Big data visualization processing method and system applied to intelligent water affairs

Abstract

The invention belongs to the technical field of smart water affairs, and particularly relates to a big data visualization processing method and system applied to smart water affairs. The invention aims to solve the problems that data are disordered and difficult to process in the existing integrated water affair pipeline management and data interference results in error reporting when the data is abnormal. The system comprises a monitoring module, a data processing module, a recording module, a water affair system scheduling processing training module, a central scheduling general control module and a mobile terminal module. The monitoring module collects data according to preset partitions, the data processing module cleans and classifies the data in a partition mode, the water affair system dispatching processing training module generates partition fault processing suggestions through deep learning, the central dispatching master control module issues instructions and visually displays the data in a partition mode, and the mobile terminal module feeds back maintenance data. The method is realized through partition acquisition preprocessing, partition model training analysis, scheduling visualization and feedback optimization. The data processing difficulty is reduced, errors are reduced, and the fault processing efficiency and the intelligent water affair management level are improved.

Description

Technical Field

[0001] This invention belongs to the field of smart water technology, and specifically relates to a big data visualization processing method and system for smart water management. Background Technology

[0002] Smart water management can monitor and process various water pipeline status indicators through intelligent sensor nodes. Based on cloud computing platform and deep learning technology, it can make decisions on abnormal status of water pipeline network and display them on the visualization front-end platform to help relevant personnel handle critical matters in a timely manner.

[0003] However, in the existing technology, the water pipeline management adopts an integrated management mode, which generates a large amount of messy water pipeline status data, increasing the difficulty of data processing. When anomalies occur, the lack of data classification and management can easily cause interference, leading to abnormal error reports and other problems, making it difficult to meet the needs of efficient smart water management. Summary of the Invention

[0004] The present invention aims to provide a big data visualization processing method and system for smart water management, mainly to solve the problems of difficult data processing and data interference causing errors when anomalies occur in the existing integrated water pipeline management.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A big data visualization processing system for smart water management includes a monitoring module, a data processing module, a recording module, a water system scheduling and processing training module, a central dispatch control module, and a mobile terminal module. The monitoring module is used to monitor water pipelines in different zones in real time according to the preset zones of water pipelines, and collect status index data of water pipelines in each zone. The preset zones are divided based on geographical boundaries, user types, pipeline functions and maintenance reach radius within 30 minutes, covering residential community water supply pipeline zones, industrial park circulating water pipeline zones, and municipal road drainage pipeline zones. The data processing module is used to divide water pipelines into zones based on geographical boundaries, user types, pipeline functions, and operation and maintenance radius. Geographical boundaries include natural barriers and artificial boundaries, user types include residential, industrial, and municipal public, pipeline functions include water supply, drainage, and circulating water, and the operation and maintenance radius is set to 2-3km. The data processing module also receives data from each zone collected by the monitoring module and cleans, filters, and classifies the data according to the zone. The recording module is used to record various types of data during system operation, including data processed by each partition, analysis results corresponding to each partition, partition-specific scheduling instructions, and partition feedback data. The water system scheduling and processing training module is used to receive data from each partition after the data processing module has categorized the data by partition. It analyzes and learns the data from each partition separately through deep learning algorithms, identifies the fault types of water pipelines in different partitions, draws conclusions about the causes of faults in each partition, and generates fault handling suggestions adapted to each partition. It is also used to receive feedback data from each partition to correct the algorithm model of its corresponding partition. The central dispatch and control module is used to receive fault conclusions and adaptation suggestions from each zone of the water system dispatch and processing training module. Based on the actual operation of water pipelines in each zone and the distribution of dedicated personnel in each zone, it issues maintenance suggestion instructions to the corresponding zone personnel, receives actual data from each zone from the mobile terminal module and transmits it back to the water system dispatch and processing training module according to zone, and displays the data of each zone on the visualization front-end platform according to zone. The mobile terminal module is authorized by zone and is used to receive maintenance suggestion instructions for the corresponding zone issued by the central dispatch and control module, record the actual fault situation, maintenance process and results of the corresponding zone and feed them back to the central dispatch and control module.

[0006] Preferably, the monitoring module collects corresponding water pipeline status index data for different zones, including: flow rate, pressure, and leakage data for residential water supply networks; flow rate, pressure, temperature, and water quality data for industrial park circulating water networks; and liquid level, flow rate, and odor data for municipal road drainage networks.

[0007] Preferably, when the data processing module cleans the data, it removes redundant and abnormal data from each partition to ensure the accuracy and validity of the data in each partition, and the cleaned data is still associated with the corresponding partition identifier.

[0008] Preferably, the water system scheduling and processing training module identifies water pipeline fault types in different zones, including: residential community water supply network zone identification of pipeline rupture and leakage faults; industrial park circulating water network zone identification of pipeline blockage and corrosion faults; municipal road drainage network zone identification of pipeline siltation and excessive liquid level faults; and municipal water supply network zone identification of valve faults.

[0009] Preferably, when the central dispatch and control module issues maintenance suggestion instructions, it takes into account the actual operation status of water pipelines in each zone and the distribution of dedicated personnel in each zone. The actual operation status of water pipelines in each zone includes the pressure and flow fluctuations of the zone's pipeline network. One maintenance team is designated for each primary zone to ensure that the instructions are accurately issued to the corresponding zone personnel.

[0010] A big data visualization processing method for smart water management includes the following steps: S1: The monitoring module collects data on water pipelines in different zones according to preset zones. The preset zones are divided based on geographical boundaries, user types, pipeline functions, and operation and maintenance radius. The data processing module divides the water pipelines into zones according to geographical boundaries, user types, pipeline functions, and operation and maintenance radius. The collected data is cleaned and classified according to the zones to ensure that the data is bound to the zone identifier. S2: The water system scheduling and processing training module adopts a deep learning model to train and learn the pre-processed data of each partition, establishes a dedicated fault identification model for each partition, and uses the dedicated model of each partition to analyze and judge whether there are faults and fault types in the water pipelines of the corresponding partition, and generates fault handling suggestions that are adapted to the characteristics of the partition network. S3: The central dispatch and control module integrates the fault analysis results and adaptation and handling suggestions of each zone, and, in combination with the distribution of staff in each zone, issues maintenance instructions to the corresponding staff in each zone. It also displays the data of each zone on the visualization front-end platform, with each zone's data forming an independent section. S4: Staff members use the authorized mobile terminal module for each zone to provide feedback on the actual maintenance data for that zone. The central dispatch and control module then transmits the feedback data from each zone back to the water system dispatch and processing training module. This module adjusts the corresponding zone model parameters based on the feedback data from each zone to optimize the performance of each zone model.

[0011] Preferably, in step S1, when the data processing module classifies the data, it strictly follows the classification results of the water pipeline. The classification results include first-level partitions, second-level partitions, and third-level unit partitions. Each data is labeled with the hierarchical identifier of "partition-sub-region-unit pipe segment".

[0012] Preferably, in step S2, when the water system scheduling and processing training module establishes the fault identification model for each zone, it combines the historical fault handling data of the corresponding zone with the zone-specific optimal solution. The historical fault handling data of the corresponding zone includes the historical leakage handling data of the residential water supply network zone, and the zone-specific optimal solution includes the anti-corrosion and maintenance scheme of the industrial park circulating water network zone, to generate fault handling suggestions adapted to the zone.

[0013] Preferably, in step S3, the central dispatch and control module displays data by zone on the visualization front-end platform: the water supply network of residential communities displays pressure, flow, and leakage fault handling progress data by zone; the circulating water network of industrial parks displays temperature, water quality, and blockage fault handling progress data by zone; and the drainage network of municipal roads displays liquid level, odor, and siltation fault handling progress data by zone.

[0014] Preferably, in step S4, the mobile terminal module feeds back the actual maintenance data of the corresponding partition according to the partition, and marks the partition. The actual maintenance data includes the actual fault data of the partition, the maintenance process data of the partition, and the maintenance result data of the partition. The actual fault data of the partition includes the location of the leak point of the water supply network partition in the residential area, the maintenance process data of the partition includes the anti-corrosion treatment steps of the circulating water network partition in the industrial park, and the maintenance result data of the partition includes the liquid level recovery status of the drainage network partition in the municipal road.

[0015] The beneficial effects of this invention are as follows: By adopting a zoned management approach, water pipeline data is collected and categorized in zones, avoiding data clutter, reducing data processing difficulty, and minimizing errors caused by data interference during anomalies; the water system scheduling and processing training module, utilizing deep learning technology, can accurately identify fault types and provide reasonable work suggestions, improving fault handling efficiency and accuracy. Simultaneously, the model is continuously optimized through data feedback correction, enhancing system performance; the central dispatch and control module implements command issuance and data integration, while the mobile terminal module provides feedback on actual conditions, forming a complete data processing and scheduling closed loop. This facilitates real-time monitoring by management personnel, enabling timely handling of critical matters and improving the level of smart water management. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 This is a system architecture diagram of the present invention patent; Figure 2 This is a flowchart of the method of this invention patent. Detailed Implementation

[0018] 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; the embodiments of the present invention will be described below according to the overall structure of the present invention.

[0019] In one exemplary design approach, a big data visualization processing system applied to smart water management has the following system architecture: Figure 1 As shown, it includes a monitoring module, a data processing module, a recording module, a water system scheduling and processing training module, a central dispatch control module, and a mobile terminal module; Monitoring module hardware configuration and data acquisition logic: The monitoring module adopts a "zoned deployment + distributed acquisition" architecture. Based on the pre-defined network distribution density and data acquisition requirements of the zones, intelligent sensor nodes are deployed in each zone. The selection of sensor nodes follows the "zone adaptation" principle. The water supply network in the residential area is divided into zones: one set of pressure sensor and flow sensor is installed every 500 meters of pipe section. The pressure sensor has a range of 0-1.6MPa to adapt to the water supply pressure range of residents. The flow sensor is electromagnetic to resist interference from impurities. At the same time, acoustic leakage detectors are installed at key nodes of the network, such as the main pipe at the entrance of the community and the branch pipes of the building, and are connected to the zone data acquisition unit through the bus. Industrial park circulating water network zoning: Flow sensors are installed at the circulating water inlet, outlet, and key branch pipes, with ranges adapted to the industrial circulating water flow range; pressure and temperature sensors are installed, with a temperature measurement range of -20℃ to 120℃; water quality sensors are installed after the circulating water sedimentation tank to detect pH value, conductivity, and suspended solids concentration; all sensors are equipped with corrosion-resistant housings, and the output signals are transmitted to the zoning data acquisition unit after being processed by a signal conditioning circuit (filtering out industrial electromagnetic interference); Municipal road drainage network zoning: Liquid level sensors are installed in drainage wells, flow sensors are installed at pipeline turning points, and odor sensors are installed next to drainage wells in densely populated road sections to detect hydrogen sulfide and ammonia concentrations. The sensors adopt a waterproof and sealed design and are connected to the zone data acquisition unit via LoRa wireless communication. Each partition data collector has a "partition identifier binding" function. The collector has a built-in storage unit that can temporarily store the collected data within 12 hours. At the same time, it uploads the data to the data processing module in real time via 4G / 5G network. The uploaded data frame contains the fields "partition code - sub-area code - unit pipe segment code - sensor ID - collection time - data value" to ensure that the data corresponds one-to-one with the partition identifier.

[0020] Data processing module hardware and software logic: The data processing module uses an industrial-grade server, equipped with a multi-core processor and large-capacity memory. The server has built-in data processing software, and the software execution logic is as follows: Partition data reception: Data uploaded by each partition data collector is received via TCP / IP protocol, and the data is initially classified and stored according to the "partition code". Each partition corresponds to an independent database table. Data cleaning: For the data in each partition, the Raida criterion is used to remove abnormal data (such as data that exceeds the sensor's range or data with excessive instantaneous fluctuations), and redundant data (such as data with a deviation of less than 0.5% for three consecutive acquisitions) is removed by the "adjacent data comparison method". During the cleaning process, the "partition-sub-region-unit segment" hierarchical identifier of the data is retained. Data Classification: The cleaned data is classified a second time according to "pipeline function + monitoring indicators". For example, the water supply network zone data in residential communities is divided into three categories: "flow data", "pressure data" and "leakage data". Each category of data is associated with the corresponding unit pipe section code and collection time. The classified data is pushed to the recording module and the water system scheduling and processing training module in real time.

[0021] Water system scheduling and processing training module implementation This module is built on a GPU server and incorporates a deep learning framework. The module execution flow is as follows: Partition model initialization: For each partition, import the historical data of that partition (including pipeline status data, fault data, and maintenance data), use "pipeline status data" as the input feature and "fault type + fault cause" as the output label, and build a hybrid deep learning model based on CNN-LSTM (CNN extracts local features of the data, and LSTM captures the temporal features of the data). Model training: The model for each partition is trained independently. During the training process, the "cross-validation method" is used to optimize the model parameters, such as the learning rate and the number of iterations. When the model's accuracy in identifying historical fault data reaches more than 95%, training is stopped, and a dedicated fault identification model for that partition is generated. Real-time fault analysis: Receives real-time data from each partition pushed by the data processing module, inputs the data into the corresponding partition's dedicated model, and the model outputs "fault judgment result", "fault type" and "fault cause probability distribution", and generates fault handling suggestions adapted to the partition by combining the pipeline network parameters of the partition. Model Iteration and Optimization: Receive the partition feedback data (including actual fault types and maintenance results) from the central dispatch and control module, use the feedback data as new training samples, and incrementally train the model for the corresponding partition. Complete a full model optimization once every quarter to ensure that the model recognition accuracy continues to improve with actual operation data.

[0022] Central Dispatch Control Module and Visual Implementation: The central dispatch and control module uses an industrial-grade PLC as the core control unit, paired with a touch-screen operation panel and remote monitoring software. The module's functions are as follows: Command issuance logic: Receive the zonal fault conclusions and handling suggestions output by the water system scheduling and processing training module, combine them with the zonal staff distribution data (stored in the PLC's built-in database, including contact information and current on-duty status of each zonal maintenance team), determine the target maintenance team through "zonal code matching," and issue maintenance instructions via SMS + APP push. The instruction content includes "zonal-sub-area-unit pipe section fault location," "fault type," "suggested maintenance plan," and "completion deadline." Data visualization display: A visualization front-end platform is built through remote monitoring software. The platform adopts a "zoning map + data panel" layout. The left side is the water pipe network zoning map, and the right side is the zoning data panel. Each zoning panel independently displays the real-time monitoring data and fault handling progress of the zoning. The data update frequency is consistent with the collection frequency. It also supports the "zoning data drill-down" function. Clicking on a unit pipe segment allows you to view the historical data and historical fault records of that pipe segment. Data feedback control: Receive maintenance data fed back from the mobile terminal module, classify the data according to "zone code", push it to the water system scheduling and processing training module in real time, and store the data in the recording module.

[0023] Mobile terminal module implementation: The mobile terminal module is developed using a dedicated Android app. The app employs a "partition authorization" mechanism, requiring staff to log in with an account and password. After logging in, staff can only view and manipulate data related to their assigned partition. The app's functions include: Command reception: Receives maintenance commands issued by the central dispatch and control module, displays them as pop-up windows, and supports viewing and confirming the command content; Data Recording: Provides three input interfaces: "Fault Record", "Repair Record" and "Result Record". Staff can record the actual fault situation, repair process and repair results in the form of text, pictures and videos. The entered data is automatically marked with the current partition and the entry time. Data feedback: After clicking the "Submit" button, the APP will encrypt and upload the recorded data to the central dispatch and control module via 4G / 5G network. After the upload is completed, a feedback receipt will be generated.

[0024] An implementation process for a big data visualization processing method applied to smart water management, such as... Figure 2 As shown, the steps include: S1: Partition Data Acquisition and Preprocessing Zoning: The data processing module divides the urban water supply network into multiple primary zones according to preset rules (geographical boundaries: urban main roads and rivers; user types: residential, industrial production, municipal public; network functions: water supply, drainage, circulating water; operation and maintenance radius: 2-3km). Each primary zone is further divided into 5-8 secondary zones, and each secondary zone is further divided into 10-15 tertiary unit zones, generating a hierarchical identification system of "zone code - sub-region code - unit segment code". Data acquisition: The sensor nodes of each zone of the monitoring module collect data at a set frequency and upload it to the data processing module through the data acquisition device; Data preprocessing: The data processing module removes redundancy and abnormal data from the data by partition, classifies it according to monitoring indicators, binds the processed data with hierarchical identifiers, and pushes it to the recording module and the water system scheduling and processing training module.

[0025] S2: Partition Fault Model Training and Analysis Model Training: The water system scheduling and processing training module imports historical data from each zone and trains a dedicated fault identification model for each zone. For example, the model for the "Chengdong Residential Water Supply Zone" uses the pressure, flow, and leakage data of the zone over the past three years as training samples. Training stops when the model's accuracy in identifying historical fault data reaches over 95%, and a dedicated fault identification model for that zone is generated. Real-time analysis: Input the real-time data after S1 preprocessing into the corresponding partition model. The model outputs the fault analysis results. For example, the analysis of the "X Industrial Circulating Water Partition" model shows that "the pipe of unit pipe section code X02-03 has a blockage fault. The cause of the fault is likely to be scale buildup in the pipe. It is recommended to use high-pressure water jet cleaning technology to deal with it." S3: Scheduling Command Issuance and Data Visualization Command issuance: The central dispatch and control module receives the fault analysis results of "X Industrial Circulating Water Zone", queries the maintenance team information of this zone, and issues a maintenance command to the team. The command content is: "Zone: X Industrial Circulating Water Zone; Sub-area: X02; Unit pipe section: X02-03; Fault type: Pipe blockage; Suggested maintenance solution: High-pressure water jet cleaning; Completion time limit: n hours"; Visualization: The flow rate, pressure and temperature curves of the zone are displayed in real time on the "X Industrial Circulating Water Zone" panel of the visualization front-end platform, and the "X02-03 Unit Pipe Section Blockage Fault" warning information is marked. The status of maintenance command issuance is displayed simultaneously.

[0026] S4: Maintenance Feedback and Model Optimization Maintenance feedback: "X Industrial Maintenance Team 1" receives instructions via a mobile terminal APP, arrives on-site, records the actual fault situation, maintenance process, maintenance results, and submits feedback data; Model optimization: The central dispatch and control module transmits the feedback data back to the water system dispatch and processing training module. This module uses the "X02-03 pipe section scaling fault data" as a new sample to incrementally train the "X industrial circulating water zone" model. After optimization, the model's accuracy in identifying scaling faults is improved.

[0027] It needs to be further explained that: System power supply: The monitoring module sensor nodes are powered by batteries and solar energy, and the battery capacity can meet the power supply needs for 7 consecutive days of cloudy and rainy weather; the data processing module, water system scheduling and processing training module, and central dispatch control module are powered by dual-circuit mains power, coupled with UPS uninterruptible power supply to ensure continuous system operation; Data security: Data transmission between modules uses SSL encryption protocol, and the database of the record module adopts regular backup and off-site disaster recovery mechanism to prevent data loss; Compatibility: The system supports data interaction with existing water management platforms, enables data sharing through API interfaces, and can connect to third-party sensing devices, facilitating future expansion. The foregoing description of specific exemplary embodiments of the present invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it is obvious that many changes and variations can be made based on the above teachings. Although embodiments of the invention have been shown and described, these specific embodiments are merely explanations of the invention and are not intended to limit it. The specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. The purpose of selecting and describing exemplary embodiments is to explain the specific principles of the invention and its practical application, so that those skilled in the art, after reading this specification, can make modifications, substitutions, variations, and various choices and changes to the embodiments as needed without departing from the principles and spirit of the invention, provided that such modifications, substitutions, variations, and choices and changes are within the scope of the claims of the invention and are protected by patent law.

Claims

1. A big data visualization processing system applied to smart water affairs, characterized in that, The system comprises a monitoring module, a data processing module, a recording module, a water system dispatching processing training module, a central dispatching master control module and a mobile terminal module. The monitoring module is configured to monitor the water pipelines in different partitions in real time according to preset partitions of the water pipelines, and collect state index data of the water pipelines in each partition. The preset partitions are divided based on geographical boundaries, user types, pipeline functions and a 30-minute operation and maintenance reachable radius, and cover residential area water supply pipeline partitions, industrial park circulating water pipeline partitions and municipal road drainage pipeline partitions. The data processing module is configured to divide the water pipelines into partitions according to geographical boundaries, user types, pipeline functions and an operation and maintenance radius. The geographical boundaries include natural barriers and artificial boundaries. The user types include residential life, industrial production and municipal public. The pipeline functions include water supply, drainage and circulating water. The operation and maintenance radius is set to 2-3 km. The data processing module also receives the partition data collected by the monitoring module, and performs cleaning, screening and classification processing on the data according to the partitions. The recording module is configured to record various data in the system operation process, including the processed data of each partition, the analysis results corresponding to each partition, partition-specific dispatching instructions and partition feedback data. The water system dispatching processing training module is configured to receive the partition data classified by the data processing module, analyze and learn the partition data respectively through a deep learning algorithm, identify the fault types of the water pipelines in different partitions, derive conclusions on the fault causes of each partition and generate fault processing work suggestions adapted to each partition, and also receive the partition feedback data to correct the algorithm model corresponding to each partition. The central dispatching master control module is configured to receive the fault conclusions of each partition and the work suggestions adapted to each partition from the water system dispatching processing training module, combine the actual operation conditions of the water pipelines in each partition and the distribution of partition-specific staff, issue maintenance suggestion instructions to the staff in the corresponding partition, receive actual data of each partition fed back by the mobile terminal module and return the data to the water system dispatching processing training module according to the partitions, and display the data of each partition on a visual front-end platform according to the partitions. The mobile terminal module is authorized according to the partitions, and is configured to receive the corresponding partition maintenance suggestion instructions issued by the central dispatching master control module, record the actual conditions, maintenance process and results of the corresponding partition faults and feed back to the central dispatching master control module.

2. The system of claim 1, wherein, The monitoring module collects corresponding water pipeline state index data for different partitions, including flow, pressure and leakage data for residential area water supply pipeline partitions, flow, pressure, temperature and water quality data for industrial park circulating water pipeline partitions, and liquid level, flow and odor data for municipal road drainage pipeline partitions.

3. The system of claim 1, wherein, When the data processing module performs cleaning processing on the data, it removes redundant data and abnormal data in each partition according to the partitions, ensures the accuracy and effectiveness of the data in each partition, and still associates the cleaned data with the corresponding partition identifier.

4. The system of claim 1, wherein, The water system scheduling processing training module identifies different partition water pipeline fault types, including: resident community water supply pipeline network partition identifies pipe rupture and leakage failure; industrial park circulating water pipeline network partition identifies pipe blockage and corrosion failure; municipal road drainage pipeline network partition identifies pipe siltation and liquid level exceeding standard failure; municipal water supply pipeline network partition identifies valve failure.

5. The system of claim 1, wherein, When the central dispatching master control module issues maintenance recommendation instructions, the actual operation of each partition water pipeline is combined with the actual operation of each partition water pipeline, including partition pipeline pressure and flow fluctuation, and each first-level partition is assigned an operation and maintenance team to ensure that instructions are accurately issued to corresponding partition staff.

6. A big data visualization processing method applied to smart water affairs, characterized in that, The system of any one of claims 1-5, comprising the following steps: S1: Collect data from different partitions of the water pipeline by the monitoring module according to the preset partition, which is divided based on geographical boundaries, user types, pipeline functions, and operation and maintenance radii. The data processing module divides the water pipeline according to geographical boundaries, user types, pipeline functions, and operation and maintenance radii, cleans and classifies the collected data according to the partition, and ensures that the data is bound to the partition identifier; S2: The water system scheduling processing training module uses a deep learning model to train and learn each partition data after preprocessing, establishes a dedicated fault identification model for each partition, analyzes and judges whether there is a fault in the corresponding partition water pipeline and the fault type using the dedicated model of each partition, and generates a fault handling suggestion adapted to the characteristics of the partition pipeline network; S3: The central dispatching master control module integrates the fault analysis results and partition adaptation processing suggestions of each partition, combines the distribution of staff in each partition, issues maintenance instructions to corresponding partition staff, and displays each partition data on the visualization front-end platform according to the partition, with each partition data being independently displayed as a block; S4: The staff feedbacks the actual maintenance data of the corresponding partition through the partition-authorized mobile terminal module, and the central dispatching master control module returns the feedback data of each partition to the water system scheduling processing training module according to the partition, and the module adjusts the model parameters of the corresponding partition according to the feedback data of each partition to optimize the performance of each partition model.

7. The method of claim 6, wherein, In step S1, the data processing module classifies the data according to the partition division results of the water pipeline, which includes first-level partition, second-level partition, and third-level unit partition, and each data is labeled with "partition-subregion-unit pipe segment" hierarchical identifier.

8. The method of claim 6, wherein, In step S2, when the water system scheduling processing training module establishes the fault identification model of each partition, it combines the historical fault handling data of the corresponding partition and the partition-specific optimal solution to generate a fault handling suggestion adapted to the partition. The historical fault handling data of the corresponding partition includes historical leakage handling data of the resident community water supply pipeline network partition, and the partition-specific optimal solution includes the corrosion maintenance scheme of the industrial park circulating water pipeline network partition.

9. The method of claim 6, wherein, In step S3, the central dispatching general control module displays data by partition on the visual front-end platform: resident community water supply network partition display pressure, flow, leakage fault handling progress data; industrial park circulating water pipe network partition display temperature, water quality, blockage fault handling progress data; municipal road drainage pipe network partition display liquid level, odor, siltation fault handling progress data.

10. The method of claim 6, wherein, In step S4, the mobile terminal module feeds back actual maintenance data of the corresponding partition by partition, marks the partition identification, and the actual maintenance data includes the partition fault actual situation data, the partition maintenance process data and the partition maintenance result data, the partition fault actual situation data includes the leakage point position of the resident community water supply network partition, the partition maintenance process data includes the anticorrosion treatment steps of the industrial park circulating water pipe network partition, and the partition maintenance result data includes the liquid level recovery situation of the municipal road drainage pipe network partition.

Images