A batching control system and method based on PLC

Abstract

The present application discloses a PLC-based batching control system and method, which relates to the field of automated control technology, and solves the technical problem that the prior art ignores the cleaning of a mixing box, so that the residues will cause low precision of the product or even potential safety hazards when it is used next time, resulting in low efficiency of batching control; the required raw materials and required raw material quantities are obtained through a raw material quantity estimation model, and the raw materials are transported according to the required raw material quantities and the raw material quantities in a dropping tank; the dropping pressure and reaction time are calculated according to the required raw material quantities; the dropping pressure speed is generated according to the required raw materials; the equipment is cleaned according to the experimental formula and the experimental demand, so as to avoid the user from contacting with harmful raw materials and the occurrence of low precision due to self-weighing; after the experiment, the equipment is cleaned according to the characteristics of the product to ensure that there is no residue, thereby improving the accuracy and safety of the experimental process and further improving the efficiency of batching control.

Description

Technical Field

[0001] The present application belongs to the field of automation control technology, and specifically is a PLC-based batching control system and method. Background Art

[0002] Ingredient control is a crucial link in the production process, especially in the chemical, food, building materials and other industries. Ingredient control directly affects the quality, production efficiency and cost of the final product. In chemical experiments, the selection and use of ingredients are crucial, and they directly affect the accuracy and reliability of the experimental results. In addition, long-term contact with chemicals by users may cause harm to the body, so it is particularly important to realize an automated ingredient control system.

[0003] The prior art (invention patent application with publication number CN106622011A) discloses a silver-plated line paint spraying section batching and control system, including a stirring box, a top of which is provided with an electrically controlled exhaust valve, a hydrometer and a pH meter are arranged inside the stirring box; a solution use box connected to the stirring box through a metering pump and a pipeline, a liquid level sensor is arranged inside the solution use box; an adding mechanism for metering and adding components to the stirring box, an adjusting motor arranged on one side of a water curtain plate and capable of driving the water curtain plate to flip so as to adjust the size of the paint curtain, and a PLC controllably connected to the liquid level sensor, the hydrometer, the pH meter, the electrically controlled exhaust valve, the adjusting motor and the adding mechanism.

[0004] In the above case, the addition of chemicals was adjusted according to the feedback information of the prepared solution, thereby ensuring the stability and accuracy of the chemical preparation ratio and reducing or eliminating the potential waste caused by the unstable ratio of the liquid medicine. However, the cleaning of the mixing box was neglected, so that the residues would cause low accuracy and even safety hazards when used next time, resulting in low efficiency of ingredient control. Therefore, the ingredient control system still needs further improvement. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a PLC-based ingredient control system to solve the technical problem that the prior art ignores the cleaning of the mixing box, resulting in residues causing low precision and even safety hazards in the product when used next time, leading to low efficiency of ingredient control.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a PLC-based batching control system, comprising: a data acquisition module, a data analysis module, a control module and a database;

[0007] The data acquisition module is used to acquire the experimental formula, experimental demand and equipment data through the data acquisition device;

[0008] The data analysis module: inputs the experimental formula and the experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities, wherein the raw material quantity estimation model is constructed by an artificial intelligence model; calculates the dripping pressure size according to the required raw material quantity; generates the dripping pressure speed according to the required raw material; and generates the reaction time according to the required raw material quantity;

[0009] The control module: transports raw materials according to the required raw material quantity and the raw material quantity in the dropping tank; transmits and stores the product after the reaction time; and cleans the equipment according to the experimental formula and the experimental demand.

[0010] Through the above steps, the present application can adaptively find the corresponding amount of raw materials according to user needs, without the need for users to search and weigh them by themselves, thereby reducing contact with them and preventing their bodies from being harmed; at the same time, the dripping pressure is adaptively changed according to the characteristics of the raw materials, so that the required raw materials with higher volatility can quickly participate in the reaction, avoiding slow dripping and reducing their performance; after the experiment, the equipment is cleaned according to the characteristics of the product to ensure that there is no residue, thereby improving the accuracy and safety of the experimental process and further improving the efficiency of ingredient control.

[0011] Furthermore, the raw material quantity estimation model is constructed by an artificial intelligence model, including:

[0012] Obtain several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities;

[0013] Divide several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0014] Select an AI model as the base model;

[0015] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0016] By verifying the pre-trained model on the test set, we finally obtained a raw material quantity estimation model whose input is the experimental formula and experimental demand, and whose output is the required raw materials and required raw material quantities.

[0017] Further, the step of calculating the dripping pressure according to the required raw material amount includes:

[0018] Obtain the required raw material quantity XYL, the dripping port area S and the standard pressure BF of the dripping tank; the standard pressure BF refers to the pressure of dripping the unit required raw material quantity DXYL under the standard dripping port area BS;

[0019] By formula Calculate the drop pressure DYD; where α1 is the proportionality coefficient, α1∈(0,1); DS is the unit area.

[0020] The present application can accurately obtain the required raw materials and their corresponding required raw material quantities for the experiment that the user wants to realize through the raw material quantity estimation model. Errors are inevitable in manual calculation and weighing of the raw material quantities. The required amount of raw materials dripped out is achieved by changing the dripping pressure of the dripping tank. The dripping pressure is accurately controlled by the equipment so that the required amount of raw materials dripped out is accurate, thereby improving the accuracy of the required raw material quantity for the experimental process.

[0021] Furthermore, the method of generating the dropping pressure speed according to the required raw material includes:

[0022] Obtain the required raw materials and their corresponding volatility level HD, the distance L between the dripping tank opening and the dripping position, and the standard dripping pressure speed BDV of the standard volatility level BHD;

[0023] By formula Calculate the dripping pressure velocity DV; wherein α2 is the proportionality coefficient, α2∈(0,1); DHD is the unit level, DL is the unit distance; β1 and β2 are weight coefficients, β1 and β2∈(0,1).

[0024] Further, generating the reaction time according to the required raw material amount includes:

[0025] Obtain the required raw material quantity XYL, the standard required raw material quantity BXYL, and the standard response time BT of the standard required raw material quantity;

[0026] By formula Calculate the reaction time FT; where α3 is the proportionality coefficient, α3∈(0,1).

[0027] Furthermore, the raw material delivery according to the required raw material amount and the raw material amount in the dropping tank includes:

[0028] Obtain the required amount of raw materials and the amount of raw materials in the drip tank;

[0029] Determine whether the amount of raw materials in the drip tank is greater than the required amount of raw materials;

[0030] If so, do nothing;

[0031] Otherwise, the raw material difference between the required raw material amount and the raw material amount in the dropping tank is calculated; the required raw material is added to the corresponding dropping tank according to the raw material difference to realize raw material transportation.

[0032] Furthermore, the equipment cleaning according to the experimental formula and experimental demand includes:

[0033] Obtain experimental formula and experimental demand;

[0034] Determine whether the experimental formula is a water-soluble substance;

[0035] If yes, clean the equipment by injecting water;

[0036] Otherwise, the degradation raw materials and the degradation raw material demand are generated according to the experimental formula and the experimental demand; the equipment is cleaned by injecting water; the degradation raw materials are raw materials that degrade the experimental formula into water-soluble substances.

[0037] Furthermore, the step of generating the degradation raw material and the required amount of the degradation raw material according to the experimental formula and the experimental required amount includes:

[0038] Acquire the experimental recipe, experimental demand and equipment data for reaction equipment size;

[0039] Inputting the experimental formula, experimental demand and reaction equipment size of equipment data into the residual quantity estimation model to obtain the formula residual quantity; the residual quantity estimation model is constructed by an artificial intelligence model;

[0040] The experimental formula and the formula residual amount are input into the degradation raw material model to obtain the degradation raw material and its corresponding degradation raw material demand; the degradation raw material model is constructed by an artificial intelligence model.

[0041] This application takes into account the cleaning of the equipment after the experiment. If residues still appear in the reaction equipment after the experiment, it will have a great impact on subsequent experiments. By predicting the residual amount of the product after this experiment, the corresponding degradation raw materials and degradation raw material amounts are calculated based on the experimental formula. The corresponding degradation raw materials and degradation raw material amounts can make the residual amount of the product be able to be timely and effectively degraded into water-soluble substances, and then discharged by water injection to avoid affecting the accuracy and safety of subsequent experiments.

[0042] Furthermore, the residual amount estimation model is constructed by an artificial intelligence model, including:

[0043] Obtain the reaction equipment size and corresponding formula residual quantity of several historical experimental formulas, experimental demand and equipment data;

[0044] Divide the reaction equipment dimensions of several historical experimental formulas, experimental demand quantities and equipment data and their corresponding formula residual quantities into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0045] Select an AI model as the base model;

[0046] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0047] By verifying the pre-trained model on the test set, we finally obtained the residual quantity estimation model whose input is the experimental formula, experimental demand and equipment data, and whose output is the residual quantity of the formula.

[0048] Furthermore, the degradation raw material model is constructed by an artificial intelligence model, including:

[0049] Obtain several historical experimental formulas and formula residuals and their corresponding degradation raw materials and degradation raw material requirements;

[0050] Divide several historical experimental formulas and formula residual amounts and their corresponding degradation raw materials and degradation raw material requirements into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0051] Select an AI model as the base model;

[0052] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0053] By verifying the pre-trained model on the test set, we finally obtained a degradation raw material model whose input is the experimental formula and formula residual amount, and whose output is the degradation raw material and the degradation raw material demand.

[0054] Another aspect of the present invention provides a PLC-based batching control method, comprising:

[0055] S0: Obtain experimental formula, experimental demand and equipment data;

[0056] S1: Inputting the experimental formula and the experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities, wherein the raw material quantity estimation model is constructed by an artificial intelligence model; and transporting the raw materials according to the required raw material quantities and the raw material quantities in the drip tank;

[0057] S2: Calculate the dripping pressure according to the required raw material amount; generate the dripping pressure speed according to the required raw material amount; generate the reaction time according to the required raw material amount;

[0058] S3: After the reaction time, the product is transferred and stored; the equipment is cleaned according to the experimental formula and experimental requirements.

[0059] Compared with the prior art, the beneficial effects of this application are:

[0060] The present application obtains a number of required raw materials and their corresponding required raw material quantities by inputting the experimental formula and the experimental demand into the raw material quantity estimation model, and transports the raw materials according to the required raw material quantities and the raw material quantities in the dropping tank; calculates the dropping pressure according to the required raw material quantities; generates the dropping pressure speed according to the required raw materials; generates the reaction time according to the required raw material quantities; transmits and stores the product after the reaction time; cleans the equipment according to the experimental formula and the experimental demand, and can adaptively find the corresponding amount of raw materials according to user needs, avoiding the user's contact with harmful raw materials and self-weighing resulting in low precision. At the same time, the dropping pressure is adaptively changed according to the characteristics of the raw materials to ensure that the raw materials can participate in the generation process of the product in a timely and effective manner; after the experiment, the equipment is cleaned according to the characteristics of the product to ensure that there is no residue, thereby improving the accuracy and safety of the experimental process and further improving the efficiency of ingredient control.

[0061] The present application calculates the dripping pressure rate according to the volatility level of the required raw material and the distance between the dripping tank mouth and the dripping position; the greater the dripping pressure rate, the faster the required raw material can drip out of the dripping tank, which can reduce the contact between the required raw material and the air, avoid the volatilization of the required raw material with higher volatility during the dripping process, resulting in poor effect of the required raw material, and further improve the accuracy of the experiment.

[0062] The present application takes into account the cleaning of the equipment after the experiment, and obtains the residual amount of the experimental product through the experimental formula, experimental requirements and reaction equipment size, and uses the residual amount as a benchmark to generate degradation raw materials that can degrade the experimental formula into water-soluble substances, as well as the amount of degradation raw materials corresponding to the degradation raw materials that can completely react with the residual amount of the experimental formula, so that the residual amount of the product can be discharged in a timely and effective manner to avoid affecting the accuracy and safety of subsequent experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 This is a schematic diagram of the principle of a PLC-based batching control system of the present application;

[0065] Figure 2 The equipment cleaning flow chart for this application;

[0066] Figure 3 This is a flow chart of a PLC-based batching control method of the present application. DETAILED DESCRIPTION

[0067] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0068] See also Figure 1 , the first aspect of the present application provides a PLC-based batching control system, including: a data acquisition module, a data analysis module, a control module and a database;

[0069] Data acquisition module: obtain experimental formula, experimental demand and equipment data through data acquisition equipment; data acquisition equipment includes various sensors, etc.;

[0070] Data analysis module: input the experimental formula and experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities. The raw material quantity estimation model is constructed through an artificial intelligence model; the dripping pressure is calculated according to the required raw material quantity, and the dripping pressure refers to the pressure applied to the dripping tank; the dripping pressure speed is generated according to the required raw materials, and the dripping pressure speed refers to the pressure speed applied to the dripping tank; the reaction time is generated according to the required raw material quantity, and the reaction time refers to the time of the experiment in the reaction equipment;

[0071] Control module: transport raw materials according to the required raw material quantity and the raw material quantity in the drip tank; transmit and store the product after the reaction time; clean the equipment according to the experimental formula and experimental demand.

[0072] Through the above steps, this embodiment can automatically control the corresponding amount of required raw materials according to user needs, and adaptively change the dripping pressure according to the characteristics of the raw materials, so that the required raw materials can be timely and effectively involved in the generation process of the product, avoiding the adverse effects of raw material quantity deviation and raw material performance reduction on the experiment; after the experiment, the equipment is cleaned according to the characteristics of the product to ensure that there is no residue, which improves the accuracy and safety of the experimental process and further improves the efficiency of ingredient control.

[0073] The raw material quantity estimation model in this embodiment is constructed by an artificial intelligence model, including:

[0074] Obtain several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities;

[0075] Divide several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain training set, verification set and test set; the ratio between the training set, test set and verification set is 7:2:1;

[0076] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a BP neural network model, etc.;

[0077] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0078] By verifying the pre-trained model on the test set, we finally obtained a raw material quantity estimation model whose input is the experimental formula and experimental demand, and whose output is the required raw materials and required raw material quantities.

[0079] In this embodiment, the amount of dropwise addition pressure is calculated according to the required amount of raw materials, including:

[0080] Obtain the required raw material quantity XYL, the dripping port area S and the standard pressure BF of the dripping tank; the standard pressure BF refers to the pressure of dripping the unit required raw material quantity DXYL under the standard dripping port area BS;

[0081] By formula Calculate the dripping pressure DYD; wherein, α1 is the proportionality coefficient, α1∈(0,1), and the specific value is set according to experience; DS is the unit area, and the specific value is set according to experience. In this embodiment, DS is set to 1 square centimeter; the smaller the dripping port area of ​​the dripping tank, the more pressure is required to drip out the required amount of raw materials to meet the requirements, and the more the required amount of raw materials, the more pressure is required to reach the target required amount of raw materials; therefore, the dripping pressure increases accordingly.

[0082] In this embodiment, the dropwise addition pressure rate is generated according to the required raw materials, including:

[0083] Obtain the required raw materials and their corresponding volatility level HD, the distance L between the dripping tank mouth and the dripping position, and the standard dripping pressure speed BDV of the standard volatility level BHD; the standard volatility level BHD refers to the lowest value of the emission level, and its corresponding standard dripping pressure speed BDV is also the dripping pressure speed at the lowest volatility level; the volatility level is assessed by experts based on the volatility of the raw materials in the air;

[0084] By formula Calculate the dripping pressure rate DV; wherein α2 is the proportional coefficient, α2∈(0,1), and the specific value is set according to experience; DHD is the unit level, DL is the unit distance, and the specific value is set according to experience. In this embodiment, DL is set to 1 cm; β1 and β2 are weight coefficients, β1 and β2∈(0,1); the specific value is set according to experience; when the volatility level of the required raw material is higher, if the dripping pressure rate is smaller, the required raw material will be in contact with the air for a longer time, affecting its performance; when the distance between the dripping tank mouth and the dripping position is longer, the required raw material needs to travel a longer distance to reach the target position, which also affects the efficiency of the experiment; therefore, the dripping pressure rate increases accordingly.

[0085] In this embodiment, the reaction time is generated according to the required raw material amount, including:

[0086] Obtain the required raw material quantity XYL, the standard required raw material quantity BXYL, and the standard response time BT of the standard required raw material quantity;

[0087] By formula Calculate the reaction time FT; wherein α3 is a proportional coefficient, α3∈(0, 1), and the specific value is set based on experience; the more raw materials are required, the longer the reaction time in the reaction equipment will be so that all the required raw materials can be fully used, making the final product more stable; therefore, the reaction time will increase accordingly; this embodiment calculates the reaction time based on the required raw material amount, thereby ensuring that a number of required raw materials have sufficient time to react, and at the same time will not cause extra waiting time, thereby saving time cost.

[0088] In this embodiment, raw material delivery is performed according to the required raw material amount and the raw material amount in the dropping tank, including:

[0089] Obtain the required amount of raw materials and the amount of raw materials in the drip tank;

[0090] Determine whether the amount of raw materials in the drip tank is greater than the required amount of raw materials;

[0091] If so, do nothing;

[0092] Otherwise, the raw material difference between the required raw material amount and the raw material amount in the dropping tank is calculated; the required raw material is added to the corresponding dropping tank according to the raw material difference to realize raw material transportation.

[0093] In this embodiment, it is determined whether the amount of raw materials in the dropping tank meets the current required amount of raw materials. If so, there is no need to add additional raw materials to the dropping tank. If not, the difference in the required amount of raw materials is added to the corresponding dropping tank to ensure that the corresponding amount of raw materials can be added to the reaction equipment at one time in each experiment, thereby improving the experimental efficiency.

[0094] See also Figure 2In this embodiment, the equipment is cleaned according to the experimental formula and the experimental demand, including:

[0095] Obtain experimental formula and experimental demand;

[0096] Determine whether the experimental formula is a water-soluble substance; a water-soluble substance is one that can be dissolved in water and completely washed away by water without leaving any residue;

[0097] If yes, clean the equipment by injecting water;

[0098] Otherwise, the degradation raw materials and the degradation raw material requirements are generated according to the experimental formula and the experimental requirements; the equipment is cleaned by injecting water; the degradation raw materials are raw materials that degrade the experimental formula into water-soluble substances.

[0099] In this embodiment, the non-water-soluble substances are first degraded, and the water-soluble substances are obtained by chemically reacting the degraded raw materials. Then, the equipment is cleaned by injecting water, which ensures that there are no experimental residues in the equipment after the experiment, provides equipment environment guarantee for subsequent experiments, and enhances the accuracy and safety of the experiment.

[0100] In this embodiment, the generation of degradation raw materials and degradation raw material requirements according to the experimental formula and experimental requirements includes:

[0101] Acquire the experimental recipe, experimental demand and equipment data for reaction equipment size;

[0102] The experimental formula, experimental demand and equipment size of the equipment data are input into the residual quantity estimation model to obtain the formula residual quantity; the residual quantity estimation model is constructed by an artificial intelligence model;

[0103] The experimental formula and the formula residual amount are input into the degradation raw material model to obtain the degradation raw material and its corresponding degradation raw material demand; the degradation raw material model is constructed through an artificial intelligence model.

[0104] The residual volume estimation model in this embodiment is constructed by an artificial intelligence model, including:

[0105] Obtain the reaction equipment size and corresponding formula residual quantity of several historical experimental formulas, experimental demand and equipment data;

[0106] The reaction equipment dimensions of several historical experimental formulas, experimental demand quantities and equipment data and their corresponding formula residual quantities are divided into training data, verification data and test data; data preprocessing is performed on the training data, verification data and test data to obtain training sets, verification sets and test sets; the ratio between the training set, the test set and the verification set is 7:2:1;

[0107] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a convolutional neural network model, etc.;

[0108] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0109] By verifying the pre-trained model on the test set, we finally obtained the residual quantity estimation model whose input is the experimental formula, experimental demand and equipment data, and whose output is the residual quantity of the formula.

[0110] The degradation raw material model in this embodiment is constructed by an artificial intelligence model, including:

[0111] Obtain several historical experimental formulas and formula residuals and their corresponding degradation raw materials and degradation raw material requirements;

[0112] Several historical experimental formulas and formula residual amounts and their corresponding degradation raw materials and degradation raw material requirements are divided into training data, verification data and test data; data preprocessing is performed on the training data, verification data and test data to obtain training sets, verification sets and test sets; the ratio between the training set, the test set and the verification set is 7:2:1;

[0113] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a BP neural network model, etc.;

[0114] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0115] By verifying the pre-trained model on the test set, we finally obtained a degradation raw material model whose input is the experimental formula and formula residual amount, and whose output is the degradation raw material and the degradation raw material demand.

[0116] See also Figure 3 Another aspect of the present application provides a PLC-based batching control method, comprising:

[0117] S0: Obtain experimental formula, experimental demand and equipment data;

[0118] S1: Input the experimental formula and experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities. The raw material quantity estimation model is constructed through an artificial intelligence model; the raw materials are transported according to the required raw material quantities and the raw material quantities in the drip tank;

[0119] S2: Calculate the dripping pressure according to the required raw material amount; generate the dripping pressure speed according to the required raw material amount; generate the reaction time according to the required raw material amount;

[0120] S3: After the reaction time, the product is transferred and stored; the equipment is cleaned according to the experimental formula and experimental requirements.

[0121] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0122] The working principle of the present application is as follows: by obtaining the experimental formula, experimental demand and equipment data, the experimental formula and experimental demand are input into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities, and the raw materials are transported according to the required raw material quantities and the raw material quantities in the dropping tank; the dropping pressure is calculated according to the required raw material quantities; the dropping pressure speed is generated according to the required raw materials; the reaction time is generated according to the required raw material quantities; the product is transmitted and stored after the reaction time; the equipment is cleaned according to the experimental formula and experimental demand, and the corresponding amount of raw materials can be adaptively found according to user needs, avoiding the user from contacting harmful raw materials and self-weighing resulting in low precision. At the same time, the dropping pressure is adaptively changed according to the characteristics of the raw materials to ensure that the raw materials can participate in the generation process of the product in a timely and effective manner; after the experiment, the equipment is cleaned according to the characteristics of the product to ensure that there is no residue, which improves the accuracy and safety of the experimental process, further improves the efficiency of the batching control, and avoids the problem that the prior art ignores the cleaning of the mixing box, so that the residue will cause low precision or even safety hazards to the product when it is used next time, resulting in low efficiency of the batching control.

[0123] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A PLC-based batching control system, characterized in that: include: Data acquisition module, data analysis module, control module and database; The data acquisition module is used to acquire the experimental formula, experimental demand and equipment data through the data acquisition device; The data analysis module: inputs the experimental formula and the experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities, wherein the raw material quantity estimation model is constructed by an artificial intelligence model; calculates the dripping pressure size according to the required raw material quantity; generates the dripping pressure speed according to the required raw material; and generates the reaction time according to the required raw material quantity; The control module: transports the raw materials according to the required raw material amount and the raw material amount in the dropping tank; transmits and stores the product after the reaction time has passed; Clean the equipment according to the experimental formula and experimental requirements; The equipment cleaning according to the experimental formula and experimental requirements includes: Obtain experimental formula and experimental demand; Determine whether the experimental formula is a water-soluble substance; If yes, clean the equipment by injecting water; Otherwise, the degradation raw materials and the required amount of the degradation raw materials are generated according to the experimental formula and the experimental demand; the equipment is cleaned by injecting water; The step of generating the degradation raw material and the required amount of the degradation raw material according to the experimental formula and the experimental required amount includes: Acquire the experimental recipe, experimental demand and equipment data for reaction equipment size; Inputting the experimental formula, experimental demand and reaction equipment size of equipment data into the residual quantity estimation model to obtain the formula residual quantity; the residual quantity estimation model is constructed by an artificial intelligence model; Inputting the experimental formula and the formula residual amount into the degradation raw material model to obtain the degradation raw material and its corresponding degradation raw material demand; the degradation raw material is a raw material that degrades the experimental formula into water-soluble substances; The degradation raw material model is constructed by an artificial intelligence model, including: Obtain several historical experimental formulas and formula residuals and their corresponding degradation raw materials and degradation raw material requirements; Divide several historical experimental formulas and formula residual amounts and their corresponding degradation raw materials and degradation raw material requirements into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtained a degradation raw material model whose input is the experimental formula and formula residual amount, and whose output is the degradation raw material and the degradation raw material demand.

2. A PLC-based batching control system according to claim 1, characterized in that: The raw material quantity estimation model is constructed by an artificial intelligence model, including: Obtain several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities; Divide several historical experimental formulas, experimental requirements and their corresponding required raw materials and required raw material quantities into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtained a raw material quantity estimation model whose input is the experimental formula and experimental demand, and whose output is the required raw materials and required raw material quantities.

3. A PLC-based batching control system according to claim 1, characterized in that: The step of calculating the dripping pressure according to the required raw material amount includes: Obtain the required raw material quantity XYL, the dripping port area S and the standard pressure BF of the dripping tank; the standard pressure BF refers to the pressure of dripping the unit required raw material quantity DXYL under the standard dripping port area BS; By formula Calculate the drop pressure DYD; where α1 is the proportionality coefficient, α1∈(0,1); DS is the unit area.

4. A PLC-based batching control system according to claim 1, characterized in that: The method of generating a dropwise addition pressure rate according to the required raw materials includes: Obtain the required raw materials and their corresponding volatility level HD, the distance L between the dripping tank mouth and the dripping position, and the standard dripping pressure speed BDV of the standard volatility level BHD; By formula Calculate the dripping pressure velocity DV; wherein α2 is the proportionality coefficient, α2∈(0,1); DHD is the unit level, DL is the unit distance; β1 and β2 are weight coefficients, β1 and β2∈(0,1).

5. A PLC-based batching control system according to claim 1, characterized in that: The step of generating the reaction time according to the required raw material amount comprises: Obtain the required raw material quantity XYL, the standard required raw material quantity BXYL, and the standard response time BT of the standard required raw material quantity; By formula Calculate the reaction time FT; where α3 is the proportionality coefficient, α3∈(0,1).

6. A PLC-based batching control system according to claim 1, characterized in that: The raw material delivery according to the required raw material amount and the raw material amount in the dropping tank includes: Obtain the required amount of raw materials and the amount of raw materials in the drip tank; Determine whether the amount of raw materials in the drip tank is greater than the required amount of raw materials; If so, do nothing; Otherwise, the raw material difference between the required raw material amount and the raw material amount in the dropping tank is calculated; the required raw material is added to the corresponding dropping tank according to the raw material difference to realize raw material transportation.

7. A PLC-based batching control system according to claim 1, characterized in that: The residual volume estimation model is constructed by an artificial intelligence model, including: Obtain the reaction equipment size and corresponding formula residual quantity of several historical experimental formulas, experimental demand and equipment data; Divide the reaction equipment dimensions of several historical experimental formulas, experimental demand quantities and equipment data and their corresponding formula residual quantities into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtained the residual quantity estimation model whose input is the experimental formula, experimental demand and equipment data, and whose output is the residual quantity of the formula.

8. A PLC-based batching control method, applied to a PLC-based batching control system according to any one of claims 1 to 7, characterized in that: include: S0: Obtain experimental formula, experimental demand and equipment data; S1: Inputting the experimental formula and the experimental demand into the raw material quantity estimation model to obtain a number of required raw materials and their corresponding required raw material quantities, wherein the raw material quantity estimation model is constructed by an artificial intelligence model; and transporting the raw materials according to the required raw material quantities and the raw material quantities in the drip tank; S2: Calculate the dripping pressure according to the required raw material amount; generate the dripping pressure speed according to the required raw material amount; generate the reaction time according to the required raw material amount; S3: After the reaction time, the product is transferred and stored; the equipment is cleaned according to the experimental formula and experimental requirements.

Images