Industrial solid waste water quenched slag fiberization production process intelligent management system and method

Abstract

This invention relates to the field of data processing technology and discloses an intelligent management system and method for the production process of industrial solid waste water-quenched slag fiberization. The method includes constructing a mathematical model of the crystal morphology of industrial solid waste water-quenched slag; constructing a multi-objective optimization model of crystal morphology based on the mathematical model to obtain the optimal set of production process parameters and expected optimization objectives; selecting key process parameters from the process parameters, classifying them into different importance levels, setting corresponding control threshold ranges and intensities, and establishing a hierarchical control matrix; obtaining measured crystal morphology parameters, and dynamically optimizing and controlling the water-quenched slag production process parameters based on the measured parameters and the hierarchical control matrix. This invention can achieve precise control of the crystal morphology of water-quenched slag, reduce production costs while ensuring product quality, and promote the high-value utilization of industrial solid waste resources.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to an intelligent management system and method for the production process of industrial solid wastewater quenching slag fiberization. Background Technology

[0002] Chinese patent CN118011981B, authorized by the Ministry of Industry and Information Technology, proposes a method and system for optimizing the production quality of coal mine support. It primarily controls and optimizes the production process of anchor bolt steel in real time based on grain density thresholds, grain size uniformity coefficient thresholds, and grain distribution uniformity coefficient thresholds. This method optimizes the production quality of anchor bolt steel by dynamically adjusting the production control state, improving the reliability and optimization rate of the production process. However, while this method can optimize production quality, it mainly focuses on the quality control of materials during production, optimizing specific problems at different stages of the process. It lacks in-depth analysis of the correlation between various process parameters and fails to effectively integrate crystal morphology models with real-time data feedback during production. Therefore, this technology cannot comprehensively solve multi-objective optimization problems in complex production processes, especially when facing the interaction of multiple process parameters, making it difficult to achieve optimal production efficiency.

[0003] Chinese patent application CN103433270A discloses a comprehensive recycling method for water-quenched slag, aiming to reduce environmental pollution and improve resource recovery rates through efficient recycling and utilization of the slag. By combining an electro-membrane separator and a crystallization tank, this method successfully transforms waste into usable products, meeting the requirements of clean production. However, while this invention offers significant environmental advantages in waste recycling, its focus is on the physicochemical treatment of solid waste, primarily using mechanical and chemical methods for waste classification. It fails to delve into how to intelligently manage and dynamically optimize the multiple process parameters involved in the production process. Therefore, although this method improves recycling efficiency, how to more precisely adjust process parameters during processing to enhance the intelligence and precision of the production process remains a weakness of this technology.

[0004] In summary, existing technologies mainly focus on adjusting a single optimization objective, lacking comprehensive optimization of the complex relationships between multiple process parameters, making it difficult to achieve a globally optimal production plan; and in terms of coordination and control among multiple key process parameters, there is a lack of a systematic solution for dynamic optimization. Summary of the Invention

[0005] To overcome the above-mentioned defects of the prior art, the present invention provides an intelligent management system and method for the production process of industrial solid wastewater quenching slag fiberization.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] Intelligent management methods for the industrial solid wastewater quenching slag fiberization production process include:

[0008] A mathematical model of crystal morphology of industrial solid waste water quenched slag is constructed. Based on the mathematical model of crystal morphology of industrial solid waste water quenched slag, a multi-objective optimization model of crystal morphology is constructed to obtain the optimal set of production process parameters and the expected optimization objectives.

[0009] Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, key process parameters are screened from the process parameters; the screened key process parameters are divided into different importance levels; for key process parameters of different importance levels, corresponding control threshold ranges and control intensities are set according to the optimal production process parameter set, and a hierarchical control matrix is ​​established.

[0010] Measured crystal morphology parameters of the water-quenched slag production process are obtained, and the production process parameters of the water-quenched slag are dynamically optimized based on the measured crystal morphology parameters and the hierarchical control matrix.

[0011] Furthermore, the construction of the mathematical model for the crystal morphology of industrial solid waste quenched slag includes:

[0012] Collect historical production data of industrial solid waste water quenched slag and extract the first record set, which includes the time series of grain size, distribution uniformity, temperature, cooling rate and additive ratio.

[0013] Based on the first record set, a nonlinear correlation model between grain size and distribution uniformity and process parameters is established to obtain a mathematical model of the crystal morphology of industrial solid waste quenched slag; the process parameters include temperature, cooling rate and additive ratio.

[0014] Furthermore, the establishment of a nonlinear correlation model between grain size and distribution uniformity and process parameters, resulting in a mathematical model of the crystal morphology of industrial solid wastewater quenched slag, includes:

[0015] Based on the first record set, a nonlinear correlation model between grain size and process parameters is established and labeled as the initial grain size model; the initial grain size model includes n1 grain size influencing parameters. ,in, For the constants of the initial model of grain size, for Time of the first The influence of a process parameter on the grain size at time t, 0≤i≤n1-1, 1≤ ≤n1-1;

[0016] Based on the first record set, a nonlinear correlation model between distribution uniformity and process parameters is established, labeled as the initial distribution uniformity model; the initial distribution uniformity model includes n² distribution uniformity influencing parameters. ,in, For the constant term of the initial model of uniform distribution, for Time of the first The influence of a process parameter on the uniformity of distribution at time t, 0≤j≤n²-1, 1≤ ≤n2-1;

[0017] The parameters of the initial model for grain size and the initial model for grain distribution uniformity are solved to obtain... and The optimal value;

[0018] Will Substituting the optimal value into the initial grain size model, we obtain the final grain size model.

[0019] Will Substituting the optimal value into the initial model of uniform distribution yields the final model of uniform distribution.

[0020] The final model of grain size and the final model of grain distribution uniformity constitute the mathematical model of crystal morphology of industrial solid waste quenched slag.

[0021] Furthermore, obtaining the optimal set of production process parameters and the expected optimization objective includes:

[0022] Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, a multi-objective optimization model of crystal morphology is established with external parameters as decision variables and minimizing grain size and maximizing distribution uniformity as optimization objectives.

[0023] Solve the multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives. The expected optimization objectives include the target value of grain size and the target value of distribution uniformity. The optimal set of production process parameters includes the historical best values ​​of the production process parameters.

[0024] Furthermore, the process of selecting key process parameters from the process parameters includes:

[0025] Based on the final model of grain size and the final model of distribution uniformity, the partial derivatives of the process parameters with respect to grain size and distribution uniformity are calculated respectively, and the influence coefficient matrix of each process parameter is obtained.

[0026] The influence coefficient matrix is ​​normalized to obtain the influence weights of process parameters on grain size and distribution uniformity.

[0027] The process parameters are sorted in descending order according to their influence weight, and the process parameters whose cumulative weight reaches the preset cumulative weight threshold θ1 are selected as the key process parameters.

[0028] Furthermore, the process of classifying the selected key process parameters into different importance levels includes:

[0029] The key process parameters are sorted in descending order according to their influence weight, and the key process parameters with the highest influence weight W1 are defined as first-level key parameters.

[0030] Key process parameters with influence weights between W1 and W2 are defined as secondary key parameters;

[0031] The critical process parameters with influence weights in the range of W2 to W3 are defined as Level 3 critical parameters, where W3 > W2 > W1, and W1, W2, and W3 are percentages.

[0032] Furthermore, the establishment of the hierarchical control matrix includes:

[0033] The historical optimal values ​​of each key process parameter are obtained from the set of optimal production process parameters, and these historical optimal values ​​are used as the standard values ​​of the corresponding key process parameters. The control threshold range for the first-level key parameters is set to the standard value of the first-level key parameter ± M1; the control threshold range for the second-level key parameters is the standard value of the second-level key parameter ± M2; and the control threshold range for the third-level key parameters is the standard value of the third-level key parameter ± M3; where M3 > M2 > M1, and M1, M2, and M3 are percentages.

[0034] Set the control intensity of the first-level key parameters to level one, the control intensity of the second-level key parameters to level two, and the control intensity of the third-level key parameters to level three.

[0035] A hierarchical control matrix is ​​generated by using the importance level of key process parameters as rows and the control threshold range and control intensity as columns.

[0036] Furthermore, the measured crystal morphology parameters include grain size parameters and crystal distribution uniformity parameters;

[0037] The dynamically optimized control of water-quenched slag production process parameters includes:

[0038] The grain size parameter and the crystal distribution uniformity parameter are input into the multi-objective optimization model of crystal morphology to obtain the optimal production process parameter values ​​under the current production state;

[0039] By comparing the deviations between the measured crystal morphology parameters and the expected optimization target, the hierarchical control matrix is ​​dynamically adjusted to obtain the adjusted hierarchical control matrix;

[0040] By combining the adjusted hierarchical control matrix, the optimal production process parameter values ​​under the current production status are parsed into operable process parameter adjustment commands.

[0041] Furthermore, the adjusted hierarchical control matrix includes:

[0042] Calculate the deviation ΔG between the grain size parameter and the target grain size value, and calculate the deviation ΔU between the crystal distribution uniformity parameter and the target distribution uniformity value;

[0043] If |ΔG|≤ΔG θ And |ΔU|≤ΔU θ If so, the existing hierarchical control matrix settings remain unchanged; ΔG θ ΔU is the preset grain size deviation threshold. θ The preset distribution uniformity deviation threshold;

[0044] If |ΔG|>ΔG θ Or |ΔU|>ΔU θ Then, the hierarchical control matrix is ​​dynamically adjusted to obtain the adjusted hierarchical control matrix.

[0045] An intelligent management system for the industrial solid wastewater quenched slag fiberization production process, used to implement the aforementioned intelligent management method for the industrial solid wastewater quenched slag fiberization production process, the system comprising:

[0046] Model building module: used to build a mathematical model of the crystal morphology of industrial solid waste water quenched slag, and based on the mathematical model of the crystal morphology of industrial solid waste water quenched slag, to build a multi-objective optimization model of crystal morphology, and to obtain the optimal set of production process parameters and expected optimization objectives;

[0047] The hierarchical control module is based on a mathematical model of the crystal morphology of industrial solid waste quenched slag. Key process parameters are selected from the process parameters. The selected key process parameters are divided into different importance levels. For key process parameters of different importance levels, corresponding control threshold ranges and control intensities are set according to the optimal production process parameter set to establish a hierarchical control matrix.

[0048] Dynamic optimization module: Obtains measured crystal morphology parameters of the water-quenched slag production process, and dynamically optimizes and controls the production process parameters of water-quenched slag based on the measured crystal morphology parameters and the hierarchical control matrix.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0050] This invention constructs a mathematical model of the crystal morphology of industrial solid waste quenching slag, thereby achieving a quantitative description of the crystal growth process, revealing the key process parameters affecting crystal morphology and their mechanisms of action, and providing a theoretical basis for process optimization.

[0051] A multi-objective optimization model for crystal morphology, based on mathematical models, can determine the optimal combination of process parameters while ensuring the minimum grain size and the most uniform distribution. Compared with traditional experience-based production, model-driven production improves the scientific nature and controllability of the production process.

[0052] By selecting key process parameters from the available parameters and classifying them into importance levels, and then setting targeted control threshold ranges and intensities, a hierarchical control matrix is ​​established. This hierarchical control strategy enables refined management of key process parameters, allowing resources to be concentrated on key adjustments, thereby reducing management costs while ensuring product quality.

[0053] By acquiring crystal morphology parameters in real time and inputting them into an optimization model, the production process parameters of water-quenched slag are dynamically optimized and controlled. This closed-loop control method can promptly detect and correct deviations in the production process, ensuring the stability of crystal morphology and improving the consistency of product quality.

[0054] The intelligent management system of this invention automates and intelligentizes the production process, reduces human intervention, and improves production efficiency. Through precise control of process parameters, it reduces energy consumption and raw material waste while ensuring the performance of water-quenched slag, resulting in significant economic and environmental benefits.

[0055] This invention provides new ideas and methods for the resource utilization of industrial solid waste. By controlling the microstructure of water-quenched slag, its application fields are broadened, realizing the high-value utilization of industrial solid waste, promoting the coordinated development of industrial production and environmental protection, and has broad application prospects.

[0056] In summary, the intelligent management system and method for the production process of industrial solid waste water-quenched slag fiberization of the present invention can achieve precise control of the crystal morphology of water-quenched slag, improve the automation and intelligence level of the production process, reduce production costs while ensuring product quality, provide strong technical support for the high-value utilization of industrial solid waste resources, and promote the green and sustainable development of industrial production. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating the principle of the intelligent management method for the industrial solid wastewater quenching slag fiberization production process in this invention.

[0059] Figure 2This is a flowchart of the method for selecting key process parameters in the intelligent management method for the production process of industrial solid wastewater quenching slag fiberization of the present invention.

[0060] Figure 3 This is a flowchart illustrating the method for classifying key process parameters into different importance levels in the intelligent management method for the industrial solid wastewater quenching slag fiberization production process of the present invention.

[0061] Figure 4 This is a flowchart of the method for obtaining measured crystal morphology parameters of water-quenched slag in the intelligent management method for the production process of industrial solid waste water-quenched slag fiberization of the present invention.

[0062] Figure 5 This is a flowchart of the method for dynamically optimizing and controlling the process parameters of water-quenched slag production in the intelligent management method for the production process of industrial solid waste water-quenched slag fiberization of the present invention.

[0063] Figure 6 This is a flowchart of the method for obtaining the adjusted hierarchical control matrix in the intelligent management method for the industrial solid wastewater quenching slag fiberization production process of the present invention.

[0064] Figure 7 This is a flowchart of the method for resolving the optimal production process parameter values ​​under the current production state into operable process parameter adjustment instructions in the intelligent management method for the industrial solid wastewater quenching slag fiberization production process of the present invention.

[0065] Figure 8 This is a functional module diagram of the intelligent management system for the industrial solid wastewater quenching slag fiberization production process in this invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] Example 1

[0068] Please see Figure 1 As shown in the figure, this embodiment provides an intelligent management method for the industrial solid waste quenching slag fiberization production process, including:

[0069] Step S1000: Construct a mathematical model of the crystal morphology of industrial solid waste water quenched slag. Based on the mathematical model of the crystal morphology of industrial solid waste water quenched slag, construct a multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives.

[0070] Further, step S1000 includes:

[0071] Step S1100: Construct a mathematical model of the crystal morphology of industrial solid waste quenching slag;

[0072] Further, step S1100 includes:

[0073] Step S1110: Collect historical production data of industrial solid waste water quenching slag and extract the first record set. The first record set includes at least the grain size time series, distribution uniformity time series, temperature time series, cooling rate time series and additive ratio time series.

[0074] Specifically, industrial solid waste water-quenched slag is a solid particulate material formed from high-temperature industrial solid waste (such as blast furnace slag or steel slag) through a rapid cooling process (usually water cooling). Its crystal structure characteristics (such as grain size and uniformity of distribution) are affected by factors such as cooling rate, temperature change, and the use of additives. Therefore, analyzing historical production data of water-quenched slag helps to reveal the dynamic evolution of crystal morphology.

[0075] Temperature time series refers to the temperature change of solid waste materials over time during the production of water-quenched slag. The temperature here primarily refers to the surface temperature of the water-quenched slag, as it directly reflects the heat conduction and heat exchange rates during the cooling process. For example, during the production of water-quenched slag, the initial temperature of the solid waste water-quenched slag may be as high as 1500℃, rapidly dropping to below 100℃ after water cooling. Temperature sensors can record the temperature changes on the surface of the water-quenched slag at fixed time intervals (e.g., per second), forming temperature time series data.

[0076] Cooling rate refers to the rate of temperature change of water-quenched solid waste slag per unit time, usually calculated by dividing the temperature change between two moments by the time interval. Cooling rate time series is a set of dynamic data formed by arranging the calculated cooling rate results in chronological order. For example, assuming that at a certain measurement point, the temperature of the solid waste drops from 1200℃ to 1000℃ in 1 second, the cooling rate is (1200-1000) / 1 = 200℃ / s. Cooling rate time series data is obtained by continuously recording the temperature change every second.

[0077] Additive ratio time series refers to the change in the dosage ratio of additives (such as stabilizers or binders) over time during the production process. This additive ratio time series can be formed by recording the dosage of additives and the corresponding time intervals.

[0078] Grain size refers to the size of crystal particles in water-quenched slag, usually characterized by the average particle diameter, measured in micrometers (μm). Grain size reflects the microstructural characteristics of water-quenched slag and directly affects its physical properties (such as strength and durability). Distribution uniformity refers to the spatial uniformity of grain size distribution, usually characterized by standard deviation or coefficient of variation. Higher distribution uniformity indicates smaller grain size differences and more stable material properties. For example, grain size data is obtained by acquiring images of water-quenched slag using a microscope and measuring the particle diameter. If a batch has a grain size of 10 μm and a standard deviation of 2 μm, it indicates a relatively uniform particle distribution.

[0079] Temperature and cooling rate are monitored in real-time at key points on the production line using temperature sensors or thermocouples to record temperature data of the solid wastewater quenched slag, and the cooling rate sequence is calculated. Grain size and distribution uniformity are quantitatively measured using an online microscopic imager and particle size analyzer. Additive dosage and timing are recorded using online metering equipment.

[0080] Data with temporal characteristics can reveal the causal relationships in crystal morphology evolution (such as the effect of temperature changes on grain size). Cooling rate and temperature are key driving factors for rapid crystal growth or solidification, and collecting this data can provide a basis for optimizing production process parameters. Distribution uniformity and grain size directly affect the final properties of materials, and data recording helps to build accurate predictive models. By collecting this data and generating temporal characteristics, the dynamic evolution of crystal morphology during the production of water-quenched slag can be comprehensively reflected, providing high-quality data support for the subsequent construction of mathematical models.

[0081] Step S1120: Perform data preprocessing on the time-series data in the first record set;

[0082] Specifically, data preprocessing aims to eliminate noise and outliers in the collected data and standardize data with different dimensions to the same scale, facilitating subsequent analysis and modeling. Data preprocessing includes data cleaning, data alignment, and data normalization.

[0083] Data cleaning refers to deleting or correcting erroneous, incomplete, or inconsistent data. For example, if a temperature sensor malfunctions at a certain point in time and records an outlier (e.g., -100°C), the data needs to be corrected through interpolation or outlier removal. Data alignment refers to synchronizing time-series data from multiple data sources according to the same time benchmark. For example, cooling rate data and additive ratio data may have been collected at different time intervals; data alignment requires interpolation or resampling to ensure consistent records at the same point in time. Data normalization aims to eliminate differences between variables of different dimensions by scaling the data to a uniform range (e.g., 0 to 1). For example, if the temperature range is 100°C to 1500°C, normalization will adjust the data to the range of 0 to 1, making all variables easier to analyze on the same scale.

[0084] Data cleaning eliminates outliers and noise, preventing prediction bias during model training due to data issues. Data alignment ensures the synchronization of multiple variables, enabling time series analysis to accurately reveal the dynamic relationships between them. Data normalization eliminates the order-of-magnitude differences between variables of different dimensions, improving model convergence and computational efficiency. Through data preprocessing, data quality can be significantly improved, providing reliable input data for the subsequent construction of mathematical models.

[0085] Step S1130: Based on the first record set, establish a nonlinear correlation model between grain size and distribution uniformity and process parameters to obtain a mathematical model of the crystal morphology of industrial solid waste quenched slag; the process parameters include temperature, cooling rate and additive ratio.

[0086] Further, step S1130 includes:

[0087] Step S1131: Based on the first record set, establish a nonlinear correlation model between grain size and process parameters, and label it as the initial grain size model; the initial grain size model includes n1 grain size influencing parameters. ,in, For the constants of the initial model of grain size, for Time of the first The influence of a process parameter on the grain size at time t, 0≤i≤n1-1, 1≤ ≤n1-1;

[0088] The initial model for grain size includes:

[0089]

[0090] in:

[0091] :express Grain size at time;

[0092] :express Grain size at time;

[0093] :express Uniformity of time distribution;

[0094] :express Temperature at any moment;

[0095] :express Cooling rate at any given time;

[0096] :express The proportion of additives at any given time;

[0097] : These are constant terms in the initial model for grain size; It is a reference value, providing a starting point or baseline for the initial model of grain size;

[0098] :for The effect of grain size at time t on grain size at time t;

[0099] :for The effect of time-distribution uniformity on grain size at time t;

[0100] :for The effect of temperature at time t on grain size at time t;

[0101] :for The effect of cooling rate at time t on grain size at time t;

[0102] :for The effect of additive ratio at time t on grain size at time t;

[0103] : This is the error term of the initial grain size model, representing the deviation in grain size caused by other unconsidered factors or model incompleteness. These deviations may originate from experimental errors, external interference factors, unknown process parameters, etc.

[0104] Step S1132: Based on the first record set, establish a nonlinear correlation model between distribution uniformity and process parameters, labeled as the initial distribution uniformity model; the initial distribution uniformity model includes n² distribution uniformity influencing parameters. ,in, For the constant term of the initial model of uniform distribution, for Time of the first The influence of a process parameter on the uniformity of distribution at time t, 0≤j≤n²-1, 1≤ ≤n2-1;

[0105] The initial model for uniform distribution includes:

[0106]

[0107] in:

[0108] :express Uniformity of time distribution;

[0109] : This is a constant term in the initial model for uniformity, providing a baseline level for uniformity when all other influencing factors (such as grain size, temperature, etc.) remain constant. It will equal ;

[0110] :for The effect of grain size at time t on the uniformity of grain distribution at time t;

[0111] :for The effect of time-time distribution uniformity on the distribution uniformity at time t;

[0112] :for The effect of temperature at time t on the uniformity of the distribution at time t;

[0113] :for The effect of cooling rate at time t on the uniformity of distribution at time t;

[0114] :for The effect of the additive ratio at time t on the uniformity of distribution at time t;

[0115] : Error term of the initial model of distribution uniformity, representing the deviation of distribution uniformity caused by unconsidered factors or model incompleteness.

[0116] Step S1133: Solve the parameters of the initial model for grain size and the initial model for grain distribution uniformity to obtain... and The optimal value;

[0117] Step S1134, will Substituting the optimal value into the initial grain size model, we obtain the final grain size model.

[0118] Step S1135, will Substituting the optimal value into the initial model of uniform distribution yields the final model of uniform distribution.

[0119] Step S1136: The final model of grain size and the final model of distribution uniformity constitute the mathematical model of crystal morphology of industrial solid waste water quenched slag.

[0120] The mathematical model for the crystal morphology of the industrial solid wastewater quenched slag is as follows:

[0121] in:

[0122] Grain size;

[0123] : Uniformity of distribution;

[0124] :temperature;

[0125] Cooling rate;

[0126] : Additive ratio;

[0127] : A nonlinear function of grain size with respect to temperature, cooling rate, and additive ratio;

[0128] The distribution uniformity is a nonlinear function of temperature, cooling rate, and additive ratio.

[0129] Specifically, grain size is influenced by a combination of process parameters, including temperature, cooling rate, and additive ratio. Due to the complexity of crystal growth, the relationship between grain size and these process parameters is nonlinear. Therefore, a nonlinear correlation model is needed to describe the quantitative relationship between them. This model considers that the grain size at the current moment is not only related to its own state at the previous moment but also affected by the process parameters at the previous moment, reflecting the dynamic characteristics of grain evolution. By fitting historical production data, the coefficients of each term in the model can be determined, resulting in an initial grain size model. The establishment of this model lays the foundation for subsequent multi-objective optimization of crystal morphology.

[0130] Higher uniformity of distribution indicates smaller differences in grain size and better isotropy of the material. Similar to grain size, uniformity of distribution is also nonlinearly affected by temperature, cooling rate, and additive ratio. Data-driven modeling methods can characterize the quantitative relationship between uniformity of distribution and various process parameters, yielding an initial model of uniformity. This model also considers the dependence of the current uniformity of distribution on its previous state and various process parameters, reflecting the dynamic evolution of crystal growth uniformity. The initial model of uniformity of distribution, together with the initial model of grain size, constitutes the core components of the mathematical model of crystal morphology.

[0131] The initial models for grain size and uniformity reflect that the grain size and uniformity at time t are not only related to their own state at time t-1, but also affected by the temperature, cooling rate, and additive ratio at time t-1, demonstrating the dynamic characteristics and multi-parameter coupling effect of crystal morphology evolution. The initial model for grain size includes n1 parameters affecting grain size. The constant term in the initial grain size model represents the grain size without the influence of process parameters. The initial model for grain size distribution uniformity includes n² parameters affecting grain size distribution uniformity. , The constant terms in the initial model for uniformity of crystal distribution represent the uniformity of distribution without the influence of process parameters; preferably, n1=6 and n2=6. By establishing these two initial models, the nonlinear correlation between morphological characteristic parameters and process parameters during crystal growth can be quantitatively described, revealing the key factors affecting crystal quality. The autoregressive terms in the model (such as G(t-1) and U(t-1)) reflect the continuity and historical dependence of crystal growth, i.e., the current state is a continuation and development of previous states. The exogenous variable terms (such as T(t-1), C(t-1), and A(t-1)) characterize the regulatory effect of process parameters on crystal morphology, reflecting the controllability of the production process. By comprehensively considering the autoregressive and exogenous variable terms, the dynamic evolution law of crystal morphology can be fully characterized, providing a theoretical basis and decision-making basis for the optimal control of the crystal growth process.

[0132] Parameter estimation refers to determining the values ​​of coefficients in a model using mathematical optimization methods to minimize the error between the model's predicted and measured values. Common parameter estimation methods include least squares estimation and maximum likelihood estimation. For initial models of grain size, it is necessary to solve... Find the optimal values ​​of n1 influencing parameters; for the initial model with uniform distribution, β needs to be solved. jThe goal is to find the optimal values ​​of n² influencing parameters. Since there are overlapping terms in the two initial models (e.g., the initial model for uniform distribution includes grain size), it is necessary to jointly solve for the parameters of both models to ensure consistency and optimality of the results. This can be achieved by constructing a multi-objective optimization problem that simultaneously minimizes the sum of squared errors of the two models, and using numerical optimization algorithms (such as gradient descent, genetic algorithms, etc.) to obtain the optimal values. and The optimal solution yields a quantitative description of the crystal morphology evolution law. Jointly solving the parameters of the grain size and distribution uniformity models allows for full consideration of the interaction between the two morphology indicators, resulting in globally optimal parameter estimates. This method avoids the problems of local optima and inconsistent results that may occur when solving each model parameter individually, improving the model's fitting accuracy and predictive ability. Through joint solving, the effects of process parameters such as temperature, cooling rate, and additive ratio on grain size and distribution uniformity can be quantitatively evaluated.

[0133] After obtaining the optimal estimates of each influencing parameter, these values ​​are substituted into the initial models for grain size and uniformity to obtain the final models for grain size and uniformity. These two models can quantitatively reflect the nonlinear relationships between grain size and uniformity and temperature, cooling rate, and additive ratio during crystal growth. Using the final models, the evolution of crystal morphology can be predicted and controlled, production process parameters can be optimized, and product quality and production efficiency can be improved.

[0134] The combined final models of grain size and uniformity distribution form a complete mathematical model of the crystal morphology of industrial solid wastewater quenched slag, capable of comprehensively depicting the dynamic evolution of crystal morphology in this slag. Based on this model, the crystal growth process can be optimized and controlled, adjusting process parameters such as temperature, cooling rate, and additive ratio to minimize grain size and achieve the most uniform distribution, resulting in ideal product performance. Simultaneously, this model provides a theoretical basis for setting process parameters, avoiding blind, experience-based adjustments and improving production efficiency and product quality consistency.

[0135] The establishment of a mathematical model for the crystal morphology of industrial solid wastewater quenched slag provides a powerful tool for intelligent optimization of the crystal growth process. Through the analysis of historical production data, key process parameters affecting crystal morphology and their operational mechanisms were revealed, and the dynamic evolution characteristics of grain size and uniformity were quantitatively characterized. Based on the mathematical model, crystal morphology under different process conditions can be predicted, and the optimal combination of process parameters can be determined through multi-objective optimization methods, achieving intelligent control of the crystal growth process. Compared with traditional experience-based production, model-driven production fully leverages the value of data, improves the scientific rigor and controllability of the production process, and effectively enhances the quality and performance of industrial solid wastewater quenched slag materials.

[0136] Step S1200: Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, construct a multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives.

[0137] Further, step S1200 includes:

[0138] Step S1210: Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, with external parameters as decision variables, including at least temperature T, cooling rate C and additive ratio A, and with minimizing grain size and maximizing distribution uniformity as optimization objectives, a multi-objective optimization model of crystal morphology is established.

[0139] The multi-objective optimization model for crystal morphology includes:

[0140]

[0141] The constraints are:

[0142]

[0143] in:

[0144] : Minimum temperature;

[0145] : The maximum temperature;

[0146] The minimum cooling rate;

[0147] : The maximum cooling rate;

[0148] The minimum proportion of additives;

[0149] The maximum value of the additive ratio;

[0150] The first objective of the multi-objective optimization model for crystal morphology;

[0151] The second objective of the multi-objective optimization model for crystal morphology;

[0152] Step S1220: Solve the multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives. The expected optimization objectives include the target value of grain size and the target value of distribution uniformity. The optimal set of production process parameters includes the historical best values ​​of production process parameters.

[0153] Specifically, grain size G directly affects the strength and durability of the material; the smaller the grain size, the better the material's performance. One optimization objective is to minimize the grain size. Distribution uniformity U reflects the stability of the grain size distribution; higher distribution uniformity results in more consistent physical properties of the material. A second optimization objective is to maximize distribution uniformity. Temperature T refers to the surface temperature of the solid wastewater quenched slag, measured in °C, and is a key parameter affecting grain size and distribution uniformity during crystal growth. Cooling rate C refers to the rate of temperature change of the solid wastewater quenched slag per unit time, measured in °C / s, affecting crystal solidification speed and microstructure. Additive ratio A refers to the proportion of additives added during production, measured as a percentage (%), used to adjust crystal morphology. These decision variables are the core of optimization; adjusting them allows for the optimization of grain size and distribution uniformity.

[0154] The constraints are set based on the physical limitations and operating range of the actual process. For example, the temperature cannot be too low to avoid affecting crystal growth, the cooling rate cannot be too high to avoid crystal damage, and the proportion of additives must be controlled within a reasonable range to ensure production costs and material properties.

[0155] The multi-objective optimization problem is solved using NSGA-II (Non-Dominated Sorting Genetic Algorithm II), a classic multi-objective optimization algorithm with efficient search capabilities and good global convergence. NSGA-II can quickly search for the Pareto optimal solution set; ensures solution diversity and avoids getting trapped in local optima; and is suitable for high-dimensional nonlinear optimization problems. The output is a set of optimal production process parameters, including optimal temperature, optimal cooling rate, and optimal additive ratio. The optimal temperature ensures minimum grain size; the optimal cooling rate balances grain size and distribution uniformity; and the optimal additive ratio improves distribution uniformity.

[0156] The expected optimization targets include the target values ​​for grain size and distribution uniformity, i.e., the crystal morphology performance under the optimal combination of process parameters.

[0157] There is a complex nonlinear relationship between grain size and distribution uniformity. Directly adjusting process parameters through experimentation is costly and inefficient. By optimizing the combination of process parameters, grain size can be significantly reduced, and crystal distribution uniformity can be improved, thereby enhancing the strength, toughness, and stability of the material. Optimization models can systematically analyze the influence of process parameters, finding the optimal solution to balance various objectives. This allows for precise adjustment of process parameters, avoiding excessive energy consumption and additive waste, thus reducing production costs. The NSGA-II algorithm provides powerful search capabilities, transforming process optimization from an experience-based approach to a data-driven one, improving the scientific rigor and reliability of decision-making. It can quickly find the global optimum, reducing trial-and-error time and achieving intelligent and efficient production processes. By constructing and solving a multi-objective optimization model for crystal morphology, intelligent optimization of the production process can be achieved, providing an efficient and precise solution for the resource utilization of industrial solid waste quenching slag.

[0158] Step S2000: Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, key process parameters are selected from the process parameters; the selected key process parameters are divided into different importance levels; for key process parameters of different importance levels, according to the optimal production process parameter set, the corresponding control threshold range and control intensity are set, and a hierarchical control matrix is ​​established.

[0159] Further, step S2000 includes:

[0160] Step S2100: Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, calculate the influence weight of process parameters on grain size and distribution uniformity, and screen out key process parameters.

[0161] Furthermore, such as Figure 2 As shown, step S2100 includes:

[0162] Step S2110: Based on the final model of grain size and the final model of distribution uniformity, calculate the partial derivatives of the process parameters with respect to grain size and distribution uniformity respectively, and obtain the influence coefficient matrix of each process parameter;

[0163] Step S2120: Normalize the influence coefficient matrix to obtain the influence weights of process parameters on grain size and distribution uniformity.

[0164] Step S2130: Sort the process parameters in descending order according to their influence weight, and select the process parameters whose cumulative weight reaches the preset cumulative weight threshold θ1 as key process parameters.

[0165] Specifically, the objective of step S2100 is to determine, through quantitative analysis, which process parameters have a significant impact on grain size and distribution uniformity, thereby providing a basis for subsequent hierarchical control strategies. Process parameters may include cooling rate, temperature, additive ratio, etc., which may affect crystal morphology characteristics in actual production, such as grain size and distribution uniformity. By constructing a mathematical model, the impact of these process parameters on grain size and distribution uniformity can be quantitatively analyzed, and the influence weight of each process parameter can be calculated.

[0166] The influence weight of a process parameter represents the degree to which a particular process parameter contributes to crystal morphology (such as grain size and distribution uniformity). A larger influence weight indicates a more significant control effect of the parameter on crystal morphology. Grain size refers to the average size of crystals in a material, while distribution uniformity describes whether the grains are evenly distributed throughout the material. An ideal water-quenched slag crystal should possess an appropriate grain size and a relatively uniform distribution, which helps improve the material's mechanical properties and aging resistance. θ1 (usually chosen as 80%) is a cumulative weight threshold, representing the process parameters with the top 80% weights selected as critical process parameters. This means that only those process parameters with the most significant impact are selected as critical process parameters, ensuring effective control.

[0167] By identifying the process parameters with significant impact, resources can be concentrated for precise control, avoiding interference from irrelevant parameters. This process not only improves production efficiency but also optimizes material properties. For example, by analyzing the effect of cooling rate on grain size, if it is found that the cooling rate has a significant controlling effect on grain size (high weighting), this parameter can be further precisely controlled, thereby improving the quality of water-quenched slag.

[0168] Step S2200: The selected key process parameters are divided into different importance levels;

[0169] Furthermore, such as Figure 3 As shown, step S2200 includes:

[0170] Step S2210: Sort the key process parameters in descending order according to their influence weight, and define the key process parameters with the highest influence weight W1 as first-level key parameters.

[0171] Step S2220: Define the key process parameters with influence weights in the range of W1 to W2 as secondary key parameters;

[0172] Step S2230: Define the key process parameters with influence weights in the range of W2 to W3 as level 3 key parameters, where W3 > W2 > W1, and W1, W2, and W3 are percentages.

[0173] Specifically, in step S2200, the key process parameters selected in step S2100 are classified by importance into different levels (Level 1, Level 2, and Level 3), and specific management and control strategies for each level are determined. This classification allows for the development of more scientific control plans for process parameters of varying importance.

[0174] Preferably, W1=40%, W2=70%, and W3=100%. Primary key parameters (the top 40% of the weighting) have the most direct and significant impact on crystal morphology and usually require priority control. For example, cooling rate typically has a significant impact on grain size and uniformity; therefore, cooling rate might be classified as a primary key parameter. Primary parameters usually require more precise control and real-time monitoring. Secondary key parameters (weighting between 40% and 70%) have a relatively smaller impact on crystal morphology, but still have some influence. For example, the proportion of additives might fall into this category. Although their impact is not as direct as cooling rate, adjusting the additive proportion may optimize crystal morphology under certain conditions. Tertiary key parameters (weighting between 70% and 100%) have a relatively weaker impact on crystal morphology, but still require monitoring and control in most cases. For example, temperature might fall into this category. Temperature's impact on grain size is more indirect, so the requirements can be appropriately relaxed during control.

[0175] The influence weights of process parameters are calculated using the partial derivatives in step S2100. The larger the absolute value of the partial derivative, the more significant the influence of the process parameter on the crystal morphology. The ranked influence weights help us rationally classify these process parameters, ensuring that key factors receive sufficient attention. In actual production, not all process parameters are equally important; grading helps in setting appropriate management strategies for each parameter. Level 1 key parameters should be strictly controlled, while level 3 parameters can have their control requirements appropriately relaxed. A reasonable grading standard is the foundation for effective control.

[0176] By classifying process parameters into different levels of importance, more precise control can be achieved, avoiding resource waste. For example, if it is found that the cooling rate has a much greater impact on grain size than temperature, then more resources can be invested in controlling the cooling rate, while temperature control can be relatively relaxed. This hierarchical management not only improves process efficiency but also optimizes production costs and quality control.

[0177] For example, suppose that during the production process it is found that the cooling rate has a very significant impact on the grain size, and therefore the influence weight of the cooling rate is greater than that of other parameters. Following step S2200, the cooling rate is defined as a primary critical parameter, requiring it to be maintained within a precise range throughout the production process. Meanwhile, the additive ratio has a smaller impact, so it is classified as a secondary or tertiary critical parameter, with more lenient control requirements.

[0178] Step S2300: For key process parameters of different importance levels, set corresponding control threshold ranges and control intensities based on the optimal production process parameter set, and establish a hierarchical control matrix.

[0179] Further, step S2300 includes:

[0180] Step S2310: Obtain the historical optimal values ​​of each key process parameter from the optimal production process parameter set, and use the historical optimal values ​​of each key process parameter as the standard values ​​of the corresponding key process parameters; set the control threshold range of the first-level key parameter to be the standard value of the first-level key parameter ± M1; the control threshold range of the second-level key parameter to be the standard value of the second-level key parameter ± M2; and the control threshold range of the third-level key parameter to be the standard value of the third-level key parameter ± M3; where M3 > M2 > M1, and M1, M2, and M3 are percentages;

[0181] Step S2320: Set the control intensity of the first-level key parameter to level one, set the control intensity of the second-level key parameter to level two, and set the control intensity of the third-level key parameter to level three.

[0182] Step S2330: Generate a hierarchical control matrix with the importance level of key process parameters as rows and the control threshold range and control intensity as columns.

[0183] Specifically, the core objective of step S2300 is to implement differentiated control strategies for key process parameters based on their importance levels, so as to ensure that each key parameter fluctuates within a reasonable range during the production process, thereby ensuring the stability of crystal morphology and the consistency of product quality.

[0184] The optimal production process parameter set includes the historical best values ​​of the production process parameters. These historical best values ​​are used as standard values ​​for each key process parameter. Using historical best values ​​as standard values ​​for each key process parameter provides a clear benchmark, ensuring that subsequent production processes can proceed towards optimal results. These historical best values ​​are obtained through long-term production data and optimization experience accumulation, and are generally highly reliable and representative. By setting standard values, the production process does not become chaotic or unstable in the absence of a target. Using historical best values ​​as standard values ​​can effectively reduce fluctuations in the production process and improve process stability. These optimal values ​​reflect the parameters that can achieve the best quality under given conditions, providing a stable reference in the production process and ensuring that each production run is as close to the optimal state as possible. Historical best values ​​are usually obtained through experiments and multiple adjustments and optimizations, and these values ​​have proven to effectively improve product quality and production efficiency. Using these historical best values ​​as new production standards can avoid repeating large-scale experiments or trial-and-error processes for each production run, saving time and resources.

[0185] In step S2310, based on the importance levels (Level 1, Level 2, Level 3) defined in step S2200, different control threshold ranges are set for the key process parameters at each level. These threshold ranges represent the allowable fluctuation range of the process parameters during production, ensuring that they operate within the control range, thereby avoiding adverse effects on crystal morphology.

[0186] Since primary critical parameters have the most significant impact on crystal morphology, they require strict control. The control threshold range is set to ±M1 of the standard value, where M1 is typically small (e.g., ±1%) to ensure minimal parameter variation and maintain crystal morphology stability. For example, if the standard cooling rate is 200℃ / s and M1 is set to 1%, the control range is 198℃ / s to 202℃ / s. Secondary critical parameters have a less significant impact than primary parameters, and their control threshold range is set to ±M2 of the standard value, where M2 is greater than M1 (e.g., ±3%). This means that this parameter has a relatively large margin of fluctuation within a certain range, but it still needs to be kept within a reasonable range to ensure good crystal morphology. For example, if the standard additive ratio is 5% and M2 is set to 3%, the control range is 4.85% to 5.15%. Tertiary critical parameters have a more indirect or smaller impact on crystal morphology, and their control threshold range is set to ±M3 of the standard value, where M3 is greater than M2 (e.g., ±5%). Fluctuations in these parameters have a smaller impact on product quality, so the control range can be appropriately relaxed. For example, if the standard temperature value is 1000℃ and M3 is set to 5%, then the control range is 950℃ to 1050℃.

[0187] By setting different levels of control thresholds, resources can be optimally allocated. Level 1 critical parameters, which significantly impact crystal morphology, require strict control to ensure product quality stability. Level 2 and 3 critical parameters, however, can be appropriately relaxed under the premise of ensuring quality, thereby improving production efficiency and reducing control costs. Furthermore, tiered control helps reduce energy waste and material consumption caused by excessive control, improving overall production economic efficiency.

[0188] The purpose of step S2320 is to specify the control intensity based on the importance level of the critical process parameters. Control intensity typically includes monitoring frequency, control precision, and emergency response measures to ensure that parameters at each level are properly managed.

[0189] Since primary critical parameters have the most significant impact on crystal morphology, their control intensity is set to "Level 1," meaning they require the highest level of monitoring and control. For example, cooling rate, as a primary critical parameter, needs to be equipped with high-precision sensors to monitor its changes in real time and finely adjusted through an automatic control system to ensure it remains within the set control range. Furthermore, a rapid response mechanism should be established to promptly handle any abnormal situations exceeding the threshold, preventing adverse effects on crystal morphology. Secondary critical parameters are controlled at "Level 2," meaning they require moderate monitoring and control. For example, additive ratio, as a secondary critical parameter, requires regular checks of its dosage and control through automatic metering equipment to ensure it remains within the set threshold range. While not requiring the high frequency of monitoring seen in primary parameters, a certain level of control precision and emergency response capability are still necessary to address potential fluctuations during production. Tertiary critical parameters are controlled at "Level 3," indicating relatively relaxed monitoring and control requirements. For example, temperature, as a tertiary critical parameter, while affecting crystal morphology, has a relatively indirect impact; regular monitoring and basic control measures can be used to ensure it does not fluctuate significantly. The monitoring frequency of such parameters can be relatively low, and the control precision can be appropriately relaxed, thereby reducing production costs and control complexity.

[0190] By setting different levels of control intensity, refined management of key process parameters can be achieved, ensuring that key parameters receive sufficient attention and control, while reducing unnecessary resource input for non-critical parameters while ensuring quality. This hierarchical management strategy not only improves the stability and reliability of the production process but also optimizes the allocation of management resources, reduces production costs, and improves overall production efficiency.

[0191] The purpose of step S2330 is to integrate the control threshold ranges and control intensities determined in the first two sub-steps into a unified hierarchical control matrix for intuitive application and management during production. The specific operation is as follows:

[0192] Matrix structure: The rows of the matrix represent key process parameters of different importance levels (level 1, level 2, level 3), while the columns include the control threshold range and control intensity.

[0193] Control threshold range: For each level of critical process parameter, enter its corresponding control threshold range. For example, the control range for the cooling rate of the first-level critical parameter is ±1%, the control range for the additive ratio of the second-level critical parameter is ±3%, and the control range for the temperature of the third-level critical parameter is ±5%.

[0194] Control intensity: Based on the level setting, the first-level key parameter is set as "Level 1 control", the second-level key parameter is set as "Level 2 control", and the third-level key parameter is set as "Level 3 control".

[0195] An example of a hierarchical control matrix is ​​shown in Table 1:

[0196] Table 1. List of hierarchical control matrices

[0197]

[0198] By establishing a hierarchical control matrix, key process parameters at different levels and their corresponding control strategies can be visually displayed within a unified framework, facilitating reference and application by production managers in actual operations. This matrix management approach helps standardize the production process, ensuring that each process parameter operates according to predetermined control strategies, reducing human error and management chaos. Furthermore, the hierarchical control matrix is ​​flexible, capable of dynamic adjustment and optimization based on feedback from production practice and the need for process optimization, further enhancing the intelligence and efficiency of the production process.

[0199] For example, suppose that in the production process of quenched slag from industrial solid wastewater, the following key process parameters and their importance levels are determined through steps S2200 and S2100:

[0200] Cooling rate (a primary key parameter, with an impact factor of 40%)

[0201] Additive ratio (secondary key parameter, with an impact weight of 20%)

[0202] Temperature (a level 3 key parameter, with a weighting of 20%)

[0203] Based on steps S2310 and S2320, set the control threshold range and control intensity for each parameter:

[0204] Cooling rate:

[0205] Control threshold range: ±1%;

[0206] Control level: Level 1 control;

[0207] Additive ratio:

[0208] Control threshold range: ±3%;

[0209] Control level: Level 2 control;

[0210] temperature:

[0211] Control threshold range: ±5%;

[0212] Control intensity: Level 3 control;

[0213] The final hierarchical control matrix is ​​shown in Table 2:

[0214] Table 2 List of the final generated hierarchical control matrices

[0215]

[0216] In actual production, if the cooling rate monitoring data shows a deviation of more than ±1% from the standard value of 200℃ / s, Level 1 control will be immediately triggered, activating the automatic adjustment device to bring the cooling rate back to the range of 198℃ / s to 202℃ / s. Simultaneously, this anomaly will be recorded, and the cause (such as equipment malfunction or operational error) will be analyzed to take preventative measures to prevent similar situations from recurring. For deviations in additive ratios and temperature, corresponding adjustment measures will be taken according to the Level 2 and Level 3 control intensities to ensure they remain within the set control ranges.

[0217] By applying this hierarchical control matrix, the production process can achieve refined management of key process parameters, ensuring the stability of crystal morphology and the consistency of product quality, while optimizing resource allocation and improving production efficiency and economic benefits.

[0218] Step S3000: Obtain the measured crystal morphology parameters of the water-quenched slag production process, and dynamically optimize and control the water-quenched slag production process parameters based on the measured crystal morphology parameters and the hierarchical control matrix.

[0219] Further, step S3000 includes:

[0220] Step S3100: Obtain the measured crystal morphology parameters of the water-quenched slag production process; the measured crystal morphology parameters include grain size parameters and crystal distribution uniformity parameters;

[0221] Furthermore, such as Figure 4 As shown, step S3100 includes:

[0222] Step S3110: Obtain microscopic images and X-ray diffraction patterns of crystals during the water-quenched slag production process;

[0223] Step S3120: Perform digital image processing on the microscopic image to extract grain size parameters;

[0224] Step S3130: Perform curve fitting on the X-ray diffraction pattern to obtain the crystal distribution uniformity parameters.

[0225] The curve fitting of the X-ray diffraction pattern includes:

[0226]

[0227] in:

[0228] Diffraction intensity, representing different diffraction angles. The diffraction intensity is measured using an X-ray diffractometer. It reflects the intensity of the diffraction phenomenon and can reveal structural information within the crystal, such as grain size and crystal orientation.

[0229] : Correction factor, which affects the height of the diffraction peak and represents the intensity of the diffraction peak. The larger the value, the higher the diffraction intensity in that direction, and the more uniform the crystal distribution in that direction.

[0230] Full width at half maximum (FWHM) is a correction factor that controls the width of the diffraction peak. The larger the value, the wider the orientation distribution of the crystal, and the greater the non-uniformity of the crystal in that direction. It is related to the distribution of grain size and orientation.

[0231] B: The amplitude coefficient of the Gaussian function, which controls the amplitude of the diffraction peak shape. The Gaussian function is usually used to describe a relatively uniform crystal structure. The larger the B value, the more concentrated the crystal distribution is in that direction.

[0232] The standard deviation of the Gaussian function determines the width of the diffraction peak. Smaller grains mean better grain size uniformity; Larger size means a wider grain size distribution and uneven crystal size.

[0233] : Quadratic coefficient, reflecting the secondary influence behind the diffraction peaks. This term is included to account for non-ideal grain distribution phenomena, such as defects inside the crystal or material inhomogeneity.

[0234] The center position of the diffraction peak indicates the angle at which the maximum value of the diffraction peak appears. The angle representing the main orientation or peak of the crystal.

[0235] This represents an exponential function with the natural constant e as its base.

[0236] (half-peak width) and (Standard deviation): These two parameters can be obtained by curve fitting of the diffraction pattern, reflecting the size distribution of the grains and the orientation distribution of the crystal. It controls the orientation distribution of the crystal. This reflects the width of the grain size distribution. These two parameters are typically obtained by fitting the experimentally obtained diffraction pattern using the least squares method.

[0237] B and These parameters are usually obtained by fitting diffraction patterns and reflect the amplitude and shape of the diffraction peaks.

[0238] By analyzing the diffraction pattern, the angular position of the maximum diffraction intensity can be determined, thus obtaining... .

[0239] Diffraction angle Determines the diffraction intensity The change. With the angle The changes in the intensity of the diffraction pattern The intensity will rise and fall, depending on the width and position of the diffraction peak. Reflected from different angles The diffraction intensity under the given conditions. Parameters obtained through fitting (such as...) and ) decided The specific form. With the independent variable... The change in the dependent variable Different trends will emerge: when When the value is large, the diffraction peaks broaden; when At larger grain sizes, the grain size distribution becomes more widespread, leading to an increase in the width of the diffraction peaks. With... (width of crystal orientation distribution) and An increase in the width of the grain size distribution leads to a wider diffraction peak and a broader range of diffraction intensity variations, indicating that the crystal distribution is becoming increasingly non-uniform. Conversely, when... and The decrease in size and the narrowing of the diffraction peaks indicate that the uniformity of the crystal has improved and the size distribution of the grains has become more concentrated.

[0240] and These are two key parameters that reflect the uniformity of crystal distribution. It reflects the uniformity of the orientation distribution of the crystal in different directions. This reflects the uniformity of grain size. By fitting these parameters, the uniformity of grains in a sample can be quantitatively assessed. The combined form of the Gaussian and Lorentz functions helps to simultaneously describe the grain size distribution (from...). The orientation distribution of the crystal (determined by) and the orientation distribution of the crystal (by) (Decision). This joint fitting can accurately capture the complex characteristics of crystal distribution, avoiding the limitations of a single model. The crystal distribution uniformity parameters obtained through fitting can be used to adjust process parameters (such as cooling rate and temperature) in the water-quenched slag production process. If or A large value indicates that the crystal is not uniform, and the crystal morphology can be optimized by adjusting process parameters such as cooling rate or temperature.

[0241] Specifically, the goal of step S3100 is to achieve dynamic optimization and intelligent control of the production process by acquiring and analyzing crystal morphology parameters in real time, thereby ensuring the quality and consistency of the final product. In step S3110, advanced detection equipment is used to acquire microscopic images and X-ray diffraction patterns of crystals during the water-quenched slag production process in real time to comprehensively monitor changes in crystal morphology parameters. An online microscopic imager is deployed at key process points on the production line, capable of continuously capturing microscopic images of the crystals. Through microscopic imaging, the size, shape, and distribution of grains can be observed, and time-series data on grain size can be obtained. After processing, this image data can be used for quantitative analysis of grain size and distribution uniformity. An X-ray diffractometer is used to acquire X-ray diffraction patterns of the crystals. X-ray diffraction technology can reflect the internal structure and crystal plane orientation of crystals. By analyzing diffraction patterns, the growth orientation and uniformity of crystals can be evaluated. After curve fitting processing, these diffraction pattern data can quantitatively describe the uniformity parameters of crystal distribution. By acquiring microscopic images and X-ray diffraction patterns in real time, the dynamic changes in crystal morphology during the production process can be comprehensively and accurately monitored. This multi-dimensional monitoring method not only improves the comprehensiveness and accuracy of the data, but also enables timely detection of any abnormalities that may occur during the production process, ensuring that the crystal morphology parameters are always kept within the predetermined control range, thereby improving product quality and production stability.

[0242] Step S3120 involves digital image processing of the acquired microscopic image to extract grain size parameters. This process typically includes the following steps:

[0243] Image segmentation: Image processing algorithms (such as thresholding, edge detection, and region growing) are used to separate the grain regions in a microscopic image from the background, generating a binary image. The purpose of image segmentation is to distinguish the grain regions of interest from the irrelevant background regions for subsequent analysis.

[0244] Feature extraction: Extracting the geometric features of grains from the segmented image, such as grain area, perimeter, and diameter. Commonly used methods include Hough transform and morphological processing. These geometric features are the basis for quantitative analysis of grain size. Morphological processing uses mathematical morphological operations (such as dilation and erosion) to process the image to enhance or extract specific structures.

[0245] Grain size calculation: Based on the extracted geometric features, the average grain size and grain size distribution width are calculated. Grain size is usually expressed as average diameter (μm), while grain size distribution width can be quantified by standard deviation or coefficient of variation.

[0246] Data statistics and analysis: Statistical analysis was performed on data from multiple microscopic images to obtain the temporal variation trend of grain size, providing a basis for subsequent crystal morphology evaluation and model optimization.

[0247] Digital image processing technology can efficiently and accurately extract grain size parameters, eliminating the subjectivity and inefficiency of manual measurement. This automated data processing method not only improves the speed and accuracy of data acquisition but also enables real-time analysis of large-scale production data, providing reliable data support for the dynamic optimization of the production process.

[0248] Step S3130 mainly involves extracting crystal distribution uniformity parameters by curve fitting of the X-ray diffraction pattern; this process includes the following steps:

[0249] X-ray diffraction pattern preprocessing: Preprocessing the acquired X-ray diffraction patterns, including denoising and baseline correction, ensures data accuracy and usability. Preprocessing steps help eliminate instrument noise and background signals, improving the accuracy of subsequent analysis. Denoising refers to removing random noise from the pattern using methods such as filtering. Baseline correction involves adjusting the background signal of the diffraction pattern to align it with the ideal baseline.

[0250] Curve fitting: Using appropriate mathematical models (such as Gaussian functions, Lorentz functions, etc.) to fit diffraction peaks to determine the distribution of crystal plane orientations. The purpose of curve fitting is to simplify complex diffraction patterns into a series of standard curves to facilitate subsequent quantitative analysis.

[0251] Crystal distribution uniformity calculation: Based on the fitted diffraction peak widths and shapes, the uniformity parameters of the crystal distribution are calculated. Commonly used indicators include the standard deviation of crystal plane orientation and full width at half maximum (FWHM), which reflect the orientation consistency of the crystal in different directions. FWHM refers to the width of the diffraction peak at half its height, reflecting the degree of dispersion of crystal orientation. The standard deviation measures the dispersion of the crystal plane orientation distribution; the smaller the standard deviation, the more uniform the distribution.

[0252] Data analysis and evaluation: Statistical analysis of data from multiple diffraction patterns is performed to evaluate the temporal variation trend of crystal distribution uniformity, providing a basis for dynamic optimization of crystal morphology.

[0253] By fitting X-ray diffraction patterns, the uniformity parameters of crystal distribution can be precisely quantified, providing more in-depth information about the internal structure than microscopic images. This method can reveal changes in crystal orientation and uniformity at different growth stages, helping production managers to adjust process parameters in a timely manner, optimize crystal morphology, and improve the physical properties and consistency of products.

[0254] By acquiring crystal morphology parameters in real time, we can promptly understand the state changes during the production process. Combined with a hierarchical control matrix, we can dynamically adjust process parameters to ensure that the production process always operates in the best condition.

[0255] Step S3200: Based on the measured crystal morphology parameters and the hierarchical control matrix, dynamically optimize and control the production process parameters of water-quenched slag.

[0256] Furthermore, such as Figure 5 As shown, step S3200 includes:

[0257] Step S3210: Input the grain size parameters and crystal distribution uniformity parameters into the crystal morphology multi-objective optimization model to obtain the optimal production process parameter values ​​under the current production state;

[0258] Specifically, the multi-objective optimization model for crystal morphology comprehensively considers grain size and crystal distribution uniformity parameters. It calculates the optimal combination of multiple process parameters (such as temperature, cooling rate, and additive ratio) using optimization algorithms (e.g., particle swarm optimization, genetic algorithms). The model aims to simultaneously optimize grain size and distribution uniformity to obtain the optimal production process parameters that meet quality requirements. Optimal production process parameters refer to the parameter values ​​that, under current production conditions, enable grain size and distribution uniformity to reach the expected best state. Typically, these parameters include temperature, cooling rate, and additive ratio.

[0259] By inputting measured parameters into the optimization model, a set of optimal process parameter combinations can be obtained, ensuring the optimization of crystal morphology quality. These optimal process parameters provide a clear basis for subsequent adjustments and control, thereby improving the stability of the production process and product quality. For example, if non-uniform grain size is found in the current production process, the optimization model can obtain a balanced solution by adjusting parameters such as cooling rate and additive ratio, ensuring that the final product quality meets expectations.

[0260] Step S3220: Compare the deviation between the measured crystal morphology parameters and the expected optimization target, dynamically adjust the hierarchical control matrix, and obtain the adjusted hierarchical control matrix;

[0261] Furthermore, such as Figure 6 As shown, step S3220 includes:

[0262] Step S3221: Calculate the deviation ΔG between the grain size parameter and the target grain size value, and calculate the deviation ΔU between the crystal distribution uniformity parameter and the target distribution uniformity value;

[0263] Step S3222: Determine whether |ΔG| exceeds the preset grain size deviation threshold ΔG. θ Determine whether |ΔU| exceeds the preset distribution uniformity deviation threshold ΔU. θ ;

[0264] Step S3223, if |ΔG|≤ΔG θ And |ΔU|≤ΔU θ If so, the existing hierarchical control matrix settings will remain unchanged;

[0265] Step S3224, if |ΔG|>ΔG θ Or |ΔU|>ΔU θ Then, the hierarchical control matrix is ​​dynamically adjusted to obtain the adjusted hierarchical control matrix.

[0266] Further, step S3224 includes:

[0267] Step S32241: Narrow the control threshold range of key process parameters at different importance levels in the hierarchical control matrix to obtain the adjusted control threshold range;

[0268] Step S32242: Increase the control intensity of key process parameters at different importance levels in the hierarchical control matrix to obtain the adjusted control intensity;

[0269] Step S32243: Generate an adjusted hierarchical control matrix with the importance level of key process parameters as rows and the adjusted control threshold range and adjusted control intensity as columns.

[0270] Specifically, the purpose of step S3221 is to calculate the deviation ΔG between the grain size parameter and its target value, and the deviation ΔU between the crystal distribution uniformity parameter and its target value. By calculating these deviations, the degree of deviation in the current production state can be quantitatively assessed, thus providing a basis for subsequent control and adjustment. The deviation in grain size reflects whether the grain size in the current production process has reached the expected target value. If the absolute value of ΔG is large, it indicates that the grain size control effect is poor, and parameters such as the cooling rate may need to be adjusted. Crystal distribution uniformity reflects whether the crystals are evenly distributed in the material. The deviation of the ΔU value shows whether the distribution in the current production meets the optimization target. If the ΔU deviation is large, it indicates that the crystal distribution is uneven, and other process parameters, such as temperature or additive ratio, need to be adjusted.

[0271] Step S3222 is used to determine whether the deviations ΔG and ΔU exceed preset thresholds. This determination determines whether the current hierarchical control matrix needs to be adjusted. ΔG θ This is a preset threshold for grain size deviation, defining the maximum allowable deviation range for grain size. If |ΔG| exceeds ΔG... θ This means the grain size exceeds the expected range, and the production process needs intervention to correct this deviation. ΔU θ This is a preset threshold for the uniformity deviation of the crystal distribution, defining the maximum allowable deviation range for crystal distribution uniformity. If |ΔU| exceeds ΔU θ This means that the crystal distribution is uneven, which may affect the quality of the final product, thus requiring adjustments to the relevant process parameters during production.

[0272] If both the grain size deviation ΔG and the crystal distribution uniformity deviation ΔU do not exceed the set threshold (i.e., |ΔG|≤ΔG) θ And |ΔU|≤ΔU θ If |ΔG| > ΔG, it indicates that the crystal morphology quality in the current production process meets the optimization target and no adjustment is needed. Therefore, the hierarchical control matrix on the production line will remain unchanged. This situation indicates that the existing process parameters and control measures are effective, and the production process requires minimal intervention to stably produce products that meet quality requirements. If |ΔG| > ΔG θ Or |ΔU|>ΔU θ This indicates that a situation has occurred during the production process that does not meet quality requirements. It is necessary to adjust the graded control matrix to correct the deviation and ensure that the crystal morphology meets the expected standard.

[0273] To more precisely control key process parameters in production, it is first necessary to narrow the control threshold ranges for different importance levels of key process parameters in the hierarchical control matrix. For example, if the control deviation of the cooling rate is too large, its control threshold can be narrowed to ±0.5% of the standard value, thereby more strictly controlling its fluctuations. For process parameters with higher importance (such as cooling rate, additive ratio, etc.), their control intensity should be increased. For example, if the current control intensity is "Level 2", it can be increased to "Level 1", meaning that these process parameters will be checked and adjusted more frequently in real time. Then, a new hierarchical control matrix is ​​generated to ensure that the control threshold range and control intensity of each key process parameter have been adjusted to values ​​most suitable for the current production state.

[0274] The purpose of dynamically adjusting the hierarchical control matrix is ​​to promptly identify and correct deviations during the production process, thereby ensuring that the crystal morphology quality remains stable and meets optimization objectives. By narrowing the threshold range and increasing the control intensity, key process parameters in the production process can be precisely controlled, reducing quality fluctuations and improving product consistency. For example, if inaccurate control of the cooling rate is detected, timely adjustment of the control intensity to "Level 1" and narrowing the control threshold can effectively improve the uniformity of grain size and distribution, ensuring that the final product quality meets the expected standards.

[0275] In step S3230, the optimal production process parameter values ​​under the current production status are parsed into operable process parameter adjustment instructions based on the adjusted hierarchical control matrix.

[0276] Furthermore, such as Figure 7 As shown, step S3230 includes:

[0277] Step S3231: Match and compare the optimal production process parameter values ​​under the current production state with the adjusted control threshold range and adjusted control intensity of the corresponding key process parameters in the adjusted hierarchical control matrix.

[0278] Step S3232: If the optimal production process parameter value under the current production state is within the adjusted control threshold range of the corresponding key process parameter, then generate the set value control instruction for the corresponding key process parameter and directly use the optimal production process parameter value as the set value of the corresponding key process parameter in the production process.

[0279] Step S3233: If the optimal production process parameter value under the current production state exceeds the adjusted control threshold range of the corresponding key process parameter, then generate the set value control instruction or fuzzy control rule of the corresponding key process parameter according to the adjusted control strength of the corresponding key process parameter.

[0280] Further, step S3233 includes:

[0281] Step S32331: For the key process parameters with the adjusted control intensity of Level 1, the average value of the corresponding optimal production process parameter value and the adjusted control threshold range is used as the instruction value to generate the setpoint control instruction for the corresponding key process parameter.

[0282] Step S32332: For key process parameters with adjusted control intensity of level two or three, generate fuzzy control rules for the corresponding key process parameters based on the degree of deviation of the optimal production process parameter value from the corresponding adjusted control threshold range.

[0283] Step S3234: Convert the setpoint control command or fuzzy control rule into a process parameter adjustment command.

[0284] Specifically, the purpose of step S3230 is to combine the optimal production process parameter values ​​(such as optimal temperature, cooling rate, and additive ratio) obtained in step S3210 with the adjusted hierarchical control matrix and transform them into operable process parameter adjustment instructions. The key to this step is to connect the theoretically calculated optimal values ​​with the actual control constraints and generate adjustment instructions that can be actually executed during the production process.

[0285] The hierarchical control matrix provides the control threshold ranges and control intensities for different process parameters at different importance levels. By comparing these with the optimal production process parameter values, it can be determined whether these parameters are within a reasonable control range and corresponding adjustment instructions can be generated. If the optimal production process parameter value is within the corresponding control threshold range, a setpoint control instruction is directly generated; if the optimal value exceeds the threshold range, an adjustment control instruction is generated based on the control intensity.

[0286] The goal of step S3231 is to match and compare the optimal production process parameter values ​​with the control threshold ranges and control intensities in the adjusted hierarchical control matrix. This process is a prerequisite for generating specific adjustment instructions and can determine whether the optimal production process parameter values ​​meet existing control standards. For each critical process parameter, the adjusted control threshold range represents the acceptable fluctuation range for that parameter. For example, the control threshold for cooling rate might be ±1% of the standard value, while the control threshold for temperature might be ±5%. Control intensity determines the level of management applied to different process parameters. For example, the control intensity for Level 1 critical parameters is higher, requiring more precise control; while the control intensity for Level 3 critical parameters is lower, allowing for greater fluctuations. By comparing the optimal parameters with the control thresholds and control intensities, it can be determined whether further adjustments to the production parameters are needed.

[0287] When the matching result in step S3231 shows that the optimal production process parameter value is within the control threshold range, it indicates that the process parameters in the current production process meet the optimization requirements and no further adjustment is needed. In this case, the system will directly generate a setpoint control instruction, using the optimal production process parameter value as the setpoint value for the corresponding process parameter in the production process. The setpoint control instruction means that the system will adjust the corresponding process parameters (such as temperature, cooling rate, etc.) to the optimal value to ensure that the production process reaches the optimal state. For example, if the calculated optimal cooling rate is 50℃ / s, and this value is within the control threshold range, the system will set the cooling rate to 50℃ / s and maintain it at that value. Directly using the optimal process parameter as a setpoint reduces the complexity of human intervention and adjustment, ensuring stable operation of the production process.

[0288] If, in step S3231, the optimal production process parameter value is found to exceed the control threshold range, then the production process needs to be adjusted. In this case, a corresponding adjustment control command is generated based on the adjusted control intensity. For key process parameters with Level 1 control intensity (such as cooling rate), if their optimal value exceeds the control range, the average value of the control threshold range in which the parameter is located will be used instead, and a setpoint control command will be generated. For key process parameters with Level 2 and Level 3 control intensity (such as temperature), fuzzy control rules are generated based on the degree of deviation between the optimal parameter value and the control threshold range. The fuzzy control rules include the adjustment direction and adjustment magnitude. For example, if the optimal temperature value is 105℃, while its control threshold range is 100℃ to 104℃, then the optimal temperature value exceeds the upper limit. The system will generate a fuzzy control rule indicating that the temperature should be "slightly reduced" or "reduced" by a certain amount so that the temperature gradually approaches the maximum value of the control threshold range.

[0289] The purpose of step S3234 is to transform the generated setpoint control commands and fuzzy control rules into specific process parameter adjustment commands. These commands will be distributed to field control equipment through the distributed control system to achieve dynamic adjustment of process parameters.

[0290] Step S3200, by combining real-time data input from measured crystal morphology parameters and a hierarchical control matrix, dynamically optimizes and controls the production process parameters of water-quenched slag, providing a precise and flexible quality optimization mechanism for the production process. Its beneficial effects include: improving the automation and intelligence level of the production process, achieving continuous dynamic optimization of quality, balancing resource utilization and cost-effectiveness, ensuring that each batch of products meets quality standards, and reducing fluctuations and instabilities in the production process. This optimized control system not only improves product quality but also demonstrates significant advantages in production efficiency and cost control, ultimately promoting the continuous improvement and upgrading of the water-quenched slag production process.

[0291] Example 2

[0292] This embodiment, based on Embodiment 1, provides an intelligent management system for the industrial solid wastewater quenching slag fiberization production process, such as... Figure 8 As shown, it includes:

[0293] Model building module: used to build a mathematical model of the crystal morphology of industrial solid waste water quenched slag, and based on the mathematical model of the crystal morphology of industrial solid waste water quenched slag, to build a multi-objective optimization model of crystal morphology, and to obtain the optimal set of production process parameters and expected optimization objectives;

[0294] The hierarchical control module is based on a mathematical model of the crystal morphology of industrial solid waste quenched slag. Key process parameters are selected from the process parameters. The selected key process parameters are divided into different importance levels. For key process parameters of different importance levels, corresponding control threshold ranges and control intensities are set according to the optimal production process parameter set to establish a hierarchical control matrix.

[0295] Dynamic optimization module: Obtains measured crystal morphology parameters of the water-quenched slag production process, and dynamically optimizes and controls the production process parameters of water-quenched slag based on the measured crystal morphology parameters and the hierarchical control matrix.

[0296] In the model building module, the construction of the mathematical model for the crystal morphology of industrial solid wastewater quenched slag includes:

[0297] Step S1110: Collect historical production data of industrial solid waste water quenching slag and extract the first record set. The first record set includes grain size time series, distribution uniformity time series, temperature time series, cooling rate time series and additive ratio time series.

[0298] Step S1120: Perform data preprocessing on the time-series data in the first record set;

[0299] Step S1130: Based on the first record set, establish a nonlinear correlation model between grain size and distribution uniformity and process parameters to obtain a mathematical model of the crystal morphology of industrial solid waste quenched slag; the process parameters include temperature, cooling rate and additive ratio.

[0300] Step S1130 includes:

[0301] Step S1131: Based on the first record set, establish a nonlinear correlation model between grain size and process parameters, and label it as the initial grain size model; the initial grain size model includes n1 grain size influencing parameters. ,in, For the constants of the initial model of grain size, for Time of the first The influence of a process parameter on the grain size at time t, 0≤i≤n1-1, 1≤ ≤n1-1;

[0302] Step S1132: Based on the first record set, establish a nonlinear correlation model between distribution uniformity and process parameters, labeled as the initial distribution uniformity model; the initial distribution uniformity model includes n² distribution uniformity influencing parameters. ,in, For the constant term of the initial model of uniform distribution, for Time of the first The influence of a process parameter on the uniformity of distribution at time t, 0≤j≤n²-1, 1≤ ≤n2-1;

[0303] Step S1133: Solve the parameters of the initial model for grain size and the initial model for grain distribution uniformity to obtain... and The optimal value;

[0304] Step S1134, will Substituting the optimal value into the initial grain size model, we obtain the final grain size model.

[0305] Step S1135, will Substituting the optimal value into the initial model of uniform distribution yields the final model of uniform distribution.

[0306] Step S1136: The final model of grain size and the final model of distribution uniformity constitute the mathematical model of crystal morphology of industrial solid waste water quenched slag.

[0307] In the model building module, obtaining the optimal production process parameter set and the expected optimization objective includes:

[0308] Step S1210: Based on the mathematical model of crystal morphology of industrial solid waste water quenched slag, with temperature T, cooling rate C and additive ratio A as decision variables, and minimizing grain size and maximizing distribution uniformity as optimization objectives, a multi-objective optimization model of crystal morphology is established.

[0309] Step S1220: Solve the multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives. The expected optimization objectives include the target value of grain size and the target value of distribution uniformity. The optimal set of production process parameters includes the historical best values ​​of production process parameters.

[0310] In the hierarchical control module, the step of selecting key process parameters from process parameters includes:

[0311] Step S2110: Based on the final model of grain size and the final model of distribution uniformity, calculate the partial derivatives of the process parameters with respect to grain size and distribution uniformity respectively, and obtain the influence coefficient matrix of each process parameter;

[0312] Step S2120: Normalize the influence coefficient matrix to obtain the influence weights of process parameters on grain size and distribution uniformity.

[0313] Step S2130: Sort the process parameters in descending order according to their influence weight, and select the process parameters whose cumulative weight reaches the preset cumulative weight threshold θ1 as key process parameters.

[0314] In the hierarchical control module, the process of classifying the selected key process parameters into different importance levels includes:

[0315] Step S2210: Sort the key process parameters in descending order according to their influence weight, and define the key process parameters with the highest influence weight W1 as first-level key parameters.

[0316] Step S2220: Define the key process parameters with influence weights in the range of W1 to W2 as secondary key parameters;

[0317] Step S2230: Define the key process parameters with influence weights in the range of W2 to W3 as level 3 key parameters, where W3 > W2 > W1, and W1, W2, and W3 are percentages.

[0318] In the hierarchical control module, establishing the hierarchical control matrix includes:

[0319] Step S2310: Obtain the historical optimal values ​​of each key process parameter from the optimal production process parameter set, and use the historical optimal values ​​of each key process parameter as the standard values ​​of the corresponding key process parameters; set the control threshold range of the first-level key parameter to be the standard value of the first-level key parameter ± M1; the control threshold range of the second-level key parameter to be the standard value of the second-level key parameter ± M2; and the control threshold range of the third-level key parameter to be the standard value of the third-level key parameter ± M3; where M3 > M2 > M1, and M1, M2, and M3 are percentages;

[0320] Step S2320: Set the control intensity of the first-level key parameter to level one, set the control intensity of the second-level key parameter to level two, and set the control intensity of the third-level key parameter to level three.

[0321] Step S2330: Generate a hierarchical control matrix with the importance level of key process parameters as rows and the control threshold range and control intensity as columns.

[0322] In the dynamic optimization module, the dynamic optimization control of the water-quenched slag production process parameters includes:

[0323] Step S3100: Obtain the measured crystal morphology parameters of the water-quenched slag production process; the measured crystal morphology parameters include grain size parameters and crystal distribution uniformity parameters;

[0324] Step S3200: Based on the measured crystal morphology parameters and the hierarchical control matrix, dynamically optimize and control the production process parameters of water-quenched slag.

[0325] Step S3100 includes:

[0326] Step S3110: Obtain microscopic images and X-ray diffraction patterns of crystals during the water-quenched slag production process;

[0327] Step S3120: Perform digital image processing on the microscopic image to extract grain size parameters;

[0328] Step S3130: Perform curve fitting on the X-ray diffraction pattern to obtain the crystal distribution uniformity parameters.

[0329] Step S3200 includes:

[0330] Step S3210: Input the grain size parameters and crystal distribution uniformity parameters into the crystal morphology multi-objective optimization model to obtain the optimal production process parameter values ​​under the current production state;

[0331] Step S3220: Compare the deviation between the measured crystal morphology parameters and the expected optimization target, dynamically adjust the hierarchical control matrix, and obtain the adjusted hierarchical control matrix;

[0332] In step S3230, the optimal production process parameter values ​​under the current production status are parsed into operable process parameter adjustment instructions based on the adjusted hierarchical control matrix.

[0333] Step S3220 includes:

[0334] Step S3221: Calculate the deviation ΔG between the grain size parameter and the target grain size value, and calculate the deviation ΔU between the crystal distribution uniformity parameter and the target distribution uniformity value;

[0335] Step S3222: Determine whether |ΔG| exceeds the preset grain size deviation threshold ΔG. θ Determine whether |ΔU| exceeds the preset distribution uniformity deviation threshold ΔU. θ ;

[0336] Step S3223, if |ΔG|≤ΔG θ And |ΔU|≤ΔU θ If so, the existing hierarchical control matrix settings will remain unchanged;

[0337] Step S3224, if |ΔG|>ΔGθ Or |ΔU|>ΔU θ Then, the hierarchical control matrix is ​​dynamically adjusted to obtain the adjusted hierarchical control matrix.

[0338] Step S3224 includes:

[0339] Step S32241: Narrow the control threshold range of key process parameters at different importance levels in the hierarchical control matrix to obtain the adjusted control threshold range;

[0340] Step S32242: Increase the control intensity of key process parameters at different importance levels in the hierarchical control matrix to obtain the adjusted control intensity;

[0341] Step S32243: Generate an adjusted hierarchical control matrix with the importance level of key process parameters as rows and the adjusted control threshold range and adjusted control intensity as columns.

[0342] Step S3230 includes:

[0343] Step S3231: Match and compare the optimal production process parameter values ​​under the current production state with the adjusted control threshold range and adjusted control intensity of the corresponding key process parameters in the adjusted hierarchical control matrix.

[0344] Step S3232: If the optimal production process parameter value under the current production state is within the adjusted control threshold range of the corresponding key process parameter, then generate the set value control instruction for the corresponding key process parameter and directly use the optimal production process parameter value as the set value of the corresponding key process parameter in the production process.

[0345] Step S3233: If the optimal production process parameter value under the current production state exceeds the adjusted control threshold range of the corresponding key process parameter, then generate the set value control instruction or fuzzy control rule of the corresponding key process parameter according to the adjusted control strength of the corresponding key process parameter.

[0346] Step S3234: Convert the setpoint control command or fuzzy control rule into a process parameter adjustment command.

[0347] Step S3233 includes:

[0348] Step S32331: For the key process parameters with the adjusted control intensity of Level 1, the average value of the corresponding optimal production process parameter value and the adjusted control threshold range is used as the instruction value to generate the setpoint control instruction for the corresponding key process parameter.

[0349] Step S32332: For key process parameters with adjusted control intensity of level two or three, generate fuzzy control rules for the corresponding key process parameters based on the degree of deviation of the optimal production process parameter value from the corresponding adjusted control threshold range.

[0350] In addition, the parts of the technical solutions provided in the embodiments of this application that are consistent with the implementation principles of the corresponding technical solutions in the prior art have not been described in detail, so as to avoid excessive elaboration.

[0351] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent management method for the industrial solid wastewater quenching slag fiberization production process, characterized in that, The method includes: A mathematical model of crystal morphology for industrial solid wastewater quenched slag is constructed. Based on this model, a multi-objective optimization model for crystal morphology is developed to obtain the optimal set of production process parameters and the expected optimization objectives. The expected optimization objectives include the target values ​​for grain size and distribution uniformity. The mathematical model for constructing the crystal morphology of industrial solid wastewater quenched slag includes: Historical production data of industrial solid waste water quenched slag was collected, and a first record set was extracted. The first record set includes at least the time series of grain size, distribution uniformity, temperature, cooling rate, and additive ratio. Based on the first record set, a nonlinear correlation model between grain size and process parameters was established, marked as the initial grain size model. The process parameters include temperature, cooling rate, and additive ratio. The initial grain size model reflects the dynamic correlation between the grain size at time t and its own state at time t-1, as well as temperature, cooling rate, and additive ratio. Based on the first record set, a nonlinear correlation model between distribution uniformity and process parameters was established, marked as the initial distribution uniformity model. The parameters of the initial grain size model and the initial distribution uniformity model were solved to obtain the final grain size model and the final distribution uniformity model. The final grain size model and the final distribution uniformity model constitute the mathematical model of the crystal morphology of industrial solid waste water quenched slag. Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, key process parameters are screened from the process parameters; the screened key process parameters are divided into different importance levels; for key process parameters of different importance levels, corresponding control threshold ranges and control intensities are set according to the optimal production process parameter set, and a hierarchical control matrix is ​​established. Measured crystal morphology parameters of the water-quenched slag production process are obtained. Based on the measured crystal morphology parameters and a hierarchical control matrix, the production process parameters of the water-quenched slag are dynamically optimized and controlled. The measured crystal morphology parameters include grain size parameters and crystal distribution uniformity parameters. The method for obtaining the measured crystal morphology parameters includes acquiring microscopic images and X-ray diffraction patterns of the crystals during the water-quenched slag production process; performing digital image processing on the microscopic images to extract the grain size parameters; and performing curve fitting on the X-ray diffraction patterns to obtain the crystal distribution uniformity parameters. The curve fitting on the X-ray diffraction patterns includes: ； in, For diffraction intensity, For correction factor, Where is the half-peak width, and B is the amplitude coefficient of the Gaussian function. Let be the standard deviation of the Gaussian function. For diffraction angle, The center position of the diffraction peak. The coefficient of the quadratic term, This represents an exponential function with the natural constant e as its base. The dynamic optimization and control of water-quenched slag production process parameters based on measured crystal morphology parameters and a hierarchical control matrix includes: inputting grain size parameters and crystal distribution uniformity parameters into a multi-objective optimization model for crystal morphology to obtain the optimal production process parameter values ​​under the current production state; calculating the deviation ΔG between the grain size parameter and the target grain size value, and calculating the deviation ΔU between the crystal distribution uniformity parameter and the target distribution uniformity value; if |ΔG|≤ΔG θ And |ΔU|≤ΔU θ If the existing hierarchical control matrix settings remain unchanged; if |ΔG|>ΔG θ Or |ΔU|>ΔU θ Then, the control threshold range of key process parameters at different importance levels in the hierarchical control matrix is ​​narrowed to obtain the adjusted control threshold range; the control intensity of key process parameters at different importance levels in the hierarchical control matrix is ​​increased to obtain the adjusted control intensity; and an adjusted hierarchical control matrix is ​​generated with the importance level of the key process parameters as rows and the adjusted control threshold range and adjusted control intensity as columns, where ΔG θ ΔU is the preset grain size deviation threshold. θ The preset distribution uniformity deviation threshold; The optimal production process parameter value under the current production state is matched and compared with the adjusted control threshold range and adjusted control intensity of the corresponding key process parameter in the adjusted hierarchical control matrix. If the optimal production process parameter value under the current production state is within the adjusted control threshold range of the corresponding key process parameter, a setpoint control instruction for the corresponding key process parameter is generated, and the optimal production process parameter value is directly used as the setpoint value of the corresponding key process parameter in the production process. If the optimal production process parameter value under the current production state exceeds the adjusted control threshold range of the corresponding key process parameter, for key process parameters with an adjusted control intensity of level one, the average value of the corresponding adjusted control threshold range is used as the instruction value to generate a setpoint control instruction for the corresponding key process parameter. For key process parameters with an adjusted control intensity of level two or three, fuzzy control rules for the corresponding key process parameter are generated based on the degree of deviation of the optimal production process parameter value from the corresponding adjusted control threshold range.

2. The intelligent management method for the industrial solid wastewater quenching slag fiberization production process according to claim 1, characterized in that, The optimal set of production process parameters and the expected optimization objective include: Based on the mathematical model of crystal morphology of industrial solid waste quenched slag, a multi-objective optimization model of crystal morphology is established with external parameters as decision variables and minimizing grain size and maximizing distribution uniformity as optimization objectives. Solve the multi-objective optimization model of crystal morphology to obtain the optimal set of production process parameters and the expected optimization objectives. The expected optimization objectives include the target value of grain size and the target value of distribution uniformity. The optimal set of production process parameters includes the historical best values ​​of the production process parameters.

3. The intelligent management method for the industrial solid wastewater quenching slag fiberization production process according to claim 2, characterized in that, The process of selecting key process parameters from process parameters includes: Based on the final model of grain size and the final model of distribution uniformity, the partial derivatives of the process parameters with respect to grain size and distribution uniformity are calculated respectively, and the influence coefficient matrix of each process parameter is obtained. The influence coefficient matrix is ​​normalized to obtain the influence weights of process parameters on grain size and distribution uniformity. The process parameters are sorted in descending order according to their influence weight, and the process parameters whose cumulative weight reaches the preset cumulative weight threshold θ1 are selected as the key process parameters.

4. The intelligent management method for the industrial solid wastewater quenching slag fiberization production process according to claim 3, characterized in that, The process parameters selected and classified into different importance levels include: The key process parameters are sorted in descending order according to their influence weight, and the key process parameters with the highest influence weight W1 are defined as first-level key parameters. Key process parameters with influence weights between W1 and W2 are defined as secondary key parameters; The critical process parameters with influence weights in the range of W2 to W3 are defined as Level 3 critical parameters, where W3 > W2 > W1, and W1, W2, and W3 are percentages.

5. The intelligent management method for the industrial solid wastewater quenching slag fiberization production process according to claim 4, characterized in that, The establishment of the hierarchical control matrix includes: The historical optimal values ​​of each key process parameter are obtained from the set of optimal production process parameters, and these historical optimal values ​​are used as the standard values ​​of the corresponding key process parameters. The control threshold range for the first-level key parameters is set to the standard value of the first-level key parameter ± M1; the control threshold range for the second-level key parameters is the standard value of the second-level key parameter ± M2; and the control threshold range for the third-level key parameters is the standard value of the third-level key parameter ± M3; where M3 > M2 > M1, and M1, M2, and M3 are percentages. Set the control intensity of the first-level key parameters to level one, the control intensity of the second-level key parameters to level two, and the control intensity of the third-level key parameters to level three. A hierarchical control matrix is ​​generated by using the importance level of key process parameters as rows and the control threshold range and control intensity as columns.

6. An intelligent management system for the industrial solid wastewater quenched slag fiberization production process, used to implement the intelligent management method for the industrial solid wastewater quenched slag fiberization production process as described in any one of claims 1-5, characterized in that, The system includes: Model building module: used to build a mathematical model of the crystal morphology of industrial solid waste water quenched slag, and based on the mathematical model of the crystal morphology of industrial solid waste water quenched slag, to build a multi-objective optimization model of crystal morphology, and to obtain the optimal set of production process parameters and expected optimization objectives; The hierarchical control module is based on a mathematical model of the crystal morphology of industrial solid waste quenched slag. Key process parameters are selected from the process parameters. The selected key process parameters are divided into different importance levels. For key process parameters of different importance levels, corresponding control threshold ranges and control intensities are set according to the optimal production process parameter set to establish a hierarchical control matrix. Dynamic optimization module: Obtains measured crystal morphology parameters of the water-quenched slag production process, and dynamically optimizes and controls the production process parameters of water-quenched slag based on the measured crystal morphology parameters and the hierarchical control matrix.

Images