A tea saponin granule preparation process optimization method and system based on intelligent regulation
By evaluating tea saponin granules and constructing process parameter regression model, equipment failure and particle size and moisture content adjustment problems in the preparation of tea saponin granules are solved, and efficient preparation and stable delivery of tea saponin granules are achieved.
Patent Information
- Application Number
- CN202410683202.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-30
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-05-30
AI Technical Summary
Equipment failures and problems in the preparation process of tea saponin granules and particle size and moisture content adjustment have led to unstable preparation efficiency and quality, which cannot meet customer needs.
By evaluating the average particle size and moisture content of tea saponin particles, a process parameter regression model is constructed, the target combination process parameters are determined, and equipment defect positioning and optimization are carried out during the preparation process to achieve intelligent adjustment and equipment failure repair.
It improves the preparation efficiency and delivery quality of tea saponin particles, meets customers' requirements for particle size and moisture content, and ensures the stability and accuracy of production.
Smart Images

Figure CN118520425B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of production process optimization, and in particular to a method and system for optimizing the preparation process of tea saponin particles based on intelligent regulation. Background Art
[0002] Tea saponin granules are granular products made of tea saponin as the main ingredient. Tea saponin is a natural saponin compound extracted from tea trees and other tea plants, with multiple biological activities and application values. Tea saponin granules are prepared by a specific process, and the process needs to be applied on the corresponding preparation equipment. Since the size of tea saponin particles may vary with demand, and its water content may also vary with demand, it is necessary to adjust the size and water content of tea saponin particles during the preparation of tea saponin particles. The method of adjustment is to intelligently adjust the preparation process of tea saponin particle preparation equipment so that the size and water content of tea saponin particles meet the requirements. During the intelligent adjustment of the preparation process, equipment failure and other situations may be encountered. In order to prevent equipment failure from causing the inability to accurately prepare tea saponin particles, and to ensure that tea saponin particles can be delivered within the scheduled time, and to improve the production and delivery rate, it is necessary to optimize the preparation process of tea saponin particles. Summary of the invention
[0003] The present invention overcomes the deficiencies of the prior art and provides a method and system for optimizing the preparation process of tea saponin particles based on intelligent regulation.
[0004] In order to achieve the above object, the technical solution adopted by the present invention is:
[0005] The first aspect of the present invention provides a method for optimizing the preparation process of tea saponin particles based on intelligent regulation, comprising the following steps:
[0006] S102: evaluating the average particle size and water content of the prepared tea saponin particles, and classifying the equipment for preparing the tea saponin particles based on the evaluation results;
[0007] S104: performing tea saponin granule preparation tests based on different process parameters in the tea saponin granule preparation equipment to be optimized, constructing a process parameter regression model based on the test results, and obtaining qualified combined process parameters;
[0008] S106: Determine the target combination process parameters, control the tea saponin granule preparation equipment to be optimized to continuously prepare the tea saponin granules under the target combination process parameters, and locate and optimize equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process.
[0009] Furthermore, in a preferred embodiment of the present invention, the step S102 is specifically:
[0010] Calibrate a device capable of preparing tea saponin granules as a tea saponin granule preparation device, and obtain sample particles of tea saponin granules prepared by the tea saponin granule preparation device and calibrate them as tea saponin granule samples;
[0011] Obtain a laser particle size analyzer, use the laser particle size analyzer to measure the average particle size of the tea saponin particle sample, obtain a historical data network, and retrieve a standard average particle size threshold of the tea saponin particle sample on the historical data network;
[0012] If the average particle size of the tea saponin granule sample is within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with qualified average particle size; if the average particle size of the tea saponin granule sample is not within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified average particle size;
[0013] Calculate the weight of the tea saponin particle sample, obtain a thermogravimetric analyzer, place the tea saponin particle sample in the thermogravimetric analyzer, and obtain a heating rate threshold that the tea saponin particle sample can withstand and a maximum temperature that the tea saponin particle sample can withstand in the historical data network;
[0014] Controlling the thermogravimetric analyzer to heat the tea saponin particle sample based on a heating rate threshold that the tea saponin particle sample can withstand, and stopping heating when the temperature in the thermogravimetric analyzer reaches a maximum temperature that the tea saponin particle sample can withstand, thereby obtaining a heated tea saponin particle sample;
[0015] Calculating the weight of the heated tea saponin granule sample, and subtracting the weight of the heated tea saponin granule sample from the weight of the tea saponin granule sample to obtain the water content of the tea saponin granule sample;
[0016] A standard moisture content threshold of the tea saponin granule sample is preset. If the moisture content of the tea saponin granule sample is within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with qualified moisture content. If the moisture content of the tea saponin granule sample is not within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified moisture content.
[0017] The tea saponin particles are analyzed. When the tea saponin particles have unqualified average particle size or unqualified water content, the tea saponin particle preparation equipment is evaluated as tea saponin particle preparation equipment to be optimized.
[0018] Furthermore, in a preferred embodiment of the present invention, the step S104 is specifically:
[0019] In the tea saponin granule preparation device, a process for controlling the volume of the tea saponin granules and a process for controlling the water content of the tea saponin granules are obtained, wherein the process for controlling the volume of the tea saponin granules is calibrated as a volume control process, and the process for controlling the water content of the tea saponin granules is calibrated as a water content control process;
[0020] If the tea saponin granule preparation equipment is the tea saponin granule preparation equipment to be optimized, then the process parameter threshold of the volume control process is obtained and calibrated as the volume control process parameter threshold, and the process parameter threshold of the water content control process is obtained and calibrated as the water content control process parameter threshold;
[0021] Combining a volume control process and a water content control process to obtain a combined process, and obtaining different combined process parameters based on the volume control process parameter threshold and the water content control process parameter threshold;
[0022] Preset a preparation test time, during which all combined process parameters are introduced into the tea saponin granule preparation device to be optimized, and control the tea saponin granule preparation device to be optimized to perform tea saponin granule preparation tests based on different combined process parameters, so as to obtain tea saponin granules under different combined process parameters;
[0023] Determine the average particle size and water content of the tea saponin particles under different combinations of process parameters, and construct a process parameter regression model based on the average particle size and water content of the tea saponin particles under different combinations of process parameters, wherein the process parameter regression model can pair the tea saponin particles with different average particle sizes and water contents with different combinations of process parameters;
[0024] Based on the process parameter regression model, the combined process parameters corresponding to the average particle size and water content of the tea saponin particles being in a qualified state are determined and calibrated as qualified combined process parameters, wherein the average particle size and water content of the tea saponin particles being in a qualified state means that the tea saponin particles are tea saponin particles with a qualified average particle size, and the tea saponin particles are tea saponin particles with a qualified water content.
[0025] Furthermore, in a preferred embodiment of the present invention, the step S106 is specifically as follows:
[0026] Obtaining order information of tea saponin particles, and determining the target average particle size and water content of the tea saponin particles based on the order information of the tea saponin particles, and calibrating them as the target average particle size and target water content;
[0027] In the process parameter regression model, the combined process parameters that can make the average particle size and water content of tea saponin particles equal to the target average particle size and target water content are determined and calibrated as the optimal combined process parameters;
[0028] All qualified combined process parameters are grouped into a qualified combined process parameter set, and it is determined whether there is a qualified combined process parameter in the qualified combined process parameter set that is equal to the optimal combined process parameter;
[0029] If yes, the best combination process parameters are calibrated as the target combination process parameters; if no, all qualified combination process parameters and the best combination process parameters are converted into feature data to obtain qualified combination process feature parameters and the best combination process feature parameters;
[0030] The optimal combined process characteristic parameters are calibrated as reference characteristic parameters, a cosine metric algorithm is introduced, and cosine metric values between all qualified combined process characteristic parameters and the reference characteristic parameters are calculated based on the cosine metric algorithm;
[0031] Selecting a qualified combined process characteristic parameter with the largest cosine metric value with the reference characteristic parameter, calibrating it as a target combined process characteristic parameter, and performing feature conversion on the target combined process characteristic parameter to obtain the target combined process parameter;
[0032] Based on the target combined process parameters, the tea saponin granule preparation equipment to be optimized is controlled to continuously prepare tea saponin granules, and during the tea saponin granule preparation process, equipment defect analysis and equipment defect optimization are performed on the tea saponin granule preparation equipment to be optimized.
[0033] Furthermore, in a preferred embodiment of the present invention, based on the target combined process parameters, the tea saponin granule preparation equipment to be optimized is controlled to continuously prepare tea saponin granules, and during the tea saponin granule preparation process, equipment defect analysis and equipment defect optimization are performed on the tea saponin granule preparation equipment to be optimized, specifically:
[0034] Applying the target combined process parameters in the tea saponin granule preparation equipment to be optimized, a type of tea saponin granule preparation equipment is obtained;
[0035] Obtaining a sensor for monitoring a combined process parameter in a tea saponin granule preparation device, calibrating the sensor as a process parameter monitoring sensor, and controlling the tea saponin granule preparation device to continuously prepare tea saponin granules;
[0036] In the process of a type of tea saponin granule preparation equipment continuously preparing tea saponin granules, a combined process parameter being run in the type of tea saponin granule preparation equipment is monitored in real time by a process parameter monitoring sensor, and calibrated as a real-time combined process parameter;
[0037] If the real-time combined process parameters are constantly equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a qualified tea saponin granule preparation equipment;
[0038] If the real-time combined process parameters are not constant and equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a first-class unqualified tea saponin granule preparation equipment;
[0039] If the tea saponin granule preparation equipment is a type of unqualified tea saponin granule preparation equipment, then based on the real-time combined process parameters and the target combined process parameters, the real-time process parameters and the target process parameters of all sub-processes in the type of unqualified tea saponin granule preparation equipment are obtained, wherein the sub-processes are a volume control process and a moisture content control process;
[0040] Calculate the Euclidean distance between the real-time process parameters and the target process parameters of all sub-processes. If the Euclidean distance between the real-time process parameters and the target process parameters of a sub-process is greater than a preset value, the corresponding sub-process is marked as an abnormal sub-process.
[0041] In the historical data network, the maintenance plan of the abnormal sub-process is retrieved and output to obtain a type of maintenance tea saponin granule preparation equipment. The target combination process parameters are applied in the type of maintenance tea saponin granule preparation equipment and tea saponin granules are continuously prepared. If the real-time combination process parameters obtained in the type of maintenance tea saponin granule preparation equipment are still not constant and equal to the target combination process parameters, a secondary analysis and optimization of equipment defects is performed on the type of maintenance tea saponin granule preparation equipment.
[0042] Furthermore, in a preferred embodiment of the present invention, the secondary analysis and optimization of equipment defects for a type of tea saponin granule preparation equipment under maintenance is specifically as follows:
[0043] In a type of tea saponin granule preparation equipment for maintenance, an algorithm for preparing tea saponin granules is obtained and calibrated as a preparation algorithm, and different algorithm functions are run and tested in the preparation algorithm to determine whether any algorithm function cannot be run;
[0044] If so, the algorithm function that cannot be run is marked as an abnormally run algorithm function, and a patch of the abnormally run algorithm function is retrieved and output in the historical data network, so that the abnormally run algorithm function does not exist in the preparation algorithm, and an optimized preparation algorithm is obtained;
[0045] The optimized preparation algorithm is applied to a type of tea saponin granule preparation equipment for maintenance. If the real-time combined process parameters of the type of tea saponin granule preparation equipment for maintenance to which the optimized preparation algorithm is applied are still not constant and equal to the target combined process parameters, the circuit structure of the type of tea saponin granule preparation equipment for maintenance is obtained, and the circuit structure of the type of tea saponin granule preparation equipment for maintenance is tested for voltage by a multimeter to obtain circuit nodes whose voltages do not match preset values, and the nodes are marked as abnormal circuit nodes;
[0046] The repair scheme of abnormal circuit nodes is retrieved and output in the historical data network, so that the real-time combined process parameters of a type of repaired tea saponin granule preparation equipment using the optimized preparation algorithm are constant and equal to the target combined process parameters, and qualified tea saponin granule preparation equipment is obtained.
[0047] The second aspect of the present invention further provides a tea saponin granule preparation process optimization system based on intelligent regulation, the process optimization system comprising a memory and a processor, the memory storing a process optimization method, and when the process optimization method is executed by the processor, the following steps are implemented:
[0048] The prepared tea saponin particles are evaluated for average particle size and water content, and the equipment for preparing the tea saponin particles is classified based on the evaluation results;
[0049] The tea saponin granule preparation test is carried out based on different process parameters in the tea saponin granule preparation equipment to be optimized, a process parameter regression model is constructed based on the test results, and qualified combined process parameters are obtained;
[0050] Determine the target combination process parameters, control the tea saponin granule preparation equipment to be optimized to continuously prepare tea saponin granules under the target combination process parameters, and locate and optimize equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process.
[0051] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: by evaluating the average particle size and water content of the prepared tea saponin particles, obtaining tea saponin particle preparation equipment with abnormalities, and conducting process parameter testing and process parameter regression model construction in the tea saponin particle preparation equipment with abnormalities, thereby obtaining qualified combined process parameters; applying qualified combined process parameters in the tea saponin particle preparation equipment, continuously preparing tea saponin particles, and locating and optimizing equipment defects of the tea saponin particle preparation equipment during the preparation process. The present invention can optimize the process and improve the preparation efficiency of tea saponin particles by intelligently adjusting the tea saponin particle preparation equipment, while meeting the preparation effect required by customers and improving the delivery efficiency and delivery quality of tea saponin particles. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.
[0053] Figure 1A flow chart of a tea saponin granule preparation process optimization method based on intelligent regulation is shown;
[0054] Figure 2 A flow chart showing a method for determining target combined process parameters and locating and optimizing equipment defects in a tea saponin granule preparation equipment to be optimized;
[0055] Figure 3 A program view of a tea saponin granule preparation process optimization system based on intelligent regulation is shown. DETAILED DESCRIPTION
[0056] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0058] Figure 1 A flow chart of a tea saponin granule preparation process optimization method based on intelligent regulation is shown, comprising the following steps:
[0059] S102: evaluating the average particle size and water content of the prepared tea saponin particles, and classifying the equipment for preparing the tea saponin particles based on the evaluation results;
[0060] S104: performing tea saponin granule preparation tests based on different process parameters in the tea saponin granule preparation equipment to be optimized, constructing a process parameter regression model based on the test results, and obtaining qualified combined process parameters;
[0061] S106: Determine the target combination process parameters, control the tea saponin granule preparation equipment to be optimized to continuously prepare the tea saponin granules under the target combination process parameters, and locate and optimize equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process.
[0062] Furthermore, in a preferred embodiment of the present invention, the step S102 is specifically:
[0063] Calibrate a device capable of preparing tea saponin granules as a tea saponin granule preparation device, and obtain sample particles of tea saponin granules prepared by the tea saponin granule preparation device and calibrate them as tea saponin granule samples;
[0064] Obtain a laser particle size analyzer, use the laser particle size analyzer to measure the average particle size of the tea saponin particle sample, obtain a historical data network, and retrieve a standard average particle size threshold of the tea saponin particle sample on the historical data network;
[0065] If the average particle size of the tea saponin granule sample is within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with qualified average particle size; if the average particle size of the tea saponin granule sample is not within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified average particle size;
[0066] Calculate the weight of the tea saponin particle sample, obtain a thermogravimetric analyzer, place the tea saponin particle sample in the thermogravimetric analyzer, and obtain a heating rate threshold that the tea saponin particle sample can withstand and a maximum temperature that the tea saponin particle sample can withstand in the historical data network;
[0067] Controlling the thermogravimetric analyzer to heat the tea saponin particle sample based on a heating rate threshold that the tea saponin particle sample can withstand, and stopping heating when the temperature in the thermogravimetric analyzer reaches a maximum temperature that the tea saponin particle sample can withstand, thereby obtaining a heated tea saponin particle sample;
[0068] Calculating the weight of the heated tea saponin granule sample, and subtracting the weight of the heated tea saponin granule sample from the weight of the tea saponin granule sample to obtain the water content of the tea saponin granule sample;
[0069] A standard moisture content threshold of the tea saponin granule sample is preset. If the moisture content of the tea saponin granule sample is within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with qualified moisture content. If the moisture content of the tea saponin granule sample is not within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified moisture content.
[0070] The tea saponin particles are analyzed. When the tea saponin particles have unqualified average particle size or unqualified water content, the tea saponin particle preparation equipment is evaluated as tea saponin particle preparation equipment to be optimized.
[0071] It should be noted that the purpose of obtaining tea saponin granule samples is that a large number of tea saponin granules are prepared. If it is necessary to perform volume analysis and water content analysis on the tea saponin granules, it is necessary to extract samples for analysis to reduce the amount of calculation and increase the analysis rate. The laser particle size analyzer can calculate the average particle size of the sample, which reflects the size of the tea saponin particles. If the average particle size is too large, it will affect the use effect of the tea saponin particles. Thermogravimetric analysis instrument is an instrument that can heat tea saponin particles and analyze their water content. Since heating tea saponin particles will evaporate their water, the water content of the tea saponin granule sample can be obtained by measuring the weight of the tea saponin granule sample before and after heating. During the heating process, it is necessary to determine the heating rate and maximum temperature that the tea saponin particles can withstand. If the heating rate and maximum temperature are exceeded, the tea saponin granule sample may be directly melted, and the water content of the particles cannot be accurately obtained. After measuring the average particle size and water content of the tea saponin granule sample, they are analyzed. If the average particle size or water content of the tea saponin granules is arbitrary or not within the preset range, it proves that there are process problems in the tea saponin granule preparation equipment, resulting in abnormal average particle size or water content of the tea saponin granules, so the tea saponin granule preparation equipment to be optimized is obtained.
[0072] Furthermore, in a preferred embodiment of the present invention, the step S104 is specifically:
[0073] In the tea saponin granule preparation device, a process for controlling the volume of the tea saponin granules and a process for controlling the water content of the tea saponin granules are obtained, wherein the process for controlling the volume of the tea saponin granules is calibrated as a volume control process, and the process for controlling the water content of the tea saponin granules is calibrated as a water content control process;
[0074] If the tea saponin granule preparation equipment is the tea saponin granule preparation equipment to be optimized, then the process parameter threshold of the volume control process is obtained and calibrated as the volume control process parameter threshold, and the process parameter threshold of the water content control process is obtained and calibrated as the water content control process parameter threshold;
[0075] Combining a volume control process and a water content control process to obtain a combined process, and obtaining different combined process parameters based on the volume control process parameter threshold and the water content control process parameter threshold;
[0076] Preset a preparation test time, during which all combined process parameters are introduced into the tea saponin granule preparation device to be optimized, and control the tea saponin granule preparation device to be optimized to perform tea saponin granule preparation tests based on different combined process parameters, so as to obtain tea saponin granules under different combined process parameters;
[0077] Determine the average particle size and water content of the tea saponin particles under different combinations of process parameters, and construct a process parameter regression model based on the average particle size and water content of the tea saponin particles under different combinations of process parameters, wherein the process parameter regression model can pair the tea saponin particles with different average particle sizes and water contents with different combinations of process parameters;
[0078] Based on the process parameter regression model, the combined process parameters corresponding to the average particle size and water content of the tea saponin particles being in a qualified state are determined and calibrated as qualified combined process parameters, wherein the average particle size and water content of the tea saponin particles being in a qualified state means that the tea saponin particles are tea saponin particles with a qualified average particle size, and the tea saponin particles are tea saponin particles with a qualified water content;
[0079] It should be noted that the volume control process and the water content control process are both sub-processes in the preparation process of tea saponin particles, wherein the volume control process includes a variety of processes, including but not limited to cutting and crushing the raw materials of tea saponin particles, and the water content control process includes preparing a solution for dissolving the raw materials of tea saponin, spray drying, fluidized bed drying, etc. In the tea saponin particle preparation equipment, the parameters of different processes can be adjusted, that is, the average particle size and water content of the tea saponin particles can be regulated, and the average particle size and water content of the tea saponin particles corresponding to different process parameters are different. The volume control process and the water content control process are combined to obtain a combined process, and due to different process parameters, there are multiple process parameters for the combined process, that is, there are multiple combined process parameters. Tea saponin particles are prepared based on different combined process parameters, and the average particle size and water content of the tea saponin particles under different combined process parameters are obtained. The average particle size and water content of the tea saponin particles under different combined process parameters can be used to construct a process parameter regression model. In the process parameter regression model, the average particle size and water content of tea saponin are input to obtain the corresponding combined process parameters, so the process parameter regression model can pair tea saponin particles with different average particle sizes and water contents with different combined process parameters. The construction formula of the process parameter regression model is:
[0080] ;
[0081] Among them, Y is the response variable, including average particle size and water content, is the corresponding combined process parameter, and is the regression coefficient of the generation estimate. After obtaining the process parameter regression model, the combined process parameters corresponding to the average particle size and water content of the tea saponin particles being in a qualified state are determined and calibrated as qualified combined process parameters.
[0082] Figure 2A flow chart of a method for determining target combined process parameters and locating and optimizing equipment defects for a tea saponin granule preparation equipment to be optimized is shown, comprising the following steps:
[0083] S202: Determine target combined process parameters through a process parameter regression model;
[0084] S204: performing process parameter defect analysis and optimization on the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process;
[0085] S206: A second analysis and optimization of equipment defects was conducted on a Class I overhaul of tea saponin granule preparation equipment.
[0086] Furthermore, in a preferred embodiment of the present invention, the step S202 is specifically:
[0087] Obtaining order information of tea saponin particles, and determining the target average particle size and water content of the tea saponin particles based on the order information of the tea saponin particles, and calibrating them as the target average particle size and target water content;
[0088] In the process parameter regression model, the combined process parameters that can make the average particle size and water content of tea saponin particles equal to the target average particle size and target water content are determined and calibrated as the optimal combined process parameters;
[0089] All qualified combined process parameters are grouped into a qualified combined process parameter set, and it is determined whether there is a qualified combined process parameter in the qualified combined process parameter set that is equal to the optimal combined process parameter;
[0090] If yes, the best combination process parameters are calibrated as the target combination process parameters; if no, all qualified combination process parameters and the best combination process parameters are converted into feature data to obtain qualified combination process feature parameters and the best combination process feature parameters;
[0091] The optimal combined process characteristic parameters are calibrated as reference characteristic parameters, a cosine metric algorithm is introduced, and cosine metric values between all qualified combined process characteristic parameters and the reference characteristic parameters are calculated based on the cosine metric algorithm;
[0092] Selecting a qualified combined process characteristic parameter with the largest cosine metric value with the reference characteristic parameter, calibrating it as a target combined process characteristic parameter, and performing feature conversion on the target combined process characteristic parameter to obtain the target combined process parameter;
[0093] Based on the target combined process parameters, the tea saponin granule preparation equipment to be optimized is controlled to continuously prepare tea saponin granules, and during the tea saponin granule preparation process, equipment defect analysis and equipment defect optimization are performed on the tea saponin granule preparation equipment to be optimized.
[0094] It should be noted that, since the tea saponin granules will be delivered to customers after production, and the average particle size and water content of the tea saponin granules required by customers may be different, it is necessary to determine the target average particle size and target water content of the tea saponin granules according to the order information, so as to produce tea saponin granules in a targeted manner. Since the process parameter regression model can determine the combined process parameters corresponding to the average particle size and water content, the combined process parameters corresponding to the target average particle size and the target water content, that is, the optimal combined process parameters, can be determined by the process parameter regression model. There are many qualified combined process parameters. If there is a qualified combined process parameter equal to the optimal combined process parameter, the corresponding qualified combined process parameter is output and calibrated as the target combined process parameter. If it does not exist, it is necessary to select the qualified combined process parameter closest to the optimal combined process parameter from all qualified combined process parameters for output. The cosine metric algorithm can be used to judge the similarity of parameters, convert the parameters into feature data, and calculate the cosine metric value between the feature data of different parameters and the reference value, output the corresponding qualified combined process parameter with the largest cosine metric value, and calibrate it as the target combined process parameter. Among them, the larger the cosine metric value between the parameters, the higher the similarity between the parameters. After obtaining the target combination process parameters, it is necessary to apply the target combination process parameters in the tea saponin granule preparation equipment to be optimized for manufacturing tea saponin granules, and perform fault tracing and equipment optimization according to the problems encountered during the manufacturing process to ensure that the efficiency and effect of tea saponin granule preparation are not affected.
[0095] Furthermore, in a preferred embodiment of the present invention, the step S204 is specifically:
[0096] Applying the target combined process parameters in the tea saponin granule preparation equipment to be optimized, a type of tea saponin granule preparation equipment is obtained;
[0097] Obtaining a sensor for monitoring a combined process parameter in a tea saponin granule preparation device, calibrating the sensor as a process parameter monitoring sensor, and controlling the tea saponin granule preparation device to continuously prepare tea saponin granules;
[0098] In the process of a type of tea saponin granule preparation equipment continuously preparing tea saponin granules, a combined process parameter being run in the type of tea saponin granule preparation equipment is monitored in real time by a process parameter monitoring sensor, and calibrated as a real-time combined process parameter;
[0099] If the real-time combined process parameters are constantly equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a qualified tea saponin granule preparation equipment;
[0100] If the real-time combined process parameters are not constant and equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a first-class unqualified tea saponin granule preparation equipment;
[0101] If the tea saponin granule preparation equipment is a type of unqualified tea saponin granule preparation equipment, then based on the real-time combined process parameters and the target combined process parameters, the real-time process parameters and the target process parameters of all sub-processes in the type of unqualified tea saponin granule preparation equipment are obtained, wherein the sub-processes are a volume control process and a moisture content control process;
[0102] Calculate the Euclidean distance between the real-time process parameters and the target process parameters of all sub-processes. If the Euclidean distance between the real-time process parameters and the target process parameters of a sub-process is greater than a preset value, the corresponding sub-process is marked as an abnormal sub-process.
[0103] In the historical data network, the maintenance plan of the abnormal sub-process is retrieved and output to obtain a type of maintenance tea saponin granule preparation equipment. The target combination process parameters are applied in the type of maintenance tea saponin granule preparation equipment and tea saponin granules are continuously prepared. If the real-time combination process parameters obtained in the type of maintenance tea saponin granule preparation equipment are still not constant and equal to the target combination process parameters, a secondary analysis and optimization of equipment defects is performed on the type of maintenance tea saponin granule preparation equipment.
[0104] It should be noted that the target combined process parameters are applied in the tea saponin granule preparation equipment to be optimized so that the tea saponin granule preparation equipment to be optimized can prepare tea saponin granules containing the target average particle size and the target water content. During the preparation process, if the real-time combined process parameters deviate and are not constant equal to the target combined process parameters, the quality of the prepared tea saponin granules will be affected and the delivery conditions will not be met. When the real-time combined process parameters are not constant equal to the target combined process parameters, the tea saponin granule preparation equipment is calibrated as a class of unqualified tea saponin granule preparation equipment, and the real-time process parameters of all sub-processes in a class of unqualified tea saponin granule preparation equipment are obtained, and the target process parameters of all sub-processes are obtained based on the target combined process parameters. The reason why the real-time combined process parameters are not constant equal to the target combined process parameters may be that the process parameters of the sub-process do not match the target value, so the Euclidean distance between the real-time process parameters of the sub-process and the target value can be calculated, and the corresponding sub-process whose Euclidean distance is greater than the preset value is calibrated as an abnormal sub-process. The Euclidean distance reflects the similarity between the data. The larger the Euclidean distance, the lower the similarity. The historical data network is a data network containing various fault solutions. In the historical data network, the maintenance plan of the abnormal sub-process can be retrieved and output. The maintenance plan of the abnormal sub-process includes but is not limited to the change of the sub-process control environment conditions, the adjustment of the set parameters, etc. If after the abnormal sub-process is repaired, the real-time combined process parameters obtained in the first type of repaired tea saponin granule preparation equipment are still not constant and equal to the target combined process parameters, it proves that there are other problems with the equipment that need to be solved.
[0105] Furthermore, in a preferred embodiment of the present invention, the step S206 is specifically:
[0106] In a type of tea saponin granule preparation equipment for maintenance, an algorithm for preparing tea saponin granules is obtained and calibrated as a preparation algorithm, and different algorithm functions are run and tested in the preparation algorithm to determine whether any algorithm function cannot be run;
[0107] If so, the algorithm function that cannot be run is marked as an abnormally run algorithm function, and a patch of the abnormally run algorithm function is retrieved and output in the historical data network, so that the abnormally run algorithm function does not exist in the preparation algorithm, and an optimized preparation algorithm is obtained;
[0108] The optimized preparation algorithm is applied to a type of tea saponin granule preparation equipment for maintenance. If the real-time combined process parameters of the type of tea saponin granule preparation equipment for maintenance to which the optimized preparation algorithm is applied are still not constant and equal to the target combined process parameters, the circuit structure of the type of tea saponin granule preparation equipment for maintenance is obtained, and the circuit structure of the type of tea saponin granule preparation equipment for maintenance is tested for voltage by a multimeter to obtain circuit nodes whose voltages do not match preset values, and the nodes are marked as abnormal circuit nodes;
[0109] The repair scheme of abnormal circuit nodes is retrieved and output in the historical data network, so that the real-time combined process parameters of a type of repaired tea saponin granule preparation equipment using the optimized preparation algorithm are constant and equal to the target combined process parameters, and qualified tea saponin granule preparation equipment is obtained.
[0110] It should be noted that the secondary analysis and optimization of equipment defects for a type of tea saponin granule preparation equipment under maintenance requires the acquisition of the preparation algorithm first. The role of the preparation algorithm in a type of tea saponin granule preparation equipment under maintenance is to control the equipment to prepare tea saponin. If the preparation algorithm is abnormal, such as there is an algorithm function in the preparation algorithm that cannot run or runs abnormally, it will affect the effect of the equipment in preparing tea saponin granules. The real-time combined process parameters are not constant and equal to the target combined process parameters, so it is necessary to retrieve the abnormal algorithm function patch and output it, so that there is no abnormal algorithm function in the preparation algorithm, and the optimized preparation algorithm is obtained and applied. If the real-time combined process parameters cannot be made constant and equal to the target combined process parameters after applying the optimized preparation algorithm, it is judged that there is a circuit fault in the equipment, which causes the equipment to be unable to work at the rated power, resulting in deviations, so the equipment circuit structure is obtained, and the circuit structure is tested for current through a multimeter, the nodes with abnormal current are judged and corrected, and qualified tea saponin granule preparation equipment is obtained.
[0111] In addition, the tea saponin granule preparation process optimization method based on intelligent regulation also includes the following steps:
[0112] In the process of obtaining qualified combined process parameters through the process parameter regression model, the process parameter regression model is cross-validated, wherein the model cross-validation includes calculating a mean square error value of the process parameter regression model and presetting a mean square error threshold of the process parameter regression model;
[0113] If the mean square error value of the process parameter regression model is not within the mean square error threshold, the process parameter regression model is calibrated as a process parameter regression abnormal model;
[0114] A grid search algorithm and a Bayesian algorithm are introduced to obtain all hyperparameter combinations in the process parameter regression anomaly model, and based on the grid search method and the Bayesian algorithm, a hyperparameter combination that can maintain the mean square error value of the process parameter regression anomaly model within a mean square error threshold is retrieved from all hyperparameter combinations, and marked as the optimal hyperparameter combination;
[0115] The optimal hyperparameter combination is output to obtain an optimized process parameter regression model, and based on the optimized process parameter regression model, qualified combined process parameters are obtained.
[0116] It should be noted that the process parameter regression model may have an abnormal mean square error value during the working process. The abnormal mean square error value will cause a deviation in the correspondence between the average particle size and water content and the combined process parameters, so that the qualified combined process parameters obtained next are abnormal, and the tea saponin particles of the correct specifications cannot be prepared according to the customer's requirements. Therefore, after obtaining the process parameter regression model, it is necessary to determine whether its mean square error value is abnormal. If it is not within the mean square error threshold, the process parameter regression model needs to be tuned. The hyperparameter tuning method is selected to tune the process parameter regression model. The hyperparameter refers to a parameter in the model that affects the model performance. The appropriate hyperparameter is very important for the performance and generalization ability of the model. The hyperparameter includes regularization parameters, etc. There are many hyperparameter combinations in the model. By combining the grid search method and the Bayesian algorithm, all hyperparameter combinations can be traversed first, and based on the Bayesian theorem, the optimal hyperparameter combination can be approximated and selected. After outputting the optimal hyperparameter combination, the mean square error value of the optimized process parameter regression model obtained will remain within the threshold.
[0117] like Figure 3 As shown, the second aspect of the present invention further provides a tea saponin granule preparation process optimization system based on intelligent regulation, the process optimization system comprises a memory 31 and a processor 32, the memory 31 stores a process optimization method, and when the process optimization method is executed by the processor 32, the following steps are implemented:
[0118] The prepared tea saponin particles are evaluated for average particle size and water content, and the equipment for preparing the tea saponin particles is classified based on the evaluation results;
[0119] The tea saponin granule preparation test is carried out based on different process parameters in the tea saponin granule preparation equipment to be optimized, a process parameter regression model is constructed based on the test results, and qualified combined process parameters are obtained;
[0120] Determine the target combination process parameters, control the tea saponin granule preparation equipment to be optimized to continuously prepare tea saponin granules under the target combination process parameters, and locate and optimize equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process.
[0121] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for optimizing the preparation process of tea saponin particles based on intelligent regulation, characterized in that: The following steps are involved: S102: evaluating the average particle size and water content of the prepared tea saponin particles, and classifying the equipment for preparing the tea saponin particles based on the evaluation results; S104: performing tea saponin granule preparation tests based on different process parameters in the tea saponin granule preparation equipment to be optimized, constructing a process parameter regression model based on the test results, and obtaining qualified combined process parameters; S106: determining target combined process parameters, controlling the tea saponin granule preparation equipment to be optimized to continuously prepare tea saponin granules under the target combined process parameters, and locating and optimizing equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process; Wherein, the S104 is specifically: In the tea saponin granule preparation device, a process for controlling the volume of the tea saponin granules and a process for controlling the water content of the tea saponin granules are obtained, wherein the process for controlling the volume of the tea saponin granules is calibrated as a volume control process, and the process for controlling the water content of the tea saponin granules is calibrated as a water content control process; If the tea saponin granule preparation equipment is the tea saponin granule preparation equipment to be optimized, then the process parameter threshold of the volume control process is obtained and calibrated as the volume control process parameter threshold, and the process parameter threshold of the water content control process is obtained and calibrated as the water content control process parameter threshold; Combining a volume control process and a water content control process to obtain a combined process, and obtaining different combined process parameters based on the volume control process parameter threshold and the water content control process parameter threshold; Preset a preparation test time, during which all combined process parameters are introduced into the tea saponin granule preparation device to be optimized, and control the tea saponin granule preparation device to be optimized to perform tea saponin granule preparation tests based on different combined process parameters, so as to obtain tea saponin granules under different combined process parameters; Determine the average particle size and water content of the tea saponin particles under different combinations of process parameters, and construct a process parameter regression model based on the average particle size and water content of the tea saponin particles under different combinations of process parameters, wherein the process parameter regression model can pair the tea saponin particles with different average particle sizes and water contents with different combinations of process parameters; Based on the process parameter regression model, the combined process parameters corresponding to the average particle size and water content of the tea saponin particles being in a qualified state are determined and calibrated as qualified combined process parameters, wherein the average particle size and water content of the tea saponin particles being in a qualified state means that the tea saponin particles are tea saponin particles with a qualified average particle size, and the tea saponin particles are tea saponin particles with a qualified water content; Wherein, the S106 is specifically: Obtaining order information of tea saponin particles, and determining the target average particle size and water content of the tea saponin particles based on the order information of the tea saponin particles, and calibrating them as the target average particle size and target water content; In the process parameter regression model, the combined process parameters that can make the average particle size and water content of tea saponin particles equal to the target average particle size and target water content are determined and calibrated as the optimal combined process parameters; All qualified combined process parameters are grouped into a qualified combined process parameter set, and it is determined whether there is a qualified combined process parameter in the qualified combined process parameter set that is equal to the optimal combined process parameter; If yes, the best combination process parameters are calibrated as the target combination process parameters; if no, all qualified combination process parameters and the best combination process parameters are converted into feature data to obtain qualified combination process feature parameters and the best combination process feature parameters; The optimal combined process characteristic parameters are calibrated as reference characteristic parameters, a cosine metric algorithm is introduced, and cosine metric values between all qualified combined process characteristic parameters and the reference characteristic parameters are calculated based on the cosine metric algorithm; Selecting a qualified combined process characteristic parameter with the largest cosine metric value with the reference characteristic parameter, calibrating it as a target combined process characteristic parameter, and performing feature conversion on the target combined process characteristic parameter to obtain the target combined process parameter; Based on the target combined process parameters, the tea saponin granule preparation equipment to be optimized is controlled to continuously prepare tea saponin granules, and during the tea saponin granule preparation process, equipment defect analysis and equipment defect optimization are performed on the tea saponin granule preparation equipment to be optimized; Wherein, based on the target combined process parameters, the tea saponin granule preparation equipment to be optimized is controlled to continuously prepare tea saponin granules, and during the tea saponin granule preparation process, equipment defect analysis and equipment defect optimization are performed on the tea saponin granule preparation equipment to be optimized, specifically: Applying the target combined process parameters in the tea saponin granule preparation equipment to be optimized, a type of tea saponin granule preparation equipment is obtained; Obtaining a sensor for monitoring a combined process parameter in a tea saponin granule preparation device, calibrating the sensor as a process parameter monitoring sensor, and controlling the tea saponin granule preparation device to continuously prepare tea saponin granules; In the process of a type of tea saponin granule preparation equipment continuously preparing tea saponin granules, a combined process parameter being run in the type of tea saponin granule preparation equipment is monitored in real time by a process parameter monitoring sensor, and calibrated as a real-time combined process parameter; If the real-time combined process parameters are constantly equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a qualified tea saponin granule preparation equipment; If the real-time combined process parameters are not constant and equal to the target combined process parameters during the process of the first-class tea saponin granule preparation equipment continuously preparing the tea saponin granules, the first-class tea saponin granule preparation equipment is evaluated as a first-class unqualified tea saponin granule preparation equipment; If the tea saponin granule preparation equipment is a type of unqualified tea saponin granule preparation equipment, then based on the real-time combined process parameters and the target combined process parameters, the real-time process parameters and the target process parameters of all sub-processes in the type of unqualified tea saponin granule preparation equipment are obtained, wherein the sub-processes are a volume control process and a moisture content control process; Calculate the Euclidean distance between the real-time process parameters and the target process parameters of all sub-processes. If the Euclidean distance between the real-time process parameters and the target process parameters of a sub-process is greater than a preset value, the corresponding sub-process is marked as an abnormal sub-process. In the historical data network, the maintenance plan of the abnormal sub-process is retrieved and output, and a type of maintenance tea saponin granule preparation equipment is obtained. The target combination process parameters are applied in the type of maintenance tea saponin granule preparation equipment and the tea saponin granules are continuously prepared. If the real-time combination process parameters obtained in the type of maintenance tea saponin granule preparation equipment are still not constant and equal to the target combination process parameters, the equipment defect secondary analysis optimization is performed on the type of maintenance tea saponin granule preparation equipment; Among them, the secondary analysis and optimization of equipment defects for a type of tea saponin granule preparation equipment under maintenance is specifically as follows: In a type of tea saponin granule preparation equipment for maintenance, an algorithm for preparing tea saponin granules is obtained and calibrated as a preparation algorithm, and different algorithm functions are run and tested in the preparation algorithm to determine whether any algorithm function cannot be run; If so, the algorithm function that cannot be run is marked as an abnormally run algorithm function, and a patch of the abnormally run algorithm function is retrieved and output in the historical data network, so that the abnormally run algorithm function does not exist in the preparation algorithm, and an optimized preparation algorithm is obtained; The optimized preparation algorithm is applied to a type of tea saponin granule preparation equipment for maintenance. If the real-time combined process parameters of the type of tea saponin granule preparation equipment for maintenance to which the optimized preparation algorithm is applied are still not constant and equal to the target combined process parameters, the circuit structure of the type of tea saponin granule preparation equipment for maintenance is obtained, and the circuit structure of the type of tea saponin granule preparation equipment for maintenance is tested for voltage by a multimeter to obtain circuit nodes whose voltages do not match preset values, and the nodes are marked as abnormal circuit nodes; The repair scheme of abnormal circuit nodes is retrieved and output in the historical data network, so that the real-time combined process parameters of a type of repaired tea saponin granule preparation equipment using the optimized preparation algorithm are constant and equal to the target combined process parameters, and qualified tea saponin granule preparation equipment is obtained.
2. According to the method for optimizing the preparation process of tea saponin particles based on intelligent regulation as described in claim 1, it is characterized in that: The S102 is specifically: Calibrate the equipment for preparing tea saponin granules as tea saponin granule preparation equipment, and obtain sample particles of tea saponin granules prepared by the tea saponin granule preparation equipment and calibrate them as tea saponin granule samples; Obtain a laser particle size analyzer, use the laser particle size analyzer to measure the average particle size of the tea saponin particle sample, obtain a historical data network, and retrieve a standard average particle size threshold of the tea saponin particle sample on the historical data network; If the average particle size of the tea saponin granule sample is within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with qualified average particle size; if the average particle size of the tea saponin granule sample is not within the standard average particle size threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified average particle size; Calculate the weight of the tea saponin particle sample, obtain a thermogravimetric analyzer, place the tea saponin particle sample in the thermogravimetric analyzer, and obtain a heating rate threshold that the tea saponin particle sample can withstand and a maximum temperature that the tea saponin particle sample can withstand in the historical data network; Controlling the thermogravimetric analyzer to heat the tea saponin particle sample based on a heating rate threshold that the tea saponin particle sample can withstand, and stopping heating when the temperature in the thermogravimetric analyzer reaches a maximum temperature that the tea saponin particle sample can withstand, thereby obtaining a heated tea saponin particle sample; Calculating the weight of the heated tea saponin granule sample, and subtracting the weight of the heated tea saponin granule sample from the weight of the tea saponin granule sample to obtain the water content of the tea saponin granule sample; A standard moisture content threshold of the tea saponin granule sample is preset. If the moisture content of the tea saponin granule sample is within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with qualified moisture content. If the moisture content of the tea saponin granule sample is not within the standard moisture content threshold, the tea saponin granule is evaluated as tea saponin granule with unqualified moisture content. The tea saponin particles are analyzed. When the tea saponin particles have unqualified average particle size or unqualified water content, the tea saponin particle preparation equipment is evaluated as tea saponin particle preparation equipment to be optimized.
3. A tea saponin granule preparation process optimization system based on intelligent regulation, characterized in that: The process optimization system includes a memory and a processor, wherein a process optimization method program is stored in the memory, and when the process optimization method program is executed by the processor, the process optimization method steps according to any one of claims 1 to 2 are implemented: The prepared tea saponin particles are evaluated for average particle size and water content, and the equipment for preparing the tea saponin particles is classified based on the evaluation results; The tea saponin granule preparation test is carried out based on different process parameters in the tea saponin granule preparation equipment to be optimized, a process parameter regression model is constructed based on the test results, and qualified combined process parameters are obtained; Determine the target combination process parameters, control the tea saponin granule preparation equipment to be optimized to continuously prepare tea saponin granules under the target combination process parameters, and locate and optimize equipment defects of the tea saponin granule preparation equipment to be optimized during the tea saponin granule preparation process.
