Automatic feeding and stirring time control method and system for high polymer material

Abstract

The invention relates to the technical field of industrial equipment control, and discloses an automatic feeding and stirring time control method and system.The method comprises the steps that the standard rotating speed of a first motor is determined based on the category of to-be-processed raw materials and the mapping relation, and the aging coefficient of the first motor is calculated based on first historical working data; inputting the standard rotating speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-constructed processing time generation model to obtain a processing time interval, and segmenting the processing time interval based on the real-time rotating speed of the first motor and the surface image of the raw material, according to the method, the processing time can be calculated according to the type and the weight of the processing material, and after the processing time is calculated, the starting time of the subsequent motor can be determined according to the processing time, so that linkage between the first motor and the second motor is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment control, and more specifically, to an automatic feeding and stirring time control method and system for polymer materials. Background Art

[0002] Polymer materials are macromolecular compounds composed of many repeating units, usually with high molecular weight and long chain structure. Polymer material reactors are equipment used for synthesizing, polymerizing and processing polymer materials, and are widely used in industrial production, medical equipment, electronic products, building materials and other fields. In the fine chemical industry, polymer material reactors are usually composed of reaction vessels, stirring systems, etc., and stirring time is its main controlled quantity and an important factor in ensuring product quality. In the prior art, there have been automatic control technologies to control non-electrical variables in the reaction process, such as processing temperature, but in the prior art, there are few controls on the processing time among non-electrical variables;

[0003] For example, the Chinese patent with publication number CN117908589A provides a reactor control method, device, equipment and computer-readable storage medium. The patent obtains the current temperature of the reactor, calls the set temperature of the reactor, and controls the feed flow rate of the reactor and / or the heat exchanger of the reactor according to the current temperature of the reactor and the set temperature of the reactor.

[0004] In the process of reactor processing, the existing technology usually controls the temperature among non-electric variables, but ignores that time among non-electric variables is also one of the important factors affecting product quality. It is rare that the processing time can be calculated according to the type and weight of the processing material, and after calculating the processing time, the start time of the subsequent motor can be determined according to the processing time, and the linkage between the main motor and the slave motor cannot be realized.

[0005] In view of this, the present invention proposes an automatic feeding and stirring time control method and system for polymer materials to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for automatically feeding and stirring time control of polymer materials.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The automatic feeding and stirring time control method for polymer materials includes:

[0009] S10: Obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed;

[0010] S20: acquiring first historical working data of the first motor, calculating an aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring;

[0011] S30: acquiring the real-time speed of the first motor and the surface image of the raw material, and segmenting the processing time interval based on the real-time speed of the first motor and the surface image of the raw material to generate processing time segments, wherein the processing time segments include a start-up phase, a working phase, and a termination phase;

[0012] S40: taking the end time of the working phase as the start time of the second motor.

[0013] Furthermore, the first historical working data includes a first historical operating time, a first historical current difference, a first historical operating temperature, and a first historical vibration intensity, and the method for calculating the first motor aging coefficient based on the first historical working data includes:

[0014]

[0015] Where, FAC is the first motor aging coefficient, n is the number of segments of the first historical operating time, HOT i is the first historical operating temperature of the i-th segment, HOT sd is the standard operating temperature, HOM i is the first historical running time of the i-th segment, HVY i is the first historical vibration intensity of the ith segment, HVY sd is the standard vibration intensity, HCD i is the first historical current difference of the i-th segment, and u1, u2, u3 and u4 are all weight factors.

[0016] Furthermore, the method for constructing the processing time generation model includes:

[0017] A first sample data set is obtained, wherein the first sample data set includes a historical first motor standard speed, a historical first motor aging coefficient, a historical weight of raw materials to be processed, and a historical processing time interval. The first sample data set is divided into a first sample training set and a first sample test set, and a regression network is constructed. The historical first motor standard speed, the historical first motor aging coefficient, and the historical weight of raw materials to be processed in the first sample training set are used as input data of the regression network, and the historical processing time interval in the first sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time processing time interval. The initial regression network is tested using the first sample test set, and the regression network that satisfies a preset error value is output as a processing time generation model.

[0018] Furthermore, the method for segmenting the processing time interval based on the real-time rotation speed of the first motor and the surface image of the raw material includes:

[0019] The real-time speed acceleration is determined based on the real-time speed of the first motor, and the processing time interval is divided into a startup phase and a rotation time interval according to the real-time speed acceleration and the corresponding first moment. The raw material surface image is input into a pre-built stirring classification model to obtain the stirring category, and the rotation time interval is divided into a working phase and a termination phase based on the second moment corresponding to the stirring category. The stirring category includes completed stirring and incomplete stirring.

[0020] Furthermore, the method for determining the speed acceleration based on the real-time speed of the first motor includes:

[0021] The real-time speed of the first motor is fitted to generate a real-time speed curve, and the slope of the real-time speed curve is used as the real-time speed acceleration.

[0022] Further, the method of dividing the processing time interval into a start-up phase and a rotation time interval according to the rotation speed acceleration and the corresponding first moment includes:

[0023] When the real-time speed acceleration is less than the preset acceleration threshold, the real-time speed acceleration is recorded, the first moment when the real-time speed acceleration is less than the threshold is recorded, and the first moment is used as the end moment of the startup phase.

[0024] Furthermore, the method for constructing the stirring classification model includes:

[0025] Obtain h groups of training data, where h is a positive integer greater than 1, and the training data includes historical raw material surface images and historical stirring categories. The historical raw material surface images and historical stirring categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical raw material surface images in the training set are used as input data, and the historical stirring categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and the initial classifier having an accuracy greater than a preset threshold is output as a stirring classification model.

[0026] Furthermore, second historical working data of the second motor is obtained, and the aging coefficient of the second motor is calculated based on the second historical working data. The termination time and the second motor aging coefficient are input into a pre-built time adjustment model to obtain the start time, wherein the termination time is the termination time of the working stage, and the start time is the start time of the second motor.

[0027] Furthermore, the method for calculating the second motor aging coefficient based on the second historical working data includes:

[0028]

[0029] Where SAC is the second motor aging coefficient, K is the number of segments of the second historical operating time, SOT i is the second historical operating temperature of the mth segment, SOT sd is the standard operating temperature, SOM i is the second historical running time of the mth segment, SVY i is the second historical vibration intensity of the mth segment, SVY sd is the standard vibration intensity, SCD i is the second historical current difference of the mth segment, and q1, q2, q3 and q4 are all weight factors.

[0030] The automatic feeding and stirring time control system for polymer materials is used to implement the above-mentioned automatic feeding and stirring time control method for polymer materials, comprising:

[0031] Data acquisition module: used to obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed;

[0032] A processing time generation module: used for obtaining first historical working data of the first motor, calculating the aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring;

[0033] Segmentation module: used to obtain the real-time speed of the first motor and the surface image of the raw material, segment the processing time interval based on the real-time speed of the first motor and the surface image of the raw material, and generate processing interval segments, which include a start-up phase, a working phase and a termination phase;

[0034] The time determination module is used to use the end time of the working phase as the start time of the second motor.

[0035] A computer-readable storage medium stores a computer program, and when the computer program is executed, the automatic feeding and stirring time control method for polymer materials is implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention first obtains the category of raw materials to be processed and the weight of raw materials to be processed, determines the standard speed of the first motor based on the category of raw materials to be processed and the mapping relationship, then obtains the first historical working data of the first motor, calculates the aging coefficient of the first motor based on the first historical working data, inputs the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw materials to be processed into a pre-constructed processing time generation model, obtains the processing time interval, obtains the real-time speed of the first motor and the surface image of the raw materials, segments the processing time interval based on the real-time speed of the first motor and the surface image of the raw materials, and finally uses the end time of the working stage as the start time of the second motor. The present invention can calculate the processing time according to the type and weight of the processing material, and after calculating the processing time, can determine the start time of the subsequent motor according to the processing time, so as to realize the linkage between the first motor and the second motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of the automatic feeding and stirring time control method for polymer materials in the present invention;

[0039] Figure 2 It is a schematic diagram of a reaction device for processing polymer materials in the present invention;

[0040] Figure 3 It is a schematic diagram of the linkage between the first motor and the second motor in the present invention;

[0041] Figure 4 A schematic diagram of a computer-readable storage medium in the present invention.

[0042] Description of reference numerals:

[0043] 10. Reactor housing; 20. Reactor liner; 30. Second motor; 40. First motor. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Example 1

[0046] See also Figure 1 As shown, this embodiment discloses a method for automatically feeding and stirring time control of polymer materials, comprising:

[0047] S10: Obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed;

[0048] It should be noted that the categories of raw materials to be processed include acrylate monomers and polyurethane precursors. Whether it is acrylate monomers or polyurethane precursors, corresponding additives are required during the stirring preparation process. For example, acrylate monomers require dispersants and emulsifiers, and polyurethane precursors require cross-linking agents and initiators. In this embodiment, acrylate monomers and polyurethane precursors correspond to their respective additives. Exemplarily, when the category of the raw materials to be processed is identified as acrylate monomers, corresponding dispersants and emulsifiers are also added to achieve the effect of automatic feeding;

[0049] It should be added that the standard speed of the first motor mentioned above refers to the stirring speed. Figure 2 As shown, 10 is a reaction device shell, 20 is a reaction device liner, 30 is a second motor, 40 is a first motor, the above-mentioned raw materials to be processed first enter the reaction device liner 20, the first motor 40 can be a stirring motor, the first motor 40 drives the stirring blades to stir the raw materials to be processed, and the second motor 30 can be a rotating motor, the reaction device liner 20 and the reaction device shell 10 are rotatably connected, the second motor 30 can drive the reaction device liner 20 to rotate, and the rotation directions of the first motor 40 and the second motor 30 are opposite. The purpose of this setting is that when the raw materials to be processed are stirred by the first motor 40 to a certain moment, the second motor 30 is started to drive the reaction device liner 20 to rotate in the opposite direction, and the centrifugal force is generated to accelerate the volatilization of the solvent inside the reaction device liner 20 and the removal of gas, and the raw materials to be processed and the corresponding additives can be mixed more evenly. It should be noted that the solvent here refers to water or ethanol, etc.;

[0050] In this embodiment, the first motor standard speed is determined by pre-establishing an index rule between the type of raw material to be processed, so as to determine the corresponding first motor standard speed through a mapping relationship, and the first motor standard speed is obtained through expert experience or experiments of technicians in this field;

[0051] S20: acquiring first historical working data of the first motor, calculating an aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring;

[0052] In some embodiments, the first historical working data includes but is not limited to the first historical operating time, the first historical current difference, the first historical operating temperature and the first historical vibration intensity. The first historical operating time refers to the total operating time of the first motor, the first historical operating temperature refers to the average operating temperature over a period of time, and the first historical vibration intensity also refers to the average vibration intensity over a period of time. The first historical current difference refers to the average of the absolute values ​​of the difference between the abnormal current value and the standard current value of the first motor in the working process of each day in the past period of time. For example, on the fth day, the abnormal current value in the working process of the first motor is obtained, and the absolute values ​​of the differences between several abnormal current values ​​and the standard current value of the first motor are calculated. The absolute values ​​of these differences are averaged to obtain the current difference corresponding to the fth day, and the current differences in several days are averaged to obtain the first historical current difference.

[0053] It should be added that, in the above determination of the abnormal current value, a current threshold interval may be preset, and when the current value is not within the current threshold interval, the current value is determined to be an abnormal current value;

[0054] The method for calculating the first motor aging coefficient based on the first historical working data includes:

[0055]

[0056] Where, FAC is the first motor aging coefficient, n is the number of segments of the first historical operating time, HOT i is the first historical operating temperature of the i-th segment, HOT sd is the standard operating temperature, HOM i is the first historical running time of the i-th segment, HVY i is the first historical vibration intensity of the ith segment, HVY sd is the standard vibration intensity, HCD i is the first historical current difference of the i-th segment, and u1, u2, u3 and u4 are all weight factors;

[0057] It can be understood that, since the first historical operating time is the total operating time of the first motor, the first historical operating time needs to be divided into n operating time intervals, which can be divided according to several days or a week. This embodiment is not limited to this. The larger the first historical operating time, the first historical current difference, the first historical operating temperature and the first historical vibration intensity, the more serious the aging degree of the first motor is, that is, the first motor aging coefficient is positively correlated with the aging degree of the first motor;

[0058] The construction method of the processing time generation model includes:

[0059] Acquire a first sample data set, wherein the first sample data set includes a historical first motor standard speed, a historical first motor aging coefficient, a historical weight of raw materials to be processed, and a historical processing time interval, divide the first sample data set into a first sample training set and a first sample test set, construct a regression network, use the historical first motor standard speed, the historical first motor aging coefficient, and the historical weight of raw materials to be processed in the first sample training set as input data of the regression network, use the historical processing time interval in the first sample training set as output data of the regression network, train the regression network, obtain an initial regression network for predicting the real-time processing time interval, use the first sample test set to test the initial regression network, and output a regression network that satisfies a preset error value as a processing time generation model, wherein the regression network is preferably a neural network model;

[0060] It should be noted that the above-mentioned historical first motor standard speed is predetermined, the historical first motor aging coefficient is also calculated through experiments, the historical weight of the raw material to be processed is directly obtained through the weight sensor, and the historical processing time interval is also determined through experiments, but the determination standard is formulated based on the effect of mixing the raw material to be processed and the additive, that is, when the effect of mixing the raw material to be processed and the additive meets the requirements, the processing time interval in the experimental process is used as the historical processing time interval in the training data;

[0061] S30: acquiring the real-time speed of the first motor and the surface image of the raw material, and segmenting the processing time interval based on the real-time speed of the first motor and the surface image of the raw material to generate processing time segments, wherein the processing time segments include a start-up phase, a working phase, and a termination phase;

[0062] In some embodiments, the method for obtaining the real-time speed of the first motor may be to measure the real-time speed of the first motor shaft by a photoelectric sensor to obtain the real-time speed of the first motor, and the surface image of the raw material is obtained by a camera in the reaction device;

[0063] The method for segmenting the processing time interval based on the real-time speed of the first motor and the surface image of the raw material includes:

[0064] Determine the real-time speed acceleration based on the real-time speed of the first motor, divide the processing time interval into a start-up phase and a rotation time interval according to the real-time speed acceleration and the corresponding first moment, input the raw material surface image into a pre-built stirring classification model to obtain the stirring category, divide the rotation time interval into a working phase and a termination phase based on the second moment corresponding to the stirring category, and include stirring completion and stirring incomplete based on the stirring category;

[0065] The method for determining the speed acceleration based on the real-time speed of the first motor includes:

[0066] Fitting the real-time speed of the first motor to generate a real-time speed curve, and using the slope of the real-time speed curve as the real-time speed acceleration;

[0067] The method of dividing the processing time interval into a start-up phase and a rotation time interval according to the rotation speed acceleration and the corresponding first moment includes:

[0068] When the real-time speed acceleration is less than the preset acceleration threshold, the real-time speed acceleration is recorded, the first moment when the real-time speed acceleration is less than the threshold is recorded, and the first moment is used as the end moment of the startup phase;

[0069] It should be noted that the startup phase refers to the startup phase of the first motor. During the process from the startup phase to the working phase of the first motor, the real-time speed of the first motor increases from rapid to stable. Therefore, the startup phase of the first motor is determined according to the real-time speed acceleration.

[0070] The method for dividing the rotation time interval into a working stage and a termination stage based on the second moment corresponding to the stirring category includes:

[0071] The stirring category is continuously obtained within the rotation time interval. When the stirring category is stirring completed, the second moment when the stirring category is stirring completed for the first time is recorded, and the second moment is used as the end moment of the working stage;

[0072] It should be added that, in this embodiment, when the motor reaches the rotation time interval from the starting stage, the raw material surface image is obtained, and the raw material surface image is continuously input into the stirring classification model to obtain the stirring category. It can be understood that stirring the raw material to be processed takes time. Therefore, at the beginning, the raw material surface image is input into the stirring classification model, and the stirring category obtained is always stirring incomplete, until a certain moment when the stirring is completed. Therefore, the second moment when the first stirring category is stirring completed is recorded, and the second moment is used as the end moment of the working stage, so that the segmentation of the processing time interval is completed;

[0073] It is understandable that after obtaining the processing time interval, this embodiment does not directly segment the processing time interval according to the preset rules, but segments the processing time interval according to the real-time processing situation, which can more accurately complete the segmentation task and improve the mixing effect of the raw materials to be processed;

[0074] The method for building the stirring classification model includes:

[0075] Obtaining h groups of training data, where h is a positive integer greater than 1, and the training data includes historical raw material surface images and historical stirring categories, taking the historical raw material surface images and the historical stirring categories as sample sets, dividing the sample sets into training sets and test sets, constructing a classifier, taking the historical raw material surface images in the training set as input data, and taking the historical stirring categories in the training set as output data, training the classifier to obtain an initial classifier, testing the initial classifier using the test set, and outputting an initial classifier having an accuracy greater than a preset threshold as a stirring classification model, wherein the classifier is preferably a naive Bayes model or a support vector machine model;

[0076] S40: taking the end time of the working phase as the start time of the second motor;

[0077] It should be noted that if Figure 3 As shown, the purpose of using the end time of the working stage of the first motor 40 as the start time of the second motor 30 in this embodiment is that when the processing time reaches the end time of the working stage, the raw materials to be processed and the additives have been stirred, and the second motor 30 is started to drive the reaction device inner tank 20 to rotate in the opposite direction, which can accelerate the volatilization of the solvent inside the reaction device inner tank 20 and the removal of gas, and can make the raw materials to be processed and the corresponding additives mixed more evenly, and because the power consumed by the second motor 30 to accelerate the rotation of the reaction device inner tank 20 is greater than the power consumed by the first motor 40, in this embodiment, the second motor 30 is not started until the raw materials to be processed and the additives have been stirred, so as to reduce the power consumed in the processing process;

[0078] In this embodiment, the category of the raw material to be processed and the weight of the raw material to be processed are first obtained, and the standard speed of the first motor is determined based on the category of the raw material to be processed and the mapping relationship, and then the first historical working data of the first motor is obtained, and the aging coefficient of the first motor is calculated based on the first historical working data. The standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed are input into a pre-constructed processing time generation model to obtain the processing time interval, and the real-time speed of the first motor and the raw material surface image are obtained. The processing time interval is segmented based on the real-time speed of the first motor and the raw material surface image, and finally the end time of the working stage is used as the start time of the second motor. This embodiment can calculate the processing time according to the type and weight of the processing material, and after calculating the processing time, it can determine the start time of the subsequent motor according to the processing time, so as to realize the linkage between the first motor and the second motor.

[0079] Example 2

[0080] S50: Acquire second historical working data of the second motor, calculate the aging coefficient of the second motor based on the second historical working data, input the termination time and the aging coefficient of the second motor into a pre-built time adjustment model, and obtain the starting time, wherein the termination time is the termination time of the working stage, and the starting time is the starting time of the second motor;

[0081] In this embodiment, the second historical working data includes but is not limited to the second historical operating time, the second historical current difference, the second historical operating temperature and the second historical vibration intensity. The second historical operating time refers to the total operating time of the second motor, the second historical operating temperature refers to the average operating temperature over a period of time, and the second historical vibration intensity also refers to the average vibration intensity over a period of time. The second historical current difference refers to the average of the absolute value of the difference between the abnormal current value and the standard current value during the working process of the second motor every day over the past period of time.

[0082] The method for calculating the second motor aging coefficient based on the second historical working data includes:

[0083]

[0084] Where SAC is the second motor aging coefficient, K is the number of segments of the second historical operating time, SOT i is the second historical operating temperature of the mth segment, SOT sd is the standard operating temperature, SOM i is the second historical running time of the mth segment, SVY i is the second historical vibration intensity of the mth segment, SVY sd is the standard vibration intensity, SCD iis the second historical current difference of the mth segment, q1, q2, q3 and q4 are all weight factors;

[0085] It can be understood that, since the second historical operating time is the total operating time of the second motor, the first historical operating time needs to be divided into m operating time intervals, which can be divided according to several days or a week. This embodiment is not limited to this. The larger the second historical operating time, the second historical current difference, the second historical operating temperature and the second historical vibration intensity, the more serious the aging degree of the second motor is, that is, the second motor aging coefficient is positively correlated with the aging degree of the second motor;

[0086] Methods for constructing a time-adjustment model include:

[0087] Obtain a second sample data set, wherein the second sample data set includes a historical end time, a historical second motor aging coefficient, and a historical start time, divide the second sample data set into a second sample training set and a second sample test set, construct a regression network, use the historical end time and the historical second motor aging coefficient in the second sample training set as input data of the regression network, use the historical start time in the second sample training set as output data of the regression network, train the regression network, obtain an initial regression network for predicting the real-time start time, use the second sample test set to test the initial regression network, and output a regression network that satisfies a preset error value as a time adjustment model, wherein the regression network is preferably a neural network model;

[0088] It should be added that this embodiment is a further improvement on Embodiment 1. After obtaining the end time of the working stage in Embodiment 1, the end time is directly used as the start time of the second motor. However, it does not take into account that the second motor is also aging. The more serious the aging of the second motor is, the slower the start of the second motor is. Therefore, when obtaining the end time of the working stage of the first motor, it is necessary to start the second motor in advance according to the aging degree of the second motor to ensure that the first motor and the second motor can be linked to each other and to improve the preparation effect of subsequent polymer materials.

[0089] Example 3

[0090] This embodiment provides an automatic feeding and stirring time control system for polymer materials based on the embodiment 1, including:

[0091] Data acquisition module: used to obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed;

[0092] It should be noted that the categories of raw materials to be processed include acrylate monomers and polyurethane precursors. Whether it is acrylate monomers or polyurethane precursors, corresponding additives are required during the stirring preparation process. For example, acrylate monomers require dispersants and emulsifiers, and polyurethane precursors require cross-linking agents and initiators. In this embodiment, acrylate monomers and polyurethane precursors correspond to their respective additives. Exemplarily, when the category of the raw materials to be processed is identified as acrylate monomers, corresponding dispersants and emulsifiers are also added to achieve the effect of automatic feeding;

[0093] In this embodiment, the first motor standard speed is determined by pre-establishing an index rule between the type of raw material to be processed, so as to determine the corresponding first motor standard speed through a mapping relationship, and the first motor standard speed is obtained through expert experience or experiments of technicians in this field;

[0094] A processing time generation module: used for obtaining first historical working data of the first motor, calculating the aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring;

[0095] In some embodiments, the first historical working data includes but is not limited to the first historical operating time, the first historical current difference, the first historical operating temperature and the first historical vibration intensity. The first historical operating time refers to the total operating time of the first motor, the first historical operating temperature refers to the average operating temperature over a period of time, and the first historical vibration intensity also refers to the average vibration intensity over a period of time. The first historical current difference refers to the average of the absolute values ​​of the difference between the abnormal current value and the standard current value of the first motor in the working process of each day in the past period of time. For example, on the fth day, the abnormal current value in the working process of the first motor is obtained, and the absolute values ​​of the differences between several abnormal current values ​​and the standard current value of the first motor are calculated. The absolute values ​​of these differences are averaged to obtain the current difference corresponding to the fth day, and the current differences in several days are averaged to obtain the first historical current difference.

[0096] It should be added that, in the above determination of the abnormal current value, a current threshold interval may be preset, and when the current value is not within the current threshold interval, the current value is determined to be an abnormal current value;

[0097] The method for calculating the first motor aging coefficient based on the first historical working data includes:

[0098]

[0099] Where, FAC is the first motor aging coefficient, n is the number of segments of the first historical operating time, HOT i is the first historical operating temperature of the i-th segment, HOT sd is the standard operating temperature, HOM i is the first historical running time of the i-th segment, HVY i is the first historical vibration intensity of the ith segment, HVY sd is the standard vibration intensity, HCD i is the first historical current difference of the i-th segment, and u1, u2, u3 and u4 are all weight factors;

[0100] It can be understood that, since the first historical operating time is the total operating time of the first motor, the first historical operating time needs to be divided into n operating time intervals, which can be divided according to several days or a week. This embodiment is not limited to this. The larger the first historical operating time, the first historical current difference, the first historical operating temperature and the first historical vibration intensity, the more serious the aging degree of the first motor is, that is, the first motor aging coefficient is positively correlated with the aging degree of the first motor;

[0101] It should be noted that the above-mentioned historical first motor standard speed is predetermined, the historical first motor aging coefficient is also calculated through experiments, the historical weight of the raw material to be processed is directly obtained through the weight sensor, and the historical processing time interval is also determined through experiments, but the determination standard is formulated based on the effect of mixing the raw material to be processed and the additive, that is, when the effect of mixing the raw material to be processed and the additive meets the requirements, the processing time interval in the experimental process is used as the historical processing time interval in the training data;

[0102] Segmentation module: used to obtain the real-time speed of the first motor and the surface image of the raw material, segment the processing time interval based on the real-time speed of the first motor and the surface image of the raw material, and generate processing interval segments, which include a start-up phase, a working phase and a termination phase;

[0103] In some embodiments, the method for obtaining the real-time speed of the first motor may be to measure the real-time speed of the first motor shaft by a photoelectric sensor to obtain the real-time speed of the first motor, and the surface image of the raw material is obtained by a camera in the reaction device;

[0104] The method for segmenting the processing time interval based on the real-time speed of the first motor and the surface image of the raw material includes:

[0105] Determine the real-time speed acceleration based on the real-time speed of the first motor, divide the processing time interval into a start-up phase and a rotation time interval according to the real-time speed acceleration and the corresponding first moment, input the raw material surface image into a pre-built stirring classification model to obtain the stirring category, divide the rotation time interval into a working phase and a termination phase based on the second moment corresponding to the stirring category, and include stirring completion and stirring incomplete based on the stirring category;

[0106] The method for determining the speed acceleration based on the real-time speed of the first motor includes:

[0107] Fitting the real-time speed of the first motor to generate a real-time speed curve, and using the slope of the real-time speed curve as the real-time speed acceleration;

[0108] The method of dividing the processing time interval into a start-up phase and a rotation time interval according to the rotation speed acceleration and the corresponding first moment includes:

[0109] When the real-time speed acceleration is less than the preset acceleration threshold, the real-time speed acceleration is recorded, the first moment when the real-time speed acceleration is less than the threshold is recorded, and the first moment is used as the end moment of the startup phase;

[0110] It should be noted that the startup phase refers to the startup phase of the first motor. During the process from the startup phase to the working phase of the first motor, the real-time speed of the first motor increases from rapid to stable. Therefore, the startup phase of the first motor is determined according to the real-time speed acceleration.

[0111] The method for dividing the rotation time interval into a working stage and a termination stage based on the second moment corresponding to the stirring category includes:

[0112] The stirring category is continuously obtained within the rotation time interval. When the stirring category is stirring completed, the second moment when the stirring category is stirring completed for the first time is recorded, and the second moment is used as the end moment of the working stage;

[0113] It should be added that, in this embodiment, when the motor reaches the rotation time interval from the starting stage, the raw material surface image is obtained, and the raw material surface image is continuously input into the stirring classification model to obtain the stirring category. It can be understood that stirring the raw material to be processed takes time. Therefore, at the beginning, the raw material surface image is input into the stirring classification model, and the stirring category obtained is always stirring incomplete, until a certain moment when the stirring is completed. Therefore, the second moment when the first stirring category is stirring completed is recorded, and the second moment is used as the end moment of the working stage, so that the segmentation of the processing time interval is completed;

[0114] It is understandable that after obtaining the processing time interval, this embodiment does not directly segment the processing time interval according to the preset rules, but segments the processing time interval according to the real-time processing situation, which can more accurately complete the segmentation task and improve the mixing effect of the raw materials to be processed;

[0115] A time determination module: used for taking the end time of the working phase as the start time of the second motor;

[0116] It should be noted that if Figure 3 As shown, the purpose of using the end time of the working stage of the first motor 40 as the start time of the second motor 30 in this embodiment is that when the processing time reaches the end time of the working stage, the raw materials to be processed and the additives have been mixed, and the second motor 30 is started to drive the reaction device inner tank 20 to rotate in the opposite direction, which can accelerate the volatilization of the solvent inside the reaction device inner tank 20 and the removal of gas, and can make the raw materials to be processed and the corresponding additives mixed more evenly. In addition, since the power consumed by the second motor 30 to accelerate the rotation of the reaction device inner tank 20 is greater than the power consumed by the first motor 40, in this embodiment, the second motor 30 is not started until the raw materials to be processed and the additives have been mixed, so as to reduce the power consumed during the processing.

[0117] Example 4

[0118] like Figure 4 As shown, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned automatic feeding and stirring time control method for polymer materials is implemented.

[0119] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art 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.

[0121] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatically feeding and stirring time control of polymer materials, characterized in that: include: S10: Obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed; S20: acquiring first historical working data of the first motor, calculating an aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring; S30: acquiring the real-time speed of the first motor and the surface image of the raw material, and segmenting the processing time interval based on the real-time speed of the first motor and the surface image of the raw material to generate processing time segments, wherein the processing time segments include a start-up phase, a working phase, and a termination phase; S40: taking the end time of the working phase as the start time of the second motor.

2. The automatic feeding and stirring time control method for polymer materials according to claim 1, characterized in that: The first historical working data includes a first historical operating time, a first historical current difference, a first historical operating temperature, and a first historical vibration intensity. The method for calculating the first motor aging coefficient based on the first historical working data includes: Where, FAC is the first motor aging coefficient, n is the number of segments of the first historical operating time, HOT i is the first historical operating temperature of the i-th segment, HOT sd is the standard operating temperature, HOM i is the first historical running time of the i-th segment, HVY i is the first historical vibration intensity of the ith segment, HVY sd is the standard vibration intensity, HCD i is the first historical current difference of the i-th segment, and u1, u2, u3 and u4 are all weight factors.

3. The automatic feeding and stirring time control method for polymer materials according to claim 1, characterized in that: The method for constructing the processing time generation model comprises: A first sample data set is obtained, wherein the first sample data set includes a historical first motor standard speed, a historical first motor aging coefficient, a historical weight of raw materials to be processed, and a historical processing time interval. The first sample data set is divided into a first sample training set and a first sample test set, and a regression network is constructed. The historical first motor standard speed, the historical first motor aging coefficient, and the historical weight of raw materials to be processed in the first sample training set are used as input data of the regression network, and the historical processing time interval in the first sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the real-time processing time interval. The initial regression network is tested using the first sample test set, and the regression network that satisfies a preset error value is output as a processing time generation model.

4. The automatic feeding and stirring time control method for polymer materials according to claim 1, characterized in that: The method for segmenting the processing time interval based on the real-time rotation speed of the first motor and the surface image of the raw material includes: The real-time speed acceleration is determined based on the real-time speed of the first motor, and the processing time interval is divided into a startup phase and a rotation time interval according to the real-time speed acceleration and the corresponding first moment. The raw material surface image is input into a pre-built stirring classification model to obtain the stirring category, and the rotation time interval is divided into a working phase and a termination phase based on the second moment corresponding to the stirring category. The stirring category includes completed stirring and incomplete stirring.

5. The automatic feeding and stirring time control method for polymer materials according to claim 4, characterized in that: The method for determining the speed acceleration based on the real-time speed of the first motor includes: The real-time speed of the first motor is fitted to generate a real-time speed curve, and the slope of the real-time speed curve is used as the real-time speed acceleration.

6. The automatic feeding and stirring time control method for polymer materials according to claim 4, characterized in that: The method of dividing the processing time interval into a start-up phase and a rotation time interval according to the rotation speed acceleration and the corresponding first moment includes: When the real-time speed acceleration is less than the preset acceleration threshold, the real-time speed acceleration is recorded, the first moment when the real-time speed acceleration is less than the threshold is recorded, and the first moment is used as the end moment of the startup phase.

7. The method for automatic feeding and stirring time control of polymer materials according to claim 4, characterized in that: The method for dividing the rotation time interval into a working stage and a termination stage based on the second moment corresponding to the stirring category includes: The stirring category is continuously obtained within the rotation time interval. When the stirring category is stirring completed, the second moment when the stirring category is stirring completed for the first time is recorded, and the second moment is used as the end moment of the working stage.

8. The method for automatic feeding and stirring time control of polymer materials according to claim 4, characterized in that: The method for constructing the stirring classification model includes: Obtain h groups of training data, where h is a positive integer greater than 1, and the training data includes historical raw material surface images and historical stirring categories. The historical raw material surface images and historical stirring categories are used as sample sets, and the sample sets are divided into training sets and test sets. A classifier is constructed, and the historical raw material surface images in the training set are used as input data, and the historical stirring categories in the training set are used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set, and the initial classifier having an accuracy greater than a preset threshold is output as a stirring classification model.

9. The method for automatic feeding and stirring time control of polymer materials according to claim 1, characterized in that: The method comprises obtaining second historical working data of the second motor, calculating an aging coefficient of the second motor based on the second historical working data, inputting the termination time and the second motor aging coefficient into a pre-built time adjustment model, and obtaining a start time, wherein the termination time is the termination time of the working stage, and the start time is the start time of the second motor.

10. The automatic feeding and stirring time control method for polymer materials according to claim 9, characterized in that: The method for calculating the second motor aging coefficient based on the second historical working data includes: Where SAC is the second motor aging coefficient, K is the number of segments of the second historical operating time, SOT i is the second historical operating temperature of the mth segment, SOT sd is the standard operating temperature, SOM i is the second historical running time of the mth segment, SVY i is the second historical vibration intensity of the mth segment, SVY sd is the standard vibration intensity, SCD i is the second historical current difference of the mth segment, and q1, q2, q3 and q4 are all weight factors.

11. An automatic feeding and stirring time control system for polymer materials, which is used to implement the automatic feeding and stirring time control method for polymer materials according to any one of claims 1 to 10, characterized in that: include: Data acquisition module: used to obtain the type and weight of the raw material to be processed, and determine the standard speed of the first motor based on the type and mapping relationship of the raw material to be processed; A processing time generation module: used for obtaining first historical working data of the first motor, calculating the aging coefficient of the first motor based on the first historical working data, inputting the standard speed of the first motor, the aging coefficient of the first motor and the weight of the raw material to be processed into a pre-built processing time generation model, and obtaining a processing time interval, wherein the processing time interval is a time interval from the start of stirring the raw material to be processed to the completion of stirring; Segmentation module: used to obtain the real-time speed of the first motor and the surface image of the raw material, segment the processing time interval based on the real-time speed of the first motor and the surface image of the raw material, and generate processing interval segments, which include a start-up phase, a working phase and a termination phase; The time determination module is used to use the end time of the working phase as the start time of the second motor.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for automatically feeding and stirring time control of polymer materials according to any one of claims 1 to 10 is implemented.

Images