Filter operation optimization intelligent control system and control method

Abstract

The invention relates to the technical field of filter tank automatic control, in particular to a filter tank operation optimization intelligent control system and method, and the method comprises the steps: setting preposed time, calculating a preposed operation coefficient of the preposed time, analyzing the turbidity of filtered water after backwashing, determining a turbidity change function, and carrying out the derivative operation of the turbidity change function. According to the time process that the post-filtration turbidity value reaches the stable turbidity value, setting cycle time, collecting cycle operation energy consumption in the cycle time, determining an energy consumption function based on the cycle operation energy consumption and a pre-operation coefficient, and combining the energy consumption function with the pre-operation coefficient to obtain comprehensive cycle energy consumption and an energy consumption curve; the lowest point of the energy consumption curve is recognized, then a flushing trigger value is obtained, and then a backwashing signal is generated according to the flushing trigger value, so that the filter operation flexibility is improved, and the filter backwashing energy consumption is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of filter tank automatic control, and in particular to an intelligent control system and a control method for optimizing filter tank operation. Background Art

[0002] Filtration is an important part of water treatment process. In the filter tank of water supply project, when the filter tank is filtering water, during the working cycle, as the amount of pollutants intercepted by the filter material layer increases, the porosity of the filter material continues to decrease, the sludge penetration deepens, the resistance to water flow increases, resulting in a decrease in filtration rate, a gradual increase in the water level of the filter tank, and an increase in the turbidity of the filtered water.

[0003] Prior art CN116585767A discloses an automatic backwash control method for a V-type filter, including: monitoring the opening of a clean water valve corresponding to the filter body through a water outlet regulating valve; monitoring the filter liquid level of the corresponding filter body through a filter level meter; determining that the corresponding filter body is blocked when the clean water valve opening is greater than a blocking threshold and the filter liquid level is greater than a first liquid level threshold; and sending a control signal to a valve controller to control the start of a backwash program. By using an electric regulating valve and an ultrasonic level meter to control the water outlet of the filter, and by using the filter blockage degree as the basis for backwash triggering, the backwash cycle can be automatically adjusted according to different water quality changes, ensuring that the filter is in a benign operating condition.

[0004] However, at present, most of the backwash parameters of the filter are fixed values ​​set by employees based on their work experience. However, during the backwash process, due to water quality fluctuations and other reasons, the fixed backwash cycle reduces the flexibility of the filter operation and also increases the energy consumption during the filter backwash process. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the background technology and to propose an intelligent control system and control method for optimizing filter operation.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An intelligent control system for filter tank operation optimization, comprising a data storage end, a parameter analysis end, an optimization analysis end and an operation control end;

[0008] The data storage end is used to store the operating parameters of the filter tank and generate storage data, wherein the operating parameters include the blockage value, the turbidity value after filtration, the turbidity of the initial filtered water and the operating energy consumption. The data storage end and the parameter analysis end are connected in a one-way communication manner;

[0009] The parameter analysis end is used to analyze the stored data, calculate the blockage value and the post-filtration turbidity value within the backwashing lead time by setting the lead time, determine the lead time operation coefficient, then analyze the turbidity of the filtered water after backwashing, determine the turbidity change function, then perform derivative operation on the turbidity change function to obtain a stable turbidity value, then set the cycle time according to the time process for the post-filtration turbidity value to reach the stable turbidity value, and collect the cycle operation energy consumption within the cycle time, determine the energy consumption function based on the cycle operation energy consumption and the lead time operation coefficient, and then the parameter analysis end transmits the energy consumption function to the optimization analysis end;

[0010] The optimization and analysis end is used to determine the target operation cycle according to the filtration time between the stable turbidity value and the pre-operation coefficient, and at the same time set the first operation period, divide the first operation period by the target operation cycle to obtain the period flushing coefficient, combine the period flushing coefficient with the energy consumption function, determine the comprehensive cycle energy consumption, and identify the pre-operation coefficient corresponding to the lowest point in the energy consumption curve according to the energy consumption curve of the comprehensive cycle energy consumption, and use it as the flushing trigger value of the filter tank. After that, the optimization and analysis end transmits the flushing trigger value to the operation control end;

[0011] The operation control end is used to monitor and collect the blockage value and post-filtration turbidity value of the filter in real time according to the flushing trigger value, and calculate the pre-operation coefficient. If the pre-operation coefficient is greater than or equal to the flushing trigger value, a backwash signal is generated and the filter is controlled to perform backwashing action.

[0012] As a further solution of the present invention, the calculation method of the pre-operation coefficient includes:

[0013] Set the lead time, take the start time of backwashing in the filter tank as the time node, and identify the operating parameters and energy consumption parameters within the lead time, where the lead time refers to the time segment before the backwashing starts in the filter tank;

[0014] Extract all the information parameters in the backwash period and the operating parameters in the lead time from the stored data. First, take the operating parameters in the lead time and use the formula Get the pre-operation coefficient Qxi;

[0015] Where i represents different backwashing processes, and i∈[1,I], I represents that there are I backwashing processes in the stored data, ZSi represents the blocking value in the lead time of backwashing process i, LBi represents the post-filtration turbidity value in the lead time of backwashing process i, and All are proportional coefficients.

[0016] As a further embodiment of the present invention, the calculation method of the turbidity change function includes:

[0017] Set the unit interval time, and mark the turbidity of the filtered water as HZj according to the unit interval time, where j represents the turbidity of the filtered water collected at different unit interval times;

[0018] Taking time as the independent variable and filtered water turbidity as the dependent variable, the filtered water turbidity of all backwashing periods was taken as the experimental group, and the artificial intelligence algorithm was used for linear fitting to obtain the turbidity change function F1 of the filtered water turbidity: , where b1 and b2 are constant coefficients, and b1>0, is the exponential factor, CS is the turbidity of the initial filtered water, and Tj is the change time of the turbidity of the filtered water.

[0019] As a further embodiment of the present invention, the calculation method of the stable turbidity value includes:

[0020] Perform a secondary derivative operation on the turbidity change function F1, and mark the result after the derivative operation as the trend change value f(Tj), where: , represents the second derivative;

[0021] When the trend change value f(Tj)>0, the interval corresponding to the flushing period Tj is marked as the trend interval, and then the first derivative of the turbidity change function F1 is taken, that is, ,in, represents the first derivative;

[0022] Take the absolute value of the first derivative of the turbidity change function F1, and within the trend interval, take the minimum absolute value, and obtain the flushing period Tj corresponding to the minimum absolute value, and then substitute this flushing period Tj into the original turbidity change function F1, and mark the obtained filtered water turbidity as the stable turbidity value Wz.

[0023] As a further solution of the present invention, a method for determining the energy consumption function includes:

[0024] A backwashing process is randomly selected as the target operation process, the starting period of the lead time in the target flushing process is taken as the starting time point, the time when the turbidity of the filtered water reaches a stable turbidity value after the backwashing is completed is taken as the ending time point, and then the starting time point and the ending time point are taken as a cycle time, the operation energy consumption in this cycle time is collected and marked as the cycle operation energy consumption Gzi;

[0025] Obtain the pre-filtered water volume FWi and the total filtered water volume TWi during each backwashing cycle, and record the backwashing energy consumption during each backwashing cycle and mark it as RBi;

[0026] The pre-operation coefficient Qxi, pre-filtered water volume FWi, total filtered water volume TWi, backwashing energy consumption RBi and periodic operation energy consumption Gzi in each backwashing process are taken as a data group, and the data of all backwashing processes in the stored data are integrated to obtain a total of I data groups, and then I data groups are used as test groups, and artificial intelligence is used for simulation calculation to obtain the energy consumption function: , where b3 is a constant coefficient, is the index, G0 is the benchmark energy consumption, and f (FWi, TWi) is the water volume filtering function.

[0027] As a further solution of the present invention, a method for determining a flushing trigger value includes:

[0028] A pre-operation coefficient is randomly selected as the target operation value, and a first operation period is set at the same time. The filtration time between the stable turbidity value and the target operation value is identified in the stored data, and the average of the filtration time is taken and marked as the target operation period;

[0029] Divide the first operation period by the target operation cycle to obtain the period flushing coefficient Xc;

[0030] Using Formula E: Get the comprehensive cycle energy consumption ZN, where is the correction factor;

[0031] The pre-operation coefficient is used as the horizontal coordinate, and the backwashing energy consumption is used as the vertical coordinate, respectively, to set a two-dimensional coordinate system, and the formula E is displayed as a linear image on the two-dimensional coordinate system to obtain an energy consumption curve;

[0032] The lowest point of the backwash energy consumption ZN in the energy consumption curve is identified, and the pre-operation coefficient corresponding to the lowest point of the backwash energy consumption ZN is obtained, and used as the flushing trigger value of the filter tank.

[0033] As a further solution of the present invention, the pre-operation coefficient in the time period flushing coefficient Xc and the pre-operation coefficient in the energy consumption function are kept consistent during the process of calculating the comprehensive period energy consumption ZN.

[0034] As a further solution of the present invention, the operating parameters of the filter tank are collected by the parameter collection end and transmitted to the data storage end for storage.

[0035] A filter operation optimization intelligent control method, the control method specifically comprises the following steps:

[0036] Step 1: Collect the operating parameters of the filter tank, and extract the blockage value and post-filtration turbidity value in each lead time from the stored data in the Scada system of the water plant, and calculate the lead operation coefficient in each lead time based on the blockage value and post-filtration turbidity value;

[0037] Step 2: Set the unit interval time, collect the turbidity of the filtered water corresponding to each unit interval time in the backwash period, obtain the turbidity of the filtered water in all backwash periods as the test group, and calculate the turbidity change function;

[0038] Step 3: Perform derivative calculation on the turbidity change function, first determine the trend interval of the flushing period, and then determine the stable turbidity value based on the trend interval;

[0039] Step 4: Based on the time process of the turbidity value after filtration in the filter tank reaching a stable turbidity value, set the cycle time, collect the cycle operation energy consumption within the cycle time, take the pre-operation coefficient and the cycle operation energy consumption as the data group, extract all the data groups in the stored data and perform simulation calculations to obtain the energy consumption function;

[0040] Step 5: Based on the filtration time between the stable turbidity value and the pre-operation coefficient, determine the period flushing coefficient, combine the period flushing coefficient with the energy consumption function, and determine the comprehensive period energy consumption;

[0041] Step 6: According to the energy consumption curve of the comprehensive cycle energy consumption, identify the pre-operation coefficient corresponding to the lowest point in the energy consumption curve and use it as the flushing trigger value of the filter. After that, the filter will collect and process the operating parameters of the filter in real time according to the flushing trigger value, and then control the filter to perform backwashing.

[0042] Compared with the prior art, the advantages of the present invention are:

[0043] The present invention analyzes the blockage value and the post-filtration turbidity value of the filter, calculates the pre-operation coefficient of the filter, and then calculates the cycle operation energy consumption of the filter within the cycle time, combines the pre-operation coefficient with the cycle operation energy consumption, determines the comprehensive cycle energy consumption of the filter in the first operation period, and determines the flushing trigger value of the filter based on the energy consumption curve of the comprehensive cycle energy consumption, so as to adjust the backwashing cycle of the filter in real time, thereby improving the flexibility of the filter operation, reducing the filter backwashing energy consumption, and further reducing the production cost of the water plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0045] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0047] Reference Figure 1 and Figure 2 , an intelligent control system for filter tank operation optimization, including a parameter acquisition end, a data storage end, a parameter analysis end, an optimization analysis end and an operation control end;

[0048] The parameter collection terminal is used to collect the operating parameters in the filter tank in real time and transmit them to the parameter analysis module, where the operating parameters include the blockage value, the turbidity value after filtration, the turbidity of the initial filtered water and the operating energy consumption;

[0049] Furthermore, the parameter acquisition module is composed of a plurality of acquisition devices, including flow sensors, inlet turbidity meters, post-filtration turbidity meters, inlet pressure gauges, post-filtration pressure gauges, process electricity meters, and blockage meters;

[0050] The data storage end is used to upload the operation parameters and energy consumption parameters of the filter tank to the water plant Scada system and store them in the water plant Scada system. At the same time, there is a two-way communication connection between the data storage end and the parameter analysis end;

[0051] The parameter analysis terminal is used to analyze the operating parameters of the filter and determine the energy consumption function of the filter during the backwashing process;

[0052] The specific method for determining the energy consumption function of the filter during backwashing includes:

[0053] S1: Based on the stored data in the data storage terminal, the lead time is set at the same time, and the start time of backwashing in the filter tank is used as the time node to identify the operating parameters and energy consumption parameters within the lead time, wherein the lead time refers to the time segment before the backwashing starts in the filter tank, and the specific value of the lead time is obtained by technicians in this field after big data calculation;

[0054] S2: Extract all the information parameters in the backwash period and the operating parameters in the lead time from the stored data. First, take the operating parameters in the lead time and use the formula The lead-time operation coefficient Qxi is obtained, where i represents different backwashing processes, and i∈[1, I], I represents that there are I backwashing processes in the stored data, that is, the filter tank has been backwashed I times in total, ZSi represents the blockage value in the lead time of backwashing process i, LBi represents the post-filtration turbidity value in the lead time of backwashing process i, and are proportionality coefficients, and and The specific values ​​are obtained by technicians in this field after big data calculation;

[0055] It should be further explained that the blockage value ZSi and the post-filtration turbidity value LBi are both average values ​​within the lead time i, and the blockage value ZSi is monitored and collected in real time by the blockage meter, and the post-filtration turbidity value LBi is monitored and collected in real time by the post-filtration turbidity meter;

[0056] S3: extracting the operation data of the backwash period from the stored data, wherein the operation data includes the backwash time, the turbidity of the initial filtered water after backwashing, and the turbidity of the filtered water;

[0057] S31: extracting the turbidity of the filtered water and calculating the stable turbidity value of the turbidity of the filtered water. The specific method for calculating the stable turbidity value includes:

[0058] The unit interval time is set, and the turbidity of the filtered water is marked as HZj according to the unit interval time, wherein j represents the turbidity of the filtered water collected at different unit interval times. Furthermore, in this embodiment, the unit interval time is set to 1 minute, that is, the collection interval time of the turbidity meter after filtration of the collection device is 1 minute;

[0059] Taking time as the independent variable and filtered water turbidity as the dependent variable, the filtered water turbidity of all backwashing periods was taken as the experimental group, and the artificial intelligence algorithm was used for linear fitting to obtain the turbidity change function F1 of the filtered water turbidity: , where b1 and b2 are constant coefficients, and b1>0, is the exponential factor, CS is the initial filtered water turbidity, Tj is the change time of filtered water turbidity, further, b1, b2 and The specific values ​​of are obtained by artificial intelligence algorithms after multiple simulation operations;

[0060] Among them, the artificial intelligence algorithm in this example is selected as a spline interpolation algorithm, and the specific spline interpolation algorithm fitting process is an existing technology and will not be described in detail here;

[0061] Then, the turbidity change function F1 is subjected to a secondary derivative operation, and the result after the derivative operation is marked as the trend change value f(Tj), where: ;

[0062] It needs to be further explained that represents the second derivative;

[0063] When the trend change value f(Tj)>0, the interval corresponding to the flushing period Tj is marked as the trend interval, and then the first derivative of the turbidity change function F1 is taken, that is, ,in represents the first derivative;

[0064] Take the absolute value of the first derivative of the turbidity change function F1, and take the minimum absolute value within the trend interval, and obtain the flushing period Tj corresponding to the minimum absolute value, and then substitute this flushing period Tj into the original turbidity change function F1, and mark the obtained filtered water turbidity as the stable turbidity value Wz;

[0065] S4: arbitrarily select a backwashing process as the target operation process, take the starting period of the lead time in the target backwashing process as the starting time point, take the time when the turbidity of the filtered water reaches a stable turbidity value after the backwashing is completed as the ending time point, and then take the starting time point and the ending time point as a cycle time, collect the operation energy consumption in this cycle time, and mark it as the cycle operation energy consumption Gzi, where i here is consistent with i in step S2, both representing different backwashing processes;

[0066] Among them, the cycle operation energy consumption refers to the sum of the normal water filtration energy consumption and backwashing energy consumption of the filter tank during the cycle time;

[0067] S5: Obtain the pre-filtered water volume FWi during each backwash and the total filtered water volume TWi within the cycle time, and record the backwash energy consumption during each backwash and mark it as RBi;

[0068] The pre-operation coefficient Qxi, pre-filtered water volume FWi, total filtered water volume TWi, backwashing energy consumption RBi and periodic operation energy consumption Gzi in each backwashing process are taken as a data group, and the data of all backwashing processes in the stored data are integrated to obtain a total of I data groups, and then I data groups are used as test groups, and artificial intelligence is used for simulation calculation to obtain the energy consumption function: , where b3 is a constant coefficient, is the index, G0 is the benchmark energy consumption, f (FWi, TWi) is the water volume filtering function, b3 and The specific values ​​of are obtained by the test group after multiple simulation operations, and the benchmark energy consumption G0 is set by technicians in this field based on big data experience;

[0069] After that, the parameter analysis end and the optimization analysis end are connected in a one-way communication manner, and the parameter analysis end transmits the energy consumption function to the optimization analysis end;

[0070] The optimization analysis end determines the flushing trigger value of the filter tank based on the received energy consumption function. The specific method for determining the flushing trigger value includes:

[0071] SS1: arbitrarily select a pre-operation coefficient as the target operation value, set the first operation period at the same time, identify the filtration time between the stable turbidity value and the target operation value in the stored data, take the average of the filtration time, and mark it as the target operation period;

[0072] Divide the first operating period by the target operating cycle to obtain the period flushing coefficient Xc, wherein the first operating period is set to one month in this embodiment;

[0073] SS2: Using formula E: Get the comprehensive cycle energy consumption ZN, where is the correction factor, and The specific value of is obtained by technicians in this field after big data calculation;

[0074] It should be further explained that the pre-operation coefficient in the period flushing coefficient Xc and the pre-operation coefficient in the energy consumption function remain consistent in the process of calculating the comprehensive period energy consumption ZN;

[0075] SS3: Set the pre-operation coefficient as the horizontal coordinate and the backwash energy consumption as the vertical coordinate, set a two-dimensional coordinate system, and display the formula E in a linear image on the two-dimensional coordinate system to obtain the energy consumption curve;

[0076] Identify the lowest point of backwash energy consumption ZN in the energy consumption curve, obtain the pre-operation coefficient corresponding to the lowest point of backwash energy consumption ZN, and use it as the flushing trigger value of the filter tank;

[0077] Afterwards, the optimization and analysis end transmits the flushing trigger value of the filter to the operation control end. Based on the flushing trigger value, the operation control end monitors and collects the blockage value and post-filtration turbidity value of the filter in real time, and calculates the pre-operation coefficient. If the pre-operation coefficient is greater than or equal to the flushing trigger value, a backwashing signal is generated, and the filter is controlled to perform backwashing.

[0078] It should be further explained that, in this embodiment, the air-water backwashing method is used to backwash the filter tank. Compared with water backwashing, air-water backwashing adds air, which increases the shear force on the filter material surface, thereby enhancing the dirt removal rate, while reducing the intensity of water flushing, further reducing the backwashing energy consumption.

[0079] A filter operation optimization intelligent control method, the control method specifically comprises the following steps:

[0080] Step 1: Collect the operating parameters of the filter tank, and extract the blockage value and post-filtration turbidity value in each lead time from the stored data in the Scada system of the water plant, and calculate the lead operation coefficient in each lead time based on the blockage value and post-filtration turbidity value;

[0081] Step 2: According to the operation data of the backwash period in the stored data, the unit interval time is set, the turbidity of the filtered water corresponding to each unit interval time in the backwash period is collected, the turbidity of the filtered water in all backwash periods is obtained, and the turbidity is used as the test group to calculate the turbidity change function F1;

[0082] Step 3: Process the turbidity change function, perform a secondary derivative operation on the turbidity change function to determine the trend interval of the flushing period, then perform a primary derivative operation on the turbidity change function, combine the result of the operation with the trend interval, and determine the stable turbidity value;

[0083] Step 4: Based on the time process of the post-filtration turbidity value in the filter tank reaching a stable turbidity value, set the cycle time, collect the cycle operation energy consumption within the cycle time, take the pre-operation coefficient and cycle operation energy consumption in each backwashing process as a data group, extract all the data groups in the stored data and perform simulation calculations to obtain the energy consumption function;

[0084] Step 5: Based on the filtration time between the stable turbidity value and the pre-operation coefficient, determine the target operation cycle, set the first operation period, divide the first operation period by the target operation cycle, obtain the period flushing coefficient, combine the period flushing coefficient with the energy consumption function, and determine the comprehensive cycle energy consumption;

[0085] Step 6: According to the energy consumption curve of the comprehensive cycle energy consumption, identify the pre-operation coefficient corresponding to the lowest point in the energy consumption curve and use it as the flushing trigger value of the filter. After that, the filter will collect and process the operating parameters of the filter in real time according to the flushing trigger value, and then control the filter to perform backwashing.

[0086] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent control system for optimizing filter operation, characterized in that: It includes data storage end, parameter analysis end, optimization analysis end and operation control end; The data storage end is used to store the operating parameters of the filter tank and generate storage data, wherein the operating parameters include the blockage value, the turbidity value after filtration, the turbidity of the initial filtered water and the operating energy consumption. The data storage end and the parameter analysis end are connected in a one-way communication manner; The parameter analysis end is used to analyze the stored data, calculate the blockage value and the post-filtration turbidity value within the backwashing lead time by setting the lead time, determine the lead time operation coefficient, then analyze the turbidity of the filtered water after backwashing, determine the turbidity change function, then perform derivative operation on the turbidity change function to obtain a stable turbidity value, then set the cycle time according to the time process for the post-filtration turbidity value to reach the stable turbidity value, and collect the cycle operation energy consumption within the cycle time, determine the energy consumption function based on the cycle operation energy consumption and the lead time operation coefficient, and then the parameter analysis end transmits the energy consumption function to the optimization analysis end; The optimization and analysis end is used to determine the target operation cycle according to the filtration time between the stable turbidity value and the pre-operation coefficient, and at the same time set the first operation period, divide the first operation period by the target operation cycle to obtain the period flushing coefficient, combine the period flushing coefficient with the energy consumption function, determine the comprehensive cycle energy consumption, and identify the pre-operation coefficient corresponding to the lowest point in the energy consumption curve according to the energy consumption curve of the comprehensive cycle energy consumption, and use it as the flushing trigger value of the filter tank. After that, the optimization and analysis end transmits the flushing trigger value to the operation control end; The operation control end is used to monitor and collect the blockage value and post-filtration turbidity value of the filter in real time according to the flushing trigger value, and calculate the pre-operation coefficient. If the pre-operation coefficient is greater than or equal to the flushing trigger value, a backwash signal is generated and the filter is controlled to perform backwashing action.

2. The filter operation optimization intelligent control system according to claim 1 is characterized in that: The calculation method of the pre-operation coefficient includes: Set the lead time, take the start time of backwashing in the filter tank as the time node, and identify the operating parameters and energy consumption parameters within the lead time, where the lead time refers to the time segment before the backwashing starts in the filter tank; Extract all the information parameters in the backwash period and the operating parameters in the lead time from the stored data. First, take the operating parameters in the lead time and use the formula Get the pre-operation coefficient Qxi; Where i represents different backwashing processes, and i∈[1,I], I represents that there are I backwashing processes in the stored data, ZSi represents the blocking value in the lead time of backwashing process i, LBi represents the post-filtration turbidity value in the lead time of backwashing process i, and All are proportional coefficients.

3. The filter operation optimization intelligent control system according to claim 1 is characterized in that: The calculation method of turbidity change function includes: Set the unit interval time, and mark the turbidity of the filtered water as HZj according to the unit interval time, where j represents the turbidity of the filtered water collected at different unit interval times; Taking time as the independent variable and filtered water turbidity as the dependent variable, the filtered water turbidity of all backwashing periods was taken as the experimental group, and the artificial intelligence algorithm was used for linear fitting to obtain the turbidity change function F1 of the filtered water turbidity: , where b1 and b2 are constant coefficients, and b1>0, is the exponential factor, CS is the turbidity of the initial filtered water, and Tj is the change time of the turbidity of the filtered water.

4. The filter operation optimization intelligent control system according to claim 3 is characterized in that: The calculation method of stable turbidity value includes: Perform a secondary derivative operation on the turbidity change function F1, and mark the result after the derivative operation as the trend change value f(Tj), where: , represents the second derivative; When the trend change value f(Tj)>0, the interval corresponding to the flushing period Tj is marked as the trend interval, and then the first derivative of the turbidity change function F1 is taken, that is, ,in, represents the first derivative; Take the absolute value of the first derivative of the turbidity change function F1, and within the trend interval, take the minimum absolute value, and obtain the flushing period Tj corresponding to the minimum absolute value, and then substitute this flushing period Tj into the original turbidity change function F1, and mark the obtained filtered water turbidity as the stable turbidity value Wz.

5. The filter operation optimization intelligent control system according to claim 2 is characterized in that: The energy consumption function is determined by: A backwashing process is randomly selected as the target operation process, the starting period of the lead time in the target flushing process is taken as the starting time point, the time when the turbidity of the filtered water reaches a stable turbidity value after the backwashing is completed is taken as the ending time point, and then the starting time point and the ending time point are taken as a cycle time, the operation energy consumption in this cycle time is collected and marked as the cycle operation energy consumption Gzi; Obtain the pre-filtered water volume FWi and the total filtered water volume TWi during each backwashing cycle, and record the backwashing energy consumption during each backwashing cycle and mark it as RBi; The pre-operation coefficient Qxi, pre-filtered water volume FWi, total filtered water volume TWi, backwashing energy consumption RBi and periodic operation energy consumption Gzi in each backwashing process are taken as a data group, and the data of all backwashing processes in the stored data are integrated to obtain a total of I data groups, and then I data groups are used as test groups, and artificial intelligence is used for simulation calculation to obtain the energy consumption function: , where b3 is a constant coefficient, is the index, G0 is the benchmark energy consumption, and f (FWi, TWi) is the water volume filtering function.

6. The filter operation optimization intelligent control system according to claim 5 is characterized in that: The flushing trigger value is determined by: A pre-operation coefficient is randomly selected as the target operation value, and a first operation period is set at the same time. The filtration time between the stable turbidity value and the target operation value is identified in the stored data, and the average of the filtration time is taken and marked as the target operation period; Divide the first operation period by the target operation cycle to obtain the period flushing coefficient Xc; Using Formula E: Get the comprehensive cycle energy consumption ZN, where is the correction factor; The pre-operation coefficient is used as the horizontal coordinate, and the backwashing energy consumption is used as the vertical coordinate, respectively, to set a two-dimensional coordinate system, and the formula E is displayed as a linear image on the two-dimensional coordinate system to obtain an energy consumption curve; The lowest point of the backwash energy consumption ZN in the energy consumption curve is identified, and the pre-operation coefficient corresponding to the lowest point of the backwash energy consumption ZN is obtained, and used as the flushing trigger value of the filter tank.

7. The filter operation optimization intelligent control system according to claim 6 is characterized in that: The pre-operation coefficient in the time period flushing coefficient Xc and the pre-operation coefficient in the energy consumption function are kept consistent in the process of calculating the comprehensive period energy consumption ZN.

8. The filter operation optimization intelligent control system according to claim 1 is characterized in that: The operating parameters of the filter tank are collected by the parameter collection end and transmitted to the data storage end for storage.

9. A filter operation optimization intelligent control method, characterized in that: The control method specifically comprises the following steps: Step 1: Collect the operating parameters of the filter tank, and extract the blockage value and post-filtration turbidity value in each lead time from the stored data in the Scada system of the water plant, and calculate the lead operation coefficient in each lead time based on the blockage value and post-filtration turbidity value; Step 2: Set the unit interval time, collect the turbidity of the filtered water corresponding to each unit interval time in the backwash period, obtain the turbidity of the filtered water in all backwash periods as the test group, and calculate the turbidity change function; Step 3: Perform derivative calculation on the turbidity change function, first determine the trend interval of the flushing period, and then determine the stable turbidity value based on the trend interval; Step 4: Based on the time process of the turbidity value after filtration in the filter tank reaching a stable turbidity value, set the cycle time, collect the cycle operation energy consumption within the cycle time, take the pre-operation coefficient and the cycle operation energy consumption as the data group, extract all the data groups in the stored data and perform simulation calculations to obtain the energy consumption function; Step 5: Based on the filtration time between the stable turbidity value and the pre-operation coefficient, determine the period flushing coefficient, combine the period flushing coefficient with the energy consumption function, and determine the comprehensive period energy consumption; Step 6: According to the energy consumption curve of the comprehensive cycle energy consumption, identify the pre-operation coefficient corresponding to the lowest point in the energy consumption curve and use it as the flushing trigger value of the filter. After that, the filter will collect and process the operating parameters of the filter in real time according to the flushing trigger value, and then control the filter to perform backwashing.

Images