Intelligent high-density pool water quality control method and system

Abstract

The application discloses an intelligent high-density pool water quality control method and system, relates to the technical field of intelligent water quality treatment, and comprises the following steps: collecting the latest data and local data in a high-density pool, preprocessing the latest data, inputting the preprocessed data into a three-dimensional digital twin model to update the state of the three-dimensional digital twin model, exchanging the local data between adjacent intelligent agents to obtain local interaction data of the intelligent agents, simulating extreme working conditions in the digital twin model, obtaining water quality change prediction results, starting a bionic swarm intelligence algorithm for distributed collaborative optimization, obtaining optimized control instructions and distributing the control instructions to each intelligent agent to execute a water quality control task, and generating a high-density pool water quality state report. The application uses an ant colony algorithm for optimization, considers not only the demand of water quality reaching the standard but also the requirement of energy saving, greatly improves economic adaptability, and ensures that the control instructions can realize efficient water quality management under various environmental conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent water quality treatment, and in particular to an intelligent high-density pool water quality control method and system. Background Art

[0002] As a core process in water treatment, high-density tank water quality control technology has evolved from mechanized control to intelligent control. With the widespread adoption of the Internet of Things (IoT), existing high-density tank water quality control technology has gradually incorporated multi-parameter sensor networks (such as turbidity and dissolved oxygen), enabling real-time collection and remote control of key water quality indicators.

[0003] Existing methods for controlling water quality in high-density tanks still have many shortcomings. Existing optimization algorithms (such as genetic algorithms and particle swarm algorithms) converge slowly and easily become trapped in local optimal solutions when subjected to sudden load shocks. For example, when the chemical oxygen demand of the influent exceeds the standard, multiple iterations are required to generate a feasible solution, during which time the water quality in the high-density tank may have deteriorated to an irreversible state. The correlation analysis between existing distributed control instructions is weak, often leading to problems such as overdosing or flow field disturbances. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent high-density pool water quality control method to solve the problems of insufficient working condition prediction accuracy and poor coordination of distributed control instructions in existing high-density pool water quality control methods.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent high-density pool water quality control method, which includes constructing a three-dimensional digital twin model, defining the core position of the high-density pool as an independent intelligent agent, setting control rules for each intelligent agent, and outputting initial configuration information of the intelligent agent;

[0008] According to the initial configuration information of the intelligent agent, the latest data and local data in the high-density pool are collected and preprocessed. The preprocessed data is input into the 3D digital twin model to update the state of the 3D digital twin model. At the same time, the local data is exchanged between adjacent intelligent agents to obtain the local interaction data of the intelligent agents.

[0009] Based on the local interaction data of the intelligent agents, extreme working conditions are simulated in the digital twin model to obtain the prediction results of water quality changes and activate the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions;

[0010] The optimized control instructions are assigned to each agent, and the water quality control task is performed to generate a high-density pool water quality status report.

[0011] As a preferred solution of the intelligent high-density pool water quality control method of the present invention, wherein: constructing a three-dimensional digital twin model includes the following steps:

[0012] Collect multi-source water quality data and upload it to the central server. Select ANSYS Fluent as the core modeling tool to build a three-dimensional digital twin model.

[0013] As a preferred solution of the intelligent high-density pool water quality control method described in the present invention, the dosing device, agitator and mud pump of the metering pump are used as intelligent bodies, the intelligent bodies are initialized and control rules are set, and the intelligent bodies after the control rules are set are verified to obtain the initial configuration information of the intelligent bodies.

[0014] As a preferred embodiment of the intelligent high-density pool water quality control method of the present invention, the latest data in the high-density pool includes the latest dissolved oxygen, sludge concentration, water flow velocity and water temperature, and the local data includes COD concentration, flow field uniformity and sludge concentration;

[0015] The preprocessing is performed by applying a five-point moving average method.

[0016] As a preferred solution of the intelligent high-density pool water quality control method described in the present invention, a rainstorm scenario is selected as the extreme working condition, the extreme working condition parameters are configured and integrated into a rainstorm working condition configuration file, the rainstorm working condition configuration file is loaded into the three-dimensional digital twin model for simulation, and the water quality change prediction results are output.

[0017] As a preferred solution of the intelligent high-density pool water quality control method of the present invention, the ant colony algorithm is selected as the bionic swarm intelligence algorithm, and the core parameters of the ant colony algorithm are set. An ant exploration space is generated according to the core parameters of the ant colony algorithm. When the ants complete their exploration in the ant exploration space, a path result of the control instruction is generated.

[0018] According to the path results of the control instructions, the multi-objective function and water quality standards are set, the score of each control instruction path is calculated and the optimized control instructions are output.

[0019] As a preferred solution of the intelligent high-density pool water quality control method described in the present invention, the optimized control instructions are integrated into the edge computing node, and the optimized control instructions are hierarchically scheduled using the priority queue mechanism. After the scheduling is completed, each intelligent agent performs an independent water quality control task and generates a final high-density pool water quality status report.

[0020] In a second aspect, the present invention provides an intelligent high-density pool water quality control system, including an output configuration module, building a three-dimensional digital twin model, defining the core position of the high-density pool as an independent intelligent agent, setting control rules for each intelligent agent, and outputting the initial configuration information of the intelligent agent;

[0021] The data interaction module collects the latest data and local data in the high-density pool based on the initial configuration information of the intelligent agent, preprocesses the latest data, inputs the preprocessed data into the 3D digital twin model to update the state of the 3D digital twin model, and exchanges local data between adjacent intelligent agents to obtain the local interaction data of the intelligent agents;

[0022] The optimization instruction module simulates extreme working conditions in the digital twin model based on the local interaction data of the intelligent agent, obtains the prediction results of water quality changes, and activates the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions;

[0023] The report generation module assigns the optimized control instructions to each agent, performs water quality control tasks, and generates a water quality status report for the high-density pool.

[0024] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent high-density pool water quality control method as described in the first aspect of the present invention is implemented.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the intelligent high-density pool water quality control method as described in the first aspect of the present invention is implemented.

[0026] The beneficial effects of the present invention are as follows: by simulating extreme working conditions in the digital twin model, water quality change prediction results are obtained and the bionic swarm intelligence algorithm is started for distributed collaborative optimization to obtain optimized control instructions, which are then assigned to each intelligent agent, and water quality control tasks are performed to generate a high-density pool water quality status report. The use of the ant colony algorithm for optimization not only takes into account the need to meet water quality standards, but also takes into account the requirements of energy conservation, greatly improving adaptability and economy, and ensuring that control instructions can achieve efficient water quality management under various environmental conditions. The use of the priority queue mechanism ensures the priority execution of key tasks, such as COD control, and the application of the high-speed GPIO interface reduces the risk of delay and data loss, and improves the execution accuracy of distributed control instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 Schematic diagram of the high-density pool water quality control architecture and three-dimensional digital twin model construction in Example 1.

[0029] Figure 2 This is a flowchart of data collection and local interaction with intelligent agents in Example 1.

[0030] Figure 3 This is the extreme working condition simulation and ant colony algorithm optimization path diagram in Example 1. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0033] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0034] Example 1, with reference to Figures 1 to 3 This embodiment provides an intelligent high-density pool water quality control method, comprising the following steps:

[0035] S1. Build a three-dimensional digital twin model and define the core position of the high-density pool as an independent intelligent agent. Load preset rules for each intelligent agent and output the initial configuration information of the intelligent agent.

[0036] The following steps are included:

[0037] S1.1. First, a high-precision sensor network is deployed to collect multi-source water quality data in the high-density pool. Specifically, a dissolved oxygen probe (measuring range of 0-20 mg / L, accuracy of ±0.1 mg / L), a turbidity meter (measuring range of 0-1000 NTU, accuracy of ±1 NTU), an ultrasonic flow meter (measuring range of 0-5 m / s, accuracy of ±0.01 m / s) and a temperature sensor (measuring range of 0-50°C, accuracy of ±0.1°C) are selected. These four sensors form a four-in-one sensor group, each of which is fixedly installed at three main locations in the high-density pool: the water inlet (monitoring the input water quality characteristics), the central area (reflecting the average state in the high-density pool) and the mud outlet (detecting the bottom sedimentation). During installation, the sensor probe is inserted 0.5 meters underwater and fixed on a stainless steel bracket to avoid interference from floating objects. The sampling frequency is set to once every five minutes. After startup, the original data set is collected and generated, namely dissolved oxygen 6mg / L, sludge concentration 700mg / L, water flow velocity 0.4m / s, and water temperature 25℃. The four data are uploaded to the central server in the form of encrypted data packets through the Internet of Things gateway (transmission rate is 10Mbps). The Internet of Things gateway is installed in the border rain box of the high-density pool. It should be noted that the distance to the nearest sensor must not exceed 20 meters to ensure signal stability.

[0038] S1.2, After the central server receives the four types of data uploaded by the sensors, it needs to build a three-dimensional digital twin model. Specifically, the central server needs to be configured as a high-performance workstation, and then run the ANSYS Fluent software (as the core modeling tool) to process the uploaded four types of data. First, open the ANSYS Fluent software interface, input the specific physical dimensions of the high-density pool in the geometry module, such as length 20m, width 12m, depth 5m, the specific physical dimensions are provided by the high-density pool body design drawing, and it is necessary to ensure consistency with reality, ANSYS Fluent software will automatically generate a basic three-dimensional rectangular frame (to represent the external boundary of the high-density pool body, that is, the three-dimensional geometric network), next, set the mesh division parameters in the mesh module of ANSYS Fluent software, specify the number of mesh elements as 500,000 (each element edge length is about 0.1 meters), select hexahedral mesh type to improve calculation accuracy, the division process takes about 2 minutes, after the division is completed, a fine mesh structure is generated, covering the entire high-density pool body inside, which can capture the details of local flow field and material distribution, such as high flow velocity area near the water inlet or low speed deposition area at the bottom of the sludge outlet. After the mesh structure is generated, the central server receives the four types of data uploaded by the sensors (i.e. dissolved oxygen 6mg / L, sludge concentration 700mg / L, water flow velocity 0.4m / s, temperature 25℃) and imports them into the setting module of ANSYS Fluent software, and assigns them to the corresponding areas of the mesh structure according to the location (i.e. water inlet, central area, sludge outlet), for example, the water inlet mesh point is assigned a dissolved oxygen value of 7mg / L, the central area is assigned a value of 6mg / L, and the sludge outlet is assigned a value of 4mg / L.

[0039] S1.3, The next operation is to activate the computational fluid dynamics module in the physical model options of ANSYS Fluent software, select the turbulence model (k-ε model) to simulate the properties of water flow turbulence, and enable the multiphase flow function to simulate the interaction between sludge particles and water body. The boundary conditions set include water inlet flow velocity 0.6m / s, sludge outlet pressure atmospheric pressure, and pool wall no-slip wall (all three boundary conditions are determined based on the specific high-density pool operation parameters). Then adjust the solution parameters, set the time step to 0.1 seconds, simulate the steady-state distribution of the initial state, click the calculation button, ANSYS Fluent software completes the simulation, generates detailed results of pool flow field and material distribution (i.e. preliminary simulation results), for example, the sludge concentration increases from 500mg / L at the water inlet to 900mg / L at the sludge outlet, the water flow velocity decreases from 0.5m / s in the center to 0.2m / s at the edge, and the dissolved oxygen decreases from 6mg / L at the surface to 4mg / L at the bottom (reflecting the spatial heterogeneity in the high-density pool). Finally, the built three-dimensional digital twin model is stored in the local hard disk of the central server in the format of fluent file.

[0040] S1.4. In order to achieve distributed control, it is necessary to initialize the intelligent agent at the core position of the high-density pool, specifically select the dosing device of the metering pump, and the dosing range is 0-10g / m 3 , agitator (power of 500W, speed range of 0-500 rpm) and sludge pump (flow range of 0-100L / time) as intelligent body carriers, each intelligent body carrier is equipped with an ARMCortex-M4 embedded microcontroller and supporting local sensors (i.e. the dosing device of the metering pump is equipped with a COD sensor with a range of 0-500mg / L and an accuracy of ±2mg / L; the agitator is equipped with a speed sensor; the sludge pump is equipped with a flow meter).

[0041] When installing the microcontroller, it must be fixed in the equipment control box. All sensors must be close to the actuator (for example, the COD sensor must be placed 5 cm away from the dosing outlet). Each intelligent agent must form a star-shaped local communication network through the ZigBee communication network. The connection distance between the farthest intelligent agent should not exceed 80 meters. At the same time, control rules must be set for each intelligent agent. For example, the dosing device of the metering pump is set to 0.5g / m per minute when the COD (chemical oxygen demand) exceeds 120mg / L. 3 The dosage of sodium hypochlorite is increased at a rate until the COD drops below 100 mg / L. The agitator is set to increase the speed by 50 rpm when the flow rate is lower than 0.3 m / s. The sludge pump is set to discharge 50 L of sludge every 6 hours when the sludge concentration exceeds 800 mg / L (the three preset control rules are set according to the preliminary simulation results).

[0042] S1.5. When all intelligent agents are initialized, a self-test communication is performed through the ZigBee communication network, allowing each intelligent agent to report the current status. For example, the dosing device of the metering pump detects that the COD is 100mg / L, the agitator speed is 200 rpm, and the sludge pump is on standby. The communication takes about 5 seconds. The current status detection results of the intelligent agent are uploaded to the central server and synchronized with the four data of the three-dimensional digital twin model. For example, it is confirmed that the COD (100mg / L) in the central area displayed by the three-dimensional digital twin model is consistent with the actual measured value of the dosing device of the metering pump, and the deviation is controlled within 2%. If it exceeds the standard, the data is re-collected to adjust the three-dimensional digital twin model. After the verification is passed, the initial configuration information of the intelligent agent is output (including the current status of the intelligent agent, such as the COD of the dosing device of the metering pump is 100mg / L and the preset rules, such as COD exceeding the standard and dosing 0.5g / m 3 ).

[0043] S2. Based on the initial configuration information of the intelligent agent, collect the latest data and local data in the high-density pool, preprocess the latest data, input the preprocessed data into the three-dimensional digital twin model to update the state of the three-dimensional digital twin model, and at the same time exchange the local data between adjacent intelligent agents to obtain the local interaction data of the intelligent agent.

[0044] The following steps are included:

[0045] S2.1. The latest data in the high-density pool refers to the latest dissolved oxygen, sludge concentration, water flow rate, and water temperature. The specific collection process also uses dissolved oxygen probes, turbidity meters, ultrasonic flow meters, and temperature sensors installed at three main locations in the high-density pool to collect the latest data.

[0046] S2.2. Send the latest collected data to the industrial edge computing node, which preprocesses the data. Specifically, a five-point moving average method is applied to each data set. This method takes the average of the current data point and the two time points before and after (a total of 5 minutes) to smooth out abnormal fluctuations. For example, if the dissolved oxygen sequence is [5.2, 6.0, 5.8, 5.0, 5.1] and the sludge concentration sequence is [780, 820, 790, 800, 810], then after processing with the five-point moving average method, the dissolved oxygen becomes 5.42 mg / L and the sludge concentration becomes 800 mg / L.

[0047] S2.3. Open the real-time update module of ANSYS Fluent software and import the preprocessed data into the 3D digital twin model through the real-time update module. Use 500,000 cells to distribute the preprocessed data by location. For example, the water inlet is updated to 5.5 mg / L dissolved oxygen, the central area is 5 mg / L, and the sludge outlet is 4.8 mg / L. The sludge concentrations are updated to 750 mg / L, 800 mg / L, and 850 mg / L, respectively. Then run a fast simulation to generate the updated 3D digital twin model status. For example, the area with decreased dissolved oxygen is concentrated at the bottom of the high-density pool (4.8 mg / L), and the sludge concentration rises to 850 mg / L near the sludge outlet. The updated three-dimensional digital twin model is displayed through a visual interface (i.e., dynamic curve and heat map). The dynamic curve shows the parameter change trend within 5 minutes (for example, the curve of dissolved oxygen dropping from 6 mg / L to 5 mg / L). The heat map marks the low dissolved oxygen area (blue, pool bottom) and high sludge area (red, sludge outlet). The heat map can support dynamic adjustment, such as dragging the mouse to rotate the view to view the side of the pool, or using the cross-section tool to cut the central area to check the vertical changes in flow rate and dissolved oxygen. The update frequency is maintained every 5 minutes.

[0048] S2.4. The local data here refers to COD concentration, flow field uniformity and sludge concentration, which are collected using COD sensors, speed sensors and flow meters. When the local data collection is completed, the ZigBee communication network (data rate is 250kbps) is started to perform data exchange, and the exchange frequency is once every 10 seconds. The specific exchange process is: the dosing device of the metering pump broadcasts the COD concentration data packet through the ZigBee communication network to the star-shaped local communication network (the specific meaning of broadcasting here is that the intelligent body sends any kind of local data to other devices in the star-shaped local communication network through the ZigBee communication network at the same time, rather than a point-to-point transmission communication method). The broadcast signal is first sent to the central communication tower (50m away). When the central communication tower receives it, it is forwarded to the agitator (30m away) and the sludge pump (40m away). After the agitator receives it, it parses the data The data is packaged and recorded in the form of COD concentration value, and 70% of the flow field uniformity data is broadcast at the same time, which is forwarded to the dosing device of the metering pump and the sludge pump via the central communication tower. The sludge pump also broadcasts the sludge concentration, and the central communication tower forwards it to the other two parties. It should be noted that the entire exchange process must be controlled within 50 milliseconds. After all intelligent agents confirm that the reception is successful, the data exchanged between each intelligent agent is recorded (for example, the dosing device of the metering pump records 70% of the flow field uniformity data, which may affect the diffusion of the agent) and is stored in a temporary buffer (with a capacity of 16KB) to form the local interaction data of the intelligent agent.

[0049] S3. Based on the local interaction data of the intelligent agent, extreme working conditions are simulated in the digital twin model to obtain the prediction results of water quality changes and activate the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions.

[0050] The following steps are included:

[0051] S3.1. Based on the interaction data of the intelligent body, it is necessary to configure extreme operating condition parameters through adaptive boundary conditions to simulate future changes in water quality. Extreme operating condition parameters include water flow increase, dissolved oxygen and sludge concentration. Specifically, based on the problem of surge in flow during the rainy season often faced by Gaomi Pool, a rainstorm scenario is selected as the extreme operating condition. First, the current water inlet status of Gaomi Pool is determined (assuming that the water flow is 100 cubic meters per hour, the dissolved oxygen is 5.5 mg / L, and the sludge concentration is 750 mg / L). The meteorological disturbance database is used to calculate the probability of rainstorm events in the Gaomi Pool area (this meteorological disturbance database stores rainfall data in the area where Gaomi Pool is located in the past 5 years, including the intensity, duration, type and frequency of each rainfall. A rainstorm event is defined as rainfall exceeding 50 mm per hour. Data that meets the requirements of rainstorm events are screened out from the rainfall data). According to the probability of rainstorm events in the Gaomi Pool area, a real-time water flow-capacity coupling analysis is initiated to determine the specific increase in water flow. Specifically, first check Check the instantaneous carrying limit of the high-density pool body (assuming it is 200 cubic meters per hour, which can be understood as the maximum flow that the high-density pool body can safely handle without triggering overflow), and combine it with the water flow at the current water inlet to calculate the remaining capacity of the high-density pool, that is, use the instantaneous carrying limit of the high-density pool body of 200 cubic meters per hour minus the current water flow at the water inlet of 100 cubic meters per hour, and the remaining capacity of the high-density pool is 100 cubic meters per hour. Taking into account that the actual impact of the rainstorm will not reach the instantaneous carrying limit, the initial estimate of the increase in water flow is 35%, that is, the water flow is increased to 135 cubic meters per hour (100 cubic meters per hour of water flow at the water inlet plus 35% of the remaining capacity of the high-density pool of 100 cubic meters per hour, that is, 35 cubic meters per hour).

[0052] Based on the initial estimate of the water flow increase, combined with the specific volume of the Gaomi Pool (assuming 1,000 cubic meters) and the duration of the rainstorm (assuming 6 hours), the total water input to the Gaomi Pool was estimated to be 135 cubic meters per hour multiplied by 6 hours, which is equal to 810 cubic meters, accounting for 81% of the Gaomi Pool's capacity, close to but not exceeding 90% (i.e., the safety range). For further optimization, a comparison with historical rainstorm cases in the Gaomi Pool showed that a 40% increase (i.e., 140 cubic meters per hour, with a total water input of 840 cubic meters) was more common under conditions with an 80% probability of rainstorms, and the total water input was still within the safety range (84% capacity). Finally, it was verified whether 140 cubic meters per hour exceeded the instantaneous load limit, confirming that there was still a margin of 60 cubic meters per hour, meeting the design constraints. Therefore, the specific increase in water flow was determined to be 40%, adjusted from 100 cubic meters per hour to 140 cubic meters per hour.

[0053] S3.2, Next, the operating parameters of the dissolved oxygen need to be configured. Specifically, since the current inlet of the high-density pool has a dissolved oxygen content of 5.5 mg / L, and considering that the storm causes the water flow to increase from 100 cubic meters per hour to 140 cubic meters per hour, first calculate the change in water flow rate, assuming that the initial flow rate of the inlet water is 0.6 m / s, then the cross-sectional area of the inlet is 100 cubic meters per hour of water flow at the current inlet of the high-density pool divided by 3600 seconds and multiplied by the initial flow rate of the inlet water, which is about 0.167 square meters. When the water flow increases to 140 cubic meters per hour, the water flow rate at the inlet is 0.84 m / s (i.e. 140 cubic meters per hour divided by 3600 seconds divided by the cross-sectional area of the inlet 0.167 square meters), so the change in water flow rate is about 40%.

[0054] S3.3, Use the weather disturbance database to analyze the effect of the change in water flow rate on oxygen transfer. Specifically, since the high flow rate of the water body accelerates the contact between the water body and the air, but the storm also brings low-oxygen rainwater (typical value 4-6 mg / L), so the dilution effect dominates. Take the benchmark value of low-oxygen rainwater 5 mg / L (i.e. the average value of low-oxygen rainwater), and compare it with the dissolved oxygen content of the current inlet of the high-density pool 5.5 mg / L, to estimate the mixed value after the dissolved oxygen content decreases, the specific estimation process is: assuming that the new dissolved oxygen is the weighted average of the two volumes, i.e. the current high-density pool water flow 100 cubic meters per hour contributes 5.5 mg / L, the additional water flow 40 cubic meters per hour contributes 5 mg / L, in the case of the adjusted total water flow 140 cubic meters per hour, the mixed value after the dissolved oxygen content decreases is (100 times 5.5 plus 40 times 5) divided by 140, about 5.36 mg / L. But further considering the turbulent effect of the water flow rate at the inlet 0.84 m / s, which will enhance the oxygen transfer attenuation (due to the turbulent effect, the low-oxygen water at the bottom upwelling), according to the water flow rate attenuation coefficient table (preset in the weather disturbance database, every 0.1 m / s of flow rate increase reduces 0.05 mg / L), the water flow rate increases 0.24 m / s, corresponding to a decrease of 0.12 mg / L, the mixed value of the dissolved oxygen content after the decrease is 5.36 mg / L minus 0.12 mg / L, which is 5.24 mg / L. In order to reflect the most unfavorable low-oxygen characteristics of the storm, take the integer of the dissolved oxygen to 4 mg / L (i.e. the lower limit), which is consistent with the low-oxygen characteristics of the rainwater (4 mg / L).

[0055] S3.4. Finally, configure the operating parameters of the sludge concentration. When adjusting the sludge concentration, call the sedimentation-scouring balance algorithm to analyze the impact of heavy rain based on the current sludge concentration of 750 mg / L at the high-density pool inlet. The water flow rate increases from 100 cubic meters per hour to 140 cubic meters per hour, an increase of 40%. First, evaluate the scouring and sedimentation effects of this change on the sludge. Since the increase in the flow of heavy rain will flush in new sediments, assuming that every 10 cubic meters per hour of flow increase brings 5 ​​mg / L of new sludge (based on the regional soil particle content), the additional 40 cubic meters per hour corresponds to an increase of 50 mg / L, and the initial estimated sludge concentration rises to 800 mg / L (that is, the current sludge concentration of 750 at the high-density pool inlet plus the corresponding increase of 50 mg / L per hour). However, heavy rain will dilute the water in Gaomi Pool at the same time. According to the current water volume of Gaomi Pool (assuming 800 cubic meters, close to 80% of the volume of 1000 cubic meters) and the newly added water volume (40 cubic meters per hour, 240 cubic meters in 6 hours), the total water volume increases to 1040 cubic meters (excess overflow treatment). The dilution ratio is calculated as the initial 800 cubic meters divided by the total water volume of 1040 cubic meters, which is about 0.77. The original sludge concentration of 750 mg / L multiplied by the dilution ratio of 0.77 is 577 mg / L, which means that the sludge concentration is reduced by about 173 mg / L after dilution. The net change in sludge concentration is calculated by combining the sediment flushing and dilution effects: 800 mg / L (including the newly added 50 mg / L) minus the 173 mg / L reduced by dilution, which is 627 mg / L. In order to conform to the actual law of rainstorm erosion, the final value of the sludge concentration was rounded to 600 mg / L with reference to historical rainstorm data (the influent sludge concentration was between 550 and 650 mg / L) to ensure a conservative estimate.

[0056] S3.5. Integrate the three extreme operating parameters of water flow rate increase, dissolved oxygen, and sludge concentration into a rainstorm operating condition profile. Load the rainstorm operating condition profile into the 3D digital twin model, and configure the simulation parameters to simulate the extreme conditions (the simulation parameters are a time step of 1 minute, a total simulation time of 12 hours, and 20 time step iterations). Specifically, the 3D digital twin model extracts the rainstorm operating condition profile from memory and initializes 700,000 grid cells. The inlet flow rate is adjusted to 0.84 m / s, and the dissolved oxygen is set to 4 mg / L. After the simulation is started, by assigning grid tasks, the entire process of water flow distribution, dissolved oxygen migration, and sludge deposition is gradually deduced with a time step of 1 minute. During the simulation, the 3D digital twin model will update the grid status in real time (i.e., update the progress bar and residual convergence curve). The residual is used as a measure of the consistency between the simulation results and the physical world. When the residual convergence curve converges to 0.001, the calculation is confirmed to be stable. In the simulation, an influent flow rate of 140 cubic meters per hour caused the bottom flow velocity to drop to 0.1 m / s. The dilution of dissolved oxygen and the deposition of sludge concentration gradually appeared in the grid. The 12-hour forecast data was generated minute by minute to obtain the final water quality change forecast results (i.e., dissolved oxygen dropped from 5 mg / L to 4 mg / L, the dilution effect increased significantly due to the increase in water flow, the deposition thickness of sludge concentration increased by 2 cm, the water flow velocity at the bottom of the high-density pool was reduced to 0.1 m / s, causing intensified deposition and COD to rise to 160 mg / L).

[0057] S3.6. Based on the results of water quality change prediction, the ant colony algorithm is selected as the bionic swarm intelligence algorithm (i.e., the core of distributed collaborative optimization, which can be understood as distributed operation among various intelligent agents to collaboratively determine the global optimal control instructions). Specifically, it is necessary to first set the core parameters of the ant colony algorithm (including the number of ants, heuristic factor, pheromone concentration, and pheromone volatility coefficient). The number of ants is set to 30, and each ant represents a control instruction combination of an intelligent agent. The specific number is selected based on the balance between the number of intelligent agents (3) and computational efficiency (that is, 10 times the number of intelligent agents). The heuristic factor (i.e., the intuitive tendency to guide ants to select control instruction paths) is set to 2. The usual value range is between 1-3. The median value is taken to balance the exploration and convergence speed, which is more likely to reflect the priority of the control effect (such as the reduction in COD). The pheromone concentration is set to 1, covering all initial control instruction paths. For example, the dosing device of the metering pump doses 6g / m 3 The agitator speed is 300 rpm, and the sludge pump frequency is every 4 hours. The pheromone volatility coefficient is set to 0.1, which means that the pheromone concentration decreases by 10% after each iteration. This prevents ants from forgetting the high-quality control instruction path too quickly and prevents them from falling into local optimality.

[0058] After the core parameters of the ant colony algorithm are set, each agent generates an initial control range as the ant's exploration space based on the local data of the high-density pool and the predicted results of water quality changes. For example, the dosage of the dosing device of the metering pump is 5-8g / m 3 , the speed of the agitator is 250-350 rpm, and the frequency of the sludge pump is every 3-5 hours.

[0059] S3.7, command 30 ants to disperse and explore in the ant exploration space, and each ant randomly selects a combination. For example, the first ant selects 5g / m 3 , speed 250 rpm, frequency every 5 hours, the second one only selects 6g / m 3 , 300 rpm, every 4 hours, and so on. When the ants are exploring, each agent needs to estimate the exploration effect of the ants, for example, the dosing device of the metering pump is used for every 1g / m 3 Reduce COD5mg / L, 5g / m 3 The COD content was reduced from 150mg / L to 125mg / L. The stirrer speed uniformity was increased by 5% every 50 rpm, and increased from 70% to 80% at 300 rpm. The sludge thickness was reduced by 0.25cm every hour when the frequency of the sludge pump was reduced, and decreased from 2cm to 1.5cm every 4 hours. After each ant completed an exploration, each agent recorded the path result of the control command through the ZigBee communication network. For example, the combination of the second ant (6g / m 3 , 300 rpm, every 4 hours) corresponds to COD110 mg / L, uniformity 80%, and sludge thickness 1.5 cm.

[0060] S3.8. According to the path results of the control instructions, set the multi-objective function (the multi-objective includes water quality compliance rate and energy saving rate, and the weights of the two objectives are 80% and 20% respectively, which are set according to the specific operation requirements of the high-density pool) and water quality standards (set according to the water quality specifications of the high-density pool effluent, i.e. COD <100mg / L, dissolved oxygen >4.5mg / L, and energy consumption limit of dosing <8g / m 3 , agitator speed <350 rpm) to evaluate the quality of the 30 control instruction paths traversed by the ants. Specifically, to calculate the score of each control instruction path, for example, Ant A's COD 110 mg / L is lower than the water quality standard, and the dissolved oxygen 4 mg / L is also lower than the water quality standard. Then, using the compliance ratio, that is, 110 divided by 100 is 1.1. Since it exceeds the standard by 10%, it is calculated to be 0.9, and then the dissolved oxygen deviation (4.5-4 divided by 4.5 is 0.11) is subtracted and multiplied by the weight of 80%, and the water quality compliance rate score is 0.632; and the energy consumption limit is 6g / m 3 8g / m3 of water quality standard 3of 0.16, and the total score is 0.632 plus 0.16, which equals 0.79 (i.e., the score of the control instruction path).

[0061] The pheromone concentration is updated according to the score of the control instruction path (i.e., a high-score control instruction path increases the pheromone concentration, and a low-score control instruction path decreases the pheromone concentration), for example, the pheromone concentration of the traversal control instruction path of ant A is increased from the initial setting of 1 to 1.2 (because the score of the traversal control instruction path of ant A is higher, that is, 0.79), while the score of the traversal control instruction path of ant B is lower (assuming 0.42), and the pheromone concentration is reduced from 1 to 0.9.

[0062] S3.9, the process of updating the pheromone concentration is repeatedly performed until a preset number of iterations is reached, and the optimal control instruction (i.e., the optimized control instruction) is output. Specifically, the ants re-explore according to the updated pheromone (high-concentration path has greater attraction) and heuristic factors. For example, in the second iteration, the ants tend to 6 g / m 3 , 6.5 g / m 3 , 320 rpm, every 4 hours, COD is reduced to 98 mg / L, uniformity is 85%, sludge thickness is 1 cm, the score of the control instruction path is increased to 0.92, and the pheromone concentration is increased to 1.3. When all 10 iterations are performed, the pheromone concentration converges to the optimal path, that is, 6 g / m 3 (COD 98 mg / L), 320 rpm (uniformity 85%), frequency every 4 hours (sludge thickness 1 cm), and the total score is 0.95, the water quality compliance rate reaches 98%, and the energy saving rate reaches 85%.

[0063] S4. The optimized control instruction is distributed to each intelligent agent, and the water quality control task is performed to generate a high-density pool water quality status report.

[0064] comprising the following steps,

[0065] S4.1, the central server integrates the optimized control instruction into the edge computing node for distribution processing. Specifically, the central server is connected with the central server through wired Ethernet, and the central server first encapsulates the optimized control instruction into a structured JSON data frame, and transmits it to the edge computing node through Ethernet. When the edge node receives it, the priority queue mechanism is used to schedule the optimized control instruction, and the priority is sorted according to the water quality influence degree, that is, the dosing device of the metering pump (COD control) has the highest priority, which is set to level 1, the agitator (flow field uniformity) is level 2, and the sludge pump (sludge thickness) is level 3.

[0066] During the scheduling process, the edge node writes the instructions into the queue in order of priority. The instructions for dosing are first assigned to the head of the queue, followed by the agitator and the sludge pump. The edge node directly establishes point-to-point communication with the microcontroller of each intelligent body through the high-speed GPIO interface. The dosing device of the metering pump receives 6g / m 3 Instructions: the agitator is set to 320 rpm, the sludge pump is set to operate once every 4 hours and the sludge discharge volume is 50L.

[0067] S4.2. After the optimized control instructions are assigned, each agent independently performs the water quality control task and monitors the water quality control effect in real time through local sensors. Specifically, the dosing device of the metering pump starts the metering pump and uses the microcontroller to send a pulse signal to the pump driver. The pump driver adds sodium hypochlorite to the high-density pool at a rate of 0.1g per second, and reaches 6g / m in 60 seconds. 3 During the dosing process, the COD sensor samples once every 5 seconds and records the gradual decrease of COD from 150mg / L, for example, 130mg / L after 10 seconds, 110mg / L after 30 seconds, and 98mg / L after 60 seconds, confirming that it drops below 100mg / L. The agitator adjusts the speed to 320 rpm, and the microcontroller drives the motor through the PWM signal (ie, duty cycle). The speed sensor detects once per second, and the flow rate increases from 0.4m / s to 0.5m / s. The sludge pump runs at a frequency of once every 4 hours. The microcontroller sets the timer (cycle is 14400 seconds). Each time the sludge pump runs, it discharges sludge at a flow rate of 50L / minute (a total of 50L, which takes 1 minute). At the same time, the flow meter monitors the sludge discharge volume. The sludge concentration drops from 850mg / L to 700mg / L, and the sludge thickness is reduced to 1 cm.

[0068] S4.3. Upload the water quality monitoring results to the edge computing node for integration to form a water quality status report for the high-density pool (including COD of 98 mg / L (100% compliance rate, target <100 mg / L), flow field uniformity of 85%, sludge concentration of 700 mg / L, sludge deposition thickness of 1 cm (reduced by 50%), with a timestamp and spatial distribution description, such as the COD decrease is mainly concentrated in the central area of ​​the high-density pool).

[0069] The high-density pool water quality report generated in this step utilizes a priority queue mechanism to hierarchically schedule control instructions based on the degree of water quality impact, ensuring that critical tasks (such as dosing) are prioritized. This mechanism improves responsiveness to core water quality indicators and avoids the resource waste associated with conventional uniform distribution. High-speed GPIO interfaces enable point-to-point communication between edge nodes and intelligent agents, reducing latency and the risk of data loss while significantly improving the accuracy of control instruction execution.

[0070] This embodiment also provides an intelligent high-density pool water quality control system, including: an output configuration module, which constructs a three-dimensional digital twin model, defines the core position of the high-density pool as an independent intelligent agent, sets control rules for each intelligent agent, and outputs the initial configuration information of the intelligent agent;

[0071] The data interaction module collects the latest data and local data in the high-density pool based on the initial configuration information of the intelligent agent, preprocesses the latest data, inputs the preprocessed data into the 3D digital twin model to update the state of the 3D digital twin model, and exchanges local data between adjacent intelligent agents to obtain the local interaction data of the intelligent agents;

[0072] The optimization instruction module simulates extreme working conditions in the digital twin model based on the local interaction data of the intelligent agent, obtains the prediction results of water quality changes, and activates the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions;

[0073] The report generation module assigns the optimized control instructions to each agent, performs water quality control tasks, and generates a water quality status report for the high-density pool.

[0074] This embodiment also provides a computer device suitable for the intelligent high-density pool water quality control method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent high-density pool water quality control method proposed in the above embodiment.

[0075] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0076] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent high-density pool water quality control method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0077] In summary, the present invention obtains the water quality change prediction results by simulating extreme working conditions in the digital twin model and starting the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain optimized control instructions, distribute the optimized control instructions to each intelligent agent, and perform water quality control tasks to generate a high-density pool water quality status report. The use of the ant colony algorithm for optimization not only takes into account the demand for water quality standards, but also takes into account the requirements of energy conservation, greatly improving the adaptability and economy, and ensuring that control instructions can achieve efficient water quality management under various environmental conditions. The use of the priority queue mechanism ensures the priority execution of key tasks, such as COD control, and the application of the high-speed GPIO interface reduces the risk of delay and data loss, and improves the execution accuracy of distributed control instructions.

[0078] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent high-density pool water quality control method, characterized by: include, A 3D digital twin model was constructed, and the core locations of the high-density tank were defined as independent intelligent entities. Specifically, the dosing device of the metering pump, the agitator, and the sludge pump were used as intelligent entities. Control rules were set for each intelligent entity, and the initial configuration information of the intelligent entity was output. According to the initial configuration information of the intelligent agent, the latest data and local data in the high-density pool are collected. The latest data in the high-density pool includes the latest dissolved oxygen, sludge concentration, water flow velocity and water temperature. The local data includes COD concentration, flow field uniformity and sludge concentration. The latest data is preprocessed and input into the 3D digital twin model to update the state of the 3D digital twin model. At the same time, the local data is exchanged between adjacent intelligent agents to obtain the local interaction data of the intelligent agents. Based on the local interaction data of the intelligent agent, extreme working conditions are simulated in the digital twin model to obtain the prediction results of water quality changes and start the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions, including the following steps: The ant colony algorithm is selected as the bionic swarm intelligence algorithm, and the core parameters of the ant colony algorithm are set. The ant exploration space is generated according to the core parameters of the ant colony algorithm. When the ants complete their exploration in the ant exploration space, the path result of the control instruction is generated. According to the path results of the control instructions, set the multi-objective function and water quality standards. The multi-objectives include water quality compliance rate and energy saving rate. Calculate the score of each control instruction path and output the optimized control instructions. The optimized control instructions are assigned to each agent, and the water quality control task is performed to generate a high-density pool water quality status report.

2. The intelligent high-density pool water quality control method according to claim 1, characterized in that: Building a 3D digital twin model includes the following steps: Collect multi-source water quality data and upload it to the central server. Select ANSYS Fluent as the core modeling tool to build a three-dimensional digital twin model.

3. The intelligent high-density pool water quality control method according to claim 2, characterized in that: Initialize the agent and set the control rules. Verify the agent after setting the control rules to obtain the initial configuration information of the agent.

4. The intelligent high-density pool water quality control method according to claim 3, characterized in that: The preprocessing is performed by applying a five-point moving average method.

5. The intelligent high-density pool water quality control method according to claim 4, characterized in that: Select a rainstorm scenario as the extreme working condition, configure the extreme working condition parameters and integrate them into a rainstorm working condition configuration file, load the rainstorm working condition configuration file into the three-dimensional digital twin model for simulation, and output the water quality change prediction results.

6. The intelligent high-density pool water quality control method according to claim 5, characterized in that: The optimized control instructions are integrated into the edge computing node, and the priority queue mechanism is used to hierarchically schedule the optimized control instructions. After the scheduling is completed, each intelligent agent performs an independent water quality control task and generates the final high-density pool water quality status report.

7. An intelligent high-density pool water quality control system, based on the intelligent high-density pool water quality control method according to any one of claims 1 to 6, characterized in that: include, Output configuration module, builds a three-dimensional digital twin model, defines the core position of the high-density pool as an independent intelligent agent, sets control rules for each intelligent agent, and outputs the initial configuration information of the intelligent agent; The data interaction module collects the latest data and local data in the high-density pool based on the initial configuration information of the intelligent agent, preprocesses the latest data, inputs the preprocessed data into the 3D digital twin model to update the state of the 3D digital twin model, and exchanges local data between adjacent intelligent agents to obtain the local interaction data of the intelligent agents; The optimization instruction module simulates extreme working conditions in the digital twin model based on the local interaction data of the intelligent agent, obtains the prediction results of water quality changes, and activates the bionic swarm intelligence algorithm for distributed collaborative optimization to obtain the optimized control instructions; The report generation module assigns the optimized control instructions to each agent, performs water quality control tasks, and generates a water quality status report for the high-density pool.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent high-density pool water quality control method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent high-density pool water quality control method according to any one of claims 1 to 6 are implemented.

Images