Parameter optimization method, device and medium for mineral casting equipment

Abstract

The application discloses a parameter optimization method and device for a mineral casting device and a medium, and relates to the related field of casting processes. The method comprises the following steps: collecting mixed raw materials in a mixing process stage of a mineral casting process, initializing vacuum parameters and stirring parameters; performing initial mixing state detection on the mixed raw materials, predicting a vacuum degree influence index in a mixing process in combination with the stirring parameters, and performing one-time optimization of the initialized vacuum parameters; predicting by-products in a stirring process based on the mixed raw materials and the stirring parameters, analyzing whether the by-products contain gas affecting the vacuum degree, and performing two-time optimization of the vacuum parameters based on the one-time optimization. The technical problem of inaccurate control of vacuum parameters in the existing process optimization of the mixing stage of a mineral casting is solved, the accuracy of control of the vacuum parameters is improved, and the technical effect of improving the stability of the quality of the mineral casting is achieved.

Description

Technical Field

[0001] This application relates to the field of casting processes, and in particular to parameter optimization methods, apparatus and media for mineral casting equipment. Background Technology

[0002] Mineral castings are widely used in many industrial fields due to their excellent performance. Optimizing the casting process is crucial for improving the quality of mineral castings, reducing production costs, and increasing production efficiency. Among these factors, precise control of vacuum parameters during the mixing process is a key factor affecting the casting process's effectiveness. Currently, the main method for optimizing vacuum parameters during the mixing process is to set initial vacuum parameters based on experience. During the mixing process, the mixing state is roughly assessed through manual observation or simple testing equipment, and then the vacuum parameters are adjusted to a limited extent. However, current methods rely heavily on experience to set parameters, lacking a systematic analysis of the characteristics of the mixing raw materials, the dynamic changes during stirring, and the influence of byproducts. This results in a lack of scientific basis for optimizing vacuum parameters, making it difficult to accurately match the actual mixing process requirements. Consequently, the vacuum degree control during the mixing process is inaccurate, easily leading to excessively high or low vacuum levels. This affects the uniformity and stability of the mixed raw materials, ultimately resulting in inconsistent quality of mineral castings.

[0003] Currently, in related technologies, there is a technical problem with inaccurate control of vacuum parameters in the process optimization of the mixing stage of mineral casting. Summary of the Invention

[0004] This application provides a parameter optimization method, apparatus, and medium for mineral casting equipment. It employs techniques such as collecting mixed raw materials during the mixing stage of the mineral casting process, simultaneously acquiring initial vacuum and stirring parameters, detecting the initial mixing state of the raw materials, predicting the impact of stirring parameters on vacuum levels during mixing, optimizing the initial vacuum parameters accordingly, predicting byproducts generated during stirring based on the mixed raw materials and stirring parameters, determining whether the byproducts contain gases that affect vacuum levels, and performing secondary optimization of the vacuum parameters based on the primary optimization. These techniques solve the technical problem of inaccurate vacuum parameter control in existing mineral casting mixing stage process optimization, achieving the technical effect of improving the accuracy of vacuum parameter control and thus improving the quality stability of mineral castings.

[0005] This application provides a parameter optimization method for mineral casting equipment, comprising: collecting mixed raw materials, initializing vacuum parameters, and stirring parameters in the mixing process stage of mineral casting; detecting the initial mixing state of the mixed raw materials, predicting the vacuum degree influence index in the mixing process based on the stirring parameters, and performing a first optimization of the initial vacuum parameters; predicting by-products of the stirring process based on the mixed raw materials and the stirring parameters, analyzing whether the by-products contain gases that affect the vacuum degree, and performing a second optimization of the vacuum parameters based on the first optimization.

[0006] In a possible implementation, the initial mixing state of the mixed raw materials is detected, and the vacuum influence index during the mixing process is predicted based on the stirring parameters. The initial vacuum parameters are then optimized, and the following processes are performed: The specific surface area, internal porosity, and moisture content of the mixed raw materials are detected to generate initial mixing state data; a stirring twin is constructed for the mixing process stage, and twin simulation is performed based on the initial mixing state data, the stirring parameters, and the quantity of raw materials mixed, analyzing the simulation parameters for the release of water vapor and adsorbed air from the raw materials; the initial vacuum degree corresponding to the initial vacuum parameters is determined, and the influence level of the release of water vapor and adsorbed air on the target vacuum degree is analyzed based on the release simulation parameters, generating the vacuum influence index; the initial vacuum parameters are optimized according to the vacuum influence index, completing the first optimization.

[0007] In a possible implementation, the initial vacuum parameters are optimized according to the vacuum degree influence index to complete one optimization, and the following processes are performed: the initial vacuum parameters are parsed, and the vacuum holding stage is extracted from multiple vacuum control stages; the vacuum pump connected to the mixing process stage and the mixing space is determined, and the vacuum degree control relationship of the vacuum pump is established; the holding control parameters of the vacuum holding stage are adjusted according to the vacuum degree influence index and the vacuum degree control relationship to complete the first optimization.

[0008] In a possible implementation, after generating the initial mixed state data, the following processing is also performed: determining whether the mixed raw material has undergone drying and preheating treatment; if so, collecting drying and preheating parameters, calling the pre-constructed preheating-air release relationship, analyzing the impact of drying and preheating treatment on the release of air adsorbed by the raw material, and optimizing the vacuum degree influence index; wherein, the preheating-air release relationship is constructed through training with preheating test samples and air release test samples.

[0009] In a possible implementation, byproduct prediction of the stirring process is performed based on the mixed raw materials and the stirring parameters. The analysis determines whether the byproducts contain gases that affect the vacuum level. A second optimization of the vacuum parameters is then performed based on the first optimization, involving the following steps: extracting information about each raw material in the mixed raw materials; performing integrated modeling of the relationship between stirring parameters and byproducts to generate a byproduct predictor; analyzing the stirring parameters using the byproduct predictor to output byproduct prediction information; if the byproduct prediction information contains gas, extracting the gas generation amount; and adjusting the holding control parameters of the vacuum holding stage based on the gas generation amount, completing the second optimization.

[0010] In a possible implementation, the following process is performed: the stirring parameters include at least stirring temperature, stirring speed, and stirring time.

[0011] In a possible implementation, information about each raw material in the mixed raw materials is extracted, and an integrated modeling of the relationship between stirring parameters and by-products is performed to generate a by-product predictor. The following processing is then performed: using the information about each raw material as constraints, historical mixing data is retrieved, including historical stirring parameters and historical by-product data; the first triggering influence relationship between stirring temperature and by-products is analyzed using the historical stirring parameters and historical by-product data; based on the first triggering influence relationship, the influence weights of stirring speed and stirring time on by-products are analyzed using the historical stirring parameters and historical by-product data, and a speed weight relationship and a time weight relationship are established; the by-product predictor is established using the first triggering influence relationship, the speed weight relationship, and the time weight relationship.

[0012] In a possible implementation, after performing a second optimization of the vacuum parameters based on the first optimization, the following processing is also performed: vacuum degree control is performed in the mixing process stage using the second optimized parameters, and vacuum degree is continuously detected in the vacuum holding stage, and dynamic optimization control is performed based on the detection results.

[0013] This application also provides a parameter optimization device for mineral casting equipment, comprising: a parameter acquisition module for acquiring mixed raw materials, initial vacuum parameters, and stirring parameters during the mixing process stage of the mineral casting process; a vacuum parameter primary optimization module for detecting the initial mixing state of the mixed raw materials, predicting the vacuum degree influence index during the mixing process based on the stirring parameters, and performing primary optimization of the initial vacuum parameters; and a vacuum parameter secondary optimization module for predicting by-products of the stirring process based on the mixed raw materials and the stirring parameters, analyzing whether the by-products contain gases that affect the vacuum degree, and performing secondary optimization of the vacuum parameters based on the primary optimization.

[0014] This application also provides a computer-readable storage medium, including: a computer program stored thereon that, when executed by a processor, implements a parameter optimization method for mineral casting equipment.

[0015] The proposed parameter optimization method, apparatus, and medium for mineral casting equipment, as described in this application, first collects the mixed raw materials, initial vacuum parameters, and stirring parameters during the mixing stage of the mineral casting process. Then, the initial mixing state of the mixed raw materials is detected. Combined with the stirring parameters, the vacuum degree influence index during the mixing process is predicted, and a first optimization of the initial vacuum parameters is performed. Finally, based on the mixed raw materials and the stirring parameters, the by-products of the stirring process are predicted, and it is analyzed whether the by-products contain gases that affect the vacuum degree. A second optimization of the vacuum parameters is then performed based on the first optimization. This achieves the technical effect of improving the accuracy of vacuum parameter control, thereby improving the quality stability of mineral castings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the apparatus according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a flowchart illustrating a parameter optimization method for mineral casting equipment provided in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of the structure of a parameter optimization device for mineral casting equipment provided in an embodiment of this application.

[0019] Explanation of reference numerals in the attached diagram: Parameter acquisition module 10, Vacuum parameter primary optimization module 20, Vacuum parameter secondary optimization module 30. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or apparatuses. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a parameter optimization method for mineral casting equipment, such as... Figure 1 As shown, the method includes: Step S100: Collect the mixing raw materials, initialize vacuum parameters and stirring parameters in the mixing process stage of the mineral casting process.

[0024] Specifically, mineral castings are castings with a certain shape and properties made primarily from mineral raw materials through specific casting processes. They are commonly used in machinery manufacturing, electronic equipment, and other fields, and have advantages such as low cost and good shock absorption. The mixing process is an important step in the mineral casting process, carried out using mineral casting equipment. It mainly involves mixing various mineral raw materials in a certain proportion to ensure uniform distribution, providing qualified mixed raw materials for subsequent molding and solidification processes.

[0025] Raw material collection equipment, such as an automatic feeder with weighing function, is used to collect and transport various mineral raw materials, such as quartz sand and feldspar powder, into a mixing container according to a pre-set raw material ratio. At the same time, sensors, such as a laser particle size analyzer, are used to detect and record the particle size distribution of the collected mixed raw materials in real time. The particle size distribution affects parameters such as subsequent mixing effect and vacuum degree.

[0026] An initial vacuum level is set using a vacuum control system, such as a vacuum pump unit controlled by a programmable logic controller (PLC). This value is initially determined based on the type and size of the mineral casting and past experience data. Simultaneously, a time threshold for reaching the target vacuum level is set to ensure the required vacuum environment is achieved within a reasonable timeframe. The vacuum level and the time to reach the target vacuum level affect the removal of air and moisture during the mineral casting process, thus impacting the quality of the casting.

[0027] Using the control panel of the mixing equipment, parameters such as mixing speed, mixing time, and mixing direction are set. These parameters determine the uniformity and mixing effect of the mixed materials. The mixing speed is controlled by a frequency converter; the mixing time is set according to the characteristics of the raw materials and the mixing requirements; the mixing direction can be set to forward, reverse, or alternating forward and reverse to achieve more uniform mixing.

[0028] Step S200: Initial mixing state detection is performed on the mixed raw materials, and the vacuum degree influence index during the mixing process is predicted in combination with the stirring parameters. Then, the initial vacuum parameters are optimized once.

[0029] Specifically, various testing devices are used to assess the initial state of the mixed raw materials. For example, a specific surface area analyzer is used to measure the specific surface area of ​​the mixed raw materials. Specific surface area refers to the total area per unit mass of material. In mineral casting, specific surface area reflects the fineness and surface activity of the raw material particles. A larger specific surface area indicates finer particles and stronger surface adsorption capacity, potentially leading to the adsorption of more air and moisture. For instance, a moisture content analyzer is used to quickly determine the moisture content of the mixed raw materials. Based on specific physical principles, such as capacitive or resistive principles, moisture content analyzers can accurately determine the moisture content of the raw materials in a short time. Moisture content affects the physicochemical reactions during mixing and changes in vacuum levels. Simultaneously, a density measuring device can be used to measure the bulk density and true density of the mixed raw materials. Bulk density reflects the compactness of the raw materials in their natural stacking state, while true density reflects the density of the raw materials themselves. The difference between the two reflects the pore structure of the raw materials, which affects the retention of air within the raw materials, thus impacting vacuum levels.

[0030] A comprehensive analysis was conducted using computer simulation software and a pre-established model, incorporating stirring parameters. This model integrated initial state data such as specific surface area, moisture content, and density, as well as stirring parameters like stirring speed and time, considering their interactions and their impact on factors such as air escape and moisture evaporation during mixing. By simulating the mixing process under different parameter combinations, the dynamic trend of vacuum level changes and key influencing indicators, such as the vacuum level fluctuation range and the time to reach a stable vacuum level, were predicted.

[0031] Based on the predicted vacuum level impact indicators, the initial vacuum parameters are adjusted through the intelligent feedback adjustment mechanism of the vacuum control system. The vacuum control system receives simulated prediction results and actual detected vacuum level data in real time, and uses control algorithms, such as fuzzy control or neural network control algorithms, for analysis and decision-making. For example, if the prediction results indicate that the vacuum level will fluctuate significantly at a certain stage during the mixing process and may fall below the set value, the system will automatically increase the pumping power of the vacuum pump to increase the pumping volume; simultaneously, based on the timing and magnitude of the fluctuations, the opening of the vacuum valves is adjusted in advance to smooth the vacuum level change curve, ensuring that the vacuum level remains stable within the set optimal range throughout the mixing process.

[0032] In one possible implementation, the initial mixing state of the mixed raw materials is detected, and the influence index of vacuum degree during the mixing process is predicted in conjunction with the stirring parameters. The initial vacuum parameters are then optimized once. Step S200 further includes step S210, which detects the specific surface area, internal porosity, and raw material moisture content of the mixed raw materials to generate initial mixing state data. Specifically, a BET specific surface area analyzer is used. This instrument is based on the principle of low-temperature nitrogen adsorption. By measuring the amount of nitrogen adsorbed by the solid under different relative pressures, the specific surface area of ​​the mixed raw materials is calculated using the BET equation. For example, a certain amount of mixed raw material sample is placed in the sample tube of the analyzer, and an adsorption-desorption experiment is performed at liquid nitrogen temperature. The instrument automatically records the adsorption data and calculates the specific surface area value.

[0033] A mercury intrusion porosimetry (MIP) pore structure analyzer utilizes the non-wetting property of mercury on solid surfaces to force mercury into the pores of a mixed raw material under external pressure. By measuring the volume of mercury intruded at different pressures and applying the Washburn equation, parameters such as pore size distribution and porosity of the mixed raw material are obtained. For example, the mixed raw material sample is placed in the sample chamber of the analyzer, the pressure is gradually increased, and the amount of mercury intruded at each pressure point is recorded, thereby constructing a pore structure characteristic curve.

[0034] An infrared moisture analyzer is used. This instrument is based on the principle of infrared heating. It rapidly heats the mixed raw material sample through infrared radiation, causing the moisture in the sample to evaporate. The sensor detects the change in sample weight during the moisture evaporation process, thereby calculating the moisture content of the raw material. For example, a small amount of mixed raw material sample is placed in the sample pan of the instrument, the heating temperature and time are set, and the instrument automatically completes the heating and measurement process, displaying the moisture value of the sample.

[0035] The results of the above-mentioned specific surface area, internal porosity, and raw material moisture detection are integrated to form an initial mixed state dataset containing multiple parameters. This data comprehensively reflects the initial physical properties of the mixed raw materials, providing a foundation for subsequent analysis and simulation.

[0036] Step S220: Construct a mixing twin for the mixing process stage. Combine the initial mixing state data, the mixing parameters, and the quantity of raw materials mixed to perform twin simulation, analyzing the simulation parameters for the release of water vapor and air adsorbed by the raw materials. Specifically, using Computer-Aided Engineering (CAE) software, a virtual model highly similar to the actual mixing process, i.e., the mixing twin, is constructed based on the actual mixing equipment and mixing process conditions. This model accurately simulates the geometry of the mixing container, the shape and movement of the mixing blades, and the physical properties of the mixed raw materials. For example, by inputting parameters such as the dimensions of the mixing container, the number, angle, and rotational speed of the mixing blades, as well as the physical properties of the mixed raw materials such as density and viscosity, a three-dimensional mixing twin model is generated.

[0037] Initial mixing state data, stirring parameters, and raw material mixing quantities are imported into a stirring twin model for multiphysics coupled simulation. The simulation integrates multiple physical processes such as fluid dynamics, heat transfer, and mass transfer to simulate the motion and mixing of the raw materials during stirring, as well as the release of water vapor and adsorbed air. For example, by setting different boundary and initial conditions, the simulation measures the shearing effect of the stirring paddle rotation on the mixed materials and how this effect promotes the evaporation of moisture and the escape of adsorbed air from within the raw materials.

[0038] Parameters related to the release of water vapor and adsorbed air from the simulation results were extracted, such as the release rate, the release amount over time, and the distribution of the release area. These parameters reflect the release patterns of water vapor and adsorbed air under given initial mixing and stirring conditions.

[0039] Step S230: Determine the initial vacuum level corresponding to the initialization vacuum parameters. Analyze the impact of water vapor and adsorbed air from raw materials on the target vacuum level based on the release simulation parameters, and generate the vacuum level influence index. Specifically, initialization vacuum parameters are set according to the requirements and experience of mineral casting processes. Combined with the release simulation parameters, the impact of water vapor and adsorbed air from raw materials on the initial vacuum level is analyzed. Considering factors such as the amount of gas released, the release rate, and the pumping capacity of the vacuum system, the change in vacuum level during stirring is calculated. For example, based on the release rates of water vapor and adsorbed air obtained from the release simulation, combined with the pumping rate of the vacuum pump and the stirring time, a kinetic model of vacuum level change is established to predict the vacuum level values ​​at different time points.

[0040] Based on the above analysis, a series of indicators were generated to quantify the impact of vacuum level, such as vacuum level fluctuation range, maximum vacuum level drop, and time to reach stable vacuum level. These indicators reflect the degree of influence of water vapor and adsorbed air release on vacuum level.

[0041] Step S240: Optimize the initial vacuum parameters according to the vacuum degree influence index to complete one optimization. Specifically, an optimization algorithm, such as a genetic algorithm or particle swarm optimization algorithm, is used to optimize the initial vacuum parameters according to the vacuum degree influence index. For example, a genetic algorithm gradually optimizes the combination of vacuum parameters by simulating selection, crossover, and mutation operations in the biological evolution process, thereby improving the stability of the vacuum degree. The initial vacuum parameters are adjusted based on the calculation results of the optimization algorithm. For example, if the analysis finds that the vacuum degree fluctuation range is too large, the vacuum parameters can be optimized by increasing the pumping power of the vacuum pump or adjusting the opening of the vacuum valve, reducing the vacuum degree fluctuation range to an allowable range. After multiple iterative optimizations, when the vacuum degree influence index meets the preset process requirements, one optimization is considered complete. The vacuum parameters obtained at this time are the optimized parameters, which can be used in actual mineral casting mixing processes.

[0042] This approach, by comprehensively monitoring the initial mixing state of the raw materials and constructing a stirring twin for simulation analysis, can more accurately predict the release of water vapor and adsorbed air from the raw materials, thus more accurately analyzing their impact on vacuum levels. Based on these accurate analytical results, optimizing vacuum parameters can improve the accuracy of vacuum control and ensure that the mixing process takes place in a stable vacuum environment.

[0043] In one possible implementation, the initial vacuum parameters are optimized based on the vacuum degree influence index to complete one optimization. Step S240 further includes step S241, parsing the initial vacuum parameters and extracting the vacuum holding stage from multiple vacuum control stages. Specifically, the initial vacuum parameters are the set of initial settings for the entire vacuum control process, including parameters for each stage such as the pre-evacuation stage, the slow / fine evacuation stage, and the vacuum holding stage. These parameters include, but are not limited to, the initial vacuum degree, target vacuum degree, pumping rate, and duration for each stage. For example, in the pre-evacuation stage, the initial vacuum degree is atmospheric pressure (10¹³ mbar), the target vacuum degree is set to 200 mbar, and the pumping rate is relatively fast, such as 50 mbar / min; in the slow / fine evacuation stage, the initial vacuum degree is 200 mbar, the target vacuum degree is 50 mbar, and the pumping rate is relatively slow, such as 10 mbar / min; the vacuum holding stage maintains the vacuum degree for a period of time after reaching the target vacuum degree of 50 mbar.

[0044] After fully analyzing and initializing the vacuum parameters, the vacuum holding stage was identified within the entire vacuum process. The vacuum holding stage is the core stage for degassing. After reaching the target vacuum level, bubbles in the mixed raw materials will gradually expand and escape under low pressure, while the stirring process will promote better dispersion and expulsion of the bubbles.

[0045] Step S242: Determine the vacuum pumps connected to the mixing space in the mixing process stage and establish the vacuum degree control relationship of the vacuum pumps. Specifically, in the mineral casting mixing process, the mixing space can be connected to one or more vacuum pumps to achieve vacuum degree control and adjustment. Select appropriate types and specifications of vacuum pumps based on the size of the mixing space, process requirements, and the required vacuum degree range. For example, for small mixing spaces, a single rotary vane vacuum pump may suffice; for large mixing equipment, it may be necessary to combine different types of vacuum pumps, such as Roots pumps and diffusion pumps, to achieve higher vacuum degrees and larger pumping volumes. The vacuum pumps connected to the mixing space are determined by consulting equipment layout diagrams, process specifications, or conducting actual site surveys.

[0046] Vacuum level control of a vacuum pump involves factors such as the pumping characteristics of the pump, the opening adjustment of the vacuum valves, and the feedback signal from the vacuum sensor. For example, by installing vacuum valves at the inlet and outlet of the vacuum pump, and adjusting the valve opening based on the real-time vacuum level measured by the vacuum sensor in the mixing space, the pumping volume of the vacuum pump can be controlled, thus achieving precise adjustment of the vacuum level.

[0047] Step S243: Based on the vacuum degree influence index and the vacuum degree control relationship, adjust the holding control parameters of the vacuum holding stage to complete the first optimization. Specifically, based on the vacuum degree influence index and the established vacuum degree control relationship, specifically adjust the holding control parameters of the vacuum holding stage. Holding control parameters include the pumping power of the vacuum pump and the opening degree of the vacuum valve. For example, if the large vacuum degree fluctuation is caused by a sudden increase in the amount of gas due to the release of water vapor and adsorbed air, the pumping power of the vacuum pump can be appropriately increased to accelerate the gas discharge rate; simultaneously, the opening degree of the vacuum valve is dynamically adjusted according to the changes in vacuum degree to ensure that the vacuum degree is maintained more stably near the target value.

[0048] After adjusting the holding control parameters, another simulation is performed to observe whether the change in vacuum level meets the process requirements. If the vacuum level fluctuation range decreases to the allowable range and can be stably maintained near the target vacuum level, then one optimization is considered complete. The holding control parameters obtained at this point are the optimized parameters and can be used in subsequent actual production.

[0049] This implementation method analyzes the initial vacuum parameters, extracts the key vacuum holding stage, and optimizes and adjusts it to effectively reduce the fluctuation range of vacuum degree during the holding stage. This provides a more stable vacuum environment for the mineral casting mixing process, better promotes the removal of air bubbles in the mixed raw materials, thereby improving the density of the casting, reducing internal defects, and enhancing the mechanical properties and appearance quality of the casting.

[0050] In one possible implementation, after generating initial mixing state data, step S200 further includes step S250, determining whether the mixed raw materials have undergone drying and preheating treatment. Specifically, drying and preheating treatment is used to remove moisture from the raw materials, improve their physical properties, and promote certain chemical reactions. After generating initial mixing state data, it is further determined whether the currently used mixed raw materials have undergone this drying and preheating treatment. This determination process can be implemented in various ways. For example, the processing record of this batch of raw materials can be queried in the production management system, which will indicate whether drying and preheating treatment has been performed and the specific processing parameters; alternatively, special signs can be set up at the production site, and operators can input information about whether the raw materials have undergone drying and preheating treatment into the system based on the signs. Determining whether the raw materials have undergone drying and preheating treatment provides accurate basic information for subsequent process control and optimization, because whether or not drying and preheating treatment is performed will significantly affect the release of adsorbed air from the raw materials, thereby affecting the control of vacuum.

[0051] Step S260: If yes, collect drying and preheating parameters, call the pre-constructed preheating-air release relationship, analyze the impact of drying and preheating treatment on the release of adsorbed air from the raw materials, and optimize the vacuum degree influence index; wherein, the preheating-air release relationship is constructed through training with preheating test samples and air release test samples. Specifically, after determining that the mixed raw materials have undergone drying and preheating treatment, relevant drying and preheating parameters need to be collected. These parameters include drying temperature, preheating time, heating method, etc. Different raw materials will undergo different physical and chemical changes at different drying temperatures. For example, some metal powders may undergo oxidation reactions at high temperatures, while some organic binders may decompose at specific temperatures. Too short a preheating time may not be able to fully remove moisture from the raw materials and achieve a uniform temperature distribution, while too long a preheating time may lead to energy waste and changes in raw material properties. The heating method also affects the drying and preheating effect. Heating methods include hot air circulation heating, infrared heating, resistance heating, etc., and different heating methods have different heating efficiencies and uniformities. By collecting these drying and preheating parameters, the actual situation of the raw materials during the drying and preheating process can be comprehensively obtained.

[0052] The preheating-air release relationship model was constructed through training with preheating test samples and air release test samples. In building this model, a series of representative preheating test samples were prepared, including mixed raw materials of different types, particle size distributions, and initial moisture contents. Each preheating test sample underwent drying preheating treatment under different conditions, and parameters such as drying temperature and preheating time were recorded. Then, using air release testing equipment and methods, the air release of each preheated sample was measured in subsequent processes, including air release rate and total release data. Using this large amount of test data, machine learning algorithms were used for training to construct a model that accurately describes the relationship between preheating parameters and the release of adsorbed air from the raw materials—the preheating-air release relationship.

[0053] The collected actual drying and preheating parameters are input into the preheating-air release relationship model. Based on the pre-trained algorithm and parameters, the model outputs the predicted release results of adsorbed air from the raw material. By comparing and analyzing the adsorbed air release of the raw material without drying and preheating treatment, the degree and pattern of influence of drying and preheating treatment on the adsorbed air release of the raw material are determined.

[0054] Based on the analysis of the impact of drying and preheating treatment on the release of adsorbed air from raw materials, the vacuum degree impact index was optimized. The vacuum degree impact index is a key parameter used to measure the influence of water vapor and the release of adsorbed air from raw materials on the vacuum degree. For example, if the analysis shows that drying and preheating treatment reduces the release of adsorbed air from raw materials, then when optimizing the vacuum degree impact index, the set value of the vacuum degree fluctuation range caused by the release of adsorbed air can be appropriately reduced. Simultaneously, based on the changes in the release rate, the pumping power of the vacuum pump and the opening adjustment strategy of the vacuum valve are adjusted so that the vacuum degree can be reached and maintained near the target value more quickly and stably. Through this targeted optimization, vacuum control can be made more precise and efficient, adapting to the characteristics of raw materials under different drying and preheating treatment conditions.

[0055] This approach determines whether the mixed raw materials have undergone drying and preheating treatment, and analyzes the impact of drying and preheating treatment on the release of adsorbed air from the raw materials. This allows for optimization of the vacuum degree impact index, enabling vacuum degree control to more accurately adapt to the actual state of the raw materials. It avoids problems such as excessive vacuum degree fluctuations or inaccurate control caused by changes in the release of adsorbed air from the raw materials due to the failure to consider drying and preheating treatment, thereby improving the stability and reliability of vacuum degree control.

[0056] Step S300: Based on the mixed raw materials and the stirring parameters, predict the by-products of the stirring process, analyze whether the by-products contain gases that affect the vacuum level, and perform a second optimization of the vacuum parameters based on the first optimization.

[0057] Specifically, by utilizing chemical reaction kinetics models and a material property database, combined with the composition of the mixed raw materials and stirring parameters, potential byproducts generated during the stirring process are predicted. Byproducts refer to substances produced in addition to the main products during chemical reactions or physical processes. In the stirring process of mineral casting, due to chemical reactions or physical changes between raw materials, some gaseous, liquid, or solid byproducts may be generated, some of which may affect the vacuum level. For example, certain mineral raw materials may undergo chemical reactions under specific stirring conditions, producing gaseous byproducts such as carbon dioxide and hydrogen. The material property database contains information on the chemical properties and reactivity of various mineral raw materials, providing basic data for byproduct prediction. Based on the physicochemical properties of the byproducts, their impact on the vacuum level is analyzed. For example, if the byproduct is gaseous and difficult to extract by the vacuum pump, or accumulates in the mixing container, it will negatively affect the vacuum level; conversely, if the byproduct is solid or liquid and does not volatilize into the gas phase, its impact on the vacuum level is relatively small. Based on the analysis results of the impact of byproducts on the vacuum level, the vacuum parameters are further optimized and adjusted through the vacuum control system. For example, if a large amount of gaseous byproducts that affect the vacuum level are predicted to be generated, the pumping capacity of the vacuum pump can be further increased, or an auxiliary exhaust device can be added to ensure that a stable vacuum environment is maintained during the stirring process.

[0058] In one possible implementation, byproduct prediction during the stirring process is performed based on the mixed raw materials and the stirring parameters. The analysis determines whether the byproducts contain gases that affect the vacuum level. A secondary optimization of the vacuum parameters is then performed based on the initial optimization. Step S300 further includes step S310, which extracts information about each raw material in the mixed raw materials, performs integrated modeling of the relationship between stirring parameters and byproducts, and generates a byproduct predictor. The stirring parameters include at least stirring temperature, stirring speed, and stirring time. Specifically, in the mineral casting mixing process, the mixed raw materials consist of various raw materials with different compositions and properties. This raw material information includes, but is not limited to, the type of raw material, chemical composition, particle size distribution, density, and specific surface area. This raw material information is extracted using detection equipment and analytical techniques, such as X-ray fluorescence spectrometry (XRF) and laser particle size analyzers. The physical and chemical properties of different raw materials directly affect the formation of byproducts during the stirring process.

[0059] Stirring parameters play a crucial role in the stirring process, including at least stirring temperature, stirring speed, and stirring time. Stirring temperature affects the chemical reaction rate and physical state changes of the raw materials; for example, higher temperatures may accelerate the decomposition of binders or promote oxidation reactions between metal powders. Stirring speed determines the degree of mixing and the magnitude of shear force between raw materials; different stirring speeds may lead to different particle agglomeration or dispersion. Stirring time affects the completeness of the reaction and the uniformity of mixing. Extensive experiments were conducted under different combinations of stirring parameters, and information on the generated byproducts, including their type, quantity, and morphology, was collected. Using this experimental data, machine learning algorithms were employed for ensemble modeling.

[0060] After relational integration modeling, a tool is generated that can predict byproducts generated during the mixing process based on the input mixed raw material information and mixing parameters; this is called a byproduct predictor. This predictor can be a software program or algorithm model that can quickly predict new mixing process conditions, thereby providing a basis for vacuum parameter optimization.

[0061] Step S320: The byproduct predictor analyzes the stirring parameters and outputs byproduct prediction information. Specifically, the stirring parameters set or planned for use in actual production, along with information on the mixed raw materials, are input into the byproduct predictor. Based on a pre-established relationship model between the stirring parameters and byproducts, the byproduct predictor quickly calculates and analyzes this input information and outputs byproduct prediction information. This prediction information includes the types of byproducts that may be generated, such as whether gaseous, solid impurities, or liquid byproducts will be generated, and the approximate probability or expected quantity range of each byproduct.

[0062] Step S330: If the by-product prediction information includes gas, extract the gas generation amount. Specifically, when the by-product prediction information indicates that gas will be generated during the stirring process, further extract the gas generation amount. This can be achieved by setting a corresponding calculation module in the by-product predictor. This module calculates the gas generation amount based on the stirring parameters and mixed raw material information, combined with a pre-established model relationship. Different amounts of gas have different degrees of impact on the vacuum level. For example, a small amount of gas has a relatively small impact on the vacuum level, while a large amount of gas generation will cause a sharp drop in the vacuum level, affecting the stability of the entire mineral casting mixing process and product quality.

[0063] Step S340: Based on the gas production volume, and building upon the initial optimization, the holding control parameters for the vacuum holding stage are further adjusted to complete the secondary optimization. Specifically, the holding control parameters for the vacuum holding stage are adjusted specifically according to the extracted gas production volume. The vacuum holding stage requires maintaining a stable vacuum level to promote bubble removal and prevent gas re-entry. If the gas production volume is large, the pumping power of the vacuum pump needs to be increased to extract the generated gas more quickly and maintain a stable vacuum level; simultaneously, the opening of the vacuum valve should be appropriately adjusted to control the gas discharge rate and avoid excessive vacuum fluctuations due to rapid gas discharge. Conversely, if the gas production volume is small, the pumping power of the vacuum pump can be appropriately reduced to save energy and reduce equipment wear.

[0064] This approach, by adjusting the control parameters during the vacuum holding stage, can more accurately adapt to various situations that may occur during actual stirring, further improving the accuracy and stability of vacuum control and providing a more reliable vacuum environment guarantee for mineral casting mixing processes.

[0065] In one possible implementation, information about each raw material in the mixed raw material is extracted, and an integrated modeling of the relationship between stirring parameters and by-products is performed to generate a by-product predictor. Step S310 further includes step S311, which retrieves historical mixing data, including historical stirring parameters and historical by-product data, using the information about each raw material as constraints. Specifically, the information about each raw material is used as a constraint to filter data related to the current mixed raw material from a large amount of historical data. Enterprises or research institutions have accumulated a large amount of historical data in long-term mineral casting mixing process practices. This data includes historical stirring parameters and historical by-product data. Through database queries, data mining, and other technical means, historical mixing data that meets the requirements is retrieved from the historical data storage system according to the set constraints of each raw material information. For example, if the current mixed raw material contains metal powder of a specific type and particle size range, relevant parameters and by-product data from past stirring with similar metal powders are retrieved.

[0066] Step S312 involves analyzing the initial triggering effect of stirring temperature on byproducts using historical stirring parameters and historical byproduct data. Specifically, stirring temperature plays a crucial triggering role in the stirring process. Different temperatures affect the chemical reaction rate, physical state changes, and intermolecular interactions of the raw materials. For example, higher temperatures may accelerate the decomposition of binders, leading to the generation of gaseous byproducts; or promote oxidation reactions between metal powders, generating solid oxide impurities. By analyzing the temperature data in historical stirring parameters and the corresponding historical byproduct data, the intrinsic relationship between stirring temperature and byproduct formation is identified, determining the temperature range within which certain byproducts are triggered, thus establishing the initial triggering effect relationship between stirring temperature and byproducts.

[0067] Statistical analysis methods can be used, such as plotting a scatter plot of temperature versus the frequency or quantity of byproducts, to observe the distribution trend of the data and identify the correlation between temperature and byproducts. Alternatively, classification algorithms from machine learning can be used, with temperature as an input feature and byproduct type as an output label, to train a model to predict the types of byproducts that may be generated at different temperatures.

[0068] Step S313: Based on the first triggering influence relationship, the influence weights of stirring speed and stirring time on by-products are analyzed by combining historical stirring parameters and historical by-product data, establishing speed-weighted relationships and time-weighted relationships. Specifically, stirring speed determines the degree of mixing and shear force between raw materials. Different stirring speeds may lead to different agglomeration or dispersion of raw material particles, thus affecting the progress of chemical reactions and the formation of by-products. Based on the known first triggering influence relationship between stirring temperature and by-products, the influence of changes in stirring speed in historical data on the amount and type of by-products is further analyzed. For example, when the stirring temperature has reached the condition for triggering the formation of a certain by-product, increasing the stirring speed may make the reaction more complete, leading to an increase in the amount of by-products; or it may change the reaction path, generating different types of by-products. By quantitatively analyzing the relationship between stirring speed and by-products, the influence weight of stirring speed on by-products is determined, and a speed-weighted relationship is established.

[0069] Stirring time affects the completeness of the reaction and the uniformity of mixing. Longer stirring times may lead to a more thorough reaction, but they can also cause side reactions and increase the formation of byproducts. Similarly, based on the initial triggering effect, the influence of changes in stirring time on byproducts in historical data is analyzed. For example, at a specific stirring temperature, with increasing stirring time, the formation of certain byproducts may initially increase and then stabilize, or exhibit other trends. By establishing mathematical models or using statistical analysis methods, the influence weight of stirring time on byproducts is determined, and a time-weighted relationship is established.

[0070] Step S314: Establish the by-product predictor based on the first triggering influence relationship, the speed weight relationship, and the time weight relationship. Specifically, integrate the analyzed first triggering influence relationship between stirring temperature and by-products, the influence weight relationship of stirring speed on by-products, and the influence weight relationship of stirring time on by-products. Multivariate regression analysis, neural networks, and other modeling methods can be used to construct a by-product prediction model that comprehensively considers the three main stirring parameters: stirring temperature, stirring speed, and stirring time. The integrated prediction model is then encapsulated into an executable program or algorithm module, i.e., the by-product predictor.

[0071] In one possible implementation, after performing a secondary optimization of the vacuum parameters based on the primary optimization, the device further includes: controlling the vacuum level in the mixing process stage with the secondary optimized parameters, continuously detecting the vacuum level in the vacuum holding stage, and performing dynamic optimization control based on the detection results.

[0072] Specifically, the vacuum level is controlled during the mixing process based on the vacuum parameters obtained from secondary optimization. By adjusting parameters such as the pumping speed of the vacuum pump and the opening degree of the valves, the vacuum level in the mixing chamber is stabilized at the set value after secondary optimization. For example, a closed-loop control system is used to compare the feedback signal from the vacuum level measuring instrument with the set value, and automatically adjust the operating state of the vacuum pump according to the magnitude of the deviation, thereby achieving precise control of the vacuum level.

[0073] During the vacuum maintenance phase, a vacuum sensor continuously monitors the vacuum level within the mixing chamber. Simultaneously, the detected vacuum data is transmitted in real-time to the control system. For example, an online vacuum sensor can be installed at a key location within the mixing chamber, and the data is transmitted to a computer in the control center via a data cable, enabling real-time monitoring and recording of the vacuum level.

[0074] During the vacuum holding phase, the vacuum level may fluctuate due to various factors, such as minor leaks in the equipment. Based on continuously monitored vacuum levels, the control system analyzes the trend in real time and compares it with the optimized setpoint. If the vacuum level deviates from the setpoint, the control system automatically adjusts relevant parameters, such as the vacuum pump's pumping speed and valve opening, according to a preset control strategy to bring the vacuum level back to near the setpoint. A proportional-integral-derivative (PID) control strategy can be used, calculating the control input based on the vacuum level deviation and its rate of change, and then adjusting the vacuum pump or valves. For example, when the vacuum level is lower than the setpoint, the pumping speed of the vacuum pump is increased or the valve opening is decreased to improve the vacuum level; when the vacuum level is higher than the setpoint, the pumping speed is decreased or the valve opening is increased to decrease the vacuum level. Through dynamic optimization control, the vacuum level is ensured to remain within the optimal range throughout the vacuum holding phase, improving the stability of the mixing process and product quality.

[0075] In actual production, the production environment may change; fluctuations in factors such as temperature, humidity, and air pressure can affect the performance of the vacuum system. This approach, through dynamic optimization control, can monitor changes in vacuum level in real time and automatically adjust control parameters based on the detection results, ensuring that the vacuum level remains within the set range. This enhances the process's adaptability to changes in the production environment and guarantees stable production.

[0076] This application employs techniques such as collecting mixed raw materials during the mixing stage of mineral casting, simultaneously acquiring initial vacuum and stirring parameters, detecting the initial mixing state of the raw materials, predicting the impact of stirring parameters on vacuum levels during mixing, optimizing the initial vacuum parameters, predicting byproducts generated during stirring based on the mixed raw materials and stirring parameters, determining whether the byproducts contain gases that affect vacuum levels, and performing secondary optimization of vacuum parameters based on the first optimization. These techniques solve the technical problem of inaccurate vacuum parameter control in existing mineral casting mixing stage process optimization, achieving the technical effect of improving the accuracy of vacuum parameter control and thus improving the quality stability of mineral castings.

[0077] In the above text, refer to Figure 1 A parameter optimization method for mineral casting equipment according to embodiments of the present invention has been described in detail. Next, reference will be made to... Figure 2 A parameter optimization apparatus for mineral casting equipment according to an embodiment of the present invention is described.

[0078] The parameter optimization device for mineral casting equipment according to embodiments of the present invention addresses the technical problem of inaccurate vacuum parameter control in existing mineral casting mixing stage process optimization, thereby improving the accuracy of vacuum parameter control and thus enhancing the quality stability of mineral castings. The parameter optimization device for mineral casting equipment includes: a parameter acquisition module 10, a primary vacuum parameter optimization module 20, and a secondary vacuum parameter optimization module 30.

[0079] The parameter acquisition module 10 is used to acquire the mixed raw materials, initial vacuum parameters, and stirring parameters in the mixing process stage of the mineral casting process; the vacuum parameter primary optimization module 20 is used to detect the initial mixing state of the mixed raw materials, predict the vacuum degree influence index in the mixing process in combination with the stirring parameters, and perform primary optimization of the initial vacuum parameters; the vacuum parameter secondary optimization module 30 is used to predict the by-products of the stirring process based on the mixed raw materials and the stirring parameters, analyze whether the by-products contain gases that affect the vacuum degree, and perform secondary optimization of the vacuum parameters based on the primary optimization.

[0080] The detailed description of the specific configuration of the vacuum parameter primary optimization module 20 is explained as follows: As mentioned above, the initial mixing state of the mixed raw materials is detected, and the vacuum degree influence index during the mixing process is predicted in combination with the stirring parameters. The primary optimization of the initial vacuum parameters is then performed. The vacuum parameter primary optimization module 20 may further include: an initial mixing state detection unit for detecting the specific surface area, internal porosity, and raw material humidity of the mixed raw materials to generate initial mixing state data; a twin simulation unit for constructing a stirring twin of the mixing process stage, performing twin simulation in combination with the initial mixing state data, the stirring parameters, and the raw material mixing quantity, and analyzing the simulation parameters for the release of water vapor and adsorbed air from the raw materials; a vacuum degree influence index generation unit for determining the initial vacuum degree corresponding to the initial vacuum parameters, analyzing the influence level of the release of water vapor and adsorbed air from the raw materials on the target vacuum degree based on the release simulation parameters, and generating the vacuum degree influence index; and a primary optimization unit for optimizing the initial vacuum parameters according to the vacuum degree influence index to complete the primary optimization.

[0081] Specifically, the initial vacuum parameters are optimized based on the vacuum degree influence index to complete one optimization. The first optimization unit may further include: a vacuum holding stage extraction subunit for parsing the initial vacuum parameters and extracting the vacuum holding stage from multiple vacuum control stages; a vacuum degree control relationship establishment subunit for determining the vacuum pump connected to the mixing process stage and the mixing space, and establishing the vacuum degree control relationship of the vacuum pump; and a holding control parameter adjustment subunit for adjusting the holding control parameters of the vacuum holding stage according to the vacuum degree influence index and the vacuum degree control relationship to complete the first optimization.

[0082] After generating the initial mixed state data, the vacuum parameter optimization module 20 may further include: a judgment unit for judging whether the mixed raw material has undergone drying and preheating treatment; and a vacuum degree influence index optimization unit for, if drying and preheating treatment has been performed, collecting drying and preheating parameters, calling the pre-constructed preheating-air release relationship, analyzing the influence of drying and preheating treatment on the release of air adsorbed by the raw material, and performing the optimization of the vacuum degree influence index; wherein, the preheating-air release relationship is constructed through training using preheating test samples and air release test samples.

[0083] The detailed description of the specific configuration of the vacuum parameter secondary optimization module 30 is as follows: As mentioned above, based on the mixed raw materials and the stirring parameters, the by-products of the stirring process are predicted, and it is analyzed whether the by-products contain gases that affect the vacuum level. On the basis of the first optimization, the vacuum parameter secondary optimization is performed. The vacuum parameter secondary optimization module 30 may further include: a by-product predictor generation unit for extracting information of each raw material in the mixed raw materials, performing integrated modeling of the relationship between stirring parameters and by-products, and generating a by-product predictor; a by-product prediction unit for analyzing the stirring parameters with the by-product predictor and outputting by-product prediction information; a gas generation extraction unit for extracting the gas generation amount if the by-product prediction information contains gas; and a secondary optimization unit for further adjusting the holding control parameters of the vacuum holding stage based on the gas generation amount, on the basis of the first optimization, to complete the secondary optimization.

[0084] The by-product predictor generation unit may further include: the stirring parameters include at least stirring temperature, stirring speed, and stirring time.

[0085] Specifically, the process involves extracting information about each raw material in the mixed raw materials, performing integrated modeling of the relationship between stirring parameters and by-products, and generating a by-product predictor. The by-product predictor generation unit may further include: a historical mixing data retrieval subunit for retrieving historical mixing data, including historical stirring parameters and historical by-product data, constrained by the information about each raw material; a first triggering influence relationship analysis subunit for analyzing the first triggering influence relationship between stirring temperature and by-products using historical stirring parameters and historical by-product data; a weighted relationship establishment subunit for analyzing the influence weights of stirring speed and stirring time on by-products based on the first triggering influence relationship and combining historical stirring parameters and historical by-product data, establishing a speed weighted relationship and a time weighted relationship; and a by-product predictor establishment subunit for establishing the by-product predictor using the first triggering influence relationship, the speed weighted relationship, and the time weighted relationship.

[0086] The device may further include a dynamic optimization control module that performs vacuum degree control in the mixing process stage with the secondary optimized parameters, and continuously detects vacuum degree in the vacuum holding stage, and performs dynamic optimization control based on the detection results.

[0087] The parameter optimization device for mineral casting equipment provided in this embodiment of the invention can execute the parameter optimization method for mineral casting equipment provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0088] Although this application makes various references to certain modules in the apparatus according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not intended to limit the scope of protection of this invention.

[0089] Based on the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor of an electronic device, can implement the parameter optimization method for mineral casting equipment as described in any of the foregoing embodiments.

[0090] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A parameter optimization method for mineral casting equipment, characterized in that, include: Collect the mixing raw materials, initialize vacuum parameters, and stir parameters in the mixing stage of the mineral casting process; The initial mixing state of the mixed raw materials is detected, and the influence index of vacuum degree during the mixing process is predicted in combination with the stirring parameters. Then, the initial vacuum parameters are optimized once. Based on the mixed raw materials and the stirring parameters, the by-products of the stirring process are predicted, and it is analyzed whether the by-products contain gases that affect the vacuum level. A second optimization of the vacuum parameters is then performed based on the first optimization. The process includes detecting the initial mixing state of the mixed raw materials, predicting the vacuum degree influence index during the mixing process based on the stirring parameters, and performing a first optimization of the initial vacuum parameters, including: The specific surface area, internal porosity, and moisture content of the mixed raw materials are measured to generate initial mixing state data; A stirring twin is constructed for the mixing process stage. Twin simulation is performed by combining the initial mixing state data, the stirring parameters, and the mixing quantity of raw materials to analyze the release simulation parameters of water vapor and adsorbed air from the raw materials. Among them, the release simulation parameters refer to the parameters related to the release of water vapor and adsorbed air from the raw materials, including the release rate, the change curve of release amount over time, and the distribution of release area. Determine the initial vacuum degree corresponding to the initialization vacuum parameters, analyze the impact of the release of water vapor and the release of air adsorbed by raw materials on the target vacuum degree based on the release simulation parameters, and generate the vacuum degree impact index. The initial vacuum parameters are optimized based on the vacuum degree influence index to complete one optimization.

2. The parameter optimization method for mineral casting equipment as described in claim 1, characterized in that, The initial vacuum parameters are optimized based on the vacuum degree influence index to complete one optimization, including: The initial vacuum parameters are analyzed to extract the vacuum holding phase from multiple vacuum control phases; Identify the vacuum pump connected to the mixing process stage and the mixing space, and establish the vacuum degree control relationship of the vacuum pump; Based on the vacuum degree influence index and the vacuum degree control relationship, the holding control parameters of the vacuum holding stage are adjusted to complete the first optimization.

3. The parameter optimization method for mineral casting equipment as described in claim 1, characterized in that, After generating the initial mixed state data, the following is also included: Determine whether the mixed raw materials have undergone drying and preheating treatment; If so, collect drying and preheating parameters, call the pre-constructed preheating-air release relationship, analyze the impact of drying and preheating treatment on the release of adsorbed air from raw materials, and optimize the vacuum degree influence index. The preheating-air release relationship is constructed through training using preheating test samples and air release test samples.

4. The parameter optimization method for mineral casting equipment as described in claim 1, characterized in that, Based on the mixed raw materials and the stirring parameters, the by-products of the stirring process are predicted, and it is analyzed whether the by-products contain gases that affect the vacuum level. A second optimization of the vacuum parameters is then performed based on the first optimization, including: Extract information about each raw material in the mixed raw materials, perform integrated modeling of the relationship between stirring parameters and by-products, and generate a by-product predictor; The byproduct predictor analyzes the stirring parameters and outputs byproduct prediction information. If the byproduct prediction information includes gas, extract the gas production amount; Based on the gas production rate, the holding control parameters during the vacuum holding stage are further adjusted on the basis of the first optimization to complete the second optimization.

5. The parameter optimization method for mineral casting equipment as described in claim 4, characterized in that, The stirring parameters include at least stirring temperature, stirring speed, and stirring time.

6. The parameter optimization method for mineral casting equipment as described in claim 5, characterized in that, Extract information about each raw material in the mixed raw material, perform integrated modeling of the relationship between stirring parameters and by-products, and generate a by-product predictor, including: Using the information on each raw material as a constraint, retrieve historical mixing data, including historical stirring parameters and historical by-product data; The relationship between stirring temperature and the first trigger effect of by-products was analyzed using historical stirring parameters and historical by-product data, respectively. Based on the first triggering influence relationship, the influence weights of stirring speed and stirring time on by-products are analyzed by combining historical stirring parameters and historical by-product data, and speed weight relationship and time weight relationship are established. The byproduct predictor is established based on the first triggering influence relationship, the speed weight relationship, and the time weight relationship.

7. The parameter optimization method for mineral casting equipment as described in claim 1, characterized in that, After performing a second optimization of the vacuum parameters based on the first optimization, it also includes: Vacuum control is performed during the mixing process using the optimized parameters, and vacuum level is continuously monitored during the vacuum holding phase. Dynamic optimization control is then implemented based on the monitoring results.

8. A parameter optimization device for mineral casting equipment, characterized in that, The apparatus is used to implement the parameter optimization method for mineral casting equipment according to any one of claims 1-7, the apparatus comprising: The parameter acquisition module is used to acquire the mixing raw materials, initial vacuum parameters, and stirring parameters in the mixing process stage of mineral casting. The vacuum parameter primary optimization module is used to detect the initial mixing state of the mixed raw materials, predict the vacuum degree influence index during the mixing process based on the stirring parameters, and perform the primary optimization of the initial vacuum parameters. The vacuum parameter secondary optimization module is used to predict the by-products of the stirring process based on the mixed raw materials and the stirring parameters, analyze whether the by-products contain gases that affect the vacuum level, and perform secondary optimization of the vacuum parameters based on the primary optimization.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the parameter optimization method for mineral casting equipment as described in any one of claims 1-7.

Images