A sewage treatment plant drainage scheduling method and system based on a fluid dynamics model

Abstract

The application provides a sewage treatment plant drainage scheduling method and system based on a fluid dynamics model, relates to the technical field of sewage treatment and drainage scheduling, and divides the influent load grade and builds a matching model of the influent load grade and drainage flow and frequency according to the influent water quality and water quantity coupling historical data; the interception amount and pipeline flow data are collected at the influent grid, the interception influence coefficient reflecting the influence of the grid interception on the pipe network drainage is obtained through correlation processing; the fluid dynamics model is used to calculate the allowable drainage range of the pipe network, the optimal drainage parameter in the allowable range is calculated by combining the current load matching model and the interception influence coefficient, and the hydraulic imbalance section is identified; finally, the valve opening of the imbalance section is adjusted with the optimal parameter as the target, so that the actual drainage of the pipe network approaches the target parameter, the overall hydraulic balance is maintained, and the drainage scheduling accuracy and pipe network stability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage treatment and drainage scheduling, and particularly relates to a sewage treatment plant drainage scheduling method and system based on a fluid dynamics model. BACKGROUND

[0002] In the process of drainage scheduling in a sewage treatment plant, multiple factors such as inflow load, biochemical reaction tank state, secondary sedimentation tank settling efficiency and effluent water quality need to be dynamically coordinated. Traditional empirical scheduling is difficult to deal with sudden changes in hydraulic load, fluctuations in pollutant concentration or extreme weather events, and therefore needs to simulate the hydraulic distribution, pollutant migration and biochemical reaction process in the plant through a precise fluid dynamics model, so as to realize collaborative optimization control of execution units such as drainage pump stations, gates, reflux pumps, and finally to ensure stable and standard effluent, minimize energy consumption and improve system anti-interference ability.

[0003] A current targeted solution is an intelligent scheduling system based on coupling of a computational fluid dynamics model (CFD) and sensor data. The system collects data through pH, DO, SS and flow sensors deployed at key nodes (such as the inlet, aeration tank and secondary sedimentation tank), drives the CFD model to dynamically simulate the flow state, pollutant diffusion and sedimentation efficiency of the whole plant, and generates scheduling instructions in combination with a model predictive control algorithm; for example, by simulating the sludge concentration field distribution in the secondary sedimentation tank through CFD, dynamically adjusting the sludge reflux ratio and sludge discharge frequency to optimize the solid-liquid separation effect and reduce energy consumption.

[0004] The core defect of this solution lies in the contradiction between the high computational complexity of the CFD model and the real-time requirement. CFD solving consumes a large amount of computing resources, resulting in delayed system response and making it difficult to realize minute-level scheduling decisions; at the same time, the model relies on accurate boundary conditions and physical parameters, and the composition of actual sewage is complex and variable, which easily leads to deviation of the simulation results from the actual working conditions. In addition, the CFD model is highly sensitive to grid quality and turbulence model selection, and may be numerically unstable when the working conditions fluctuate sharply, requiring frequent manual calibration, which weakens the autonomy of the system. SUMMARY

[0005] The present application aims to provide a sewage treatment plant drainage scheduling method and system based on a fluid dynamics model, to solve the problems of delayed scheduling response due to model calculation complexity and reliance on manual intervention due to poor model adaptability in the prior art.

[0006] To solve the above technical problems, in a first aspect, the present application provides a sewage treatment plant drainage scheduling method based on a fluid dynamics model, comprising:

[0007] Based on the water quality and water quantity coupling historical monitoring data of the influent inlet of the sewage treatment plant, different influent load grades are divided, and a matching relationship model between the influent load grade and the drainage flow and the drainage frequency is established;

[0008] The interception amount of the influent grid and the flow data of the drainage pipeline are synchronously collected at the influent grid of the sewage treatment plant, and the interception influence coefficient reflecting the influence degree of the interception state of the influent grid on the drainage capacity of the pipe network is calculated by correlating the interception amount and the flow data;

[0009] The allowed drainage range of the drainage pipe network is calculated by using a fluid dynamics model, the matching relationship model corresponding to the current influent load grade and the interception influence coefficient are taken as inputs, and the optimal drainage flow and the optimal drainage frequency matched with the current influent load grade and within the allowed drainage range are calculated by taking the allowed drainage range as a constraint;

[0010] Based on the flow data, in combination with the hydraulic loss distribution of each section of the pipe network simulated by the fluid dynamics model, the hydraulic imbalance section with abnormal flow distribution in the pipe network is identified;

[0011] The optimal drainage flow and the optimal drainage frequency are taken as target control parameters, the opening of the valve in the hydraulic imbalance section is automatically adjusted to adjust the flow distribution of each pipe section, so that the actual drainage state of the pipe network tends to approach the target control parameters and maintains overall hydraulic balance.

[0012] Optionally, the interception amount of the influent grid and the flow data of the drainage pipeline are paired in time sequence to form a plurality of data pairs, the interception amount and the flow data in the data pairs are calculated to obtain an interception amount change sequence and a flow change sequence, the change amounts of corresponding positions in the interception amount change sequence and the flow change sequence are correlated and calculated, and the ratio of the interception amount change to the flow amount change is taken as a preliminary influence coefficient of each time point.

[0013] The interception amount of the influent grid and the flow data of the drainage pipeline are paired in time sequence to form a plurality of data pairs;

[0014] The interception amount and the flow data in the data pairs are calculated to obtain an interception amount change sequence and a flow change sequence;

[0015] The change amounts of corresponding positions in the interception amount change sequence and the flow change sequence are correlated and calculated, and the ratio of the interception amount change to the flow amount change is taken as a preliminary influence coefficient of each time point.

[0016] The preliminary influence coefficients of all time points are statistically analyzed, and the average value is obtained after removing the abnormal values, and the average value is taken as the interception influence coefficient reflecting the influence degree of the interception state of the influent grid on the drainage capacity of the pipe network.

[0017] Optionally, the allowed drainage range of the drainage pipe network is calculated by using the fluid dynamics model, the matching relationship model corresponding to the current incoming water load level and the interception influence coefficient are taken as inputs, and the optimal drainage flow and the optimal drainage frequency that match the current incoming water load level and are within the allowed drainage range are calculated by taking the allowed drainage range as a constraint, including:

[0018] The water flow state of the drainage pipe network is simulated by using the fluid dynamics model, and the maximum and minimum allowed drainage flow of the drainage pipe network are determined to define the allowed drainage range;

[0019] The recommended drainage flow and the recommended drainage frequency corresponding to the current incoming water load level are obtained, and the interception influence coefficient is taken as an adjustment factor to calculate the adjusted drainage flow and the drainage frequency;

[0020] Within the allowed drainage range, an optimization function with the adjusted drainage flow as a variable is established, and the optimal drainage flow is obtained by solving the optimization function;

[0021] According to the proportional relationship between the optimal drainage flow and the adjusted drainage flow, the optimal drainage frequency is calculated.

[0022] Optionally, based on the flow data, the hydraulic imbalance section of the pipe network with abnormal flow distribution is identified by combining the hydraulic loss distribution of each section of the pipe network simulated by the fluid dynamics model, including:

[0023] Flow data of a plurality of monitoring points in the drainage pipe network are collected to form a pipe network flow data set;

[0024] The hydraulic loss values of each section of the pipe network under different flow conditions are calculated by using the fluid dynamics model to establish a pipe network hydraulic loss distribution model;

[0025] Based on the hydraulic loss values of each section of the pipe network in the pipe network hydraulic loss distribution model, the expected flow values of each section under the theoretical equilibrium state are inversely calculated in combination with the pipe network topology structure and the fluid continuity principle;

[0026] The actual flow monitoring values of each section are extracted from the pipe network flow data set, and the relative deviation rates between the actual flow monitoring values and the corresponding theoretical expected flow values of each section are calculated;

[0027] The relative deviation rates are compared and analyzed with a preset deviation threshold, and according to the comparison and analysis result, all sections with a relative deviation rate exceeding the deviation threshold are marked and determined as the hydraulic imbalance section.

[0028] Optionally, the optimal drainage flow rate and the optimal drainage frequency are taken as target control parameters, and the flow distribution of each pipe section is adjusted by automatically adjusting the opening degree of the valve in the hydraulic imbalance section, so that the actual drainage state of the pipe network tends to the target control parameters and maintains overall hydraulic balance, comprising:

[0029] According to the spatial distribution of the hydraulic imbalance section, the control valve and its specific position that need to be adjusted in the hydraulic imbalance section are determined;

[0030] For the control valve, the opening degree change amount of the control valve that needs to be adjusted is calculated according to the difference between the target control parameter and the current actual drainage state, and the opening degree of the corresponding control valve is adjusted by the automatic control system according to the opening degree change amount, thereby affecting the actual drainage state;

[0031] The flow data of each monitoring point of the adjusted pipe network is collected, and the matching degree of the current actual drainage state and the target control parameter is calculated;

[0032] When the matching degree does not meet the predetermined requirement, the opening degree change amount of the valve is recalculated and iteratively adjusted until the actual drainage state stably tends to the target control parameter and maintains overall hydraulic balance.

[0033] Optionally, based on the historical monitoring data of water quality and water quantity at the inlet of the sewage treatment plant, different inlet load grades are divided, and a matching relationship model between the inlet load grade and the drainage flow rate and the drainage frequency is established, comprising:

[0034] The historical water quality monitoring data and the historical water quantity monitoring data of the inlet are obtained, and the historical water quality parameter value and the historical water quantity parameter value at the same time point are multiplied to calculate the inlet load value at the time point;

[0035] The inlet load value is divided into multiple grades, and each grade corresponds to a corresponding load range;

[0036] For the inlet load grade, the corresponding drainage flow rate value and the drainage frequency value are extracted from the historical water quantity monitoring data, and the statistical characteristic value is calculated by the drainage flow rate value and the drainage frequency value;

[0037] Based on the statistical characteristic value, a mapping relationship between the inlet load grade and the drainage flow rate and the drainage frequency is established, and the mapping relationship is represented in the form of a lookup table.

[0038] In a second aspect, the application provides a sewage treatment plant drainage scheduling system based on a fluid dynamics model, comprising:

[0039] The establishing module is configured to divide different influent load grades based on the water quality and water quantity coupled historical monitoring data of the influent inlet of the sewage treatment plant, and establish a matching relationship model between the influent load grades and the drainage flow and the drainage frequency.

[0040] The calculating module is configured to synchronously collect the interception amount of the influent grid and the flow data of the drainage pipeline at the influent grid of the sewage treatment plant, and calculate an interception influence coefficient reflecting the influence degree of the interception state of the influent grid on the drainage capacity of the pipe network by associating the interception amount with the flow data.

[0041] The second calculating module is configured to calculate an allowable drainage range of the drainage pipe network by using a fluid dynamics model, take the matching relationship model corresponding to the current influent load grade and the interception influence coefficient as inputs, and calculate optimal drainage flow and optimal drainage frequency that match the current influent load grade and are within the allowable drainage range by taking the allowable drainage range as a constraint.

[0042] The identifying module is configured to identify a hydraulic imbalance section with abnormal flow distribution in the pipe network based on the flow data and in combination with the hydraulic loss distribution of each section of the pipe network simulated by the fluid dynamics model.

[0043] The adjusting module is configured to take the optimal drainage flow and the optimal drainage frequency as target control parameters, adjust the flow distribution of each section of the pipe network by automatically adjusting the opening degree of the valve in the hydraulic imbalance section, and make the actual drainage state of the pipe network tend to the target control parameters and maintain overall hydraulic balance.

[0044] In a third aspect, the present application provides an electronic device, comprising:

[0045] A memory is configured to store a computer program.

[0046] A processor is configured to implement the steps of the sewage treatment plant drainage scheduling method based on the fluid dynamics model according to the first aspect when the computer program is executed.

[0047] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program can implement the steps of the sewage treatment plant drainage scheduling method based on the fluid dynamics model according to the first aspect when the computer program is executed by a processor.

[0048] The sewage treatment plant drainage scheduling method based on a fluid dynamics model provided in the application can overcome the hysteresis of pure reaction by establishing a matching relationship model of influent load and drainage strategy based on historical data, and can provide a scientific and forward-looking benchmark strategy for drainage scheduling; can quantify the dynamic influence of physical blockage on drainage capacity by synchronously collecting the grid interception amount and pipeline flow data and calculating the interception influence coefficient, and can provide a key disturbance parameter for optimized scheduling; can realize the economic optimization of drainage flow and frequency on the premise of ensuring the safety of the pipe network by calculating the safe drainage range using the fluid dynamics model and solving the optimal solution; can accurately locate the pipe sections with abnormal flow distribution in the pipe network by identifying the hydraulic imbalance sections through data and model simulation, and realize the deepening from macroscopic scheduling to microscopic perception; can not only achieve the total drainage target, but also actively eliminate the hydraulic imbalance of the pipe network by automatically adjusting the valve with the optimal parameters as the target, and realize the overall balance and stable operation of the system.

[0049] Further, the accurate interception influence coefficient is dynamically calculated by time sequence correlation and statistical analysis of the grid interception amount and flow data; the safe boundary defined by the fluid dynamics model, the influent load strategy and the influence factor are dynamically coupled for constraint optimization solution; the abnormal pipe section is accurately diagnosed by comparing the theoretical value of the model with the measured value. The corresponding technical effects are summarized as follows: the accurate perception of the influent grid state and the influence quantification are realized, the fast convergence and solution of the optimized scheduling algorithm within the absolute safe boundary are ensured, and the accurate diagnosis capability for the internal implicit faults (such as blockage and leakage) of the pipe network is improved, thereby comprehensively enhancing the adaptability, safety and reliability of the scheduling system. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 A flowchart of a sewage treatment plant drainage scheduling method based on a fluid dynamics model provided by an embodiment of the present application;

[0052] Figure 2 A specific implementation flowchart of a sewage treatment plant drainage scheduling method based on a fluid dynamics model provided by an embodiment of the present application;

[0053] Figure 3 A specific implementation flowchart of a sewage treatment plant drainage scheduling method based on a fluid dynamics model provided by an embodiment of the present application;

[0054] Figure 4 A structural schematic diagram of a sewage treatment plant drainage scheduling system based on a fluid dynamics model is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0055] In the drainage scheduling process of a sewage treatment plant, although the existing intelligent scheduling method based on a high-precision computational fluid dynamics model, such as a CFD model, improves the normativity of operation to a certain extent, there are still significant bottlenecks: first, the CFD model has high computational complexity and takes a long time to solve, which cannot meet the minute-level scheduling requirement, resulting in a lag in system response and failing to effectively respond to rapid fluctuations in influent load; second, the model relies on fixed parameters and ideal boundary conditions, and has poor adaptability in the actual complex and variable water quality scenarios, and the simulation results are prone to deviate from the actual working conditions, which needs frequent manual calibration, seriously restricting the autonomy and reliability of the system.

[0056] To solve the above problems, the present application provides a sewage treatment plant drainage scheduling method based on a fluid dynamics model. The method establishes a matching relationship model between influent load levels and drainage strategies to provide preset optimal scheduling benchmarks for different working conditions; further, the correlation analysis of the grid interception amount and the pipe flow is introduced to dynamically calculate the interception influence coefficient representing the actual physical blockage degree; finally, the above factors are embedded in a lightweight fluid dynamics model, and the optimal drainage flow and frequency are solved with the hydraulic safety range of the pipe network as a constraint, and the valve is automatically adjusted to eliminate the hydraulic imbalance of the pipe network. Through the technical path of "classification presetting, dynamic sensing, coupling optimization, and closed-loop control", the present method effectively overcomes the defects of redundant calculation and poor adaptability of the traditional CFD model, not only significantly improves the response speed through model lightweight and strategy presetting, but also enhances the self-adaptive ability of the system to complex working conditions by means of dynamic correction of the optimization process, thereby realizing safe, efficient, and self-adaptive drainage scheduling.

[0057] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] The core of the present application is to provide a sewage treatment plant drainage scheduling method based on a fluid dynamics model, and a flowchart of a specific embodiment thereof is shown in Figure 1 The method comprises:

[0059] S101, based on the water quality and water quantity coupling historical monitoring data of the influent inlet of the sewage treatment plant, different influent load grades are divided, and a matching relationship model between the influent load grade and the drainage flow and drainage frequency is established;

[0060] Optionally, S101 can specifically include the following steps:

[0061] S1011, historical water quality monitoring data and historical water quantity monitoring data of the influent inlet are obtained, and historical water quality parameter values and historical water quantity parameter values at the same time point are multiplied to calculate influent load values at the time point;

[0062] S1012, the influent load values are divided into multiple grades, and each grade corresponds to a corresponding load range;

[0063] S1013, for the influent load grade, corresponding drainage flow values and drainage frequency values are extracted from the historical water quantity monitoring data, and statistical characteristic values thereof are calculated through the drainage flow values and drainage frequency values;

[0064] S1014, based on the statistical characteristic values, a mapping relationship between the influent load grade and the drainage flow and the drainage frequency is established, wherein the mapping relationship is in the form of a lookup table.

[0065] In the above scheme, the historical water quality monitoring data refers to data obtained by monitoring the concentrations of various pollutants such as chemical oxygen demand COD, ammonia nitrogen NH3-N, and total suspended solids TSS contained in the influent of the sewage treatment plant in the past period of time; the historical water quantity monitoring data refers to data recorded by monitoring the instantaneous flow and cumulative flow of the influent in the same period; the influent load value refers to data representing the total amount of pollutants entering the sewage treatment plant per unit time; the drainage flow value refers to the volume of liquid passing through the drainage pipeline per unit time; the drainage frequency value refers to the number of times the drainage pump starts and stops per unit time; the influent load grade refers to a classification label obtained by dividing the historical influent load value according to certain rules; the matching relationship model refers to a data model stored in the form of a lookup table, which records the recommended drainage flow and recommended drainage frequency values corresponding to different influent load grades, realizing the corresponding association between the load grade and the drainage parameters.

[0066] In the embodiments of the present application, first, the historical water quality monitoring data and the historical water quantity monitoring data of the influent inlet are acquired from the monitoring system of the sewage treatment plant through S1011, the water quality parameters and the water quantity parameters at the same time are matched through the time stamp, the water quality parameter unit is converted to kg / m3 by unit conversion, and the influent load value at the time is obtained by the product operation between the water quality parameters and the water quantity parameters; for example, the COD concentration is 300 mg / L (converted to 0.3 kg / m3) at a certain time, the influent flow is 1000 m3 / h, and the influent load value = 0.3 kg / m3 x 1000 m3 / h = 300 kg / h.

[0067] Secondly, all the historical influent load values are collected through S1012, the influent load values are divided into intervals by statistical analysis technology, and continuous and non-overlapping influent load grades are formed. For example, the influent load values are divided into low load (<200 kg / h), medium load (200-500 kg / h) and high load (>500 kg / h) by using the percentile method.

[0068] Then, based on the influent load grades, the drainage flow value and the drainage frequency value of the corresponding period of the grade are extracted from the historical water quantity monitoring data by data screening technology through S1013, and the statistical characteristic values of the drainage flow value and the drainage frequency value are obtained by statistical calculation technology; for example, for the 50 period data of the “medium load” grade, the arithmetic average method is used to calculate the drainage flow average value = (the total of the flow of each period) / 50 = 800 m3 / h, and the drainage frequency average value = (the total of the frequency of each period) / 50 = 4 times / h.

[0069] Finally, data association technology is used to establish a mapping relationship between each influent load grade and the corresponding drainage flow statistical characteristic value and drainage frequency statistical characteristic value through S1014, and the mapping relationship is presented in the form of a lookup table by tabular storage technology.

[0070] In practical application, a sewage treatment institution optimizes drainage scheduling. Historical water quality monitoring data and historical water quantity monitoring data of the inlet for nearly six months are called from a monitoring system, data at the same time is matched according to a time stamp, COD concentration is converted from mg / L to kg / m³ (for example, 250 mg / L is converted to 0.25 kg / m³), after which the inlet load value is obtained by multiplying the corresponding inlet flow rate, that is, 0.25 kg / m³ x 800 m³ / h = 200 kg / h; then, all inlet load values are divided into three levels, that is, low load (<180 kg / h), medium load (180-450 kg / h) and high load (>450 kg / h), by using a K-means clustering algorithm; drainage data of the corresponding time period of the three levels is screened from the historical water quantity monitoring data, and characteristic values are calculated and counted, that is, the average drainage flow rate of the low load level is 500 m³ / h, the average drainage frequency is 2 times / hour, the average drainage flow rate of the medium load level is 750 m³ / h, the average drainage frequency is 3 times / hour, the average drainage flow rate of the high load level is 1000 m³ / h, and the average drainage frequency is 5 times / hour; finally, a mapping relationship between the three load levels and the corresponding drainage parameters is established, a lookup table is formed and stored in a scheduling system, and is used for subsequent scheduling.

[0071] The overall scheme of S101 integrates inlet water quality and water quantity data to calculate a comprehensive inlet load index, divides the inlet load index into multiple levels, analyzes the statistical law of drainage operation under different load levels, and finally establishes a mapping relationship between the load level and the drainage parameter. The whole method realizes efficient conversion from raw data to rule knowledge, forms a drainage operation guidance tool based on data and capable of quickly responding to changes in inlet conditions, and significantly improves the systematicness and forwardness of drainage management.

[0072] S102, simultaneously collecting the interception amount of the inlet grille and the flow data of the drainage pipeline at the inlet grille of the sewage treatment plant, and calculating an interception influence coefficient reflecting the influence degree of the interception state of the inlet grille on the drainage capacity of the pipe network by associating the interception amount with the flow data;

[0073] Optionally, S102 can specifically include the following steps:

[0074] S1021, pairing the interception amount of the inlet grille and the flow data of the drainage pipeline according to time sequence to form a plurality of data pairs;

[0075] S1022, calculating the change amount of the interception amount and the flow data in the data pairs between adjacent time points respectively to obtain an interception amount change sequence and a flow change sequence;

[0076] S1023, associate the change amount at the corresponding position in the interception amount change sequence and the flow change sequence, take the ratio of the interception amount change amount and the flow change amount as the preliminary influence coefficient of each time point;

[0077] S1024, statistically analyze the preliminary influence coefficients of all time points, remove outliers, and take the average value as the interception influence coefficient reflecting the influence degree of the interception state of the inlet grille on the drainage capacity of the pipe network.

[0078] In the above scheme, the interception amount of the inlet grille refers to the mass of suspended solids, impurities and other solid substances intercepted by the inlet grille per unit time; the flow data of the drainage pipeline refers to the volume of liquid passing through the drainage pipeline per unit time; the interception influence coefficient is a parameter obtained by correlating the interception amount and the flow data. The data pair refers to a combination formed by pairing the interception amount and the flow data at the same time point, ensuring the time synchronization of the two types of data; the interception amount change sequence refers to a continuous data set formed by calculating the change amount of the interception amount at adjacent time points; the flow change sequence refers to a continuous data set formed by calculating the change amount of the flow data at adjacent time points; the preliminary influence coefficient refers to a temporary coefficient obtained by calculating the ratio of the interception amount change amount and the flow change amount at the same position; the outlier refers to an extreme value deviating from most of the data in the preliminary influence coefficient, which needs to be removed by statistical method to ensure the accuracy of the result.

[0079] In the embodiment of the application, as shown in Figure 2 S1021, interception amount data and flow data arranged according to time stamps are extracted from the grille monitoring sensor and the pipeline flow sensor of the sewage treatment plant by using time sequence pairing technology, the interception amount and the flow data corresponding to the same time stamp are paired according to the collection time stamps of the two types of data, and a plurality of data pairs are formed; for example, a sewage treatment plant collects data once an hour, the interception amount at 10 o'clock is 5 kg, the flow is 800 m³ / h, the interception amount at 11 o'clock is 6 kg, the flow is 780 m³ / h, the interception amount at 12 o'clock is 7 kg, and the flow is 760 m³ / h, after pairing according to time stamps, three data pairs are formed (10 o'clock, 5 kg, 800 m³ / h), (11 o'clock, 6 kg, 780 m³ / h), (12 o'clock, 7 kg, 760 m³ / h).

[0080] Secondly, the interception amount and flow data in the data pair are respectively processed by using the difference calculation method in S1022, and the adjacent two time points are taken as a group, the value of the latter time point is subtracted from the value of the former time point, the interception amount change and the flow change of each group are obtained, and all the changes are arranged according to the time stamp to form the interception change sequence and the flow change sequence; for example, based on the above data pair, the interception amount change from 10:00 to 11:00 is 6kg-5kg=1kg, and the flow change is 780m³ / h-800m³ / h=-20m³ / h; the interception amount change from 11:00 to 12:00 is 7kg-6kg=1kg, and the flow change is 760m³ / h-780m³ / h=-20m³ / h, thus forming the interception change sequence [1kg, 1kg] and the flow change sequence [-20m³ / h, -20m³ / h].

[0081] Then, the change amounts at the corresponding positions in the interception change sequence and the flow change sequence are associated and calculated by using the ratio calculation method in S1023, and the obtained result is taken as the preliminary influence coefficient of each time point, and the formula is: For example, the preliminary influence coefficient of a sewage treatment plant from 10:00 to 11:00 is , the preliminary influence coefficient from 11:00 to 12:00 is , and the preliminary influence coefficient sequence [-0.05, -0.05] is formed.

[0082] Finally, the mean value of all the preliminary influence coefficients is calculated in S1024 , and the standard deviation is , the values exceeding the range of are determined as abnormal values and deleted, and then the sum of the remaining preliminary influence coefficients is divided by the number of data, and the obtained average value is taken as the interception influence coefficient.

[0083] In practical applications, to quantify the impact of the influent bar screen on the drainage capacity of the pipe network, a wastewater treatment plant first installed a weighing interception sensor at the influent bar screen and an electromagnetic flow sensor in the downstream drainage pipe. After continuously collecting data for three days, the interception and flow data at the same time point were paired using time series pairing technology, forming 72 data pairs (e.g., (Day 1, 8:00 AM, 4.2 kg, 810 m³ / h), (Day 1, 9:00 AM, 4.8 kg, 800 m³ / h), etc.). Then, these data pairs were grouped according to adjacent time points. By subtracting the value from the previous time point from the value at the later time point, 71 changes in interception volume (e.g., 4.8kg - 4.2kg = 0.6kg, interception volume at 10:00 AM on day 1: 5.3kg - 4.8kg = 0.5kg, etc.) and 71 changes in flow rate (e.g., 800m³ / h - 810m³ / h = -10m³ / h, flow rate at 10:00 AM on day 1: 795m³ / h - 800m³ / h = -5m³ / h, etc.) are calculated, forming a corresponding change sequence; then, the preliminary influence coefficient for each interval is calculated according to the positional correspondence (e.g., ... , (etc.), resulting in 71 preliminary impact coefficients; finally, the mean of the preliminary impact coefficients was calculated to be -0.07 kg・h / m³ and the standard deviation was 0.02. Using the 3σ rule, the three extreme values ​​(such as -0.15 and -0.005) that exceeded the range of -0.07±0.06 (i.e. -0.13 to -0.01) were identified as outliers and deleted. The remaining 68 preliminary impact coefficients were summed and divided by 68 to obtain the final interception impact coefficient of -0.068 kg・h / m³, which was stored in the scheduling system for subsequent use.

[0084] The overall scheme of S102 described above effectively eliminates the interference of extreme data caused by accidental factors on the results through statistical analysis and outlier removal, ensuring the stability and reliability of the final interception impact coefficient. By using the mean calculation method to integrate dynamic impact data from multiple time intervals, the final coefficient can reflect the long-term average impact of grid interception on drainage capacity, avoiding the limitations of data from a single time interval. This allows the drainage scheduling strategy to fully adapt to changes in the grid interception status, reduces the deviation in the assessment of pipeline drainage capacity caused by ignoring the impact of the grid, and improves the scientificity and accuracy of the overall scheduling.

[0085] S103. Calculate the allowable drainage range of the drainage network using a fluid dynamics model. Take the matching relationship model corresponding to the current influent load level and the interception influence coefficient as inputs, and use the allowable drainage range as constraints to calculate the optimal drainage flow rate and optimal drainage frequency that match the current influent load level and are within the allowable drainage range.

[0086] Optionally, S103 may specifically include the following steps:

[0087] S1031, simulate water flow state of the sewer network by a fluid dynamics model, determine maximum and minimum allowable drainage flow of the sewer network, and define an allowable drainage range;

[0088] S1032, obtain recommended drainage flow and recommended drainage frequency corresponding to the current inflow load level, and calculate adjusted drainage flow and drainage frequency by taking the interception influence coefficient as an adjustment factor;

[0089] S1033, establish an optimization function with the adjusted drainage flow as a variable within the allowable drainage range, and obtain optimal drainage flow by solving the optimization function;

[0090] S1034, calculate optimal drainage frequency according to a proportional relationship between the optimal drainage flow and the adjusted drainage flow.

[0091] In the above scheme, the fluid dynamics model refers to a mathematical model capable of simulating water flow velocity, pressure, water level and other states in the sewer network; the allowable drainage range refers to a drainage flow interval calculated by the fluid dynamics model and ensuring safe operation of the sewer network; the interception influence coefficient is a parameter quantifying the influence degree of the interception state of the inflow grille on the drainage capacity of the sewer network; the adjustment factor refers to converting the interception influence coefficient into a correction term that can be directly used to adjust the drainage parameters; the optimization function refers to a mathematical function established with the adjusted drainage flow as a variable and with a specific operation target as the core; the optimal drainage flow refers to a drainage flow value most conforming to a preset target obtained by solving the optimization function within the allowable drainage range; and the optimal drainage frequency refers to a drainage frequency value adapted to the optimal drainage flow calculated according to a proportional relationship between the optimal drainage flow and the adjusted drainage flow.

[0092] In the embodiments of the present application, as Figure 3As shown, first, by S1031, the basic data of the drainage pipe network is collected by using the fluid dynamics simulation technology, the basic data is input into the fluid dynamics model, a digital model consistent with the actual pipe network is constructed, different drainage flow conditions are set in the model, the water flow state in the pipe network under each condition is simulated, and the maximum allowable drainage flow and the minimum allowable drainage flow of the pipe network are determined according to the safe operation standard of the pipe network, and the interval between the maximum allowable drainage flow and the minimum allowable drainage flow is defined as the allowable drainage range; for example, the drainage pipe network of a sewage treatment plant, after inputting the parameters such as pipe diameter 300mm, length 500m, pipe material HDPE, etc., through SWMM model simulation, it is found that when the drainage flow exceeds 850m³ / h, the water level of the upstream No.1 drainage well exceeds the pipe top by 0.1m, and when the drainage flow is less than 300m³ / h, the flow velocity of the downstream No.3 pipe section is only 0.4m / s, therefore the maximum allowable drainage flow is determined as 850m³ / h, the minimum allowable drainage flow is determined as 300m³ / h, and the allowable drainage range is defined as 300-850m³ / h.

[0093] Secondly, by S1032, the recommended drainage flow and the recommended drainage frequency corresponding to the current inflow load grade are extracted from the matching relationship model by using the data query technology, and the interception influence coefficient is obtained by using the parameter calling technology, the interception influence coefficient is used as an adjustment factor, and the adjusted drainage flow and drainage frequency are calculated by using the parameter correction algorithm, the calculation formula is , wherein the recommended drainage flow and the recommended drainage frequency come from the matching relationship model, and the interception influence coefficient is used to correct the influence of the grid interception on the drainage parameters; for example, the current inflow load is medium load, the recommended drainage flow extracted from the matching relationship model is 800m³ / h, the recommended drainage frequency is 4 times / hour, and the interception influence coefficient is -0.068, the adjusted drainage flow is calculated by substituting the formula, first calculating the value in the parentheses as 1+(-0.068) / 10=0.9932, then multiplying the recommended drainage flow 800m³ / h by 0.9932 to obtain the adjusted drainage flow as 800×0.9932=794.56m³ / h, and the adjusted drainage frequency is 4×0.9932≈3.97 times / hour.

[0094] Firstly, by S1033, the optimization target is determined according to the operation requirements of the sewage treatment plant (such as reducing energy consumption, improving drainage efficiency, ensuring water quality, etc.), and the core optimization direction is determined; according to the determined optimization target and the characteristic parameters of the drainage equipment (such as energy consumption-flow curve, efficiency-flow curve, etc.), an optimization function is established, if the optimization target is "minimum energy consumption", a function with drainage flow as independent variable and energy consumption as dependent variable is constructed based on the correlation between equipment energy consumption and flow, the formula is: , the Q is the drainage flow (Q ∈ [minimum drainage flow, maximum drainage flow]), the a, b, c are the coefficients fitted according to the device characteristics; a numerical solution algorithm (such as gradient descent method) is selected, the adjusted drainage flow is taken as the initial value of iteration and substituted into the optimization function, and the target function value corresponding to the initial value is calculated; then the iterative calculation is started: the flow value is adjusted step by step according to the algorithm logic, and after each adjustment, it is first judged whether the new flow is within the allowed range, if it is within the range, the new target function value is calculated, compared with the previous value and the flow value that makes the target function better is reserved, if it is out of the range, the adjustment value is discarded and the adjustment direction is re-planned; when the iteration stopping condition is met, the iteration is stopped; finally, the flow value corresponding to the iteration termination is determined as the optimal drainage flow, and it is verified whether the value is within the allowed drainage range, if it is within the range, it is directly output, if it is slightly out of the range due to algorithm error, the value closest to the range is taken as the final result.

[0095] Finally, the optimal drainage frequency is calculated by S1034 using the proportional calculation method according to the proportional relationship between the optimal drainage flow and the adjusted drainage flow, and the calculation formula is .

[0096] In actual application, in the process of drainage scheduling in a certain sewage treatment plant, the SWMM model is used to construct the plant drainage pipe network model, the basic parameters such as pipe diameter, pipe length, number of inspection wells, pipe material and the like are input, the pipe network water level and flow rate under different flow rates are simulated, it is found that when the flow rate exceeds 850 m³ / h, the water level of No. 1 inspection well overflows, when the flow rate is lower than 300 m³ / h, the flow rate of No. 5 pipe section is lower than 0.6 m / s and easy to be silted, and it is determined that the allowed drainage range is 300-850 m³ / h; then the matching relationship model is queried, the current inflow load is medium load, the corresponding recommended drainage flow is 800 m³ / h, the recommended drainage frequency is 4 times / hour, the interception influence coefficient is -0.068, the adjusted parameters are calculated by , the adjusted drainage flow = 800 × (1+(-0.068) / 10) = 794.56 m³ / h, and the adjusted drainage frequency = 4 × 0.9932 ≈ 3.97 times / hour; then the optimization function is established with "minimum drainage pump energy consumption" as the target, the coefficients a = 0.0012, b = 0.45 and c = 95 are determined according to the characteristics of the plant A brand drainage pump, and the optimization function is The gradient descent method of Python is used to solve in the range of 300-850 m3 / h, and 794.56 m3 / h is taken as an initial value. The initial energy consumption is calculated as 0.0012*794.56^2+0.45*794.56+95≈1209.83Kw / h. After 20 iterations of adjustment, when the flow rate is 740 m3 / h, the energy consumption is 0.0012*740^2+0.45*740+95≈1085.12Kw / h, and it is determined that 740 m3 / h is the optimal drainage flow rate. Finally, the optimal drainage frequency is calculated as 3.97*(740 / 794.56)≈3.7 times / hour according to the proportion, and combined with the control habit of the equipment in the plant, it is adjusted to 4.0 times / hour. The optimal parameters 740 m3 / h and 4 times / hour are sent to the drainage control system for execution.

[0097] The overall scheme of S103 above simulates the pipe network water flow state through the fluid dynamics model, determines the allowed drainage range to ensure the safe operation of the pipe network, and avoids problems such as accumulation and overflow caused by drainage parameters exceeding the carrying capacity of the pipe network; the recommended parameters are corrected by the interception influence coefficient, so that the drainage parameters can adapt to the actual influence of the grid interception state, and the adaptability of the parameters to the working conditions is improved; by establishing an optimization function and solving it, the parameter optimization oriented to the preset target is realized, and the safety and economy of the pipe network operation are considered; the entire process organically combines model simulation, actual influence factors and optimization targets, so that the optimal drainage parameters obtained finally not only meet the safety requirements of the pipe network, but also meet the operation efficiency requirements, and provide a reliable basis for the stable and scientific scheduling of the drainage system of the sewage treatment plant.

[0098] S104, based on the flow rate data, in combination with the hydraulic loss distribution of each section of the pipe network simulated by the fluid dynamics model, identifying the hydraulic imbalance section with abnormal flow distribution in the pipe network;

[0099] Optionally, S104 can specifically include the following steps:

[0100] S1041, collecting flow rate data of multiple monitoring points in the drainage pipe network to form a pipe network flow rate data set;

[0101] S1042, calculating the hydraulic loss value of each section of the pipe network under different flow rate conditions through the fluid dynamics model, and establishing a pipe network hydraulic loss distribution model;

[0102] S1043, based on the hydraulic loss value of each section of the pipe network in the pipe network hydraulic loss distribution model, in combination with the pipe network topology structure and the fluid continuity principle, reversely calculating the expected flow rate value of each pipe section under the theoretical balance state;

[0103] S1044, extracting actual flow monitoring values of each pipe section from the pipe network flow data set, and calculating the relative deviation rate between the actual flow monitoring values of each pipe section and the corresponding theoretical expected flow values;

[0104] S1045, comparing and analyzing the relative deviation rate with a preset deviation threshold, and according to the comparison and analysis result, marking all pipe sections with a relative deviation rate exceeding the deviation threshold as water imbalance sections.

[0105] In the above scheme, the flow data refers to the actual drainage flow collected by each monitoring point in the drainage pipe network; the fluid dynamics model refers to a mathematical model capable of simulating water flow in the pipe network and calculating hydraulic loss; the hydraulic loss distribution of each section of the pipe network refers to the distribution of energy loss of each pipe section in the pipe network due to friction, local resistance, etc. calculated by the fluid dynamics model; the water imbalance section refers to a pipe section with a deviation between actual flow and theoretical expected flow exceeding a preset threshold; the pipe network flow data set refers to a structured data set containing monitoring point position, collection time, and flow value; the pipe network topology refers to the connection relationship between pipe sections and nodes in the pipe network; the theoretical expected flow value refers to a flow benchmark value of a pipe section in an ideal balanced state calculated based on hydraulic loss and fluid principles; and the relative deviation rate refers to an index quantifying the deviation degree of actual flow and expected flow.

[0106] In the embodiments of the present application, first, a multi-point flow monitoring technology is used in S1041 to install flow sensors at key nodes of the pipe network, collect flow data at a fixed frequency, and after removing invalid data, arrange the pipe network flow data set containing "monitoring point number-collection time-flow value"; for example, a sewage treatment plant in a certain place installs electromagnetic flow sensors at 5 key monitoring points, continuously collects data for 24 hours, forms a data set of 470 valid data, and each record contains "No. 1-2025-08-28-08:00-780m³ / h" information.

[0107] Secondly, in S1042, hydraulic loss simulation technology is used to input the parameters of each section of the pipe network into the fluid dynamics model, set multiple flow conditions, simulate and calculate the hydraulic loss values of each pipe section under different conditions, and arrange to form a pipe network hydraulic loss distribution model; for example, a sewage treatment plant in A place inputs the parameters of 10 pipe sections into the SWMM model, obtains that the loss of No. 1 pipe section is 0.3m and the loss of No. 2 pipe section is 0.25m under the condition of 300m³ / h, and accordingly establishes the loss distribution model.

[0108] Then, in S1043, reverse calculation technology is used to associate the hydraulic loss distribution model with the pipe network topology, take the actual total inflow as a constraint, and calculate the expected flow value of each pipe section under the theoretical balanced state according to the fluid continuity principle;

[0109] Then, the 24-hour average flow of each pipe section is extracted from the flow data set as the actual flow monitoring value by using the deviation calculation technology in S1044, the expected flow value is called, and the relative deviation rate is calculated by the formula: The relative deviation rate is calculated, where the actual flow monitoring value is the average flow of the pipe section, and the theoretical expected flow value is the calculated reference value. For example, the actual flow of pipe section No. 2 is 420 m³ / h, and the expected flow is 500 m³ / h. The relative deviation rate = |420-500| / 500x100% = 16%.

[0110] Finally, the threshold comparison technology is used in S1045 to compare the deviation rate of each pipe section with the threshold value according to the operation experience of the pipe network. The pipe sections exceeding the threshold value are marked and verified again to determine the hydraulic imbalance section.

[0111] In actual application, in a certain sewage treatment plant, first, electromagnetic flow sensors are installed at 5 key nodes of the pipe network, and 24-hour data are collected at a frequency of 15 minutes / time, and the pipe network flow data set of 477 effective data is arranged. Second, the parameters of 12 pipe sections (main pipe 400 mm / HDPE material, branch pipe 300 mm / concrete material) are input into the EPANET model, and the working conditions of 300 / 500 / 700 m³ / h are set to establish the hydraulic loss distribution model. Then, the average flow of the main pipe is 500 m³ / h as a constraint, and the expected flow of each pipe section is calculated according to the principle of fluid continuity (pipe section No. 1 is 500 m³ / h, branch pipe No. 2 is 243 m³ / h, etc.). Then, the actual average flow of each pipe section is extracted (branch pipe No. 2 is 420 m³ / h, branch pipe No. 3 is 280 m³ / h, etc.), and the deviation rate is calculated (branch pipe No. 2 is 72.8%, branch pipe No. 3 is 8.9%, etc.). Finally, the threshold value is preset to 15%, and after comparison, pipe sections No. 2, No. 6 and No. 10 are marked. After secondary verification that the sensors and the calculation are correct, the 3 sections are determined as the hydraulic imbalance sections.

[0112] The overall scheme of S104 above obtains real flow data through multi-point monitoring to provide a reliable basis for analysis. The hydraulic loss is calculated by combining the fluid model to realize scientific analysis of the hydraulic characteristics of the pipe network. The expected flow is calculated based on the topological structure and the principle of fluid to ensure that the theoretical value is reasonable. The imbalance section is accurately identified by comparing the deviation rate with the threshold value to avoid the subjectivity of experience-based judgment. The final result provides a clear target for pipe network maintenance, reduces blind inspection, and provides a basis for optimizing operation parameters and improving drainage efficiency to alleviate local drainage problems caused by hydraulic imbalance.

[0113] S105, the optimal drainage flow and the optimal drainage frequency are used as target control parameters to automatically adjust the opening of the valve in the hydraulic imbalance section to adjust the flow distribution of each pipe section, so that the actual drainage state of the pipe network tends to the target control parameters and maintains overall hydraulic balance.

[0114] Optionally, S105 can specifically include the following steps:

[0115] S1051, determining the control valve and its specific position that need to be adjusted in the water imbalance section according to the spatial distribution of the water imbalance section;

[0116] S1052, for the control valve, calculating the opening change amount of the control valve that needs to be adjusted according to the difference between the target control parameter and the current actual drainage state, and adjusting the opening of the corresponding control valve through the automatic control system according to the opening change amount, thereby affecting the actual drainage state;

[0117] S1053, collecting the flow data of each monitoring point of the adjusted pipe network, and calculating the matching degree of the current actual drainage state and the target control parameter;

[0118] S1054, when the matching degree does not meet the predetermined requirement, recalculating the opening change amount of the valve and iteratively adjusting until the actual drainage state stably approaches the target control parameter and maintains overall hydraulic balance.

[0119] In the above scheme, the target control parameter is the optimal drainage flow and the optimal drainage frequency; the pipe section with the actual flow deviating from the theoretically expected flow by more than a preset threshold value is the water imbalance section; the control valve refers to the equipment installed on the pipe section of the pipe network and having the opening adjustment function; the opening change amount refers to the percentage of the opening of the control valve that needs to be increased or decreased to make the actual flow of the pipe section approach the target value, which is calculated by a specific algorithm combined with hydraulic characteristics; the automatic control system refers to a system that can receive adjustment instructions and drive the valve actuator to act; the current actual drainage state refers to the actual flow, actual frequency and other data of each monitoring point of the pipe network before and after adjustment, reflecting the operation of the pipe network; the matching degree refers to an index quantifying the degree of agreement between the actual drainage state and the target control parameter; the predetermined requirement refers to the preset matching degree threshold.

[0120] In the embodiment of the application, first, the control valve and its position that need to be adjusted are determined by S1051, the spatial distribution data of the water imbalance section is obtained by using the pipe network GIS system, the influence weight of the pipe section on the flow distribution is analyzed by combining the hydraulic simulation software, the key adjustment pipe section is selected, and then the control valve on the pipe section and its installation coordinates are located; for example, in the pipe network in a certain sewage treatment plant, there is a water imbalance in the section from node D1 to D3, it is clear that the section includes D1-D2 and D2-D3 two pipe sections through the GIS system, and it is finally determined that the adjustment valve is the valve V5 (coordinate P1) on the D1-D2 pipe section and the valve V6 (coordinate P2) on the D2-D3 pipe section through the hydraulic simulation analysis that the flow deviation of the two pipe sections dominates the overall imbalance.

[0121] Then, through S1052, the current flow, drainage frequency, etc. of the pipe section corresponding to the control valve is collected by the pipe network sensor network, and the deviation value is obtained by comparing it with the optimal drainage flow, optimal drainage frequency, etc. target parameters, and then the PID control algorithm is used to calculate the valve opening degree change according to the deviation value, the formula is: opening degree change = proportional coefficient x deviation + integral coefficient x deviation accumulation + differential coefficient x deviation change rate, and finally the automatic control execution system drives the valve to complete the opening degree adjustment.

[0122] Then, through S1053, the adjusted actual flow, frequency data is collected by the intelligent sensor of the pipe network monitoring point, and the parameter deviation rate is calculated according to the deviation rate formula ( ), and the average value is taken as the overall matching degree.

[0123] Finally, through S1054, the overall matching degree is compared with the predetermined qualified standard, if it does not meet the standard, the process of collecting current data, calculating new opening degree change by PID algorithm, and automatically adjusting the valve is repeated until the matching degree meets the standard.

[0124] In practical application, in a certain sewage treatment plant, combined with the pipe network drawing and EPANET model, the second pipe section (A2-A3) is controlled by the middle V2 valve (15m away from A2 node), the sixth pipe section (A6-A7) is controlled by the inlet V6 valve, and the tenth pipe section (A10-A11) is adjusted by the middle V10 valve (12m away from A10 node). The expected flow of the second pipe section is 243m³ / h, the expected flow of the sixth pipe section is 310m³ / h, and the expected flow of the tenth pipe section is 185m³ / h. The actual flow measured by the sensor is 420m³ / h for the second pipe section, 250m³ / h for the sixth pipe section, and 220m³ / h for the tenth pipe section. According to the PID algorithm, the automatic system completes the adjustment; 30 minutes after the adjustment, the average of the three groups of data is 258m³ / h for the second pipe section, 302m³ / h for the sixth pipe section, and 190m³ / h for the tenth pipe section; according to the deviation rate formula, the deviation rate of each pipe section is about 6.2%, 2.6%, and 2.7%, respectively, and the overall matching degree is about 3.8%, which is lower than the threshold of 15%; after continuous monitoring for 2 hours, the matching degree is stable at 1.5%-3.0%, confirming that the pipe network tends to approach the target state, and the balance adjustment is completed.

[0125] The overall scheme of S105 above realizes precise control of the flow distribution of the pipe network by positioning the key control valve and intelligently calculating the opening adjustment amount; through the rapid response and closed-loop adjustment mechanism of the automatic control system, the actual drainage state is stably converged to the target value; finally, through continuous state feedback and iterative optimization, the problem of hydraulic imbalance is effectively eliminated, and the stability, control precision and self-adaptive ability of the drainage system are significantly improved.

[0126] The following is a complete example for steps 101-105. In a certain sewage treatment plant, first, the historical monitoring data of the inlet for the past six months is retrieved, including water quality indicators such as COD, NH3-N, and inlet flow. By matching the same time data through time stamp, the water quality concentration unit is converted to kg / m³, and then multiplied by the flow to obtain the inlet load value (for example: COD concentration 250 mg / L is converted to 0.25 kg / m³, combined with 800 m³ / h flow, the load value is calculated as 200 kg / h); the K-means clustering algorithm is used to divide all load values into three levels: low load, medium load, and high load; then the drainage operation records of the corresponding period of each level are extracted, and the statistical characteristic values are calculated: low load level average drainage flow 500 m³ / h, frequency 2 times / hour; medium load level 750 m³ / h, 3 times / hour; high load level 1000 m³ / h, 5 times / hour; finally, a mapping relationship table of three levels of load and drainage parameters is established and stored in the system.

[0127] Then, the system synchronously collects the data of the inlet grid interception and the drainage pipeline flow. By time series pairing, data pairs are formed, such as continuous three-hour data (8 hours, 4.2 kg, 810 m³ / h), (9 hours, 4.8 kg, 800 m³ / h), (10 hours, 5.3 kg, 795 m³ / h); then the change amount of adjacent period is calculated, 9 hours interception change +0.6 kg, flow change -10 m³ / h; 10 hours interception change +0.5 kg, flow change -5 m³ / h; according to this, the preliminary influence coefficient is calculated (9 hours: 0.6 / (-10)=-0.06 kg·h / m³; 10 hours: 0.5 / (-5)=-0.1 kg·h / m³), after removing the abnormal values deviating from μ±3σ range, the average of the remaining coefficients is obtained as the interception influence coefficient -0.068 kg·h / m³.

[0128] Then, the system simulates the pipe network operation state through the fluid dynamics model, determines the safe drainage range as 300-850 m³ / h according to the pipe diameter, material, and other parameters, the current inlet load is medium load, and the recommended parameters 800 m³ / h, 3 times / hour are extracted from the mapping table; combined with the interception influence coefficient -0.068, the parameters are corrected: adjusted flow = 800×(1-0.068 / 10)=794.56 m³ / h, adjusted frequency = 3×0.9932≈2.98 times / hour; an optimization function is established with "minimum energy consumption" as the target (coefficients a=0.0012, b=0.45, c=95), and the optimal drainage flow is solved as 740 m³ / h within the safe range, and the optimal frequency is calculated as 2.78 times / hour according to the proportion.

[0129] Finally, the system identifies three sections of hydraulic imbalance pipelines, such as No. 2 branch pipe (actual flow rate 420 m³ / h, expected flow rate 243 m³ / h, deviation rate 72.8%), based on the flow rate data of the monitoring points of the pipe network and the simulation results of the fluid model; after positioning the key regulating valve V5 (No. 2 branch pipe inlet), it is calculated that the opening degree needs to be increased by 12% to balance the flow rate; the automatic control system adjusts the valve opening degree, and monitoring finds that the flow rate of No. 2 branch pipe decreases to 260 m³ / h (deviation rate is reduced to 7%) after adjustment, but No. 4 branch pipe appears new deviation, and the system iteratively calculates to adjust V5 and associated valve V7 for the second time, and after three rounds of adjustment, the flow rate deviation rates of all pipe sections are less than 15%, the actual total drainage flow rate is stabilized at 735 m³ / h, and the matching degree with the target 740 m³ / h is > 99%, and the overall pipe network realizes hydraulic balance.

[0130] Figure 4 FIG. 1 is a structural schematic diagram of a specific embodiment of a sewage treatment plant drainage scheduling system based on a fluid dynamics model provided by the embodiments of the present application, referring to Figure 4 The system can include:

[0131] The establishment module 41 is configured to divide different water inlet load grades based on the coupled historical monitoring data of water quality and water volume of the water inlet of the sewage treatment plant, and establish a matching relationship model between the water inlet load grades and drainage flow rate and drainage frequency.

[0132] The calculation module 42 is configured to synchronously collect the interception amount of the water inlet grid and the flow rate data of the drainage pipeline at the water inlet grid of the sewage treatment plant, and calculate an interception influence coefficient reflecting the influence degree of the interception state of the water inlet grid on the drainage capacity of the pipe network by associating the interception amount with the flow rate data.

[0133] The second calculation module 43 is configured to calculate the allowed drainage range of the drainage pipe network by using the fluid dynamics model, take the matching relationship model corresponding to the current water inlet load grade and the interception influence coefficient as inputs, and calculate the optimal drainage flow rate and the optimal drainage frequency that match the current water inlet load grade and are within the allowed drainage range as constraints.

[0134] The identification module 44 is configured to identify the hydraulic imbalance sections with abnormal flow rate distribution in the pipe network based on the flow rate data and in combination with the hydraulic loss distribution of each section of the pipe network simulated by the fluid dynamics model.

[0135] The adjustment module 45 is configured to take the optimal drainage flow rate and the optimal drainage frequency as target control parameters, adjust the flow rate distribution of each pipe section by automatically adjusting the opening degree of the valve in the hydraulic imbalance section, and make the actual drainage state of the pipe network tend to the target control parameters and maintain overall hydraulic balance.

[0136] The fluid dynamics model based sewage treatment plant drainage scheduling system of the embodiments of the present application is used to implement the aforementioned fluid dynamics model based sewage treatment plant drainage scheduling method, and therefore the specific embodiments in the fluid dynamics model based sewage treatment plant drainage scheduling system can be seen from the aforementioned embodiments of the fluid dynamics model based sewage treatment plant drainage scheduling method, and the specific embodiments can be referred to the description of the corresponding embodiments of each part, which will not be repeated here.

[0137] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the aforementioned fluid dynamics model based sewage treatment plant drainage scheduling methods.

[0138] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of any of the aforementioned fluid dynamics model based sewage treatment plant drainage scheduling methods.

[0139] In an exemplary embodiment, the aforementioned computer readable storage medium can include, but is not limited to, a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0140] The embodiments of the present application also provide a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps in any of the aforementioned fluid dynamics model based sewage treatment plant drainage scheduling method embodiments.

[0141] The skilled person can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0142] The above describes in detail a sewage treatment plant drainage scheduling method and system based on a fluid dynamics model provided by the present application. The principles and implementation modes of the present application are described by applying specific examples, and the above description of the examples is only used to help understand the method of the present application and its core idea. It should be pointed out that, for those skilled in the art, some improvements and modifications can be made to the present application without departing from the principles of the present application, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A wastewater treatment plant drainage scheduling method based on a fluid dynamics model, characterized in that, include: Based on historical monitoring data of water quality and quantity coupled at the inlet of the sewage treatment plant, different inlet load levels are classified, and a matching relationship model between the inlet load level and the drainage flow rate and drainage frequency is established. Simultaneously collect the interception volume of the inlet screen and the flow rate of the drainage pipe at the inlet screen of the sewage treatment plant. By correlating the interception volume and the flow rate data, calculate the interception influence coefficient, which reflects the degree of influence of the inlet screen interception status on the drainage capacity of the pipe network. The allowable drainage range of the drainage network is calculated using a fluid dynamics model. The matching relationship model corresponding to the current inflow load level and the interception influence coefficient are used as inputs. With the allowable drainage range as a constraint, the optimal drainage flow rate and the optimal drainage frequency that match the current inflow load level and are within the allowable drainage range are calculated. Based on the aforementioned flow data, and combined with the hydraulic loss distribution of each section of the pipeline network obtained by the fluid dynamics model simulation, hydraulic imbalance sections in the pipeline network with abnormal flow distribution are identified. Using the optimal drainage flow rate and the optimal drainage frequency as target control parameters, the flow distribution of each pipe section is adjusted by automatically regulating the opening of valves in the hydraulically unbalanced section, so that the actual drainage state of the pipe network approaches the target control parameters and maintains the overall hydraulic balance.

2. The method according to claim 1, characterized in that, Simultaneously, data on the interception volume of the influent screen and the flow rate of the drainage pipe are collected at the influent screen of the wastewater treatment plant. By correlating the interception volume and the flow rate data, an interception influence coefficient reflecting the degree of influence of the influent screen's interception status on the drainage capacity of the pipe network is calculated, including: The interception volume of the inlet grille and the flow rate data of the drainage pipe are paired according to the time series to form multiple data pairs; The changes in the interception amount and traffic data in the data pair between adjacent time points are calculated to obtain the interception amount change sequence and the traffic change sequence; The changes at corresponding positions in the interception change sequence and the traffic change sequence are correlated and calculated, and the ratio of the interception change to the traffic change is taken as the preliminary influence coefficient for each time point. Statistical analysis was performed on the preliminary impact coefficients at all time points. After removing outliers, the average value was calculated and used as the interception impact coefficient, which reflects the degree of influence of the inlet grille interception status on the drainage capacity of the pipe network.

3. The method according to claim 1, characterized in that, The allowable drainage range of the drainage network is calculated using a fluid dynamics model. Taking the matching relationship model corresponding to the current influent load level and the interception influence coefficient as input, and using the allowable drainage range as a constraint, the optimal drainage flow rate and optimal drainage frequency that match the current influent load level and are within the allowable drainage range are calculated, including: The flow state of the drainage network is simulated by a fluid dynamics model to determine the maximum and minimum allowable drainage flow rate of the drainage network and define the allowable drainage range. Obtain the recommended drainage flow rate and recommended drainage frequency corresponding to the current influent load level, and use the interception influence coefficient as an adjustment factor to calculate the adjusted drainage flow rate and drainage frequency; Within the allowable drainage range, an optimization function is established with the adjusted drainage flow rate as the variable, and the optimal drainage flow rate is obtained by solving the optimization function; The optimal drainage frequency is calculated based on the ratio between the optimal drainage flow rate and the adjusted drainage flow rate.

4. The method according to claim 1, characterized in that, Based on the aforementioned flow data, and combined with the hydraulic loss distribution of each section of the pipeline network obtained from the fluid dynamics model simulation, hydraulically unbalanced sections in the pipeline network with abnormal flow distribution are identified, including: Collect flow data from multiple monitoring points in the drainage pipe network to form a pipe network flow dataset; The hydraulic loss values ​​of each section of the pipeline network under different flow conditions are calculated by using a fluid dynamics model, and a hydraulic loss distribution model of the pipeline network is established. Based on the hydraulic loss values ​​of each section of the pipeline network in the aforementioned pipeline network hydraulic loss distribution model, and combined with the pipeline network topology and the principle of fluid continuity, the expected flow rate of each section under the theoretical equilibrium state is calculated in reverse. Extract the actual flow monitoring values ​​of each pipe segment from the pipeline flow dataset, and calculate the relative deviation rate between the actual flow monitoring values ​​of each pipe segment and the corresponding theoretical expected flow values; The relative deviation rate is compared and analyzed with a preset deviation threshold. Based on the comparison and analysis results, all pipe sections with relative deviation rates exceeding the deviation threshold are marked, and the pipe sections are identified as hydraulically unbalanced sections.

5. The method according to claim 4, characterized in that, The process of calculating the hydraulic losses of different sections of the pipeline network under different flow conditions using a fluid dynamics model and establishing a hydraulic loss distribution model for the pipeline network includes: Identify all pipe segments in the drainage network that need to be calculated, and assign a unique identifier to each pipe segment; Multiple different flow rate conditions can be set, and these flow rate conditions cover a range from minimum to maximum flow rate. Based on the pipe diameter, pipe length, and pipe inner wall roughness parameters of the pipe section, calculate the hydraulic loss value of the pipe section under the flow rate condition; The hydraulic loss values ​​of all pipe segments under all flow conditions are organized with the unique identifiers of the pipe segments and the flow condition values ​​to form a structured data set; Based on the structured dataset, a hydraulic loss distribution model for the pipeline network is established. This model can output the corresponding hydraulic loss value by inputting the pipe segment identifier and flow rate value.

6. The method according to claim 1, characterized in that, Using the optimal drainage flow rate and the optimal drainage frequency as target control parameters, the flow distribution of each pipe segment is adjusted by automatically regulating the valve opening in the hydraulically unbalanced section, so that the actual drainage state of the pipe network approaches the target control parameters and maintains overall hydraulic balance, including: Based on the spatial distribution of the hydraulically unbalanced road section, determine the control valves that need to be adjusted in the hydraulically unbalanced road section and their specific locations; For the control valve, based on the difference between the target control parameters and the current actual drainage state, the required change in the opening of the control valve is calculated, and based on the change in opening, the opening of the corresponding control valve is adjusted by the automatic control system, thereby affecting the actual drainage state. Collect flow data from each monitoring point in the pipeline network after adjustment, and calculate the degree of matching between the current actual drainage status and the target control parameters; When the matching degree does not meet the predetermined requirements, the valve opening change is recalculated and iteratively adjusted until the actual drainage state stabilizes and approaches the target control parameters and maintains overall hydraulic balance.

7. The method according to claim 1, characterized in that, The method, based on historical monitoring data coupling water quality and quantity at the inlet of the wastewater treatment plant, classifies different influent load levels and establishes a matching relationship model between the influent load levels and the discharge flow rate and discharge frequency, including: Historical water quality monitoring data and historical water volume monitoring data of the inlet are obtained, and the historical water quality parameter value and historical water volume parameter value at the same time point are multiplied to calculate the inlet load value at the time point. The influent load value is divided into multiple levels, and each level corresponds to a specific load range; For the influent load level, the corresponding drainage flow rate and drainage frequency value are extracted from the historical water volume monitoring data, and its statistical characteristic value is calculated through the drainage flow rate and drainage frequency value. Based on the statistical characteristic values, a mapping relationship is established between the influent load level and the drainage flow rate and drainage frequency, wherein the mapping relationship is represented in the form of a lookup table.

8. A wastewater treatment plant drainage scheduling system based on a fluid dynamics model, characterized in that, include: A module is established to classify different influent load levels based on historical monitoring data of water quality and quantity coupled at the influent of a wastewater treatment plant, and to establish a matching relationship model between the influent load level and the discharge flow rate and discharge frequency. The calculation module is used to simultaneously collect the interception volume of the inlet screen and the flow rate of the drainage pipe at the inlet screen of the sewage treatment plant. By performing correlation processing on the interception volume and the flow rate data, the interception influence coefficient, which reflects the degree of influence of the inlet screen interception status on the drainage capacity of the pipe network, is calculated. The second calculation module is used to calculate the allowable drainage range of the drainage network using a fluid dynamics model. It takes the matching relationship model corresponding to the current inflow load level and the interception influence coefficient as input, and the allowable drainage range as a constraint to calculate the optimal drainage flow rate and the optimal drainage frequency that match the current inflow load level and are within the allowable drainage range. The identification module is used to identify hydraulically unbalanced sections in the pipeline network with abnormal flow distribution based on the flow data and the hydraulic loss distribution of each section of the pipeline network obtained by the fluid dynamics model. The adjustment module is used to take the optimal drainage flow rate and the optimal drainage frequency as target control parameters, and adjust the flow distribution of each pipe section by automatically adjusting the opening of the valves in the hydraulically unbalanced section, so that the actual drainage state of the pipe network approaches the target control parameters and maintains the overall hydraulic balance.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the wastewater treatment plant drainage scheduling method based on a fluid dynamics model as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables the wastewater treatment plant drainage scheduling method based on a fluid dynamics model as described in any one of claims 1 to 7.

Images