Intelligent comprehensive management system of intelligent pipe network based on GIS (Geographic Information System)

Abstract

The invention relates to the field of geographic information systems, and discloses a GIS-based intelligent comprehensive management system for an intelligent pipe network, which comprises the following steps: S1, receiving a pipe network operation data flow sent by an Internet of Things sensor; s2, carrying out real-time analysis on the operation data flow based on a streaming processing framework, detecting pipeline abnormity by utilizing an isolation forest algorithm, and generating a response instruction; s3, integrating the spatial data and attribute data of various pipe network types through a GIS platform, and generating a cross-pipe network collaborative optimization suggestion; s4, storing the operation data flow and the collaborative optimization suggestion to a block chain, and generating a data record which cannot be tampered; and S5, the 2D / 3D visual data and the response instruction are sent to the client. According to the invention, through the streaming processing framework and the isolation forest algorithm, the server detects the pipeline abnormity within 500 milliseconds and generates the response instruction, so that the occurrence rate of sudden accidents such as water leakage or pipe explosion is obviously reduced, and the real-time performance and safety of pipe network operation are improved.

Description

Technical Field

[0001] The present invention relates to the field of geographic information systems, and in particular to a GIS-based intelligent integrated management system for smart pipe networks. Background Art

[0002] In existing technologies, the management of urban underground pipeline networks (such as water supply, gas, sewage, and heat) mostly relies on pipeline network management systems based on geographic information systems (GIS). These systems collect pipeline operation data (such as pressure, flow, and temperature) through sensors and combine them with GIS platforms to achieve pipeline data visualization, archiving, and planning support.

[0003] However, existing technologies have significant limitations in pipeline anomaly detection and response. Traditional systems often rely on static or periodic data collection, with data analysis typically performed on an hourly or minutely basis. This makes it difficult to achieve real-time anomaly detection and response within milliseconds. This results in delayed responses to emergencies (such as leaks and pipe bursts), increasing safety risks in pipeline network operations. Summary of the Invention

[0004] In order to make up for the above shortcomings, the present invention provides a GIS-based smart pipe network intelligent integrated management system, which aims to improve the problem that traditional systems mostly adopt static or periodic data collection methods, and data analysis is usually in units of hours or minutes, making it difficult to achieve millisecond-level real-time anomaly detection and response.

[0005] In a first aspect, the present invention provides the following technical solution: a GIS-based intelligent integrated management system for smart pipe networks, applied to a server, comprising the following steps:

[0006] S1. Receive a pipe network operation data stream sent by an IoT sensor, wherein the operation data stream includes pressure, flow, and temperature data;

[0007] S2. Analyze the operation data stream in real time based on a stream processing framework, detect pipeline anomalies using an isolation forest algorithm, and generate response instructions, wherein the response instructions are used to trigger an alarm or maintenance operation;

[0008] S3. Integrate spatial and attribute data of various pipe network types through a GIS platform to generate cross-pipeline network collaborative optimization recommendations, including pipe network types such as water supply, gas, sewage, and heat;

[0009] S4. Storing the operational data flow and collaborative optimization suggestions in a blockchain to generate tamper-proof data records for data security and auditing purposes;

[0010] S5. Send 2D / 3D visualization data and response instructions to the client, where the visualization data includes the pipeline network status and abnormal risk heat map.

[0011] Using this technical solution, the server receives JSON-formatted pipeline network operation data streams (including timestamps, sensor IDs, pressure, flow, and temperature) from IoT sensors via a network interface. It uses the Apache Kafka streaming framework to analyze the data in real time and employs the Isolation Forest algorithm to generate response instructions (such as alarms and valve adjustments). The GIS platform integrates GeoJSON spatial data and MySQL attribute data for the water, gas, sewage, and heating networks to generate collaborative optimization recommendations and store them on the Hyperledger Fabric blockchain, generating a SHA-256 hash to ensure immutability. The server pushes 2D / 3D visualization data (based on Three.js) and anomaly risk heat maps to Flutter-based web and mobile clients via WebSocket.

[0012] Preferably, the step S2 includes:

[0013] S201, receiving thousands of running data streams per second through a stream processing framework;

[0014] S202: Apply the Isolation Forest Algorithm to detect outliers. The formula of the Isolation Forest Algorithm is:

[0015] ; in:

[0016] Input data point, representing a single running data (including pressure flow temperature ,Right now ;

[0017] Data Points The path length in the isolation tree represents the number of steps from the root node to the terminal node;

[0018] Data Points Average path length in multiple isolation trees;

[0019] Normalization factor, which represents The average path length of samples is calculated as:

[0020] ; in ;

[0021] Total number of training samples;

[0022] Abnormal score, if , it is judged as abnormal;

[0023] S203. When an abnormality is detected, a response instruction is generated, including an alarm notification or valve adjustment suggestion, and pushed to the client within 500 milliseconds.

[0024] Preferably, the step S3 includes:

[0025] S301, receiving spatial data of longitude and latitude coordinates and attribute data of pipe material, diameter, and service life of various pipe network types;

[0026] S302: Analyze the potential impact of anomalies of one type of pipe network on other types of pipe networks based on the GIS platform, and generate collaborative optimization suggestions, including a joint maintenance plan and a resource allocation plan.

[0027] Preferably, the step S4 includes:

[0028] S401. Storing the operation data flow and collaborative optimization suggestions in a distributed ledger to generate an unalterable hash value;

[0029] S402. Based on blockchain permission management, data access rights are allocated to municipal departments and operating companies to support audits by regulatory agencies.

[0030] Preferably, the step S5 includes:

[0031] S501, generate 2D / 3D pipe network visualization data, support city panorama and single pipe network view switching;

[0032] S502. Push real-time alarms and visualization data to the client through a cross-platform mobile application developed based on Flutter.

[0033] Preferably, the IoT sensor uses LoRa or NB-IoT protocol to transmit the operating data stream, achieving low power consumption and stable communication.

[0034] Preferably, it also includes:

[0035] S601: Generate a dynamic trend analysis of the pipe network operation status based on the operation data stream, wherein the dynamic trend analysis includes a prediction of the time series changes of pressure, flow rate and temperature;

[0036] S602: Adjust the priority of the collaborative optimization suggestions based on the dynamic trend analysis, and give priority to maintenance tasks in high-risk areas.

[0037] In a second aspect, the present invention provides the following technical solution: a GIS-based intelligent integrated management system for smart pipe networks, applied to a server, comprising:

[0038] The data receiving module is configured to execute step S1 and receive the pipe network operation data stream;

[0039] an anomaly detection module, configured to execute step S2, detect pipeline anomalies using the isolation forest algorithm and generate response instructions;

[0040] a pipe network collaboration module, configured to execute step S3, integrate data of various pipe network types and generate collaborative optimization suggestions;

[0041] A blockchain storage module, configured to execute step S4 and store the data in the blockchain;

[0042] The visualization push module is configured to execute step S5 to send visualization data and response instructions to the client.

[0043] In the third aspect, the invention provides the following technical solution: a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the above-mentioned GIS-based intelligent integrated management method for smart pipe networks is implemented.

[0044] In a fourth aspect, the present invention provides the following technical solution: a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned GIS-based smart pipe network intelligent integrated management method is implemented.

[0045] The present invention has the following beneficial effects:

[0046] 1. In this invention, through the streaming processing framework and isolation forest algorithm, the server detects pipeline anomalies and generates response instructions within 500 milliseconds, significantly reducing the incidence of sudden accidents such as leaks or pipe bursts. Compared with the delay of traditional periodic monitoring, it improves the real-time performance and safety of pipeline network operation.

[0047] 2. In the present invention, water supply, gas, sewage, and heat pipe network data are integrated through the GIS platform to analyze cross-pipeline network impacts and generate joint maintenance plans, effectively reducing duplicate maintenance work, improving resource allocation efficiency, and breaking through the limitations of traditional single pipe network management.

[0048] 3. In this invention, blockchain is used to store operational data and collaborative optimization suggestions, generate tamper-proof records, provide secure authority management and audit paths for municipal departments, operating companies and regulatory agencies, and enhance data transparency and collaborative trust.

[0049] 4. In the present invention, through 2D / 3D pipe network visualization and dynamic heat map, the pipe network status and abnormal risks are displayed in real time, and view switching is supported, which makes it easier for maintenance personnel to quickly locate problems and perform operations, thereby improving on-site maintenance and decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a system interaction architecture diagram of a GIS-based intelligent integrated management method for smart pipe networks proposed in the present invention;

[0051] Figure 2 This is a flow chart of a GIS-based intelligent integrated management method for smart pipe networks proposed by the present invention;

[0052] Figure 3 This is a schematic diagram of multi-type pipe network collaboration and blockchain storage for a GIS-based intelligent integrated management method for smart pipe networks proposed in the present invention;

[0053] Figure 4 This is a system architecture diagram of a GIS-based smart pipe network intelligent integrated management system proposed in this invention. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0055] Example 1

[0056] Reference Figure 1-Figure 3 In a first embodiment of the present invention, the present invention provides a GIS-based intelligent integrated management system for smart pipe networks, which is applied to a server and includes the following steps:

[0057] S1, receiving the pipe network operation data stream sent by the IoT sensor, the operation data stream includes pressure, flow and temperature data;

[0058] S2. Analyze the operational data stream in real time based on a stream processing framework, using the Isolation Forest algorithm to detect pipeline anomalies and generate response instructions, which are used to trigger alarms or maintenance operations.

[0059] S3. Integrate spatial and attribute data of various pipe network types through the GIS platform to generate cross-pipeline network collaborative optimization suggestions. Pipeline network types include water supply, gas, sewage, and heat.

[0060] S4. Store the operational data flow and collaborative optimization suggestions on the blockchain to generate tamper-proof data records for data security and auditing.

[0061] S5. Send 2D / 3D visualization data and response instructions to the client. The visualization data includes the pipeline network status and abnormal risk heat map.

[0062] Specifically, the server receives pipeline network operation data streams from IoT sensors via a network interface. The data streams are encapsulated in JSON format, with each data entry containing a timestamp, sensor ID, pressure (kPa), flow (m³ / h), and temperature (°C). The server uses a streaming framework (such as Apache Kafka) to process the data stream, detect anomalies in real time, and generate response instructions, which are sent to the client or external device in JSON format. The GIS platform integrates spatial data (based on the WGS84 coordinate system) and attribute data (stored in relational database tables) for the water, gas, sewage, and heating pipeline networks to generate collaborative optimization recommendations, which are stored as reports. A blockchain uses a distributed ledger (such as Hyperledger Fabric) to store operational data and recommendations, generating hash values ​​to ensure immutability. The server pushes 2D / 3D visualizations to the client via the WebSocket protocol, which then renders heat maps of pipeline network status and anomaly risks, accessible via web and mobile devices.

[0063] Step S2 includes:

[0064] S201, receiving thousands of running data streams per second through a stream processing framework;

[0065] S202. Apply the isolation forest algorithm to detect outliers. The formula of the isolation forest algorithm is:

[0066] ; in:

[0067] Input data point, representing a single running data (including pressure flow temperature ,Right now ;

[0068] Data Points The path length in the isolation tree represents the number of steps from the root node to the terminal node;

[0069] Data Points Average path length in multiple isolation trees;

[0070] Normalization factor, which represents The average path length of samples is calculated as:

[0071] ; in ;

[0072] Total number of training samples;

[0073] Abnormal score, if , it is judged as abnormal;

[0074] S203. When an abnormality is detected, a response instruction is generated, including an alarm notification or valve adjustment suggestion, and pushed to the client within 500 milliseconds.

[0075] Specifically, the server subscribes to the data stream topic through Kafk consumers, processing thousands of data per second, with a data buffer size of 100 and a sliding window mechanism (window length 50) to ensure real-time performance. The isolation forest algorithm constructs 100 random trees, each of which is used for data points. Perform random segmentation and calculate path length Average path length The normalization factor is calculated by averaging multiple trees. Use the total number of samples Calculation, Euler constant Anomaly score When the error exceeds 0.6, the server generates a response instruction (in SON format, including the exception type, location, and recommended action, such as closing the valve) and pushes it to the client through NebSocket7 within 500 milliseconds. The client then displays the alarm information.

[0076] Step S3 includes:

[0077] S301, receiving spatial data of longitude and latitude coordinates and attribute data of pipe material, diameter, and service life of various pipe network types;

[0078] S302. Analyze the potential impact of anomalies in one type of pipe network on other types of pipe networks based on the GIS platform, and generate collaborative optimization suggestions, including joint maintenance plans and resource allocation plans.

[0079] Specifically, the server receives spatial data (latitude and longitude coordinates, stored in GeoJSON format) and attribute data (stored as MySQL tables, including fields such as material, diameter, and age) of various pipe network types. The GIS platform processes spatial data based on open source frameworks (such as PostGIS), analyzes the impact of water supply network anomalies (such as leakage) on the pressure of the gas network, and uses topological analysis algorithms to calculate the spatial proximity between pipe networks. Collaborative optimization recommendations are generated in JSON format, including joint maintenance plans (for example, "prioritize repair of water supply pipeline section A and simultaneously check adjacent gas pipelines") and resource allocation plans (for example, "dispatch two maintenance teams to coordinates (39.9,116.4)"), and are stored in a distributed database for query.

[0080] Step S4 includes:

[0081] S401. Storing operational data flows and collaborative optimization suggestions in a distributed ledger to generate an unalterable hash value.

[0082] S402. Based on blockchain permission management, data access rights are allocated to municipal departments and operating companies to support audits by regulatory agencies.

[0083] Specifically, the server uses Hyperledger Fabric to create a private chain. Operational data flows and collaborative optimization suggestions are submitted as transactions. Each transaction includes a timestamp, data content, and a digital signature. A SHA-256 hash value is generated and stored in the distributed ledger. Permissions management is implemented through chaincode (smart contracts). Municipal departments are assigned read-only permissions, while operating companies are assigned read-write permissions. Regulators can access audit logs via an API. Data storage utilizes a sharding mechanism, with distributed nodes (at least three) synchronizing the ledger to ensure immutability and traceability. The server regularly verifies hash value consistency to prevent data tampering.

[0084] Step S5 includes:

[0085] S501, generate 2D / 3D pipe network visualization data, support city panorama and single pipe network view switching;

[0086] S502. Push real-time alarms and visualization data to the client through a cross-platform mobile application developed based on Flutter.

[0087] Specifically, the server uses the Three.js library to generate 2D / 3D pipeline network visualization data. The 2D view displays a city pipeline network plan, while the 3D view supports three-dimensional rendering, allowing users to switch between a panoramic city view (covering the entire pipeline network) and a single pipeline network view (focusing on a single pipeline type). Anomaly risk heat maps are generated based on the operational data stream, using a color gradient (red for high risk, green for low risk) to represent risk distribution. The server pushes visualization data and alarm information through a cross-platform mobile app developed with Flutter (supporting iOS and Android). Data is transmitted via the WebSocket protocol, and the client renders and displays notifications in real time (e.g., "Pipeline section A is abnormal; immediate inspection recommended").

[0088] IoT sensors use LoRa or NB-IoT protocols to transmit operating data streams for low-power and stable communication.

[0089] Specifically, IoT sensors transmit operational data streams via the LoRa or NB-IoT protocols. LoRa uses the 915MHz frequency band, with a transmission range of up to 5 kilometers, making it suitable for urban environments. NB-IoT uses narrowband IoT, ensuring low power consumption (battery life exceeds one year). The sensors generate a piece of data per second (including pressure, flow, and temperature), which is forwarded to the server via a gateway. Data is encrypted using the AES-128 algorithm to ensure secure transmission. After the server verifies the data integrity, it is stored in a Kafka topic for subsequent processing.

[0090] Also includes:

[0091] S601. Generate a dynamic trend analysis of the pipe network operation status based on the operation data stream, the dynamic trend analysis including the prediction of the time series change of pressure, flow and temperature;

[0092] S602. Adjust the priority of collaborative optimization suggestions based on dynamic trend analysis, and give priority to maintenance tasks in high-risk areas.

[0093] Specifically, the server performs dynamic trend analysis based on operational data streams (stored in a time series database such as InfluxDB), using an ARIMA model to predict temporal changes in pressure, flow, and temperature (forecast window: 1 hour, step size: 5 minutes). Trend analysis results are stored in JSON format, including predicted values ​​and confidence intervals. Based on the trend analysis, the server adjusts the priority of collaborative optimization recommendations, using a priority queue algorithm (based on risk scores, ranging from 0-100) to prioritize maintenance tasks in high-risk areas (scores > 80). It then generates dispatch instructions (e.g., "Prioritize dispatching the team to coordinates (39.9,116.4)") and stores them on the blockchain for auditability.

[0094] Example 2:

[0095] Reference Figure 4 In a second embodiment of the present invention, the present invention provides a GIS-based intelligent integrated management system for smart pipe networks, which is applied to a server and includes:

[0096] The data receiving module is configured to execute step S1 and receive the pipe network operation data stream;

[0097] an anomaly detection module, configured to execute step S2, detect pipeline anomalies using the isolation forest algorithm and generate response instructions;

[0098] a pipe network collaboration module, configured to execute step S3, integrate data of various pipe network types and generate collaborative optimization suggestions;

[0099] A blockchain storage module, configured to execute step S4 and store the data in the blockchain;

[0100] The visualization push module is configured to execute step S5 to send visualization data and response instructions to the client.

[0101] Specifically, the system is deployed on a cloud server. The data reception module is implemented as a Kafka consumer, subscribing to a running data stream topic. The anomaly detection module runs a Python script, calling the scikit-learn library to implement the Isolation Forest algorithm and process buffer data. The pipeline network collaboration module integrates the PostGIS extension to process spatial data and generate collaborative optimization recommendations. The blockchain storage module interacts with private chains through the Hyperledger Fabric API to store transaction data. The visualization push module uses a Node.js server, combined with Three.js and WebSocket, to generate and push visualization data. The client uses React or Flutter to render the interface.

[0102] The following is an introduction with reference to specific embodiments:

[0103] Example 1: Real-time monitoring scenario of urban integrated pipe network

[0104] In this embodiment, a server is deployed on the cloud computing platform of the city's pipe network management center and receives IoT sensor data streams from the water and gas pipeline networks. The data streams are transmitted in Protobuf format. Each data entry contains a timestamp, sensor ID, pressure (kPa), flow (m³ / h), and temperature (°C). These data are sent to the server via the LoRa protocol at one-second intervals. The server uses the Apache Flink streaming framework, configured with a 100-entry buffer, and applies the Isolation Forest algorithm to detect anomalies. Algorithm parameters are set to 100 trees, 100 samples, an anomaly score threshold of 0.6, and a detection time of less than 400 milliseconds. The anomaly detection results generate JSON-formatted response instructions (e.g., "Close the valve on section A of the water pipeline"), which are pushed to the maintenance team's mobile devices via the MQTT protocol. A GIS platform, based on the OpenLayers framework, integrates GeoJSON spatial data and MySQL attribute data (including pipe diameter and material) from the water and gas pipeline networks to analyze the vibration impact of water leaks on the gas pipelines and generate joint maintenance recommendations (e.g., "Check the stability of section B of the gas pipeline"). The data and recommendations are stored on the Hyperledger Fabric blockchain, using SHA-256 hashing to ensure immutability. City authorities access the data through chaincode. The server uses Deck.gl to generate a 3D pipe network visualization, switching between panoramic and single-pipeline network views. Abnormal areas are highlighted with a red heat map, and the data is pushed to a Flutter-based mobile app.

[0105] Example 2: Collaborative management of sewage and heating pipe networks in industrial parks

[0106] In this example, a server runs at an edge computing node in an industrial park, receiving sensor data streams from sewage and heating networks. The data streams, encapsulated in CSV format and transmitted via the NB-IoT protocol, include pressure (in bar), flow (in L / min), and temperature (in °C). The server uses Spark Streaming to process the data streams, setting a sliding window of 50 data items and processing 2,000 data items per second. It uses the Isolation Forest algorithm (with 50 trees, 500 samples, and an anomaly score threshold of 0.65) to detect anomalies within 300 milliseconds and generate response instructions (e.g., "Pause sewage pump station C"). The GIS platform, based on QGIS, integrates spatial data (WGS84 coordinates) and attribute data (stored in PostgreSQL, including pipe age and material) for the sewage and heating networks. It analyzes the impact of sewage network blockage on the temperature distribution of the heating network and generates collaborative optimization recommendations (e.g., "Prioritize clearing sewage pipe section D and adjusting heating parameters for the heating pipe"). Operational data and recommendations are stored on an Ethereum private chain, using a Keccak-256 hash to ensure data security. Operators assign read and write permissions through smart contracts. The server uses MapboxGLJS to generate 2D / 3D visualizations of the data, displaying heat maps of sewage pipe network blockage risks. These visualizations are then pushed to a React-based web interface, where maintenance personnel can view them in real time through a browser.

[0107] Example 3: Cross-regional pipeline network data sharing and auditing scenario

[0108] In this example, a server is deployed on the distributed cloud platform of the Regional Pipeline Management Alliance. It receives sensor data streams from water, gas, sewage, and heating pipelines. This data is serialized in Avro format and transmitted via the LoRa protocol. It includes timestamps, pressure (kPa), flow (m³ / h), and temperature (°C). The server processes the data stream using Kafka Streams, configures a 200-line data buffer, and applies the Isolation Forest algorithm (with 200 trees, 2000 samples, and an anomaly score threshold of 0.6). The server maintains detection time within 500 milliseconds and generates response instructions (e.g., "Notify gas pipeline section E of maintenance"). The GIS platform, based on ArcGIS Online, integrates spatial data (in GeoJSON format) and attribute data (stored in MongoDB, including pipe diameters and materials) from multiple pipeline types, analyzes the interactions between cross-regional pipeline networks, and generates collaborative optimization recommendations (e.g., "Coordinate water supply maintenance plans for cities A and B"). The data and recommendations are stored on the Corda blockchain, generating SHA-256 hashes. Audit logs are accessible to cross-regional regulators through distributed nodes. The server uses Cesium.js to generate 3D pipeline network visualization, supports cross-region view switching, displays abnormal risks as dynamic heat maps, and pushes them to Flutter-based mobile applications via WebSocket, allowing supervisors to view data sharing status in real time.

[0109] Example 4: Predictive maintenance scenario based on dynamic trend analysis

[0110] In this embodiment, a server runs on the private cloud of a city pipeline operator and receives sensor data streams from the water and sewage pipeline networks. This data, transmitted in JSON Lines format and sent every two seconds via the NB-IoT protocol, includes pressure, flow, and temperature data. The server uses the Flink streaming framework, sets a 100-data window, and applies the Isolation Forest algorithm (with 100 trees, 1000 samples, and an anomaly score threshold of 0.6), maintaining a detection time of less than 450 milliseconds. It then generates response instructions (e.g., "Adjust the pressure at the pump station in section F of the sewage pipeline"). The GIS platform, based on GeoServer, processes spatial data (in Shapefile format) and attribute data (stored in Redis, including pipeline age and material), analyzes the impact of water pipeline leakage on sewage pipeline flow, and generates collaborative optimization recommendations (e.g., "Simultaneously maintain water pipeline section G and sewage pipeline section H"). The server uses the Prophet model for dynamic trend analysis, predicting pressure and flow changes within one hour (with a 95% confidence interval). Based on the predictions, the server adjusts maintenance priorities, prioritizing maintenance tasks in high-risk areas (e.g., those with a risk score > 85). Data and recommendations are stored on the Hyperledger Fabric blockchain, generating immutable transaction records that can be accessed by operational enterprises through an API. The server uses ECharts to generate 2D data visualizations, displaying trend curves and risk heat maps, which are then pushed to a React Native-based mobile app via HTTP.

[0111] Example 5: Mobile-first on-site maintenance scenario

[0112] In this example, a server is deployed in a hybrid cloud environment at the city's pipe network management center. It receives sensor data streams from the gas and heat pipe networks. This data, compressed in MessagePack format and transmitted via the LoRa protocol, includes pressure (kPa), flow (m³ / h), and temperature (°C). The server processes the data stream using Apache Storm, configured with an 80-line data buffer. It applies the Isolation Forest algorithm (80 trees, 800 samples, and an anomaly score threshold of 0.62), maintains detection time within 350 milliseconds, and generates response instructions (e.g., "Notify maintenance of heat pipe section I"). The GIS platform, based on MapServer, integrates spatial data (in GeoJSON format) and attribute data (stored in MySQL, including pipe material and installation date) from the gas and heat pipe networks. It analyzes the impact of abnormal gas pipe pressure on heat pipes and generates collaborative optimization recommendations (e.g., "Adjust the pressure of gas pipe section J and simultaneously inspect the heat pipe"). The data is stored on the Quorum blockchain, using SHA-3 hashing to ensure immutability. The maintenance team accesses the data via chaincode. The server uses Plotly to generate 2D / 3D visualization data, prioritizing mobile display optimization. Abnormal areas are presented as interactive heat maps, which are pushed through Flutter-based mobile applications. On-site maintenance personnel can directly click on the heat map to locate abnormal points and submit maintenance records.

[0113] Example 3

[0114] The third embodiment of the present invention is based on the same inventive concept. The present invention proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the GIS-based smart pipe network intelligent integrated management method of the above embodiment.

[0115] Example 4

[0116] The fourth embodiment of the present invention is based on the same inventive concept. The present invention proposes a computer device, including: a processor and a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory to execute the GIS-based smart pipe network intelligent comprehensive management method of the above embodiment.

[0117] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0118] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A GIS-based intelligent integrated management method for smart pipe networks, applied to a server, characterized in that: The following steps are involved: S1. Receive a pipe network operation data stream sent by an IoT sensor, wherein the operation data stream includes pressure, flow, and temperature data; S2. Analyze the operation data stream in real time based on a stream processing framework, detect pipeline anomalies using an isolation forest algorithm, and generate response instructions, wherein the response instructions are used to trigger an alarm or maintenance operation; S3. Integrate spatial and attribute data of various pipe network types through a GIS platform to generate cross-pipeline network collaborative optimization recommendations, including pipe network types such as water supply, gas, sewage, and heat; S4. Storing the operational data flow and collaborative optimization suggestions in a blockchain to generate tamper-proof data records for data security and auditing purposes; S5. Send 2D / 3D visualization data and response instructions to the client, where the visualization data includes the pipeline network status and abnormal risk heat map.

2. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: The step S2 comprises: S201, receiving thousands of running data streams per second through a stream processing framework; S202: Apply the Isolation Forest Algorithm to detect outliers. The formula of the Isolation Forest Algorithm is: ； in: Input data point, representing a single running data (including pressure flow temperature ,Right now ; Data Points The path length in the isolation tree represents the number of steps from the root node to the terminal node; Data Points Average path length among multiple isolation trees; Normalization factor, which represents The average path length of samples is calculated as: ； in ; Total number of training samples; Abnormal score, if , it is judged as abnormal; S203. When an abnormality is detected, a response instruction is generated, including an alarm notification or valve adjustment suggestion, and pushed to the client within 500 milliseconds.

3. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: The step S3 comprises: S301, receiving spatial data of longitude and latitude coordinates and attribute data of pipe material, diameter, and service life of various pipe network types; S302: Analyze the potential impact of anomalies of one type of pipe network on other types of pipe networks based on the GIS platform, and generate collaborative optimization suggestions, including a joint maintenance plan and a resource allocation plan.

4. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: The step S4 comprises: S401. Storing the operation data flow and collaborative optimization suggestions in a distributed ledger to generate an unalterable hash value; S402. Based on blockchain permission management, data access rights are allocated to municipal departments and operating companies to support audits by regulatory agencies.

5. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: The step S5 comprises: S501, generate 2D / 3D pipe network visualization data, support city panorama and single pipe network view switching; S502. Push real-time alarms and visualization data to the client through a cross-platform mobile application developed based on Flutter.

6. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: The IoT sensor uses LoRa or NB-IoT protocol to transmit the operating data stream, achieving low power consumption and stable communication.

7. The GIS-based intelligent integrated management method for smart pipe networks according to claim 1 is characterized in that: Also includes: S601: Generate a dynamic trend analysis of the pipe network operation status based on the operation data stream, wherein the dynamic trend analysis includes a prediction of the time series changes of pressure, flow rate and temperature; S602: Adjust the priority of the collaborative optimization suggestions based on the dynamic trend analysis, and give priority to maintenance tasks in high-risk areas.

8. A GIS-based intelligent integrated management system for smart pipe networks, applied to a server, characterized in that: The GIS-based intelligent integrated management method for a smart pipe network according to any one of claims 1 to 7 comprises: The data receiving module is configured to execute step S1 and receive the pipe network operation data stream; an anomaly detection module, configured to execute step S2, detect pipeline anomalies using the isolation forest algorithm and generate response instructions; a pipe network collaboration module, configured to execute step S3, integrate data of various pipe network types and generate collaborative optimization suggestions; A blockchain storage module, configured to execute step S4 and store the data in the blockchain; The visualization push module is configured to execute step S5 to send visualization data and response instructions to the client.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the GIS-based intelligent integrated management method for smart pipe networks as described in any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by the processor, the GIS-based intelligent integrated management method for the smart pipe network is implemented as described in any one of claims 1 to 7.

Images