Production quality monitoring method for mineral soil conditioner production line

Abstract

The invention relates to the technical field of chemical analysis, in particular to a production quality monitoring method for a mineral soil conditioner production line. The method comprises the following steps: collecting raw material component content data of raw material components in each ore raw material in a mineral soil conditioner production line; constructing a correlation analysis model of a raw material fluctuation coefficient and a yield fluctuation coefficient on the basis of the collected raw material component content data, and determining a content stable interval of raw material components in each ore raw material on the basis of the correlation analysis model, so as to construct a production quality risk evaluation model; and collecting current raw material component content data in real time, substituting the data into the constructed production quality risk evaluation model to calculate the risk degree of each raw material component, and if the absolute value of the calculated risk degree of each raw material component is greater than a preset risk threshold, determining that the risk is a production quality risk with proportion deviation, and if the absolute value is greater than the preset risk threshold, determining that the risk is a production quality risk with proportion deviation. And adjusting the ratio of the corresponding raw material components according to the numerical value of the risk degree. According to the invention, the stability of the production quality of the mineral soil conditioner is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of chemical analysis technology, specifically to a production quality monitoring method for mineral soil conditioner production lines. Background Technology

[0002] Mineral soil conditioners are materials used to improve soil quality, primarily by adjusting the physical and chemical properties of the soil to enhance its fertility, permeability, and water retention capacity. Common mineral soil conditioners include raw materials such as gypsum, vermiculite, potassium feldspar, dolomite, and perlite. Because the production of mineral soil conditioners requires natural minerals as raw materials, the purity of these natural minerals, i.e., the percentage of their effective components, is uncertain.

[0003] Existing technologies for producing mineral soil conditioners with fixed formulas may result in significant fluctuations in the content of raw materials, making it difficult to ensure uniformity in the final product's proportions and potentially leading to large differences in the ratios between components. Summary of the Invention

[0004] To address the technical problem of poor production quality stability in mineral soil conditioners, the present invention aims to provide a production quality monitoring method for mineral soil conditioner production lines. The specific technical solution adopted is as follows: In a first aspect, embodiments of the present invention provide a method for monitoring the production quality of a mineral soil conditioner production line, the method comprising: Collect data on the content of raw material components in each ore raw material in the mineral soil conditioner production line; Based on the collected raw material composition data, a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient is constructed, and the stable range of the raw material composition in each ore raw material is determined based on the correlation analysis model, thereby constructing a production quality risk assessment model. The system collects real-time data on the content of raw material components and inputs it into the constructed production quality risk assessment model to calculate the risk level of each raw material component. If the absolute value of the calculated risk level of a raw material component is greater than the preset risk threshold, it is determined to be a production quality risk with a ratio deviation, and the ratio of the corresponding raw material component is adjusted according to the value of the risk level.

[0005] In some embodiments, the collection of raw material component content data in each ore raw material in the mineral soil conditioner production line includes: Pre-set X-ray fluorescence spectrometers are installed on the conveying devices at the raw material stage and the reaction stage of the production line, respectively; The ore raw materials that have passed through the raw material stage are subjected to multiple component content tests at preset time intervals to obtain raw material component content data corresponding to the time intervals. Synchronously collect element content data at corresponding time intervals, and establish a time correspondence between the raw material component content data and element content data of the same batch of ore raw materials.

[0006] In some embodiments, the synchronous acquisition of element content data corresponding to the time interval includes: During each time interval, the elemental content of the reaction product is simultaneously detected multiple times using the X-ray fluorescence spectrometer used in the reaction stage. The average value of multiple element content detection results is taken as the element content data of the reaction product within this time interval. Specifically, for raw material components whose molecular formula changes after the reaction stage, the main element content of the raw material component in the final product is determined as the detection object for element content detection.

[0007] In some embodiments, the raw material fluctuation coefficient and the production fluctuation coefficient are obtained in the following ways: The first deviation characteristic value of the raw material component content is determined based on the deviation between the real-time component content of the raw material in the ore raw material within each time interval and the average content of the raw material component over all time intervals; The reciprocal of the proportion of the corresponding raw material component in the formula is used as the first weight, and the first deviation characteristic value of the raw material component is combined with the first weight to calculate the raw material fluctuation coefficient of each raw material component in each time interval. The second deviation characteristic value of the content of the product after reaction is determined based on the deviation between the real-time component content of the product after reaction within each time interval and the average content of the raw material component over all time intervals. The yield fluctuation coefficient of each raw material component within each time interval is calculated by using the reciprocal of the proportion of the corresponding raw material component in the formula as the second weight, and combining the second deviation characteristic value of the product after the reaction with the second weight.

[0008] In some embodiments, constructing a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient includes: The raw material fluctuation coefficient of each raw material component is used as the x-coordinate of the coordinate system, and the production fluctuation coefficient of the corresponding raw material component is used as the y-coordinate of the coordinate system. The numerical combination of the raw material fluctuation coefficient and the production fluctuation coefficient of the same batch of ore raw materials at the same time interval is used as coordinate points and entered into the coordinate system. The coordinate point with the smallest absolute value of the raw material fluctuation coefficient is used as the initial point set, and other coordinate points are added to the initial point set in order of increasing absolute value of the raw material fluctuation coefficient to form multiple new point sets. Perform linear fitting on all coordinate points within each new point set to obtain the corresponding fitted line; By analyzing the characteristics of the fitted straight line, the overall level of the production fluctuation coefficient within multiple point sets, and the degree of deviation of each coordinate point from the fitted straight line, a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient is constructed.

[0009] In some embodiments, determining the stable content range of raw material components in each ore raw material based on the correlation analysis model includes: Calculate the degree of division when each coordinate point in the correlation analysis model is used as a segmentation point; The coordinate point with the largest division degree is selected as the dividing point, and the residual state of fluctuation in the correlation analysis model is divided into a stable segment and a deviation segment. Extract the raw material component content data of the coordinate points corresponding to the stable segment, and perform outlier removal processing on the raw material component content data of the stable segment; The numerical range of raw material component content data in the stable segment after removing outliers is determined, and the numerical range is corrected according to a preset correction method. The corrected numerical range is then determined as the stable content range of raw material components in each of the ore raw materials.

[0010] In some embodiments, constructing a production quality risk assessment model includes: Calculate the deviation between the real-time content of each of the raw material components and the corresponding stable content range of the raw material component, wherein the deviation is 0 when it is within the stable content range, negative when it is below the lower limit of the stable content range, and positive when it is above the upper limit of the stable content range; The number of components with positive deviations and the number of components with negative deviations in all the current raw ore materials are counted. By combining the magnitude of the deviations of each raw material component and the difference in the number of raw material components with positive and negative deviations, a production quality risk assessment model is generated to determine the risk level of each raw material component to the final product's blending quality.

[0011] In some embodiments, the real-time acquisition of current raw material component content data and its input into the constructed production quality risk assessment model to calculate the risk level of each raw material component includes: The current raw material component content data is collected in real time at a preset detection frequency and input into the constructed production quality risk assessment model; The production quality risk assessment model calculates the deviation of each current raw material component based on the real-time content data of each current raw material component and the corresponding stable content range of the current raw material component. The production quality risk assessment model calculates and determines the risk level of each current raw material component by combining the magnitude of the deviation of each current raw material component and the difference in the number of component types with positive and negative deviations.

[0012] In some embodiments, the step of counting the number of component types with positive deviations and the number of component types with negative deviations in the raw material composition of all the current ore raw materials includes: The deviation of the raw material composition of all the current ore raw materials is calculated. Components with deviations greater than 0 are marked, and the number of component types with positive deviations is accumulated. Components with deviations less than 0 are marked, and the number of components with negative deviations is accumulated. Record the difference between the number of component types with positive deviation and the number of component types with negative deviation, and store the number of component types and the difference as the basic parameters for subsequent risk degree calculation.

[0013] In some embodiments, adjusting the proportions of the corresponding raw material components based on the risk level includes: The risk level of each of the raw material components is compared with the preset risk threshold. When the absolute value of the risk level of a certain raw material component is greater than the risk threshold, it is determined that the proportion of the raw material component needs to be adjusted. If the risk level is negative, it indicates that the content of the corresponding raw material component is too low. In this case, the conveyor belt speed of the raw material component in the mixing stage is increased to increase the input of the raw material component. If the risk level is positive, it indicates that the content of the corresponding raw material component is too high. The conveyor belt speed of the raw material component in the mixing stage should be reduced to decrease the amount of the raw material component input.

[0014] In a second aspect, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0015] Thirdly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

[0017] The embodiments of the present invention have at least the following beneficial effects: This invention lays a data foundation for subsequent analysis by collecting component content data of raw materials and reaction products. It then constructs a correlation analysis model between raw material fluctuation coefficients and yield fluctuation coefficients, combining fluctuation residue and gradation degree to determine the stable content range, thereby forming a production quality risk assessment model for quantifiable risk, solving the problem of fluctuation assessment caused by the uncertainty of natural ore purity. Finally, it collects data in real time and substitutes it into the model to calculate the risk level. When the risk exceeds the threshold, the proportion is dynamically adjusted by regulating the conveyor belt speed, effectively avoiding proportion deviations in fixed formula production, ensuring the stability of mineral soil conditioner product quality, and improving the accuracy and efficiency of production line quality control. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a production quality monitoring method for a mineral soil conditioner production line provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the production quality monitoring method for mineral soil conditioner production lines proposed according to the present invention.

[0021] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0022] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0024] 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 invention pertains.

[0025] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0026] The following description, in conjunction with the accompanying drawings, details the specific scheme of the production quality monitoring method for mineral soil conditioner production lines provided by this invention.

[0027] Example 1: Please see Figure 1 The diagram illustrates a flowchart of a production quality monitoring method for a mineral soil conditioner production line according to an embodiment of the present invention. The method includes the following steps: S10. Collect data on the content of raw material components in each ore raw material in the mineral soil conditioner production line.

[0028] It should be noted that the main production process of mineral soil conditioner is as follows: 1) Raw material stage: The raw ore is coarsely crushed by a jaw crusher, and then medium and finely crushed by a hammer crusher or impact crusher to break the ore into smaller pieces; 2) Reaction stage: According to the process requirements of the mineral soil conditioner product, various raw material components are prepared through corresponding physicochemical reactions; 3) Mixing stage: According to the target formula of the product, the ground mineral powder of one or more raw material components is transported to a mixer in proportion to obtain a composite mineral soil conditioner with stable and uniform raw material components.

[0029] Specifically, pre-installed X-ray fluorescence spectrometers (XRF) are installed on the conveyor devices at both the raw material and reaction stages of the mineral soil conditioner production line. The conveyor device is, for example, a conveyor belt. The XRF spectrometer is a chemical analysis device based on the principle of X-ray fluorescence spectroscopy. Its working mechanism involves emitting X-rays internally, which irradiate the material passing through the conveyor belt, exciting various element atoms in the material. The detector captures the generated fluorescence signal, thereby calculating the content of various raw material components in the ore. This instrument is suitable for rapid, real-time detection of multi-component solid materials such as ore raw materials. During installation, it is necessary to ensure that the instrument's detection probe is directly facing the center of the material conveying path on the conveyor belt, maintaining a pre-set distance from the material surface. Before formal data collection, calibration with a standard ore sample with known raw material component content is required to eliminate systematic errors and ensure detection accuracy. In this embodiment, the pre-set distance is 10-20 cm, but it can be adjusted according to the instrument model.

[0030] Furthermore, the component content of the ore raw materials passing through the raw material stage is detected multiple times at preset time intervals to obtain the raw material component content data corresponding to the time interval. In this embodiment of the invention, the preset time interval is 3 seconds, and in other embodiments, the implementer can adjust this value according to the actual situation. Within each time interval, the instrument performs a preset number of component content tests on the passed ore sample, and the average value of all test results within these 3 seconds is taken as the raw material component content data (unit: %) for that period. By taking the average value through multiple tests, the influence of uneven material distribution and random instrument errors on the data can be reduced, thereby improving the reliability of the raw material component content data. In this embodiment of the invention, the preset number of tests ranges from 3 to 5, and can be specifically set to 3.

[0031] Element content data are collected synchronously at corresponding time intervals, and a time correspondence between the raw material component content data and element content data for the same batch of ore is established. "Synchronous collection" refers to the coordinated time dimension of reaction stage detection and raw material stage detection. That is, for ore raw materials detected at a certain time interval in the raw material stage, after the reaction is completed, the instrument in the reaction stage must perform corresponding detection when the batch of raw materials arrives at the detection location. Establishing the time correspondence requires calculating three time segments: the transportation time from the raw material stage detection location to the reaction stage, the reaction process time in the reaction stage, and the transportation time from the reaction stage back to the detection location. The sum of the raw material stage detection time and these three time segments is the corresponding detection time in the reaction stage, ensuring accurate matching of data from both stages for the same batch of raw materials. For raw material components whose molecular formula changes before and after the reaction (e.g., CaCO3 changes to CaO, using the content of the main element (e.g., Ca) in the product as the detection target), the detection results are ensured to reflect the actual contribution of the raw material component. The transportation time from the raw material stage detection location to the reaction stage is calculated by the conveyor belt speed and the distance between the two locations. The reaction time in the reaction stage is determined by the temperature and pressure set in the process. That is, it is determined by the standard time that the production line presets for the reaction of a specific ore raw material to ensure that the raw material can fully complete the physicochemical reaction. For example, if the process sets the reaction temperature to 800℃ and the pressure to 0.3MPa, and it is necessary to maintain these conditions for 30 minutes to allow the raw material to react completely, then the reaction time in the reaction stage is determined to be 30 minutes.

[0032] During each time interval, the elemental content of the reaction product is detected multiple times simultaneously using an X-ray fluorescence spectrometer during the reaction stage. The number of detections is the same as that during the raw material stage (3-5 times). The average value of the multiple detection results is taken as the elemental content data of the reaction product during that time interval, ensuring the consistency and comparability of the detection data between the two stages, and laying a data foundation for subsequent analysis of the correlation between raw material fluctuations and product fluctuations.

[0033] S11. Based on the collected raw material component content data, construct a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient, and determine the stable range of raw material component content in each ore raw material based on the correlation analysis model, thereby constructing a production quality risk assessment model.

[0034] Since the effective content of natural minerals is uncertain, if the production process is not adjusted according to the corresponding content of the raw materials, the content in the resulting product will not match the expectations. For example, if one batch of limestone has a CaO content of 52% and another batch has 48%, then if limestone is added with a fixed formula, the product obtained from the batch with the 48% limestone content will have a lower CaO content than the batch with the 52% limestone content.

[0035] First, determine the real-time content of a certain raw material component in the ore raw material at each time interval. This content is the average of multiple test results within that time interval. Then, calculate the arithmetic mean of the test data of that raw material component over a certain historical period (e.g., 24 hours) at all fixed time intervals. Finally, comparing the deviations of the two values ​​above—the real-time average of each time interval and the arithmetic mean of the historical periods—reflects the first deviation in the raw material composition content. The first deviation is determined through... calculate( (This represents the content of the k-th raw material component in the t-th time period of the raw material stage). The positive or negative result reflects the direction of deviation, and the absolute value reflects the degree of deviation. This is the first deviation eigenvalue.

[0036] Using the reciprocal of the proportion of the corresponding raw material component in the formula as the first weight, and combining the first deviation characteristic value with the first weight, the raw material fluctuation coefficient of each raw material component in each time interval is calculated according to the following formula. : In the formula, Let be the proportion of the kth raw material component in the formula. Its reciprocal can be used as a weight to amplify the impact of deviations in low-proportion raw material components (the base of low-proportion raw material components is small, and the same deviation has a greater impact on the fluctuation of the ratio). It is a hyperbolic tangent function used to normalize the raw material fluctuation coefficient to the (-1,1) interval, which facilitates the comparison of fluctuation coefficients of different raw material components and subsequent calculations.

[0037] Furthermore, the deviation between the real-time content of the raw material components in the post-reaction product (the average elemental content detected at each time interval corresponding to the reaction stage) and the average content of the raw material components across all time intervals is used to reflect the second deviation characteristic value of the post-reaction product content. The calculation logic for the second deviation characteristic value is consistent with that of the first deviation characteristic value, i.e. ( (This refers to the content of the k-th raw material component in the t-th time period of the reaction stage.) This is the second deviation characteristic value. Using the reciprocal of the proportion of the corresponding raw material component in the formula as the second weight, and combining the second deviation characteristic value and the second weight, the production fluctuation coefficient of each raw material component within each time interval is calculated using the same calculation logic as the raw material fluctuation coefficient, according to the following formula. : Among them, the t-th time period of the raw material stage and the t-th time period after the reaction stage correspond to the same batch of raw materials. The actual time of the t-th time period after the reaction stage = the time of the t-th time period of the raw material stage + the transportation time from the raw material to the reaction stage + the reaction time + the transportation time from the reaction stage to the detection location, ensuring that the coefficient calculation is based on the data of the same batch of raw materials.

[0038] Furthermore, the raw material fluctuation coefficient of each raw material component... The x-coordinate of the coordinate system corresponds to the production fluctuation coefficient of the raw material components. A Cartesian coordinate system is constructed, with the y-coordinate serving as the coordinate system. A separate coordinate system is established for each raw material component (e.g., one coordinate system for gypsum and one for potassium feldspar) to avoid interference from the content data of different raw material components.

[0039] Combine the values ​​corresponding to the raw material fluctuation coefficient and the production fluctuation coefficient of the same batch of ore raw materials at the same time interval. , These points are used as coordinate points and entered into the coordinate system corresponding to the raw material components. Through continuous data collection, each coordinate system will form a dataset consisting of multiple coordinate points, with each point representing the fluctuation correlation state of the same batch of raw materials at a certain moment.

[0040] The initial point set is set with the coordinate point having the smallest absolute value of the raw material fluctuation coefficient. Other coordinate points are then added sequentially in ascending order of absolute value of the raw material fluctuation coefficient, forming multiple new point sets (e.g., if the initial point set contains one point, adding a second point creates a set with two points, and so on, until all points are added). A first-order fit is performed on all coordinate points within each new point set to obtain the corresponding fitted line. The fitted line reflects the linear correlation between the raw material fluctuation coefficient and the production fluctuation coefficient within the point set, and its slope... (The fitting slope of the nth point set of the kth raw material component) can reflect the degree of influence of raw material fluctuations on output fluctuations (when the slope is close to 0, the raw material fluctuations have little impact on output fluctuations and the adjustment ability of the reaction stage is strong; when the absolute value of the slope is large, the impact is significant and the adjustment ability is weak).

[0041] By analyzing the characteristics (slope) of the fitted line ), the mean of the output fluctuation coefficient within the point set ( ), the average absolute value of the output fluctuation coefficient of the nth point set for the kth raw material component) and the degree of deviation of the points within the point set from the fitted straight line ( , To fit the straight line at the ordinate of the x-coordinate at the i-th point, the residual fluctuation of each point set is calculated using the following formula. : Fluctuation residual reflects the stabilization state after the reaction of different raw material fluctuation levels; the smaller the value, the better the stabilization effect. By integrating the characteristics of the fitted straight line, the mean of production fluctuation, and fluctuation residual, a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient is constructed to quantify the production system's ability to regulate raw material fluctuations.

[0042] Furthermore, the division degree is calculated for each coordinate point in the correlation analysis model when used as a segmentation point. The division degree is used to measure the rationality of the segmentation point in dividing the residual state of fluctuations. The calculation requires first finding the average difference in residual fluctuations between adjacent points in the segment preceding (including the nth point) of the k-th raw material component. Mean difference in residual fluctuation between adjacent points and the later segment Then calculate the consistency of the slope in the first segment. ( The difference in residual fluctuation between any point within a segment and its subsequent points is consistent with the slope of the subsequent segment. Where n is the total number of points corresponding to the nth point of the kth raw material component. The final division degree is calculated using the following formula. : Division degree The larger the value, the better the segmentation effect. The coordinate point with the highest segmentation degree is selected as the dividing point, dividing the residual fluctuation state in the correlation analysis model into a stable segment where the system can be adjusted and a deviation segment with larger residual fluctuations. The stable segment corresponds to the set of points with smaller raw material fluctuation coefficients; within this segment, the reaction stage can stabilize the production fluctuations. The deviation segment corresponds to the set of points with larger raw material fluctuation coefficients; the reaction stage cannot adjust the fluctuations.

[0043] Extract the raw material component content data corresponding to the coordinate points of the stable segment, and perform outlier removal processing on the data (e.g., using the 3σ principle to remove outliers exceeding "data mean ± 3 times standard deviation") to avoid interference from random factors. Determine the numerical range of the raw material component content data in the stable segment after outlier removal (taking the minimum and maximum values ​​of the data). Combine this with the physicochemical characteristics of the raw material components (e.g., volatile raw material components need to compensate for volatilization loss, and difficult-to-react raw material components need to ensure sufficient reaction), and correct this range. The corrected numerical range is the stable content range of the raw material components in each ore raw material (when the raw material component content is within this range, it will basically not affect the product ratio quality and no intervention is required). Specifically, determining the stable range of raw material component content in each ore raw material requires first extracting raw material component content data from the stable segment of the correlation analysis model. Using the 3σ principle (i.e., removing outliers exceeding "data mean ± 3 times standard deviation"), the minimum and maximum values ​​of the remaining data are taken as the initial range. This is then corrected by considering the physicochemical properties of the components. For example, the lower limit for volatile components is increased to compensate for losses, and the lower limit for difficult-to-react components is increased to ensure reaction. Finally, the stable range of raw material component content in each ore raw material is obtained. Specific values ​​can be referenced as follows: K2O in potassium feldspar is 12.2%-13.2%, CaO in dolomite is 30.8%-31.9%, CaSO4·2H2O in gypsum is 78.7%-79.6%, SiO2 in vermiculite is 45.9%-46.9%, and CaCO3 in limestone is 93.1%-93.6% (all are mass fractions and need to be fine-tuned according to the actual ore purity).

[0044] Furthermore, the deviation between the real-time content of each raw material component and its corresponding stable content range is calculated. Among them, when the content is within the range =0, below the lower limit of the interval. When it is negative and higher than the upper limit of the interval A positive value indicates that the absolute value of the deviation reflects the degree of deviation from the stable range.

[0045] Count the number of raw material components with positive deviations among all current raw material components. Number of raw material components with negative deviation Calculate the difference between the two. This difference reflects the synergistic effect of deviations in multiple raw material components (the smaller the difference, the more balanced the distribution of positive and negative deviation raw material components, and the higher the risk of imbalance).

[0046] Taking the kth raw material component as an example, the magnitude of the deviation of the kth raw material component is considered ( ), maximum deviation ( ), minimum value ( )and The risk level of the kth raw material component is calculated using the following formula. (K is the total number of raw material components), and the formula for calculating this risk level is also the production quality risk assessment model; The risk level reflects the degree of influence of raw material components on the final product's formulation quality. Its numerical range is (-1, 1), with a higher absolute value indicating a higher risk. Based on the risk level calculation logic for each raw material component, a production quality risk assessment model is integrated. This model has the function of "inputting real-time content data → outputting the risk level of each raw material component," providing a core tool for real-time risk monitoring. It should be noted that the value of k ranges from [1, K], where K is the total number of raw material components.

[0047] Furthermore, the deviation of the raw material composition of all current ore raw materials is calculated (P1, P2, ..., P...). K This ensures coverage of all raw material components used in production, including gypsum, vermiculite, and potassium feldspar. Raw material components with a deviation greater than 0 are marked, and the number of raw material components with positive deviations is accumulated. Raw material components with deviations less than 0 are marked, and the number of raw material components with negative deviations is accumulated. Raw material components with a deviation of 0 are not included in the labeling and accumulation. Calculation ,Record , The difference is stored as a basis for subsequent risk calculations, ensuring that the model can call these data to quantify the synergistic effects of multiple raw material components during calculation.

[0048] S12. Real-time collection of current raw material component content data and input into the constructed production quality risk assessment model to calculate the risk level of each raw material component. If the absolute value of the calculated raw material component risk level is greater than the preset risk threshold, it is determined to be a production quality risk with a ratio deviation, and the ratio of the corresponding raw material component is adjusted according to the value of the risk level.

[0049] The current raw material component content data is collected in real time at a preset detection frequency. The collection device is an X-ray fluorescence spectrometer that has been calibrated at the raw material stage. After collection, the data is validated for validity, such as determining whether the data is within the instrument's detection range and whether there are any jumps. Invalid data is discarded to ensure the reliability of the data input into the model. In this embodiment of the invention, the preset detection frequency is consistent with the time interval in S10, which is 3 seconds. In other embodiments, the implementer can adjust this value according to the actual situation.

[0050] Furthermore, the verified real-time content data of the current raw material components is input into the constructed production quality risk assessment model. The model automatically calls the content stability interval parameters of the corresponding raw material components and calculates the deviation using the formula. =Real-time content - Interval benchmark value to calculate the deviation of each raw material component The model calls the stored... , Data, combined , , According to the risk formula Calculate and determine the risk level of each raw material component The system outputs risk level results to provide a basis for risk assessment. In this embodiment of the invention, the interval benchmark value is the midpoint or upper / lower limit of the interval, which can be set according to the process.

[0051] Furthermore, a preset risk threshold is established. In this embodiment of the invention, the preset risk threshold is 0.6. In other embodiments, the implementer may adjust this value according to the actual situation. This risk threshold is determined based on historical data from the production line. When the absolute value of the risk is greater than 0.6, the probability of product non-compliance due to deviation in product proportion exceeds 90%, requiring intervention measures to be triggered. For key raw material components, such as those that determine the soil pH regulation capacity, the threshold can be lowered to 0.5 to improve monitoring sensitivity.

[0052] Risk level of each raw material component Compare with a preset risk threshold: If If the concentration is ≤0.6, it is determined that there is no risk of proportioning deviation in the raw material composition, and no adjustment is required; if If the value is greater than 0.6, the raw material component is deemed to pose a production quality risk, and the formulation needs to be adjusted. If the risk level... A negative value indicates that the content of the corresponding raw material component is too low. The conveyor speed for this component during the mixing stage needs to be increased. Conveyor speed is positively correlated with the amount conveyed per unit time; increasing the speed can increase the amount of this raw material component input, compensating for the low content. If the risk level... A positive value indicates that the content of the corresponding raw material component is too high. It is necessary to reduce the conveyor speed of the conveyor belt during the mixing stage of the raw material component, reduce the input amount, and avoid imbalance in the ratio.

[0053] After adjustment, data on the content of raw material components are continuously collected and substituted into the model to recalculate the risk level until... With a concentration ≤0.6, dynamic optimization of the formulation is achieved to ensure that the final product meets quality requirements. Simultaneously, newly collected data is added to the model to recalculate raw material fluctuation coefficients, production fluctuation coefficients, fluctuation residues, and content stability ranges, enabling iterative updates to the risk assessment model and improving its adaptability to production changes.

[0054] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0055] Figure 2 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 2 As shown, the computer device 20 includes: a memory 21, a processor 22, and a computer program 23 stored in the memory 21 and running on the processor 22, wherein when the processor 22 executes the computer program 23, the computer device can execute the aforementioned production quality monitoring method for any mineral soil conditioner production line.

[0056] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform the production quality monitoring method for mineral soil conditioner production lines provided in embodiments of the present invention.

[0057] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0058] It should be understood that the apparatus provided in this embodiment of the invention is used to perform the above-described production quality monitoring method for mineral soil conditioner production lines, and therefore can achieve the same effect as the above-described implementation method.

[0059] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination of functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0060] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the production quality monitoring method for mineral soil conditioner production lines provided in the above embodiments.

[0061] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the production quality monitoring method for mineral soil conditioner production lines provided in the above embodiments.

[0062] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the production quality monitoring method for mineral soil conditioner production lines provided in the above embodiments.

[0063] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0064] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0065] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0066] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0068] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring the production quality of mineral soil conditioner production lines, characterized in that, The method includes the following steps: Collect data on the content of raw material components in each ore raw material in the mineral soil conditioner production line; Based on the collected raw material component content data, a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient is constructed, and the stable range of the raw material component content in each ore raw material is determined based on the correlation analysis model, thereby constructing a production quality risk assessment model. The system collects real-time data on the content of raw material components and inputs it into the constructed production quality risk assessment model to calculate the risk level of each raw material component. If the absolute value of the calculated risk level of a raw material component is greater than the preset risk threshold, it is determined to be a production quality risk with a ratio deviation, and the ratio of the corresponding raw material component is adjusted according to the value of the risk level.

2. The production quality monitoring method for mineral soil conditioner production lines according to claim 1, characterized in that, The data on the content of raw material components in each ore raw material in the mineral soil conditioner production line includes: Pre-set X-ray fluorescence spectrometers are installed on the conveying devices at the raw material stage and the reaction stage of the production line, respectively; The ore raw materials that have passed through the raw material stage are subjected to multiple component content tests at preset time intervals to obtain raw material component content data corresponding to the time intervals. Synchronously collect element content data at corresponding time intervals, and establish a time correspondence between the raw material component content data and element content data of the same batch of ore raw materials.

3. The production quality monitoring method for mineral soil conditioner production lines according to claim 2, characterized in that, The element content data collected synchronously at corresponding time intervals includes: During each time interval, the elemental content of the reaction product is simultaneously detected multiple times using the X-ray fluorescence spectrometer used in the reaction stage. The average value of multiple element content detection results is taken as the element content data of the reaction product within this time interval. Specifically, for raw material components whose molecular formula changes after the reaction stage, the main element content of the raw material component in the final product is determined as the detection object for element content detection.

4. The production quality monitoring method for mineral soil conditioner production lines according to claim 2, characterized in that, The raw material fluctuation coefficient and the production fluctuation coefficient are obtained through the following methods: The first deviation characteristic value of the raw material component content is determined based on the deviation between the real-time component content of the raw material in the ore raw material within each time interval and the average content of the raw material component over all time intervals; The reciprocal of the proportion of the corresponding raw material component in the formula is used as the first weight, and the first deviation characteristic value of the raw material component is combined with the first weight to calculate the raw material fluctuation coefficient of each raw material component in each time interval. The second deviation characteristic value of the content of the product after reaction is determined based on the deviation between the real-time component content of the product after reaction within each time interval and the average content of the raw material component over all time intervals. The yield fluctuation coefficient of each raw material component within each time interval is calculated by using the reciprocal of the proportion of the corresponding raw material component in the formula as the second weight, and combining the second deviation characteristic value of the product after the reaction with the second weight.

5. The production quality monitoring method for mineral soil conditioner production lines according to claim 1, characterized in that, The construction of the correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient includes: The raw material fluctuation coefficient of each raw material component is used as the x-coordinate of the coordinate system, and the production fluctuation coefficient of the corresponding raw material component is used as the y-coordinate of the coordinate system. The numerical combination of the raw material fluctuation coefficient and the production fluctuation coefficient of the same batch of ore raw materials at the same time interval is used as coordinate points and entered into the coordinate system. The coordinate point with the smallest absolute value of the raw material fluctuation coefficient is used as the initial point set, and other coordinate points are added to the initial point set in order of increasing absolute value of the raw material fluctuation coefficient to form multiple new point sets. Perform linear fitting on all coordinate points within each new point set to obtain the corresponding fitted line; By analyzing the characteristics of the fitted straight line, the overall level of the production fluctuation coefficient within multiple point sets, and the degree of deviation of each coordinate point from the fitted straight line, a correlation analysis model between the raw material fluctuation coefficient and the production fluctuation coefficient is constructed.

6. The production quality monitoring method for mineral soil conditioner production lines according to claim 5, characterized in that, The determination of the stable content range of raw material components in each ore raw material based on the correlation analysis model includes: Calculate the degree of division when each coordinate point in the correlation analysis model is used as a segmentation point; The coordinate point with the largest division degree is selected as the dividing point, and the residual state of fluctuation in the correlation analysis model is divided into a stable segment and a deviation segment. Extract the raw material component content data of the coordinate points corresponding to the stable segment, and perform outlier removal processing on the raw material component content data of the stable segment; The numerical range of raw material component content data in the stable segment after removing outliers is determined, and the numerical range is corrected according to a preset correction method. The corrected numerical range is then determined as the stable content range of raw material components in each of the ore raw materials.

7. The production quality monitoring method for mineral soil conditioner production lines according to claim 1, characterized in that, The construction of the production quality risk assessment model includes: Calculate the deviation between the real-time content of each of the raw material components and the corresponding stable content range of the raw material component, wherein the deviation is 0 when it is within the stable content range, negative when it is below the lower limit of the stable content range, and positive when it is above the upper limit of the stable content range; The number of components with positive deviations and the number of components with negative deviations in all the current raw ore materials are counted. By combining the magnitude of the deviations of each raw material component and the difference in the number of raw material components with positive and negative deviations, a production quality risk assessment model is generated to determine the risk level of each raw material component to the final product's blending quality.

8. The production quality monitoring method for mineral soil conditioner production lines according to claim 7, characterized in that, The real-time acquisition of current raw material component content data and its input into the constructed production quality risk assessment model are used to calculate the risk level of each raw material component, including: The current raw material component content data is collected in real time at a preset detection frequency and input into the constructed production quality risk assessment model; The production quality risk assessment model calculates the deviation of each current raw material component based on the real-time content data of each current raw material component and the corresponding stable content range of the current raw material component. The production quality risk assessment model calculates and determines the risk level of each current raw material component by combining the magnitude of the deviation of each current raw material component and the difference in the number of component types with positive and negative deviations.

9. The production quality monitoring method for mineral soil conditioner production lines according to claim 7, characterized in that, The statistical analysis of the number of component types with positive and negative deviations in the raw material composition of all the aforementioned ore raw materials includes: The deviation of the raw material composition of all the current ore raw materials is calculated. Components with deviations greater than 0 are marked, and the number of component types with positive deviations is accumulated. Components with deviations less than 0 are marked, and the number of components with negative deviations is accumulated. Record the difference between the number of component types with positive deviation and the number of component types with negative deviation, and store the number of component types and the difference as the basic parameters for subsequent risk degree calculation.

10. The production quality monitoring method for mineral soil conditioner production lines according to claim 1, characterized in that, The adjustment of the proportions of the corresponding raw material components based on the risk level includes: The risk level of each of the raw material components is compared with the preset risk threshold. When the absolute value of the risk level of a certain raw material component is greater than the risk threshold, it is determined that the proportion of the raw material component needs to be adjusted. If the risk level is negative, it indicates that the content of the corresponding raw material component is too low. In this case, the conveyor belt speed of the raw material component in the mixing stage is increased to increase the input of the raw material component. If the risk level is positive, it indicates that the content of the corresponding raw material component is too high. The conveyor belt speed of the raw material component in the mixing stage should be reduced to decrease the amount of the raw material component input.

Images