A method and system for evaluating processability of lead-zinc tailings

Abstract

The application discloses a lead-zinc tailing processability evaluation method and system, relates to the technical field of tailing recycling, and comprises the following steps: obtaining a lead-zinc tailing sample, detecting the lead-zinc tailing sample, obtaining basic performance data corresponding to the lead-zinc tailing sample, inputting the basic performance data into a trained lead-zinc tailing process performance prediction model for prediction, obtaining process performance prediction information output by the lead-zinc tailing process performance prediction model, obtaining process requirement parameters of a target product, comparing the process performance prediction information with the process requirement parameters of the target product, obtaining a comparison result, generating a processability evaluation result of the lead-zinc tailing sample for the target product according to the comparison result, and establishing a prediction and evaluation system based on data driving, predicting the process performance of the lead-zinc tailing, and generating the processability evaluation conclusion. The application overcomes the limitations of traditional experience judgment, and improves the pertinence and economy of tailing resource utilization.

Description

Technical Field

[0001] This application relates to the field of tailings recycling technology, specifically to a method and system for evaluating the processability of lead-zinc tailings. Background Technology

[0002] Lead-zinc tailings are the main solid waste generated after lead-zinc ore is beneficiated and enriched for valuable metals. With the continuous development and utilization of lead-zinc mineral resources in my country, the amount of tailings stockpiled is constantly increasing, leading to increasingly serious environmental risks, land occupation, and resource waste. Large-scale, high-value resource utilization of lead-zinc tailings has become an inevitable requirement for promoting the green and circular development of the mining industry.

[0003] However, the resource utilization of lead-zinc tailings faces a core challenge: the technological performance of tailings is highly dependent on the properties of the raw ore, the beneficiation process, and the storage history, resulting in significant fluctuations in their physical, chemical, and mineralogical properties. This uncertainty directly determines the suitability and processing feasibility of tailings as a secondary resource in downstream applications such as building materials, backfill materials, or the recovery of valuable components. The evaluation methods for related technologies mainly rely on time-consuming experimental testing and small-scale pilot production, which suffer from problems such as long cycles, high costs, and delayed guidance, making it difficult to meet the industry's needs for large-scale consumption and rapid, precise ore blending.

[0004] In view of this, there is an urgent need for a technical solution that can connect the basic characteristic detection of lead-zinc tailings, the prediction of process performance, and the comparison of the process requirements of the target product to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for evaluating the processability of lead-zinc tailings, aiming to solve at least one of the technical problems existing in the prior art.

[0006] The technical solution of this application is: a method for evaluating the processability of lead-zinc tailings, the method comprising: Obtain lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples; The basic performance data is input into the trained lead-zinc tailings process performance prediction model for prediction, and the process performance prediction information output by the lead-zinc tailings process performance prediction model is obtained. Obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison result. Based on the comparison results, the processability evaluation results of the lead-zinc tailings sample for the target product are generated.

[0007] In some embodiments of this application, the step of testing the lead-zinc tailings sample to obtain the basic performance data corresponding to the lead-zinc tailings sample includes: The chemical composition parameters of the lead-zinc tailings sample were obtained by performing spectral analysis on the sample. Diffraction analysis was performed on the lead-zinc tailings sample to obtain the mineral composition parameters of the lead-zinc tailings sample; Laser particle size analysis was performed on the lead-zinc tailings sample to obtain the particle size distribution parameters of the lead-zinc tailings sample; Plasticity index analysis was performed on the lead-zinc tailings samples to obtain the plasticity index parameters of the lead-zinc tailings samples; The drying characteristics of the lead-zinc tailings samples were analyzed to obtain the drying characteristic parameters of the lead-zinc tailings samples. The sintering characteristics of the lead-zinc tailings samples were analyzed to obtain the sintering characteristic parameters of the lead-zinc tailings samples. At least one of the chemical composition parameters, mineral composition parameters, particle size distribution parameters, plasticity index parameters, drying characteristic parameters, and sintering characteristic parameters of the lead-zinc tailings sample shall be used as the basic performance data corresponding to the lead-zinc tailings sample.

[0008] In some embodiments of this application, the step of performing sintering characteristic analysis on the lead-zinc tailings sample to obtain the sintering characteristic parameters of the lead-zinc tailings sample includes: Simultaneous thermal analysis was performed on the lead-zinc tailings sample to obtain the simultaneous thermal analysis curve of the lead-zinc tailings sample; Several mass loss characteristic intervals and corresponding characteristic thermal effect peaks are identified from the synchronous thermal analysis curves. The lead-zinc tailings samples were sintered at several different preset sintering temperatures to obtain the microstructural features of the lead-zinc tailings samples at the different preset sintering temperatures. The critical reaction temperature range is determined based on the mass loss characteristic range. The sintering control parameters are determined based on the key reaction temperature range. The densification temperature range and crack risk temperature threshold of the material are determined based on several of the aforementioned microstructural features. At least one of the key reaction temperature range, sintering control parameters, material densification temperature range, and crack risk temperature threshold is used as the sintering characteristic parameter.

[0009] In some embodiments of this application, the process performance prediction information includes predicted plasticity parameters, predicted drying shrinkage rate, predicted sintering temperature range, and predicted sintering strength; the step of obtaining process requirement parameters of the target product and comparing the process performance prediction information with the process requirement parameters of the target product to obtain a comparison result includes: Obtain the process requirement parameters of the target product; the process requirement parameters include at least one of the following: plasticity index range, drying shrinkage threshold, sintering temperature range, and minimum compressive strength value. The predicted plasticity parameter is compared with the range of the plasticity index to obtain a first comparison result; The predicted drying shrinkage rate is compared with the drying shrinkage rate threshold to obtain a second comparison result; The predicted sintering temperature range is compared with the sintering temperature range to obtain a third comparison result; The predicted sintering strength is compared with the minimum compressive strength value to obtain the fourth comparison result; The comparison result is determined based on the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result.

[0010] In some embodiments of this application, the method further includes: Based on the comparison results, the performance information to be optimized for the lead-zinc tailings samples is identified; Based on the performance information to be optimized and the basic performance data, at least one auxiliary material corresponding to the performance information to be optimized and the addition ratio of the auxiliary material are retrieved from the preset auxiliary material database.

[0011] In some embodiments of this application, the trained lead-zinc tailings process performance prediction model is trained in the following manner: Acquire training samples and validation samples; the training samples include basic performance data of the samples and real process performance data of the samples; the validation samples include basic performance data of validation and real process performance data of validation corresponding to the basic performance data of validation. The sample basic performance data is used as the input of the lead-zinc tailings process performance prediction model, and the sample real process performance data is used as the output of the lead-zinc tailings process performance prediction model. The training sample is used to train the lead-zinc tailings process performance prediction model to obtain the lead-zinc tailings process performance prediction model to be verified. The verification basic performance data is input into the lead-zinc tailings process performance prediction model to be verified, and the verification process performance prediction information output by the lead-zinc tailings process performance prediction model to be verified is obtained. The loss function value corresponding to the lead-zinc tailings process performance prediction model to be verified is calculated based on the verification process performance prediction information and the actual verification process performance data. The loss function value is used to adjust the model parameters of the lead-zinc tailings process performance prediction model to be verified, and the training samples are used to retrain the lead-zinc tailings process performance prediction model to be verified until the preset training stopping condition is reached, so as to obtain the trained lead-zinc tailings process performance prediction model.

[0012] In some embodiments of this application, obtaining training samples and validation samples includes: Obtain historical basic performance data and historical process performance data corresponding to historically collected lead-zinc tailings samples; The sample basic performance data and the verification basic performance data are constructed based on the historical basic performance data. Based on the historical process performance data, obtain the actual verification process performance data corresponding to the verification basic performance data; The verification basic performance data and the verification process performance real data are used as the verification samples; The sample basic performance data is labeled based on the historical process performance data to obtain the sample process performance real data corresponding to the sample basic performance data. The basic performance data of the sample and the actual process performance data of the sample are used as the training samples.

[0013] This application provides a system for evaluating the processability of lead-zinc tailings, the system comprising: The sample acquisition module is used to acquire lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples. The performance prediction module is used to input the basic performance data into the trained lead-zinc tailings process performance prediction model for prediction, and obtain the process performance prediction information output by the lead-zinc tailings process performance prediction model. The parameter comparison module is used to obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison result. The result generation module is used to generate a processability evaluation result of the lead-zinc tailings sample for the target product based on the comparison results.

[0014] This application obtains lead-zinc tailings samples, tests them, and obtains the basic performance data corresponding to the samples. This basic performance data is then input into a trained lead-zinc tailings process performance prediction model for prediction, yielding the process performance prediction information output by the model. The application also obtains the process requirement parameters for the target product, compares the predicted process performance information with these parameters, and generates a comparison result. Based on this comparison result, a processability evaluation result for the lead-zinc tailings samples relative to the target product is generated. This application establishes a data-driven prediction and evaluation system to predict the process performance of lead-zinc tailings and generate processability evaluation conclusions, overcoming the limitations of traditional experience-based judgments and improving the targeting and economic efficiency of tailings resource utilization. Attached Figure Description

[0015] Figure 1 This is a flowchart of the steps in a method for evaluating the processability of lead-zinc tailings provided in an embodiment of this application; Figure 2 This is a graph showing the relationship between the strength of lead-zinc tailings dry billets and the moisture content during molding, provided in an embodiment of this application. Figure 3 This is a TG-DSC analysis chart of lead-zinc tailings provided in the embodiments of this application; Figure 4a This is a schematic diagram showing the changes in compressive strength of lead-zinc tailings sintered test blocks at different sintering temperatures, provided in the embodiments of this application. Figure 4b This is a graph showing the changes in bulk density and mass loss rate of lead-zinc tailings sintered test blocks at different sintering temperatures, as provided in the embodiments of this application. Figure 5a This is a SEM analysis image of unsintered lead-zinc tailings provided in the embodiments of this application; Figure 5b This is a SEM analysis image of sintered lead-zinc tailings at 900℃ provided in the embodiments of this application; Figure 5c This is a SEM analysis image of sintered lead-zinc tailings at 1000℃ provided in the embodiments of this application; Figure 5d This is a SEM analysis image of sintered lead-zinc tailings at 1050℃ provided in the embodiments of this application; Figure 5e This is a SEM analysis image of sintered lead-zinc tailings at 1000℃ provided in the embodiments of this application; Figure 6 This is a schematic diagram of a lead-zinc tailings processing performance evaluation system provided in an embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0017] With the continuous deepening of my country's industrialization, the non-ferrous metal mining industry generates and stores massive amounts of ore dressing tailings annually, with lead-zinc tailings accounting for a significant proportion. These tailings are typically considered solid waste, and their traditional storage and disposal methods not only consume vast amounts of land resources but also risk causing serious soil and groundwater pollution due to the migration of residual heavy metal ions, posing a long-term threat to the ecological environment. Meanwhile, the production of traditional cement, a core material for infrastructure construction, is a high-energy-consuming, high-resource-consuming process that emits large amounts of carbon dioxide, contradicting global sustainable development goals. Therefore, using lead-zinc tailings as raw materials for industrial product processing has become a crucial issue that urgently needs to be addressed in the environmental protection field. Against this backdrop, the resource utilization of lead-zinc tailings offers a highly promising solution for achieving waste-to-waste treatment and turning waste into treasure.

[0018] Therefore, this application provides a method for evaluating the processability of lead-zinc tailings. By predicting the process performance information of lead-zinc tailings samples and generating processability evaluation results, the method achieves predictability of processability and provides a scientific solution for tailings resource utilization.

[0019] Reference Figure 1 The diagram illustrates a flowchart of the steps in a method for evaluating the processability of lead-zinc tailings according to an embodiment of this application.

[0020] The method may specifically include the following steps: Step 101: Obtain lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples.

[0021] Among them, lead-zinc tailings samples refer to representative solid samples obtained from solid waste generated after lead-zinc ore beneficiation, using standardized sampling methods, and their source information must be clearly recorded. Basic performance data refers to a dataset obtained through standard testing methods that describes the essential properties of tailings samples, including at least physical and chemical properties, and serves as the basis for tailings characteristic characterization and subsequent applications.

[0022] The specific implementation of this step includes: sample acquisition, pretreatment, standardized testing, and data generation. Sample acquisition refers to collecting representative original samples from the tailings dam according to a predetermined plan, and numbering and registering them; pretreatment refers to drying, crushing, mixing, and reducing the samples to prepare standard test specimens; standardized testing refers to using professional instruments to conduct physicochemical tests on the specimens according to national or industry standards; data generation refers to calibrating and organizing the instrument results to form a structured test report.

[0023] This application uses basic performance data from lead-zinc tailings testing to ensure the standardization and representativeness of the data source, providing a reliable basis for subsequent analysis and avoiding the risk of sample bias; it also standardizes the testing process and makes the results repeatable, improving the comparability of data from different batches and sources.

[0024] In some embodiments of this application, step 101, "testing the lead-zinc tailings sample to obtain the basic performance data corresponding to the lead-zinc tailings sample," includes the following sub-steps: Sub-step 11: Perform spectral analysis on the lead-zinc tailings sample to obtain the chemical composition parameters of the lead-zinc tailings sample; Sub-step 12: Perform diffraction analysis on the lead-zinc tailings sample to obtain the mineral composition parameters of the lead-zinc tailings sample; Sub-step 13: Perform laser particle size analysis on the lead-zinc tailings sample to obtain the particle size distribution parameters of the lead-zinc tailings sample; Sub-step 14: Perform plasticity index analysis on the lead-zinc tailings samples to obtain the plasticity index parameters of the lead-zinc tailings samples; Sub-step 15: Analyze the drying characteristics of lead-zinc tailings samples to obtain the drying characteristic parameters of the lead-zinc tailings samples; Sub-step 16: Analyze the sintering characteristics of the lead-zinc tailings samples to obtain the sintering characteristic parameters of the lead-zinc tailings samples; Sub-step 17: Use at least one of the following parameters of lead-zinc tailings sample: chemical composition parameter, mineral composition parameter, particle size distribution parameter, plasticity index parameter, drying characteristic parameter, and sintering characteristic parameter as the basic performance data corresponding to the lead-zinc tailings sample.

[0025] Among these parameters, chemical composition parameters mainly refer to the percentage of oxides or elemental content of major elements and trace heavy metals in the tailings, obtained through spectroscopic analysis methods such as X-ray fluorescence spectroscopy. Mineral composition parameters refer to the qualitative and semi-quantitative identification of crystalline mineral phases in the tailings (such as quartz, mica, chlorite, calcite, kaolinite, sphalerite, galena, etc., and their relative contents) determined by X-ray diffraction analysis. Particle size distribution parameters refer to the cumulative distribution curve of particles based on volume or quantity, characteristic particle size, and uniformity index obtained by laser particle size analyzer. Plasticity index parameters refer to the index characterizing the cohesiveness and molding ability of tailings, calculated according to geotechnical testing standards (such as using a combined liquid and plastic limit tester). Drying characteristic parameters refer to the drying curve, critical moisture content, and drying rate obtained through thermogravimetric analysis or isothermal drying experiments. Sintering characteristic parameters refer to information such as sintering temperature range, shrinkage rate, sintered body strength, and phase evolution obtained through high-temperature thermal analysis or sintering experiments.

[0026] The detection process of this application includes the following sequentially executed sub-steps: First, perform spectral analysis on the lead-zinc tailings sample, using an X-ray fluorescence spectrometer to determine its chemical composition and obtain chemical composition parameters expressed in oxide form; Second, perform diffraction analysis on the lead-zinc tailings sample, using an X-ray diffractometer for phase identification and combining this with Rietveld refinement and other methods for semi-quantitative analysis to obtain mineral composition parameters; Third, perform laser particle size analysis on the lead-zinc tailings sample, passing the dispersed sample through a laser particle size analyzer to obtain particle size distribution parameters including D10, D50, D90, and distribution width; Fourth, perform plasticity index analysis on the lead-zinc tailings sample, determining its liquid limit and plastic limit according to standard test methods and calculating the difference between the two to obtain the plasticity index parameter; Fifth, perform drying characteristic analysis on the lead-zinc tailings sample, recording its weight loss process under controlled temperature and humidity conditions to obtain drying characteristic curves and key parameters. Specifically, this application studied the drying characteristics of blanks with different moisture contents. Different moisture content conditions of 5%, 7.5%, 10%, 12.5%, 15%, and 17.5% were set, and the powder was pressed into Φ50×50mm blanks under a pressure of 15MPa. Finally, the blanks were continuously dried in a constant temperature drying oven at 105℃ for 12 hours. The size and appearance changes of the specimens were observed, and the compressive strength of the dried blanks was tested using a computer-controlled pressure testing machine. In the sixth step, the sintering characteristics of the lead-zinc tailings samples were analyzed. Using a high-temperature comprehensive thermal analyzer or a tube furnace, the linear changes, mass loss, and properties of the final product were measured at different temperature ranges to obtain sintering characteristic parameters. Finally, at least one of the obtained chemical composition parameters, mineral composition parameters, particle size distribution parameters, plasticity index parameters, drying characteristic parameters, and sintering characteristic parameters was selected and combined according to the needs of the specific application scenario as the basic performance data output corresponding to the lead-zinc tailings sample. It should be noted that, through the fifth step of observation of the changes in the sample after drying, this application found that the appearance of the lead-zinc tailings billet did not change significantly under different moisture content conditions, no cracks were generated, and there was no significant change in structure. Further testing revealed that the volume change of the billet was also very small, and the volume shrinkage rate was basically less than 1%. Figure 2 This is a graph showing the relationship between the strength of lead-zinc tailings dry billets and the moisture content during molding, provided in an embodiment of this application. Figure 2As can be seen, the forming moisture content has a certain impact on the strength of lead-zinc tailings dry billets. With the moisture content in the tailings varying from 5% to 17.5%, the strength of the dry billets first increases and then decreases, remaining at a relatively high level within the range of 12.5% ​​to 15%. This is because at low moisture content, the water film thickness between the billet particles is low and its distribution is small. Although it can be formed under pressure and the billet structure does not change after drying, the disappearance of the water film makes the particles more loose, making them easily deformed and damaged under external pressure. When the moisture content increases, the water film thickness increases, the distribution becomes denser, the particles become more compact, and the strength of the dry billet also increases. However, when the moisture content is too high, the water film adsorbed between the particles is thicker, the distance between the particles is larger, more pores are formed after drying, the structure is more unstable, and the strength decreases accordingly. Overall, although the dry billet strength is relatively low, the fluctuation is small and it is relatively stable. Therefore, it can be seen that the tailings billet is not significantly affected by drying, which is conducive to drying control. When the molding moisture content is in the range of 12.5% ​​to 15%, the drying performance is relatively good.

[0027] In the application embodiment of preparing sintered building materials from tailings, all the above sub-steps can be performed in a focused manner. The prepared sample powder is loaded into the sample cells of XRF (X-ray fluorescence spectroscopy), XRD (X-ray diffraction), and laser particle size analyzer for the first four analyses. At the same time, a portion of the sample is taken to prepare test strips of specified dimensions for plasticity index determination. Another portion of the sample is used for programmed temperature drying and high-temperature sintering experiments. Finally, the data generated from all sub-steps are integrated into a unified database to form a complete sample characteristic profile, which serves as the basic performance data package for subsequent sintering formula design and process optimization.

[0028] In some embodiments of this application, sub-step 16 may specifically include the following steps: Sub-step 111: Perform simultaneous thermal analysis on the lead-zinc tailings sample to obtain the simultaneous thermal analysis curve of the lead-zinc tailings sample; Sub-step 112: Identify several mass loss characteristic intervals and the corresponding characteristic thermal effect peaks from the synchronous thermal analysis curve; Sub-step 113: Sinter the lead-zinc tailings samples at several different preset sintering temperatures to obtain the microstructural characteristics of the lead-zinc tailings samples at several different preset sintering temperatures. Sub-step 114: Determine the critical reaction temperature range based on the mass loss characteristic range; Sub-step 115: Determine the sintering control parameters based on the critical reaction temperature range; Sub-step 116: Determine the densification temperature range and crack risk temperature threshold of the material based on several microstructural characteristics; Sub-step 117: Use at least one of the following as sintering characteristic parameters: critical reaction temperature range, sintering control parameters, material densification temperature range, and crack risk temperature threshold.

[0029] Among them, the simultaneous thermal analysis curve refers to the thermogravimetric curve of sample mass versus temperature and the differential scanning calorimetry curve of heat versus temperature, measured simultaneously by a simultaneous thermal analyzer under the same programmed temperature-controlled atmosphere. The two curves are strictly corresponding on the time and temperature coordinates. The mass loss characteristic range refers to the temperature range on the thermogravimetric curve where the sample mass decreases significantly and continuously due to physicochemical reactions such as dehydration, decomposition, oxidation, or volatilization. The characteristic thermal effect peak refers to the peak on the differential scanning calorimetry curve corresponding to endothermic or exothermic effects. Its peak temperature is associated with the mass loss characteristic range and together identifies the temperature point of a specific reaction. Microstructural characteristics refer to the cross-sectional or surface morphology of sintered samples observed by instruments such as scanning electron microscopes at different preset sintering temperatures, including but not limited to the degree of particle melting and adhesion, porosity and pore size distribution, grain size and growth, and the presence and morphology of cracks or defects.

[0030] In the specific implementation of this application, the sintering characteristic analysis step includes the following sequentially executed sub-steps: First, simultaneous thermal analysis is performed on the lead-zinc tailings sample to obtain its simultaneous thermal analysis curve from room temperature to a preset maximum temperature under a set heating rate and atmosphere; second, the temperature ranges (mass loss characteristic ranges) corresponding to all obvious mass loss steps are identified and marked from the simultaneous thermal analysis curves using the tangent method or derivative method, and the temperature position and area (characteristic thermal effect peak) of the corresponding endothermic or exothermic peak on the differential scanning calorimetry curve within each range are determined; simultaneously, isothermal sintering experiments are conducted on parallel-prepared tailings sample compacts at several different preset sintering temperatures, and the sintered samples are prepared as observation samples. The microstructure characteristics are observed and recorded using a scanning electron microscope. Then, based on the mass loss characteristic range, especially the temperature range where the main components undergo violent decomposition or reaction, the key reaction temperature range that needs to be controlled during sintering is determined. Based on this key reaction temperature range, sintering control parameters are further derived, such as recommended heating rates, holding temperatures, and atmosphere control requirements. Next, based on the evolution of several microstructure characteristics, such as the temperature at which particles begin to melt and adhere significantly and porosity begins to decrease sharply, the material densification temperature range for achieving effective material densification is determined. At the same time, based on the temperature at which macroscopic cracks or excessive expansion begin to appear, the cracking risk temperature threshold is determined.

[0031] In a specific implementation scenario of this application, in order to explore the physicochemical changes that occur in lead-zinc tailings during the calcination process and to provide a basis for subsequent research, a synchronous thermal analyzer was used to perform synchronous thermal analysis on the lead-zinc tailings. Specifically, the synchronous thermal analysis adopted TG-DSC (Thermogravimetry - Differential Scanning Calorimetry) technology, which is a combined technique that combines thermogravimetric analysis and differential scanning calorimetry. Figure 3 The TG-DSC analysis chart of lead-zinc tailings provided in this application embodiment corresponds to a temperature range from room temperature to 1200℃, with a heating rate set to 10℃ / min. As can be seen from the TG curve, the lead-zinc tailings exhibit an overall trend of weight loss during heating, with a cumulative mass loss rate of 14.72%. Further analysis reveals that the mass loss process of lead-zinc tailings can be divided into four stages: (1) The first stage is when the temperature rises from room temperature to around 370℃. In this range, the TG curve declines slowly, and the mass loss rate is only 0.24%. The mass loss in this stage is mainly caused by the volatilization of adsorbed water and crystal water. However, since the test sample was dried before thermal analysis, some adsorbed water and crystal water have been discharged, resulting in a small mass loss. (2) The second stage is when the temperature rises from 370℃ to around 575℃. The TG curve begins to decline significantly, while the DSC curve shows obvious exothermic and endothermic peaks. The exothermic peak at around 490.5℃ may be caused by the combustion of organic matter contained in the tailings, and the endothermic peak at around 554.3℃ is mainly related to the decomposition of pyrite and silicates, and is also affected by the endothermic effect of the quartz phase transition. The mass of quartz does not change during the phase transition, but the combustion of organic matter and the decomposition of pyrite and silicates will cause the loss of tailings mass. (3) The third stage is from 575℃ to around 870℃. In this stage, the DSC curve shows a clear peak, and the mass loss of tailings is the largest, with a mass loss rate of about 8.99%. It is speculated that the exothermic peak is caused by the further oxidation of the decomposition products of pyrite, and the endothermic peak is mainly caused by the decomposition of carbonate minerals in the tailings. Since the content of carbonate minerals in the tailings is relatively large, the mass loss is increased. (4) The temperature rises from 870℃ to 1200℃ in the fourth stage. In the early stage of this stage, the tailings quality changes relatively slowly, and the DSC curve also increases slowly, indicating that the physicochemical changes inside the tailings are mainly melting, and the tailings are in a stable sintering process. However, when the temperature is higher than 1150℃, the tailings quality shows a significant decreasing trend and an endothermic peak appears. This may be caused by the decomposition of aluminosilicate minerals at high temperature.

[0032] The above analysis shows that the lead-zinc tailings undergo reactions such as organic combustion and mineral decomposition during sintering, resulting in a significant mass loss rate. This indicates the generation of a considerable amount of gas, which will have a certain impact on the structure of the sintered bricks. Characteristic thermal effect peaks (endothermic and exothermic peaks) are quite pronounced, especially in the third stage, where the content of reacting substances is high and the mass change is significant. Therefore, in the subsequent preparation of sintered bricks, a slower heating rate should be set to prevent the violent reaction from damaging the structure of the sintered bricks due to excessively rapid heating. Furthermore, a certain holding time should be set within the temperature range of 575℃ to 870℃ to ensure the complete progress of the reaction. In addition, the sintering temperature can be selected by referring to the temperature range of 870℃ to 1150℃ in the fourth stage. Within this range, the tailings mainly undergo solid-phase reactions with relatively small mass changes, making it suitable for long-term sintering. In other words, by combining the synchronous thermal analysis curves, the characteristic mass loss range and the corresponding characteristic thermal effect peaks are identified. Based on the characteristic mass loss range, the key reaction temperature range is determined, and further, the sintering control parameters are determined based on the key reaction temperature range.

[0033] Next, examples are given for sub-steps 113 and 116. For instance, sintering temperatures are set to 850, 900, 950, 1000, 1050, and 1100℃. The dried Φ50×50mm lead-zinc tailings billet is placed in a box-type resistance furnace. The temperature is first increased from room temperature to 130℃ at a rate of 5℃ / min, then increased from 130℃ to 700℃ at a rate of 3℃ / min, held for 60 min, and then increased from 700℃ to the set sintering temperature at a rate of 2℃ / min, held for 60 min, and finally allowed to cool naturally in the furnace chamber to obtain sintered test blocks. The sintering strength, bulk density, mass loss rate, and appearance of the sintered test blocks are measured. The microstructural characteristics of the lead-zinc tailings sintered materials at different preset sintering temperatures are analyzed to determine the material densification temperature range and cracking risk temperature threshold. Figure 4a This is a schematic diagram illustrating the changes in compressive strength of lead-zinc tailings sintered test blocks at different sintering temperatures, provided in the embodiments of this application. Figure 4b The graph shows the changes in bulk density and mass loss rate of lead-zinc tailings sintered test blocks at different sintering temperatures, as provided in the embodiments of this application. Figure 4a and Figure 4bAs can be seen, the change in compressive strength of the specimens can be clearly divided into two stages with the increase of sintering temperature. From 850℃ to 1000℃, the strength of the specimens increases slowly with the increase of sintering temperature, and the increase is small. The bulk density of the specimens shows a decreasing trend. This may be because some minerals still decompose in this temperature range, and the generated gases lead to a decrease in bulk density. On the other hand, less molten liquid is formed, sintering shrinkage is small, and the sintering effect is not obvious, so the increase in strength is small. When the sintering temperature reaches 1050℃, the strength and bulk density of the specimens increase sharply, indicating that this temperature is the temperature at which the lead-zinc tailings begin to sinter. A large amount of liquid melt begins to be generated inside the green body, the pores are filled, the firing shrinkage increases, and the green body gradually sintersties densely. Therefore, the density and strength after firing both increase sharply and reach their peak values. However, as the sintering temperature continues to increase, this trend begins to recede, possibly because the excessively high temperature causes cracks in the specimens, thus weakening the strength. Overall, the test blocks obtained after sintering at 1050℃ have better performance. However, due to the continuous increase in mass loss during the sintering process and the generation of more gas, the bulk density of the test blocks is relatively small, and the firing strength is lower than the minimum standard of 10MPa for sintered ordinary bricks, resulting in poor brick-making performance when used alone.

[0034] To better understand the relationship between the physical properties and microstructure of lead-zinc tailings under different temperatures, SEM (Scanning Electron Microscope) analysis was performed on the sintered products of lead-zinc tailings at different temperatures. Figure 5a , Figure 5b , Figure 5c , Figure 5d , Figure 5e The images shown are SEM analysis images of lead-zinc tailings at different temperatures (unsintered, sintered at 900℃, sintered at 1000℃, sintered at 1050℃, and sintered at 1000℃) provided in the embodiments of this application. Figure 5a As shown, the main characteristics of unburned tailings are individual particles with flaky fragments attached to their surface; such as Figure 5b As shown, at a sintering temperature of 900℃, the lead-zinc tailings undergo chemical reaction and decomposition, resulting in indistinct particle boundaries and a rough surface exhibiting densely packed molten spherical particles with highly concentrated micropores. However, larger flaky particles also exist on the surface. Figure 5c As shown, when the sintering temperature reaches 1000℃, the number of spherical particles decreases. At this point, some of the tailings begin to transform into a molten liquid state, but the quantity is small, and the overall structure remains porous. Figure 5dAs shown, when the sintering temperature reaches 1050℃, the tailings no longer exhibit a uniform and dense porous structure. This is mainly because the molten liquid portion of the tailings increases at this sintering temperature, and the resulting liquid material fills the pores between the particles. Furthermore, prismatic particles appear, which is due to the sufficient development of the particles under high-temperature calcination, accelerating the crystallization rate of the tailings. When the temperature rises to 1100℃, as... Figure 5e As shown, the number of prismatic crystals increases significantly, the surface of the crystals is smoother, there are fewer flocculent fragments, and large blocks of cooled melt also appear. In general, between 900℃ and 1100℃, with increasing sintering temperature, the tailings particles react and crystallize more fully, resulting in fewer micropores and smoother, clearer tailings boundaries. Based on the SEM images, the optimal sintering temperature can be determined to be above 1050℃. This also explains the significant increase in strength of the lead-zinc tailings sintered specimens at 1050℃, thus determining the material densification temperature range as 900℃-1050℃ and the cracking risk temperature threshold as 1100℃.

[0035] Finally, at least one of the key reaction temperature range, sintering control parameters, material densification temperature range, and crack risk temperature threshold is used as the sintering characteristic parameters of the lead-zinc tailings sample. At least one of the chemical composition parameters, mineral composition parameters, particle size distribution parameters, plasticity index parameters, drying characteristic parameters, and sintering characteristic parameters obtained in the preceding steps and this step is used as the basic performance data corresponding to the lead-zinc tailings sample.

[0036] In some embodiments of this application, the trained lead-zinc tailings process performance prediction model is trained in the following manner: Acquire training samples and validation samples; training samples include basic performance data of samples and real process performance data of samples; validation samples include basic performance data of validation and real process performance data of validation corresponding to the basic performance data of validation. The basic performance data of the sample is used as the input of the lead-zinc tailings process performance prediction model, and the real process performance data of the sample is used as the output of the lead-zinc tailings process performance prediction model. The lead-zinc tailings process performance prediction model is trained using training samples to obtain the lead-zinc tailings process performance prediction model to be verified. Input the verification basic performance data into the lead-zinc tailings process performance prediction model to be verified, and obtain the verification process performance prediction information output by the lead-zinc tailings process performance prediction model to be verified. The loss function value corresponding to the lead-zinc tailings process performance prediction model to be verified is calculated based on the verification process performance prediction information and the actual verification process performance data. The loss function value is used to adjust the model parameters of the lead-zinc tailings process performance prediction model to be validated, and the model is retrained using training samples until the preset training stopping condition is reached, thus obtaining the trained lead-zinc tailings process performance prediction model.

[0037] In the specific implementation of this application, model training is achieved through a closed-loop process including data preparation, iterative training, and validation optimization. The specific steps include: First, data acquisition and partitioning: a sufficient number of sample data pairs are obtained from a standard tailings process database. These are randomly divided into a training set (for model learning) and a validation set (for model tuning and evaluation) according to a predetermined ratio. Second, model initialization and training: the basic performance data of the samples in the training set are used as input features, and the corresponding real process performance data of the samples are used as target labels. These are input into the initialized prediction model. The model uses optimization algorithms such as backpropagation to iteratively update its internal parameters by minimizing the difference between the predicted output and the real label, resulting in a model to be validated after one round of training. The initial model includes, but is not limited to, neural networks and gradient boosting trees. Third, model validation and evaluation: the validation basic performance data from the validation set is input... The above-mentioned model to be verified is input to obtain its verification process performance prediction information. This prediction information is compared with the actual measured process performance information of the verification set, and the loss function value of the model on unseen data is calculated to evaluate its generalization performance. The fourth step is iterative optimization and termination. Based on the verification loss function value, the model parameters are adjusted using an optimizer, such as using Adam to adjust the model's learning rate parameter, and the training set is reused for the next round of training. The training-verification loop of this application continues until the preset training termination condition is met. At this time, the model parameters with the best verification performance are saved, which is the final trained lead-zinc tailings process performance prediction model.

[0038] In some embodiments of this application, the steps of "obtaining training samples and validation samples" specifically include the following sub-steps: Obtain historical basic performance data and historical process performance data corresponding to historically collected lead-zinc tailings samples; Construct sample baseline performance data and validation baseline performance data based on historical baseline performance data; Based on historical process performance data, obtain the actual verification process performance data corresponding to the verification basic performance data; The verification samples will be the basic performance data and the actual process performance data. The basic performance data of the sample is labeled based on historical process performance data to obtain the true process performance data of the sample; The basic performance data of the samples and the real performance data of the sample processes were used as training samples.

[0039] Among them, historical basic performance data is the set of input features of the sample, such as chemical composition spectrum, mineral composition, particle size distribution, etc.; historical process performance data is the corresponding target output set, that is, the performance indicators actually measured through standard process tests, such as sintering temperature, shrinkage rate, strength, etc.

[0040] In the specific implementation of this application, all available, paired historical basic performance data and corresponding historical process performance data are read from an integrated tailings material database or data file. After cleaning and standardizing the acquired historical basic performance data, it is divided into two parts according to a preset random seed and ratio: one part serves as sample basic performance data (training set input features), and the other part serves as validation basic performance data. The resulting validation basic performance data is combined with its corresponding historical process performance data to form a complete validation sample, which will be used to evaluate model performance during the validation phase. For the divided sample basic performance data, based on its sample ID, the corresponding measured process performance value is found from the historical process performance data and associated as a label with each set of feature data. This process generates sample process performance real data. The labeled sample basic performance data is then combined with its corresponding sample process performance real data to form a complete training sample set.

[0041] In one specific implementation, 500 pairs of historical tailings data were retrieved from a materials database. Each dataset contained one set of historical basic performance data and one set of historical process performance data. First, the 500 sets of basic performance data were cleaned, and numerical features were standardized using Z-scores. Then, the data were randomly shuffled and divided into two parts at an 8:2 ratio: 400 sets were used as sample basic performance data, and 100 sets were used as validation basic performance data. Next, labels were applied to both sets of data: based on a common sample ID, corresponding real labels were found and bound from the historical process performance data. For example, the basic data with ID TK-2023-001 was bound with labels such as the same ID, the measured optimal sintering temperature of 1100℃, and the drying shrinkage rate of 5.1%. Finally, the 400 sets of labeled data were used to construct a training sample set, and the 100 sets of labeled data were used to construct a validation sample set.

[0042] The above steps yielded 400 training sets and 100 validation sets. A three-layer fully connected neural network was used as the prediction model, with mean squared error as the loss function. The 400 training sets were input into the model in batches, and the model continuously adjusted the weights to reduce prediction error. After each epoch of training, its performance was tested using 100 sets of validation data. The training process showed that after 150 epochs, the validation loss reached a stable minimum and did not decrease further, triggering an early stopping mechanism. The model's state at this point was saved and deployed as the final trained model for prediction. Verification showed that the model's average prediction error on the validation set was less than 8%, meeting the requirements for engineering applications.

[0043] Step 102: Input the basic performance data into the trained lead-zinc tailings process performance prediction model for prediction, and obtain the process performance prediction information output by the lead-zinc tailings process performance prediction model.

[0044] Step 103: Obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison results.

[0045] The trained lead-zinc tailings process performance prediction model refers to a mathematical model established and trained and validated based on basic performance data from a large number of historical tailings samples and measured process performance data in standard process experiments, using machine learning algorithms (such as random forests and neural networks) or multivariate statistical methods. This model can capture the complex nonlinear relationships between chemical composition, mineral composition, physical properties, and final process performance. Process performance prediction information refers to quantitative indicators of the expected behavior of lead-zinc tailings samples in a typical ceramic or building materials process chain, calculated using mathematical models, empirical formulas, or machine learning models built into or associated with the system, based on the basic performance data of the tailings samples. These indicators include at least predicted plasticity, predicted drying shrinkage, predicted sintering temperature range, and predicted sintering strength. The process requirements parameters for the target product are the technological conditions that must be met in key processes such as molding, drying, and sintering, as defined by national, industry, or enterprise internal control standards for the product to be produced. These serve as rigid or flexible benchmarks for determining the suitability of raw materials and the feasibility of the process.

[0046] In practice, steps 102 and 103 can be executed sequentially. The structured basic performance data obtained in step 101 is used as a feature vector and completely input into the trained prediction model. The model outputs a set of structured process performance prediction information. For step 103: First, based on the target product type specified by the user (such as sintered porous bricks or ceramsite), the system automatically retrieves and obtains the corresponding process requirement parameters from the integrated process parameter knowledge base. This parameter set at least covers key dimensions such as the plasticity index range, drying shrinkage threshold, sintering temperature range, and minimum compressive strength value.

[0047] In some embodiments of this application, the process performance prediction information includes predicted plasticity parameters, predicted drying shrinkage rate, predicted sintering temperature range, and predicted sintering strength. Step 103 may specifically include the following sub-steps: Sub-step 21: The step of comparing the predicted process performance information with the process requirement parameters of the target product to obtain the comparison results includes: Sub-step 22: Obtain the process requirement parameters of the target product; the process requirement parameters include at least one of the following: plasticity index range, drying shrinkage threshold, sintering temperature range, and minimum compressive strength value; Sub-step 23: Compare the predicted plasticity parameters with the range of plasticity index to obtain the first comparison result; Sub-step 24: Compare the predicted drying shrinkage rate with the drying shrinkage rate threshold to obtain the second comparison result; Sub-step 25: Compare the predicted sintering temperature range with the sintering temperature range to obtain the third comparison result; Sub-step 26: Compare the predicted sintering strength with the minimum compressive strength value to obtain the fourth comparison result; Sub-step 27: Determine the comparison result based on the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result.

[0048] In the specific implementation of this application, the comparison step 103 includes the following sequentially executed sub-steps: First, obtain the process requirement parameters of the target product. Based on the product type selected by the user (e.g., ceramsite, sintered bricks, permeable ceramic bricks), the system retrieves preset core process requirement parameters corresponding to that product type from the built-in process parameter database. These parameters include at least: the plasticity index range for evaluating the molding ability of the clay, the drying shrinkage rate threshold for controlling the risk of deformation and cracking of the green body during the drying process, the sintering temperature range set to ensure firing quality and energy efficiency, and the minimum compressive strength value to ensure the final mechanical properties of the product. All or part of these parameters can be retrieved for this comparison. Subsequently, a step-by-step comparison process is initiated: the predicted plasticity parameters output by the model are compared with the range of plasticity indices in the database to determine whether they fall within the required range, generating the first comparison result regarding the applicability of the molding process; the predicted drying shrinkage rate is compared with the drying shrinkage rate threshold (e.g., the maximum allowable shrinkage rate of 8%) to determine whether it is below the threshold, generating the second comparison result regarding the stability of the drying process; the predicted sintering temperature range is compared with the standard sintering temperature range to assess their overlap and deviation, generating the third comparison result regarding the compatibility of the firing regime; the predicted sintering strength is compared with the minimum compressive strength value to determine whether it meets or exceeds the minimum requirements, generating the fourth comparison result regarding whether the product's mechanical properties meet the standards. Finally, the system performs a comprehensive analysis of the above first to fourth comparison results according to the preset comprehensive judgment logic, and finally outputs a comprehensive comparison result that includes sub-item conclusions and overall recommendations.

[0049] In one embodiment of this application aimed at evaluating the use of lead-zinc tailings for producing permeable landscape bricks, the basic performance data of the lead-zinc tailings (e.g., SiO2 58%, Al2O3 18%, D50=75μm, main minerals are quartz, feldspar, etc.) are first input into a deployed prediction model. The model outputs prediction information: a predicted plasticity index of 11.5, a predicted drying shrinkage rate of 6.2%, a predicted optimal sintering temperature range of 1080-1120℃, and a predicted compressive strength of 32MPa. Subsequently, in step 103, the process requirement parameters for the permeable landscape bricks are automatically retrieved: a plasticity index range of [10,15], a drying shrinkage rate threshold of ≤7.0%, a sintering temperature range of 1100-1150℃, and a minimum compressive strength of 28MPa. At this point, the comparison results are: the first, second, and fourth results are all met; the third result shows that the predicted sintering temperature range partially overlaps with the required range, but the predicted lower limit of the optimal sintering temperature is too low.

[0050] In some embodiments of this application, sub-step 27 may be followed by: Based on the comparison results, identify the performance information to be optimized in lead-zinc tailings samples; Based on the performance information to be optimized and the basic performance data, at least one excipient and its addition ratio corresponding to the performance information to be optimized are retrieved from the preset excipient database.

[0051] Among them, the performance information to be optimized refers to the specific process performance dimensions that need to be improved or adjusted and their quantitative gaps, identified through analysis and comparison of results (especially the sub-items that do not meet or are close to meeting the requirements). For example, if the predicted sintering strength is lower than the required value, the performance information to be optimized can be specifically stated as the compressive strength needs to be increased by at least X MPa. The preset auxiliary material database is a structured material knowledge base that includes information on various auxiliary materials commonly used to improve the process performance of tailings-based materials (such as binders, fluxes, plasticizers, aggregates, mineralizers, etc.). Each record includes at least the auxiliary material name, chemical composition, mechanism of action, applicable performance deficiency type, and a reference addition ratio range based on historical data or empirical formulas for different basic tailings characteristics.

[0052] Following the aforementioned evaluation case of permeable landscape bricks, assuming the comparison results show that although the predicted compressive strength meets the standard, the safety margin is insufficient, and the lower limit of the predicted sintering temperature range is lower than the required range, this application identifies the following performance information to be optimized: 1. Further improve the redundancy of mechanical properties; 2. Increase the sintering initiation temperature by approximately 20°C. At this point, this application can further combine the basic data of the tailings having a high aluminum content and a low alkali metal content, and query the auxiliary material database. For the strength enhancement requirement, silica fume is recommended as an active filler to fill pores and promote the formation of the mullite phase at high temperatures; for the temperature enhancement requirement, feldspar powder is recommended as a flux to reduce the viscosity of the high-temperature liquid phase and optimize the sintering process. The final output is the auxiliary materials and their addition ratios corresponding to the performance information to be optimized. For example: Option A – adding 2%–4% silica fume, expected to increase strength by 5–8 MPa, with a slight impact on sintering temperature; Option B – adding 3%–5% potassium feldspar powder, expected to effectively increase the sintering initiation temperature by 20–30°C, and possibly slightly increase strength. Composite addition can also be considered.

[0053] Step 104: Based on the comparison results, generate a processability evaluation result of the lead-zinc tailings sample for the target product.

[0054] Continuing with the previous example, the comparison results show that the first, second, and fourth results are all satisfactory; the third result shows that the predicted sintering temperature range partially overlaps with the required range, but the predicted lower limit is too low. Based on the preset comprehensive decision-making rules, all the sub-item comparison results are summarized, and a comprehensive comparison result is output, which is the processability evaluation result.

[0055] According to the rules, the comparison results of the above examples generate the final processability evaluation result: the raw material is generally suitable for the target product, the predicted strength meets the standard, and the improvement direction is given, namely the auxiliary material addition method of scheme A or scheme B given in the above steps, and it is recommended to optimize the temperature from 1100℃ in the actual firing test to ensure that the product pore structure and strength reach the best balance.

[0056] In summary, this application obtains lead-zinc tailings samples, tests these samples to obtain basic performance data, inputs this data into a trained lead-zinc tailings process performance prediction model for prediction, obtains the process performance prediction information output by the model, acquires the process requirement parameters for the target product, compares the predicted process performance information with the process requirement parameters for the target product, obtains the comparison results, and generates a processability evaluation result for the lead-zinc tailings samples relative to the target product. This application establishes a data-driven prediction and evaluation system to predict the process performance of lead-zinc tailings, accurately compares the results with the process requirements of the target product, and scientifically generates processability evaluation conclusions. This effectively overcomes the limitations of traditional experience-based judgments, significantly improves the targeting and economy of tailings resource utilization, and provides reliable data support for resource utilization decision-making.

[0057] Reference Figure 6 The diagram shows a schematic representation of a lead-zinc tailings processing performance evaluation system provided in an embodiment of this application. The system includes: The sample acquisition module 601 is used to acquire lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples. The performance prediction module 602 is used to input the basic performance data into the trained lead-zinc tailings process performance prediction model for prediction, and obtain the process performance prediction information output by the lead-zinc tailings process performance prediction model. The parameter comparison module 603 is used to obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison result. Result generation module 604 is used to generate a processability evaluation result of the lead-zinc tailings sample for the target product based on the comparison result.

[0058] As the system implementation is basically similar to the method implementation, it is described in a relatively simple way. For relevant details, please refer to the description of the method implementation.

[0059] This application also provides an electronic device that may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the method described above.

[0060] This application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the method described above.

[0061] The specific embodiments described above are preferred embodiments of this application, and are not intended to limit the specific scope of this application. The scope of this application includes but is not limited to the specific embodiments described above. All equivalent changes made in accordance with the shape and structure of this application are within the protection scope of this application.

Claims

1. A method for evaluating the processability of lead-zinc tailings, characterized in that, The method includes: Obtain lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples; The basic performance data is input into the trained lead-zinc tailings process performance prediction model for prediction, and the process performance prediction information output by the lead-zinc tailings process performance prediction model is obtained. Obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison result. Based on the comparison results, the processability evaluation results of the lead-zinc tailings sample for the target product are generated.

2. The method according to claim 1, characterized in that, The steps of testing the lead-zinc tailings sample to obtain the corresponding basic performance data include: The chemical composition parameters of the lead-zinc tailings sample were obtained by performing spectral analysis on the sample. Diffraction analysis was performed on the lead-zinc tailings sample to obtain the mineral composition parameters of the lead-zinc tailings sample; Laser particle size analysis was performed on the lead-zinc tailings sample to obtain the particle size distribution parameters of the lead-zinc tailings sample; Plasticity index analysis was performed on the lead-zinc tailings samples to obtain the plasticity index parameters of the lead-zinc tailings samples; The drying characteristics of the lead-zinc tailings samples were analyzed to obtain the drying characteristic parameters of the lead-zinc tailings samples. The sintering characteristics of the lead-zinc tailings samples were analyzed to obtain the sintering characteristic parameters of the lead-zinc tailings samples. At least one of the chemical composition parameters, mineral composition parameters, particle size distribution parameters, plasticity index parameters, drying characteristic parameters, and sintering characteristic parameters of the lead-zinc tailings sample shall be used as the basic performance data corresponding to the lead-zinc tailings sample.

3. The method according to claim 2, characterized in that, The steps of performing sintering characteristic analysis on the lead-zinc tailings sample to obtain the sintering characteristic parameters of the lead-zinc tailings sample include: Simultaneous thermal analysis was performed on the lead-zinc tailings sample to obtain the simultaneous thermal analysis curve of the lead-zinc tailings sample; Several mass loss characteristic intervals and corresponding characteristic thermal effect peaks are identified from the synchronous thermal analysis curves. The lead-zinc tailings samples were sintered at several different preset sintering temperatures to obtain the microstructural features of the lead-zinc tailings samples at the different preset sintering temperatures. The critical reaction temperature range is determined based on the mass loss characteristic range. The sintering control parameters are determined based on the key reaction temperature range. The densification temperature range and crack risk temperature threshold of the material are determined based on several of the aforementioned microstructural features. At least one of the key reaction temperature range, sintering control parameters, material densification temperature range, and crack risk temperature threshold is used as the sintering characteristic parameter.

4. The method according to claim 1, characterized in that, The process performance prediction information includes predicted plasticity parameters, predicted drying shrinkage rate, predicted sintering temperature range, and predicted sintering strength; the steps of obtaining the process requirement parameters of the target product, comparing the process performance prediction information with the process requirement parameters of the target product, and obtaining the comparison result include: Obtain the process requirement parameters of the target product; the process requirement parameters include at least one of the following: plasticity index range, drying shrinkage threshold, sintering temperature range, and minimum compressive strength value. The predicted plasticity parameter is compared with the range of the plasticity index to obtain the first comparison result; The predicted drying shrinkage rate is compared with the drying shrinkage rate threshold to obtain a second comparison result; The predicted sintering temperature range is compared with the sintering temperature range to obtain a third comparison result; The predicted sintering strength is compared with the minimum compressive strength value to obtain the fourth comparison result; The comparison result is determined based on the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result.

5. The method according to claim 4, characterized in that, The method further includes: Based on the comparison results, the performance information to be optimized for the lead-zinc tailings samples is identified; Based on the performance information to be optimized and the basic performance data, at least one auxiliary material corresponding to the performance information to be optimized and the addition ratio of the auxiliary material are retrieved from the preset auxiliary material database.

6. The method according to claim 1, characterized in that, The trained lead-zinc tailings process performance prediction model was obtained through the following method: Acquire training samples and validation samples; the training samples include basic performance data of the samples and real process performance data of the samples; the validation samples include basic performance data of validation and real process performance data of validation corresponding to the basic performance data of validation. The sample basic performance data is used as the input of the lead-zinc tailings process performance prediction model, and the sample real process performance data is used as the output of the lead-zinc tailings process performance prediction model. The training sample is used to train the lead-zinc tailings process performance prediction model to obtain the lead-zinc tailings process performance prediction model to be verified. The verification basic performance data is input into the lead-zinc tailings process performance prediction model to be verified, and the verification process performance prediction information output by the lead-zinc tailings process performance prediction model to be verified is obtained. The loss function value corresponding to the lead-zinc tailings process performance prediction model to be verified is calculated based on the verification process performance prediction information and the actual verification process performance data. The loss function value is used to adjust the model parameters of the lead-zinc tailings process performance prediction model to be verified, and the training samples are used to retrain the lead-zinc tailings process performance prediction model to be verified until the preset training stopping condition is reached, so as to obtain the trained lead-zinc tailings process performance prediction model.

7. The method according to claim 6, characterized in that, The acquisition of training samples and validation samples includes: Obtain historical basic performance data and historical process performance data corresponding to historically collected lead-zinc tailings samples; The sample basic performance data and the verification basic performance data are constructed based on the historical basic performance data. Based on the historical process performance data, obtain the actual verification process performance data corresponding to the verification basic performance data; The verification basic performance data and the verification process performance real data are used as the verification samples; The sample basic performance data is labeled based on the historical process performance data to obtain the sample process performance real data corresponding to the sample basic performance data. The basic performance data of the sample and the actual process performance data of the sample are used as the training samples.

8. A system for evaluating the processability of lead-zinc tailings, characterized in that, The system includes: The sample acquisition module is used to acquire lead-zinc tailings samples, test the lead-zinc tailings samples, and obtain the basic performance data corresponding to the lead-zinc tailings samples. The performance prediction module is used to input the basic performance data into the trained lead-zinc tailings process performance prediction model for prediction, and obtain the process performance prediction information output by the lead-zinc tailings process performance prediction model. The parameter comparison module is used to obtain the process requirement parameters of the target product, compare the process performance prediction information with the process requirement parameters of the target product, and obtain the comparison result. The result generation module is used to generate a processability evaluation result of the lead-zinc tailings sample for the target product based on the comparison results.

9. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1-7.

Images