Monitoring control system of park drainage pipe network
By setting up sensors at key nodes of the park's drainage network to construct a distributed sensor network, real-time data is collected, pollution coefficients are calculated, artificial intelligence models are used to predict wastewater levels, and multi-stage treatment is carried out in the wastewater treatment pond. This solves the problem of existing technologies failing to monitor wastewater before discharge, realizes real-time monitoring and treatment of wastewater, and reduces pollution to water resources.
Patent Information
- Application Number
- CN202411467718.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies fail to monitor wastewater in drainage networks before discharge, which may result in wastewater failing to meet discharge standards and polluting water resources and the environment.
By setting up sensors at key nodes of the park's drainage network, a distributed sensor network is constructed to collect real-time data, calculate pollution coefficients, use artificial intelligence models to predict wastewater levels, and carry out multi-stage treatment in wastewater treatment ponds to ensure that wastewater meets discharge standards before being discharged.
It enables real-time monitoring and treatment of sewage in the drainage network, ensuring that sewage meets discharge standards, reducing pollution to the park's water resources, and protecting the ecological environment.
Smart Images

Figure CN118982215A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of drainage pipe monitoring, relates to a monitoring and control technology for a park drainage pipe network, and specifically is a monitoring and control system for a park drainage pipe network. Background Art
[0002] The park drainage network is an important part of the urban infrastructure, responsible for collecting, transporting and treating rainwater, sewage and other wastewater in the park; it is usually composed of a series of pipelines, pumping stations, inspection wells, valves and other facilities to form a complete drainage system; by real-time monitoring of the status of the drainage network, abnormal conditions of the network, such as blockage, leakage, etc., can be discovered in time, so that countermeasures can be taken quickly, avoiding human negligence or delays that may occur in traditional inspection methods, and improving the management efficiency of the network; the monitoring and control system can collect and analyze network operation data in real time, such as flow, pressure, water level, etc.; through the analysis of these data, the operation parameters of the network can be optimized; by monitoring the water quality parameters in the drainage network, water quality abnormalities can be discovered in time, and pollutants can be prevented from being discharged in excess of the standard, which helps to protect the water environment in the park and prevent water pollution from posing a potential threat to the ecological environment and residents' health.
[0003] The prior art (the invention patent application with publication number CN112923981A) discloses an intelligent detection system for a drainage network, which includes a monitoring center, a cloud server, an intelligent terminal and multiple data detection devices, wherein the cloud server is respectively connected to the monitoring center, the intelligent terminal and the multiple data acquisition detection devices, and the data detection device includes a sensor device and a centralized controller, wherein the centralized controller is respectively connected to the sensor device and the cloud server. By real-time monitoring of the data of the drainage pipe and even the sewage outlet, it is possible to monitor whether there is rainwater and sewage confluence and whether the sewage factory discharges sewage illegally without permission; however, the prior art monitors the drainage pipe outlet and the sewage pipe outlet to analyze whether there is rainwater and sewage confluence and whether the factory discharges sewage illegally without permission, but does not consider monitoring the sewage in the drainage network before discharge, resulting in the discharged sewage possibly not meeting the discharge standards, thereby polluting the water resources environment.
[0004] The present invention provides a monitoring and control system for a park drainage network to solve the above technical problems. Summary of the invention
[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a monitoring and control system for a park drainage network, which is used to solve the technical problem that the prior art does not consider monitoring the sewage in the drainage network before discharge, resulting in the discharged sewage may not meet the discharge standards and pollute the water resources environment.
[0006] To achieve the above-mentioned object, the first aspect of the present invention provides a monitoring and control system for a park drainage network, comprising: a monitoring and analysis module, and a data acquisition module and a terminal control module connected thereto; Data acquisition module: obtain the topology of the drainage network in the park, and build a distributed sensor network based on the topology; collect real-time data of key nodes in the drainage network through the distributed sensor network, pre-process the real-time data, encrypt it and store it in the data center; the real-time data includes real-time flow, real-time pollution and real-time water level; Monitoring and analysis module: Calculate the pollution coefficient of key nodes based on real-time data, and judge whether the sewage at key nodes meets the discharge standard according to the pollution coefficient; if yes, predict the pollution level after the sewage at all key nodes is collected; if no, generate a sewage treatment signal; judge whether the pollution level after the sewage is collected is low; if yes, generate a discharge treatment signal; if no, generate a sewage treatment signal; and, Treat the sewage in the sewage treatment pool; test the treated sewage to obtain test data, and determine whether the sewage can be discharged based on the test data; if yes, generate a drainage treatment signal to discharge the sewage; if no, treat the sewage again; Terminal control module: Open the sewage treatment valve based on the sewage treatment signal to allow the sewage in the drainage network to flow to the sewage treatment pool; open the drainage treatment valve according to the drainage treatment signal to discharge the treated sewage that meets the standards.
[0007] Preferably, the step of constructing a distributed sensor network according to the topology graph includes: Retrieve the topological map of the drainage network, obtain the key nodes in the drainage network from the topological map, set sensors at the key nodes and test the performance of the sensors. When the sensors cannot be used normally, replace the corresponding sensors; the key nodes include confluence wells, rainwater wells and pumping stations; A communication network is set up between each sensor, and the communication network between the sensors is tested to determine whether the communication network between the sensors is normal; if yes, the communication network between the sensors is continuously monitored; if not, the communication network is reset.
[0008] It should be noted that setting up a communication network between sensors requires selecting a suitable communication protocol based on the type of sensor and data before establishing a network connection.
[0009] The present invention obtains key nodes in the drainage network according to the topological diagram of the park drainage network, and sets sensors at the key nodes; and tests the performance of the sensors to ensure that the sensors can work normally; a communication network is set up between the sensors, and the network signals are tested, which is conducive to ensuring that the sensor data can be transmitted normally, laying a foundation for subsequent analysis.
[0010] Preferably, the pre-processing of the real-time data and then encrypting and storing it in the data center includes: Retrieve real-time data and determine whether the real-time data contains all sub-data; if yes, encrypt and store the real-time data; if no, manually supplement the real-time data and encrypt and store the supplemented real-time data; An encryption algorithm is randomly selected from an encryption algorithm database to encrypt the preprocessed real-time data, and the encrypted real-time data is stored in a data center; wherein the encryption algorithm database is constructed according to the existing encryption algorithm.
[0011] It should be noted that the sub-data including real-time flow, real-time pollution or real-time water level sub-data are used to detect the integrity of real-time data. When the real-time data is incomplete, it needs to be supplemented manually.
[0012] The present invention judges the integrity of real-time data. When the real-time data does not contain all sub-data, the real-time data is supplemented manually, which is conducive to ensuring the integrity of the real-time data; the real-time data is encrypted using a random encryption algorithm to ensure the security of the real-time data; the encrypted real-time data is stored in a data center, which is conducive to facilitating the management of the real-time data.
[0013] Preferably, the calculation of the pollution coefficient of the key node based on the real-time data includes: Retrieve the real-time data of key nodes, and mark the real-time flow, real-time pollution degree and real-time water level in the real-time data as SL, SW and SS respectively; The pollution coefficient of the key node is calculated by the formula WX=α×(SL×SW) / SS^2; where α is a proportional coefficient greater than 0.
[0014] The present invention calculates the pollution coefficient of key nodes according to real-time data, can conduct comprehensive analysis on the real-time data, and is conducive to laying a foundation for subsequent judgment.
[0015] Preferably, judging whether the sewage at the key node meets the discharge standard according to the pollution coefficient includes: The pollution coefficient of the key node is retrieved to determine whether the pollution coefficient is less than the set pollution threshold; if so, it is determined that the sewage at the key node meets the discharge standard; if not, it is determined that the sewage at the key node does not meet the discharge standard and a sewage treatment signal is generated.
[0016] The present invention determines whether the pollution coefficient of the key node is less than the set pollution threshold. When the pollution coefficient is less than the set pollution threshold, it is determined that the sewage of the key node meets the discharge standard, which is beneficial to reducing pollution in the park.
[0017] Preferably, the prediction of the pollution level after sewage from all key nodes is collected includes: Retrieve real-time data and pollution coefficients of key nodes; integrate real-time data and pollution coefficients into a prediction array, and integrate all prediction arrays into a pollution prediction sequence; Retrieve the pollution prediction model, input the pollution prediction sequence into the pollution prediction model, obtain the corresponding prediction data, and analyze the pollution level of the sewage based on the prediction data; wherein, the pollution prediction model is constructed based on the artificial intelligence model; the prediction data includes the predicted pollution degree and the predicted pollution coefficient.
[0018] The present invention integrates the real-time data of key nodes and the pollution coefficient into a prediction array, integrates all the prediction data into a pollution prediction sequence, and uses a pollution prediction model to analyze the pollution prediction sequence, which is conducive to making the prediction result more accurate.
[0019] Preferably, the analysis of the pollution level of sewage based on the predicted data includes: Retrieve the prediction data, and mark the predicted pollution degree and predicted pollution coefficient in the prediction data as YWD and YWX respectively; calculate the sewage grade coefficient by the formula DX=β×ln(YWD)+γ×YWX; where β and γ are proportional coefficients greater than 0; When the sewage grade coefficient is less than the first-level threshold, the sewage pollution level is marked as low; when the sewage grade coefficient is not less than the first-level threshold and less than the second-level threshold, the sewage pollution level is marked as medium; when the sewage grade coefficient is not less than the second-level threshold, the sewage pollution level is marked as high.
[0020] It should be noted that the first-level threshold and the second-level threshold are set artificially based on experience, and the first-level threshold is lower than the second-level threshold; when the pollution level is low, it means that the sewage has reached the discharge standard; then there is no need to treat the sewage and it can be discharged directly.
[0021] The present invention calculates the grade coefficient of sewage according to the predicted pollution degree and the predicted pollution coefficient in the predicted data, and determines the pollution grade of sewage according to the grade coefficient of sewage; when the pollution grade is low, the sewage can be directly discharged, which is beneficial to reduce the pollution in the park and protect the water resource environment in the park.
[0022] Preferably, the pollution prediction model is constructed based on an artificial intelligence model, including: Acquire standard training data; wherein the standard training data includes standard output data consistent with the content attributes of the pollution prediction sequence and standard output data consistent with the content attributes of the prediction data; The artificial intelligence model is trained using standard training data, and the trained artificial intelligence model is marked as a pollution prediction model; wherein the artificial intelligence model includes a convolutional neural network model or a long short-term memory neural network model.
[0023] It should be noted that after the artificial intelligence training is completed, the accuracy of the artificial intelligence needs to be verified. The artificial intelligence is verified using verification data. When the accuracy is greater than the accuracy threshold, the artificial intelligence model is marked as a pollution prediction model. Otherwise, the artificial intelligence model is corrected or retrained.
[0024] Preferably, the treatment of sewage in the sewage treatment pool comprises: S1: Preliminary screening of sewage to remove particulate matter and grease in sewage; Screen deslagging, grit chamber, chlorination precipitation and activated carbon adsorption treatment of sewage to remove suspended matter and heavy metals in sewage; S2: discharge sewage to the regulating tank, adjust the amount and quality of sewage, and control the speed of water flow and the height of water level; S3: Treat sewage through biological treatment methods; use the metabolism of microorganisms to decompose organic matter in sewage into simple inorganic substances; biological treatment methods include activated sludge method, anaerobic fermentation and anaerobic ammonia oxidation; simple inorganic substances include carbon dioxide and ammonia; S4: Deeply treat sewage to remove non-degradable organic matter and nutrients; and treat sludge generated during sewage treatment. Deep treatment methods include biofilters and ultraviolet disinfection; sludge treatment methods include digestion, dehydration, drying and incineration.
[0025] Preferably, judging whether the sewage can be discharged according to the detection data includes: Retrieve the test data and determine whether all sub-data in the test data are less than the corresponding discharge threshold. If yes, it is determined that the sewage can be discharged and a discharge treatment signal is generated; if not, it is determined that the sewage cannot be discharged and the sewage is treated again.
[0026] It should be noted that the test data includes organic matter content, heavy metal content, suspended matter content and oil content. The emission threshold is determined according to the data type of the test data, and the emission threshold is set according to the emission standard.
[0027] The present invention detects the treated sewage, determines whether the sewage meets the discharge standard according to the detection data, and re-treats the sewage that does not meet the discharge standard, so that the sewage can be discharged after meeting the standard, which is beneficial to reducing the pollution to water resources.
[0028] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention obtains key nodes in the drainage network according to the topological diagram of the park drainage network, and sets sensors at the key nodes; and tests the performance of the sensors to ensure that the sensors can work normally; sets a communication network between the sensors, and tests the network signals, which is conducive to ensuring that the data of the sensors can be transmitted normally; collects real-time data of key nodes through a distributed sensor network, and judges the integrity of the real-time data. When the real-time data does not contain all sub-data, the real-time data is supplemented manually, which is conducive to ensuring the integrity of the real-time data; encrypts the real-time data using a random encryption algorithm to ensure the security of the real-time data; stores the encrypted real-time data in a data center, which is conducive to facilitating the management of real-time data; calculates the pollution coefficient of the key node according to the real-time data, and when the pollution coefficient is less than the set pollution threshold, it is determined that the sewage at the key node meets the discharge standard, which is conducive to reducing pollution in the park.
[0029] 2. The present invention integrates the real-time data of key nodes and the pollution coefficient into a prediction array, integrates all the prediction data into a pollution prediction sequence, and uses a pollution prediction model to analyze the pollution prediction sequence, which is conducive to making the prediction result more accurate; the grade coefficient of the sewage is calculated according to the predicted pollution degree and the predicted pollution coefficient in the prediction data, and the pollution grade of the sewage is determined according to the grade coefficient of the sewage; when the pollution grade is low, the sewage can be directly discharged, which is conducive to reducing the pollution in the park and protecting the water resources environment in the park; the sewage in the sewage treatment pool is treated, and the treated sewage is tested to obtain test data, and it is judged whether the sewage meets the discharge standard according to the test data, and the sewage that does not meet the discharge standard is re-treated, so that the sewage can be discharged after meeting the standard, which is conducive to reducing the pollution of water resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.
[0031] Figure 1 It is a schematic diagram of the overall framework structure of the present invention; Figure 2 A schematic diagram of the process steps of the present invention; Figure 3 A schematic diagram of specific steps for collecting real-time data according to the present invention; Figure 4It is a schematic diagram of the steps of monitoring sewage in the drainage network according to the present invention; Figure 5 It is a schematic diagram of the steps of treating and detecting sewage according to the present invention. DETAILED DESCRIPTION
[0032] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0033] See also Figure 1-Figure 2 , the first aspect of the present invention provides a monitoring and control system for a park drainage network, including: a monitoring and analysis module, and a data acquisition module and a terminal control module connected thereto; Data acquisition module: obtain the topology of the drainage network in the park, and build a distributed sensor network based on the topology; collect real-time data of key nodes in the drainage network through the distributed sensor network, pre-process the real-time data, encrypt it and store it in the data center; the real-time data includes real-time flow, real-time pollution and real-time water level; Monitoring and analysis module: Calculate the pollution coefficient of key nodes based on real-time data, and judge whether the sewage at key nodes meets the discharge standard according to the pollution coefficient; if yes, predict the pollution level after the sewage at all key nodes is collected; if no, generate a sewage treatment signal; judge whether the pollution level after the sewage is collected is low; if yes, generate a discharge treatment signal; if no, generate a sewage treatment signal; and, Treat the sewage in the sewage treatment pool; test the treated sewage to obtain test data, and determine whether the sewage can be discharged based on the test data; if yes, generate a drainage treatment signal to discharge the sewage; if no, treat the sewage again; Terminal control module: Open the sewage treatment valve based on the sewage treatment signal to allow the sewage in the drainage network to flow to the sewage treatment pool; open the drainage treatment valve according to the drainage treatment signal to discharge the treated sewage that meets the standards.
[0034] See also Figure 3, obtain the topological map of the drainage network of the park, obtain the key nodes in the drainage network from the topological map, set sensors at the key nodes and test the performance of the sensors. When the sensors cannot be used normally, replace the corresponding sensors; set up a communication network between the sensors, test the communication network between the sensors, and determine whether the communication network between the sensors is normal; if yes, continue to monitor the communication network between the sensors; if no, reset the communication network; collect real-time data of key nodes in the drainage network through the distributed sensor network, and determine whether the real-time data contains all sub-data; if yes, encrypt and store the real-time data; if no, manually supplement the real-time data, and encrypt and store the supplemented real-time data; randomly select an encryption algorithm from the encryption algorithm database to encrypt the pre-processed real-time data, and store the encrypted real-time data in the data center.
[0035] For example: suppose that key nodes A, B and C are obtained in the topology diagram of the drainage network; sensors are respectively set at key nodes A, B and C; the sensor performance is tested and it is found that the sensor of key node B cannot be used normally. After replacing the sensor of key node B, it can be used normally.
[0036] A communication network is set up between each sensor, and the communication network is tested. It is found that the communication network between the sensors of key node A and key node C cannot communicate normally. Then, the communication network between the sensors of key node A and key node C is reset so that normal communication can be achieved.
[0037] The real-time data of key nodes A, B and C are collected through sensors. It is found that the real-time water level is missing in the real-time data of key node C. Then the real-time water level data of key node C is supplemented artificially; the encryption algorithm G is randomly selected from the encryption algorithm library to encrypt the real-time data and then stored in the data center.
[0038] See also Figure 4 , retrieve the real-time data of the key nodes, mark the real-time flow, real-time pollution degree and real-time water level in the real-time data as SL, SW and SS respectively; calculate the pollution coefficient of the key node by the formula WX=α×(SL×SW) / SS^2; where α is a proportional coefficient greater than 0; judge whether the pollution coefficient is less than the set pollution threshold; if yes, it is determined that the sewage at the key node meets the discharge standard; if not, it is determined that the sewage at the key node does not meet the discharge standard, and a sewage treatment signal is generated.
[0039] For example, suppose real-time data of key nodes A, B, and C are collected, and α=0.5; the three sets of data obtained by analysis are as follows: The first set of data: the real-time flow rate of key node A SL=34; the real-time pollution degree SW=23; the real-time water level SS=3; then the pollution coefficient WX=43.44; The second set of data: the real-time flow rate of key node B SL=24; the real-time pollution degree SW=12; the real-time water level SS=2; then the pollution coefficient WX=36; The third set of data: the real-time flow rate of key node C SL=18; the real-time pollution degree SW=28; the real-time water level SS=4; then the pollution coefficient WX=15.75; If the pollution threshold is set to 37, the sewage from key node A cannot be discharged. The sewage treatment valve of key node A is opened to discharge the sewage from key node A into the sewage treatment pool. The sewage from key nodes B and C meets the discharge standard, and the pollution of the sewage collected by key nodes B and C is predicted.
[0040] Integrate real-time data and pollution coefficient into a prediction array, and integrate all prediction arrays into a pollution prediction sequence; call the pollution prediction model, input the pollution prediction sequence into the pollution prediction model, and obtain the corresponding prediction data; mark the predicted pollution degree and predicted pollution coefficient in the prediction data as YWD and YWX respectively; calculate the grade coefficient of sewage by the formula DX=β×ln(YWD)+γ×YWX; wherein β and γ are proportional coefficients greater than 0; when the grade coefficient of sewage is less than the first threshold, the pollution grade of sewage is marked as low; when the grade coefficient of sewage is not less than the first threshold and less than the second threshold, the pollution grade of sewage is marked as medium; when the grade coefficient of sewage is not less than the second threshold, the pollution grade of sewage is marked as high; judge whether the pollution grade of sewage after collection is low; if yes, generate a discharge treatment signal; if not, generate a sewage treatment signal; open the sewage treatment valve based on the sewage treatment signal to allow the sewage in the drainage network to flow to the sewage treatment pool.
[0041] It should be noted that the pollution prediction model is built based on the artificial intelligence model. The specific steps are as follows: Acquire standard training data; wherein the standard training data includes standard output data consistent with the content attributes of the pollution prediction sequence and standard output data consistent with the content attributes of the prediction data; Using standard training data to train an artificial intelligence model, and marking the trained artificial intelligence model as a pollution prediction model; wherein the artificial intelligence model includes a convolutional neural network model or a long short-term memory neural network model; Obtain verification data and use the verification data to verify the trained artificial intelligence model to obtain the accuracy of the artificial intelligence model. When the accuracy of the artificial intelligence model is greater than the accuracy threshold, the artificial intelligence model is marked as a pollution prediction model; otherwise, rebuild the artificial intelligence model or correct the artificial intelligence model.
[0042] For example, suppose the sewage collected by key nodes B and C is predicted; β=10, γ=0.5, and the predicted data is as follows: The predicted pollution degree YWD=56, the predicted pollution coefficient YWX=76; the calculated sewage grade coefficient DX=78.25; the sewage grade coefficient is compared with the first-level threshold 20 and the second-level threshold 40, and the sewage grade is high, so the sewage treatment valves at the key nodes B and C are opened to allow the sewage to flow into the sewage treatment pool.
[0043] See also Figure 5 , conduct preliminary screening treatment on sewage to remove particulate matter and grease in sewage; conduct screen deslagging, grit chamber, chlorination precipitation and activated carbon adsorption treatment on sewage to remove suspended matter and heavy metals in sewage; discharge sewage to regulating tank to adjust the water volume and water quality of sewage, and control the speed of water flow and the height of water level; treat sewage through biological treatment methods; utilize the metabolism of microorganisms to decompose organic matter in sewage into simple inorganic matter; conduct deep treatment on sewage to remove difficult-to-degrade organic matter and nutrients; and treat the sludge generated during sewage treatment.
[0044] The treated sewage is tested to obtain test data, and it is determined whether all sub-data in the test data are less than the corresponding discharge threshold value. If so, it is determined that the sewage can be discharged and a discharge treatment signal is generated; if not, it is determined that the sewage cannot be discharged and the sewage is treated again; the drainage treatment valve is opened according to the drainage treatment signal to discharge the treated sewage that meets the standards.
[0045] For example, suppose that the treated sewage is tested to obtain test data; if the heavy metal content in the test data is greater than the set discharge threshold, the sewage is treated again; After deep treatment, the sewage is retested to obtain test data; the test data is analyzed and it is found that all sub-data in the test data are less than the corresponding discharge threshold, then the drainage treatment valve is opened to discharge the treated sewage.
[0046] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.
[0047] The working principle of the present invention is as follows: the present invention obtains a topological map of a drainage network in a park, and constructs a distributed sensor network according to the topological map; collects real-time data of key nodes in the drainage network through the distributed sensor network, and encrypts and stores the real-time data after preprocessing in a data center; calculates the pollution coefficient of the key nodes based on the real-time data, and judges whether the sewage of the key nodes meets the discharge standard according to the pollution coefficient; if yes, predicts the pollution level of the sewage after all key nodes are collected; if not, generates a sewage treatment signal; judges whether the pollution level after the sewage is collected is low; if yes, generates a discharge treatment signal; if not, generates a sewage treatment signal; treats the sewage in the sewage treatment pool; detects the treated sewage to obtain detection data, and judges whether the sewage can be discharged according to the detection data; if yes, generates a drainage treatment signal, and discharges the sewage; if not, re-treats the sewage; opens the sewage treatment valve based on the sewage treatment signal, so that the sewage in the drainage network flows to the sewage treatment pool; opens the drainage treatment valve according to the drainage treatment signal, and discharges the sewage that meets the standards after treatment.
[0048] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. A monitoring and control system for a park drainage network, comprising: Monitoring and analysis module, and the data acquisition module and terminal control module connected thereto; characterized in that: Data acquisition module: obtain the topology of the drainage network in the park, and build a distributed sensor network based on the topology; collect real-time data of key nodes in the drainage network through the distributed sensor network, pre-process the real-time data, encrypt it and store it in the data center; the real-time data includes real-time flow, real-time pollution and real-time water level; Monitoring and analysis module: Calculate the pollution coefficient of key nodes based on real-time data, and judge whether the sewage at key nodes meets the discharge standard according to the pollution coefficient; if yes, predict the pollution level after the sewage at all key nodes is collected; if no, generate a sewage treatment signal; judge whether the pollution level after the sewage is collected is low; if yes, generate a discharge treatment signal; if no, generate a sewage treatment signal; and, Treat the sewage in the sewage treatment pool; test the treated sewage to obtain test data, and determine whether the sewage can be discharged based on the test data; if yes, generate a drainage treatment signal to discharge the sewage; if no, treat the sewage again; Terminal control module: Open the sewage treatment valve based on the sewage treatment signal to allow the sewage in the drainage network to flow to the sewage treatment pool; open the drainage treatment valve according to the drainage treatment signal to discharge the treated sewage that meets the standards.
2. A monitoring and control system for a park drainage network according to claim 1, characterized in that: The step of constructing a distributed sensor network according to the topology graph includes: Retrieve the topological map of the drainage network, obtain the key nodes in the drainage network from the topological map, set sensors at the key nodes and test the performance of the sensors. When the sensors cannot be used normally, replace the corresponding sensors; the key nodes include confluence wells, rainwater wells and pumping stations; A communication network is set up between each sensor, and the communication network between the sensors is tested to determine whether the communication network between the sensors is normal; if yes, the communication network between the sensors is continuously monitored; if not, the communication network is reset.
3. A monitoring and control system for a park drainage network according to claim 1, characterized in that: The real-time data is pre-processed, encrypted and stored in the data center, including: Retrieve real-time data and determine whether the real-time data contains all sub-data; if yes, encrypt and store the real-time data; if no, manually supplement the real-time data and encrypt and store the supplemented real-time data; An encryption algorithm is randomly selected from an encryption algorithm database to encrypt the preprocessed real-time data, and the encrypted real-time data is stored in a data center; wherein the encryption algorithm database is constructed according to the existing encryption algorithm.
4. A monitoring and control system for a park drainage network according to claim 1, characterized in that: The calculation of the pollution coefficient of the key node based on the real-time data includes: Retrieve the real-time data of key nodes, and mark the real-time flow, real-time pollution degree and real-time water level in the real-time data as SL, SW and SS respectively; The pollution coefficient of the key node is calculated by the formula WX=α×(SL×SW) / SS^2; where α is a proportional coefficient greater than 0.
5. A monitoring and control system for a park drainage network according to claim 4, characterized in that: The method of judging whether the sewage at the key nodes meets the discharge standard according to the pollution coefficient includes: The pollution coefficient of the key node is retrieved to determine whether the pollution coefficient is less than the set pollution threshold; if so, it is determined that the sewage at the key node meets the discharge standard; if not, it is determined that the sewage at the key node does not meet the discharge standard and a sewage treatment signal is generated.
6. A monitoring and control system for a park drainage network according to claim 1, characterized in that: The pollution level prediction after sewage collection at all key nodes includes: Retrieve real-time data and pollution coefficients of key nodes; integrate real-time data and pollution coefficients into a prediction array, and integrate all prediction arrays into a pollution prediction sequence; Retrieve the pollution prediction model, input the pollution prediction sequence into the pollution prediction model, obtain the corresponding prediction data, and analyze the pollution level of the sewage based on the prediction data; wherein, the pollution prediction model is constructed based on the artificial intelligence model; the prediction data includes the predicted pollution degree and the predicted pollution coefficient.
7. A monitoring and control system for a park drainage network according to claim 6, characterized in that: The analysis of the pollution level of sewage based on the prediction data includes: Retrieve the prediction data, and mark the predicted pollution degree and predicted pollution coefficient in the prediction data as YWD and YWX respectively; calculate the sewage grade coefficient by the formula DX=β×ln(YWD)+γ×YWX; where β and γ are proportional coefficients greater than 0; When the sewage grade coefficient is less than the first-level threshold, the sewage pollution level is marked as low; when the sewage grade coefficient is not less than the first-level threshold and less than the second-level threshold, the sewage pollution level is marked as medium; when the sewage grade coefficient is not less than the second-level threshold, the sewage pollution level is marked as high.
8. A monitoring and control system for a park drainage network according to claim 6, characterized in that: The pollution prediction model is constructed based on an artificial intelligence model, including: Acquire standard training data; wherein the standard training data includes standard output data consistent with the content attributes of the pollution prediction sequence and standard output data consistent with the content attributes of the prediction data; The artificial intelligence model is trained using standard training data, and the trained artificial intelligence model is marked as a pollution prediction model; wherein the artificial intelligence model includes a convolutional neural network model or a long short-term memory neural network model.
9. A monitoring and control system for a park drainage network according to claim 1, characterized in that: The treatment of sewage in the sewage treatment pool comprises: S1: Preliminary screening of sewage to remove particulate matter and grease in sewage; Screen deslagging, grit chamber, chlorination precipitation and activated carbon adsorption treatment of sewage to remove suspended matter and heavy metals in sewage; S2: discharge sewage to the regulating tank, adjust the amount and quality of sewage, and control the speed of water flow and the height of water level; S3: Treat sewage through biological treatment methods; use the metabolism of microorganisms to decompose organic matter in sewage into simple inorganic substances; biological treatment methods include activated sludge method, anaerobic fermentation and anaerobic ammonia oxidation; simple inorganic substances include carbon dioxide and ammonia; S4: Deeply treat sewage to remove non-degradable organic matter and nutrients; and treat sludge generated during sewage treatment. Deep treatment methods include biofilters and ultraviolet disinfection; sludge treatment methods include digestion, dehydration, drying and incineration.
10. A monitoring and control system for a park drainage network according to claim 9, characterized in that: The step of judging whether the sewage can be discharged according to the detection data includes: Retrieve the test data and determine whether all sub-data in the test data are less than the corresponding discharge threshold. If yes, it is determined that the sewage can be discharged and a discharge treatment signal is generated; if not, it is determined that the sewage cannot be discharged and the sewage is treated again.
Citation Information
Patent Citations
Rain sewage pipe network traceability tracking system and method
CN114444259A
Method for positioning pollutant concentration area of sewage pipe network
CN116735824A
Sewage discharge control method and system
CN116815900A
Distributed hydrological information management platform
CN118153864A
Sewage discharge alarm method, device and equipment of drainage well and medium
CN118430197A
Cited By
Sewage management method and system for digital printing and dyeing
CN119168331A
