation parameter for each weight stabilization period based on the relative changes in soft capsule weight data between adjacent weight stabilization periods; and to determine the probability of temperature anomaly in soft capsule production at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the average weight fluctuation of soft capsules for each weight stabilization period before the current temperature control time.

[0039] The temperature control module is used to correct the temperature of the guide plate at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the temperature anomaly during the weight stability period at the current temperature control time, and to determine the corrected temperature of the guide plate; and to perform low-temperature filling production of soft capsules based on the corrected temperature of the guide plate.

[0040] Thirdly, this application provides a computer device including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to perform the process as described in the first aspect or any embodiment of the first aspect of this application.

[0041] Fourthly, this application provides a computer program product comprising computer program code, which, when executed, performs the process as described in the first aspect of this application or any embodiment thereof.

[0042] Fifthly, this application provides a computer-readable storage medium that stores computer program code, which, when executed, performs the process as described in the first aspect of this application or any embodiment thereof.

[0043] This application has the following beneficial effects:

[0044] This application firstly determines the counting and weighing delay time based on the low-temperature soft capsule filling production process. It considers the characteristic that, under normal circumstances, the weight data of soft capsules changes according to the magnitude of the change in the number of soft capsules in the filling zone. Then, based on the characteristic that soft capsule adhesion disrupts the stability between the soft capsule weight data and the particle count value, a first weight deviation parameter and a second weight deviation parameter are sequentially determined. Furthermore, by combining the average weight fluctuation of the soft capsules, a more accurate temperature anomaly probability is determined, and the guide plate correction temperature is further determined. This results in higher accuracy in temperature control during the low-temperature soft capsule filling production process based on the guide plate correction temperature. Attached Figure Description

[0045] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flow chart of a low-temperature soft capsule low-temperature filling production process provided in one embodiment of the present invention;

[0047] Figure 2 This is a structural diagram of an intelligent control system for low-temperature soft capsule filling production provided in one embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of a computer device structure provided in one embodiment of the present invention. Detailed Implementation

[0049] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a low-temperature soft capsule low-temperature filling production process and intelligent control system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0051] The following description, in conjunction with the accompanying drawings, details the specific solution of a low-temperature soft capsule low-temperature filling production process and intelligent control system provided by the present invention.

[0052] This application provides a low-temperature soft capsule low-temperature filling production process. Please refer to [link to relevant documentation]. Figure 1 The diagram illustrates a flow chart of a low-temperature soft capsule low-temperature filling production process according to an embodiment of the present invention, the process including:

[0053] Step S101: At each sampling moment during the low-temperature soft capsule filling process, collect the particle count value of each filling zone and the soft capsule weight data in the temporary storage box corresponding to each filling zone.

[0054] Soft capsules requiring cryogenic filling are placed into the inlet. After entering the inlet, the capsules pass through a vibrating guide plate. Below the guide plate is a temperature control device to regulate the filling temperature. The guide plate separates the soft capsules, preventing them from sticking together or becoming excessively soft due to high temperatures, which could lead to drug leakage. The guide plate has a slight inclination angle to control the flow of capsules during filling, preventing excessive accumulation and compression at the outlet. The inclination angle of the guide plate is controlled by a telescopic frame. The bottom of the guide plate connects to a separation tank, which disperses the soft capsules from the guide plate into different filling zones, allowing for multiple outlets and accelerating filling efficiency. Ventilation holes at the bottom of the separation tank are used to dry the soft capsules, further preventing sticking. During the process of the soft capsules entering the separation tank, an electric valve controls the opening and closing of a specific outlet. If a blockage occurs at an outlet, the supply of soft capsules to that outlet can be stopped without affecting the use of the other outlets. In one specific implementation of this invention, the temperature control device uses an intelligent temperature control instrument that can adjust itself according to the specific implementation environment.

[0055] After passing through the separation tank, the soft capsules enter the discharge device, which includes a temporary storage bin. A weight sensor at the bottom of the temporary storage bin monitors the weight of the soft capsules inside. The soft capsules in the temporary storage bin are fed into the discharge head via a discharge plate, thus discharging the soft capsules. Once the particle counter in the filling section reaches a predetermined quantity, it sends a signal to the electric valve at the discharge port to close the valve. In this embodiment, the predetermined quantity is set to 60, corresponding to 60 soft capsules per can, but this can be adjusted. After all valves are closed, the tilt angle of the guide plate is adjusted (reduced) using a telescopic frame to make it horizontal, preventing excessive compression of the next batch of cryogenic capsules at the bottom of the guide plate, which could cause the soft capsules to rupture and leak medication due to pressure. When the next round of filling begins, the telescopic frame is adjusted to adjust the tilt angle of the guide plate, and the electric valve is opened. The above process is repeated. The above process is carried out inside a cryogenic chamber. The temporary storage bin has two outlets: one connected to the discharge port and the other to the inlet. The temporary storage bin, connected to the inlet, allows soft capsules that have become stuck due to temperature anomalies to return to the inlet. This temperature control enables the separation of stuck soft capsules, resulting in higher quality tubular capsules produced through low-temperature soft capsule filling. It should be noted that each filling section corresponds to only one discharge port, and each discharge port corresponds to only one temporary storage bin. In the subsequent analysis of this embodiment, all filling sections and temporary storage bins refer to the same filling section and the same temporary storage bin. The filling sections and temporary storage bins correspond to each other, meaning the particle count in the filling section corresponds to the weight data of the soft capsules in the temporary storage bin.

[0056] The particle count value is collected in real time at each sampling moment by a particle counter in each filling section; the weight data of the soft capsules in the temporary storage box at each sampling moment is collected in real time by a weight sensor installed at the bottom of the temporary storage box corresponding to each filling section. In a specific implementation of this invention, the sampling frequency is set to once every 0.1 seconds, and the sampling time period is set to 1 minute before the current temperature control time. The sampling frequency and the length of the sampling time period can be adjusted according to the specific implementation environment, and will not be further limited or elaborated here. It should be noted that the temperature control frequency in this application is set to be adjusted once every minute, and can be adjusted according to the specific implementation environment, and will not be further elaborated here.

[0057] Step S102: Determine the counting and weighing delay time based on the correlation between the delay changes in soft capsule weight data and particle count values ​​in the time sequence; divide all sampling times into at least two weight stability time periods based on the counting and weighing delay time and the moment when the particle count values ​​change; determine the first weight deviation parameter based on the standard deviation of the soft capsule weight data in each weight stability time period.

[0058] Due to the standardized production of soft capsules, the weight and size of a single soft capsule are fixed. In the production process, soft capsules first pass through a filling section and then enter a temporary storage bin. Therefore, when there is no soft capsule adhesion, the particle count in the filling section usually corresponds to the weight data of the soft capsules in the corresponding temporary storage bin after a certain delay; that is, there is a fixed proportional relationship between particle count and weight. If soft capsule adhesion occurs, multiple adhered soft capsules will only be counted once, thus disrupting the proportional relationship between soft capsule weight data and particle count value. Therefore, this characteristic can be used to judge abnormal soft capsule adhesion, thereby indirectly judging abnormal temperature conditions. Considering that the premise of analyzing the proportional relationship between particle count and weight is to accurately delay the particle count value, the required counting and weighing delay time can first be determined based on the correlation characteristics reflected by the proportional relationship between particle count and weight under normal circumstances.

[0059] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the counting and weighing delay time includes:

[0060] A preset time delay window is traversed using a preset traversal step size to determine the reference delay duration obtained in each traversal. In a specific implementation of this invention, the preset traversal step size is set to 0.1 seconds, and the length of the preset time delay window is set to 5 seconds. That is, traversal starts from 0.1 seconds, and a reference delay duration is selected every 0.1 seconds until the reference delay duration reaches 5 seconds, thereby obtaining 50 reference delay durations, including 0.1 seconds. The delay matching degree of each reference delay duration is further calculated, and the counting and weighing delay duration is selected based on the delay matching degree. It should be noted that the implementer can adjust the preset traversal step size and the length of the preset time delay window according to the specific implementation environment, which will not be elaborated further here.

[0061] Each reference delay duration is sequentially used as the target delay duration; the moment when the particle count value of the filling zone changes is taken as the particle count change moment; in chronological order, each particle count change moment is delayed by the target delay duration to determine the corresponding reference interval moment; using the reference moment as the interval, all sampling moments are divided into at least two reference stable time periods. The moment when the particle count value changes is also the moment when the particle count value increases. Since this application requires strict control of the number of soft capsules per can, the increase in particle count value is usually 1.

[0062] For the actual counting and weighing delay, the reference interval corresponds to the moment when the number of particles changes, ensuring that the soft capsule weight data remains stable within the reference stable time period divided by the reference interval. That is, the reference interval corresponds to the moment when the soft capsule weight data changes. After the reference interval, the reference stable time period remains stable. Therefore, the stability of the reference stable time period can be used to determine the probability that the target delay time belongs to the actual counting and weighing delay, i.e., the delay matching degree. In addition, when the time delay of the soft capsule falling into the temporary storage box is short, it may be due to impacts, etc., resulting in a situation where the overall reference stable time period is relatively unstable, but it is actually a normal fluctuation in weight data. Therefore, the delay matching degree of the target delay time can be determined based on the length of all reference stable time periods and the stability of the soft capsule weight data.

[0063] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of delayed matching includes:

[0064] Under the target delay duration, the soft capsule weight data at all sampling times are arranged in chronological order and then curve-fitted to obtain the soft capsule weight time-series curve. On the soft capsule weight time-series curve, the mean slope of the tangent at all sampling times in each reference stable time period is taken as the corresponding fluctuation significance. The reference stable time period does not include the reference interval time. The corresponding confidence level is determined based on the normalized value of the time length of each reference stable time period. The local matching degree of each reference stable time period is determined based on the product between the negative correlation mapping value of fluctuation significance and the confidence level.

[0065] The slope represents the change in the curve. Therefore, the greater the significance of the fluctuation obtained from the mean slope of the tangent, the more it matches the characteristics of weight change. This indicates that the weight data in the corresponding reference stable time period is more unstable, and the corresponding delay matching degree is smaller. Furthermore, considering that factors such as the impact after the soft capsule falls into the storage bin can also affect the monitoring of the weight sensor, causing changes in the weight sensor within a short period of time when it should actually remain stable, the shorter the reference stable time period, the greater the impact of weight changes caused by factors such as the impact after the soft capsule falls into the storage bin on the overall stability. Therefore, the shorter the analyzed reference stable time period, the shorter the time between the two adjacent soft capsules falling in, and the lower the reliability of the corresponding stability should be; conversely, the longer the reference stable time period, the higher the reliability of the corresponding reference stable time period should be. Therefore, the reliability degree is further combined with the significance of fluctuation to comprehensively determine the local contribution of each reference stable time period to the matching degree of the target delay time, i.e., the local matching degree; finally, the local matching degree of the target delay time is determined by summing the local matching degrees of all reference stable time periods.

[0066] In one specific implementation of this invention, the process of obtaining the delay matching degree of the target delay duration is expressed by the formula: ;in, Delay duration for target The degree of delayed matching; Delay duration for target The number of reference stable time periods; Delay duration for target Next The length of a reference stable time period; Delay duration for target Next The mean of the tangent slope at all sampling times within a reference stable time period, i.e., the significance of fluctuation; Delay duration for target Next The reliability of a reference stable time period; for The normalization function ensures that the sum of the normalized values ​​of the time lengths corresponding to all reference stable time periods is 1.

[0067] Further based on the target delay duration The method for calculating the degree of delay matching is to calculate the degree of delay matching for all reference delay durations. Since the greater the degree of delay matching, the more likely the corresponding reference delay duration is to be the actual counting and weighing delay duration, the reference delay duration with the largest degree of delay matching is finally taken as the counting and weighing delay duration, which is the duration for the soft capsule weight data to respond to the change after the particle count value changes.

[0068] Furthermore, based on the counting and weighing delay time combined with the moment when the particle count value changes, all sampling moments are divided into at least two weight-stable time periods. The division process is similar to the method for dividing the reference stable time period. Specifically: in chronological order, each particle count change moment is delayed by the counting and weighing delay time to determine the corresponding weight change moment; all sampling moments are divided into at least two weight-stable time periods with the weight change moment as the interval; the weight-stable time period does not include the weight change moment. It should be noted that the weight-stable time period in this embodiment includes at least two sampling moments; therefore, when selecting the sampling frequency, a higher sampling frequency is usually required for analysis to ensure that each weight-stable time period includes at least two sampling moments.

[0069] After determining the counting and weighing delay time, it is further necessary to analyze the proportional relationship between particle count and weight to indirectly determine abnormal soft capsule adhesion and adjust the temperature accordingly. If there is no adhesion between soft capsules on the feed plate, each additional soft capsule adds the weight corresponding to the weight of one additional soft capsule. Therefore, the average weight of the soft capsules should remain stable over time, and their size should remain near the standard weight. Conversely, if adhesion exists, it indicates that the weight change corresponding to each additional soft capsule is actually the weight of multiple soft capsules. Therefore, the need for temperature adjustment can be determined based on the weight increase. Furthermore, the first weight deviation parameter is determined based on the standard deviation of the soft capsule weight data during each weight stabilization period.

[0070] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the first weight deviation parameter includes:

[0071] The reference particle count for each weight stabilization period is determined. Based on the particle count value after the change in particle count at each weight-temperature time interval, the corresponding reference particle count is determined. Specifically, the particle count value at the next sampling time after each particle count change is used as the changed count; the changed count at each weight change time is used as the reference particle count for the first weight stabilization period after each weight change. Through correspondence analysis, the reference particle count matching each weight stabilization period is determined, that is, the particle count value after the change in particle count is used as the reference particle count for the corresponding weight stabilization period after the change in soft capsule weight data response.

[0072] In each weight stabilization period, the ratio between the soft capsule weight data and the number of reference particles at each sampling time is used as the corresponding average soft capsule weight value; the ratio between the average soft capsule weight value and the standard soft capsule weight is used to determine the reference standard ratio at each sampling time; the mean of the reference standard ratios corresponding to all sampling times in each weight stabilization period is positively correlated to determine the corresponding first weight deviation parameter. In a specific implementation of this invention, the standard soft capsule weight is pre-obtained through the soft capsule production standard.

[0073] When there is no soft capsule adhesion, the calculated average weight of a single soft capsule remains constant, so the average weight should be consistent with the standard weight, and the corresponding reference standard ratio is usually 1. However, when soft capsule adhesion exists, the number of reference particles due to adhesion is less than the actual number, resulting in a larger calculated average weight relative to the standard weight; therefore, the obtained reference standard ratio is usually greater than 1. To avoid the influence of randomness, a first weight deviation parameter characterizing the abnormal soft capsule adhesion is determined by calculating the mean of the reference standard ratios at all sampling times and performing a positive correlation mapping. In a specific implementation of this invention, the method for performing a positive correlation mapping on the mean of the reference standard ratios corresponding to all sampling times within each weight stability period is as follows: subtract 1 from the mean of the reference standard ratios corresponding to all sampling times within each weight stability period to obtain the corresponding positive correlation mapping result, i.e., the first weight deviation parameter. A first weight deviation parameter greater than 0 corresponds to an abnormal adhesion situation, and a larger first weight deviation parameter indicates a larger number of adhered soft capsules and a more severe adhesion abnormality.

[0074] Step S103: Based on the relative changes in soft capsule weight data between adjacent weight stabilization time periods, determine the second weight deviation parameter for each weight stabilization time period; based on the first weight deviation parameter, the second weight deviation parameter, and the average weight fluctuation of soft capsules for each weight stabilization time period before the current temperature control time, determine the probability of temperature anomaly in soft capsule production at the current temperature control time.

[0075] Furthermore, considering that the particle count value increases by 1 each time it changes, the deviation between the soft capsule weight data of adjacent weight stabilization periods usually corresponds to the standard weight of the soft capsule when there is no adhesion. Conversely, when adhesion occurs, the deviation between the soft capsule weight data of adjacent weight stabilization periods will be greater than the standard weight of the soft capsule. Therefore, based on this characteristic, the second weight deviation parameter for each weight stabilization period is determined according to the relative change of soft capsule weight data between adjacent weight stabilization periods.

[0076] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the second weight deviation parameter includes:

[0077] The average weight of the soft capsules at all sampling times within each weight stabilization period is taken as the corresponding overall weight data value. The difference between the overall weight data value of each weight stabilization period and the overall weight data value of the previous weight stabilization period is taken as the weight change value for each weight stabilization period. The overall weight data value represents the overall size of the soft capsules within a weight stabilization period. Therefore, based on the characteristic that a single capsule count corresponds to a weight stabilization period, if there is no soft capsule adhesion, the weight change value should be consistent with the standard weight of the soft capsules. Conversely, if soft capsule adhesion occurs within a corresponding weight stabilization period, the weight change value will be greater than the standard weight of the soft capsules, and is usually an integer multiple of the standard mass of the soft capsules. Therefore, a positive correlation mapping is further performed between the weight change value and the standard weight of the soft capsules to determine the second weight deviation parameter for each weight stabilization period.

[0078] In one specific implementation of this invention, the method for positively mapping the ratio between the weight change value and the standard weight of the soft capsule is as follows: subtract 1 from the ratio between the weight change value and the standard weight of the soft capsule to obtain the corresponding positive correlation mapping result, which is the second weight deviation parameter; such that when the second weight deviation parameter is greater than 0, it corresponds to an adhesion abnormality, and the larger the second weight deviation parameter is, the more adhesions there are and the more severe the adhesion abnormality is.

[0079] When there is no adhesion, the average weight of soft capsules during each weight stabilization period is usually a constant value. However, the more severe the adhesion and the higher the frequency of adhesion, the more unstable the average weight of soft capsules during each weight stabilization period becomes. The more severe the adhesion, the more abnormal the temperature. Therefore, based on the first weight deviation parameter, the second weight deviation parameter, and the fluctuation of the average weight of soft capsules during each weight stabilization period before the current temperature control time, the probability of temperature anomaly in soft capsule production at the current temperature control time can be determined.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the probability of temperature anomalies includes:

[0081] The total number of weight stabilization time periods where the corresponding first weight deviation parameter is greater than a preset first parameter threshold is used as the first reference number; the total number of weight stabilization time periods where the corresponding second weight deviation parameter is greater than a preset second parameter threshold is used as the second reference number; the sum of the first and second reference numbers is normalized to determine the anomaly frequency reference value. In a specific implementation of this invention, the preset first parameter threshold is set to 0. Since both the first and second weight deviation parameters being greater than 0 correspond to adhesion anomalies, the larger the first and second reference numbers, the more severe the temperature anomaly, and the higher the corresponding probability of temperature anomaly.

[0082] The mean of the average weight of soft capsules at all sampling times within each weight stabilization period is taken as the corresponding relative weight value of the soft capsule; the standard deviation of the relative weight values ​​of soft capsules across all weight stabilization periods is taken as the true weight fluctuation value. The standard deviation can characterize the dispersion of a set of data. Therefore, the larger the true weight fluctuation value obtained from the standard deviation of the relative weight of soft capsules across all weight stabilization periods, the more unstable the overall value of the average weight of soft capsules in each weight stabilization period is, the more severe the corresponding adhesion anomaly is, and the higher the probability of the corresponding temperature anomaly should be.

[0083] Therefore, the product between the abnormal frequency reference value and the actual weight fluctuation value is further normalized based on the correlation to determine the probability of temperature anomaly in soft capsule production at the current temperature control moment; thus, the higher the probability of temperature anomaly, the more necessary temperature control becomes. In a specific implementation of this invention, the process of obtaining the temperature anomaly probability is expressed by the formula: ;in, The probability of temperature anomalies in soft capsule production at the current temperature control point; This is the standard deviation of the relative weight of the soft capsules during all weight stabilization periods prior to the current temperature control moment, which is also the true weight fluctuation value. The first reference number is the total number of time periods during which the first weight deviation parameter is greater than the preset first parameter threshold before the current temperature control time. This refers to the total number of time periods during which the second weight deviation parameter is greater than the preset second parameter threshold before the current temperature control time, which is also known as the second reference number. It is a linear normalization function; other normalization methods may be adopted depending on the specific implementation environment. This is a reference value for the frequency of abnormalities.

[0084] Step S104: Based on the first weight deviation parameter, the second weight deviation parameter, and the temperature anomaly during the weight stability period at the current temperature control time, correct the temperature of the guide plate at the current temperature control time and determine the corrected temperature of the guide plate; perform low-temperature filling production of soft capsules based on the corrected temperature of the guide plate.

[0085] The higher the probability of temperature anomalies, the greater the need for temperature control. Since capsule adhesion is caused by low temperatures, the greater the probability of temperature anomalies, the larger the temperature adjustment should be. Further temperature control for soft capsule low-temperature filling production should be implemented based on the probability of temperature anomalies.

[0086] Preferably, in some possible implementations of the embodiments of the present invention, the process of controlling the temperature during the low-temperature filling production of soft capsules based on the probability of temperature anomalies includes:

[0087] The system obtains the initial temperature of the guide plate before adjustment at the current temperature control moment, as well as the highest temperature that the guide plate can control. When the probability of temperature anomaly is less than or equal to a preset anomaly threshold, the initial temperature is used as the corrected temperature of the guide plate after adjustment at the current temperature control moment. In a specific implementation of this invention, the preset anomaly threshold is set to 0.2, which can be adjusted according to the specific implementation environment; that is, when the probability of temperature anomaly is low, the temperature is considered relatively normal, and no temperature adjustment is made, using the initial temperature before adjustment as the corrected temperature of the guide plate after adjustment.

[0088] When the probability of temperature anomaly exceeds a preset anomaly threshold, the larger the overall value of the first and second weight deviation parameters, the more severe the soft capsule adhesion, and the higher the required temperature should be to reduce soft capsule adhesion. Therefore, the sum of the cumulative values ​​of the first weight deviation parameters and the second weight deviation parameters over all weight stabilization periods is used as the temperature demand at the current temperature control moment; this ensures that the greater the temperature demand, the greater the upward adjustment of the temperature. Conversely, a higher probability of temperature anomaly indicates more severe adhesion, and a greater need for upward temperature adjustment; therefore, the product of the temperature demand and the temperature anomaly probability is normalized to determine the temperature adjustment range.

[0089] The base temperature control value is determined based on the difference between the highest temperature and the initial temperature. The final temperature adjustment value is determined by multiplying the temperature adjustment range by the base temperature control value. The corrected guide plate temperature at the current temperature control moment is determined by the sum of the initial temperature and the final temperature adjustment value. The base temperature control value, obtained from the difference between the highest and initial temperatures, ensures that the temperature adjustment does not exceed the upper temperature limit, resulting in a more accurate corrected guide plate temperature. Further details are omitted here.

[0090] In one specific implementation of this invention, the process of obtaining the guide plate correction temperature is expressed by the following formula: ;in, Correct the temperature of the guide plate after the current temperature control time. This is the initial temperature before the current temperature control adjustment. This is the highest temperature that the guide plate can control; The probability of temperature anomalies in soft capsule production at the current temperature control point; This is the cumulative value of the first weight deviation parameter for all weight stabilization periods prior to the current temperature control moment; This is the cumulative value of the second weight deviation parameter for all weight stabilization periods prior to the current temperature control moment; The temperature requirement at the current temperature control moment; This represents the temperature adjustment range at the current temperature control moment. This is the baseline value for temperature control at the current temperature control moment; This represents the final temperature adjustment value at the current temperature control moment.

[0091] After the guide plate temperature is adjusted according to the current temperature control time, the temperature is controlled in real time by the temperature control device below the guide plate, and the low temperature soft capsule low temperature filling production continues.

[0092] In summary, a low-temperature soft capsule filling production process is first based on the low-temperature soft capsule filling production flow. Given that the weight data of soft capsules changes accordingly when the number of soft capsules in the filling zone changes under normal circumstances, the counting and weighing delay time is first determined. Then, based on the characteristic that soft capsule adhesion disrupts the stability between soft capsule weight data and particle count values, a first weight deviation parameter and a second weight deviation parameter are sequentially determined. Furthermore, by combining the average weight fluctuation of soft capsules, a more accurate temperature anomaly probability is determined, and the guide plate correction temperature is further determined, resulting in higher accuracy in temperature control during the low-temperature soft capsule filling production process based on the guide plate correction temperature.

[0093] This application also provides an intelligent control system for low-temperature soft capsule filling production. Please refer to [link / reference]. Figure 2 The diagram shows a structural diagram of an intelligent control system for low-temperature soft capsule filling production according to an embodiment of the present invention. The system includes: a data acquisition module 201, a first determination module 202, a second determination module 203, and a temperature control module 204.

[0094] Data acquisition module 201 is used to collect the particle count value of each filling zone and the soft capsule weight data in the temporary storage box corresponding to each filling zone at each sampling time during the low temperature soft capsule filling production process.

[0095] The first determining module 202 is used to determine the counting and weighing delay time based on the correlation between the delay changes between the soft capsule weight data and the particle count value in the time sequence; divide all sampling times into at least two weight stability time periods based on the counting and weighing delay time and the time when the particle count value changes; and determine the first weight deviation parameter based on the standard deviation of the soft capsule weight data in each weight stability time period.

[0096] The second determining module 203 is used to determine the second weight deviation parameter for each weight stable time period based on the relative change of soft capsule weight data between adjacent weight stable time periods; and to determine the probability of temperature anomaly in soft capsule production at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the average weight fluctuation of soft capsules for each weight stable time period before the current temperature control time.

[0097] The temperature control module 204 is used to correct the temperature of the guide plate at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the temperature anomaly during the weight stability period at the current temperature control time, and to determine the corrected temperature of the guide plate; and to carry out low-temperature filling production of soft capsules based on the corrected temperature of the guide plate.

[0098] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent control system for low-temperature soft capsule low-temperature filling production provided in the above embodiments and the low-temperature soft capsule low-temperature filling production process embodiment belong to the same concept, and the specific implementation process is detailed in the process embodiment, which will not be repeated here.

[0099] This application also provides a computer device; please refer to [link / reference]. Figure 3The illustration shows a schematic diagram of a computer device structure provided by an embodiment of the present invention. The computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can execute any of the aforementioned low-temperature soft capsule low-temperature filling production processes.

[0100] This application also provides a computer program product that, when run on a computer device, enables the computer device to execute any of the aforementioned low-temperature soft capsule low-temperature filling production processes.

[0101] This application also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer device, the computer device can execute any of the aforementioned low-temperature soft capsule low-temperature filling production processes.

[0102] In the embodiments provided in this application, it should be understood that the computer equipment, computer program product and computer-readable storage medium provided are all used to execute the corresponding low-temperature soft capsule low-temperature filling production process provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the low-temperature soft capsule low-temperature filling production process provided above, and will not be repeated here.

[0103] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A low-temperature soft capsule low-temperature filling production process, characterized in that, The process includes: At each sampling moment during the low-temperature soft capsule filling process, the particle count value of each filling zone and the soft capsule weight data in the temporary storage box corresponding to each filling zone are collected. Based on the correlation between the delayed changes in soft capsule weight data and particle count values ​​in chronological order, the counting and weighing delay time is determined; based on the counting and weighing delay time and the moment when the particle count value changes, all sampling moments are divided into at least two weight stability time periods; based on the standard deviation of the soft capsule weight data in each weight stability time period, a first weight deviation parameter is determined. Based on the relative changes in soft capsule weight data between adjacent weight stabilization periods, the second weight deviation parameter for each weight stabilization period is determined; based on the first weight deviation parameter, the second weight deviation parameter, and the average weight fluctuation of soft capsules for each weight stabilization period before the current temperature control time, the probability of temperature anomaly in soft capsule production at the current temperature control time is determined. Based on the first weight deviation parameter, the second weight deviation parameter, and the temperature anomaly probability during the current weight stability period at the current temperature control moment, the temperature of the guide plate at the current temperature control moment is corrected to determine the corrected temperature of the guide plate; and soft capsule low-temperature filling production is carried out based on the corrected temperature of the guide plate. The process of obtaining the weight stability period includes: The moment when the particle count value of the filling zone changes is taken as the particle count change moment; in terms of time sequence, each particle count change moment is delayed by the counting and weighing delay time to determine the corresponding weight change moment; all sampling moments are divided into at least two weight stability time periods with the weight change moment as the interval; the weight stability time period does not include the weight change moment; The process of obtaining the first weight deviation parameter includes: Determine the reference particle count for each weight stabilization period; based on the particle count value after the change in particle count at each weight stabilization period, determine the corresponding reference particle count. In each weight stabilization period, the average weight of the soft capsules is determined by the ratio between the soft capsule weight data at each sampling time and the number of reference particles. The reference standard ratio at each sampling time is determined by the ratio between the average weight of the soft capsules and the standard weight of the soft capsules. The mean of the reference standard ratios corresponding to all sampling times in each weight stabilization period is positively correlated to determine the corresponding first weight deviation parameter. The process of obtaining the second weight deviation parameter includes: The average weight of the soft capsules at all sampling times during each weight stabilization period is taken as the corresponding overall weight data value. The difference between the overall weight data value of each weight stabilization period and the overall weight data value of the previous weight stabilization period is taken as the weight change value of each weight stabilization period. By performing a positive correlation mapping between the weight change value and the standard weight of the soft capsule, a second weight deviation parameter is determined for each weight stabilization period. The process of obtaining the probability of temperature anomalies includes: The total number of weight stabilization periods in which the corresponding first weight deviation parameter is greater than the preset first parameter threshold is taken as the first reference number; the total number of weight stabilization periods in which the corresponding second weight deviation parameter is greater than the preset second parameter threshold is taken as the second reference number; the sum of the first reference number and the second reference number is normalized to determine the abnormal frequency reference value. The mean of the average weight values ​​of soft capsules at all sampling times during each weight stabilization period is taken as the corresponding relative weight value of the soft capsule; the standard deviation of the relative weight values ​​of soft capsules during all weight stabilization periods is taken as the true weight fluctuation value. The product between the abnormal frequency reference value and the actual weight fluctuation value is normalized to determine the probability of temperature anomaly in soft capsule production at the current temperature control time.

2. The low-temperature soft capsule low-temperature filling production process according to claim 1, characterized in that, The process of obtaining the counting and weighing delay time includes: The preset time delay window is traversed with a preset traversal step size to determine the reference delay duration obtained in each traversal; each reference delay duration is used as the target delay duration in turn; in terms of time sequence, each particle number change moment is delayed by the target delay duration to determine the corresponding reference interval moment; with the reference moment as the interval, all sampling moments are divided into at least two reference stable time periods. Based on the length of all reference stable time periods and the stability of soft capsule weight data, the degree of delay matching for the target delay duration is determined; the reference delay duration with the highest degree of delay matching is taken as the counting and weighing delay duration.

3. The low-temperature soft capsule low-temperature filling production process according to claim 2, characterized in that, The process of obtaining the degree of delay matching includes: Under the target delay duration, the soft capsule weight data at all sampling times are arranged in chronological order and then curve-fitted to obtain a soft capsule weight time-series curve. On the soft capsule weight time-series curve, the mean of the slope of the tangent at all sampling times in each reference stable time period is taken as the corresponding fluctuation significance. The reference stable time period does not include the reference interval time. The corresponding confidence level is determined based on the normalized value of the time length of each reference stable time period. The local matching degree for each reference stable time period is determined by multiplying the negative correlation mapping value of the volatility significance with the confidence level; the delay matching degree for the target delay duration is determined by summing the local matching degrees for all reference stable time periods.

4. The low-temperature soft capsule low-temperature filling production process according to claim 1, characterized in that, The process of obtaining the number of reference particles includes: The particle count value at the next sampling time after each particle number change is taken as the changed quantity; the changed quantity of the particle number at the corresponding weight change time is taken as the reference particle number for the first weight stabilization period after each weight change time.

5. The low-temperature soft capsule low-temperature filling production process according to claim 1, characterized in that, The process of controlling the temperature during the low-temperature filling production of soft capsules based on the probability of temperature anomalies includes: Obtain the initial temperature of the guide plate before the current temperature control adjustment, as well as the highest temperature that the guide plate can control. When the temperature anomaly probability is less than or equal to the preset anomaly threshold, the initial temperature is used as the corrected temperature of the guide plate after adjustment at the current temperature control moment. When the probability of temperature anomaly exceeds a preset anomaly threshold, the sum of the accumulated values ​​of the first weight deviation parameters over all weight stabilization periods and the accumulated values ​​of the second weight deviation parameters over all weight stabilization periods is taken as the temperature demand level at the current temperature control moment. The product of the temperature demand level and the probability of temperature anomaly is normalized to determine the temperature adjustment range. The temperature control base value is determined based on the difference between the highest temperature and the initial temperature. The final temperature adjustment value is determined based on the product of the temperature adjustment range and the temperature control base value. The corrected temperature of the guide plate after adjustment at the current temperature control moment is determined based on the sum of the initial temperature and the final temperature adjustment value.

6. A smart control system for low-temperature soft capsule filling production, characterized in that, The system includes: The data acquisition module is used to collect the particle count value of each filling zone and the soft capsule weight data in the temporary storage box corresponding to each filling zone at each sampling time during the low-temperature soft capsule filling process. The first determining module is used to determine the counting and weighing delay time based on the correlation between the delay changes in soft capsule weight data and particle count values ​​in chronological order; to divide all sampling times into at least two weight stability time periods based on the counting and weighing delay time and the time when the particle count values ​​change; and to determine the first weight deviation parameter based on the standard deviation of the soft capsule weight data in each weight stability time period. The process of obtaining the weight stability period includes: The moment when the particle count value of the filling zone changes is taken as the particle count change moment; in terms of time sequence, each particle count change moment is delayed by the counting and weighing delay time to determine the corresponding weight change moment; all sampling moments are divided into at least two weight stability time periods with the weight change moment as the interval; the weight stability time period does not include the weight change moment; The process of obtaining the first weight deviation parameter includes: Determine the reference particle count for each weight stabilization period; based on the particle count value after the change in particle count at each weight stabilization period, determine the corresponding reference particle count. In each weight stabilization period, the average weight of the soft capsules is determined by the ratio between the soft capsule weight data at each sampling time and the number of reference particles. The reference standard ratio at each sampling time is determined by the ratio between the average weight of the soft capsules and the standard weight of the soft capsules. The mean of the reference standard ratios corresponding to all sampling times in each weight stabilization period is positively correlated to determine the corresponding first weight deviation parameter. The second determining module is used to determine the second weight deviation parameter for each weight stabilization period based on the relative changes in soft capsule weight data between adjacent weight stabilization periods; and to determine the probability of temperature anomaly in soft capsule production at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the average weight fluctuation of soft capsules for each weight stabilization period before the current temperature control time. The process of obtaining the second weight deviation parameter includes: The average weight of the soft capsules at all sampling times during each weight stabilization period is taken as the corresponding overall weight data value. The difference between the overall weight data value of each weight stabilization period and the overall weight data value of the previous weight stabilization period is taken as the weight change value of each weight stabilization period. By performing a positive correlation mapping between the weight change value and the standard weight of the soft capsule, a second weight deviation parameter is determined for each weight stabilization period. The process of obtaining the probability of temperature anomalies includes: The total number of weight stabilization periods in which the corresponding first weight deviation parameter is greater than the preset first parameter threshold is taken as the first reference number; the total number of weight stabilization periods in which the corresponding second weight deviation parameter is greater than the preset second parameter threshold is taken as the second reference number; the sum of the first reference number and the second reference number is normalized to determine the abnormal frequency reference value. The mean of the average weight values ​​of soft capsules at all sampling times during each weight stabilization period is taken as the corresponding relative weight value of the soft capsule; the standard deviation of the relative weight values ​​of soft capsules during all weight stabilization periods is taken as the true weight fluctuation value. The product between the abnormal frequency reference value and the actual weight fluctuation value is normalized to determine the probability of temperature abnormality in soft capsule production at the current temperature control time. The temperature control module is used to correct the temperature of the guide plate at the current temperature control time based on the first weight deviation parameter, the second weight deviation parameter, and the temperature anomaly during the weight stability period at the current temperature control time, and to determine the corrected temperature of the guide plate; and to perform low-temperature filling production of soft capsules based on the corrected temperature of the guide plate.

Images