Preparation process adjustment method for gypsum

Abstract

The present application relates to the technical field of gypsum preparation, and provides a method for adjusting the preparation process of gypsum. The method includes: collecting the particle size characteristics and acidic characteristics of gypsum particle raw materials; preparing a coating solution, and collecting solution attribute information and solution composition information; establishing a twin model according to the particle size characteristics, acidic characteristics, solution attribute information and solution composition information; connecting the twin model with an optimization model, and the optimization model is embedded with a prediction network; performing optimization according to the prediction network to obtain optimization parameters that meet preset effects; controlling a coating device to perform coating adjustment on the gypsum particle raw materials with the optimization parameters. The present application solves the technical problem that in the process of generating gypsum from citric acid gypsum, due to characteristics such as many impurities and small crystal grains, it is difficult to precisely control the sustained-release effect of the coating layer, realizes the harmless treatment of citric acid gypsum through intelligent process adjustment, improves the sustained-release performance of building gypsum powder, and ensures the effect of gypsum preparation efficiency.

Description

Technical Field

[0001] This application relates to the technical field of building material preparation, specifically to the technical field of gypsum preparation, and particularly to a preparation process adjustment method for gypsum. Background Art

[0002] With the rapid development of industrialization, citric acid gypsum, as an important industrial by-product, has seen its output increase year by year. However, due to its unique chemical and physical properties, such as containing a large amount of organic impurities like hyphae, fine crystal grains, thin flake-shaped crystals, and a low pH value, it is extremely difficult to directly process it into building gypsum. These properties not only affect the preparation efficiency and product quality of building gypsum but also have a serious negative impact on the environment. As the problem of citric acid gypsum accumulation becomes increasingly prominent, these untreated citric acid gypsums not only occupy a large amount of land resources but may also pollute the soil, water bodies, and air through percolation, volatilization, etc., posing a serious threat to the ecological environment. Summary of the Invention

[0003] This application provides a preparation process adjustment method for gypsum, aiming to solve the technical problem that it is difficult to precisely control the slow-release effect of the coating layer during the process of generating gypsum from citric acid gypsum due to characteristics such as a large number of impurities and small crystal grains.

[0004] In view of the above problems, this application provides a preparation process adjustment method for gypsum.

[0005] This application provides a preparation process adjustment method for gypsum, and the method includes: preparing raw gypsum particles, and collecting the particle size characteristics and acidic characteristics of the raw gypsum particles; preparing a coating solution for coating the raw gypsum particles, and collecting the solution property information and solution composition information of the coating solution; establishing a gypsum preparation twin model according to the particle size characteristics, the acidic characteristics, the solution property information, and the solution composition information; connecting the gypsum preparation twin model with a coating process optimization model, wherein the coating process optimization model is embedded with a slow-release effect prediction network; performing slow-release effect optimization according to the slow-release effect prediction network embedded in the coating process optimization model to obtain optimized coating parameters that meet the preset slow-release effect, wherein the optimized coating parameters include the number of coating layers and the thickness of each coating layer; conveying the raw gypsum particles to a coating device, and controlling the coating device to perform multi-layer coating adjustment on the raw gypsum particles with the optimized coating parameters.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The above method for adjusting the preparation process of gypsum first collects and measures the particle size and acidity level of gypsum particle raw materials. Then, a coating solution is prepared, and the properties and composition information of the solution are collected. Subsequently, according to the particle size, acidity level, solution property information, and solution composition information, a twin model for gypsum preparation is established. This model simulates the behavior of gypsum particles during the coating process to help predict and optimize the coating effect. After that, this twin model is connected to an optimization model for the coating process. This optimization model for the coating process incorporates a prediction network for the slow-release effect, which can predict the slow-release effect of gypsum under different coating processes. Using this prediction network, optimization of the slow-release effect can be carried out. By continuously adjusting the coating parameters, a set of optimal parameters can be obtained, enabling the gypsum to have an ideal slow-release effect after coating. Then, the gypsum particle raw materials are conveyed to the coating equipment, and the operation of the equipment is controlled according to the obtained optimized coating parameters. In this way, precise multi-layer coating adjustment of gypsum particles can be achieved, thereby obtaining a final product with the expected slow-release effect. The entire process through intelligent and refined control effectively solves the problem of poor slow-release effect during the preparation of citric acid gypsum, improving the quality and performance of gypsum.

[0008] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a method for adjusting the preparation process of gypsum in an embodiment;

[0011] Figure 2 It is a schematic flowchart after collecting solution information of a method for adjusting the preparation process of gypsum in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] By providing a method for adjusting the preparation process of gypsum in the embodiments of the present application, the technical problem that it is difficult to precisely control the slow-release effect of the coating layer due to characteristics such as many impurities and small crystal grains during the process of generating gypsum from citric acid gypsum is solved.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0014] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0015] Embodiment

[0016] As Figure 1 shown, the present application provides a method for adjusting the preparation process of gypsum, and the method includes:

[0017] Prepare raw gypsum particles, and collect the particle size characteristics and acidic characteristics of the raw gypsum particles; prepare a coating solution for coating the raw gypsum particles, and collect the solution property information and solution composition information of the coating solution.

[0018] With the continuous development of the building materials market and the increasing environmental protection requirements, the performance and quality requirements for gypsum materials are also getting higher and higher. However, traditional gypsum coating processes often have difficulty in precisely controlling the slow-release effect of the coating layer, resulting in unstable performance of the final product and inability to meet market demands. In addition, impurities in citric acid gypsum have an adverse impact on the gypsum preparation process, and also reduce the gypsum preparation efficiency.

[0019] In the embodiments of the present application, during the preparation of gypsum, the system terminal obtains citric acid gypsum as a raw material. Citric acid gypsum is a by-product generated during the production of citric acid. It contains certain impurities and has characteristics such as small crystal grains and acidity. In order to handle these characteristics and improve the properties of citric acid gypsum, the system terminal collects the particle size characteristics of the particles formed from the citric acid gypsum raw material to gypsum particle raw material. The particle size directly affects the dispersibility, fluidity, and processing performance of citric acid gypsum. At the same time, its acidity characteristics are collected because acidity will affect the effect and stability of subsequent coating treatment. Subsequently, a coating solution for coating the gypsum particle raw material is prepared. This coating solution is designed to cover the surface of the gypsum particle raw material, forming one or more layers of coating. These coatings can effectively coat the gypsum particle raw material and have the ability to slowly release internal substances to ensure that the active ingredients in the gypsum particle raw material are released in a stable and continuous manner when needed. When preparing the coating solution, the system terminal collects and records the attribute information of the solution, such as the pH value, concentration, viscosity, etc. of the solution. These attributes are crucial for the stability and effect of the coating process. At the same time, the composition information of the solution is also collected, that is, which chemical components are included in the solution and their respective contents, so as to adjust the formula according to actual needs. These steps are to ensure that the gypsum particle raw material can meet specific performance and application requirements after being coated.

[0020] Further, as Figure 2 shown, after collecting the solution attribute information and solution composition information of the coating solution, the method further includes:

[0021] Conduct a compatibility analysis on the coating solution and the gypsum particle raw material, and output a compatibility detection index. Among them, the compatibility analysis includes the chemical reaction rate, solution adhesion, acid tolerance rate, and impurity precipitation rate; when the compatibility detection index is greater than the preset compatibility threshold, activate the coating process optimization model; when the compatibility detection index is less than the preset compatibility threshold, output a solution replacement reminder.

[0022] Preferably, in order to ensure good compatibility and adaptability between the coating solution and the gypsum particle raw material, a series of adaptability analyses are carried out at the system terminal. These analyses cover key indicators such as the chemical reaction rate, solution adhesion, acid tolerance rate, and impurity precipitation rate. Among them, the chemical reaction rate can evaluate whether an adverse chemical reaction will occur when the coating solution contacts the gypsum particles. The solution adhesion can evaluate whether the coating solution can adhere tightly to the surface of the gypsum particles to form an effective covering layer. The acid tolerance rate can evaluate the stability of the coating solution in an acidic environment, that is, whether it can maintain its original coating performance. The impurity precipitation rate can evaluate whether the coating solution will introduce unnecessary impurities when contacting the gypsum particles, thus affecting the quality of the final product. For the chemical reaction rate, the system terminal analyzes whether an adverse reaction will occur based on historical experience, chemical properties, and reaction mechanisms, considering the solution composition information of the coating solution and the chemical composition information of the gypsum particle raw material. If a reaction will occur, the system terminal calculates the probability of the reaction, that is, the chemical reaction rate, according to historical data. This is generated by calculating the ratio of the number of times the same coating solution reacts when forming a coating layer in historical data to the total number of times this coating solution is used. If no reaction occurs, the system terminal sets the chemical reaction rate to 0. For the solution adhesion, the system terminal evaluates the adhesion of the solution by assessing the integrity of the coating layer formed by the same coating solution in historical data based on professional knowledge and historical experience. For the acid tolerance rate, the system terminal calculates the acid tolerance rate by analyzing whether there will be a violent reaction, whether a precipitate will be formed, and whether there will be a change in chemical composition when the coating solution and the gypsum particle raw material are in an acidic environment with different pH values. This calculation process is similar to the previous one and is based on historical data. For the impurity precipitation rate, the system terminal analyzes whether there are impurities in the solution and particles separated by centrifugation, filtration, etc. after the same coating solution is mixed with the gypsum particles in historical data, and calculates the impurity precipitation rate. Through the above steps, the system terminal can obtain an adaptability detection index. If each item in this index is higher than the preset adaptation threshold, it represents good adaptability between the coating solution and the gypsum particle raw material, and the coating process optimization model can be activated to further optimize the coating parameters. Otherwise, the coating solution needs to be replaced. At this time, the system terminal will output a solution replacement reminder to remind the operator to take corresponding measures to ensure the smooth progress of the subsequent coating process.

[0023] Establish a twin model for gypsum preparation according to the particle size characteristics, the acid characteristics, the solution attribute information, and the solution composition information.

[0024] In one embodiment, the system constructs a digital twin model for gypsum preparation based on the particle size characteristics, acidic characteristics of the gypsum particle raw materials, as well as the solution property information and solution composition information of the coating solution. This twin model is a virtual and digital simulation of the gypsum preparation process, which can be used to simulate various situations and changes that may occur during the actual gypsum preparation process, so as to predict and optimize the gypsum preparation conditions. Specifically, the system terminal establishes a physical model according to the physical processes of gypsum preparation, such as the mixing of particles and the flow of solution. This includes the simulation of physical phenomena such as the dispersion of gypsum particles, the stirring of solution, and mixing. Subsequently, the particle size characteristics and solution property information are analyzed to understand the physical parameters of the gypsum particle raw materials, such as particle size, shape, density, etc., and the operating parameters of the coating solution, such as flow rate and stirring speed. Then, the system terminal analyzes the reaction mechanism between the gypsum particles and the chemical substances in the solution according to the chemical principles of gypsum preparation. This includes chemical processes such as dissolution, precipitation, and crystallization. Based on the chemical reaction mechanism, a chemical model is established. This model needs to be able to describe the interaction and transformation relationships between various chemical substances during the gypsum preparation process. Then, the acidic characteristics and solution composition information are analyzed to understand the chemical parameters such as the pH value of the gypsum particle raw materials, as well as the chemical parameters such as ion concentration, reactant types and concentrations of the coating solution. Finally, the system terminal sets the parameters of the constructed physical model and chemical model according to these physical and chemical parameters. After the model parameter setting is completed, the system terminal integrates the physical model and the chemical model to form a complete twin model for gypsum preparation. This model can simultaneously simulate the physical and chemical phenomena during the gypsum preparation process, enabling the system terminal to predict the performance and reaction mechanism of gypsum under different preparation conditions without actually conducting experimental operations, which helps to improve the preparation efficiency and quality of gypsum.

[0025] Connect the twin model for gypsum preparation with the optimization model for coating process, wherein the optimization model for coating process is embedded with a sustained release effect prediction network.

[0026] In one embodiment, during the process of generating gypsum with citric acid gypsum, by constructing a digital twin model for gypsum preparation, the physical and chemical processes of gypsum preparation can be simulated. To further optimize the gypsum preparation conditions and improve its performance, the system terminal connects the gypsum preparation twin model with the coating process optimization model. The coating process optimization model is trained with historical coating parameters and is also established by integrating a sustained-release effect prediction network. Specifically, the system terminal extracts a large number of historical coating parameters from historical data, and these parameters include the number of historical coating layers and the thickness of each historical coating layer. Subsequently, the number of neurons in the input layer is designed according to the specific parameters of the coating process. Then, the number of hidden layers and the number of neurons in each layer are determined according to the complexity of the problem and the characteristics of the data. After that, the weights and bias terms of the neural network are randomly initialized. And the historical coating parameters are propagated forward through the neural network to calculate the output of each layer. Then, the output results are evaluated through the integrated sustained-release effect prediction network. If the evaluation results do not meet the expected expectations, training continues until the expectations are met. Then, the system terminal embeds the pre-constructed sustained-release effect prediction network into the coating process optimization model. And the output layer of the coating process optimization model is connected to the input layer of the sustained-release effect prediction network. This sustained-release effect prediction network is a neural network model trained based on the monitoring data of the sustained-release process without environmental interference and the monitoring data of the sustained-release process under environmental interference, and can predict and optimize the sustained-release effect in the coating process, thereby ensuring that the gypsum product has better performance and usage effects. The sustained-release effect prediction network analyzes the sustained-release data generated by the gypsum preparation twin model to predict the stability and time when citric acid gypsum releases specific components. Through collaborative work with the gypsum preparation twin model, this network can guide the system terminal to optimize the coating process, enabling the gypsum product to not only meet specific performance requirements but also maintain a stable sustained-release effect.

[0027] Furthermore, the present application provides a method for training the sustained-release effect prediction network, including:

[0028] Obtain the initialization parameters of the sustained-release effect prediction network; according to the gypsum preparation twin model, obtain the first sustained-release data sample, where the first sustained-release data sample is the monitoring data of the sustained-release process without environmental interference.

[0029] Preferably, to optimize the coating process and predict its sustained-release effect, the system terminal determines the network structure of the long short-term memory network (LSTM), including a feature extraction layer, an LSTM layer, and a fully connected layer, according to the complexity of the problem and the characteristics of the data. The long short-term memory network is suitable for processing time series data and can capture long-term dependencies in the data. Subsequently, the system terminal sets the initial parameters for each layer of the long short-term memory network, that is, the initial weight and bias values. These initial values are obtained through random initialization. Then, the system terminal integrates the sustained-release stability rate deviation calculation formula and the sustained-release duration deviation calculation formula into the feature extraction layer. These two calculation formulas are pre-constructed. Then, the system terminal simulates the sustained-release process according to the constructed gypsum preparation twin model to obtain the first sustained-release data sample. These data samples are the monitoring data of the sustained-release process simulated by the twin model without the interference of the actual environment, including the thickness of the coating layer, the sustained-release speed, etc. They represent the sustained-release performance of the gypsum product under ideal conditions and are an important basis for the subsequent training and prediction of the network model.

[0030] Perform sample prediction on the first sustained-release data sample according to the sustained-release effect prediction network to obtain a first sustained-release stability rate sample and a first sustained-release duration sample; train according to the first sustained-release stability rate sample and the first sustained-release duration sample until the preset accuracy rate is reached, and update the parameters of the sustained-release effect prediction network.

[0031] Preferably, in the process of constructing and training the sustained-release effect prediction network, the system terminal first predicts the first sustained-release data sample according to the initialized long short-term memory network. During the prediction process, the long short-term memory network performs weighted calculation on the first sustained-release data sample according to the initial weights, and calculates the first sustained-release stability rate sample. At the same time, the ratio of the thickness of each coating layer in the first sustained-release data sample to the sustained-release rate is calculated to generate the first sustained-release duration sample. Then, the calculated first sustained-release stability rate sample and the first sustained-release duration sample are used to train the long short-term memory network. Specifically, the system terminal uses forward propagation and combines the calculation formula integrated in the feature extraction layer to perform deviation prediction on the first sustained-release stability rate sample and the first sustained-release duration sample. Subsequently, the deviation prediction result is compared with the preset accuracy rate. This preset accuracy rate is set according to the precision requirement and is the maximum allowable deviation. If the deviation prediction result does not meet the requirement of the preset accuracy rate, it means that there is a loss in the long short-term memory network. At this time, the system terminal calculates the loss between the deviation prediction result and the preset accuracy rate through the mean square error. Then, the gradient of the loss with respect to the parameters of the long short-term memory network is calculated through backpropagation, and the weights of the long short-term memory network are updated according to this gradient. Repeat the steps of forward propagation, loss calculation, and backpropagation to update the weights until the requirement of the preset accuracy rate is met, and output this long short-term memory network to generate the sustained-release effect prediction network. Through this process, it can be ensured that the sustained-release effect prediction network can accurately predict the sustained-release effect in the gypsum preparation process, providing strong support for the treatment of citric acid gypsum.

[0032] Further, the present application provides a method for obtaining the first sustained-release stability rate sample, and the method further includes:

[0033] Decompose the first sustained-release data sample to output the first initial sustained-release data sample and the first final sustained-release data sample; for the first initial sustained-release data sample and the first final sustained-release data sample, output the first initial sustained-release stability rate sample and the first final sustained-release stability rate sample; perform weight calculation on the first initial sustained-release stability rate sample and the first final sustained-release stability rate sample to output the first sustained-release stability rate sample.

[0034] Optionally, when predicting the slow-release effect during the citric acid gypsum treatment process using the slow-release effect prediction network, the system terminal first processes and analyzes the first slow-release data sample. This data sample contains the monitoring data from the start to the end of the slow release of the gypsum. To train the slow-release effect prediction network more precisely, the system terminal divides the first slow-release data sample into two stages, namely the first initial slow-release data sample and the first final slow-release data sample. These two stages are divided based on actual needs according to the physical or chemical characteristics of the slow-release process. For example, the initial and final stages are defined according to the change in the slow-release rate. Subsequently, for the data samples of these two stages, the system terminal calculates their slow-release stability rates. The stability rate is an index to measure the degree of duration fluctuation during the slow-release process. For the initial and final stages, since the slow-release conditions and environments are different, their stability rates may also vary. Therefore, the system terminal calculates the corresponding stability rate deviations respectively through the slow-release stability rate deviation calculation formula integrated in the feature extraction layer. These two stability rate deviations are the stability rates of these two stages, namely the first initial slow-release stability rate sample and the first final slow-release stability rate sample. After that, the system terminal performs a weighted calculation on the first initial slow-release stability rate sample and the first final slow-release stability rate sample according to the weights currently configured in the slow-release effect prediction network, fuses the stability rates of the two stages into one, and generates the first slow-release stability rate sample. This sample reflects the comprehensive stability rate of the entire slow-release process. This sample will be used as one of the important input data for training the slow-release effect prediction network to guide the slow-release effect prediction network to learn how to predict the slow-release effect during the citric acid gypsum treatment process.

[0035] Further, the present application provides a method for training the slow-release effect prediction network, and the method further includes:

[0036] Preparing a twin model according to the gypsum to obtain a second slow-release data sample, where the second slow-release data sample is the monitoring data of the slow-release process under environmental interference; predicting the sample of the second slow-release data sample according to the slow-release effect prediction network to obtain a second slow-release stability rate sample and a second slow-release duration sample; training according to the second slow-release stability rate sample and the second slow-release duration sample until the preset accuracy rate is reached, and updating the parameters of the slow-release effect prediction network.

[0037] Optionally, during the treatment of citric acid gypsum, the system terminal also obtains a second slow-release data sample based on the gypsum preparation twin model simulation. These data are monitoring data of the slow-release process under various interference factors that may exist. These interference factors include temperature, humidity, changes in raw material quality, etc. Using the second slow-release data sample to train the slow-release effect prediction network can help the slow-release effect prediction network learn how to adapt to these interferences, thereby improving the generalization ability of the slow-release effect prediction network in a real environment. Subsequently, the system terminal uses the same method as the first slow-release data sample to train the slow-release effect prediction network to predict the second slow-release data sample and obtain the second slow-release stability rate sample and the second slow-release duration sample. These two samples respectively reflect the stability and duration of the gypsum slow-release process under the simulated interference environment. The slow-release effect prediction network is then trained with these two samples to make the weights and biases in the slow-release effect prediction network closer to actual needs. By continuously training and updating the model parameters, the system terminal can gradually improve the predictive ability of the slow-release effect prediction network for the slow-release process, which helps to better understand the slow-release mechanism of citric acid gypsum treatment during gypsum preparation.

[0038] The sustained-release effect is optimized according to the sustained-release effect prediction network embedded in the coating process optimization model to obtain the optimal coating parameters that meet the preset sustained-release effect, wherein the optimal coating parameters include the number of coating layers and the thickness of each coating layer.

[0039] In one embodiment, in order to release organic matter such as mycelium and trace amounts of oil, pigment and other organic matter generated during the citric acid gypsum coating process at a stable rate, the system terminal uses the slow-release effect prediction network embedded in the coating process optimization model to optimize the slow-release effect. The system terminal continuously tries and adjusts the coating parameters, that is, changes the number of coating layers or the thickness of each layer, to minimize the slow-release effect deviation output by the slow-release effect prediction network, thereby finding a set of parameter combinations that can meet the preset slow-release effect, that is, optimizing the coating parameters.

[0040] Furthermore, the present application provides a method for optimizing the sustained release effect according to the sustained release effect prediction network embedded in the coating process optimization model to obtain the optimal coating parameters that meet the preset sustained release effect, and the method also includes:

[0041] The first set of input data and the second set of input data are analyzed according to the coating process optimization model to obtain initial optimization coating parameters; the initial optimization coating parameters are predicted using the sustained release effect prediction network to output a sustained release effect deviation, wherein the sustained release effect deviation includes a sustained release stability rate deviation and sustained release duration deviation ; By minimizing the sustained-release effect deviation, the optimal coating parameters that meet the preset sustained-release effect are obtained.

[0042] Preferably, the system terminal inputs two sets of input data into the constructed optimization model for the coating process. These two sets of data include the key parameters of the coating process, such as the number of coating layers and the thickness of each coating layer. The model generates initial optimized coating parameters based on this data. These initial optimized coating parameters are a set of coating parameters that the model sets according to the learned knowledge and conforms to the current situation. Subsequently, the system terminal inputs these initial optimized coating parameters into the sustained-release effect prediction network. The sustained-release effect prediction network predicts the sustained-release effect of the gypsum product based on the initial optimized coating parameters and outputs a deviation of the sustained-release effect. This deviation represents the difference between the prediction result and the preset target of the sustained-release effect, including the deviation of the sustained-release stability rate and the deviation of the sustained-release duration . Then, the system terminal compares whether this deviation of the sustained-release effect meets the requirements of the preset sustained-release effect. If not, the system terminal inputs these initial optimized coating parameters into the optimization model for the coating process for parameter optimization to minimize the deviation of the sustained-release effect, that is, the deviation of the sustained-release effect output by the sustained-release effect prediction network tends to be stable. At this time, the system terminal compares whether this deviation of the sustained-release effect meets the requirements of the preset sustained-release effect. If it still does not meet the requirements, the system terminal re-initializes the parameters and repeats the above process until a set of optimized coating parameters that meet the preset sustained-release effect is found.

[0043] Furthermore, the present application provides the formula for calculating the deviation of the sustained-release stability rate

[0044] The formula for calculating the deviation of the sustained-release stability rate is as follows: ;

[0045] wherein, is the number of coating layers, represents the sustained-release time of the i-th coating layer, is the average value of the sustained-release times of each layer, is the deviation of the sustained-release stability rate, and the standard deviation of the sustained-release times of all coating layers is calculated to evaluate the dispersion degree of the sustained-release times.

[0046] Optionally, the formula for calculating the deviation of the sustained-release stability rate integrated in the feature extraction layer of the sustained-release effect prediction network is designed to evaluate the dispersion degree of the sustained-release times of each coating layer in the coating process. The specific formula is as follows: ;

[0047] wherein, N represents the number of coating layers, that is, the number of coating operations performed on the citric acid gypsum particles in the entire coating process. represents the sustained-release time of the i-th coating layer, the thickness of the i-th layer, is the sustained-release rate constant of the i-th layer. is the deviation of the sustained-release stability rate, which is the result of the standard deviation of the sustained-release time of all coating layers and is used to evaluate the dispersion degree of the sustained-release time, that is, the quality of the sustained-release stability rate. The higher the dispersion degree, the greater the difference in the sustained-release time of each layer, and the relatively poorer the sustained-release stability rate.

[0048] Furthermore, the present application provides the deviation of the sustained-release duration The calculation formula of, the method further includes:

[0049] The deviation of the sustained-release duration The calculation formula is as follows: ;

[0050] Wherein, represents the absolute deviation between the actual average sustained-release duration and the target sustained-release time ; represents the average value of the sustained-release times of all coating layers, represents the sustained-release time of the i-th coating layer, is the thickness of the i-th layer, is the sustained-release rate constant of the i-th layer, is the expected sustained-release time, is the number of coating layers.

[0051] Optionally, the calculation formula of the deviation of the sustained-release duration integrated by the feature extraction layer of the sustained-release effect prediction network is used to measure the difference between the actual average sustained-release duration and the target sustained-release time. The specific calculation formula is as follows: ;

[0052] Wherein, The deviation of the sustained-release duration represents the absolute deviation between the actual average sustained-release duration and the target sustained-release time. represents the average value of the sustained-release times of all coating layers. is the sustained-release time of the i-th coating layer adjusted by the sustained-release rate constant ki. is the thickness of the i-th coating layer, is the sustained-release rate constant of the i-th layer, which is used to describe the sustained-release rate of this layer. is the expected sustained-release time, which is determined according to specific application requirements. is the number of coating layers, which represents the number of coating layers constructed in the entire coating process of the citric acid gypsum. By calculating the deviation of the sustained-release duration, the gap between the actual sustained-release duration and the target sustained-release time can be intuitively understood, and further guide the optimization and adjustment of the coating parameters.

[0053] Transport the gypsum particle raw materials to the coating equipment, and control the coating equipment to perform multi-layer coating adjustment on the gypsum particle raw materials with the optimized coating parameters.

[0054] In one embodiment, during the production process of gypsum particles, the system terminal transports the gypsum particle raw materials to the coating equipment. These devices operate according to the determined optimized coating parameters. Through the precise control of these parameters, the coating equipment can perform multi-layer coating adjustment on the gypsum particle raw materials, ensuring that each layer of coating is uniform, stable, and meets the expected performance requirements. This process can improve the quality of gypsum particles and enhance their physical and chemical properties to meet the requirements of different application scenarios.

[0055] In summary, the embodiments of the present application have at least the following technical effects:

[0056] In the embodiments of the present application, gypsum particle raw materials are prepared and their particle sizes and acidic characteristics are collected. Then, a coating solution is prepared and its solution properties and composition information are collected. Based on this information, a twin model for gypsum preparation is established and connected to an optimization model for the coating process. The optimization model for the coating process also embeds a slow-release effect prediction network. Subsequently, this network is used to optimize the slow-release effect to obtain optimized coating parameters including the number of coating layers and the thickness of each coating layer. During the coating process, the gypsum particle raw materials are transported to the coating equipment and multi-layer coating adjustment is performed according to the optimized coating parameters. In the stage of analyzing the compatibility between the coating solution and the raw materials, if the compatibility detection index meets the preset threshold, the optimization model for the coating process is activated; if not, it is prompted to replace the solution. In addition, in order to train the slow-release effect prediction network, the twin model for gypsum preparation is used to obtain slow-release data samples under non-environmental interference and environmental interference, and the network is trained to improve the prediction accuracy. During the optimization process, by predicting the deviation of the slow-release effect of the initial optimized coating parameters and minimizing these deviations, finally, optimized coating parameters that meet the preset slow-release effect are obtained. These technical effects together solve the technical problem that it is difficult to precisely control the slow-release effect of the coating layer during the process of generating gypsum from citric acid gypsum due to characteristics such as many impurities and small crystal grains, and achieve the effect of harmlessly treating citric acid gypsum through intelligent process adjustment, improving the slow-release performance of building gypsum powder, and ensuring the efficiency of gypsum preparation.

[0057] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0058] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0059] This specification and the drawings are merely illustrative of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications therein.

Claims

1. A method for adjusting the preparation process of gypsum, characterized in that, The method includes: Preparing a gypsum particle raw material, and collecting the particle size characteristics and acidic characteristics of the gypsum particle raw material; Preparing a coating solution for coating the gypsum particle raw material, and collecting the solution property information and solution composition information of the coating solution; According to the particle size characteristics, the acidic characteristics, the solution property information and the solution composition information, establishing a twin model for gypsum preparation, including: the system terminal establishing a physical model according to the physical process of gypsum preparation; analyzing the particle size characteristics and the solution property information to obtain the physical parameters of gypsum and the operation parameters of the coating solution; the system terminal analyzing the reaction mechanism between gypsum and the chemical substances in the solution according to the chemical principle of gypsum preparation; establishing a chemical model based on the reaction mechanism, and the chemical model is used to describe the interaction and transformation relationship between various chemical substances; analyzing the acidic characteristics and the solution composition information to obtain the chemical parameters of gypsum and the coating solution; the system terminal respectively setting parameters for the physical model and the chemical model according to the physical parameters and the chemical parameters, and the system terminal integrating the physical model and the chemical model to form a twin model for gypsum preparation; Connecting the twin model for gypsum preparation with an optimization model for the coating process, wherein the optimization model for the coating process is embedded with a slow-release effect prediction network, and the optimization model for the coating process is trained by historical coating parameters, and the historical coating parameters include the number of historical coating layers and the historical coating thickness of each layer; the slow-release effect prediction network is a neural network model trained according to the monitoring data of the slow-release process under the condition of not being disturbed by the environment and being disturbed by the environment, and it predicts the stability and time of citric acid gypsum when releasing specific components by analyzing the slow-release data generated by the twin model; Optimizing the slow-release effect according to the slow-release effect prediction network embedded in the optimization model for the coating process, and obtaining optimized coating parameters that meet the preset slow-release effect, wherein the optimized coating parameters include the number of coating layers and the coating thickness of each layer; Conveying the gypsum particle raw material to a coating device, and controlling the coating device to perform multi-layer coating adjustment on the gypsum particle raw material with the optimized coating parameters.

2. The method according to claim 1, characterized in that After collecting the solution property information and the solution composition information of the coating solution, it further includes: Performing a compatibility analysis on the coating solution and the gypsum particle raw material, and outputting a compatibility detection index, wherein the compatibility analysis includes a chemical reaction rate, a solution adhesion force, an acid tolerance rate, and an impurity precipitation rate; When the compatibility detection index is greater than a preset compatibility threshold, activating the optimization model for the coating process; When the compatibility detection index is less than the preset compatibility threshold, outputting a reminder for replacing the solution.

3. The method according to claim 1, characterized in that, Training the slow-release effect prediction network, including: Obtaining the initial parameters of the slow-release effect prediction network; According to the twin model for gypsum preparation, obtaining a first slow-release data sample, wherein the first slow-release data sample is the monitoring data of the slow-release process under the condition of not being disturbed by the environment; Performing sample prediction on the first slow-release data sample according to the slow-release effect prediction network, and obtaining a first slow-release stability rate sample and a first slow-release duration sample; Train according to the first slow-release stability rate sample and the first slow-release duration sample until a preset accuracy rate is reached, and update the parameters of the slow-release effect prediction network.

4. The method according to claim 3, wherein Obtain the first slow-release stability rate sample, including: Decompose the first slow-release data sample to output a first initial slow-release data sample and a first final slow-release data sample; For the first initial slow-release data sample and the first final slow-release data sample, output a first initial slow-release stability rate sample and a first final slow-release stability rate sample; Perform weight calculation on the first initial slow-release stability rate sample and the first final slow-release stability rate sample to output the first slow-release stability rate sample.

5. The method according to claim 3, wherein Training the slow-release effect prediction network further includes: According to the gypsum, prepare a twin model to obtain a second slow-release data sample, where the second slow-release data sample is the monitoring data of the slow-release process under environmental interference; Perform sample prediction on the second slow-release data sample according to the slow-release effect prediction network to obtain a second slow-release stability rate sample and a second slow-release duration sample; Train according to the second slow-release stability rate sample and the second slow-release duration sample until the preset accuracy rate is reached, and update the parameters of the slow-release effect prediction network.

6. The method according to claim 1, characterized in that, Perform slow-release effect optimization according to the slow-release effect prediction network embedded in the coating process optimization model to obtain optimized coating parameters that meet the preset slow-release effect, including: Analyze the first group of input data and the second group of input data according to the coating process optimization model to obtain initial optimized coating parameters; Predict the initial optimized coating parameters using the slow-release effect prediction network, and output the slow-release effect deviation, where the slow-release effect deviation includes the slow-release stability rate deviation and the slow-release duration deviation ; Obtain optimized coating parameters that meet the preset slow-release effect by minimizing the slow-release effect deviation.

7. The method according to claim 6, wherein The deviation of the sustained-release stability rate The calculation formula is as follows: ； Among them, is the coating layer number, represents the sustained release time of the i-th coating layer, is the average value of the sustained release times of each layer, is the deviation of the sustained release stability rate, and the standard deviation of the sustained release times of all coating layers is calculated to evaluate the dispersion degree of the sustained release time.

8. The method according to claim 6, wherein The deviation of the sustained release duration The calculation formula is as follows: ； Among them, represents the absolute deviation between the actual average sustained-release duration and the target sustained-release time ; represents the average value of the sustained-release times of all coating layers, represents the sustained-release time of the i-th coating layer, is the thickness of the i-th layer, is the sustained-release rate constant of the i-th layer, is the desired sustained-release time, is the number of coating layers.

Images