Mine water efficient purification calculation method, system, device and medium

Abstract

The present application belongs to the technical field of water purification data processing, and specifically provides a mine water efficient purification calculation method, system, device and medium. The method mainly comprises: obtaining mine water original data; preprocessing the mine water original data to obtain water quality comprehensive indicators; performing trend analysis on the comprehensive indicators and calculating water quality stability in cooperation with pH value, identifying pollution rules in combination with correlation analysis, generating abnormal mode identification through pattern recognition and cross-validation; determining the purification requirement level based on the abnormal mode identification, and dynamically adjusting and optimizing the dosing amount parameter. The present application effectively solves the problems in the prior art that fixed parameters are relied on, it is difficult to match the dynamic changes of water quality, the purification is not complete, the resource consumption is increased, and frequent manual adjustment is required, realizes real-time self-adaptive processing of mine water purification, improves the purification efficiency, reduces resource waste, reduces the frequency of manual intervention, and guarantees the economy and stability of the processing.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of water purification data processing, and particularly relates to a mine water efficient purification calculation method, system, device and medium. BACKGROUND

[0002] Mine water purification is of great significance to water resource recycling and ecological environment protection. At present, mine water treatment is mostly carried out by collecting basic water quality data and combining with conventional purification processes, such as monitoring suspended solids, heavy metal content and other indicators, presetting fixed dosing amount and equipment operation parameters to remove pollutants.

[0003] In actual mine exploitation, water quality is affected by factors such as rainfall infiltration and mining intensity changes, and the pollutant concentration often shows rapid fluctuation characteristics. The existing treatment method relies on pre-set fixed parameters to carry out purification operation, which is difficult to match the dynamic changes of water quality in real time: when the pollutant concentration increases, the purification may not be complete; when the concentration decreases, the excessive reagent may increase resource consumption, and frequent manual intervention is required to adjust the parameters, which affects the treatment efficiency and economy to some extent. SUMMARY

[0004] The application provides a mine water efficient purification calculation method, system, device and medium, which effectively solves the problems of relying on fixed parameters, being difficult to match the dynamic changes of water quality, leading to incomplete purification, increased resource consumption and frequent manual adjustment in the prior art, realizes real-time adaptive treatment of mine water purification, improves purification efficiency, reduces resource waste, reduces the frequency of manual intervention, and guarantees the economy and stability of the treatment.

[0005] In order to achieve the above purpose, the application adopts the following technical solutions:

[0006] In a first aspect, the application provides a mine water efficient purification calculation method, comprising:

[0007] Obtaining mine water original data.

[0008] Pretreating the mine water original data to obtain water quality comprehensive indicators.

[0009] Performing trend analysis on the comprehensive indicators and calculating water quality stability in cooperation with pH value, identifying pollution rules in combination with correlation analysis, and generating abnormal mode identification through pattern recognition and cross-validation.

[0010] Determining the purification demand level based on the abnormal mode identification, dynamically adjusting and optimizing the dosing amount parameters.

[0011] Simulating the purification effect according to the dosing parameters, and generating control suggestions by comparing the difference with the target value.

[0012] Obtaining device operating state data; converting the control suggestion into device instructions, performing security verification in cooperation with the device operating state data, and correcting in combination with the water flow rate to generate final instructions.

[0013] Further, the mine water original data includes heavy metal concentration, suspended matter concentration, and water flow rate.

[0014] The mine water original data is preprocessed to obtain water quality comprehensive indexes, including:

[0015] The original data is subjected to abnormality removal processing to generate a clean data set.

[0016] The clean data set is subjected to normalization processing to generate a standardized water quality data set.

[0017] The heavy metal concentration, suspended matter concentration, and water flow rate are combined through data fusion processing to generate water quality comprehensive indexes.

[0018] Further, the mine water original data also includes pH value.

[0019] The comprehensive indexes are subjected to trend analysis and water quality stability is calculated in cooperation with the pH value, pollution rules are identified through correlation analysis, and abnormal pattern identification is generated through pattern recognition and cross-validation, including:

[0020] The water quality comprehensive indexes are subjected to trend analysis to extract pollutant concentration trend characteristics.

[0021] The pollutant concentration trend characteristics and the pH value are cooperatively evaluated to generate water quality stability evaluation results.

[0022] The pollutant concentration trend characteristics and the water quality comprehensive indexes are subjected to correlation analysis to identify the cooperative change rules of heavy metals and suspended matters, and pollutant correlation factors are generated.

[0023] The water quality stability evaluation results are compared with historical data for pattern recognition to generate abnormal pattern identification.

[0024] The abnormal pattern identification and the pollutant correlation factors are subjected to cross-validation to generate validated abnormal pattern identification.

[0025] Further, based on the abnormal pattern identification, the purification demand level is determined, and the dosing amount parameter is dynamically adjusted and optimized, including:

[0026] Based on the validated abnormal pattern identification, the purification demand level is determined to generate a purification demand level parameter.

[0027] The dosing amount reference is dynamically adjusted according to the purification demand level parameter to generate a preliminary dosing amount reference.

[0028] The preliminary dosing amount benchmark is optimized in combination with the system operation state to generate an optimized dosing amount parameter.

[0029] Further, the purification effect is simulated according to the dosing parameter, and a control suggestion is generated by comparing the difference with a target value, including:

[0030] The purification process is simulated based on the optimized dosing amount parameter to generate simulated purification effect data.

[0031] The simulated purification effect data is compared with a preset target value to generate a purification difference result.

[0032] A purification control suggestion is generated according to the purification difference result.

[0033] Further, the control suggestion is converted into a device instruction, which is verified in combination with device operation state data and corrected in combination with the water flow rate to generate a final instruction, including:

[0034] The purification control suggestion is converted into a control instruction to generate a preliminary control instruction.

[0035] The preliminary control instruction is synergistically optimized in combination with the device operation state data to generate a device synergistic instruction.

[0036] The safety operation range of the device synergistic instruction is verified to generate a safety control instruction.

[0037] The safety control instruction is corrected based on the water flow rate to generate a final control instruction.

[0038] Further, the safety control instruction is corrected based on the water flow rate to generate a final control instruction, including:

[0039] A first threshold value is set; and a current water flow rate change rate is calculated based on the water flow rate.

[0040] When the water flow rate change rate is greater than the first threshold value, the dosing amount parameter of the safety control instruction is corrected.

[0041] In a second aspect, the present application provides a mine water efficient purification calculation system, comprising:

[0042] An original data acquisition module: obtains mine water original data.

[0043] A comprehensive index preprocessing module: pre-processes the mine water original data to obtain water quality comprehensive indexes.

[0044] A pollution mode recognition and abnormality identification module: analyzes the trend of the comprehensive indexes and calculates the water quality stability in combination with the pH value, identifies the pollution law in combination with the correlation analysis, and generates an abnormality mode identification through mode recognition and cross-validation.

[0045] Purification demand and dosing optimization module: determine purification demand level based on abnormal pattern identification, dynamically adjust and optimize dosing amount parameters.

[0046] Purification simulation and control suggestion module: simulate purification effect according to dosing parameters, generate control suggestions by comparing differences with target values.

[0047] Device instruction and safety verification module: obtain device running state data; convert control suggestions into device instructions, perform safety verification in cooperation with device running state data, and correct in combination with water flow rate to generate final instructions.

[0048] In a third aspect, the present application provides a mine water efficient purification computing device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the steps of the mine water efficient purification computing method of the first aspect when the computer program is executed.

[0049] In a fourth aspect, the present application provides a readable storage medium, comprising: a computer program instruction stored in the readable storage medium, the computer program instruction is read and executed by a processor, and the steps of the mine water efficient purification computing method of the first aspect are executed.

[0050] The beneficial effects of the present application are:

[0051] The present application effectively solves the problems in the prior art that fixed parameters are relied on, it is difficult to match dynamic changes of water quality, purification is not complete, resource consumption is increased, and frequent manual adjustment is required, by adopting the scheme of obtaining mine water original data and preprocessing, analyzing water quality stability and pollution rules, generating abnormal identification to dynamically adjust dosing amount, simulating effect and generating control suggestions, and generating final instructions in combination with device state and water flow rate, real-time self-adaptive processing of mine water purification is realized, purification efficiency is improved, resource waste is reduced, frequency of manual intervention is reduced, and economicity and stability of processing are ensured.

[0052] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood from the practice of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures indicated in the specification and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0054] Figure 1 A flowchart of a mine water efficient purification calculation method of the present application is shown.

[0055] Figure 2 A module diagram of a mine water efficient purification calculation system of the present application is shown. DETAILED DESCRIPTION

[0056] To solve the problems raised in the background art, the present application first acquires mine water original data, obtains comprehensive indexes through preprocessing, analyzes the trend and calculates water quality stability in combination with pH value, generates abnormal mode identification after identifying pollution rules, determines purification demand level based thereon, dynamically optimizes dosing amount parameters, simulates purification effect and generates control suggestions, acquires equipment operation state data again, converts the control suggestions into equipment instructions, generates final instructions after safety verification and correction.

[0057] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0058] In some embodiments, as shown in Figure 1 The present application provides a mine water efficient purification calculation method, comprising:

[0059] S1. Acquire mine water original data.

[0060] S2. Preprocess the mine water original data to obtain water quality comprehensive indexes.

[0061] S3. Analyze the trend of the comprehensive indexes and calculate water quality stability in combination with pH value, identify pollution rules in combination with correlation analysis, and generate abnormal mode identification through pattern recognition and cross-validation.

[0062] S4. Determine purification demand level based on the abnormal mode identification, dynamically adjust and optimize dosing amount parameters.

[0063] S5. Simulate purification effect according to the dosing parameters, generate control suggestions by comparing differences with target values.

[0064] S6. Acquire equipment operation state data; convert the control suggestions into equipment instructions, perform safety verification in combination with the equipment operation state data, and correct in combination with water flow rate to generate final instructions.

[0065] In some embodiments, in S1, the mine water original data includes heavy metal concentration, suspended matter concentration, and water flow rate.

[0066] Heavy metal concentration represents the mass concentration of dissolved heavy metal ions (such as iron ions, manganese ions, zinc ions) in mine water, which can be measured in real time by an electrochemical sensor installed in the water inlet pipeline.

[0067] Suspended solids concentration represents the mass concentration of non-dissolved solid particles (such as coal dust, rock debris) in mine water, which can be collected in real time by an optical turbidity sensor or a laser scattering instrument.

[0068] Water flow rate refers to the volume flow rate of mine water through the purification pipeline per unit time, which can be monitored in real time by an electromagnetic flowmeter.

[0069] In S2, the original data of mine water is preprocessed to obtain water quality comprehensive indicators, including:

[0070] S21. Perform outlier removal processing on the original data to generate a clean data set.

[0071] Standard deviation outlier detection algorithm can be used to perform outlier removal processing.

[0072] Specifically, taking a specified time (such as 60 seconds) as a time window, the median and standard deviation of each parameter value in the window are calculated. For any data point of any parameter (including heavy metal concentration, suspended solids concentration, water flow rate) in the window, if the absolute value of the deviation of the point value from the median exceeds a specified multiple (such as 3 times) of the standard deviation, it is identified as an outlier and removed.

[0073] S22. Normalize the clean data set to generate a standardized water quality data set.

[0074] Linear scaling conversion is performed on the heavy metal concentration, suspended solids concentration, and water flow rate parameters, respectively, and normalized to [0, 1].

[0075] S23. Through data fusion processing, heavy metal concentration, suspended solids concentration, and water flow rate are combined to generate water quality comprehensive indicators.

[0076] Using a weighted linear combination algorithm, the three parameters (heavy metal concentration normalized value, suspended solids concentration normalized value, water flow rate normalized value) in the standardized water quality data set are added according to the pre-set weight coefficients to obtain the water quality comprehensive indicators.

[0077] The weight coefficients can be allocated according to the pollutant hazard level principle.

[0078] Exemplarily, the heavy metal pollutant has biological accumulation, chemical stability and high ecological toxicity, and the weight coefficient is 0.6; the suspended matter concentration directly affects the flocculant settling efficiency, and the weight coefficient is 0.3; the water flow rate has a low weight on the effect of the reagent mixing, and the weight coefficient is 0.1.

[0079] In some embodiments, in S1, the mine water original data further includes a pH value.

[0080] In S3, the trend of the comprehensive index is analyzed, and the water quality stability is calculated in combination with the pH value, the pollution rule is identified by combining the correlation analysis, and the abnormal mode identification is generated through pattern recognition and cross-validation, including:

[0081] S31. The trend of the water quality comprehensive index is analyzed to extract the pollutant concentration trend characteristics.

[0082] The linear regression method is used to calculate the change slope of the water quality comprehensive index in the specified window (such as a 10-minute window), and the slope value is the pollutant concentration trend characteristics.

[0083] S32. The pollutant concentration trend characteristics and the pH value are combined for cooperative evaluation to generate the water quality stability evaluation result.

[0084] The water quality stability calculation is performed, and the formula is used: ; wherein, S represents the water quality stability evaluation result, represents the pollutant concentration trend characteristics.

[0085] S33. The correlation analysis is performed on the pollutant concentration trend characteristics and the water quality comprehensive index to identify the cooperative change rule of the heavy metal and the suspended matter, and the pollutant correlation factor is generated.

[0086] The heavy metal component and the suspended matter component are separated from the water quality comprehensive index, the Pearson correlation coefficient of the two component sequences in the same time window is calculated, and the pollutant correlation factor is generated.

[0087] S34. The water quality stability evaluation result is compared with the historical data to perform pattern recognition, and the abnormal mode identification is generated.

[0088] The water quality stability evaluation result data under the same working condition in the recent specified number of days (such as 30 days) stored in the historical database is called, and the mean and the standard deviation are calculated, according to the mean and the standard deviation The threshold range (such as ) is set, if the water quality stability evaluation result exceeds the threshold range, it is determined to be abnormal, and the abnormal mode identification is generated.

[0089] S35. Cross-checking is performed on the abnormal pattern identifier and the pollutant correlation factor to generate a checked abnormal pattern identifier.

[0090] When the abnormal pattern identifier is abnormal, it is checked whether the pollutant correlation factor is greater than a preset abnormal threshold value. If yes, the abnormality is confirmed, and a checked abnormal pattern identifier is generated. Otherwise, it is determined as a false alarm.

[0091] The abnormal threshold value can be determined according to the critical correlation coefficient of the adsorption effect of heavy metal ions and suspended solids in the mine water treatment scene. The critical correlation coefficient is obtained by statistical analysis of the cooperative variation law of pollutants in historical water quality data.

[0092] In some embodiments, in S4, the purification demand level is determined based on the abnormal pattern identifier, and the dosing amount parameter is dynamically adjusted and optimized, including:

[0093] S41. The purification demand level is determined based on the checked abnormal pattern identifier, and a purification demand level parameter is generated.

[0094] The checked abnormal pattern identifier is a Boolean value: 0 represents a normal state, and 1 represents an abnormal state. When the identifier value is 1, a multi-level (such as three levels) demand level mechanism is activated.

[0095] The purification demand level parameter output is a discrete integer identifier value: identifier value 0 corresponds to level 0, which is the baseline purification intensity; identifier value 1 corresponds to level 1, which is moderate purification enhancement; identifier value 1 for three consecutive times corresponds to level 2, which is high purification enhancement; and identifier value 1 for five consecutive times corresponds to level 3, which is emergency purification enhancement.

[0096] For example, when the checked abnormal pattern identifier is 1 for the first time, the purification demand level parameter generated is 1; if the checked abnormal pattern identifier is 1 for three consecutive times, the purification demand level parameter generated is 2.

[0097] S42. The preliminary dosing amount reference is dynamically adjusted according to the purification demand level parameter to generate a preliminary dosing amount reference.

[0098] The preset baseline dosing amount , a mapping relationship between the level and the dosing amount is established: ; wherein A represents the preliminary dosing amount reference.

[0099] S43. The preliminary dosing amount reference is optimized in combination with the system running state to generate an optimized dosing amount parameter.

[0100] The system running state data includes a mixer power margin parameter P, which represents the real-time working capacity of the mixing equipment; wherein the working capacity range is 0~100%, and 100% indicates full load.

[0101] The optimization adopts a stirring power constraint formula: ; wherein, represents the optimization of the dosing parameter.

[0102] In some embodiments, in S5, the purification effect is simulated according to the dosing parameter, and a control suggestion is generated by comparing the difference with the target value, including:

[0103] S51. Perform a purification process simulation based on the optimized dosing parameter to generate simulated purification effect data.

[0104] A three-dimensional reaction kinetics model is used to simulate the dosing reaction process, and the three-dimensional reaction kinetics model is input with the optimized dosing parameter, and the output includes three indicators: heavy metal residual concentration, suspended matter settling rate, and water quality clarity, which constitute the simulated purification effect data.

[0105] S52. Compare the simulated purification effect data with the preset target value to generate a purification difference result.

[0106] The preset target value is strictly set according to the national standard, wherein the target limit value of heavy metal residual concentration is 0.05 mg / L, the target value of suspended matter settling rate is 95%, and the target reference value of water quality clarity is 2.0 NTU.

[0107] The comparison process performs three judgments:

[0108] If the heavy metal residual concentration is greater than 0.05 mg / L, the heavy metal exceeds the standard flag is output as 1, otherwise it is 0; if the suspended matter settling rate is less than 95%, the settling deficiency flag is output as 1, otherwise it is 0; and the clarity deviation D is calculated.

[0109] The clarity deviation D calculation formula is: ; wherein, represents the measured clarity value in the simulated purification effect data, represents the target clarity reference value, represents the time conversion coefficient, , represents the sedimentation time adjustment amount, represents the turbidity deviation value, experiments show that every 0.1 NTU deviation needs to correspond to 1 minute of sedimentation time adjustment, then 10 is taken.

[0110] S53. Generate a purification control suggestion according to the purification difference result.

[0111] Based on the difference flag state, the corresponding device operation suggestion is generated: when the heavy metal exceeds the standard flag is 1, it is suggested to increase the oxidant dosage by 25%; when the settling deficiency flag is 1, it is suggested to increase the flocculant concentration by 10%; according to the clarity deviation value N, it is suggested to extend the sedimentation time by N minutes.

[0112] In some embodiments, in S6, the control suggestion is converted into device instructions, verified with device running state data for safety, and corrected with water flow rate to generate final instructions, including:

[0113] S61. Convert the purification control suggestion into control instructions to generate preliminary control instructions.

[0114] The purification control suggestion contains a dosage adjustment percentage parameter, denoted as , j = 1, 2, …, corresponding to different reagents, and a voltage mapping function is used to generate device voltage signals: ; wherein, represents the preliminary control voltage of the jth reagent, represents the reference voltage of the jth reagent device, represents the adjustment percentage of the jth reagent in the purification control suggestion.

[0115] S62. Perform collaborative optimization of preliminary control instructions with device running state data to generate device collaborative instructions.

[0116] Device running state data includes the power margin of each device.

[0117] The optimization formula is: ; wherein, represents the collaborative optimization voltage of the jth reagent, represents the real-time power margin of the jth device, represents the margin safety threshold.

[0118] S63. Verify the safety operation range of the device collaborative instructions to generate safety control instructions.

[0119] Set the device voltage safety interval , , and the correction rule is: ; wherein, represents the safety control instruction voltage value, represents the device collaborative instruction input voltage, represents the minimum safe working voltage of device j, represents the maximum safe working voltage of device j.

[0120] S64. Based on the water flow rate, the safety control instructions are corrected to generate final control instructions.

[0121] In some embodiments, in S64, based on the water flow rate, the safety control instructions are corrected to generate final control instructions, including:

[0122] S641. Set a first threshold value; calculate a current water flow rate change rate based on the water flow rate.

[0123] The first threshold value is a flow rate mutation threshold value, which can be determined based on a critical influence threshold value of water flow mutation on the stability of medicament diffusion in the mine water treatment system. The water flow rate change rate is denoted as a.

[0124] S642. When the water flow rate change rate is greater than the first threshold value, correct the dosing amount parameter of the safety control instruction.

[0125] If the water flow rate change rate a is greater than the flow rate mutation threshold value, the final control voltage value of the jth medicament of the final control instruction is : ; wherein, the safety control instruction input voltage is denoted as V, the correction coefficient is denoted as k, which can be determined according to a coupling relationship model of flow rate change and pollutant concentration decay in fluid mechanics.

[0126] In some embodiments, as Figure 2 shown, the present application also provides a mine water efficient purification calculation system, which comprises:

[0127] An original data acquisition module: acquires mine water original data.

[0128] A comprehensive index preprocessing module: pre-processes the mine water original data to obtain water quality comprehensive indexes.

[0129] A pollution pattern recognition and anomaly identification module: performs trend analysis on the comprehensive indexes, calculates water quality stability in cooperation with pH value, identifies pollution rules in combination with correlation analysis, and generates anomaly pattern identification through pattern recognition and cross-validation.

[0130] A purification demand and dosing optimization module: determines the purification demand level based on the anomaly pattern identification, dynamically adjusts and optimizes the dosing amount parameter.

[0131] A purification simulation and control suggestion module: simulates the purification effect according to the dosing parameter, generates control suggestions by comparing the difference with the target value.

[0132] An equipment instruction and safety verification module: acquires equipment running state data; converts the control suggestions into equipment instructions, performs safety verification in cooperation with the equipment running state data, and corrects the final instructions in combination with the water flow rate.

[0133] In some embodiments, the present application also provides a mine water efficient purification calculation device, which comprises a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to realize the steps of the mine water efficient purification calculation method.

[0134] In some embodiments, the application further provides a readable storage medium, comprising: computer program instructions stored in the readable storage medium, when read and executed by a processor, performing the steps of the mine water efficient purification calculation method.

[0135] Wherein, any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory.

[0136] It should be noted that, in this paper, such as "first" and "second" and other relational terms are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "include", "contain" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0137] Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A mine water high-efficiency purification calculation method, characterized in that, The method comprises the following steps: obtaining raw mine water data; preprocessing the raw mine water data to obtain a water quality comprehensive index; performing trend analysis on the comprehensive index and calculating water quality stability in cooperation with the pH value, identifying pollution rules in combination with correlation analysis, and generating an abnormal mode identifier through pattern recognition and cross-validation; determining the purification requirement level based on the abnormal mode identifier, dynamically adjusting and optimizing the dosing amount parameter; simulating the purification effect according to the dosing parameter, and generating a control suggestion by comparing the difference with the target value; obtaining equipment operation state data; converting the control suggestion into equipment instructions, cooperating with the equipment operation state data for safety verification, and combining with the water flow rate for correction to generate the final instruction; wherein the raw mine water data includes the pH value; the trend analysis on the comprehensive index and the calculation of the water quality stability in cooperation with the pH value, the identification of the pollution rules in combination with the correlation analysis, and the generation of the abnormal mode identifier through the pattern recognition and the cross-validation, comprise: calculating the change slope of the water quality comprehensive index in the specified window by using the linear regression method to obtain the pollution concentration trend characteristics; The water quality stability evaluation result is generated by combining the pollutant concentration trend characteristics and the pH value, and the formula is as follows: ; wherein, S represents the water quality stability evaluation result, represents the pollutant concentration trend characteristics; separating the heavy metal component and the suspended matter component from the water quality comprehensive index, and calculating the Pearson correlation coefficient of the two component sequences in the same time window as the pollution correlation factor; The water quality stability evaluation result data of the same working condition in the recent specified days stored in the call history database are calculated for mean value and standard deviation , the threshold range is set according to the mean value and the standard deviation , if the water quality stability evaluation result exceeds the threshold range, it is determined as abnormal, and an abnormal mode identifier is generated; when the abnormal mode identifier is abnormal, checking whether the pollution correlation factor is greater than the preset abnormal threshold value, if yes, confirming the abnormality, generating the verified abnormal mode identifier, otherwise, determining it as a false alarm.

2. The mine water high efficiency purification calculation method according to claim 1, characterized in that, The raw mine water data includes heavy metal concentration, suspended matter concentration and water flow rate; The preprocessing of the raw mine water data to obtain the water quality comprehensive index comprises: performing abnormal removal processing on the raw data to generate a clean data set; performing normalization processing on the clean data set to generate a standardized water quality data set; combining the heavy metal concentration, the suspended matter concentration and the water flow rate through data fusion processing to generate the water quality comprehensive index.

3. The mine water high efficiency purification calculation method according to claim 1, characterized in that, The determination of the purification requirement level based on the abnormal mode identifier, the dynamic adjustment and optimization of the dosing amount parameter, comprise: determining the purification requirement level based on the verified abnormal mode identifier to generate a purification requirement level parameter; dynamically adjusting the dosing amount reference according to the purification requirement level parameter to generate a preliminary dosing amount reference; optimizing the preliminary dosing amount reference in combination with the system operation state to generate an optimized dosing amount parameter.

4. The mine water high efficiency purification calculation method according to claim 1, characterized in that, The simulation of the purification effect according to the dosing parameter, and the generation of the control suggestion by comparing the difference with the target value, comprise: simulating the purification process based on the optimized dosing amount parameter to generate simulation purification effect data; performing standard comparison between the simulation purification effect data and the preset target value to generate a purification difference result; generating a purification control suggestion according to the purification difference result.

5. The mine water high efficiency purification calculation method according to claim 1, characterized in that, The conversion of the control suggestion into equipment instructions, the safety verification in cooperation with the equipment operation state data, and the correction in combination with the water flow rate to generate the final instruction, comprise: converting the purification control suggestion into a control instruction to generate a preliminary control instruction; optimizing the preliminary control instruction in combination with the equipment operation state data to generate an equipment cooperative instruction; verifying the safety operation range of the equipment cooperative instruction to generate a safety control instruction; linking and correcting the safety control instruction based on the water flow rate to generate the final control instruction.

6. The mine water high efficiency purification calculation method according to claim 5, characterized in that, The safety control instruction is linked to correct based on the water flow rate, and a final control instruction is generated, including: Setting a first threshold value; calculating the current water flow rate change rate based on the water flow rate; When the water flow rate change rate is greater than the first threshold value, the dosing amount parameter of the safety control instruction is corrected.

7. A mine water high efficiency purification computing system, characterized in that, It includes: Raw data acquisition module: obtain mine water raw data; Comprehensive index preprocessing module: pre-process the mine water raw data to obtain water quality comprehensive index; Pollution pattern recognition and anomaly identification module: trend analysis is performed on the comprehensive index, and the water quality stability is calculated in cooperation with the pH value, the pollution law is identified in combination with the correlation analysis, and the anomaly pattern identification is generated through pattern recognition and cross-validation; Purification demand and dosing optimization module: determine the purification demand level based on the anomaly pattern identification, dynamically adjust and optimize the dosing amount parameter; Purification simulation and control suggestion module: simulate the purification effect according to the dosing parameter, generate control suggestions by comparing the difference with the target value; Device instruction and safety verification module: obtain device running state data; convert the control suggestions into device instructions, perform safety verification in cooperation with the device running state data, and correct based on the water flow rate to generate the final instruction; The mine water raw data includes pH value; the water quality stability is calculated in cooperation with the pH value based on the trend analysis of the comprehensive index, the pollution law is identified in combination with the correlation analysis, and the anomaly pattern identification is generated through pattern recognition and cross-validation, including: The linear regression method is used to calculate the change slope of the water quality comprehensive index in the specified window, and the pollution concentration trend characteristics are obtained; The water quality stability evaluation result is generated by combining the pollutant concentration trend characteristics and the pH value, and the formula is as follows: ; wherein, S represents the water quality stability evaluation result, represents the pollutant concentration trend characteristics; The heavy metal component and the suspended matter component are separated from the water quality comprehensive index, and the Pearson correlation coefficient of the two component sequences in the same time window is calculated as the pollution correlation factor; The water quality stability evaluation result data of the same working condition in the recent specified days stored in the call history database are calculated for mean value and standard deviation , the threshold range is set according to the mean value and the standard deviation , if the water quality stability evaluation result exceeds the threshold range, it is determined as abnormal, and an abnormal mode identifier is generated; When the anomaly pattern identification is abnormal, check whether the pollution correlation factor is greater than the preset abnormal threshold value, if yes, confirm the anomaly, generate the verified anomaly pattern identification, otherwise, determine it as a false alarm.

8. A mine water high efficiency purification computing device, characterized by, It includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to realize the steps of the mine water efficient purification calculation method in any one of claims 1-6.

9. A readable storage medium, characterized by, It includes: the computer program instructions are stored in the readable storage medium, and the computer program instructions are read and run by a processor to execute the steps of the mine water efficient purification calculation method in any one of claims 1-6.

Images