A multi-source data fusion regulation method for tailings pond tail water treatment

Abstract

The application relates to the technical field of data fusion, and discloses a multi-source data fusion regulation method for tailing pond tail water treatment, which is used for solving the problem that invisible blockage may occur in part of the tail water treatment process when multi-source data fusion is carried out. The method comprises the following steps: based on a treatment section identifier, determining a continuous treatment period corresponding to a target treatment section from a tail water treatment fusion data set, and grouping section time sequence data by combining corresponding tail water treatment fusion data in the continuous treatment period; generating water quality standard change data based on the section time sequence data set and preset reclaimed water quality requirements; generating treatment load change data based on the section time sequence data set; and generating implicit blockage identification data according to the water quality standard change data and the treatment load change data, so that the stability, continuity and management reliability of the tailing pond tail water treatment process are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of data fusion technology, and more specifically to a multi-source data fusion and control method for tailings pond tailings water treatment. Background Technology

[0002] With the continuous development of green mining systems, intelligent tailings dam monitoring technologies, and industrial water treatment data acquisition technologies, tailings dam wastewater treatment processes are increasingly characterized by complex water composition, continuously changing treatment conditions, and dynamically increasing reuse requirements. During sedimentation, filtration, membrane separation, and reuse treatment, tailings dam wastewater continuously generates a large amount of wastewater quality data, treatment process operation data, energy supply data, and control feedback data. This data is typically acquired by water quality monitoring equipment, treatment equipment monitoring units, energy management units, or wastewater treatment management platforms, and then uniformly analyzed and processed through industrial data processing systems or wastewater reuse management systems. Wastewater treatment systems usually need to analyze the operational status of the wastewater treatment process based on the aforementioned multi-source industrial data, and generate corresponding wastewater treatment control data and reuse management information accordingly. Therefore, how to accurately analyze the wastewater treatment status and improve the rationality of wastewater treatment control results under the condition of coexisting multi-source industrial data has become an important technical direction of continuous focus in the fields of tailings dam wastewater resource reuse and industrial data processing.

[0003] In existing technologies, tailings treatment control systems based on multi-source industrial data fusion have been applied to tailings pond tailings reuse management scenarios. These systems typically acquire relevant industrial data from water quality monitoring equipment, treatment equipment monitoring units, and energy management units to comprehensively analyze the water quality status, equipment operating status, and energy supply status during the tailings pond tailings treatment process. Based on the analysis results, corresponding tailings treatment control schemes are generated. Leveraging multi-source data fusion and industrial operation status analysis technologies, these systems can adjust treatment flow rates, membrane separation operation, cleaning agent dosing, or operating periods according to changes in tailings water quality and treatment process operation, thereby improving the automation level and reuse management capabilities of the tailings treatment process.

[0004] In existing effluent treatment control mechanisms, the operational status of the effluent treatment process is typically quantitatively evaluated based on whether the effluent quality meets reuse requirements, whether the pollutant concentration exceeds set limits, or whether the current treatment equipment is in an alarm state. The evaluation results are then used as the basis for generating subsequent control data. During control, the system generally uses the current water quality compliance status or the equipment's immediate alarm status as the judgment benchmark to make corresponding adjustments to the effluent treatment process, thereby determining the appropriate treatment flow rate adjustment, membrane separation operation adjustment, or cleaning agent dosing adjustment methods. This approach is widely used in practice. Its basic idea is to maintain consistency in the effluent treatment control logic through a unified water quality compliance judgment and equipment status judgment mechanism, facilitating unified analysis of the operational status of different treatment stages.

[0005] However, the above-mentioned technologies have at least the following technical problems: In the actual operating environment of tailings dam wastewater treatment, some wastewater treatment processes may experience a hidden blockage state where water quality data meets reuse requirements, but the operating load of the treatment process continues to increase. For example, during the filtration or membrane separation stage, fine suspended solids, colloidal substances, or residual reagents in the wastewater may gradually adhere to the treatment medium or membrane separation channels, causing the operating load of the treatment process to continuously increase. However, because the effluent quality can still meet the standards for a short period of time, the system may still be judged as operating normally based on surface water quality results. This type of state may not immediately manifest as water quality exceeding standards or equipment alarms, but it may lead to a decrease in the stability of subsequent treatment processes. In this situation, if the tailings treatment process is still evaluated uniformly based solely on whether the tailings water quality meets the standards, whether the pollutant concentration exceeds the limit, or whether the equipment alarms, it is easy to fail to effectively identify the hidden blockage state where the water quality meets the standards but the treatment load continues to rise. This can lead to the situation where the surface treatment results are normal but the actual treatment capacity is reduced, and the operation process is still judged as not requiring control. This results in a deviation between the tailings treatment control results and the actual treatment load state, which in turn affects the stability, continuity, and reliability of the tailings dam tailings treatment process and reuse management. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-source data fusion and control method for tailings pond tailings water treatment, so as to solve the problems existing in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A multi-source data fusion and control method for tailings pond tailings water treatment includes the following steps: Step 1: Acquire multi-source industrial data and preset reclaimed water quality requirements during the tailings pond tailings water treatment process. The multi-source industrial data includes tailings water quality data, treatment process operation data, and energy supply data. The tailings water quality data includes suspended solids concentration data, heavy metal ion concentration data, and residual beneficiation reagent concentration data. The treatment process operation data includes treatment flow rate data, treatment pressure data, and cleaning agent dosing data. The energy supply data includes photovoltaic power supply data, energy storage power data, and treatment process power load data. The preset reclaimed water quality requirements include suspended solids concentration limits corresponding to the suspended solids concentration data, heavy metal ion concentration limits corresponding to the heavy metal ion concentration data, and residual beneficiation reagent concentration limits corresponding to the residual beneficiation reagent concentration data. Step 2: Standardize the multi-source industrial data to obtain standard tailings water treatment data. The standardization process includes configuring the acquisition time, data source identifier, data type identifier, and treatment section identifier for the multi-source industrial data. Step 3: Based on the acquisition time and treatment section identifier, perform time-series correlation and section matching on the standard tailings water treatment data to obtain tailings water treatment data. Step 4: Based on the treatment section identifier, determine the continuous treatment period corresponding to the target treatment section from the effluent treatment fusion dataset, and form a section time-series data group from the corresponding effluent treatment fusion data within the continuous treatment period; Step 5: Generate water quality compliance change data based on the section time-series data group and the preset reclaimed water quality requirements, generate treatment load change data based on the section time-series data group, and generate latent blockage identification data based on the water quality compliance change data and treatment load change data; Step 6: Generate operation status data based on the effluent treatment fusion data and latent blockage identification data, including water quality compliance status, treatment load status, cleaning demand status, energy supply adaptation status, and latent blockage status; Step 7: Generate effluent treatment control data based on the operation status data, including at least one of treatment flow rate control data, membrane separation operation control data, cleaning agent dosing control data, and operation period control data; Step 8: Output the effluent treatment control data, obtain the control feedback data after executing the effluent treatment control data, and add the control feedback data to the effluent treatment fusion dataset.

[0008] Preferably, the step of determining the continuous treatment period corresponding to the target treatment section from the effluent treatment fusion dataset based on the treatment section identifier is as follows: Based on the treatment section identifier, read the treatment section identifier corresponding to each effluent treatment fusion data in the effluent treatment fusion dataset; divide the effluent treatment fusion data with the same treatment section identifier into the same data group; and associate each data group with the corresponding treatment section identifier to obtain the effluent fusion data group corresponding to each treatment section; Based on the data type identifier, identify the data type of the effluent treatment fusion data in each effluent fusion data group to determine whether each effluent fusion data group contains effluent water quality data and whether it contains treatment process operation data; When the same effluent fusion data group contains both effluent water quality data and treatment process operation data, the data integrity status of the treatment section corresponding to the effluent fusion data group is determined to be complete; When the same effluent fusion data group lacks effluent water quality data or treatment process operation data, the data integrity status of the treatment section corresponding to the effluent fusion data group is determined to be complete. Incomplete status; processing sections with complete data status are identified as candidate processing sections, and tailwater treatment fusion data corresponding to the candidate processing sections is extracted from the tailwater treatment fusion dataset based on the processing section identifiers corresponding to the candidate processing sections; the tailwater treatment fusion data corresponding to the candidate processing sections is arranged according to the order of collection time to obtain the time sequence arrangement data of the candidate processing sections; based on the time sequence arrangement data of the sections, tailwater treatment fusion data with adjacent collection times and the same processing section identifier are formed into a continuous processing sequence, and the collection time corresponding to the first tailwater treatment fusion data in the continuous processing sequence is taken as the start time of the continuous processing period, and the collection time corresponding to the last tailwater treatment fusion data in the continuous processing sequence is taken as the end time of the continuous processing period to obtain the continuous processing period corresponding to the candidate processing section; the candidate processing sections with continuous processing periods are identified as target processing sections, and the continuous processing period corresponding to the target processing sections is used as the continuous processing period for generating the time sequence data group of the sections.

[0009] Preferably, the steps for obtaining the time-series data group of the treatment section are as follows: based on the treatment section identifier corresponding to the target treatment section, extract the effluent treatment fusion data corresponding to the target treatment section from the effluent treatment fusion dataset to obtain the target treatment section fusion data; based on the continuous treatment period corresponding to the target treatment section, filter the effluent treatment fusion data whose collection time is within the continuous treatment period from the target treatment section fusion data to obtain the continuous period fusion data; arrange the continuous period fusion data according to the order of collection time to obtain the continuous period time-series data; based on the data type identifier, extract the effluent water quality data, treatment process operation data, and energy supply data from the continuous period time-series data, and associate the effluent water quality data, treatment process operation data, and energy supply data corresponding to the same collection time to obtain the time-series association data; combine the time-series association data corresponding to each collection time according to the order of collection time to obtain the time-series data group of the treatment section corresponding to the target treatment section.

[0010] Preferably, the steps for obtaining the water quality compliance change data are as follows: Based on preset reclaimed water quality requirements, extract the suspended solids concentration limit corresponding to the suspended solids concentration data, the heavy metal ion concentration limit corresponding to the heavy metal ion concentration data, and the residual mineral processing reagent concentration limit corresponding to the residual mineral processing reagent concentration data; Based on the time-series data group of the treatment section, extract the suspended solids concentration data, heavy metal ion concentration data, and residual mineral processing reagent concentration data corresponding to each collection time in the continuous treatment period of the target treatment section according to the chronological order of collection time; Compare the suspended solids concentration data, heavy metal ion concentration data, and residual mineral processing reagent concentration data corresponding to each collection time with the corresponding concentration limits to obtain the pollutant single-item compliance data corresponding to each collection time; wherein, the pollutant single-item compliance data includes suspended solids single-item compliance data, heavy metal ion single-item compliance data, and... Individual compliance data for residual mineral processing reagents; based on the individual compliance data for pollutants at each collection time, determine the overall water quality compliance data for each collection time, including compliance and non-compliance states; based on the tailwater quality data and corresponding concentration limits at each collection time, calculate the compliance margin values ​​for suspended solids, heavy metal ions, and residual mineral processing reagents at each collection time; among the compliance margin values ​​for suspended solids, heavy metal ions, and residual mineral processing reagents at the same collection time, select the smallest compliance margin value as the water quality compliance margin data for that collection time; arrange the overall water quality compliance data and water quality compliance margin data for each collection time in chronological order to obtain the water quality compliance change data of the target treatment section during the continuous treatment period.

[0011] Preferably, the step of acquiring the processing load change data is as follows: Extracting the processing operation data corresponding to each collection time within the continuous processing period of the target processing section from the section time-series data group; the processing operation data includes processing flow data, processing pressure data, and cleaning agent dosing data; determining the collection time where the processing flow data is greater than zero and the processing pressure data is greater than zero as the effective processing collection time; and obtaining the effective processing operation data based on the processing flow data, processing pressure data, and cleaning agent dosing data corresponding to the effective processing collection time; arranging the effective processing operation data according to the chronological order of the collection time to obtain the effective processing time-series data corresponding to the target processing section; and calculating the processing pressure data and processing flow data corresponding to each effective processing collection time in the effective processing time-series data. The system collects unit flow pressure load data; calculates adjacent load change data based on unit flow pressure load data corresponding to adjacent effective processing acquisition times; generates load increase direction data based on adjacent load change data; wherein, when adjacent load change data is greater than zero, the corresponding load increase direction data is determined as load increase, and when adjacent load change data is not greater than zero, the corresponding load increase direction data is determined as load not increase; calculates adjacent cleaning intervention change data based on cleaning agent dosing data corresponding to adjacent effective processing acquisition times; and generates processing load change data based on adjacent load change data, load increase direction data, and adjacent cleaning intervention change data; wherein, processing load change data includes unit flow pressure load time series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data.

[0012] Preferably, the steps for acquiring the hidden blockage identification data are as follows: Extracting overall water quality compliance data and water quality compliance margin data for each collection time within the continuous treatment period from the water quality compliance change data; extracting unit flow pressure load time-series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data for the target treatment section within the continuous treatment period from the treatment load change data; generating water quality compliance maintenance data based on the overall water quality compliance data and water quality compliance margin data for each collection time; wherein, when the overall water quality compliance data for each collection time within the continuous treatment period all represent the compliance status, and the water quality compliance margin data for each collection time is not less than zero, the water quality compliance maintenance data is determined as the compliance maintenance status; generating continuous load increase data based on adjacent load change data and load increase direction data, the continuous load increase data including continuous increase status... The system identifies two states: a state of unrelieved load and a state of continuous load increase. Based on adjacent load change data and adjacent cleaning intervention change data, cleaning intervention response data is generated. Specifically, when adjacent cleaning intervention change data is greater than or equal to zero, and adjacent load change data is greater than zero, the cleaning intervention response data for the corresponding adjacent effective treatment collection time is determined to be in a state of unrelieved load. When water quality meets standards and the data shows a state of maintained compliance, and the data shows a state of continuous load increase, the hidden blockage status is identified as existing. When water quality meets standards and the data shows a state of maintained compliance, the data shows a state of continuous load increase, and the cleaning intervention response data includes a state of unrelieved load, the hidden blockage status is updated to a state of hidden blockage awaiting cleaning. Hidden blockage identification data is generated based on the target treatment section identifier, continuous treatment period, water quality meets standards and maintain compliance data, continuous load increase data, cleaning intervention response data, and hidden blockage status identifier.

[0013] Preferably, the step of generating operational status data based on effluent treatment fusion data and latent blockage identification data includes: extracting the target treatment section identifier, continuous treatment period, water quality compliance maintenance data, load continuously increasing data, cleaning intervention response data, and latent blockage status identifier from the latent blockage identification data; extracting the corresponding treatment process operation data and energy supply data of the target treatment section during the continuous treatment period from the effluent treatment fusion data; determining the water quality compliance status in the operational status data based on the water quality compliance maintenance data, including compliance status and non-compliance status; determining the treatment load status in the operational status data based on the load continuously increasing data, including load increasing status and load not increasing status; and determining the treatment load status based on the treatment load status, cleaning intervention response data, and latent blockage status identifier. The system identifies the cleaning demand status in the operational status data, including pre-cleaning and enhanced cleaning status. It also determines the energy supply suitability status based on energy supply data. Specifically, it assesses the satisfaction of photovoltaic power supply and energy storage data with the processing power load data based on photovoltaic power supply data, energy storage power data, and processing power load data, and determines the energy supply suitability status accordingly. Furthermore, it identifies hidden blockage status in the operational status data based on hidden blockage status identifiers, including both present and absent hidden blockage statuses. Finally, it correlates the water quality compliance status, processing load status, cleaning demand status, energy supply suitability status, and hidden blockage status to generate operational status data corresponding to the target processing section.

[0014] Preferably, the step of generating tailwater treatment control data based on operating status data includes: extracting the water quality compliance status, treatment load status, cleaning demand status, energy supply suitability status, and latent blockage status corresponding to the target treatment section from the operating status data; determining the control trigger status based on the water quality compliance status and latent blockage status, including water quality anomaly trigger status and latent blockage trigger status; determining the control object corresponding to the target treatment section based on the treatment load status and cleaning demand status; wherein, when the treatment load status is a load increase status and the cleaning demand status is a pre-cleaning status or an enhanced cleaning status, The target treatment section is identified as the control object; when the treatment section identifier corresponding to the target treatment section represents the membrane separation section, the control object is the membrane separation section; when the treatment section identifier corresponding to the target treatment section represents the filtration section, the control object is the filtration section; control type data is generated based on the control trigger state and the control object; specifically, when the control trigger state is a water quality anomaly trigger state, treatment flow rate adjustment type data and membrane separation operation adjustment type data are generated; when the control trigger state is a latent clogging trigger state, membrane separation operation adjustment type data and cleaning agent dosing adjustment type data are generated; based on the energy supply adaptation state... The control type data undergoes time-period matching processing. Specifically, when the energy supply matching status is "energy supply matching," the current operating segment corresponding to the control type data is retained. When the energy supply matching status is "energy supply mismatch," operating segment adjustment data is generated, and this data is associated with the control type data. Wastewater treatment control data is generated based on the control type data. Specifically, when the control type data includes treatment flow rate adjustment data, treatment flow rate adjustment data is generated; when the control type data includes membrane separation operation adjustment data, membrane separation operation adjustment data is generated; when the control type data includes cleaning... When generating cleaning agent dosing adjustment data, cleaning agent dosing adjustment data is generated. When the control trigger state is a hidden blockage trigger state, the effluent treatment control data is marked as hidden blockage control data, the no-control result generated based on the water quality compliance state is canceled, and the hidden blockage control data is used as the effluent treatment control data corresponding to the target treatment section. At least one of the following is associated with the treatment flow rate adjustment data, membrane separation operation adjustment data, cleaning agent dosing adjustment data, and operation period adjustment data, with the target treatment section identifier, continuous treatment period, and hidden blockage state to obtain the effluent treatment control data corresponding to the target treatment section.

[0015] The technical effects and advantages of this invention are as follows: Based on the treatment section identifier, the continuous treatment period corresponding to the target treatment section is determined from the tailings treatment fusion dataset. The tailings treatment fusion data corresponding to the continuous treatment period is then combined into a section time-series data group. Water quality compliance change data is generated based on the section time-series data group and the preset reclaimed water quality requirements. Treatment load change data is also generated based on the section time-series data group. Furthermore, hidden blockage identification data is generated based on the water quality compliance change data and the treatment load change data. This effectively improves the stability, continuity, and management reliability of the tailings dam tailings treatment process. Attached Figure Description

[0016] Figure 1 A flowchart of a multi-source data fusion and control method for tailings dam wastewater treatment provided in this application embodiment. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The multi-source data fusion and control method for tailings pond tailings water treatment involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This invention provides a multi-source data fusion and control method for tailings dam wastewater treatment, such as... Figure 1 As shown, it includes the following steps: Step 1: Obtain multi-source industrial data and preset reclaimed water quality requirements during the tailings dam tailings wastewater treatment process. Multi-source industrial data includes tailings wastewater quality data, treatment process operation data, and energy supply data. Tailings wastewater quality data includes suspended solids concentration data, heavy metal ion concentration data, and residual beneficiation reagent concentration data. Treatment process operation data includes treatment flow rate data, treatment pressure data, and cleaning agent dosing data. Energy supply data includes photovoltaic power supply data, energy storage power data, and treatment process power load data. Preset reclaimed water quality requirements include suspended solids concentration limits corresponding to the suspended solids concentration data, heavy metal ion concentration limits corresponding to the heavy metal ion concentration data, and residual beneficiation reagent concentration limits corresponding to the residual beneficiation reagent concentration data. Step 2: Standardize the multi-source industrial data to obtain standard wastewater treatment data. Standardization includes configuring the acquisition time, data source identifier, data type identifier, and treatment section identifier for the multi-source industrial data. Step 3: Based on the collection time and treatment section identifier, perform time-series correlation and section matching on the standard effluent treatment data to obtain effluent treatment fusion data and form an effluent treatment fusion dataset; In this embodiment, it should be noted that performing time-series association and process segment matching on standard effluent treatment data based on collection time and processing segment identifier is a conventional data organization method in industrial data fusion processing. Its basic principle is to determine the corresponding processing time period of standard effluent treatment data collected from different data sources according to the collection time, and to determine the processing stage according to the processing segment identifier. This allows for the correlation of effluent water quality data, processing operation data, and energy supply data within the same processing time period and processing segment, forming fused effluent treatment data that reflects the operational status of the effluent treatment process. The above processing method is mainly used to solve the correspondence problem of industrial data from different sources in the time and processing segment dimensions. Specific data association, field matching, and dataset construction methods can be implemented using existing data fusion, data table association, or time-series data management technologies. This embodiment does not limit the specific implementation method.

[0019] Step 4: Based on the treatment section identifier, determine the continuous treatment period corresponding to the target treatment section from the tailwater treatment fusion dataset, and form the tailwater treatment fusion data corresponding to the continuous treatment period into a section time series data group. In this embodiment, it should be specifically explained that the step of determining the continuous treatment period corresponding to the target treatment section from the effluent treatment fusion dataset based on the treatment section identifier is as follows: Based on the treatment section identifier, the treatment section identifier corresponding to each effluent treatment fusion data in the effluent treatment fusion dataset is read. The effluent treatment fusion data with the same treatment section identifier are divided into the same data group, and each data group is associated with the corresponding treatment section identifier to obtain the section fusion data group corresponding to each treatment section. Based on data type identification, the data type of the effluent treatment fusion data in each section's fusion data group is identified to determine whether each section's fusion data group contains effluent water quality data and whether it contains treatment process operation data. When the same section's integrated data group contains both effluent water quality data and treatment process operation data, the data integrity status of the corresponding treatment section of the integrated data group is determined to be complete; when the same section's integrated data group lacks either effluent water quality data or treatment process operation data, the data integrity status of the corresponding treatment section of the integrated data group is determined to be incomplete. The processing section with complete data status is identified as the candidate processing section, and the effluent treatment fusion data corresponding to the candidate processing section is extracted from the effluent treatment fusion dataset based on the processing section identifier corresponding to the candidate processing section. According to the order of collection time, the tailwater treatment fusion data corresponding to the candidate treatment sections are arranged to obtain the time sequence arrangement data of the candidate treatment sections. Based on the time sequence data of the treatment sections, the tailwater treatment fusion data with adjacent collection times and the same treatment section identifier are formed into a continuous processing sequence. The collection time corresponding to the first tailwater treatment fusion data in the continuous processing sequence is taken as the start time of the continuous processing period, and the collection time corresponding to the last tailwater treatment fusion data in the continuous processing sequence is taken as the end time of the continuous processing period, thus obtaining the continuous processing period corresponding to the candidate treatment section. Candidate processing sections with continuous processing periods are identified as target processing sections, and the continuous processing periods corresponding to the target processing sections are used as the continuous processing periods for generating time series data groups for the processing sections.

[0020] In this embodiment, it should be specifically explained that the steps for obtaining the work section time sequence data group are as follows: Based on the treatment section identifier corresponding to the target treatment section, extract the effluent treatment fusion data corresponding to the target treatment section from the effluent treatment fusion dataset to obtain the target section fusion data; Based on the continuous treatment period corresponding to the target treatment section, the effluent treatment fusion data collected within the continuous treatment period is selected from the target section fusion data to obtain the continuous time period fusion data. The data from the continuous time periods are arranged in chronological order of collection time to obtain the time-series data for the continuous time periods. Based on data type identification, wastewater quality data, treatment process operation data, and energy supply data are extracted from continuous time-series data. The wastewater quality data, treatment process operation data, and energy supply data corresponding to the same collection time are then correlated to obtain time-series correlated data. The time-series correlation data corresponding to each collection time are combined in chronological order of collection time to obtain the time-series data group corresponding to the target processing section.

[0021] Step 5: Generate water quality compliance change data based on the time-series data set of the treatment section and the preset reclaimed water quality requirements; generate treatment load change data based on the time-series data set of the treatment section; and generate latent blockage identification data based on the water quality compliance change data and the treatment load change data. Among them, the water quality compliance change data is used to characterize the change in effluent water quality compliance of the target treatment section during the continuous treatment period; the treatment load change data is used to characterize the change in treatment load of the target treatment section during the continuous treatment period; and the latent blockage identification data is used to characterize whether the target treatment section has an operating state where the water quality meets the standards but the treatment load continues to increase. In this embodiment, it should be specifically explained that the steps for obtaining water quality compliance change data are as follows: Based on the preset reclaimed water quality requirements, the suspended solids concentration limit corresponding to the suspended solids concentration data, the heavy metal ion concentration limit corresponding to the heavy metal ion concentration data, and the residual mineral processing reagent concentration limit corresponding to the residual mineral processing reagent concentration data were extracted. Based on the time-series data of the work section, the suspended solids concentration data, heavy metal ion concentration data, and residual mineral processing reagent concentration data of the target processing section are extracted in chronological order of collection time during the continuous processing period. The concentration data of suspended solids, heavy metal ions, and residual mineral processing reagents at each collection time were compared with the corresponding concentration limits to obtain the individual pollutant compliance data for each collection time. The individual pollutant compliance data included the individual compliance data of suspended solids, heavy metal ions, and residual mineral processing reagents. Based on the individual pollutant compliance data corresponding to each collection time, the overall water quality compliance data for each collection time is determined. Specifically, when the individual compliance data for suspended solids, heavy metal ions, and residual mineral processing reagents at the same collection time all indicate compliance, the overall water quality compliance data for that collection time is determined to be in a compliant state. When at least one of the individual compliance data for suspended solids, heavy metal ions, and residual mineral processing reagents at the same collection time indicates non-compliance, the overall water quality compliance data for that collection time is determined to be in a non-compliant state. Based on the tailwater quality data and corresponding concentration limits for each collection time, the compliance margin values ​​for suspended solids, heavy metal ions, and residual beneficiation reagents for each collection time were calculated. Specifically, the compliance margin value for suspended solids is the ratio of the difference between the suspended solids concentration limit and the suspended solids concentration data to the suspended solids concentration limit; the compliance margin value for heavy metal ions is the ratio of the difference between the heavy metal ion concentration limit and the heavy metal ion concentration data to the heavy metal ion concentration limit; and the compliance margin value for residual beneficiation reagents is the ratio of the difference between the residual beneficiation reagent concentration limit and the residual beneficiation reagent concentration data to the residual beneficiation reagent concentration limit. Among the suspended solids compliance margin value, heavy metal ion compliance margin value, and residual mineral processing agent compliance margin value corresponding to the same collection time, the compliance margin value with the smallest value is selected as the water quality compliance margin data corresponding to that collection time. According to the chronological order of the collection time, the overall water quality compliance data and water quality compliance margin data corresponding to each collection time are arranged to obtain the water quality compliance change data of the target treatment section during the continuous treatment period.

[0022] It should be noted that obtaining water quality compliance change data can help to analyze the effluent water quality of the target treatment section during a continuous treatment period and compare it with the preset reclaimed water quality requirements. This not only determines whether the water quality meets the standards at a single collection time, but also establishes the relationship between water quality compliance changes over a continuous period. This provides data support from the water quality side for identifying situations where "the surface water quality meets the standards, but the operating load changes abnormally".

[0023] In this embodiment, it should be specifically explained that the steps for obtaining load change data are as follows: Extract the processing operation data of the target processing section at each collection time during the continuous processing period from the section time sequence data group. The processing operation data includes processing flow data, processing pressure data, and cleaning agent dosing data. Processing flow data refers to the amount of effluent passing through the target treatment section within the corresponding collection time. It is used to characterize the actual amount of effluent processed by the treatment section per unit time, such as the effluent flow data entering the filtration section or membrane separation section.

[0024] Processing pressure data refers to the operating pressure data of the target treatment section within the corresponding collection time. It is used to characterize the pressure state formed when the effluent passes through the filter medium, membrane module or related treatment channel, such as filtration pressure data, membrane pre-membrane pressure data or membrane separation operating pressure data.

[0025] Cleaning agent dosage data refers to the amount of cleaning agent added to the target treatment section during the corresponding collection time for cleaning or maintaining treatment capacity. It is used to characterize whether chemical cleaning has been carried out in the treatment section and the degree of cleaning intervention.

[0026] The collection time when the processing flow data is greater than zero and the processing pressure data is greater than zero is determined as the effective processing collection time. Based on the processing flow data, processing pressure data and cleaning agent dosing data corresponding to the effective processing collection time, the effective processing operation data is obtained. The effective processing operation data are arranged in chronological order of collection time to obtain the effective processing time sequence data corresponding to the target processing section. Based on the processing pressure data and processing flow data corresponding to each effective processing acquisition time in the effective processing time series data, the unit flow pressure load data corresponding to each effective processing acquisition time is calculated; where the unit flow pressure load data is the ratio between the processing pressure data and the processing flow data corresponding to the same effective processing acquisition time. Based on the unit flow rate and pressure load data corresponding to adjacent effective processing and acquisition times, the adjacent load change data is calculated; wherein, the adjacent load change data is the difference between the unit flow rate and pressure load data corresponding to the later effective processing and acquisition time and the unit flow rate and pressure load data corresponding to the earlier effective processing and acquisition time. Load increase direction data is generated based on adjacent load change data; when the adjacent load change data is greater than zero, the corresponding load increase direction data is determined as load increase, and when the adjacent load change data is not greater than zero, the corresponding load increase direction data is determined as load not increase. Based on the cleaning agent dosing data corresponding to adjacent effective treatment collection times, the adjacent cleaning intervention change data is calculated; whereby, the adjacent cleaning intervention change data is the difference between the cleaning agent dosing data corresponding to the next effective treatment collection time and the cleaning agent dosing data corresponding to the previous effective treatment collection time. Based on adjacent load change data, load increase direction data, and adjacent cleaning intervention change data, processing load change data is generated. Among them, the processing load change data includes unit flow pressure load time series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data. The load increase direction data is used to characterize whether the unit flow pressure load data increases between adjacent effective processing acquisition times.

[0027] It should be noted that acquiring data on changes in processing load allows the system to extract changes in processing load from the processing operation data within a continuous processing period. This enables the system to no longer rely solely on water quality results or equipment alarm status to determine its operating status. Instead, it can combine operational data such as processing flow rate, processing pressure, and cleaning agent dosage to identify whether there is a trend of continuously increasing processing load in the target processing section, thereby improving the ability to detect potential blockage risks.

[0028] In this embodiment, it should be specifically explained that the steps for obtaining hidden blockage identification data are as follows: Extract the overall water quality compliance data and water quality compliance margin data of the target treatment section at each collection time during the continuous treatment period from the water quality compliance change data; Extract the unit flow pressure load time series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data of the target treatment section during the continuous treatment period from the load change data. Based on the overall water quality compliance data and water quality compliance margin data corresponding to each collection time, water quality compliance maintenance data is generated; among them, when the overall water quality compliance data corresponding to each collection time in the continuous processing period all represent the compliance status, and the water quality compliance margin data corresponding to each collection time is not less than zero, the water quality compliance maintenance data is determined as the compliance maintenance status. Based on adjacent load change data and load increase direction data, load continuously increasing data is generated. Specifically, when the adjacent load change data corresponding to each adjacent effective processing acquisition time within a continuous processing period are all greater than zero, and the corresponding load increase direction data all indicate load increase, the load continuously increasing data is determined to be in a continuously increasing state. When there are adjacent load change data corresponding to adjacent effective processing acquisition times within a continuous processing period that are not greater than zero, or the corresponding load increase direction data indicates that the load has not increased, the load continuously increasing data is determined to be in a non-continuously increasing state. Based on adjacent load change data and adjacent cleaning intervention change data, cleaning intervention response data is generated; among them, when the adjacent cleaning intervention change data is greater than or equal to zero and the adjacent load change data is greater than zero, the cleaning intervention response data corresponding to the adjacent effective processing acquisition time is determined as the load not being relieved. When the water quality meets the standard and the load continues to rise, the hidden blockage status is identified as a hidden blockage status. When the water quality compliance data is in the compliance status, the load continuously rising data is in the continuously rising status, and the cleaning intervention response data includes the load not being relieved status, the hidden blockage status is updated to the hidden blockage to be cleaned status. Based on the target treatment section identifier, continuous treatment period, water quality compliance data, load continuously increasing data, cleaning intervention response data, and latent blockage status identifier, latent blockage identification data is generated.

[0029] It should be noted that acquiring hidden blockage identification data allows for joint judgment of changes in water quality compliance and load changes on the operation side. When the effluent quality still meets the reuse requirements but the treatment load continues to increase, it can promptly identify potential hidden blockages in the target treatment section, preventing the system from misjudging that no control is needed based solely on water quality compliance results. This improves the accuracy of effluent treatment control and the reliability of continuous operation.

[0030] Step 6: Generate operational status data based on the effluent treatment fusion data and hidden blockage identification data. The operational status data includes water quality compliance status, treatment load status, cleaning demand status, energy supply matching status, and hidden blockage status. In this embodiment, it should be specifically explained that the steps for generating operational status data based on effluent treatment fusion data and hidden blockage identification data are as follows: Extract the target treatment section identifier, continuous treatment period, water quality compliance maintenance data, load continuously increasing data, cleaning intervention response data, and hidden blockage status identifier from the hidden blockage identification data; Extract the operation data and energy supply data of the target treatment section during the continuous treatment period from the fusion data of wastewater treatment; The water quality compliance status in the operational status data is determined based on the water quality compliance maintenance data; specifically, when the water quality compliance maintenance data is in the compliance maintenance status, the water quality compliance status is determined as the compliance status; when the water quality compliance maintenance data is not in the compliance maintenance status, the water quality compliance status is determined as the non-compliance status. The processing load status in the operation status data is determined based on the continuously increasing load data; specifically, when the continuously increasing load data is in a continuously increasing state, the processing load status is determined to be in a load increasing state; when the continuously increasing load data is not in a continuously increasing state, the processing load status is determined to be in a load not increasing state. The cleaning demand status in the operation status data is determined based on the processing load status, cleaning intervention response data, and hidden blockage status indicators. Among them, when the processing load status is a load increase status and the hidden blockage status indicator indicates the existence of a hidden blockage status, the cleaning demand status is determined as a pre-cleaning status. When the cleaning intervention response data includes a load unrelieved status, the cleaning demand status is determined as an enhanced cleaning status. The energy supply adaptation status in the operation status data is determined based on the energy supply data; in particular, the photovoltaic power supply data, energy storage power data and the power load data of the processing process are used to determine the satisfaction of the photovoltaic power supply data and energy storage power data with the power load data of the processing process, and the energy supply adaptation status is determined based on the satisfaction. The hidden blockage status in the operation status data is determined based on the hidden blockage status identifier; when the hidden blockage status identifier is either a hidden blockage status or a hidden blockage status to be cleaned, the hidden blockage status is determined to be a hidden blockage status; when the hidden blockage status identifier is neither a hidden blockage status nor a hidden blockage status to be cleaned, the hidden blockage status is determined to be a hidden blockage status. By associating water quality compliance status, treatment load status, cleaning demand status, energy supply compatibility status, and hidden blockage status, operational status data corresponding to the target treatment section is generated.

[0031] It should be noted that generating operational status data based on effluent treatment fusion data and hidden blockage identification data can further incorporate hidden blockage identification results on top of the water quality status, treatment process operation status, and energy supply status reflected in conventional effluent treatment fusion data. This allows the operational status data to not only reflect whether the effluent meets standards, whether the treatment load is abnormal, and whether the energy supply is appropriate, but also whether there is a hidden blockage state in the target treatment section where "water quality meets standards but the treatment load continues to increase." This avoids generating operational status solely based on surface water quality compliance results, improving the accuracy of operational status judgment and the relevance of subsequent effluent treatment control data generation.

[0032] Step 7: Generate tailwater treatment control data based on the operating status data. The tailwater treatment control data includes at least one of the following: treatment flow rate control data, membrane separation operation control data, cleaning agent dosing control data, and operating time control data. In this embodiment, it should be specifically explained that the step of generating tailwater treatment control data based on operating status data is as follows: Extract the water quality compliance status, treatment load status, cleaning demand status, energy supply matching status, and hidden blockage status corresponding to the target treatment section from the operation status data. The control trigger state is determined based on the water quality compliance status and the latent blockage status; when the water quality compliance status is not met, the control trigger state is determined to be the water quality abnormality trigger state; when the water quality compliance status is met and the latent blockage status is latent blockage, the control trigger state is determined to be the latent blockage trigger state. The control target for the target processing section is determined based on the processing load status and cleaning demand status. Specifically, when the processing load status is in the increased load state and the cleaning demand status is in the pre-cleaning state or the enhanced cleaning state, the target processing section is determined as the control target. When the processing section identifier corresponding to the target processing section represents the membrane separation section, the control target is the membrane separation section. When the processing section identifier corresponding to the target processing section represents the filtration section, the control target is the filtration section. Control type data is generated based on the control trigger state and the control object; specifically, when the control trigger state is the water quality abnormality trigger state, treatment flow rate control type data and membrane separation operation control type data are generated; when the control trigger state is the hidden blockage trigger state, membrane separation operation control type data and cleaning agent dosing control type data are generated. The control type data is matched with the energy supply matching status. When the energy supply matching status is "energy supply matching status", the current running segment corresponding to the control type data is retained. When the energy supply matching status is "energy supply mismatch status", running segment adjustment data is generated and associated with the control type data. Wastewater treatment control data is generated based on the control type data; specifically, when the control type data includes treatment flow rate control data, treatment flow rate control data is generated; when the control type data includes membrane separation operation control data, membrane separation operation control data is generated; and when the control type data includes cleaning agent dosing control data, cleaning agent dosing control data is generated. When the control trigger state is the latent blockage trigger state, the tailwater treatment control data is marked as latent blockage control data, the no-control result generated based on the water quality compliance state is canceled, and the latent blockage control data is used as the tailwater treatment control data corresponding to the target treatment section. At least one of the following data—processing flow regulation data, membrane separation operation regulation data, cleaning agent dosing regulation data, and operating time regulation data—is correlated with the target treatment section identifier, continuous treatment period, and hidden blockage status to obtain the tailwater treatment control data corresponding to the target treatment section.

[0033] Step 8: Output the tailwater treatment control data and obtain the control feedback data after executing the tailwater treatment control data. Add the control feedback data to the tailwater treatment fusion dataset.

[0034] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0035] 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 multi-source data fusion and control method for tailings dam wastewater treatment, characterized in that, Includes the following steps: Step 1: Obtain multi-source industrial data and preset reclaimed water quality requirements during the tailings dam tailings wastewater treatment process. Multi-source industrial data includes tailings wastewater quality data, treatment process operation data, and energy supply data. Tailings wastewater quality data includes suspended solids concentration data, heavy metal ion concentration data, and residual beneficiation reagent concentration data. Treatment process operation data includes treatment flow rate data, treatment pressure data, and cleaning agent dosing data. Energy supply data includes photovoltaic power supply data, energy storage power data, and treatment process power load data. Preset reclaimed water quality requirements include suspended solids concentration limits corresponding to the suspended solids concentration data, heavy metal ion concentration limits corresponding to the heavy metal ion concentration data, and residual beneficiation reagent concentration limits corresponding to the residual beneficiation reagent concentration data. Step 2: Standardize the multi-source industrial data to obtain standard wastewater treatment data. Standardization includes configuring the acquisition time, data source identifier, data type identifier, and treatment section identifier for the multi-source industrial data. Step 3: Based on the collection time and treatment section identifier, perform time-series correlation and section matching on the standard effluent treatment data to obtain effluent treatment fusion data and form an effluent treatment fusion dataset; Step 4: Based on the treatment section identifier, determine the continuous treatment period corresponding to the target treatment section from the tailwater treatment fusion dataset, and form the tailwater treatment fusion data corresponding to the continuous treatment period into a section time series data group. Step 5: Generate water quality compliance change data based on the section time series data group and the preset reclaimed water quality requirements; generate treatment load change data based on the section time series data group; and generate hidden blockage identification data based on the water quality compliance change data and the treatment load change data. Step 6: Generate operational status data based on the effluent treatment fusion data and hidden blockage identification data. The operational status data includes water quality compliance status, treatment load status, cleaning demand status, energy supply matching status, and hidden blockage status. Step 7: Generate tailwater treatment control data based on the operating status data. The tailwater treatment control data includes at least one of the following: treatment flow rate control data, membrane separation operation control data, cleaning agent dosing control data, and operating time control data. Step 8: Output the tailwater treatment control data and obtain the control feedback data after executing the tailwater treatment control data. Add the control feedback data to the tailwater treatment fusion dataset.

2. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that: The step of determining the continuous treatment period corresponding to the target treatment section from the effluent treatment fusion dataset based on the treatment section identifier is as follows: Based on the treatment section identifier, the treatment section identifier corresponding to each effluent treatment fusion data in the effluent treatment fusion dataset is read. The effluent treatment fusion data with the same treatment section identifier are divided into the same data group, and each data group is associated with the corresponding treatment section identifier to obtain the section fusion data group corresponding to each treatment section. Based on data type identification, the data type of the effluent treatment fusion data in each section's fusion data group is identified to determine whether each section's fusion data group contains effluent water quality data and whether it contains treatment process operation data. When the same section's integrated data group contains both effluent water quality data and treatment process operation data, the data integrity status of the corresponding treatment section of the integrated data group is determined to be complete; when the same section's integrated data group lacks either effluent water quality data or treatment process operation data, the data integrity status of the corresponding treatment section of the integrated data group is determined to be incomplete. The processing section with complete data status is identified as the candidate processing section, and the effluent treatment fusion data corresponding to the candidate processing section is extracted from the effluent treatment fusion dataset based on the processing section identifier corresponding to the candidate processing section. According to the order of collection time, the tailwater treatment fusion data corresponding to the candidate treatment sections are arranged to obtain the time sequence arrangement data of the candidate treatment sections. Based on the time sequence data of the treatment sections, the tailwater treatment fusion data with adjacent collection times and the same treatment section identifier are formed into a continuous processing sequence. The collection time corresponding to the first tailwater treatment fusion data in the continuous processing sequence is taken as the start time of the continuous processing period, and the collection time corresponding to the last tailwater treatment fusion data in the continuous processing sequence is taken as the end time of the continuous processing period, thus obtaining the continuous processing period corresponding to the candidate treatment section. Candidate processing sections with continuous processing periods are identified as target processing sections, and the continuous processing periods corresponding to the target processing sections are used as the continuous processing periods for generating time series data groups for the processing sections.

3. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that, The steps for obtaining the time sequence data group of the work section are as follows: Based on the treatment section identifier corresponding to the target treatment section, extract the effluent treatment fusion data corresponding to the target treatment section from the effluent treatment fusion dataset to obtain the target section fusion data; Based on the continuous treatment period corresponding to the target treatment section, the effluent treatment fusion data collected within the continuous treatment period is selected from the target section fusion data to obtain the continuous time period fusion data. The data from the continuous time periods are arranged in chronological order of collection time to obtain the time-series data for the continuous time periods. Based on data type identification, wastewater quality data, treatment process operation data, and energy supply data are extracted from continuous time-series data. The wastewater quality data, treatment process operation data, and energy supply data corresponding to the same collection time are then correlated to obtain time-series correlated data. The time-series correlation data corresponding to each collection time are combined in chronological order of collection time to obtain the time-series data group corresponding to the target processing section.

4. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that, The steps for obtaining the water quality compliance change data are as follows: Based on the preset reclaimed water quality requirements, the suspended solids concentration limit corresponding to the suspended solids concentration data, the heavy metal ion concentration limit corresponding to the heavy metal ion concentration data, and the residual mineral processing reagent concentration limit corresponding to the residual mineral processing reagent concentration data were extracted. Based on the time-series data of the work section, the suspended solids concentration data, heavy metal ion concentration data, and residual mineral processing reagent concentration data of the target processing section are extracted in chronological order of collection time during the continuous processing period. The concentration data of suspended solids, heavy metal ions, and residual mineral processing reagents at each collection time were compared with the corresponding concentration limits to obtain the individual pollutant compliance data for each collection time. The individual pollutant compliance data included the individual compliance data of suspended solids, heavy metal ions, and residual mineral processing reagents. Based on the individual pollutant compliance data corresponding to each collection time, the overall water quality compliance data corresponding to each collection time is determined. The overall water quality compliance includes compliance status and non-compliance status. Based on the tailwater quality data and corresponding concentration limits for each collection time, the compliance margin values ​​for suspended solids, heavy metal ions, and residual mineral processing reagents for each collection time were calculated respectively. Among the suspended solids compliance margin value, heavy metal ion compliance margin value, and residual mineral processing agent compliance margin value corresponding to the same collection time, the compliance margin value with the smallest value is selected as the water quality compliance margin data corresponding to that collection time. According to the chronological order of the collection time, the overall water quality compliance data and water quality compliance margin data corresponding to each collection time are arranged to obtain the water quality compliance change data of the target treatment section during the continuous treatment period.

5. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that: The steps for obtaining the load change data are as follows: Extract the processing operation data of the target processing section at each collection time during the continuous processing period from the section time sequence data group. The processing operation data includes processing flow data, processing pressure data, and cleaning agent dosing data. The collection time when the processing flow data is greater than zero and the processing pressure data is greater than zero is determined as the effective processing collection time. Based on the processing flow data, processing pressure data and cleaning agent dosing data corresponding to the effective processing collection time, the effective processing operation data is obtained. The effective processing operation data are arranged in chronological order of collection time to obtain the effective processing time sequence data corresponding to the target processing section. Based on the processing pressure data and processing flow data corresponding to each effective processing acquisition time in the effective processing time series data, calculate the unit flow pressure load data corresponding to each effective processing acquisition time. Based on the unit flow pressure load data corresponding to adjacent effective processing and acquisition times, calculate the adjacent load change data; Load increase direction data is generated based on adjacent load change data; when the adjacent load change data is greater than zero, the corresponding load increase direction data is determined as load increase, and when the adjacent load change data is not greater than zero, the corresponding load increase direction data is determined as load not increase. Based on the cleaning agent dosing data corresponding to adjacent effective treatment collection times, calculate the adjacent cleaning intervention change data; Based on adjacent load change data, load increase direction data, and adjacent cleaning intervention change data, processed load change data is generated; the processed load change data includes unit flow pressure load time series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data.

6. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that: The steps for obtaining the hidden blockage identification data are as follows: Extract the overall water quality compliance data and water quality compliance margin data of the target treatment section at each collection time during the continuous treatment period from the water quality compliance change data; Extract the unit flow pressure load time series data, adjacent load change data, adjacent cleaning intervention change data, and load increase direction data of the target treatment section during the continuous treatment period from the load change data. Based on the overall water quality compliance data and water quality compliance margin data corresponding to each collection time, water quality compliance maintenance data is generated; among them, when the overall water quality compliance data corresponding to each collection time in the continuous processing period all represent the compliance status, and the water quality compliance margin data corresponding to each collection time is not less than zero, the water quality compliance maintenance data is determined as the compliance maintenance status. Based on adjacent load change data and load increase direction data, load continuously increasing data is generated, which includes both continuously increasing and non-continuously increasing states. Based on adjacent load change data and adjacent cleaning intervention change data, cleaning intervention response data is generated; among them, when the adjacent cleaning intervention change data is greater than or equal to zero and the adjacent load change data is greater than zero, the cleaning intervention response data corresponding to the adjacent effective processing acquisition time is determined as the load not being relieved. When the water quality meets the standard and the load continues to rise, the hidden blockage status is identified as a hidden blockage status. When the water quality compliance data is in the compliance status, the load continuously rising data is in the continuously rising status, and the cleaning intervention response data includes the load not being relieved status, the hidden blockage status is updated to the hidden blockage to be cleaned status. Based on the target treatment section identifier, continuous treatment period, water quality compliance data, load continuously increasing data, cleaning intervention response data, and latent blockage status identifier, latent blockage identification data is generated.

7. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that: The steps for generating operational status data based on effluent treatment fusion data and hidden blockage identification data are as follows: Extract the target treatment section identifier, continuous treatment period, water quality compliance maintenance data, load continuously increasing data, cleaning intervention response data, and hidden blockage status identifier from the hidden blockage identification data; Extract the operation data and energy supply data of the target treatment section during the continuous treatment period from the fusion data of wastewater treatment; Based on the water quality compliance data, the water quality compliance status in the operational status data is determined. The water quality compliance status includes compliance status and non-compliance status. The processing load status in the operation status data is determined based on the continuously increasing load data. The processing load status includes the load increase status and the load not increase status. Based on the processing load status, cleaning intervention response data, and hidden blockage status indicators, the cleaning demand status in the operation status data is determined. The cleaning demand status includes pre-cleaning status and enhanced cleaning status. The energy supply adaptation status in the operation status data is determined based on the energy supply data; in particular, the photovoltaic power supply data, energy storage power data and the power load data of the processing process are used to determine the satisfaction of the photovoltaic power supply data and energy storage power data with the power load data of the processing process, and the energy supply adaptation status is determined based on the satisfaction. The hidden blockage status in the operation status data is determined based on the hidden blockage status identifier. The hidden blockage status includes the presence of a hidden blockage status and the absence of a hidden blockage status. By associating water quality compliance status, treatment load status, cleaning demand status, energy supply compatibility status, and hidden blockage status, operational status data corresponding to the target treatment section is generated.

8. The multi-source data fusion and control method for tailings dam wastewater treatment according to claim 1, characterized in that: The step of generating tailwater treatment control data based on operational status data is as follows: Extract the water quality compliance status, treatment load status, cleaning demand status, energy supply matching status, and hidden blockage status corresponding to the target treatment section from the operation status data. The control trigger state is determined based on the water quality compliance status and the hidden blockage status. The control trigger state includes the water quality abnormality trigger state and the hidden blockage trigger state. The control target for the target processing section is determined based on the processing load status and cleaning demand status. Specifically, when the processing load status is in the increased load state and the cleaning demand status is in the pre-cleaning state or the enhanced cleaning state, the target processing section is determined as the control target. When the processing section identifier corresponding to the target processing section represents the membrane separation section, the control target is the membrane separation section. When the processing section identifier corresponding to the target processing section represents the filtration section, the control target is the filtration section. Control type data is generated based on the control trigger state and the control object; specifically, when the control trigger state is the water quality abnormality trigger state, treatment flow rate control type data and membrane separation operation control type data are generated; when the control trigger state is the hidden blockage trigger state, membrane separation operation control type data and cleaning agent dosing control type data are generated. The control type data is matched with the energy supply matching status. When the energy supply matching status is "energy supply matching status", the current running segment corresponding to the control type data is retained. When the energy supply matching status is "energy supply mismatch status", running segment adjustment data is generated and associated with the control type data. Wastewater treatment control data is generated based on the control type data; specifically, when the control type data includes treatment flow rate control data, treatment flow rate control data is generated; when the control type data includes membrane separation operation control data, membrane separation operation control data is generated; and when the control type data includes cleaning agent dosing control data, cleaning agent dosing control data is generated. When the control trigger state is the latent blockage trigger state, the tailwater treatment control data is marked as latent blockage control data, the no-control result generated based on the water quality compliance state is canceled, and the latent blockage control data is used as the tailwater treatment control data corresponding to the target treatment section. At least one of the following data—processing flow regulation data, membrane separation operation regulation data, cleaning agent dosing regulation data, and operating time regulation data—is correlated with the target treatment section identifier, continuous treatment period, and hidden blockage status to obtain the tailwater treatment control data corresponding to the target treatment section.

Images