A method and system for real-time monitoring of leaks in thermal pipelines based on soil environment

Abstract

The application discloses a heat pipeline leakage monitoring system based on soil environment real-time monitoring, which comprises a leakage monitoring sensor, a heat conduction characteristic database, a data processing module and a preplan control module; a heat conduction model is established based on a heat pipeline leakage monitoring method of soil environment real-time monitoring, and model checking identification and leakage type pre-judgment are carried out according to digital twin soft measurement and real-time acquisition of temperature data; an AHP hierarchical analysis method is adopted to construct a hierarchical structure model for deductive analysis, to confirm the leakage category and the leakage point and to show them on a GIS map, and to generate preplan control instructions to preplan and control the Internet of Things equipment in the leakage point area; the application can collect temperature sensing data in real time through the leakage monitoring sensor buried outside the heat pipeline, accurately evaluate and pre-judge the real-time leakage monitoring of the heat pipeline by combining a simulation model, quickly identify the leakage type and the leakage point and make emergency preplan control, and improve the efficiency and accuracy of heat pipeline leakage monitoring.

Description

Technical Field

[0001] This invention belongs to the field of smart heating, specifically relating to a method and system for monitoring leaks in heating pipelines based on real-time monitoring of the soil environment. Background Technology

[0002] Heating pipelines are a crucial component of urban heating systems, and their safe operation directly impacts the quality of life and energy efficiency for urban residents. However, due to long-term use, aging, corrosion, and external damage, heating pipelines may experience leaks or large-scale spills, leading to serious consequences such as unstable heating, energy waste, environmental pollution, and safety hazards. Therefore, timely and effective monitoring of heating pipeline leaks is a vital means of ensuring their safe operation.

[0003] Leakage monitoring technology for heating pipelines is a crucial supporting technology for urban heating systems. Its purpose is to promptly detect and address faults in the heating network by real-time monitoring and analysis of parameters such as temperature, pressure, and flow rate, ensuring the safe, stable, and efficient operation of the heating system. Urban heating network monitoring technology involves multiple disciplines, including thermodynamics, fluid mechanics, signal processing, control theory, and information technology, making it a comprehensive and interdisciplinary technical field.

[0004] Currently, commonly used methods for monitoring leaks in thermal pipelines include pressure testing, temperature testing, acoustic testing, and infrared testing. Each of these methods has its advantages and disadvantages, but they all share some common problems, such as low monitoring accuracy, limited monitoring range, high monitoring cost, and the influence of various factors on the monitoring results. Therefore, how to comprehensively utilize multiple monitoring methods and data to improve the efficiency and accuracy of thermal pipeline leak monitoring is a pressing technical challenge that needs to be addressed. Summary of the Invention

[0005] The purpose of this invention is to solve the above-mentioned problems and provide a real-time monitoring system for leaks in thermal pipelines based on soil environment. This system can use temperature sensors to collect temperature data of thermal pipelines and surrounding soil, analyze temperature data changes through a thermal conductivity database and thermal conductivity model, determine the type and location of leaks through a data analysis submodule, and quickly make contingency plans and adjustments, thereby improving the efficiency and accuracy of thermal pipeline leak monitoring.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0007] This invention proposes a real-time soil environment monitoring system for monitoring leaks in thermal pipelines, comprising a leak monitoring sensor, a thermal conductivity database, a data processing module, and a contingency control module; the data processing module includes: a data analysis submodule, a data prediction submodule, and a leak location submodule;

[0008] The leakage monitoring sensors are buried in sections in the controllable underground soil around the heating pipeline to collect temperature data of the underground heat transfer area of ​​the heating pipeline in real time.

[0009] The thermal conductivity database is used to record the thermal conductivity parameters of the heating pipeline and the surrounding soil, and to establish a thermal conductivity model.

[0010] The data analysis submodule accesses the digital twin simulation model of the heating pipeline. Based on the water supply temperature and pressure of the entire heating pipeline network and the measured flow data of the heating station, it calculates the theoretical values ​​of temperature, pressure and flow of the entire heating pipeline network. These values ​​are then used as soft measurement data for the heat conduction model. Combined with the real-time collected temperature data of the underground heat transfer area of ​​the heating pipeline, the heat conduction model is verified and identified.

[0011] The data prediction submodule is pre-set with soil temperature change models for thermal pipelines under different conditions, and predicts the leakage type based on real-time collected temperature data;

[0012] The leak location submodule uses the Analytic Hierarchy Process (AHP) to construct a hierarchical model for deduction and analysis, and to confirm the leak type and leak location.

[0013] The contingency control module generates control schemes based on the leak location and leak type, and can optionally send corresponding control commands to the automatic control system to perform rapid pre-processing of leak accidents.

[0014] The system supports soft measurement of the entire heating system's operational parameters by accessing a digital twin simulation model of the heating pipeline. By acquiring the temperature and pressure of the heat source water supply and the measured flow data of the heating stations, it can quickly calculate the temperature, pressure, and flow distribution across the entire heating pipeline network. It accurately obtains temperature, pressure, and flow data in the pipeline's "meter monitoring blind spots," enabling online perception and monitoring of the entire network's operational status. Furthermore, based on the soft measurement results, it provides early warning information for potential operational faults in the actual heating pipeline leakage monitoring system.

[0015] Soft measurement complements physical measurement. By integrating real-time system operating status data into a digital twin simulation model of the thermal pipeline, and following the system's operation, it can repeatedly perform full-process simulation calculations at set intervals to obtain theoretical values ​​of the entire network's operating status parameters (temperature, pressure, flow direction, and flow rate). These theoretical values ​​can be considered a virtual measurement of the thermal pipeline. The system can combine topology diagrams or GIS maps to display pressure distribution maps, temperature distribution maps, flow velocity distribution maps, etc., enabling operators to monitor fluid flow direction, velocity, real-time station heating status, and heat source demand load in the pipeline network in real time.

[0016] Here, data source access is supported in three main ways: connecting to SQL Server, MySQL, Oracle, and PostgreSQL databases; other database types, OPC, or API interfaces require data to be placed in the aforementioned intermediate database to achieve matching and correspondence between data source information and system information.

[0017] Furthermore, it also includes: the leak monitoring sensor is a temperature capsule, which incorporates a temperature sensor and a wireless communication device including GIS positioning. Multiple temperature capsules are buried in the underground soil of the heating pipeline within segmented areas where wireless signals can be received; the burial locations are uniform and controllable.

[0018] A temperature capsule is a device that integrates temperature sensors and wireless communication technology to monitor leaks and operational status in heating pipe networks. It can be buried next to pipelines and detects abnormal changes in the heating pipeline by collecting and transmitting real-time temperature data around the pipeline. Temperature capsules can effectively reduce water loss in heating pipe networks, improve the safety and efficiency of heating systems, and save energy and costs.

[0019] The temperature capsule is a cylindrical or spherical sealed container made of stainless steel or other high-temperature, corrosion-resistant, and pressure-resistant materials. Inside, it contains a battery, a microcircuit board, a temperature sensor, and a GIS positioning wireless communication module. The wireless communication module uses Bluetooth, Wi-Fi, ZigBee, LoRa, or other low-power, long-range, and highly reliable wireless communication technologies for bidirectional communication with the data center.

[0020] Furthermore, the thermal conductivity database is used to record the thermal conductivity influence parameters of the heating pipeline and the surrounding soil, and to establish a thermal conductivity model, as follows:

[0021] The thermal conductivity database collects and inputs physical property data of thermal pipelines and surrounding soil as parameters affecting thermal conductivity, including but not limited to material, structure, thickness, density, specific heat capacity, and thermal conductivity.

[0022] Based on the physical properties of the heating pipe, such as its material, structure, thickness, density, specific heat capacity, and thermal conductivity, as well as the physical properties of the surrounding soil, such as its type, moisture content, density, specific heat capacity, and thermal conductivity,

[0023] An equivalent thermal conductivity model is selected to describe the thermal conductivity characteristics of the heating pipeline and the surrounding soil. Heat conduction equations for the heating pipeline and the surrounding soil are established, such as Fourier's law and the heat diffusion equation. Thermal conductivity influence parameters and soft measurement data of the heating pipeline in the area are input into the thermal conductivity database to solve for the temperature distribution and heat flux density of the heating pipeline and the surrounding soil.

[0024] Here, the equivalent thermal conductivity model can simplify the complex heat conduction process by representing materials or structures with different thermal properties with an equivalent thermal conductivity, thereby reducing the amount of calculation and model complexity. It can also be applied to different operating conditions and environments. By adjusting the parameters or structure of the equivalent thermal conductivity, the adaptability and sensitivity of the model can be improved. It can be easily combined with other thermal models or simulation software. By inputting or outputting the equivalent thermal conductivity, thermal analysis and optimization of different thermal elements or systems can be achieved.

[0025] The data analysis submodule is used to analyze real-time temperature data changes combined with soft measurement data of thermal pipelines in the area, and to verify and identify the real-time measurement data under different operating conditions in the heat conduction model, as follows:

[0026] (1) Read the real-time temperature data from the leak monitoring sensor, store it in the memory of the data analysis module, and perform filtering, smoothing, and noise reduction to improve the quality and availability of the data.

[0027] (2) Based on the temperature distribution and heat flux density obtained from the heat conduction model and the soft measurement data of the heat pipeline in the area, calculate the heat conduction parameters of the heat pipeline and the surrounding soil, such as thermal conductivity, specific heat capacity, density, etc., and compare them with the parameters in the heat conduction characteristic database to evaluate the degree of model verification.

[0028] (3) If the verification degree of the model does not meet the preset threshold, adjust the structure and parameters of the heat conduction model and repeat steps (2) to (3) until the verification degree of the model reaches a satisfactory level.

[0029] (4) Based on the heat conduction model, calculate the heat conduction characteristics of the heat pipeline and the surrounding soil, such as thermal resistance, thermal inertia, and thermal diffusivity, and perform correlation analysis with the real-time temperature data to evaluate the recognition degree of the model.

[0030] (5) If the recognition level of the model does not meet the preset threshold, adjust the structure or parameters of the heat conduction model and repeat steps (2) to (5) until the recognition level of the model reaches the threshold.

[0031] (6) Output the verified and identified heat conduction model and the verification and identification indicators of the model, such as consistency index, consistency ratio, correlation coefficient, etc.

[0032] Furthermore, the data prediction submodule is pre-configured with a soil temperature change model for the thermal pipeline under different conditions, and predicts the leakage type based on the real-time collected temperature data, as follows:

[0033] (1) Based on different leakage types, such as pipeline rupture, pipeline corrosion leakage, pipeline weld leakage, etc., different leakage locations, leakage temperatures, leakage flow rates and other parameters are preset as boundary conditions, and the heat conduction equation is solved again to obtain the temperature distribution and heat flux density under different leakage types.

[0034] (2) The temperature distribution and heat flux density under different leakage types are used as the input of the data prediction submodule. A classification model for leakage type identification is established based on the decision tree. The parameters and weights of the model are trained, and the accuracy and stability of the model are evaluated.

[0035] (3) Read the real-time temperature data from the leak monitoring sensor and use it as the input of the data prediction submodule. Use the trained classification model to predict the leak type and output the prediction result and confidence level.

[0036] Furthermore, the leak location submodule employs the Analytic Hierarchy Process (AHP) to construct a hierarchical model for deduction and analysis, confirming the leak location and displaying it on a GIS map, as detailed below:

[0037] (1) Based on the real-time collected temperature data, input the trained classification model in the data prediction submodule, predict the leakage type, and output the prediction result and confidence level;

[0038] (2) Based on the thermal conductivity database and thermal conductivity model, determine the criteria level for leak monitoring, that is, the factors that affect the type of leak, including but not limited to soil temperature, soil moisture, pipeline temperature, pipeline pressure, and pipeline flow rate.

[0039] (3) Based on the distribution and sampling frequency of the leak monitoring sensors, determine the scheme level of leak monitoring, namely, temperature data of different areas and time periods;

[0040] (4) Determine the judgment matrix between each level based on historical data;

[0041] (5) Calculate the maximum eigenvalue and eigenvector of each judgment matrix to obtain the weight vector of each level;

[0042] (6) Calculate the consistency index and consistency ratio of each judgment matrix, check the consistency of each judgment matrix, and if they are inconsistent, adjust the judgment matrix until the consistency requirements are met.

[0043] (7) Calculate the total ranking vector based on the weight vectors of each level;

[0044] (8) Determine the maximum and minimum leakage types based on the total sorting vector;

[0045] (9) Based on the optimal leakage type and the worst leakage type, the results of leakage monitoring are divided into levels, namely leakage levels; where the optimal leakage type is the most likely leakage situation; and the worst leakage type is the least likely leakage situation.

[0046] (10) At the same time, input the real-time collected temperature data into the verified heat conduction model to confirm the leak location and lock the leak area by associating it with the GIS location of the temperature capsule.

[0047] Furthermore, the contingency control module generates contingency control instructions based on the leakage type and leakage location, and transmits them through an interface to the intelligent control and scheduling system where the thermal pipeline is located. In response to the contingency control instructions, it performs pre-control and scheduling of the IoT control devices associated with the leakage area.

[0048] Specifically, it also includes: setting the response command range, and selectively responding to the planned control commands based on the safety control range of the IoT control equipment and the actual operation of the thermal pipeline.

[0049] Specifically, it also includes an alarm display submodule, which is used to associate with the leak location submodule, respond to the confirmation of the leak location, and display it intuitively in the form of a GIS map, with different leak levels distinguished and marked by different colors or symbols.

[0050] A method for monitoring leaks in thermal pipelines based on real-time soil environmental monitoring includes the following steps:

[0051] (1) Temperature sensors are buried in sections in the underground soil around the controllable perimeter of the heating pipeline to collect temperature data of the underground heat transfer area of ​​the heating pipeline in real time.

[0052] (2) Record the thermal conductivity parameters of the heating pipeline and the surrounding soil, and establish a thermal conductivity database and thermal conductivity model;

[0053] (3) Analyze the changes in real-time temperature data and the soft measurement data of thermal pipelines in the area, and verify and identify the real-time measurement data under different working conditions in the heat conduction model.

[0054] (4) Pre-install a soil temperature change model for the thermal pipeline under different conditions, and predict the leakage type based on the real-time temperature data collected;

[0055] (5) Using the AHP (Analytical Hierarchy Process) method, a hierarchical model was constructed for deduction and analysis to confirm the leakage type and locate the leakage point;

[0056] (6) Generate control instructions based on the leakage type and the location of the leak, and selectively perform pre-control scheduling on IoT control devices in the leakage area.

[0057] (7) The location of the leak will be displayed and alerted in the form of a GIS map.

[0058] The beneficial effects of this invention are:

[0059] (1) By using temperature sensors to collect temperature data of thermal pipelines and surrounding soil, and by analyzing the changes in temperature data through thermal conductivity database and thermal conductivity model, the type and location of leaks can be accurately determined, thereby improving the efficiency and accuracy of thermal pipeline leak monitoring.

[0060] (2) The heat conduction model is verified and identified using the data analysis module. The soil temperature change model of the heat pipeline under different conditions is pre-set, which can adapt to different working conditions and environments and improve the adaptability and sensitivity of heat pipeline leakage monitoring.

[0061] (3) Using GIS graphics to display monitoring results can facilitate operators to observe and handle them, and improve the efficiency of investigating and diagnosing leaks in heating pipelines.

[0062] (4) Associated intelligent control system, rapid response to leak diagnosis, timely control of associated equipment in the leak area based on the pre-plan control instructions, effectively reducing economic losses from leaks.

[0063] (5) Improve the accuracy of leak monitoring by combining physical measurement, online soft measurement and real-time online simulation model.

[0064] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0065] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0066] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0067] Figure 1 This is a diagram of the architecture of a real-time soil environment monitoring system for monitoring leaks in thermal pipelines, based on the present invention.

[0068] Figure 2 This is a schematic diagram of the leakage monitoring logic of the present invention;

[0069] Figure 3 This is a flowchart of the method for real-time monitoring of thermal pipeline leaks based on soil environment, as proposed in this invention. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions 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, 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.

[0071] Example 1

[0072] This embodiment provides a real-time soil environment monitoring system for monitoring leaks in thermal pipelines, such as... Figure 1 As shown, its specific components are as follows:

[0073] The system includes a thermal pipeline 1, multiple temperature capsules 2 (21, 22…2n), a thermal conductivity database 3, and a data processing module 4. The data processing module 4 includes a data analysis submodule 41, a data prediction submodule 42, a leak location submodule 43, a display and alarm submodule 44, and a contingency control module 5.

[0074] Multiple temperature capsules 2 (21, 22…2n) are buried in the controllable surrounding underground soil of the heating pipeline 1 in equal segments. Each temperature capsule 2 is installed within 100 meters of the heating pipeline 1, at a distance of about 15cm from the pipeline radius.

[0075] The temperature data of the heating pipeline 1 and the surrounding soil are collected in real time and sent to the data processing module 4 via wireless signal.

[0076] Thermal conductivity database 3 is a database stored within data processing module 4. It records the physical properties of the heating pipeline and surrounding soil, including material, structure, thickness, density, specific heat capacity, and thermal conductivity, as well as operating parameters such as temperature, pressure, and flow rate of the heating pipeline. Based on these parameters, an equivalent thermal conductivity model is used to describe the thermal conductivity characteristics of the heating pipeline and surrounding soil, establishing heat conduction equations such as Fourier's law and the heat diffusion equation to solve for the temperature distribution and heat flux density of the heating pipeline and surrounding soil. The data sources for thermal conductivity database 3 are: the "Heating Pipeline Design Manual" and a soil physical property database.

[0077] The data processing module 4 is a PC-based computer component. The data analysis submodule 41 connects to the MySQL database of the digital twin online simulation model of the entire heating pipeline network via an API interface to calculate the theoretical values ​​of temperature, pressure, and flow rate of the entire heating pipeline network in real time. Simultaneously, it receives temperature data sent by temperature capsule 2, analyzes temperature data changes based on the thermal conductivity database 3 and the thermal conductivity model, and verifies and identifies the real-time measurement data under different operating conditions in the thermal conductivity model. The data prediction submodule 42 pre-sets the soil temperature change model of heating pipeline 1 under different leakage conditions, predicts the leakage type based on the real-time collected temperature data, and classifies the leakage degree, such as no leakage, small-scale leakage, medium-scale leakage, large-scale leakage, etc. Based on the leakage location submodule 43, it uses the AHP (Analytic Hierarchy Process) to construct a hierarchical model for deduction and analysis, confirms the location and degree of leakage, and outputs the monitoring results. The alarm display submodule 44 responds to the confirmation of the leakage location and displays it intuitively in the form of a GIS map, with different leakage levels distinguished and marked by different colors or symbols.

[0078] The software platform for data processing module 4 can be Matlab, and its main functions include:

[0079] Data preprocessing: Filtering, smoothing, and denoising the temperature data to improve its quality and usability;

[0080] Thermal conductivity model selection: Based on the parameters in thermal conductivity database 3, select an appropriate thermal conductivity model, such as the equivalent thermal conductivity model, the effective medium theory model, the fractal theory model, etc., to describe the thermal conductivity characteristics of the thermal pipeline and the surrounding soil.

[0081] Solving the heat conduction equation: Based on the heat conduction model, establish the heat conduction equation, such as Fourier's law and the heat diffusion equation, and solve for the temperature distribution and heat flux density of the heat pipeline and the surrounding soil.

[0082] Model verification and identification: Based on temperature distribution and heat flux density, calculate the thermal conductivity parameters of the heating pipeline and surrounding soil, such as thermal conductivity, specific heat capacity, and density. Compare these parameters with those in the thermal conductivity characteristic database 3 to evaluate the degree of model verification, such as consistency index and consistency ratio. If the degree of model verification does not meet the preset threshold, adjust the structure or parameters of the thermal conductivity model and repeat the above steps until the degree of model verification reaches a satisfactory level. Based on the thermal conductivity model, calculate the thermal conductivity characteristic values ​​of the heating pipeline and surrounding soil, such as thermal resistance, thermal inertia, and thermal diffusivity. Perform correlation analysis with real-time acquired temperature data to evaluate the degree of model identification, such as correlation coefficient. If the degree of model identification does not meet the preset threshold, adjust the structure or parameters of the thermal conductivity model and repeat the above steps until the degree of model identification reaches a satisfactory level.

[0083] Leakage type prediction: Based on different leakage types, such as pipeline rupture, pipeline corrosion leakage, pipeline weld leakage, etc., different leakage locations, leakage temperatures, leakage flow rates and other parameters are preset as boundary conditions, and the heat conduction equation is solved again to obtain the temperature distribution and heat flux density under different leakage types.

[0084] The temperature distribution and heat flux density under different leakage types are used as inputs to the data prediction submodule 42 to establish a classification model for leakage type identification, such as decision tree, support vector machine, neural network, etc., train the parameters and weights of the model, and evaluate the accuracy and stability of the model.

[0085] The real-time temperature data is used as input to the leak location submodule 43. Using the trained classification model, the leak type and degree of leakage are predicted, such as no leak, small-scale leak, medium-scale leak, large-scale leak, etc., as well as the location and extent of the leak, and the monitoring results are output.

[0086] The alarm display submodule 44 is an LCD screen that receives monitoring results from the leak location submodule 43 and displays them on the screen in graphical or textual form for easy observation and handling by operators. The alarm display submodule 44 has a resolution of 1920×1080 and displays the following content:

[0087] A plan of the heating pipeline, marking the location and number of temperature sensors, as well as the location and type of leaks;

[0088] A cross-sectional view of the heating pipeline shows the temperature distribution and heat flux density of the heating pipeline and the surrounding soil, as well as the location and extent of the leak;

[0089] Operating parameters of the heating pipeline, such as temperature, pressure, and flow rate, as well as leakage parameters, such as leakage location, leakage temperature, and leakage flow rate;

[0090] Model verification and identification metrics, such as consistency metrics, consistency ratio, correlation coefficient, etc., as well as accuracy and stability metrics of classification models for leakage type identification, such as precision and recall.

[0091] The contingency control module 5 generates contingency control instructions based on the output monitoring results and sends them to the intelligent control system for further rapid pre-control.

[0092] Here, this system can connect to the intelligent control system via an interface. The intelligent control system can serve as an optimization and scheduling system for the smart heating system, enabling rapid diagnosis and control of its IoT-managed equipment through responses to control commands. The interface can optionally include HTTP, Web Service, or API interfaces.

[0093] Example 2

[0094] A method for monitoring leaks in thermal pipelines based on real-time soil environmental monitoring, such as... Figure 2 As shown, it includes the following steps:

[0095] S1: Install liquid level and temperature sensors in sections in the underground soil around the controllable perimeter of the heating pipeline to collect temperature data of the underground heat transfer area of ​​the heating pipeline in real time.

[0096] S2: Record the thermal conductivity parameters of the heating pipeline and the surrounding soil, and establish a thermal conductivity database and thermal conductivity model;

[0097] S3: Analyze the changes in real-time acquired temperature data and the soft measurement data of the thermal pipeline in the area, and verify and identify the model based on the real-time measurement data under different working conditions in the heat conduction model;

[0098] S4: Pre-installed thermal pipeline soil temperature change model under different conditions, predict the leakage type based on real-time temperature data;

[0099] S5: The AHP (Analytical Hierarchy Process) method is used to construct a hierarchical model for deduction and analysis, to confirm the leakage type and locate the leakage point;

[0100] S6: Generates pre-plan control instructions based on the leakage type and leakage location, and can selectively perform pre-control scheduling for IoT control devices in the leakage area.

[0101] S7: The identified leak locations will be visually displayed and alerted in the form of a GIS map.

[0102] like Figure 3 The diagram shows the leakage monitoring logic; step S2, establishing the thermal conductivity database and thermal conductivity model, is as follows:

[0103] Assume the thermal conductivity of the heating pipeline and the surrounding soil are λ1 and λ2, the specific heat capacity is c1 and c2, the density is ρ1 and ρ2, the radius of the heating pipeline is r0, and the thickness of the soil is h.

[0104] Assuming the thermal conductivity of the heating pipeline and surrounding soil can be described by an equivalent thermal conductivity model, i.e.:

[0105]

[0106] Assume that the heat conduction equation of the heating pipeline and the surrounding soil can be described by the heat diffusion equation, that is:

[0107]

[0108] Where T is temperature, t is time, and r is the radius from the center of the heating pipe;

[0109] Assume the temperature of the heating pipeline is T0, and the temperature of the surrounding environment is T. a If the heat loss coefficient of the heating pipeline is k, then the boundary conditions are:

[0110] T(r0,t)=T0-k(t-t0);

[0111] T(r0+h,t)=T a ;

[0112] T(r,t0)=T a ,

[0113] Where t0 is the initial time;

[0114] Assume there is a leak in the heating pipeline, and the location of the leak is r. l The leakage temperature is T l The boundary conditions are:

[0115] T(r l ,t)=T l ;

[0116] Based on the heat conduction equation and boundary conditions, solve for the temperature distribution and heat flux density of the heat pipes and surrounding soil:

[0117]

[0118] Step S3: Analyze the changes in real-time acquired temperature data, and verify and identify the model based on the real-time measurement data under different operating conditions in the heat conduction model, as detailed below:

[0119] (1) Assume that the number of temperature capsules is n, and the position of each sensor is r. i The temperature data collected by each temperature capsule is T. i (t), where i = 1, 2, ..., n, and t is time;

[0120] (2) Based on the temperature distribution and heat flux density, calculate the thermal conductivity parameters of the heating pipeline and surrounding soil, such as λ1, λ2, c1 and c2, ρ1 and ρ2, k, etc., and compare them with the parameters in the thermal conductivity database to evaluate the model's verification degree, such as consistency index:

[0121]

[0122] Consistency ratio Where RI is the random consistency index. For T i The average value of (t);

[0123] (3) If the verification degree of the model does not meet the preset threshold, adjust the structure and parameters of the heat conduction model and repeat steps (2) to (3) until the verification degree of the model reaches a satisfactory level.

[0124] (4) Based on the heat conduction model, calculate the heat conduction characteristics of the heating pipeline and the surrounding soil, such as:

[0125] Thermal resistance:

[0126] Thermal inertia:

[0127] Thermal diffusivity:

[0128] Correlation analysis is performed with real-time acquired temperature data to assess the model's accuracy; for example, the correlation coefficient:

[0129]

[0130] (5) If the recognition level of the model does not meet the preset threshold, adjust the structure or parameters of the heat conduction model and repeat steps (2) to (5) until the recognition level of the model reaches the threshold.

[0131] (6) Output the verified and identified heat conduction model and the verification and identification indicators of the model, such as consistency index, consistency ratio, correlation coefficient, etc.

[0132] S4: A model of soil temperature variation under different conditions for pre-installed heating pipelines. Based on real-time temperature data, the model predicts the type of leakage, as detailed below:

[0133] (1) Based on different leakage types, such as pipe rupture, pipe leakage, and loose pipe joints, different leakage locations, leakage temperatures, and leakage flow rates are preset as boundary conditions. The heat conduction equation is then resolved to obtain the temperature distribution and heat flux density under different leakage types. In the above steps, a heat source S inside the soil is added to the heat conduction equation.

[0134]

[0135] (2) The temperature distribution and heat flux density under different leakage types are used as the input of the data prediction submodule. A classification model for leakage type identification is established based on the decision tree. The parameters and weights of the model are trained, and the accuracy and stability of the model are evaluated.

[0136] The boundary conditions are:

[0137] T(r=0,t)=T S (t);

[0138]

[0139] Among them, T S (t) represents the surface temperature, L represents the soil layer thickness, and Q... L (t) represents the leakage heat flux;

[0140] (3) Read the real-time temperature data collected from the temperature capsule and use it as the input of the data prediction submodule. Use the trained classification model to predict the leakage type and output the prediction results and confidence level.

[0141] The classification model for leak type identification is: y = f(T1, T2, ..., T n )

[0142] Where y is the leakage type, T1, T2, ..., T n For temperature data at different depths, f is a classification function, such as decision tree, support vector machine, neural network, etc.

[0143] S5: Using the Analytic Hierarchy Process (AHP), a hierarchical model is constructed for deductive analysis to preliminarily determine the location of the leak, as follows:

[0144] (1) Based on the real-time collected temperature data, determine the target level of leakage monitoring, i.e. the leakage type, set as: T={t1,t2,t3,t4}, where t1 represents no leakage, t2 represents small-scale leakage, t3 represents medium-scale leakage, and t4 represents large-scale leakage.

[0145] (2) Based on the thermal conductivity database and the modified thermal conductivity model, the criteria level for leak monitoring is determined, namely the factors affecting the type of leak, which are set as: C={c1,c2,c3,c4,c5}, where c1 represents soil temperature, c2 represents soil moisture, c3 represents pipeline temperature, c4 represents pipeline pressure, and c5 represents pipeline flow rate.

[0146] (3) Calculate the temperature distribution and heat flux density to determine whether there is a leak in the heating pipeline, and the location and extent of the leak, such as when T (r,t) An abnormal decrease or q (r,t) When an abnormal increase occurs, it is considered that a leak exists, and the location of the leak is r_l;

[0147] (4) Based on the distribution and sampling frequency of the leak monitoring sensors, determine the levels of the leak monitoring scheme, i.e., the temperature data for different areas and time periods, denoted as:

[0148] S = {s1, s2, ..., c} n}, where s i This represents the temperature data for the i-th region and time period;

[0149] (5) Based on historical data, determine the judgment matrix between each level, that is, the relative importance of each factor to the leakage type or the relative contribution of each temperature data to each factor, denoted as:

[0150] A = (a ij ) m×n

[0151] Where a ij This indicates the importance of the i-th factor relative to the j-th factor, or the contribution of the i-th temperature data to the j-th factor, where m represents the number of factors or the number of temperature data.

[0152] (6) Calculate the maximum eigenvalue and eigenvector of each judgment matrix to obtain the weight vector of each level, that is, the comprehensive influence of each factor on the leakage type or the comprehensive evaluation of each temperature data on the leakage type, denoted as:

[0153] W = (w1, w2, ..., w n ) T

[0154] Where w i This represents the weight of the i-th factor or the evaluation of the i-th temperature data, satisfying AW = λ. max W, where λ max This represents the largest eigenvalue of the judgment matrix;

[0155] (7) Calculate the consistency index and consistency ratio of each judgment matrix, check the consistency of each judgment matrix, and if there is any inconsistency, adjust the judgment matrix until the consistency requirement is met.

[0156] Let the consistency index be:

[0157] The consistency ratio is:

[0158] RI is the random consistency index. When CR < 0.1, the consistency of the judgment matrix is ​​considered to be within the acceptable range.

[0159] (8) Calculate the overall ranking vector based on the weight vectors of each level, which is the comprehensive ranking of each temperature data for each leakage type, denoted as:

[0160] V = (v ij ) n×k

[0161] Where v ij This represents the sorting of the i-th temperature data with respect to the j-th leakage type, where n represents the number of temperature data points, k represents the number of leakage types, and V = SW, where S = (s ij ) n×mThe weight matrix of the temperature data layer to the factor layer is W = (w ij ) m×k This is the weight matrix of the factor layer to the leakage type layer;

[0162] (9) Based on the total sorting vector, determine the optimal leakage type, i.e., the most likely leakage situation, and the worst leakage type, i.e., the least likely leakage situation, denoted as t. max and t min ,satisfy:

[0163] t max =argmax j ∑ i v ij ;

[0164] t min =argmin j ∑ i v ij

[0165] Based on the optimal and worst leakage types, the leakage monitoring results are divided into levels, i.e., leakage levels, denoted as L={l1,l2,l3,l4}, where l1 represents normal, l2 represents minor, l3 represents moderate, and l4 represents severe.

[0166] (10) Simultaneously input the real-time collected temperature data into the calibrated heat conduction model, calculate the temperature distribution and heat flux density, and determine whether there is a leak in the heat pipeline, as well as the location and extent of the leak, based on the temperature distribution and heat flux density. For example, if T(r,t) shows an abnormal decrease or q(r,t) shows an abnormal increase, it is considered that there is a leak, and the location of the leak is r. l The extent of leakage is related to T l and q(r) l The size of ,t) is related; and the GIS location of the temperature capsule is associated with the leak area.

[0167] Based on leakage type L and leakage location r l Generate contingency control instructions and transmit them via an interface to the intelligent control and scheduling system where the heating pipeline is located;

[0168] Set the response command range, and selectively respond to the planned control commands based on the safety control range of the IoT control equipment and the actual operation of the thermal pipeline;

[0169] If it is within the scope of the response command, then respond to the contingency plan control command and perform pre-control scheduling on the IoT control devices associated with the leak area;

[0170] The location of the leak is displayed intuitively in the form of a GIS map, with different colors or symbols used to distinguish and mark different levels of leakage.

[0171] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A real-time monitoring system for monitoring a leakage of a heat pipe based on a soil environment, characterized by, The system comprises a leakage monitoring sensor, a heat conduction characteristic database, a data processing module and a preplan control module. The leakage monitoring sensor is segmentally embedded in the underground soil of the controllable periphery of the heat pipeline to collect temperature data of the underground heat transfer area of the heat pipeline in real time. The heat conduction characteristic database is used to record the heat conduction influence parameters of the heat pipeline and the surrounding soil and establish a heat conduction model. The data processing comprises a data analysis submodule, a data pre-judgment submodule and a leakage positioning submodule. The data analysis submodule accesses a digital twin simulation model of the heat pipeline, calculates the theoretical values of the temperature, pressure and flow of the whole network of the heat pipeline based on the measured flow data of the heat supply station and the supply water temperature and pressure of the whole network of the heat pipeline, and uses the theoretical values as the soft measurement data of the heat conduction model to combine the real-time collected temperature data of the underground heat transfer area of the heat pipeline to check and identify the heat conduction model. The data pre-judgment submodule presets the soil temperature variation parameters of the heat pipeline under different leakage conditions to establish a classification model for identifying the leakage type. The leakage positioning submodule adopts the AHP hierarchical analysis method to construct a hierarchical structure model for deductive analysis to confirm the leakage point and the leakage type. The preplan control module generates a control scheme based on the leakage point and the leakage type and optionally sends corresponding control instructions to an automatic control system to quickly pre-process the leakage accident. The leakage positioning submodule adopts the AHP hierarchical analysis method to construct a hierarchical structure model for deductive analysis to determine the leakage point and the leakage type, which is as follows: (1) According to the real-time collected temperature data, the trained classification model in the data pre-judgment submodule is input to predict the leakage type and output the prediction result and the confidence level. (2) According to the heat conduction characteristic database and the heat conduction model, the criterion level of the leakage monitoring is determined, i.e. the factors affecting the leakage type, including but not limited to the soil temperature, the soil moisture, the pipeline temperature, the pipeline pressure and the pipeline flow. (3) According to the distribution and sampling frequency of the leakage monitoring sensor, the scheme level of the leakage monitoring is determined, i.e. the temperature data of different regions and time periods. (4) According to the historical data, the judgment matrix between the levels is determined. (5) The maximum eigenvalue and the eigenvector of each judgment matrix are calculated to obtain the weight vector of each level. (6) The consistency index and the consistency ratio of each judgment matrix are calculated to test the consistency of each judgment matrix. If the consistency is not satisfied, the judgment matrix is adjusted until the consistency requirement is met. (7) The total ordering vector is calculated according to the weight vector of each level. (8) The maximum leakage type and the minimum leakage type are determined according to the total ordering vector. (9) The result level of the leakage monitoring, i.e. the leakage level, is divided according to the optimal leakage type and the worst leakage type. (10) The real-time collected temperature data are input into the checked heat conduction model to confirm the leakage point and lock the leakage area in association with the GIS positioning of the temperature capsule.

2. The soil environment-based real-time monitoring heat line leakage monitoring system according to claim 1, wherein, The leakage monitoring sensor is a temperature capsule with a built-in temperature sensor and a wireless communication device containing GIS positioning. 3.The real-time monitoring heat pipeline leakage monitoring system based on soil environment according to claim 1, characterized in that, The heat conduction characteristic database is used to record the heat conduction influence parameters of the heat pipeline and the surrounding soil and establish a heat conduction model, which is as follows: The heat conduction characteristic database collects and inputs the physical property data of the heat pipe and the surrounding soil as the heat conduction influence parameters, including but not limited to materials, structures, thicknesses, densities, specific heat capacities, thermal conductivities, soil types, and water contents; An equivalent thermal conductivity coefficient model is selected, and a heat conduction equation of the heat pipe and the surrounding soil is established, the heat conduction influence parameters in the heat conduction database are input, and the temperature distribution and the heat flow density of the heat pipe and the surrounding soil are solved. 4.The soil environment based real-time monitoring heat pipeline leakage monitoring system according to claim 1, characterized in that, The data analysis submodule is used to analyze the real-time collected temperature data changes, and to calibrate and identify the real-time measured data under different working conditions in the heat conduction model, specifically as follows: (1) reading the real-time collected temperature data from the leakage monitoring sensor, performing smoothing and denoising preprocessing; (2) calculating the heat conduction parameters of the heat pipe and the surrounding soil according to the temperature distribution and the heat flow density and the heat pipe soft measurement data in the region, comparing the parameters with the parameters in the heat conduction characteristic database, and evaluating the calibration degree of the model; (3) if the calibration degree of the model does not meet the preset threshold, adjusting the structure and parameters of the heat conduction model, repeating steps (2) to (3), until the calibration degree of the model reaches a satisfactory level; (4) according to the heat conduction model, calculating the heat conduction characteristic values of the heat pipe and the surrounding soil, and performing correlation analysis on the real-time collected temperature data, evaluating the identification degree of the model; (5) if the identification degree of the model does not meet the preset threshold, adjusting the structure or parameters of the heat conduction model, repeating steps (2) to (5), until the identification degree of the model reaches the threshold; (6) outputting the calibrated and identified heat conduction model and the calibration and identification indexes of the model. 5.The real-time monitoring heat pipeline leakage monitoring system based on soil environment according to claim 1, characterized in that, The data prediction submodule predefines the soil temperature change model of the heat pipe under different conditions, and predicts the leakage type according to the real-time collected temperature data, specifically as follows: (1) according to different leakage types, presetting different leakage positions, leakage temperatures, leakage flow rates and other parameters as boundary conditions, re-solving the heat conduction equation to obtain the temperature distribution and heat flow density under different leakage types; (2) taking the preset temperature distribution and heat flow density under different leakage types as the input of the data prediction submodule, establishing a classification model for leakage type identification based on a decision tree, training the parameters and weights of the model, and evaluating the accuracy and stability of the model; (3) reading the real-time collected temperature data from the leakage monitoring sensor, taking it as the input of the data prediction submodule, using the trained classification model to predict the leakage type, and outputting the prediction result and confidence. 6.The soil environment based real-time monitoring heat pipeline leakage monitoring system according to claim 1, wherein, The pre-control module generates a pre-control instruction based on the leakage type and the leakage point, and transmits the pre-control instruction to the intelligent control and scheduling system associated with the heat pipe through an interface, responds to the pre-control instruction, and pre-controls and schedules the Internet of Things control equipment associated with the leakage area. 7.The soil environment based real-time monitoring heat pipeline leakage monitoring system according to claim 6, characterized in that, Further comprising: setting a response instruction range, and selectively responding to the pre-control instruction according to the safety control range of the Internet of Things control equipment and the actual operation of the heat pipe. 8.The soil environment based real-time monitoring heat pipeline leakage monitoring system according to claim 1 or 6, characterized in that, Further comprising an alarm display submodule for associating with the leakage positioning submodule, responding to the confirmation of the leakage point, and intuitively displaying in the form of a GIS map, different leakage levels being distinguished and marked by different colors or symbols.

9. A method for monitoring leakage of a heat pipeline based on real-time monitoring of a soil environment, for the system for monitoring leakage of a heat pipeline based on real-time monitoring of a soil environment according to any one of claims 1 to 8, characterized by, Comprise the following steps: (1) in the controllable perimeter of the heat pipeline underground soil section buried temperature sensor, real-time collection of heat line pipe underground heat transfer area temperature data; (2) record the heat pipeline and the heat conduction influence parameter of surrounding soil, establish the heat conduction characteristic database and heat conduction model; (3) analysis real-time collection temperature data change and the soft measurement data of the region heat pipeline, the real-time measurement data of different working condition in the heat conduction model is checked and identified; (4) preheat pipeline in different situation soil temperature change model, according to the real-time collection of temperature data to predict the type of leakage; (5) using AHP hierarchical analysis method, build hierarchical structure model to deduce analysis, confirm the leakage category and lock the leakage point; (6) based on the leakage category and lock the leakage point to generate plan control instruction, optional for the leakage area of the Internet of things control equipment for pre-control scheduling; (7) the point area of the leakage is directly shown and alarmed in the form of GIS map.

Images