Collaborative scheduling system for intelligent proportioning of boric acid

Abstract

The invention relates to the technical field of ceramic production, in particular to a boric acid intelligent proportioning collaborative scheduling system. The system comprises a data acquisition module which is used for acquiring data such as green body characteristics, glaze characteristics, kiln environment, boric acid inventory and production plans in ceramic production in real time; the intelligent proportioning decision module is used for generating a boric acid optimal proportioning scheme by utilizing a green body-glaze suitability evaluation unit, an intelligent proportioning optimization unit, an alternative scheme recommendation unit and the like based on the acquired data; the collaborative scheduling module is used for generating and executing a scheduling instruction according to the matching scheme, the inventory information and the production plan; and the execution control module is responsible for accurately controlling weighing, conveying and mixing of boric acid according to instructions. Through cooperation of all the modules, the system can achieve intelligent and accurate proportioning and efficient cooperative scheduling of boric acid in the ceramic production process, the quality and efficiency of ceramic production are effectively improved, and it is guaranteed that production is conducted stably and orderly.

Description

Technical Field

[0001] The present invention relates to the technical field of ceramic production, and particularly to an intelligent boric acid proportioning and collaborative scheduling system. Background Art

[0002] In the field of ceramic production, the quality of the glaze plays a crucial role in the performance, appearance, and overall quality of the final ceramic products. As one of the key components in the glaze formula, the rationality of the addition amount and proportion of boric acid directly affects many aspects such as the melting characteristics, fluidity, bonding strength with the green body, and the color and luster of the product.

[0003] In the traditional ceramic production process, the proportioning of boric acid often relies on the experience of operators and some conventional formula patterns in the past. Operators determine the addition amount of boric acid in the glaze based on subjective judgment and limited practical experience. However, ceramic production involves numerous variables. The characteristics of the green body vary due to factors such as raw materials and manufacturing processes, the components of the glaze itself are different, and the kiln environment is constantly changing dynamically. These complex and variable factors make it difficult to accurately match the actual production requirements by simply relying on manual experience to determine the boric acid proportion, which is extremely likely to lead to poor glaze performance, thereby affecting the quality of ceramic products, and problems such as glaze surface defects and poor bonding with the green body may occur.

[0004] Moreover, in terms of production plan arrangement and material management, there is a lack of a systematic collaborative mechanism for the inventory management, distribution, and scheduling of boric acid. On the one hand, it is difficult to accurately estimate the actual demand for boric acid in different production stages and different production lines, which is likely to cause inventory backlogs or shortages; on the other hand, when there is a shortage of boric acid in stock, there is a lack of effective countermeasures and it is impossible to provide appropriate alternative materials and corresponding proportioning schemes in a timely manner, which may lead to production interruptions, increase production costs, and seriously affect the continuity and overall efficiency of ceramic production. Summary of the Invention

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an intelligent boric acid proportioning and collaborative scheduling system, which can real-time obtain various data in the ceramic production process, generate an optimized boric acid proportioning scheme through intelligent algorithms, and perform collaborative scheduling to ensure the accurate weighing, conveying, and mixing of boric acid, and provide a suitable alternative solution when the boric acid inventory is insufficient, improving the quality and efficiency of ceramic production and reducing production costs.

[0006] An intelligent boric acid proportioning and collaborative scheduling system includes: A data acquisition module, which is used to real-time obtain the green body characteristic data, glaze characteristic data, kiln environment parameters, boric acid inventory information, and production plan and process parameters in the ceramic production process; An intelligent proportioning decision-making module, communicatively connected to the data acquisition module, is configured to generate an optimized boric acid proportioning plan based on the received data; A collaborative scheduling module, communicatively connected to the intelligent proportioning decision-making module and the data acquisition module, is configured to generate and execute a collaborative scheduling instruction for the boric acid proportioning plan based on the boric acid proportioning plan, boric acid inventory information, and production plan; An execution control module, communicatively connected to the collaborative scheduling module, is configured to control the accurate weighing, conveying, and mixing of the boric acid proportioning plan according to the collaborative scheduling instruction.

[0007] Preferably, the intelligent proportioning decision-making module includes a glaze formula model library, a body-glaze compatibility evaluation unit, an intelligent proportioning optimization unit, and an alternative plan recommendation unit; The glaze formula model library stores the target glaze formulas of different types of ceramic products, including the target addition amount range of boric acid and its influence model on glaze performance; The body-glaze compatibility evaluation unit evaluates the compatibility between the current body and the target glaze based on the body characteristic data and glaze characteristic data; The intelligent proportioning optimization unit determines the optimized boric acid addition amount and proportioning plan under the current production conditions by using a neural network model based on the preset glaze formula model library, body characteristic data, glaze characteristic data, the evaluation result of the body-glaze compatibility evaluation unit, and furnace environment parameter data; The alternative plan recommendation unit is configured to recommend alternative boron compounds or fluxes and their corresponding proportioning plans based on a preset alternative material database and a performance equivalence evaluation model when the boric acid inventory is insufficient.

[0008] Preferably, the evaluation of the compatibility between the current body and the target glaze specifically includes: Based on the chemical composition data of the body and the glaze, using a preset thermal expansion coefficient calculation model, calculate the average thermal expansion coefficients of the current body and the target glaze within a predetermined temperature range, respectively, and calculate the percentage difference between the two. When the percentage difference exceeds the preset thermal expansion coefficient compatibility threshold, it is determined that the risk of thermal expansion mismatch is relatively high; Obtain the firing shrinkage rate data of the body and the firing shrinkage rate data of the glaze, calculate the absolute difference value between the two. When the absolute difference value exceeds the preset firing shrinkage rate compatibility threshold, it is determined that the risk of firing shrinkage mismatch is relatively high; Based on the chemical composition data of the body and the glaze, use a preset melting temperature prediction model to predict the temperature at which the body starts to soften and the temperature at which the glaze starts to melt, and calculate the temperature difference between the two. When the temperature difference exceeds the preset melting temperature compatibility threshold, it is determined that the risk of melting temperature mismatch is relatively high; Comprehensive Adaptability Evaluation: Calculate the comprehensive adaptability based on the thermal expansion coefficient matching degree, firing shrinkage rate difference, and melting temperature matching degree; The formula for calculating the comprehensive adaptability is: ; In the formula, , and are respectively the thermal expansion coefficient matching degree, firing shrinkage rate difference, and melting temperature matching degree between the current green body and the target glaze, , and are the corresponding weight coefficients.

[0009] Preferably, the method for determining the optimized boric acid addition amount and ratio scheme under the current production conditions by using the neural network model specifically includes: Data preprocessing: Clean, standardize or normalize the input data, and divide the processed data into a training set, a validation set, and a test set for training, parameter adjustment, and performance evaluation of the neural network model; Neural network model training: Use the historical data in the training set to train the neural network model. Calculate the output of the network through forward propagation, compare it with the actual boric acid addition amount and ratio, and calculate the loss function; Use the backpropagation algorithm to adjust the weights and bias terms in the network according to the gradient of the loss function, so that the predicted output of the network gradually approaches the actual value; Use the validation set to monitor the training process of the model to prevent overfitting and adjust the hyperparameters; Model evaluation and selection: Use the test set to evaluate the performance of the trained neural network model, adopt appropriate evaluation indicators to measure the prediction accuracy and generalization ability of the model, and select the neural network model with the best performance according to the evaluation results for predicting the boric acid addition amount and ratio in actual production; Online prediction and output: During the actual production process, the data acquisition module real-time obtains the current green body characteristic data, glaze characteristic data, and kiln environment parameters; Use these real-time data, the initial boric acid range obtained from the glaze formula model library, and the adaptability score calculated by the green body-glaze adaptability evaluation unit as the input of the trained neural network model. The neural network model calculates through forward propagation and outputs the total boric acid addition amount predicted to obtain the best product quality and adaptability under the current production conditions and the specific ratio scheme.

[0010] Preferably, the neural network model includes: Input layer: It includes multiple neurons, corresponding to the following input features respectively: The initial addition amount range of boric acid in the target glaze formula extracted from the glaze formula model library; The fitness score obtained from the green body - glaze compatibility evaluation unit and the evaluation results of each sub - step; The current or predicted key furnace parameters obtained from the furnace environment parameter monitoring unit; The current green body characteristic data and glaze characteristic data obtained from the data acquisition module; Hidden layer: It contains at least one hidden layer. Neurons in each hidden layer are fully connected to all neurons in the previous layer. Each neuron receives weighted inputs from neurons in the previous layer and processes them through a non - linear activation function to generate the output of the neuron; Output layer: It is used to predict the addition amount and ratio of boric acid and output the total addition amount of boric acid and the specific ratio scheme that can obtain the best product quality and compatibility under the current production conditions.

[0011] Preferably, the collaborative scheduling module includes a demand forecasting unit, an allocation optimization unit, a scheduling unit, an alternative solution scheduling unit, and an abnormal situation warning unit: The demand forecasting unit predicts the demand for different specifications of boric acid in different production lines or batches at different time periods based on the current production plan and the ratio scheme output by the intelligent ratio decision module; The allocation optimization unit formulates an allocation plan for boric acid according to the prediction results of the boric acid demand forecasting unit, boric acid inventory data, and production priorities, and determines which production link, in what way, and how much boric acid to transport; The scheduling unit is used to control the automatic boric acid conveying equipment to transport the specified specification and amount of boric acid to the corresponding glaze preparation station, and control the automatic mixing equipment to mix with other glaze components according to the ratio provided by the intelligent ratio decision module; The alternative solution scheduling unit is used to generate procurement, storage, and allocation scheduling instructions for the corresponding alternative materials when the intelligent ratio decision module recommends an alternative solution for boric acid; The abnormal situation warning unit is used to send a warning message when the boric acid inventory is lower than the preset threshold or the conveying equipment fails.

[0012] Preferably, formulating an allocation plan for boric acid according to the prediction results of the boric acid demand forecasting unit, boric acid inventory data, and production priorities specifically includes: Objective function construction: The allocation optimization unit constructs an objective function with the goal of maximizing production efficiency, meeting production demands, and minimizing costs; Constraint condition setting: Set the constraint conditions that need to be satisfied when solving the objective function; Allocation plan solution: Use a linear programming algorithm to solve the optimization problem composed of the above - mentioned objective function and constraint conditions to obtain the optimal solution, thereby determining the allocation plan of which production link, in what way, and how much boric acid to transport; The objective function is: ; Where, To obtain the minimum value, is the number of boric acid stock points, The production process is the production line or the number of production batches. For the The inventory point to the The cost of delivering a unit of boric acid in each production link, For the The inventory point to the The amount of boric acid delivered in each production link, For the The storage cost of boric acid per unit at each inventory point, For the The remaining inventory at a stock point after allocation is completed.

[0013] Preferably, the constraints include demand constraints, inventory constraints and production priority constraints; Demand constraint: The boric acid demand at each production stage must be met, expressed as:

[0014] in For the Boric acid demand in each production link; Inventory constraint: The amount of boric acid delivered from each inventory point cannot exceed its inventory, and the remaining inventory cannot be negative, expressed as: ; in For the Initial boric acid inventory at each storage location; Production priority constraint: For production links with different production priorities, set a priority coefficient to give priority to the needs of high-priority production links while meeting basic needs.

[0015] Preferably, the objective function further includes a penalty term that makes it more costly to fail to meet the requirements of a high-priority production link; The objective function formula after considering the penalty term is: ; in For the The priority coefficient of each production link, For the Unmet needs in the production process.

[0016] Compared with the prior art, the advantages of the present invention are as follows: Improve the accuracy of formulation: Through the intelligent formulation decision module, combined with various production data and advanced algorithm models, an optimized boric acid formulation scheme can be generated to improve the accuracy of boric acid formulation, thereby enhancing the quality of ceramic products.

[0017] Achieve collaborative scheduling: The collaborative scheduling module can reasonably allocate and schedule boric acid resources according to the boric acid formulation scheme, inventory information, and production plan to ensure the coordinated progress of the production process and improve production efficiency.

[0018] Provide alternative solutions: When the boric acid inventory is insufficient, the alternative solution recommendation unit can timely recommend suitable alternative materials and formulation schemes to avoid production interruptions and ensure the continuity of production. Detailed implementation manners

[0019] To better explain the present invention for easy understanding, the following provides an implementation manner of a boric acid intelligent formulation collaborative scheduling system in ceramic production, including: System construction and initialization: First, construct the entire boric acid intelligent formulation collaborative scheduling system, and perform hardware connection and communication configuration on the data acquisition module, intelligent formulation decision module, collaborative scheduling module, execution control module, and information management and monitoring module according to the design requirements to ensure stable and efficient data interaction between modules.

[0020] In the data acquisition module, set various sensors and data interfaces to accurately and real-time obtain the green body characteristic data, glaze characteristic data, kiln environment parameters, boric acid inventory information, production plan and process parameters, and quality inspection data during the ceramic production process. At the same time, initialize the glaze formula model library in the intelligent formulation decision module, and input the target glaze formulas of different types of ceramic products, including in detail the target addition amount range of boric acid and the influence model data of its performance on the glaze; also complete the corresponding basic data input for the alternative material database, covering the material information of various alternative boron compounds or fluxes, such as material names, chemical compositions, physical properties, action mechanisms in ceramic production, historical usage records, and corresponding product performance feedback, and associate the possible addition amount ranges of each material in the production of different ceramic products.

[0021] Data acquisition and transmission: During the actual operation of ceramic production, the data acquisition module continuously collects various data through devices such as sensors it is connected to. For example, the chemical composition data of the green body is obtained through a composition analyzer installed on the green body production line, and the temperature and humidity sensors in the kiln are used to monitor the kiln environment parameters in real time. These collected raw data are transmitted to the intelligent proportioning decision-making module and the collaborative scheduling module in a timely manner according to the predetermined communication protocol and data format, providing basic support for subsequent analysis and decision-making.

[0022] Operation of the intelligent proportioning decision-making module: Evaluation of the adaptability between the green body and the glaze: After receiving the green body characteristic data and glaze characteristic data transmitted by the data acquisition module, the green body-glaze adaptability evaluation unit in the intelligent proportioning decision-making module conducts the adaptability evaluation in the following manner: Based on the chemical composition data of the green body and the glaze, using a preset thermal expansion coefficient calculation model, calculate the average thermal expansion coefficients of the current green body and the target glaze within a predetermined temperature range respectively, and calculate the percentage difference between the two. When the percentage difference exceeds the preset thermal expansion coefficient adaptability threshold (such as set to 5%), it is determined that the risk of thermal expansion mismatch is relatively high.

[0023] Obtain the firing shrinkage rate data of the green body and the firing shrinkage rate data of the glaze, calculate the absolute difference value between the two. If this absolute difference value exceeds the preset firing shrinkage rate adaptability threshold (such as set to 0.5%), it is determined that the risk of firing shrinkage mismatch is relatively high.

[0024] Based on the chemical composition data of the green body and the glaze, using a preset melting temperature prediction model, predict the temperature at which the green body starts to soften and the temperature at which the glaze starts to melt, and calculate the temperature difference between the two. When the temperature difference exceeds the preset melting temperature adaptability threshold (such as set to 50°C), it is determined that the risk of melting temperature mismatch is relatively high.

[0025] Finally, based on the above thermal expansion coefficient matching degree, firing shrinkage rate difference and melting temperature matching degree, calculate the comprehensive adaptability according to the formula (where , and are set to 0.4, 0.3, 0.3 respectively) to comprehensively evaluate the adaptability between the green body and the glaze.

[0026] Intelligent proportioning optimization: After the intelligent ratio optimization unit obtains the preset glaze formula model library, green body characteristic data, glaze characteristic data, the evaluation results of the green body-glaze compatibility evaluation unit, and the kiln environment parameter data, it first cleans these input data to remove outliers and incorrect data, and then performs standardization or normalization processing to make the data range meet the input requirements of the neural network model. The processed data is divided into a training set, a validation set, and a test set according to a certain ratio (such as 7:2:1).

[0027] The neural network model is trained using the historical data in the training set. During the training process, the output of the network is calculated through forward propagation and compared with the actual boric acid addition amount and ratio, and the mean square error loss function is calculated. Then, using the backpropagation algorithm, the weights and bias terms in the network are adjusted according to the gradient of the loss function, so that the predicted output of the network gradually approaches the actual value. At the same time, the validation set is used to monitor the training process of the model. When the loss on the validation set no longer decreases or shows an upward trend, the training is stopped to prevent overfitting, and hyperparameters (such as learning rate, the number of neurons in the hidden layer, etc.) are adjusted.

[0028] The performance of the trained neural network model is evaluated using the test set, and evaluation indicators such as the correlation coefficient and mean absolute error are used to measure the prediction accuracy and generalization ability of the model. According to the evaluation results, the neural network model with the best performance is selected for predicting the boric acid addition amount and ratio in actual production. During actual production, the current green body characteristic data, glaze characteristic data, and kiln environment parameters transmitted by the real-time data acquisition module, as well as the initial boric acid range obtained from the glaze formula model library and the compatibility score calculated by the green body-glaze compatibility evaluation unit, are used as the input of the trained neural network model. Through forward propagation calculation, the total boric acid addition amount predicted to obtain the best product quality and compatibility under the current production conditions and the specific ratio scheme are output.

[0029] Alternative solution recommendation: When the alternative solution recommendation unit in the intelligent ratio decision module detects a shortage of boric acid inventory, it conducts the recommendation work based on the preset alternative material database and the performance equivalence evaluation model.

[0030] First, according to the type and production process requirements of the current ceramic product, possible applicable alternative materials with certain chemical composition similarity to boric acid, suitable for this type of ceramic product, and with good product quality feedback in the historical usage records are screened out from the alternative material database.

[0031] Then, for these preliminarily screened alternative materials, using the performance equivalence evaluation model, based on thermal performance equivalence (by comparing the differences in indicators such as coefficient of thermal expansion, firing shrinkage rate, melting temperature, etc. with boric acid), chemical performance equivalence (analyzing the chemical reaction characteristics with the body and glaze, and comparing the effects on aspects such as chemical stability, corrosion resistance, and color of the glaze), and physical performance equivalence (considering the effects on physical properties such as fluidity, wettability, and surface tension of the glaze), calculate the equivalence scores of each alternative material and boric acid in each aspect respectively, and calculate the comprehensive equivalence score according to the formula (where is the comprehensive equivalence score, is the thermal performance equivalence score, is the chemical performance equivalence score, is the physical performance equivalence score, , , are the weight coefficients of thermal performance, chemical performance, and physical performance respectively, which are set to 0.3, 0.3, and 0.4 respectively).

[0032] Recommend the top-ranked alternative boron compounds or fluxes and their corresponding proportioning schemes in descending order of the comprehensive equivalence score. At the same time, generate a detailed performance evaluation report for each recommended scheme, including the equivalence analysis of thermal performance, chemical performance, and physical performance, as well as the prediction of the final product quality, for the operators to refer to for decision-making.

[0033] Operation of the collaborative scheduling module: Demand forecasting: The demand forecasting unit in the collaborative scheduling module, based on the current production plan and the proportioning scheme output by the intelligent proportioning decision-making module, uses methods such as time series analysis, combined with the production progress arrangements of different production lines or batches and the product specification requirements, to predict the demand for boric acid of different specifications in different production lines or batches at different time periods. For example, for a certain ceramic tableware production line, according to its production plan for the next week and the corresponding boric acid proportioning scheme, predict the specific number of kilograms of boric acid with specific purity and particle size specifications required every day, and transmit these predicted demand data to the distribution optimization unit.

[0034] Distribution optimization: After receiving the prediction results from the demand forecasting unit, the boric acid inventory data from the data acquisition module, and the pre-set production priorities (which can be determined according to factors such as order urgency and product importance), the distribution optimization unit formulates the boric acid distribution plan in the following way: Construct the objective function (where is the minimum operation, is the number of boric acid inventory points, is the quantity of production links (production lines or batches), is from the th inventory point to the th production link for transporting a unit of boric acid, is from the th inventory point to the th production link for the quantity of boric acid transported, is the storage cost per unit of boric acid at the th inventory point, is the th inventory point's remaining inventory after the allocation is completed).

[0035] At the same time, set the demand constraint (where is the demand for boric acid at the th production link), the inventory constraint (where is the initial boric acid inventory at the th inventory point) and , and the production priority constraint (by introducing the priority coefficient , for high-priority production links, ensure priority on the basis of meeting the basic demand. A penalty term can be added to the objective function, where is the unmet demand at the th production link).

[0036] Use linear programming or integer programming algorithms to solve the optimization problem composed of the above objective function and constraint conditions, and obtain the optimal solution, so as to determine the allocation plan of which production link to transport how much boric acid in what way, and transfer this plan to the scheduling unit.

[0037] Scheduling operation: Based on the allocation plan formulated by the allocation optimization unit, the scheduling unit controls the automatic boric acid conveying equipment to transport the specified specification and quantity of boric acid to the corresponding glaze preparation workstations. During the transportation process, real-time monitoring of parameters such as transportation speed and flow rate is carried out through the automated control system to ensure the accuracy of transportation. After arriving at the workstation, control the automatic mixing equipment to mix with other glaze components according to the ratio provided by the intelligent ratio decision module, and ensure the uniformity of mixing and the accuracy of the ratio through precise metering devices and stirring devices.

[0038] Alternative scheduling: When the intelligent ratio decision module recommends a boric acid substitution plan, the substitution plan scheduling unit generates procurement, storage, and distribution scheduling instructions for the corresponding substitute materials. Specifically, according to the recommended substitute materials and their ratio plans, procurement demand information is sent to the procurement department, specifying requirements such as the quantity and quality standards for procurement. At the same time, the warehouse management department is coordinated to plan the storage locations of the substitute materials and formulate a distribution plan to transport the substitute materials to the corresponding production processes, ensuring that the substitute materials can be smoothly put into use and maintaining the normal progress of production.

[0039] Abnormal situation warning: The abnormal situation warning unit monitors the boric acid inventory situation in real time (obtaining inventory data through interaction with the data acquisition module), the operating status of the conveying equipment (through the fault detection sensors connected to the conveying equipment), and the ratio execution situation (comparing the actual executed ratio with the plan output by the intelligent ratio decision module). When the boric acid inventory is lower than the preset threshold (such as set to the safety inventory level) or the conveying equipment fails (such as the conveyor belt jamming, pipeline blockage, etc.), a warning message is immediately issued. The warning message can be conveyed to the relevant operators through means such as audible and visual alarms, system interface pop-ups, and SMS push, so as to take corresponding measures in a timely manner to ensure production safety and product quality.

[0040] The execution control module executes operations: After receiving the scheduling instructions transmitted by the collaborative scheduling module, the execution control module precisely controls each link of the boric acid ratio plan. For the weighing link of boric acid, through weighing equipment such as high-precision electronic scales connected, precise weighing is carried out according to the quantity required by the instructions, and the error is controlled within a very small range. In the conveying link, the conveying equipment is driven to stably convey the weighed boric acid to the designated position according to the set speed and route, avoiding situations such as spilling and leakage. In the mixing link, the automatic mixing equipment is controlled to fully mix the boric acid with other glaze components according to parameters such as the preset stirring speed and stirring time, ensuring that the mixed glaze meets the ratio requirements and providing qualified glaze raw materials for the subsequent ceramic production processes.

[0041] Through the above specific implementation manners, a boric acid intelligent ratio collaborative scheduling system of the present invention can achieve intelligent and precise ratio of boric acid and efficient collaborative scheduling during the ceramic production process, effectively improving the quality and efficiency of ceramic production and ensuring the stable and orderly progress of production.

[0042] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0043] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent boric acid proportioning and collaborative scheduling system, characterized in that Including: A data acquisition module for real-time acquisition of green body characteristic data, glaze characteristic data, kiln environment parameters, boric acid inventory information, and production plan and process parameters during the ceramic production process; An intelligent proportioning decision module, communicatively connected to the data acquisition module, for generating an optimized boric acid proportioning scheme based on the received data; A collaborative scheduling module, communicatively connected to the intelligent proportioning decision module and the data acquisition module, for generating and executing a collaborative scheduling instruction for the boric acid proportioning scheme based on the boric acid proportioning scheme, boric acid inventory information, and production plan; An execution control module, communicatively connected to the collaborative scheduling module, for controlling the precise weighing, conveying, and mixing of the boric acid proportioning scheme according to the collaborative scheduling instruction; The intelligent proportioning decision module includes a glaze formula model library, a green body - glaze compatibility evaluation unit, an intelligent proportioning optimization unit, and an alternative solution recommendation unit; The glaze formula model library stores the target glaze formulas of different types of ceramic products, including the target addition amount range of boric acid and its influence model on glaze performance; The green body - glaze compatibility evaluation unit evaluates the compatibility between the current green body and the target glaze based on the green body characteristic data and the glaze characteristic data; The intelligent proportioning optimization unit determines the optimized boric acid addition amount and proportioning scheme under the current production conditions using a neural network model based on the preset glaze formula model library, green body characteristic data, glaze characteristic data, the evaluation result of the green body - glaze compatibility evaluation unit, and the kiln environment parameter data; The alternative solution recommendation unit is used to recommend alternative boron compounds or fluxes and their corresponding proportioning schemes based on a preset alternative material database and a performance equivalence evaluation model when the boric acid inventory is insufficient.

2. The intelligent boric acid ratio matching and collaborative scheduling system according to claim 1, characterized in that The evaluation of the compatibility between the current green body and the target glaze specifically includes: Based on the chemical composition data of the green body and the glaze, using a preset thermal expansion coefficient calculation model, calculate the average thermal expansion coefficients of the current green body and the target glaze within a predetermined temperature range respectively, and calculate the percentage difference between the two. When the percentage difference exceeds the preset thermal expansion coefficient compatibility threshold, it is determined that the risk of thermal expansion mismatch is relatively high; Obtain the firing shrinkage rate data of the green body and the firing shrinkage rate data of the glaze, calculate the absolute difference value between the two. When the absolute difference value exceeds the preset firing shrinkage rate compatibility threshold, it is determined that the risk of firing shrinkage mismatch is relatively high; Based on the chemical composition data of the green body and the glaze, use a preset melting temperature prediction model to predict the temperature at which the green body starts to soften and the temperature at which the glaze starts to melt, and calculate the temperature difference between the two. When the temperature difference exceeds the preset melting temperature compatibility threshold, it is determined that the risk of melting temperature mismatch is relatively high; Comprehensive compatibility evaluation: Calculate the comprehensive compatibility based on the thermal expansion coefficient matching degree, firing shrinkage rate difference, and melting temperature matching degree; The formula for calculating the comprehensive compatibility is: ; In the formula, , and are respectively the thermal expansion coefficient matching degree between the current green body and the target glaze, the difference in firing shrinkage rate, and the melting temperature matching degree, , and are the corresponding weight coefficients.

3. The intelligent boric acid proportioning and collaborative scheduling system according to claim 1, characterized in that, The determination of the optimized boric acid addition amount and proportioning scheme under the current production conditions using a neural network model specifically includes: Data preprocessing: Clean, standardize or normalize the input data, and divide the processed data into a training set, a validation set, and a test set for training, parameter adjustment, and performance evaluation of the neural network model; Neural network model training: Use the historical data in the training set to train the neural network model. Calculate the output of the network through forward propagation and compare it with the actual boric acid addition amount and ratio to calculate the loss function. Use the backpropagation algorithm to adjust the weights and bias terms in the network according to the gradient of the loss function, so that the predicted output of the network gradually approaches the actual value. Use the validation set to monitor the training process of the model, prevent overfitting, and adjust the hyperparameters; Model evaluation and selection: Use the test set to evaluate the performance of the trained neural network model, adopt appropriate evaluation indicators to measure the prediction accuracy and generalization ability of the model, and select the neural network model with the best performance according to the evaluation results for predicting the boric acid addition amount and ratio in actual production; Online prediction and output: During the actual production process, the data acquisition module obtains the current green body characteristic data, glaze characteristic data, and kiln environment parameters in real time. Use these real-time data, the initial boric acid range obtained from the glaze formula model library, and the fitness score calculated by the green body-glaze compatibility evaluation unit as the input of the trained neural network model. The neural network model calculates through forward propagation and outputs the total boric acid addition amount predicted to obtain the best product quality and compatibility under the current production conditions and the specific ratio plan.

4. The intelligent boric acid proportioning and collaborative scheduling system according to claim 3, characterized in that, The neural network model includes: Input layer: It includes multiple neurons, corresponding to the following input features respectively: The initial addition amount range of boric acid in the target glaze formula extracted from the glaze formula model library; The fitness score obtained from the green body-glaze compatibility evaluation unit and the evaluation results of each sub-step; The current or predicted key kiln parameters obtained from the kiln environment parameter monitoring unit; The current green body characteristic data and glaze characteristic data obtained from the data acquisition module; Hidden layer: It contains at least one hidden layer. The neurons in each hidden layer are fully connected to all neurons in the previous layer. Each neuron receives the weighted input from the neurons in the previous layer and is processed by a non-linear activation function to generate the output of the neuron; Output layer: It is used to predict the addition amount and ratio of boric acid and output the total boric acid addition amount predicted to obtain the best product quality and compatibility under the current production conditions and the specific ratio plan.

5. The intelligent boric acid proportioning and collaborative scheduling system according to claim 1, wherein The collaborative scheduling module includes a demand prediction unit, an allocation optimization unit, a scheduling unit, an alternative scheduling unit, and an exception warning unit: The demand prediction unit predicts the demand for different specifications of boric acid in different production lines or batches at different time periods based on the current production plan and the ratio plan output by the intelligent ratio decision module; The allocation optimization unit formulates the allocation plan of boric acid according to the prediction results of the boric acid demand prediction unit, the boric acid inventory data, and the production priority; The scheduling unit is used to control the automatic conveying equipment of boric acid to convey boric acid of specified specifications and quantities to the corresponding glaze preparation workstations, and control the automatic mixing equipment to mix with other glaze components according to the ratio provided by the intelligent ratio decision module; The alternative solution scheduling unit is used to generate scheduling instructions for the procurement, storage and distribution of corresponding alternative materials when the intelligent ratio decision module recommends a boric acid alternative solution; The abnormal situation warning unit is used to send warning information when the boric acid inventory is lower than the preset threshold or the conveying equipment fails.

6. The intelligent boric acid proportioning and collaborative scheduling system according to claim 1, wherein Based on the prediction results of the boric acid demand prediction unit, the boric acid inventory data and the production priority, formulate the distribution plan of boric acid, specifically including: Objective function construction: The distribution optimization unit constructs an objective function with the goal of maximizing production efficiency, meeting production requirements and minimizing costs; Constraint condition setting: Set the constraint conditions to be satisfied when solving the objective function; Distribution plan solution: Use the linear programming algorithm to solve the optimization problem composed of the above objective function and constraint conditions to obtain the optimal solution, so as to determine the distribution plan of boric acid; The objective function is: ; Wherein, is the minimum value operation, is the number of boric acid inventory points, is the number of production links, i.e., the number of production lines or production batches, is from the th inventory point to the th production link, the cost of transporting a unit of boric acid, is from the th inventory point to the th production link, the amount of boric acid transported, is the storage cost per unit of boric acid at the th inventory point, is the remaining inventory at the th inventory point after the allocation is completed.

7. An intelligent boric acid proportioning and collaborative scheduling system according to claim 6, characterized in that The constraint conditions include demand constraints, inventory constraints and production priority constraints; Demand constraint: The boric acid demand of each production link must be met, expressed as:

8. Among them is the demand for boric acid in the th production link; Inventory constraint: The amount of boric acid conveyed from each inventory point cannot exceed its inventory, and the remaining inventory cannot be negative, expressed as: ; Among them is the initial boric acid inventory of the th inventory point; Production priority constraint: For production links with different production priorities, set priority coefficients, and on the basis of meeting the basic requirements, give priority to ensuring the needs of high-priority production links.

9. The intelligent boric acid proportioning and collaborative scheduling system according to claim 7, characterized in that, The objective function also includes a penalty term, which makes the cost of unmet high-priority production link requirements higher; The objective function formula considering the penalty term is: ; Among them is the priority coefficient of the th production link, is the unmet demand of the th production link.

Images