Intelligent water affair dynamic monitoring and collaborative purification system

Abstract

The invention discloses an intelligent water affair dynamic monitoring and collaborative purification system, and relates to the field of urban water supply pipe networks, and the system comprises a multi-node monitoring network which collects water quality parameters in a water supply pipe network in a distributed manner and transmits data; the hydraulic drive energy supply device converts kinetic energy of fluid in the pipeline into electric energy to supply power to related equipment; the edge processing device is used for executing dynamic balance scheduling of local flow and pressure on the basis of real-time monitoring data and a hydraulic model; and the remote service platform is used for fusing and correcting the converged data, predicting a water quality change trend based on a time sequence model, generating a global optimization scheduling scheme according to a target set by a user, encrypting and issuing the global optimization scheduling scheme to the edge processing device for execution, and storing operation data and operation records of the whole process in an anti-tampering manner. The rapid response capability of the water supply network under the abnormal condition is effectively improved, and the self-adaptive configuration efficiency of monitoring resources and the safety and credibility level of the operation process are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of urban water supply networks, and more specifically to a smart water dynamic monitoring and collaborative purification system. Background Technology

[0002] Urban water supply networks are core infrastructure for ensuring residents' lives and the operation of cities. Real-time perception and intelligent control of their operational status are key issues in the field of smart water management.

[0003] In existing technologies, the deployment of monitoring nodes is usually based on fixed spacing or experience, lacking a detailed consideration of the functional importance and risk differences of different areas of the pipeline network. For example, key locations such as water source inlets and pipeline ends often use the same monitoring density as ordinary water transmission trunk lines, resulting in insufficient monitoring in key areas or redundant resources in ordinary areas. More importantly, this deployment mode is static and cannot be adaptively adjusted according to dynamic risk factors such as real-time changes in pipeline water quality and areas with frequent historical accidents. This makes the monitoring network susceptible to blind spots or delayed responses when facing local water quality deterioration or sudden pollution events.

[0004] In terms of continuous operation and rapid response of monitoring systems, traditional monitoring equipment relies on mains power or regularly replaced batteries, which are prone to failure when power outages occur due to disasters such as floods and earthquakes, causing the monitoring network to collapse. At the same time, the handling of abnormal events is highly dependent on the analysis and command issuance of the cloud center, and the data round-trip transmission delay is large, making it difficult to meet the timeliness requirements of scenarios that urgently need local rapid intervention, such as pipeline pressure imbalance. This centralized decision-making mode is particularly vulnerable when the network is interrupted and cannot form effective edge autonomy capabilities.

[0005] Furthermore, the existing system has relatively weak data management and decision-making traceability capabilities. Key information such as monitoring data, control instructions, and scheduling plans are usually stored in a central database, which is at risk of being tampered with or lost. In the event of a water quality safety incident, it is difficult to conduct clear and reliable responsibility tracing and event review. Control strategies are often based on preset fixed thresholds and lack the ability to dynamically optimize scheduling by combining multiple objectives such as real-time water quality, flow, and energy consumption. Moreover, the scheduling process lacks tamper-proof evidence records, which is not conducive to the auditing and optimization of the operation process.

[0006] Therefore, how to design a smart water dynamic monitoring and collaborative purification system to comprehensively improve the safety resilience, operational efficiency and management reliability of the water supply network is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] In view of this, the present invention provides a smart water dynamic monitoring and collaborative purification system, which aims to solve the problems existing in the current water system, such as monitoring blind spots and reliance on power supply, fixed and insufficient monitoring density, single control strategy and lack of reliable traceability of data management. It aims to achieve real-time, accurate and flexible monitoring of the operation status of urban water supply network, and to respond quickly to various abnormal and disaster events while ensuring water quality safety. It also ensures that all operation processes are auditable and traceable, thereby improving the overall safety and operational resilience of urban water supply infrastructure.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: A smart water dynamic monitoring and collaborative purification system includes: A multi-node monitoring network is used to collect water quality parameters and transmit data in a distributed manner within a water supply network. A hydraulically driven power supply device is connected to a multi-node monitoring network to convert the kinetic energy of the fluid in the pipeline into electrical energy and to power the multi-node monitoring network and other front-end equipment. The edge processing device is communicatively connected to a multi-node monitoring network and a hydraulically driven power supply device. It is used to perform dynamic equalization scheduling of local flow and pressure based on real-time monitoring data and hydraulic models when water quality abnormalities or pipeline pressure imbalances are detected. The remote service platform is connected to the edge processing device and the multi-node monitoring network. It is used to fuse and correct the aggregated data, predict water quality change trends based on time series models, generate a global optimization scheduling scheme according to user-defined goals and encrypt and send it to the edge processing device for execution, and store the entire process operation data and operation records in a tamper-proof manner.

[0009] Preferably, the node deployment of the multi-node monitoring network is configured differently based on the monitoring demand level of the pipeline network, including: Assign functional attribute labels to different locations in the pipeline network. The functional attribute labels include at least: key water supply nodes K, water quality sensitive area nodes S, conventional water transmission and distribution nodes N, and dense user access points U. A basic deployment density value is preset for each type of functional attribute tag. , label∈{K,S,U,N}, and satisfy: > > > ; Based on the aforementioned basic deployment density value In conjunction with the actual constraints of the pipeline network topology, the initial deployment locations of monitoring nodes are determined on the pipeline segments with corresponding functional attributes.

[0010] Preferably, the hydraulically driven power supply device includes an energy conversion component and an energy management circuit; The energy conversion component employs piezoelectric elements or electromagnetic induction coils, arranged in a ring or symmetrical manner along the inner wall of the pipe. The angle between its energy collection sensitive direction and the water flow direction within the pipe is... Set to 15°≤ ≤45°; The energy management circuit includes an overvoltage protection unit, an energy storage unit, and an energy storage switching unit. When the voltage of the energy storage unit... Below the threshold When the energy storage switching unit automatically switches the power supply to the backup power supply; when the voltage of the energy storage unit... Restored to above the threshold At that time, switch back to hydraulic power supply mode.

[0011] Preferably, the edge processing device performs dynamic load balancing scheduling, including: Upon receiving an abnormal alarm or remote command, the shutdown priority of each node is calculated based on the real-time pipeline topology and hydraulic model; the priority P is:

[0012] in, This is the standardized value of the node's historical average water consumption. This is the standardized value of the pipeline distance from this node to the water source. α, β, and γ are the historical stability coefficients of the node devices, and α, β, and γ are the weighting coefficients. Nodes are shut down in order of priority from low to high until the number of shut-down nodes reaches the total number of nodes in the pipeline network. Stop when the time comes. Preferably, if the node to be shut down belongs to the category of water supply critical node K or water quality sensitive area node S, the shutdown operation can only be performed after waiting for a secondary confirmation instruction from the remote service platform.

[0013] Preferably, the remote service platform includes: The data processing module is used to perform spatiotemporal alignment, outlier removal, and sensor bias correction on multi-source monitoring data. The predictive analytics module employs a time-series forecasting model based on a sliding time window, with near-term forecasts... Using historical data from the past few hours as input, predict the future. The trend of key water quality parameters within an hour, and the confidence level when the predicted result exceeds the safety threshold. Higher than the preset threshold When this happens, an alert is triggered; The optimization scheduling module adopts an adaptive optimization algorithm, taking user-defined target water quality, energy consumption cost and response delay as constraints, to generate an optimization scheme including pump power adjustment range, chemical dosage adjustment and standby treatment unit start and stop. The record storage module uses a chained data structure based on a hash function to store operation records with timestamps, device numbers, and parameter hash values, for tamper-proof evidence storage and third-party auditing.

[0014] Preferably, the predictive analysis module also dynamically optimizes and adjusts the node deployment locations of the multi-node monitoring network, including: Continuously assess the water quality stability of each pipe section and calculate the dynamic risk coefficient. :

[0015] Where j represents the pipe section number, This represents the coefficient of variation of the core water quality parameters for this pipe section over the most recent hour. and These represent the mean and standard deviation of the coefficient of variation for the corresponding parameters. This refers to the frequency of water quality parameters exceeding standards in this pipeline section over the past 24 hours. This is the highest frequency of exceeding the limit within the system. The indicators of whether the pipe section is located in a historically high-risk area are w1, w2, and w3, which are weighting coefficients. Set a high-risk threshold With low risk threshold ; When a certain section of the pipe Continue to exceed Reaching the preset duration At that time, the remote service platform generates a dynamic density enhancement command, which, between the nodes at both ends of the pipeline segment, increases the basic deployment density value compared to the original functional attribute label. Higher temporary density value Add multiple temporary monitoring nodes; When a certain section of the pipe Persistently below Reaching the preset duration At that time, the remote service platform generates an optimization and removal command to remove non-critical monitoring nodes within the pipeline section, restoring their deployment density to near [a certain level]. The level.

[0016] Preferably, in the optimized scheduling module, the reward function R of the adaptive optimization algorithm is designed as follows:

[0017] in, To achieve the water quality compliance rate, For energy consumption costs, Let be the system response delay, and a, b, and c be the weighting coefficients.

[0018] As can be seen from the above technical solution, compared with the prior art, the technical solution of the present invention has the following beneficial effects: 1. This system integrates data acquisition, self-sufficient power supply, edge intelligence and cloud analysis. The edge processing device can quickly respond to anomalies based on the local hydraulic model and perform preliminary scheduling such as pressure balancing. The remote service platform performs global data fusion, trend prediction and optimization scheme generation. It effectively shortens the overall response link from anomaly perception to control execution and improves the system's handling efficiency in emergency situations.

[0019] 2. It provides intelligent and flexible monitoring network deployment and adjustment capabilities based on risk perception and functional zoning. During initial deployment, it performs differentiated density configuration based on the importance of the area. During operation, it continuously calculates the dynamic risk coefficient of each pipe section, automatically identifies areas with large water quality fluctuations or high historical risks, and triggers dynamic densification or optimization and merging of monitoring nodes. This enables monitoring resources to adaptively focus on high-risk pipe sections, ensuring the monitoring accuracy of core areas while optimizing the overall network coverage efficiency and operation and maintenance costs.

[0020] 3. The system uses a chain data structure based on hash functions to store all key operations, parameters and execution results through the record storage module of the remote service platform, ensuring that the data is tamper-proof. At the same time, when executing key scheduling commands such as shutdown at the edge, a safety rule requiring secondary confirmation from the remote platform is set for key water supply nodes K or water quality sensitive area nodes S, avoiding the risk of misoperation of automatic control and enhancing the prudence and security of control decisions for important pipeline nodes. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0022] Figure 1 A framework diagram of a smart water dynamic monitoring and collaborative purification system provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the working process of the smart water dynamic monitoring and collaborative purification system provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] like Figure 1 As shown, this embodiment provides a smart water dynamic monitoring and collaborative purification system, including: A multi-node monitoring network is used to collect water quality parameters and transmit data in a distributed manner within a water supply network. A hydraulically driven power supply device is connected to a multi-node monitoring network to convert the kinetic energy of the fluid in the pipeline into electrical energy and to power the multi-node monitoring network and other front-end equipment. The edge processing device is communicatively connected to a multi-node monitoring network and a hydraulically driven power supply device. It is used to perform dynamic equalization scheduling of local flow and pressure based on real-time monitoring data and hydraulic models when water quality abnormalities or pipeline pressure imbalances are detected. The remote service platform is connected to the edge processing device and the multi-node monitoring network. It is used to fuse and correct the aggregated data, predict water quality change trends based on time series models, generate a global optimization scheduling scheme according to user-defined goals and encrypt and send it to the edge processing device for execution, and store the entire process operation data and operation records in a tamper-proof manner.

[0025] By constructing a collaborative system consisting of a multi-node monitoring network, a hydraulic self-powered device, an edge processing device, and a remote service platform, layered intelligent monitoring and dynamic control of the water supply network are achieved. On the one hand, differentiated monitoring deployment is carried out based on the importance of the network area, and the network density is dynamically adjusted in conjunction with real-time risks, so that monitoring resources are precisely focused on high-risk pipe sections, improving coverage efficiency and flexibility. On the other hand, the abnormal response time is shortened by combining edge rapid response with cloud-based global optimization, and the traceability of system decisions and operational security are enhanced by the full-process tamper-proof evidence storage and key operation secondary confirmation mechanism, thereby improving the overall resilience, energy efficiency, and reliable management level of the water supply system.

[0026] The following provides a further detailed description of each component of the above system; The multi-node monitoring network in this embodiment is used to collect water quality parameters and transmit data in a distributed manner within the water supply network. The node deployment of the multi-node monitoring network is configured differently based on the monitoring demand level of the network, including: Assign functional attribute labels to different locations in the pipeline network. The functional attribute labels include at least: key water supply node K, water quality sensitive area node S, conventional water transmission and distribution node N, and dense user access point U. Among them, key water supply node K refers to the direct access point of water source or the intersection of main pipeline network, water quality sensitive area node S refers to the end of pipeline network or area with frequent historical water quality fluctuations, and dense user access point U refers to pipeline network node that connects more than a preset number of user branch pipes. A basic deployment density value is preset for each type of functional attribute tag. , label∈{K,S,U,N}, and satisfy: > > > ; Based on the aforementioned basic deployment density value In conjunction with the actual constraints of the pipeline network topology, the initial deployment locations of monitoring nodes are determined on the pipeline segments with corresponding functional attributes.

[0027] Furthermore, the monitoring nodes in the multi-node monitoring network include a water quality multi-parameter sensor, a microcontroller, and a low-power wireless communication module; the low-power wireless communication module adopts the LoRaWAN or NB-IoT communication protocol; the water quality multi-parameter sensor is used to collect pH value, turbidity, residual chlorine concentration, and conductivity. The node deployment here is not a simple uniform distribution, but a two-layer optimization mechanism that combines differentiated initial configuration based on functional attribute tags with real-time elastic adjustment based on dynamic risk coefficients. This design enables monitoring resources to intelligently focus on key areas such as water source inlets and pipe network ends, as well as real-time high-risk pipe sections, improving the coverage accuracy and operation and maintenance economy of the monitoring network, and realizing the transformation from static deployment to dynamic perception.

[0028] The hydraulically driven power supply device in this embodiment is connected to a multi-node monitoring network to convert the kinetic energy of the fluid in the pipeline into electrical energy and to supply power to the multi-node monitoring network and other front-end devices. Specifically, it includes energy conversion components and energy management circuits; The energy conversion components employ piezoelectric elements or electromagnetic induction coils, arranged in a ring or symmetrical pattern along the inner wall of the pipe. The angle between the energy collection sensing direction and the water flow direction within the pipe is... Set to 15°≤ ≤45°; The energy management circuit includes an overvoltage protection unit, an energy storage unit, and an energy storage switching unit. When the voltage of the energy storage unit... Below the threshold When the energy storage switching unit automatically switches the power supply to the backup power supply; when the voltage of the energy storage unit... Restored to above the threshold When necessary, switch back to hydraulic power supply mode; By optimizing the energy harvesting angle and setting up intelligent charging and discharging management circuits, it effectively overcomes the dependence of conventional monitoring equipment on external power grids or limited batteries. Especially in power outage scenarios caused by disasters, it provides indispensable autonomy for front-end monitoring and control nodes, ensuring the system's basic operational capabilities under extreme conditions.

[0029] The edge processing device in this embodiment is communicatively connected to a multi-node monitoring network and a hydraulic drive power supply device. It is used to perform dynamic equalization scheduling of local flow and pressure based on real-time monitoring data and hydraulic models when water quality abnormalities or pipeline pressure imbalances are detected. Specifically, the dynamic load balancing scheduling performed by the edge processing device includes: Upon receiving an abnormal alarm or remote command, the shutdown priority of each node is calculated based on the real-time pipeline topology and hydraulic model; the priority P is:

[0030] in, This is the standardized value of the node's historical average water consumption. This is the standardized value of the pipeline distance from this node to the water source. α, β, and γ are the historical stability coefficients of the node devices, and α, β, and γ are the weighting coefficients. Nodes are shut down in order of priority from low to high until the number of shut-down nodes reaches the total number of nodes in the pipeline network. When the node shutdown priority is calculated, the node's historical stability coefficient is used. The weighting coefficients α, β, γ are calculated based on the data reporting success rate and self-test failure rate of the monitoring equipment at this node over the past week; these coefficients satisfy: α > β > γ, and α ≥ 0.5. Furthermore, if the node to be shut down belongs to the category of water supply critical node K or water quality sensitive area node S, the shutdown operation can only be performed after waiting for a secondary confirmation instruction from the remote service platform.

[0031] This edge processing device, through its built-in hydraulic model and explicit node shutdown priority algorithm, can autonomously perform preliminary adjustments such as local pressure balancing before cloud commands arrive or when the network is interrupted. At the same time, it adds a security rule for remote secondary confirmation of critical node operations, which improves response speed and local autonomy while embedding important security redundancy design, balancing efficiency and risk.

[0032] The remote service platform in this embodiment includes: The data processing module is used to perform spatiotemporal alignment, outlier removal, and sensor bias correction on multi-source monitoring data. The predictive analytics module employs a time-series forecasting model based on a sliding time window, with near-term forecasts... Using historical data from the past few hours as input, predict the future. The trend of key water quality parameters within an hour, and the confidence level when the predicted result exceeds the safety threshold. Higher than the preset threshold When this happens, an alert is triggered; The optimization scheduling module adopts an adaptive optimization algorithm, taking user-defined target water quality, energy consumption cost and response delay as constraints, to generate an optimization scheme including pump power adjustment range, chemical dosage adjustment and standby treatment unit start and stop. The record storage module uses a chained data structure based on a hash function to store operation records with timestamps, device numbers, and parameter hash values, for tamper-proof evidence storage and third-party auditing. Furthermore, the data processing module is also used to perform data consistency verification: compare the values ​​of specific water quality parameters collected by adjacent monitoring nodes at the same time. If the absolute value of the difference exceeds 20% of the safety threshold of the parameter, the data is marked as pending verification and a remote diagnostic command to the relevant sensor is triggered. Furthermore, the predictive analysis module also dynamically optimizes and adjusts the node deployment locations of the multi-node monitoring network, including: Continuously assess the water quality stability of each pipe section and calculate the dynamic risk coefficient. :

[0033] Where j represents the pipe section number, This represents the coefficient of variation of the core water quality parameters for this pipe section over the most recent hour. and These represent the mean and standard deviation of the coefficient of variation for the corresponding parameters. This refers to the frequency of water quality parameters exceeding standards in this pipeline section over the past 24 hours. This is the highest frequency of exceeding the limit within the system. The indicators of whether the pipe section is located in a historically high-risk area are w1, w2, and w3, which are weighting coefficients. Set a high-risk threshold With low risk threshold ; When a certain section of the pipe Continue to exceed Reaching the preset duration At that time, the remote service platform generates a dynamic density enhancement command, which, between the nodes at both ends of the pipeline segment, increases the basic deployment density value compared to the original functional attribute label. Higher temporary density value Add multiple temporary monitoring nodes; When a certain section of the pipe Persistently below Reaching the preset duration At that time, the remote service platform generates an optimization and removal command to remove non-critical monitoring nodes within the pipeline section, restoring their deployment density to near [a certain level]. The level; Here, the predictive analysis module sets a high-risk threshold that is dynamically optimized and adjusted. With low risk threshold Based on the dynamic risk coefficients of all pipe sections in the same historical period The statistical distribution is dynamically determined, specifically as follows: Take the 80th percentile of this historical dataset. Take the 20th percentile of this historical dataset; Furthermore, in the optimization scheduling module, the reward function R of the adaptive optimization algorithm is designed as follows:

[0034] in, To achieve the water quality compliance rate, For energy consumption costs, Let a, b, and c be the system response delay, and a, b, and c be the weighting coefficients of . The action space of the adaptive optimization algorithm includes: adjusting the pump power by ±ΔP based on the rated power, where 5% ≤ ΔP ≤ 20%; adjusting the reagent dosage by ±ΔD based on the baseline value, where 5% ≤ ΔD ≤ 15%; and switching the start-stop status of the standby purification unit. It not only completes data fusion, correction, and future trend prediction, but also generates scheduling schemes based on global optimization algorithms and drives the dynamic reconstruction of the monitoring network itself. Most importantly, its hash chain-based evidence storage module establishes an immutable record for all operations, which, together with data consistency verification and other mechanisms, constitutes an auditable and traceable process for system operation, realizing closed-loop trusted management from monitoring, analysis, decision-making to execution.

[0035] like Figure 2 As shown below, the specific working process of the smart water dynamic monitoring and collaborative purification system in this embodiment in response to sudden water pollution incidents will be further described in detail below. The specific steps include: 1) Pollution monitoring and alarm; When a sudden intrusion of pollutants (such as chemical leaks) occurs in the water supply network, monitoring nodes deployed at key nodes and sensitive areas will be the first to detect abnormal spikes in water quality parameters (such as specific conductivity and turbidity). The data is transmitted to the system in real time through a self-powered hydraulic device.

[0036] 2) Rapid isolation and initial control at the edge; Upon receiving an alarm indicating that the pollution level has been exceeded, the edge processing device closest to the pollution point immediately activates. Based on the locally stored network topology, it quickly calculates the downstream areas that may be affected by the polluted water mass and, according to a preset priority formula, automatically issues instructions to shut down several non-critical water supply branch nodes in that area, physically isolating the polluted water in a local pipe section and preventing it from spreading further to the entire network.

[0037] 3) Precise source tracing and dynamic deployment in the cloud; The remote service platform receives global data synchronously. Its predictive analysis module combines water flow speed and direction to simulate the diffusion path and concentration changes of pollutants. At the same time, it dynamically calculates the risk coefficient of each pipe section on the diffusion path and immediately dispatches or activates temporary monitoring nodes to high-risk pipe sections to achieve accurate and intensive tracking of the pollution front.

[0038] 4) Collaborative purification and disposal with reliable traceability; Based on the nature and scope of pollutants, the platform's optimization and scheduling module generates collaborative purification plans, such as instructing downstream water treatment plants to adjust reagent dosage and activate backup water sources to flush pipelines. These plans are encrypted and distributed, and are coordinated and executed by edge devices. From the initial detection of pollution to the final restoration of water quality, data and operational results at every stage of the entire process are immutably stored, providing a complete and credible chain of evidence for subsequent event retrospective analysis and liability determination.

[0039] The smart water dynamic monitoring and collaborative purification system provided in this embodiment, through a dual-driven intelligent monitoring network layout, a reliable operating architecture with edge autonomy, and a cloud-based globally optimized collaborative decision-making and traceability mechanism, not only achieves closed-loop handling from anomaly detection, rapid isolation, accurate source tracing to collaborative purification, but also enhances the resilience, efficiency, and reliable management level of the water supply system in response to sudden pollution and other abnormal events through dynamic allocation of monitoring resources and auditable recording of the operation process.

[0040] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0041] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart water dynamic monitoring and collaborative purification system, characterized in that, include: A multi-node monitoring network is used to collect water quality parameters and transmit data in a distributed manner within a water supply network. A hydraulically driven power supply device is connected to a multi-node monitoring network to convert the kinetic energy of the fluid in the pipeline into electrical energy and to power the multi-node monitoring network and other front-end equipment. The edge processing device is communicatively connected to a multi-node monitoring network and a hydraulically driven power supply device. It is used to perform dynamic equalization scheduling of local flow and pressure based on real-time monitoring data and hydraulic models when water quality abnormalities or pipeline pressure imbalances are detected. The remote service platform is connected to the edge processing device and the multi-node monitoring network. It is used to fuse and correct the aggregated data, predict water quality change trends based on time series models, generate a global optimization scheduling scheme according to user-defined goals and encrypt and send it to the edge processing device for execution, and store the entire process operation data and operation records in a tamper-proof manner.

2. The intelligent water dynamic monitoring and collaborative purification system according to claim 1, characterized in that, The node deployment of the multi-node monitoring network is configured differently based on the monitoring demand level of the pipeline network, including: Assign functional attribute labels to different locations in the pipeline network. The functional attribute labels include at least: key water supply nodes K, water quality sensitive area nodes S, conventional water transmission and distribution nodes N, and dense user access points U. A basic deployment density value is preset for each type of functional attribute tag. , label∈{K,S,U,N}, and satisfy: > > > ; Based on the aforementioned basic deployment density value In conjunction with the actual constraints of the pipeline network topology, the initial deployment locations of monitoring nodes are determined on the pipeline segments with corresponding functional attributes.

3. The intelligent water dynamic monitoring and collaborative purification system according to claim 1, characterized in that, The hydraulically driven power supply device includes an energy conversion component and an energy management circuit. The energy conversion component employs piezoelectric elements or electromagnetic induction coils, arranged in a ring or symmetrical manner along the inner wall of the pipe. The angle between its energy collection sensitive direction and the water flow direction within the pipe is... Set to 15°≤ ≤45°; The energy management circuit includes an overvoltage protection unit, an energy storage unit, and an energy storage switching unit. When the voltage of the energy storage unit... Below the threshold When the energy storage switching unit automatically switches the power supply to the backup power supply; when the voltage of the energy storage unit... Restored to above the threshold At that time, switch back to hydraulic power supply mode.

4. The intelligent water dynamic monitoring and collaborative purification system according to claim 1, characterized in that, The edge processing device performs dynamic load balancing scheduling, including: Upon receiving an abnormal alarm or remote command, the shutdown priority of each node is calculated based on the real-time pipeline topology and hydraulic model; the priority P is: ； in, This is the standardized value of the node's historical average water consumption. This is the standardized value of the pipeline distance from this node to the water source. α, β, and γ are the historical stability coefficients of the node devices, and α, β, and γ are the weighting coefficients. Nodes are shut down in order of priority from low to high until the number of shut-down nodes reaches the total number of nodes in the pipeline network. Stop when the time comes.

5. The intelligent water dynamic monitoring and collaborative purification system according to claim 4, characterized in that, If a node is shut down in order of priority from low to high, and the node to be shut down belongs to the category of water supply critical node K or water quality sensitive area node S, then the shutdown operation can only be performed after waiting for a secondary confirmation instruction from the remote service platform.

6. The intelligent water dynamic monitoring and collaborative purification system according to claim 1, characterized in that, The remote service platform includes: The data processing module is used to perform spatiotemporal alignment, outlier removal, and sensor bias correction on multi-source monitoring data. The predictive analytics module employs a time-series forecasting model based on a sliding time window, with near-term forecasts... Using historical data from the past few hours as input, predict the future. The trend of key water quality parameters within an hour, and the confidence level when the predicted result exceeds the safety threshold. Higher than the preset threshold When this happens, an alert is triggered; The optimization scheduling module adopts an adaptive optimization algorithm, taking user-defined target water quality, energy consumption cost and response delay as constraints, to generate an optimization scheme including pump power adjustment range, chemical dosage adjustment and standby treatment unit start and stop. The record storage module uses a chained data structure based on a hash function to store operation records with timestamps, device numbers, and parameter hash values, for tamper-proof evidence storage and third-party auditing.

7. The intelligent water dynamic monitoring and collaborative purification system according to claim 6, characterized in that, The predictive analysis module also dynamically optimizes and adjusts the node deployment locations of the multi-node monitoring network, including: Continuously assess the water quality stability of each pipe section and calculate the dynamic risk coefficient. : ； Where j represents the pipe section number, This represents the coefficient of variation of the core water quality parameters for this pipe section over the most recent hour. and These represent the mean and standard deviation of the coefficient of variation for the corresponding parameters. This refers to the frequency of water quality parameters exceeding standards in this pipeline section over the past 24 hours. This is the highest frequency of exceeding the limit within the system. The indicators of whether the pipe section is located in a historically high-risk area are w1, w2, and w3, which are weighting coefficients. Set a high-risk threshold With low risk threshold ; When a certain section of the pipe Continue to exceed Reaching the preset duration At that time, the remote service platform generates a dynamic density enhancement command, which, between the nodes at both ends of the pipeline segment, increases the basic deployment density value compared to the original functional attribute label. Higher temporary density value Add multiple temporary monitoring nodes; When a certain section of the pipe Persistently below Reaching the preset duration At that time, the remote service platform generates an optimization and removal command to remove non-critical monitoring nodes within the pipeline section, restoring their deployment density to near [a certain level]. The level.

8. The intelligent water dynamic monitoring and collaborative purification system according to claim 6, characterized in that, In the optimized scheduling module, the reward function R of the adaptive optimization algorithm is designed as follows: ； in, To achieve the water quality compliance rate, For energy consumption costs, Let be the system response delay, and a, b, and c be the weighting coefficients.

Images