A method and system for treating graphite purification wastewater

Abstract

This invention provides a method and system for treating graphite purification wastewater, relating to the field of graphite purification wastewater treatment technology. The method includes collecting historical wastewater treatment data, extracting parameters based on process results to form historical process parameter data corresponding to different treatment processes; performing correlation analysis on the treatment results based on the historical process parameter data for different treatment processes to form process parameter correlation feature information for corresponding treatment processes; obtaining real-time process targets for different treatment processes, and combining the corresponding process parameter correlation feature data to perform efficiency-based process parameter analysis to form real-time process parameter information. This method allows for reasonable adjustments to the current wastewater treatment process to improve its energy efficiency in wastewater treatment.

Description

Technical Field

[0001] This invention relates to the field of graphite purification wastewater treatment technology, and more specifically, to a method and system for treating graphite purification wastewater. Background Technology

[0002] Graphite, also known as black lead, is an allotrope of carbon. It has low hardness, stable chemical properties, and does not readily react with acids and alkalis. It is also resistant to high temperatures, corrosion, thermal shock, and radiation; possesses high strength and toughness; and exhibits self-lubricating, electrical, and thermal conductivity. It is widely used in metallurgy, machinery, electronics, military, defense, and aerospace industries. The demand for graphite in social production and daily life is increasing with societal development, leading to a gradual increase in graphite production and purification. However, the graphite purification process generates large amounts of wastewater that pose serious environmental risks, making wastewater treatment a crucial management aspect of the graphite industry.

[0003] With scientific advancements, graphite purification methods have been improved and developed to varying degrees. Currently, the main purification methods include the alkali-acid method, the hydrofluoric acid method, the chlorination-calcination method, and the high-temperature method. There is also ongoing research and development into graphite purification processes to improve purity while simultaneously achieving effective wastewater treatment. However, this approach, primarily focused on adjusting process methods, presents significant challenges in development and implementation. Furthermore, the need for effective wastewater treatment based on current mature purification methods remains urgent.

[0004] Therefore, designing a method and system for treating graphite purification wastewater, and making reasonable adjustments to the current wastewater treatment process to improve its energy efficiency, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a method for treating graphite purification wastewater. By acquiring historical process parameter data of the wastewater treatment process, a reasonable correlation analysis is performed between process parameters and process result parameters. A correlation feature model between process parameters and process results is established, and then, based on this correlation feature model, effective control and adjustment of processing parameters for a given process objective are achieved. It is understood that, on the one hand, by using the correlation feature model, the control and adjustment of processing parameters corresponding to real-time process production can be quickly achieved, avoiding the waste of raw materials and energy caused by the lag in the impact of control parameter adjustments on the results in real-time process implementation, and accurately achieving process objectives. On the other hand, the control and adjustment of process parameters are based on efficiency, which can greatly improve the efficiency of process implementation and significantly improve the energy efficiency of wastewater treatment.

[0006] The present invention also aims to provide a treatment system for graphite purification wastewater. This system acquires historical data and real-time process target information required for data processing and analysis through a data acquisition unit, and performs reasonable feature extraction of historical data in a feature extraction unit to establish an effective correlation feature model. The real-time control and analysis unit realizes reasonable analysis of parameter control of process targets using the correlation feature model. The different units' power supply and data are closely linked to form a tight whole to achieve efficient and energy-saving wastewater treatment, which is an important material basis for completing the treatment of graphite purification wastewater.

[0007] In a first aspect, the present invention provides a method for treating graphite purification wastewater, comprising: collecting historical purification wastewater treatment data, extracting parameters based on process treatment results to form historical process treatment parameter data corresponding to different treatment processes; performing correlation analysis on the treatment results based on the historical process treatment parameter data corresponding to different treatment processes to form process treatment parameter correlation feature information for the corresponding treatment processes; obtaining real-time process targets for different treatment processes, and performing efficiency-based process parameter analysis in conjunction with the corresponding process treatment parameter correlation feature data to form real-time process parameter information.

[0008] In this invention, the method acquires historical process parameter data of the wastewater treatment process and performs a reasonable correlation analysis between process parameters and process results. This establishes a correlation characteristic model between process parameters and process results. Based on this model, effective control and adjustment of processing parameters for a given process objective are achieved. It is understood that, on the one hand, the correlation characteristic model allows for rapid control and adjustment of processing parameters in real-time process production, avoiding the waste of raw materials and energy caused by the lag in the impact of control parameter adjustments on results during real-time process implementation, and accurately achieving process objectives. On the other hand, the control and adjustment of process parameters are based on efficiency, which can greatly improve the efficiency of process implementation and significantly enhance the energy efficiency of wastewater treatment.

[0009] One possible approach is to collect historical wastewater treatment data and extract parameters based on the process results to form historical process treatment parameter data corresponding to different treatment processes. This includes: extracting process treatment parameter data for different batches of wastewater under different treatment processes based on historical wastewater treatment data; and clustering the process treatment parameter data corresponding to the same treatment process for different batches of wastewater to form historical process treatment parameter data corresponding to different treatment processes.

[0010] In this invention, correlation analysis is performed on historical wastewater treatment data for process treatment results. First, reasonable data preprocessing is required for the historical data. It is understood that correlation analysis for process treatment results has different correlation parameters for different treatment processes, and these correlation parameters will have different values ​​in different treatment batches. However, for correlation analysis of process treatment results, the data of different treatment batches under the same treatment process are merely different combinations of expressions under the correlation relationship. Therefore, correlation analysis can be achieved by using this combination expression. Based on this, the data preprocessing needs to extract the parameter data corresponding to all different treatment batches under the same treatment process to form parameter data that can achieve correlation analysis under the treatment process.

[0011] As one possible implementation, the process processing parameter data includes, but is not limited to, wastewater property parameter data, equipment parameter data necessary for implementing the process in the treatment process, and auxiliary material parameter data necessary for implementing the process in the treatment process.

[0012] In this invention, the relevant parameters selected for different treatment steps are different. Considering the characteristics of wastewater treatment processes, these parameters are mainly contained in three types of data. Among them, the wastewater property parameter data mainly includes the parameter data of specific substances and physicochemical properties that need to achieve the process objectives in different steps, such as pH value and concentration of specific metal ions. The parameter data of the equipment necessary to implement the process in the treatment steps mainly includes the control parameters of the equipment necessary to achieve the process objectives in different steps, such as stirring rate, permeability of reverse osmosis device, and control temperature. The parameter data of the additives necessary to implement the process in the treatment steps mainly includes the parameter data of the excipients that must be added in different steps to achieve the process objectives, such as total amount added, addition rate, and material concentration value. Understandably, for a specific wastewater treatment process, the operation method of each step is predetermined. The key to achieving the process objectives lies in how to control the parameters within each step. Process parameters at different steps can be acquired and determined using data acquisition instruments, equipment control units, and other power supply units with input and control adjustment capabilities. Furthermore, the Internet of Things and big data can be used to collect and process parameter data, ensuring the rationality and accuracy of the data source.

[0013] As one possible approach, correlation analysis is performed on the processing results based on historical processing parameter data corresponding to different processing steps to form correlation feature information of the processing parameters of the corresponding processing steps. This includes: extracting parameter values ​​of the processing parameters according to the processing batches from the historical processing parameter data corresponding to the same processing step to establish quantitative data of the processing parameters of the corresponding batches; and performing correlation analysis on the quantitative data of the processing parameters of the batches corresponding to different processing batches of the same processing step to form correlation feature data of the processing parameters of the corresponding processing steps.

[0014] In this invention, after obtaining the parameter data of all processing batches under the processing step, correlation analysis can be performed to extract the corresponding feature information. To conduct a reasonable correlation analysis, the parameter values ​​need to be extracted and processed appropriately. Therefore, it is first necessary to extract the quantified values ​​of the relevant parameters to form quantified data, and then perform a reasonable correlation analysis on the quantified data to form the correlation feature data corresponding to the processing step.

[0015] As one possible implementation, for historical process parameter data corresponding to the same treatment process, parameter values ​​are extracted according to treatment batches to establish corresponding batch-specific quantitative data of process parameters. This includes: extracting wastewater property parameter values ​​for different treatment batches from historical process parameter data corresponding to the same treatment process, and determining the relative changes in wastewater property parameters relative to baseline wastewater property parameters; extracting equipment control parameter values ​​for different treatment batches from historical process parameter data corresponding to the same treatment process, and determining the relative changes in equipment control parameter values ​​relative to baseline equipment control parameters; and extracting equipment control parameter values ​​for different treatment batches from historical process parameter data corresponding to the same treatment process. For process processing parameter data, extract auxiliary material parameter values ​​for different processing batches and determine the relative changes of different auxiliary material parameter values ​​relative to the auxiliary material baseline parameter values; for historical process processing parameter data corresponding to the same processing process, extract process processing result parameter values ​​for different processing batches and determine the relative changes of process processing result parameter values ​​relative to the process processing baseline result values; for all relative changes of different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and process processing result values ​​corresponding to different processing batches under the same processing process, conduct multi-parameter change relationship analysis and establish corresponding process batch processing parameter quantification models.

[0016] In this invention, it is understood that quantifying the relevant parameters affecting the processing results of a processing step, if analysis is based solely on the parameter values, the inherent correlations and constraints between different parameters lead to varying value ranges for different processing batches, resulting in an inconsistent analytical basis. Specifically, the selection of parameter values ​​varies across different processing batches, making direct analysis based on parameter values ​​unreasonable for extracting relevant feature information. This unreasonableness manifests in subsequent real-time process analysis within models built using parameter values, and the parameter values ​​determined by the model may be unattainable in actual process implementation. Therefore, this application establishes a common benchmark for parameters by acquiring relative quantities, ensuring the rationality and accuracy of data analysis. The benchmark data can be based on parameter values ​​from any processing batch in historical data, or it can be uniformly set according to actual conditions to improve the convenience of data processing.

[0017] As one possible approach, a multi-parameter variation relationship analysis is performed on the relative changes of all different wastewater property parameters, equipment control parameters, auxiliary material parameters, and process results for different batches under the same treatment process. This establishes a corresponding quantitative model for the process batch treatment parameters. This includes: clustering the relative changes of all different wastewater property parameters, equipment control parameters, auxiliary material parameters, and process results for different batches to form process batch parameter relative change data groups; and performing multi-parameter variation relationship analysis on the process batch parameter relative change data groups corresponding to different batches in the following manner: [The analysis involves] clustering the relative changes of all parameters for different batches... By comparison, if a parameter of a certain type changes in relative value and the corresponding result shows a linear trend, then the parameter of that type is labeled as a linear process influence parameter value. The number of parameter relative change value types is gradually increased until no more parameter relative change values ​​are labeled as linear process influence parameters. All remaining parameter relative change values ​​that have not been labeled as linear process influence parameters are labeled as non-linear process influence parameters. Based on the labeling of all parameter relative change values, the following process batch processing parameter quantification model is established for all relative change values ​​of different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and process processing results for each processing batch: Where n represents the number of the relative change value of different parameters that are calibrated as linear process influence parameters. This represents the relative change value of parameter number n, which is calibrated as a linear process and affects the parameter value. The linear polynomial, and , Represents the relative change of the parameter. The constant of the first term, Represents the relative change of the parameter. The linear constant term, m, represents the number of the relative change value of different parameters calibrated as nonlinear process influence parameters. The relative change value of parameter number m, which is calibrated as an influence parameter of nonlinear process. The linear high-order power term, where k represents the relative change value of parameter m, which is calibrated as a nonlinear process influence parameter. The highest power corresponding to the linear power term. , Represents the relative change of the parameter. The constant of the kth power term, This represents the power constant term.

[0018] In this invention, it should be noted that different parameters in the processing steps have different degrees and ways of influencing the processing results. This difference is translated into whether the correlation between the parameters and the processing results exhibits linearity or nonlinearity in the model. Therefore, it is necessary to reasonably determine the form of the correlation between the parameters and the processing results. It is understandable that conducting trend analysis on the relative changes in the results of multiple parameters aims to determine the pattern of change in the relative changes in the results caused by numerical changes in the relative changes of parameters of a certain type across multiple processing batches. For the analysis of linear trends, considering the inherent error in the data, variance can be used to eliminate the influence of error on the judgment of linear trends. Of course, the limits of variance analysis can be determined through big data analysis. Furthermore, for the linear trend analysis process, it's considered to synchronize the changing directions of multiple parameters. This involves sorting and comparing the relative changes of multiple parameters across different processing batches according to the direction of their numerical change. For example, sorting different batches of data with the numerical value gradually increasing could be used. Of course, different parameters may not have a unified direction in their relative changes. That is, if the processing batch data is sorted based on the increasing trend of any single parameter's relative change, some parameters might show a gradually decreasing relative change. This does not affect the analysis of linear trends, because if the parameters and the resulting parameters have a linear influence, then sorting will exhibit a linear change under a defined batch order. Additionally, for nonlinear trends, the magnitude of the power in the nonlinear terminology, especially in power terms, can be determined based on actual needs or further multi-parameter analysis.

[0019] As one possible implementation, correlation analysis is performed on the quantitative data of process batch processing parameters corresponding to different processing batches under the same processing procedure to form correlation feature data of process processing parameters corresponding to the processing procedure. This includes: a quantitative model of all process batch processing parameters corresponding to different processing batches under the same processing procedure. The following correlation analysis was performed: The batch processing parameter quantification model corresponding to any batch of processing is selected with the same number of unknown constants as the batch processing parameter quantification model. The process involves determining the values ​​of all unknown constants to form an initial process processing parameter quantification model. For the remaining processing batches, one batch of data is randomly selected each time, and the relative change values ​​of all corresponding parameters are substituted into the relative change values ​​of the model results obtained from the initial process processing parameter quantification model. The difference between the relative change value of the model results and the relative change value of the corresponding process processing results is then determined. Two adjacent differences are compared, and if the difference in the latter is larger, the data of the latter batch is deleted. The comparison of adjacent differences is performed sequentially to obtain the selected processing batches with a sorted order. Based on the order of the selected processing batches, and using the relative change values ​​of the process processing results and the relative change values ​​of all parameters corresponding to the processing batches as a benchmark, the constants in the initial process processing parameter quantification model are gradually adjusted to ultimately form a process processing parameter correlation feature model.

[0020] In this invention, the resulting batch processing parameter quantification model consists of data with definite parameter values ​​but different parameter positions within the model's relational formula. Reasonable unknown constants are determined by mapping the parameter data across different processing batches to the processing results. Of course, historical processing batch data is enormous; determining unknown constants only requires a number of processing batches equal to the number of unknown constant data. Considering the accuracy of the established model, this application establishes a reasonable accuracy adjustment direction by arbitrarily filtering the remaining processing batch data, thereby effectively ensuring that the adjusted model is more accurate and reasonable.

[0021] One possible approach is to acquire real-time process targets for different processing steps and perform efficiency-based process parameter analysis by combining the corresponding process processing parameter correlation feature data to form real-time process parameter information. This includes: for different processing steps, determining the relative change value of the real-time process processing result based on the corresponding real-time process target and the process processing baseline result value; for different processing steps, determining the combination of different parameter relative change values ​​to achieve the relative change value of the real-time process processing result based on the corresponding real-time process processing result relative change value and the process processing parameter correlation feature model, forming real-time process parameter value selection combination data; performing a comparative analysis of the real-time process parameter value selection combination data on process processing efficiency to determine the optimal process parameter value combination; and determining the parameter values ​​corresponding to different parameters based on the optimal process parameter value combination, thus forming real-time process parameter information.

[0022] In this invention, after establishing the feature models corresponding to different processing steps, the models can be used to control or adjust the real-time process parameters. It is understood that since the parameters involved in the model are related to the processing results, the selection of parameters is formed in the form of parameter value groups, and there are various options. As for how to select a reasonable combination of parameters, this application determines the best combination of parameters by considering the energy efficiency consumed by the process implementation. The results obtained in this way are more in line with the actual production situation and needs, and can reduce the overall processing cost to a certain extent.

[0023] As one possible approach, a comparative analysis of the process processing efficiency is performed on the real-time process parameter value selection combination data to determine the optimal process parameter value combination. This includes determining the corresponding total energy consumption of the process for different parameter combinations in the real-time process parameter value selection combination data. Total process time Where i represents the number of different parameter combinations in the real-time process parameter value selection combination data; for different parameter combinations, based on the corresponding total energy consumption of the process. Total process time Determine the process efficiency value ,in, α represents the energy consumption weighting ratio, β represents the time weighting ratio, and α+β=1; determine the process efficiency value in different parameter combinations. The smallest combination of parameters is calibrated as the optimal combination of process parameter values.

[0024] In this invention, the energy efficiency analysis mainly includes the energy consumption required to complete the process processing target by setting these parameters in the process, as well as the completion time after setting the parameters. For different processes or actual needs, the energy efficiency analysis will have different emphases. This emphase is adjusted by the weight ratio to ensure the rationality and accuracy of the analysis.

[0025] Secondly, the present invention provides a treatment system for graphite purification wastewater, comprising: a data acquisition unit for acquiring historical purification wastewater treatment data and real-time process targets; a feature extraction unit for extracting parameters based on the historical purification wastewater treatment data acquired by the data acquisition unit to form historical process treatment parameter data for different treatment processes, and performing correlation analysis on the treatment results to form process treatment parameter correlation feature information for the corresponding treatment processes; and a real-time control analysis unit for performing efficiency-based process parameter analysis based on the real-time process targets acquired by the data acquisition unit and combined with the process treatment parameter correlation feature information formed by the feature extraction unit to form real-time process parameter information.

[0026] In this invention, the system acquires historical data and real-time process target information required for data processing and analysis through the data acquisition unit, and completes reasonable feature extraction of historical data in the feature extraction unit to establish an effective correlation feature model. The real-time control analysis unit realizes reasonable analysis of parameter control of process targets using the correlation feature model. The different unit power supply and data are closely linked to each other, forming a tight whole to achieve efficient and energy-saving wastewater treatment, which is an important material basis for completing the treatment of graphite purification wastewater.

[0027] The beneficial effects of the graphite purification wastewater treatment method and system provided by this invention are as follows: This method acquires historical process parameter data for wastewater treatment and performs a reasonable correlation analysis between process parameters and process outcome parameters. It establishes a correlation characteristic model between process parameters and process outcomes, and then uses this model to effectively control and adjust the processing parameters for a given process objective. This means that, on the one hand, the correlation characteristic model allows for rapid control and adjustment of the corresponding processing parameters in real-time process production, avoiding the waste of raw materials and energy caused by the lag in the impact of control parameter adjustments on the results during real-time process implementation, and accurately achieving process objectives. On the other hand, controlling and adjusting process parameters based on efficiency can significantly improve the efficiency of process implementation and the energy efficiency of wastewater treatment.

[0028] The system acquires historical data and real-time process target information required for data processing and analysis through the data acquisition unit, and completes reasonable feature extraction of historical data in the feature extraction unit to establish an effective correlation feature model. The real-time control and analysis unit realizes reasonable analysis of parameter control of process targets using the correlation feature model. The different units' power supply and data are closely linked to form a tight whole to achieve efficient and energy-saving wastewater treatment, which is an important material basis for completing the treatment of graphite purification wastewater. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A step diagram illustrating a method for treating graphite purification wastewater according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a graphite purification wastewater treatment system provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0032] Graphite, also known as black lead, is an allotrope of carbon. It has low hardness, stable chemical properties, and does not readily react with acids and alkalis. It is also resistant to high temperatures, corrosion, thermal shock, and radiation; possesses high strength and toughness; and exhibits self-lubricating, electrical, and thermal conductivity. It is widely used in metallurgy, machinery, electronics, military, defense, and aerospace industries. The demand for graphite in social production and daily life is increasing with societal development, leading to a gradual increase in graphite production and purification. However, the graphite purification process generates large amounts of wastewater that pose serious environmental risks, making wastewater treatment a crucial management aspect of the graphite industry.

[0033] With scientific advancements, graphite purification methods have been improved and developed to varying degrees. Currently, the main purification methods include the alkali-acid method, the hydrofluoric acid method, the chlorination-calcination method, and the high-temperature method. There is also ongoing research and development into graphite purification processes to improve purity while simultaneously achieving effective wastewater treatment. However, this approach, primarily focused on adjusting process methods, presents significant challenges in development and implementation. Furthermore, the need for effective wastewater treatment based on current mature purification methods remains urgent.

[0034] refer to Figures 1-2This invention provides a method for treating graphite purification wastewater. This method acquires historical process parameter data of the wastewater treatment process and performs a reasonable correlation analysis between process parameters and process results. A correlation feature model is established between process parameters and process results. Based on this model, effective control and adjustment of processing parameters for a given process objective are achieved. It is understood that, on the one hand, the correlation feature model allows for rapid control and adjustment of processing parameters corresponding to real-time process production, avoiding the waste of raw materials and energy caused by the lag in the impact of control parameter adjustments on results during real-time process implementation, and accurately achieving process objectives. On the other hand, the control and adjustment of process parameters are based on efficiency, which can greatly improve the efficiency of process implementation and significantly improve the energy efficiency of wastewater treatment.

[0035] A method for treating graphite purification wastewater specifically includes the following steps: S1: Collect historical wastewater treatment data and extract parameters based on the process treatment results to form historical process treatment parameter data corresponding to different treatment processes.

[0036] Historical wastewater treatment data is collected, and parameters are extracted based on the process treatment results to form historical process treatment parameter data corresponding to different treatment processes. This includes: extracting process treatment parameter data for different batches of wastewater under different treatment processes based on historical wastewater treatment data; and clustering the process treatment parameter data corresponding to the same treatment process for different batches of wastewater to form historical process treatment parameter data corresponding to different treatment processes.

[0037] To conduct correlation analysis on historical wastewater treatment data for specific process results, the first step is to perform appropriate data preprocessing. It's understandable that correlation analysis for process results involves different correlation parameters for different treatment processes, and these parameters may have different values ​​in different batches. However, for correlation analysis of process results, the data from different batches under the same treatment process are simply different combinations of correlation relationships. Therefore, this combination can be used to achieve correlation analysis. Based on this, the data preprocessing needs to extract the parameter data corresponding to all different batches under the same treatment process, forming parameter data that allows for correlation analysis under each treatment process.

[0038] Processing parameter data includes, but is not limited to, wastewater property parameters, equipment parameters necessary for implementing the process, and auxiliary material parameters necessary for implementing the process.

[0039] The relevant parameters selected for different treatment processes are different. Considering the characteristics of wastewater treatment processes, these parameters are mainly contained in three types of data. Among them, the data on the properties of wastewater mainly includes the parameters of specific substances and physicochemical properties that need to be achieved in different processes, such as pH value and concentration of specific metal ions. The data on the parameters of the equipment necessary to implement the treatment process mainly includes the control parameters of the equipment necessary to achieve the process objectives in different processes, such as stirring rate, permeability of reverse osmosis device, and control temperature. The data on the parameters of the additives necessary to implement the treatment process mainly includes the parameters of the excipients that must be added in different processes to achieve the process objectives, such as total amount added, addition rate, and material concentration value. Understandably, for a specific wastewater treatment process, the operation method of each step is predetermined. The key to achieving the process objectives lies in how to control the parameters within each step. Process parameters at different steps can be acquired and determined using data acquisition instruments, equipment control units, and other power supply units with input and control adjustment capabilities. Furthermore, the Internet of Things and big data can be used to collect and process parameter data, ensuring the rationality and accuracy of the data source.

[0040] S2: Based on the historical process parameter data corresponding to different processing steps, conduct correlation analysis on the processing results to form the process parameter correlation feature information of the corresponding processing steps.

[0041] Based on the historical process parameter data corresponding to different processing steps, a correlation analysis is performed on the processing results to form the process processing parameter correlation feature information of the corresponding processing steps. This includes: extracting the parameter values ​​of the processing parameters according to the processing batch for the historical process processing parameter data corresponding to the same processing step, and establishing the corresponding process batch processing parameter quantitative data; and performing correlation analysis on the process batch processing parameter quantitative data corresponding to different processing batches of the same processing step to form the process processing parameter correlation feature data of the processing steps.

[0042] After obtaining the parameter data for all batches in the processing procedure, correlation analysis can be performed to extract the corresponding feature information. However, to conduct a reasonable correlation analysis, the parameter values ​​need to be properly extracted and processed. Therefore, the first step is to extract the quantified values ​​of the relevant parameters to form quantified data, and then perform a reasonable correlation analysis on the quantified data to form the correlation feature data corresponding to the processing procedure.

[0043] For historical process parameter data corresponding to the same treatment process, parameter values ​​are extracted according to treatment batches to establish corresponding batch-specific quantitative data of process parameters. This includes: extracting wastewater property parameter values ​​for different treatment batches from historical process parameter data corresponding to the same treatment process, and determining the relative changes in wastewater property parameters relative to baseline wastewater property parameters; extracting equipment control parameter values ​​for different treatment batches from historical process parameter data corresponding to the same treatment process, and determining the relative changes in equipment control parameter values ​​relative to baseline equipment control parameters; and extracting equipment control parameter values ​​for different batches from historical process parameter data corresponding to the same treatment process. Data was collected to extract auxiliary material parameter values ​​for different treatment batches, and the relative changes of different auxiliary material parameter values ​​relative to the auxiliary material baseline parameter values ​​were determined. For historical process processing parameter data corresponding to the same processing process, process processing result parameter values ​​for different processing batches were extracted, and the relative changes of process processing result parameter values ​​relative to the process processing baseline result values ​​were determined. For the relative changes of all different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and process processing result values ​​corresponding to different treatment batches under the same processing process, multi-parameter change relationship analysis was performed to establish a corresponding process batch processing parameter quantification model.

[0044] It is understandable that quantifying the parameters affecting the processing results of a process step, if analysis is based solely on the parameter values, will lead to inconsistencies in the analytical basis due to the inherent correlations and constraints between different parameters, resulting in varying value ranges for different processing batches. In other words, the selection of parameter values ​​within different ranges for different processing batches makes direct analysis based on parameter values ​​unreasonable in extracting relevant feature information. This unreasonableness will manifest in subsequent real-time process analysis in models built using parameter values, and the parameter values ​​determined by the model may be unattainable in actual process implementation. Therefore, this application establishes a common benchmark for parameters by acquiring relative quantities, ensuring the rationality and accuracy of data analysis. The benchmark data can be based on parameter values ​​from any processing batch in historical data, or it can be uniformly set according to actual conditions to improve the convenience of data processing.

[0045] For different batches of the same treatment process, a multi-parameter variation relationship analysis is performed on the relative changes of all different wastewater property parameters, equipment control parameters, auxiliary material parameters, and process treatment results. A corresponding quantitative model of the process batch treatment parameters is established, including: clustering the relative changes of all different wastewater property parameters, equipment control parameters, auxiliary material parameters, and process treatment results of different batches to form process batch parameter relative change data groups; and performing multi-parameter variation relationship analysis on the process batch parameter relative change data groups corresponding to different batches in the following manner: comparing the relative changes of all parameters in different batches... When a parameter of a certain type changes in relative value, and the corresponding relative change in result exhibits a linear trend, then the relative change in parameter of that type is labeled as a linear process influence parameter value. The number of parameter relative change value types is gradually increased until no more parameter relative change values ​​are labeled as linear process influence parameters. All remaining parameter relative change values ​​of the types that have not been labeled as linear process influence parameters are labeled as non-linear process influence parameters. Based on the labeling of all parameter relative change values, the following process batch processing parameter quantification model is established for the relative change values ​​of all different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and the relative change values ​​of process processing results for each processing batch: Where n represents the number of the relative change value of different parameters that are calibrated as linear process influence parameters. This represents the relative change value of parameter number n, which is calibrated as a linear process and affects the parameter value. The linear polynomial, and , Represents the relative change of the parameter. The constant of the first term, Represents the relative change of the parameter. The linear constant term, m, represents the number of the relative change value of different parameters calibrated as nonlinear process influence parameters. The relative change value of parameter number m, which is calibrated as an influence parameter of nonlinear process. The linear high-order power term, where k represents the relative change value of parameter m, which is calibrated as a nonlinear process influence parameter. The highest power corresponding to the linear power term. , Represents the relative change of the parameter. The constant of the kth power term, This represents the power constant term.

[0046] It should be noted that different parameters in the processing steps have different degrees and ways of affecting the processing results. This difference translates into whether the correlation between the parameters and the processing results exhibits linearity or nonlinearity in the model. Therefore, it is necessary to reasonably determine the form of the correlation between the parameters and the processing results. Understandably, the purpose of trend analysis on the relative changes in the results of multiple parameters is to determine the pattern of change in the relative changes in the results caused by numerical changes in the relative changes of a certain type of parameter across multiple processing batches. For the analysis of linear trends, considering the inherent error in the data, variance can be used to eliminate the influence of error on the judgment of linear trends. Of course, the limits of variance analysis can be determined through big data analysis. Furthermore, for the linear trend analysis process, it's considered to synchronize the changing directions of multiple parameters. This involves sorting and comparing the relative changes of multiple parameters across different processing batches according to the direction of their numerical change. For example, sorting different batches of data with the numerical value gradually increasing could be used. Of course, different parameters may not have a unified direction in their relative changes. That is, if the processing batch data is sorted based on the increasing trend of any single parameter's relative change, some parameters might show a gradually decreasing relative change. This does not affect the analysis of linear trends, because if the parameters and the resulting parameters have a linear influence, then sorting will exhibit a linear change under a defined batch order. Additionally, for nonlinear trends, the magnitude of the power in the nonlinear terminology, especially in power terms, can be determined based on actual needs or further multi-parameter analysis.

[0047] Correlation analysis is performed on the quantitative data of process batch processing parameters corresponding to different processing batches under the same processing procedure to form correlation feature data of process processing parameters corresponding to the processing procedure, including: quantitative models of all process batch processing parameters corresponding to different processing batches under the same processing procedure. The following correlation analysis was performed: The batch processing parameter quantification model corresponding to any batch of processing is selected with the same number of unknown constants as the batch processing parameter quantification model. The process involves determining the values ​​of all unknown constants to form an initial process processing parameter quantification model. For the remaining processing batches, one batch of data is randomly selected each time, and the relative change values ​​of all corresponding parameters are substituted into the relative change values ​​of the model results obtained from the initial process processing parameter quantification model. The difference between the relative change value of the model results and the relative change value of the corresponding process processing results is then determined. Two adjacent differences are compared, and if the difference in the latter is larger, the data of the latter batch is deleted. The comparison of adjacent differences is performed sequentially to obtain the selected processing batches with a sorted order. Based on the order of the selected processing batches, and using the relative change values ​​of the process processing results and the relative change values ​​of all parameters corresponding to the processing batches as a benchmark, the constants in the initial process processing parameter quantification model are gradually adjusted to ultimately form a process processing parameter correlation feature model.

[0048] The resulting batch processing parameter quantification model consists of data with definite parameter values ​​but different parameter positions within the model's relational formula. Reasonable unknown constants are determined by mapping the parameter data across different processing batches to the processing results. Of course, the historical batch data is enormous; determining the unknown constants only requires a number of batches equal to the number of unknown constant data. Considering the accuracy of the established model, this application establishes a reasonable accuracy adjustment direction by arbitrarily filtering the remaining processing batch data, thereby effectively ensuring that the adjusted model is more accurate and reasonable.

[0049] S3: Obtain the real-time process targets for different processing steps, and combine them with the corresponding process processing parameter correlation feature data to perform efficiency-based process parameter analysis, forming real-time process parameter information.

[0050] The system acquires real-time process targets for different processing steps and performs efficiency-based process parameter analysis based on the corresponding process processing parameter correlation feature data to form real-time process parameter information. This includes: determining the relative change value of the real-time process processing result for different processing steps based on the corresponding real-time process target and the process processing baseline result value; determining different combinations of relative change values ​​of parameters to achieve the relative change value of the real-time process processing result based on the corresponding relative change value of the real-time process processing result and the process processing parameter correlation feature model, forming real-time process parameter value selection combination data; conducting a comparative analysis of the real-time process parameter value selection combination data for process processing efficiency to determine the optimal process parameter value combination; and determining the parameter values ​​corresponding to different parameters based on the optimal process parameter value combination, thus forming real-time process parameter information.

[0051] After establishing the feature models corresponding to different processing steps, the models can be used to control or adjust the real-time process parameters. It is understandable that since the parameters involved in the model are related to the processing results, the selection of parameters is formed in the form of parameter value groups, and there are various options. As for how to select a reasonable parameter combination, this application determines the best parameter combination by considering the energy efficiency consumed by the process implementation. The results obtained in this way are more in line with the actual production situation and needs, and can reduce the overall processing cost to a certain extent.

[0052] A comparative analysis of process processing efficiency is performed on real-time process parameter value selection and combination data to determine the optimal process parameter value combination. This includes determining the corresponding total energy consumption of different parameter combinations in the real-time process parameter value selection and combination data. Total process time Where i represents the number of different parameter combinations in the real-time process parameter value selection combination data; for different parameter combinations, based on the corresponding total energy consumption of the process. Total process time Determine the process efficiency value ,in, α represents the energy consumption weighting ratio, β represents the time weighting ratio, and α+β=1; determine the process efficiency value in different parameter combinations. The smallest combination of parameters is calibrated as the optimal combination of process parameter values.

[0053] Energy efficiency analysis mainly includes the energy consumption required to complete the process target by setting these parameters in the process, as well as the completion time after setting the parameters. For different processes or actual needs, the energy efficiency analysis will have different focuses. This focus is adjusted by weighting ratio to ensure the rationality and accuracy of the analysis.

[0054] The present invention also provides a treatment system for graphite purification wastewater, the system comprising: a data acquisition unit for acquiring historical purification wastewater treatment data and real-time process targets; a feature extraction unit for extracting parameters based on the historical purification wastewater treatment data acquired by the data acquisition unit to form historical process treatment parameter data for different treatment processes, and performing correlation analysis on the treatment results to form process treatment parameter correlation feature information for the corresponding treatment processes; and a real-time control analysis unit for performing efficiency-based process parameter analysis based on the real-time process targets acquired by the data acquisition unit and combined with the process treatment parameter correlation feature information formed by the feature extraction unit to form real-time process parameter information.

[0055] The system acquires historical data and real-time process target information required for data processing and analysis through the data acquisition unit, and completes reasonable feature extraction of historical data in the feature extraction unit to establish an effective correlation feature model. The real-time control and analysis unit realizes reasonable analysis of parameter control of process targets using the correlation feature model. The different units' power supply and data are closely linked to form a tight whole to achieve efficient and energy-saving wastewater treatment, which is an important material basis for completing the treatment of graphite purification wastewater.

[0056] In summary, the beneficial effects of the graphite purification wastewater treatment method and system provided by the embodiments of the present invention are as follows: This method acquires historical process parameter data for wastewater treatment and performs a reasonable correlation analysis between process parameters and process outcome parameters. It establishes a correlation characteristic model between process parameters and process outcomes, and then uses this model to effectively control and adjust the processing parameters for a given process objective. This means that, on the one hand, the correlation characteristic model allows for rapid control and adjustment of the corresponding processing parameters in real-time process production, avoiding the waste of raw materials and energy caused by the lag in the impact of control parameter adjustments on the results during real-time process implementation, and accurately achieving process objectives. On the other hand, controlling and adjusting process parameters based on efficiency can significantly improve the efficiency of process implementation and the energy efficiency of wastewater treatment.

[0057] The system acquires historical data and real-time process target information required for data processing and analysis through the data acquisition unit, and completes reasonable feature extraction of historical data in the feature extraction unit to establish an effective correlation feature model. The real-time control and analysis unit realizes reasonable analysis of parameter control of process targets using the correlation feature model. The different units' power supply and data are closely linked to form a tight whole to achieve efficient and energy-saving wastewater treatment, which is an important material basis for completing the treatment of graphite purification wastewater.

[0058] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0059] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0060] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0061] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0062] The “protocol” mentioned in the embodiments of this application may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. The embodiments of this application do not specifically limit this.

[0063] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0064] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0065] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0066] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0067] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0068] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0069] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0070] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0071] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0072] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, 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 apparatuses or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0076] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for treating graphite purification wastewater, characterized in that, include: Collect historical wastewater treatment data, extract parameters based on process treatment results, and generate historical process treatment parameter data corresponding to different treatment processes; Based on the historical process processing parameter data corresponding to different processing steps, a correlation analysis is performed on the processing results to form process processing parameter correlation feature information for the corresponding processing steps. The real-time process targets for different processing steps are obtained, and efficiency-based process parameter analysis is performed by combining the corresponding process processing parameter correlation feature data to form real-time process parameter information.

2. The method for treating graphite purification wastewater according to claim 1, characterized in that, The process involves collecting historical wastewater treatment data, extracting parameters based on the process results, and generating historical process parameter data for different treatment processes, including: Based on the historical wastewater treatment data, process treatment parameter data of different batches of wastewater under different treatment processes were extracted. Cluster the process treatment parameter data corresponding to the same treatment process for different batches of wastewater to form historical process treatment parameter data corresponding to different treatment processes.

3. The method for treating graphite purification wastewater according to claim 2, characterized in that, The process processing parameter data includes, but is not limited to, wastewater property parameter data, equipment parameter data necessary for implementing the process in the treatment process, and auxiliary material parameter data necessary for implementing the process in the treatment process.

4. The method for treating graphite purification wastewater according to claim 2, characterized in that, The step involves performing a correlation analysis on the processing results based on the historical processing parameter data corresponding to different processing steps, forming correlation feature information of the processing parameters for the corresponding processing steps, including: For the historical process processing parameter data corresponding to the same processing process, the parameter values ​​of the processing parameters are extracted according to the processing batch, and the corresponding process batch processing parameter quantitative data is established. Correlation analysis is performed on the quantitative data of the process batch processing parameters corresponding to different processing batches of the same processing process to form the correlation feature data of the process processing parameters corresponding to the processing process.

5. The method for treating graphite purification wastewater according to claim 4, characterized in that, The historical process processing parameter data corresponding to the same processing step is processed by extracting parameter values ​​according to the processing batch, and establishing corresponding batch processing parameter quantification data, including: For the historical process processing parameter data corresponding to the same processing process, extract the wastewater property parameter values ​​of different processing batches, and determine the relative change value of the wastewater property parameter values ​​relative to the wastewater property reference parameter value; For the historical process processing parameter data corresponding to the same processing process, extract the equipment control parameter values ​​of different processing batches, and determine the relative change value of the equipment control parameter values ​​relative to the equipment control reference parameter values. For the historical process processing parameter data corresponding to the same processing process, extract the auxiliary material parameter values ​​of different processing batches, and determine the relative change value of the auxiliary material parameter values ​​relative to the auxiliary material reference parameter values. For the historical process processing parameter data corresponding to the same processing process, extract the process processing result parameter values ​​corresponding to different processing batches, and determine the relative change value of the process processing result parameter value relative to the process processing baseline result value. For the relative changes of all different wastewater property parameters, equipment control parameters, auxiliary material parameters, and process results corresponding to different batches under the same processing procedure, a multi-parameter change relationship analysis is performed to establish a corresponding process batch processing parameter quantification model.

6. The method for treating graphite purification wastewater according to claim 5, characterized in that, The method involves performing multi-parameter variation relationship analysis on the relative changes of all different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and the relative changes of the process processing results for different batches under the same processing procedure, and establishing a corresponding quantitative model for the process batch processing parameters, including: Cluster the relative change values ​​of all different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and the relative change values ​​of process processing results for different batches of treatment to form a process batch parameter relative change data group; For the data sets of relative changes in process batch parameters corresponding to different processing batches, perform multi-parameter change relationship analysis in the following manner: Compare the relative changes of all parameters in different processing batches. If there is a parameter of a certain type whose relative change value changes and the corresponding relative change value shows a linear trend, then the parameter of that type is labeled as a parameter value affected by the linear process. Gradually increase the number of types of relative change values ​​for parameters until no more relative change values ​​of parameters that are calibrated as linear processes affect parameter values ​​appear. The relative change values ​​of all remaining types of parameters that have not been calibrated as linear process influence parameters are calibrated as nonlinear process influence parameters. Based on the calibration of the relative change values ​​of all parameters, the following process batch processing parameter quantification model is established for the relative change values ​​of all different wastewater property parameters, different equipment control parameters, different auxiliary material parameters, and the relative change values ​​of the process processing results corresponding to each processing batch: Where n represents the number of the relative change value of different parameters that are calibrated as linear process influence parameters. This represents the relative change value of parameter number n, which is calibrated as a linear process and affects the parameter value. The linear polynomial, and , Represents the relative change of the parameter. The constant of the first term, Represents the relative change of the parameter. The linear constant term, m, represents the number of the relative change value of different parameters calibrated as nonlinear process influence parameters. The relative change value of parameter number m, which is calibrated as an influence parameter of nonlinear process. The linear high-order power term, where k represents the relative change value of parameter m, which is calibrated as a nonlinear process influence parameter. The highest power corresponding to the linear power term. , Represents the relative change of the parameter. The constant of the kth power term, This represents the power constant term.

7. The method for treating graphite purification wastewater according to claim 6, characterized in that, The correlation analysis of the quantitative data of the batch processing parameters of different processing batches corresponding to the same processing process is performed to form the correlation feature data of the processing parameters corresponding to the processing process, including: A quantitative model for the processing parameters of all batches of the same processing procedure, corresponding to different batches. The following correlation analysis methods were used: Arbitrarily select a batch of processes with the same number of unknown constants as the batch processing parameter quantization model of the process. The values ​​of all unknown constants are determined to form a quantitative model of the initial process parameters; For the remaining processing batches, each time a processing batch of data is randomly selected, and the relative change values ​​of all corresponding parameters are substituted into the model result relative change value obtained by the initial process processing parameter quantification model, and the difference between the model result relative change value and the corresponding process processing result relative change value is determined. By comparing two adjacent differences, if the difference in the latter is larger, the data in the latter batch is deleted. The process of comparing adjacent differences is repeated in turn, and finally the filtered batches with sorted order are obtained. Following the order of the selected processing batches, and using the relative change value of the process processing result and the relative change value of all parameters corresponding to the processing batch as a benchmark, the constants in the initial process processing parameter quantification model are gradually adjusted to ultimately form a process processing parameter correlation feature model.

8. The method for treating graphite purification wastewater according to claim 7, characterized in that, The process involves acquiring real-time process targets for different processing steps and performing efficiency-based process parameter analysis based on the corresponding process processing parameter correlation feature data to form real-time process parameter information, including: For different processing steps, the relative change value of the real-time processing result is determined based on the corresponding real-time process target and the process processing baseline result value; For different processing steps, based on the relative change value of the corresponding real-time processing result and the correlation feature model of the processing parameters, combinations of different parameter relative change values ​​that achieve the relative change value of the real-time processing result are determined, forming real-time process parameter value selection combination data; The optimal combination of process parameter values ​​is determined by comparing and analyzing the process processing efficiency of the selected combination data of real-time process parameter values. Based on the optimal combination of process parameter values, the parameter values ​​corresponding to different parameters are determined, forming the real-time process parameter information.

9. The method for treating graphite purification wastewater according to claim 8, characterized in that, The step of comparing and analyzing the real-time process parameter value combination data for process processing efficiency to determine the optimal process parameter value combination includes: By selecting different parameter combinations from the real-time process parameter value combination data, the corresponding total energy consumption of the process is determined. Total process time , where i represents the number of different parameter combinations in the real-time process parameter value selection combination data; For different parameter combinations, the total energy consumption of the corresponding process will vary. and the total duration of the process Determine the process efficiency value ,in, α represents the energy consumption weight ratio, β represents the time weight ratio, and α+β=1; Determine the process efficiency value for different parameter combinations. The smallest combination of parameters is calibrated as the optimal combination of process parameter values.

10. A system for treating graphite purification wastewater, employing the method for treating graphite purification wastewater according to any one of claims 1-9, characterized in that, include: The data acquisition unit is used to collect historical wastewater treatment data and real-time process targets; The feature extraction unit is used to extract parameters based on the historical wastewater treatment data obtained by the data acquisition unit, form historical process treatment parameter data for different treatment processes, and perform correlation analysis on the treatment results to form process treatment parameter correlation feature information for the corresponding treatment process. The real-time control and analysis unit is used to perform efficiency-based process parameter analysis based on the real-time process target obtained by the data acquisition unit and the process processing parameter correlation feature information formed by the feature extraction unit, thereby forming real-time process parameter information.

Images