Heat supply pipe network inspection method based on digital twinborn technology

Abstract

The invention relates to the technical field of heat supply network operation and maintenance, solves the problems of traditional heat supply network inspection information fragmentation, subjective evaluation and fuzzy fault location, and particularly relates to a heat supply network inspection method based on a digital twinborn technology. Meanwhile, multi-source inspection data is collected and imported into the model after being subjected to cleaning, standardization, fusion and noise reduction preprocessing, data synchronization is achieved, evaluation units are divided according to the pipe network topology, intelligent evaluation of the operation state is achieved through a core index-basic index grading system and a quantification algorithm, and when a fault or a potential risk is triggered, the operation state is evaluated. Three-dimensional coordinates of a fault point are accurately locked through combination of multi-level positioning logic, image recognition, a clustering algorithm and the like, finally, a preset processing scheme is matched, and an optimal scheme is output through multi-dimensional simulation evaluation, so that the pipe network inspection efficiency and the fault disposal scientificity are improved, and the operation and maintenance cost and the fault loss are reduced.

Description

Technical Field

[0001] This invention relates to the field of heating pipeline network operation and maintenance technology, and in particular to a heating pipeline network inspection method based on digital twin technology. Background Technology

[0002] As a core infrastructure for urban energy supply, the stability of heating pipe networks directly affects the quality of life for residents and the safety of industrial production. Traditional methods of inspecting heating pipe networks mainly rely on manual on-site inspections, paper-based records, and local sensor monitoring, which have many inherent defects and are no longer sufficient to meet the needs of modern intelligent operation and maintenance of pipe networks. Specifically: Traditional inspection methods suffer from information fragmentation. Pipeline design data, construction records, and operation and maintenance data are stored in a scattered manner, lacking unified integration and visualization. This makes it difficult for inspection personnel to fully grasp the spatial location of the pipeline, equipment parameters, and historical operation status, and they are prone to omissions and misjudgments due to information deviations or omissions. Meanwhile, condition assessment relies on human experience, the assessment standards are vague and highly subjective, and it is impossible to achieve refined and intelligent prediction. Repairs can often only be carried out after a fault occurs, making it difficult to identify potential risks in advance. Fault location mainly relies on manual inspection, which is inefficient and has poor location accuracy. Moreover, fault handling plans are mostly based on experience and lack pre-verification. This can easily lead to secondary faults, waste of resources, or excessively long handling cycles due to unreasonable plans.

[0003] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a heating pipeline network inspection method based on digital twin technology. This method constructs a digital twin model of the heating pipeline network by integrating BIM, GIS, and CFD technologies, consolidating data throughout the entire lifecycle, and simultaneously collecting multi-source inspection data. This data is then pre-processed through cleaning, standardization, fusion, and noise reduction before being imported into the model to achieve data synchronization. Furthermore, the method divides the network into evaluation units according to its topology and uses a core-basic indicator hierarchical system and quantitative algorithms to achieve intelligent assessment of operational status. When a fault or potential risk is triggered, the method accurately locates the three-dimensional coordinates of the fault point through multi-level positioning logic combined with image recognition and clustering algorithms. Finally, it matches a preset processing plan and outputs the optimal solution through multi-dimensional simulation evaluation. This improves the efficiency of pipeline network inspection and the scientific nature of fault handling, reduces operation and maintenance costs and fault losses, and addresses the aforementioned technical deficiencies.

[0005] The objective of this invention can be achieved through the following technical solution: a heating pipeline inspection method based on digital twin technology, comprising the following steps: Step 1: Basic Construction for Inspection: Based on BIM technology, a three-dimensional geometric model of the pipeline network is constructed, and GIS technology is integrated to overlay geographic coordinates, topography and building distribution information. Combined with CFD technology, a fluid dynamics model is constructed, and integrated to form a digital twin model of the heating pipeline network. Step 2: Multi-source inspection data acquisition and preprocessing: Collect multi-source inspection data, preprocess the multi-source inspection data to obtain standardized multi-source inspection data, and import it into the digital twin model to achieve data synchronization; Step 3: Inspection Status Assessment: Divide the assessment units according to the pipeline network topology, obtain the core assessment indicators and corresponding weights of each unit, decompose the basic indicators of the core assessment indicators and perform quantitative calculations, calculate the comprehensive score of the target layer based on the comprehensive score formula, and determine whether each assessment unit is in a normal state, a potential risk state, or a fault state by combining the preset score range. Step 4: Inspection and Fault Location: Generate a heat map of pipeline operation status based on the status judgment results. When a fault or potential risk state is triggered, determine the initial range of the fault by combining the deployment location of abnormal parameter sensors. Step 5: In-depth location: By identifying fault characteristics and combining GIS spatial mapping to determine the initial location of the fault, the K-means clustering algorithm is used to optimize the fault location, and the precise three-dimensional coordinates of the fault point are determined by integrating BIM and GIS coordinates. At the same time, a fault location list is constructed. Step Six: Simulation and Evaluation of the Treatment Plan: Based on the fault location list, match the preset treatment plan and conduct simulation. Verify the effect of the simulation from multiple dimensions until the final preset treatment plan is output.

[0006] Preferably, the basic construction and analysis process for the inspection is as follows: Collect design data, construction records, historical operation and maintenance data, geographical information and environmental data along the pipeline route of the target heating network, and construct a three-dimensional geometric model of the target heating network based on existing BIM technology, marking the pipeline route, pipe diameter, material, connection method and the location and parameters of key equipment; By integrating BIM 3D geometric models with GIS technology and overlaying geographic coordinates, topography, and building distribution information along the pipeline network, a fluid dynamics model of the pipeline network is constructed based on existing CFD technology to simulate the flow state of the heating medium within the pipeline network, including the distribution patterns of temperature, pressure, and flow rate. The 3D geometric model, GIS spatial model, and CFD fluid dynamics model are integrated to form a complete digital twin model.

[0007] Preferably, the inspection status assessment and analysis process is as follows: T1: Extract real-time operation data of all nodes of the target heating network in batches from the synchronized digital twin model; T2: Retrieve historical operation and maintenance data, preset operating thresholds, and pipeline design parameters stored in the digital twin model to form a basic set of evaluation data; T3: Perform correlation matching between the extracted real-time operation data and historical data, and divide the evaluation units according to the pipeline network topology.

[0008] Preferably, it also includes T4: obtaining the core evaluation index Hj of each evaluation unit in the target heating network, j = 1, 2, 3, 4, and simultaneously obtaining the preset initial weight coefficient wj corresponding to each core evaluation index; T5: Obtain the basic indicators from each core evaluation indicator, and perform quantitative calculations on the quantitative indicators (including positive and negative indicators) and qualitative indicators in the basic indicators; T6: Calculate the target layer comprehensive score based on the formula, retrieve the preset target layer comprehensive score interval [MZmin, MZmax], perform discrimination processing on the target layer comprehensive score, and output the results of normal state, fault state and potential risk state; T7: Based on the comprehensive score of the target layer of each evaluation unit, the normal state, fault state and potential risk state of each evaluation unit are marked in the digital twin model to generate a heat map of the pipeline network operation status.

[0009] Preferably, the inspection fault location analysis process is as follows: Based on the heat map of pipeline network operation status, when a fault state or potential risk state is triggered, real-time sensor data associated with parameter values ​​exceeding preset parameter value thresholds are extracted, and the initial range of fault impact is determined by the sensor deployment location information. Visual image data of corrosion, settlement and damage on the outer wall of the pipeline within the initial range and temperature anomaly data corresponding to infrared thermal imaging are collected. At the same time, the thickness of corrosion and scaling on the inner wall of the pipeline are detected by an ultrasonic detector, and the condition of valve sealing surfaces and image data of blockages inside the pipeline are collected by a visual sensor and transmitted back to the digital twin model in real time.

[0010] Preferably, the collected visual image data is processed by image recognition to identify fault features. These features are then compared with the standard state dataset of the pipeline in the digital twin model to extract the image acquisition GPS coordinates corresponding to the fault features. Combined with the GIS spatial mapping relationship of the digital twin model, the preliminary location coordinates of the fault features in the target heating pipeline network are determined. The fault location coordinates are then clustered using existing clustering algorithms to determine the concentrated distribution area of ​​the fault features. Based on the center coordinates of the concentrated distribution area, the fault range is defined by expanding to both sides according to the pipeline direction to obtain the corrected fault area.

[0011] Preferably, the process for constructing and analyzing the inspection fault location list is as follows: By calling the BIM 3D geometric information of the digital twin model, the precise pipe diameter, material, connection method, and key node location parameters of elbows / valve in the target heating network within the fault area are obtained, and a local fine model is constructed in combination with the network topology. Using the degree of sensor parameter anomaly and the level of visual fault characteristics as input, combined with the historical fault location case library, a preset reverse reasoning algorithm is used to deduce the location of the fault point. The positioning deviation is corrected by the positioning optimization algorithm. The three-dimensional coordinates of the BIM model and the geographic coordinates of GIS are integrated to determine the precise three-dimensional coordinates (longitude, latitude, and depth) of the fault point. A fault location list is constructed based on the pipeline number, pipeline mileage, and names and numbers of associated equipment to which the fault point belongs. The location of the fault point is then visually marked in the digital twin model with a flashing red icon and a fault type label.

[0012] Preferably, the simulation evaluation and analysis process of the processing scheme is as follows: Based on the fault types in the fault location list, the preset handling schemes corresponding to the fault types are obtained, and the preset handling schemes are simulated. The simulation of the preset treatment plan is used to verify the effect in multiple dimensions, including effect compliance verification, safety compliance verification, and economic verification. The verification results of effect compliance verification, safety compliance verification, and economic verification are obtained, and the verification results include verification pass and verification fail. The number of successful verifications is obtained based on the verification results. The number of successful verifications is then processed until the preset processing scheme is deemed valid and output.

[0013] The beneficial effects of this invention are as follows: (1) This invention integrates BIM three-dimensional geometric model, GIS spatial information model and CFD fluid dynamics model to form a complete digital twin covering the geometric shape, spatial location and medium flow law of the pipeline network, so as to solve the problem of fragmented pipeline network information and ambiguous spatial positioning in traditional inspection. By constructing a hierarchical evaluation framework of core indicators and basic indicators, combined with quantitative and qualitative indicator quantification algorithms and comprehensive scoring discrimination mechanism, the objectivity and accuracy of inspection status evaluation are improved, and potential risks can be identified in advance.

[0014] (2) This invention also achieves three-dimensional accurate positioning of fault points through a multi-level positioning logic of initial range definition, preliminary location determination and precise coordinate optimization, which greatly shortens the fault location time and reduces the intensity of manual inspection. In addition, for fault handling solutions, a test process of scheme matching, simulation and multi-dimensional verification is designed to verify the effectiveness of the scheme from three dimensions: effect achievement, safety compliance and economy, to ensure the output of the optimal handling scheme, reduce operation and maintenance costs and ensure that the pipeline network can be quickly restored to normal operation. Attached Figure Description

[0015] The invention will now be further described with reference to the accompanying drawings; Figure 1 This is a reference diagram of the method of the present invention; Figure 2 This is a reference diagram for the thermal analysis of the pipeline network operation status in this invention. Detailed Implementation

[0016] 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.

[0017] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments; Example 1: Please refer to Figures 1 to 2 As shown, this invention is a heating network inspection method based on digital twin technology, comprising the following steps: Step 1: Basic Construction for Inspection: Based on BIM technology, a three-dimensional geometric model of the pipeline network is constructed, and GIS technology is integrated to overlay geographic coordinates, topography and building distribution information. Combined with CFD technology, a fluid dynamics model is constructed, and integrated to form a digital twin model of the heating pipeline network. Step 2: Multi-source inspection data acquisition and preprocessing: Collect multi-source inspection data, preprocess the multi-source inspection data to obtain standardized multi-source inspection data, and import it into the digital twin model to achieve data synchronization; Step 3: Inspection Status Assessment: Divide the assessment units according to the pipeline network topology, obtain the core assessment indicators and corresponding weights of each unit, decompose the basic indicators of the core assessment indicators and perform quantitative calculations, calculate the comprehensive score of the target layer based on the comprehensive score formula, and determine whether each assessment unit is in a normal state, a potential risk state, or a fault state by combining the preset score range. Step 4: Inspection and Fault Location: Generate a heat map of pipeline operation status based on the status judgment results. When a fault or potential risk state is triggered, determine the initial range of the fault by combining the deployment location of abnormal parameter sensors. Step 5: In-depth location: By identifying fault characteristics and combining GIS spatial mapping to determine the initial location of the fault, the K-means clustering algorithm is used to optimize the fault location, and the precise three-dimensional coordinates of the fault point are determined by integrating BIM and GIS coordinates. At the same time, a fault location list is constructed. Step Six: Simulation and Evaluation of Handling Solutions: Based on the fault location list, match the preset handling solutions and conduct simulation. Verify the effects of the simulation from multiple dimensions until the final preset handling solution is output. The process of building the inspection infrastructure in step one is as follows: Collect design data, construction records, historical operation and maintenance data, geographical information and environmental data along the pipeline route of the target heating network; Construct a three-dimensional geometric model of the target heating network based on existing BIM technology, and clarify the pipeline route, diameter, material, connection method, and location and parameters of key equipment; By integrating BIM 3D geometric models with GIS technology and overlaying information such as geographic coordinates, topography, and building distribution along the pipeline network, accurate mapping of the pipeline network's spatial location can be achieved. A fluid dynamics model of the pipeline network is constructed based on existing CFD technology to simulate the flow state of the heating medium in the pipeline network, including the distribution patterns of temperature, pressure, and flow rate. By integrating the three-dimensional geometric model, GIS spatial model, and CFD fluid dynamics model, a complete digital twin model is formed. At the same time, the multi-source inspection data of the real-time target heating network is preprocessed and imported into the digital twin model to achieve data synchronization of the target heating network. The multi-source inspection data includes: hot water temperature inside the pipe (range 45-60℃) collected by temperature sensors, pipe pressure (range 0.3-0.6MPa) collected by pressure sensors, medium flow rate (range 50-150m³ / h) collected by flow sensors, pump station vibration frequency (range 10-50Hz) and valve opening (0-100%) collected by vibration sensors, ambient temperature (-10-25℃) and humidity (30%-80%) collected by environmental sensors, images of the pipe outer wall collected by drones, images of the pipe interior collected by robots, and manually entered inspection records and historical operation and maintenance data. Step Two: Multi-source inspection data acquisition and preprocessing, specifically including: The preprocessing of multi-source inspection data includes data cleaning, data standardization, data fusion, and data denoising. Specifically, it involves: removing outlier data and missing values; converting data from different sources and in different formats into a unified standard format; fusing multi-source inspection data using a weighted average method or Bayesian estimation method; and denoising the fused data using wavelet transform or Kalman filtering algorithms to obtain standardized multi-source inspection data.

[0018] Example 2: Step 3: Inspection Status Assessment: Divide the assessment units according to the pipeline network topology, obtain the core assessment indicators and corresponding weights for each unit, decompose the basic indicators of the core assessment indicators and perform quantitative calculations, calculate the comprehensive score of the target layer based on the comprehensive score formula, and determine whether each assessment unit is in a normal state, a potential risk state, or a fault state based on the preset score range. Specifically, this includes: T1: Extract real-time operating data of all nodes of the target heating network in batches from the synchronized digital twin model, including core parameters such as temperature, pressure, flow rate, vibration frequency, and valve opening of each pipe section, valve, heat exchanger, pump station and other equipment, to ensure coverage of the main pipe, branch pipe and key equipment related nodes of the network; T2: Retrieve historical operation and maintenance data (fault records, maintenance records, and normal operating parameter ranges for the past 1-3 years), preset operating thresholds (such as industry standard or manufacturer-set values ​​for medium temperature 45-60℃, pipeline pressure 0.3-0.6MPa, etc.) and pipeline design parameters (pipe diameter, material, design flow rate, etc.) stored in the digital twin model to form a basic set of evaluation data; T3: Perform correlation matching between the extracted real-time operation data and historical data, and divide the evaluation units according to the pipeline network topology (such as main pipeline units, regional branch pipeline units, and key equipment related units) to ensure that no part of the evaluation scope is missed; T4: Obtain the core evaluation index Hj for each evaluation unit in the target heating network, j = 1, 2, 3, 4. The core evaluation index Hj includes operational stability H1, equipment health H2, energy utilization efficiency H3, and safety risk level H4 (the higher the level, the greater the risk, level 1-5). At the same time, obtain the preset initial weight coefficient wj corresponding to each core evaluation index. T5: Obtain the basic indicators from each core evaluation indicator, and perform quantitative calculations on the quantitative indicators (including positive and negative indicators) and qualitative indicators in the basic indicators. The quantitative formula for positive indicators is: S = (X - Xmin) / (Xmax - Xmin) × 100, and the quantitative formula for negative indicators is: S = (Xmax - X) / (Xmax - Xmin) × 100, where X is the indicator parameter, S is the quantitative value, Xmax is the maximum allowable value in the design, and Xmin is the minimum allowable value in the design. Qualitative indicators are quantified: Level 5 is assigned 100 points, Level 4 is assigned 80 points, Level 3 is assigned 60 points, Level 2 is assigned 40 points, and Level 1 is assigned 20 points. For example, the basic indicators among the core evaluation metrics are: Operational stability: parameter fluctuation range (whether temperature / pressure fluctuation exceeds ±5% within 10 consecutive minutes), parameter compliance rate (the percentage of time that real-time parameters are within the threshold), and the number of abnormal equipment start-ups and shutdowns; Equipment health: the percentage of equipment operating time to design life, corrosion / scaling related parameters (such as the percentage of corrosion area and simulated value of scale thickness), and historical fault recurrence rate; Energy utilization efficiency: the ratio of energy consumption per unit flow to design energy consumption, heat exchange efficiency (the ratio of the temperature difference between the inlet and outlet of the heat exchanger to the design temperature difference), and pipeline heat loss rate (comparison of actual heat loss in CFD simulation with theoretical value); Safety risk level: the cumulative duration of parameters exceeding the threshold and the fault evolution rate (the rate at which parameters deviate from the normal range in potential fault scenarios); T6: Calculate the target layer comprehensive score based on the formula, retrieve the preset target layer comprehensive score interval [MZmin, MZmax], and perform discrimination processing on the target layer comprehensive score: If the overall target score is less than MZmin, it is determined to be a fault state; if the overall target score is ∈ [MZmin, MZmax], it is determined to be a potential risk state; if the overall target score is greater than MZmax, it is determined to be a normal state. Among them, formula , where j represents the core evaluation indicator, wij represents the preset weight coefficient of the i-th indicator under the j-th core evaluation indicator, Si is the quantitative score of the i-th indicator under the j-th core evaluation indicator, m is the number of indicators under the j-th core evaluation indicator, and i and m are both natural numbers greater than zero. T7: Based on the comprehensive score of the target layer of each evaluation unit, the normal state, fault state and potential risk state of each evaluation unit are marked in the digital twin model to generate a heat map of the pipeline network operation status.

[0019] Example 3: Inspection fault location specifically includes: Based on the heat map of pipeline network operation status, when a fault state or potential risk state is triggered, real-time sensor data associated with parameter values ​​exceeding preset parameter value thresholds are extracted, and the initial range of fault impact is determined by the sensor deployment location information. For example, if the sensors that cause a continuous rise in temperature and a drop in pressure are concentrated in a 3-5km section of the main pipeline, then this section can be preliminarily identified as the approximate area of ​​the fault. Collect visual image data of pipeline outer wall corrosion, settlement, and damage within the initial range, as well as data of temperature anomaly areas corresponding to infrared thermal imaging; At the same time, the thickness of corrosion and scale on the inner wall of the pipeline are detected by ultrasonic detectors, and data such as the condition of valve sealing surfaces and images of blockages inside the pipeline are collected by visual sensors and transmitted back to the digital twin model in real time. Image recognition processing (such as using convolutional neural network algorithms) is performed on the collected visual image data to identify fault features such as settlement marks on the outer wall of the pipeline, outlines of blockages on the inner wall, and wear on valve sealing surfaces. These features are compared with the standard state dataset of the pipeline in the digital twin model to extract the image acquisition GPS coordinates corresponding to the fault features. Combined with the GIS spatial mapping relationship of the digital twin model, the preliminary location coordinates of the fault features in the target heating pipeline network are determined. Existing clustering algorithms (such as K-means algorithm) are used to perform cluster analysis on the fault location coordinates to determine the concentrated distribution area of ​​the fault features, eliminate isolated misidentified points, and use the center coordinates of the concentrated distribution area as a reference to expand to both sides according to the pipeline direction to define the fault range and obtain the corrected fault area. Among them, standard state data of corresponding pipe sections and valves are retrieved from the digital twin model, including: complete image of standard pipe outer wall, standard inner wall cross-sectional dimensions and image, image of valve sealing surface in good condition, standard coordinates of pipe axis, standard area of ​​pipe cross section and other parameters, to form a standard state dataset; The process of constructing a fault location list during inspections is as follows: By calling the BIM 3D geometric information of the digital twin model, the precise pipe diameter, material, connection method, elbow / valve and other key node location parameters of the target heating network in the fault area are obtained, and a local fine model is constructed in combination with the network topology. Using the degree of sensor parameter anomaly and the level of visual fault characteristics as input, combined with the historical fault location case library, the location of the fault point is deduced by a preset reverse reasoning algorithm. The location deviation is corrected by the location optimization algorithm (such as particle swarm optimization algorithm and least squares positioning algorithm). The three-dimensional coordinates of the BIM model and the geographic coordinates of GIS are integrated to determine the precise three-dimensional coordinates (longitude, latitude and depth) of the fault point. By linking the equipment ledger data in the digital twin model, the pipeline number, pipeline mileage, and names and numbers of associated equipment (such as adjacent valves, pump stations, and heat exchangers) to which the fault point belongs can be determined, thus completing the accurate location of the fault point; Based on information such as the pipeline number, pipeline mileage (e.g., 3.8km of the main pipeline ZG-008 section), and names and numbers of associated equipment (e.g., adjacent valves, pump stations, heat exchangers), a fault location list is constructed. Based on the fault location list, the fault location is intuitively marked in the digital twin model with a flashing red icon and a fault type label. It supports switching between three-dimensional perspectives, zooming in and out, and can be linked to view the surrounding pipeline network structure, equipment distribution, and real-time parameter changes. The simulation evaluation of the treatment plan specifically includes: Based on the fault type in the fault location list (such as partial blockage of pipeline), the preset handling scheme corresponding to the fault type is obtained, and the preset handling scheme is simulated. The simulation of the preset treatment plan is used to verify the effect in multiple dimensions, including effect compliance verification, safety compliance verification, and economic verification. The verification results of effect compliance verification, safety compliance verification, and economic verification are obtained, and the verification results include verification pass and verification fail. Among them, the effect verification is to compare the simulation results with the operation and maintenance plan targets (such as whether the flow rate after repair reaches 120m³ / h, whether the heating temperature is restored to 45-60℃, and whether the total operation time is controlled within 4 hours). Safety and compliance verification: Check whether there are any behaviors that exceed safety thresholds during the simulation process (such as pipeline pressure below 0.1MPa, excavation distance from gas pipeline less than 1.2m), and whether it complies with pipeline network operation and maintenance safety specifications and environmental protection requirements; Economic verification: Statistically analyze equipment energy consumption, material losses, and personnel costs during the simulation process to assess whether the plan involves excessive investment (such as redundant equipment selection or excessive personnel allocation). Based on the verification results, the number of verifications passed is obtained. If the number of verifications passed is not equal to 3, it is determined that the preset processing solution has a defect. The preset processing solution is then adjusted until it is determined to be effective. If the number of verifications passed is equal to 3, the preset processing solution is determined to be effective. The preset processing solution is then directly output to perform fault operation and maintenance management on the target heating network. In summary, by integrating BIM 3D geometric models, GIS spatial information models, and CFD fluid dynamics models, a complete digital twin covering the pipeline network's geometry, spatial location, and media flow patterns is formed. This addresses the issues of fragmented pipeline network information and ambiguous spatial positioning in traditional inspections. Furthermore, by constructing a hierarchical evaluation framework of core indicators and basic indicators, combined with quantitative and qualitative indicator quantification algorithms and a comprehensive scoring mechanism, a refined and intelligent evaluation of the pipeline network's operational status can be achieved. This improves the objectivity and accuracy of inspection status assessments and enables the early identification of potential risks. Simultaneously, through a multi-level positioning logic of initial range definition, preliminary location determination, and precise coordinate optimization, combined with sensor deployment location, image recognition technology, K-means clustering algorithm, and BIM and GIS coordinate fusion, the system achieves precise three-dimensional positioning of fault points, significantly shortening fault location time and reducing the intensity of manual inspections. Furthermore, for fault handling solutions, a testing process of solution matching, simulation, and multi-dimensional verification is designed to verify the effectiveness of the solution from three dimensions: effectiveness achievement, safety compliance, and economy, ensuring the output of the optimal handling solution, reducing operation and maintenance costs, and ensuring the rapid restoration of the pipeline network to normal operation.

[0020] The threshold is set for comparative analysis of results to determine whether they are good or bad. The value of the threshold is determined by a combination of large-scale model analysis of sample data and human experience. It can also be adjusted appropriately based on seasonal or common-sense influencing factors.

[0021] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A heating pipeline inspection method based on digital twin technology, characterized in that, Includes the following steps: Step 1: Basic Construction for Inspection: Based on BIM technology, a three-dimensional geometric model of the pipeline network is constructed, and GIS technology is integrated to overlay geographic coordinates, topography and building distribution information. Combined with CFD technology, a fluid dynamics model is constructed, and integrated to form a digital twin model of the heating pipeline network. Step 2: Multi-source inspection data acquisition and preprocessing: Collect multi-source inspection data, preprocess the multi-source inspection data to obtain standardized multi-source inspection data, and import it into the digital twin model to achieve data synchronization; Step 3: Inspection Status Assessment: Divide the assessment units according to the pipeline network topology, obtain the core assessment indicators and corresponding weights of each unit, decompose the basic indicators of the core assessment indicators and perform quantitative calculations, calculate the comprehensive score of the target layer based on the comprehensive score formula, and determine whether each assessment unit is in a normal state, a potential risk state, or a fault state by combining the preset score range. Step 4: Inspection and Fault Location: Generate a heat map of pipeline operation status based on the status judgment results. When a fault or potential risk state is triggered, determine the initial range of the fault by combining the deployment location of abnormal parameter sensors. Step 5: In-depth location: By identifying fault characteristics and combining GIS spatial mapping to determine the initial location of the fault, the K-means clustering algorithm is used to optimize the fault location, and the precise three-dimensional coordinates of the fault point are determined by integrating BIM and GIS coordinates. At the same time, a fault location list is constructed. Step Six: Simulation and Evaluation of the Treatment Plan: Based on the fault location list, match the preset treatment plan and conduct simulation. Verify the effect of the simulation from multiple dimensions until the final preset treatment plan is output.

2. The heating pipeline inspection method based on digital twin technology according to claim 1, characterized in that, The basic construction and analysis process for the inspection system is as follows: Collect design data, construction records, historical operation and maintenance data, geographical information and environmental data along the pipeline route of the target heating network, and construct a three-dimensional geometric model of the target heating network based on existing BIM technology, marking the pipeline route, pipe diameter, material, connection method and the location and parameters of key equipment; By integrating BIM 3D geometric models with GIS technology and overlaying geographic coordinates, topography, and building distribution information along the pipeline network, a fluid dynamics model of the pipeline network is constructed based on existing CFD technology to simulate the flow state of the heating medium within the pipeline network, including the distribution patterns of temperature, pressure, and flow rate. The 3D geometric model, GIS spatial model, and CFD fluid dynamics model are integrated to form a complete digital twin model.

3. The heating pipeline inspection method based on digital twin technology according to claim 1, characterized in that, The inspection status assessment and analysis process is as follows: T1: Extract real-time operation data of all nodes of the target heating network in batches from the synchronized digital twin model; T2: Retrieve historical operation and maintenance data, preset operating thresholds, and pipeline design parameters stored in the digital twin model to form a basic set of evaluation data; T3: Perform correlation matching between the extracted real-time operation data and historical data, and divide the evaluation units according to the pipeline network topology.

4. The heating pipeline inspection method based on digital twin technology according to claim 3, characterized in that, It also includes T4: obtaining the core evaluation index Hj of each evaluation unit in the target heating network, j = 1, 2, 3, 4, and obtaining the preset initial weight coefficient wj corresponding to each core evaluation index; T5: Obtain the basic indicators from each core evaluation indicator, and perform quantitative calculations on the quantitative indicators (including positive and negative indicators) and qualitative indicators in the basic indicators; T6: Calculate the target layer comprehensive score based on the formula, retrieve the preset target layer comprehensive score interval [MZmin, MZmax], perform discrimination processing on the target layer comprehensive score, and output the results of normal state, fault state and potential risk state; T7: Based on the comprehensive score of the target layer of each evaluation unit, the normal state, fault state and potential risk state of each evaluation unit are marked in the digital twin model to generate a heat map of the pipeline network operation status.

5. The heating pipeline inspection method based on digital twin technology according to claim 1, characterized in that, The process for fault location and analysis during inspection is as follows: Based on the heat map of pipeline network operation status, when a fault state or potential risk state is triggered, real-time sensor data associated with parameter values ​​exceeding preset parameter value thresholds are extracted, and the initial range of fault impact is determined by the sensor deployment location information. Visual image data of corrosion, settlement and damage on the outer wall of the pipeline within the initial range and temperature anomaly data corresponding to infrared thermal imaging are collected. At the same time, the thickness of corrosion and scaling on the inner wall of the pipeline are detected by an ultrasonic detector, and the condition of valve sealing surfaces and image data of blockages inside the pipeline are collected by a visual sensor and transmitted back to the digital twin model in real time.

6. The heating pipeline inspection method based on digital twin technology according to claim 5, characterized in that, Image recognition processing is performed on the collected visual image data to identify fault features. These features are then compared with the standard state dataset of the pipeline in the digital twin model to extract the GPS coordinates of the images corresponding to the fault features. Combined with the GIS spatial mapping relationship of the digital twin model, the preliminary location coordinates of the fault features in the target heating pipeline network are determined. Existing clustering algorithms are used to perform cluster analysis on the fault location coordinates to determine the concentrated distribution area of ​​the fault features. Using the center coordinates of the concentrated distribution area as a reference, the fault range is defined by expanding to both sides according to the pipeline direction to obtain the corrected fault area.

7. The heating pipeline inspection method based on digital twin technology according to claim 6, characterized in that, The process of constructing and analyzing the inspection fault location list is as follows: By calling the BIM 3D geometric information of the digital twin model, the precise pipe diameter, material, connection method, and key node location parameters of elbows / valve in the target heating network within the fault area are obtained, and a local fine model is constructed in combination with the network topology. Using the degree of sensor parameter anomaly and the level of visual fault characteristics as input, combined with the historical fault location case library, a preset reverse reasoning algorithm is used to deduce the location of the fault point. The positioning deviation is corrected by the positioning optimization algorithm. The three-dimensional coordinates of the BIM model and the geographic coordinates of GIS are integrated to determine the precise three-dimensional coordinates (longitude, latitude, and depth) of the fault point. A fault location list is constructed based on the pipeline number, pipeline mileage, and names and numbers of associated equipment to which the fault point belongs. The location of the fault point is then visually marked in the digital twin model with a flashing red icon and a fault type label.

8. The heating pipeline inspection method based on digital twin technology according to claim 1, characterized in that, The simulation evaluation and analysis process of the treatment scheme is as follows: Based on the fault types in the fault location list, the preset handling schemes corresponding to the fault types are obtained, and the preset handling schemes are simulated. The simulation of the preset treatment plan is used to verify the effect in multiple dimensions, including effect compliance verification, safety compliance verification, and economic verification. The verification results of effect compliance verification, safety compliance verification, and economic verification are obtained, and the verification results include verification pass and verification fail. The number of successful verifications is obtained based on the verification results. The number of successful verifications is then processed until the preset processing scheme is deemed valid and output.

Images