Heat supply pipe network inspection and fault diagnosis system based on GIS
The GIS-based heating pipeline inspection system utilizes single-mode optical fiber and temperature sensors for real-time monitoring and evaluation of heating pipelines, solving the problems of corrosion and temperature inspection in heating pipelines and achieving efficient fault diagnosis and risk assessment.
Patent Information
- Application Number
- CN202511365153.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-23
- Publication Date
- 2026-02-03
AI Technical Summary
The existing heating network inspection system cannot detect corrosion on the outer wall of the pipes in a comprehensive and timely manner, and the temperature inspection effect is poor, resulting in heat energy waste and increased management difficulty.
A GIS-based heating pipeline inspection and fault diagnosis system is adopted. GIS data of heating pipelines are collected through single-mode sensing optical fiber and temperature sensors. A dynamic reference temperature field model is constructed using acoustic signal processing and Fourier's law. The model is then combined with a risk assessment module for weighted fusion to achieve real-time monitoring and assessment of pipeline corrosion and temperature distribution.
It enables real-time monitoring of corrosion status and temperature distribution along the entire heating pipeline, reducing heat loss, improving inspection efficiency and coverage, timely detection of insulation layer defects and identification of dangerous sections with a high probability of leakage or rupture, and supports visualized fault diagnosis.
Smart Images
Figure CN121456524A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of heat supply pipe network inspection, and particularly relates to a GIS-based heat supply pipe network inspection and fault diagnosis system. BACKGROUND
[0002] With the urbanization process advancing at an unprecedented speed, a large number of people gather in cities, and newly built residential areas, commercial complexes and industrial parks make the construction scale of heat supply pipe network continue to expand, and its coverage gradually extends from the traditional urban core area to the emerging urban and rural junction and even remote suburbs. The complex underground pipeline network is increasingly large, not only containing main roads and branch lines of different pipe diameters and materials, but also needing to consider the dual tasks of old facility reconstruction and new system access, and the complexity and management difficulty of the entire heat supply pipe network system are significantly improved.
[0003] The safe and stable operation of the heat supply pipe network has become a key element related to people's livelihood. As the lifeline of winter heating, it is directly related to whether the indoor temperature of thousands of households can meet the standard, and affects the basic living quality and health level of residents. Once a fault such as leakage, blockage or rupture occurs, not only will it cause waste of heat energy and increase of maintenance cost, but also may cause secondary disasters and threaten public safety. Therefore, through the use of the heat supply pipe network inspection and fault diagnosis system, the safe and efficient operation of the heat supply system can be ensured.
[0004] The heat supply pipe network is mostly buried underground and is in a high-temperature, high-pressure and corrosive environment for a long time. When localized corrosion such as pitting corrosion and stress corrosion cracking occurs in the corrosion process of metal pipelines, transient elastic stress waves will be released. At present, most heat supply pipe network inspection and fault diagnosis systems cannot comprehensively and timely detect the corrosion of the outer wall of the pipeline; at the same time, as the service life increases, the insulation layer of the heat supply pipeline may age, be damaged, etc., which intensifies heat loss and increases energy consumption, but the existing inspection means are limited, and the problem of poor insulation can only be detected when the surface temperature significantly rises. SUMMARY
[0005] The application provides a GIS-based heat supply pipe network inspection and fault diagnosis system, which aims to solve the problems that the existing technology cannot comprehensively and timely detect the corrosion of the outer wall of the pipeline, and the temperature inspection effect of the heat supply pipe network is poor.
[0006] The GIS-based heat supply pipe network inspection and fault diagnosis system comprises a pipe network monitoring module, an association module, a performance quantification module, a risk assessment module and a diagnosis decision module.
[0007] The pipe network monitoring module can collect GIS data of the heat supply pipeline based on a sensor unit closely laid along the outer wall of the heat supply pipeline in advance, and convert original stress wave data in the GIS data into an acoustic signal spectrum in time domain;
[0008] The correlation module can perform signal processing and feature extraction on the acoustic signal spectrum, analyze the total stress energy E band of corrosion in the key interval of the heat supply pipeline, and determine whether the heat supply pipeline is in an active corrosion period; the calculation formula of the total stress energy E band is as follows:
[0009]
[0010] Wherein, f1 and f2 are the lower limit and upper limit of the target frequency band, d f is all continuous frequency points from f1 to f2, and P(f) is the power spectral density;
[0011] The performance quantification module can construct a dynamic reference temperature field model based on Fourier's law, simulate the theoretical surface temperature of the heat supply pipeline in an ideal insulation state, compare the temperature distribution data with the theoretical surface temperature, calculate the relative heat loss rate, and output the corresponding defect grade D;
[0012] The risk assessment module can weight and fuse the total stress energy E band output by the correlation module and the insulation defect grade D output by the performance quantification module, and incorporate the key parameters of the pipeline to identify the dangerous section with high probability of leakage or rupture;
[0013] The diagnosis decision module starts a grading response mechanism based on the risk assessment result, and displays on the GIS visualization platform.
[0014] Further, the sensor unit includes a single-mode sensing optical fiber and a temperature sensor, the single-mode sensing optical fiber is used to detect the original stress wave data of the heat supply pipeline, and the temperature sensor is used to measure the temperature data of the surface of the heat supply pipeline.
[0015] Further, the correlation module includes a preprocessing unit and a feature auxiliary identification unit.
[0016] After obtaining the original stress wave data, the preprocessing unit first eliminates background noise caused by environmental vibration by an adaptive filtering algorithm, and then enhances the original stress wave data by wavelet transform to improve the signal-to-noise ratio.
[0017] The feature auxiliary identification unit can calculate the total stress energy E band according to the acoustic feature spectrum and sliding window integration.
[0018] Further, the performance quantification module comprises a model construction unit, a calculation unit and a grade determination unit.
[0019] The model construction unit is capable of constructing a dynamic reference temperature field model based on Fourier's law.
[0020] The calculation unit is capable of calculating a relative heat loss rate η according to the degree, area and distribution of the temperature deviation of the temperature abnormal area from the reference value output by the model construction unit, for measuring the heat loss of the heat supply pipeline.
[0021] The grade determination unit is constructed based on K-means clustering analysis algorithm, and is capable of automatically dividing the insulation layer defects of the heat supply pipeline into multiple grades based on the relative heat loss rate η and a preset threshold.
[0022] Further, the model construction unit is also capable of performing pixel-level comparison between the temperature distribution data and the theoretical surface temperature output by the dynamic reference temperature field model.
[0023] Further, the calculation formula of the relative heat loss rate η is as follows:
[0024]
[0025] wherein, T medium is the medium temperature in the heat supply pipeline, T ambient is the target temperature of the environment, and T actual is the real-time temperature of the heat supply pipeline in the temperature distribution data.
[0026] Further, the specific content of the risk assessment module is as follows:
[0027] 1) constructing a multi-dimensional feature set composed of stress total energy E band , relative heat loss rate η and defect grade D;
[0028] 2) adopting a weighted scoring method, normalizing and weighting the three key indicators of stress total energy E band , relative heat loss rate η and defect grade D, and obtaining a comprehensive score S;
[0029] 3) the risk assessment module takes the comprehensive score S of each pipe section as input and maps it to a pre-defined 5x5 risk matrix.
[0030] Further, the calculation formula of the comprehensive score S is as follows:
[0031] S = α·E + β·η + γ·D
[0032] wherein, α, β, γ are weight coefficients, and α + β + γ = 1.
[0033] Further, the horizontal axis of the risk matrix is the total stress energy E band , and the vertical axis is the defect level D. Each cell in the risk matrix corresponds to a final comprehensive risk level.
[0034] Compared with the prior art, the present application has at least the following beneficial effects:
[0035] Based on further analysis and research of the problems of the prior art, the GIS layout information of the heat supply pipe network can be collected by the single-mode sensing optical fiber and the temperature sensor, the real-time monitoring of the corrosion state and temperature distribution data of the heat supply pipeline is realized, the defects of the thermal insulation layer are found in time, the thermal insulation efficiency is evaluated, and the heat energy loss is reduced, thereby improving the monitoring efficiency and coverage, and facilitating subsequent better patrol and fault diagnosis.
[0036] At the same time, the total stress energy E band and the thermal insulation defect level D output by the performance quantification module are weighted and fused, the associated rules in the historical fault database are combined, the high-probability leakage or rupture risk section is identified in the risk matrix, thereby the multi-source information is converted into intuitive and sortable risk priority, and the fault diagnosis structure is visualized. BRIEF DESCRIPTION OF DRAWINGS
[0037] Figure 1 A module diagram of the GIS-based heat supply pipe network patrol and fault diagnosis system provided by an embodiment of the present application is provided. DETAILED DESCRIPTION
[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments.
[0039] As shown in Figure 1 , the GIS-based heat supply pipe network patrol and fault diagnosis system provided by the present application includes a pipe network monitoring module, an association module, a performance quantification module, a risk assessment module and a diagnosis decision module.
[0040] The pipe network monitoring module can collect GIS data of the heat supply pipeline based on the sensor unit closely laid along the outer wall of the heat supply pipeline in advance, and convert the original stress wave data in the GIS data into an acoustic signal spectrum in the time domain, thereby realizing comprehensive detection of the transient elastic stress wave of the heat supply pipeline. The GIS data includes original stress wave data and temperature distribution data.
[0041] The sensor unit includes a single-mode sensing optical fiber and a temperature sensor. When the stress wave generated by corrosion is transmitted to the optical fiber, the photoelastic effect causes a slight change (Δn≈10 -6 ~ 10 -5). The change of refractive index causes the modulation of phase and frequency of the transmitted laser in the single-mode sensing fiber, forming optical perturbation related to the stress wave characteristics.
[0042] The Mach-Zehnder interferometer can demodulate the phase information. The returned light is divided into two paths: one is the signal light, and the other is the local reference light. The two lights meet and interfere to form the interference light intensity.
[0043] The time-to-digital converter (TDC) measures the time interval Δt from the emission pulse to the reception of the backscattered light signal, and calculates the spatial distance L = c·Δt / 2 combined with the speed of light c, to obtain the original stress wave data; the time-to-digital converter continuously scans at a repetition frequency of kilohertz, real-time acquires and reconstructs the dynamic strain distribution on the entire optical fiber path, and finally generates an acoustic feature map in the form of a three-dimensional matrix.
[0044] The temperature sensors are arranged at a certain distance along the axis of the heating pipeline to form a dense temperature monitoring network for measuring the temperature data of the surface of the heating pipeline, which facilitates the subsequent judgment of the integrity and performance attenuation of the thermal insulation layer based on the thermal resistance value of the thermal insulation layer.
[0045] The correlation module can perform signal processing and feature extraction on the acoustic signal map, analyze the total stress energy of corrosion in the key interval of the heating pipeline, and judge whether the heating pipeline is in the active corrosion period, providing key basis for pipeline corrosion monitoring and fault diagnosis.
[0046] The correlation module includes a preprocessing unit and a feature-assisted identification unit.
[0047] After obtaining the original stress wave data, the preprocessing unit first eliminates the background noise caused by environmental vibrations such as traffic and pump stations through an adaptive filtering algorithm to ensure signal purity, and then uses wavelet transform to enhance the original stress wave data and improve the signal-to-noise ratio to highlight corrosion-related features.
[0048] The feature-assisted identification unit can calculate the total stress energy E band according to the acoustic feature map and sliding window integration.
[0049] The sliding window integration divides the key frequency band (such as 100-300 kHz) and calculates the total stress energy E band . The greater the energy value of the total stress energy E band as a corrosion activity index, the more intense the corrosion activity, indicating that it is in the active corrosion period. Different corrosion mechanisms produce different signal frequency centers, which can be used to assist in identifying the corrosion mechanism, integrating the energy E band , and calculating the frequency center f c, which is convenient for distinguishing the dominant frequency characteristics of different corrosion types and analyzing the energy proportion of a specific frequency band; and is convenient for assisting in identifying the active period of corrosion.
[0050] Stress total energy E band The calculation formula is as follows:
[0051]
[0052] Wherein, f1 and f2 are the lower limit and upper limit of the target frequency band, for example, in corrosion monitoring, it can be set as the key interval of 100-300 kHz, df is all continuous frequency points from f1 to f2, P(f) is the power spectral density, which represents the power intensity in a unit frequency band.
[0053] Frequency center of gravity f c The calculation formula is as follows:
[0054]
[0055] Wherein, f is the frequency variable.
[0056] The performance quantification module can construct a dynamic reference temperature field model based on the Fourier law, simulate the theoretical surface temperature of the heat supply pipeline in an ideal insulation state, compare the temperature distribution data with the theoretical surface temperature, calculate the relative heat loss rate, output the corresponding defect level D, and facilitate quantitative evaluation of the attenuation degree of insulation performance and the defect level D, so as to realize accurate mapping of the insulation performance quantification index, and provide data basis for subsequent inspection and fault diagnosis.
[0057] The performance quantification module includes a model construction unit, a calculation unit and a level determination unit.
[0058] The model construction unit can construct a dynamic reference temperature field model based on the Fourier law. When constructing, the collected temperature distribution data is input as a data source, and the environmental air temperature data is used as a reference for the basic temperature zone. Based on the differential form of the Fourier law , the pipeline is divided into a three-dimensional grid by using the finite element analysis method, and each unit follows the energy conservation equation. By iteratively solving the nonlinear partial differential equation set, the theoretical temperature value of each position on the outer surface of the pipeline is calculated, and a complete "theoretical temperature field" is generated as an evaluation reference. The steady-state / transient heat transfer process under the ideal insulation layer can be dynamically simulated to generate a mill-level theoretical surface temperature cloud map. The energy conservation equation describes the dynamic balance relationship of heat transfer inside the heat supply pipeline, and the energy conservation equation is as follows:
[0059]
[0060] Wherein, p is the material density, c p is the specific heat capacity at constant pressure, k is the thermal diffusivity coefficient, is the temperature gradient, and Φ is the internal heat source term.
[0061] The model construction unit can also perform pixel-level comparison of the temperature distribution data with the theoretical surface temperature output by the dynamic reference temperature field model. In an ideal case, if the insulation layer is intact, the temperature distribution on the surface of the pipeline should be consistent with the temperature distribution simulated by the dynamic reference temperature field model. However, when the insulation layer has defects such as damage, thinning, or water immersion, the heat transfer on the surface of the pipeline will change, causing temperature abnormalities in local areas. The model construction unit labels the temperature abnormal area and outputs it to the calculation unit.
[0062] The calculation unit can calculate the relative heat loss rate η according to the degree of temperature deviation from the reference value, the area, and the distribution of the temperature abnormal area output by the model construction unit, which is used to measure the heat loss of the heating pipeline.
[0063] The calculation formula of the relative heat loss rate η is as follows:
[0064]
[0065] where T meium is the temperature of the medium in the heating pipeline, T ambient is the target temperature of the environment, and T actual is the real-time temperature of the heating pipeline in the temperature distribution data.
[0066] The grade determination unit is constructed based on the K-means clustering analysis algorithm and can automatically divide the insulation layer defects of the heating pipeline into multiple grades based on the relative heat loss rate η and the preset threshold, thereby realizing accurate mapping from temperature to insulation performance quantitative indicators.
[0067] For example: η < 5% is the intact grade, 5% ≤ η < 15% is the slight defect grade, 15% ≤ η < 30% is the moderate defect grade, and η ≥ 30% is the serious defect grade.
[0068] The risk assessment module can perform weighted fusion of the stress total energy E band output by the correlation module and the insulation defect grade D output by the performance quantification module, and incorporate the pipeline criticality parameters, combine the correlation rules in the historical fault database, and update the risk score of each section of the heating pipeline in real time to identify the dangerous sections with high probability of leakage or rupture, providing a basis for priority inspection. The specific content is as follows:
[0069] 1) Construct a multi-dimensional feature set composed of the stress total energy E band , the relative heat loss rate η, and the defect grade D.
[0070] 2) Use the weighted scoring method to combine the stress total energy E band, relative heat loss rate η and defect level D three key indicators are normalized and weighted sum, get the comprehensive score S. Comprehensive score S calculation formula is as follows:
[0071] S = a · E + β · η + γ · D
[0072] Among them, a, β, γ is the weight coefficient, and a + β + γ = 1.
[0073] The above normalization is based on the Min-Max standardization method, which maps each indicator to the [0, 1] interval, eliminating dimensional differences.
[0074] The weight coefficient (a, β, γ) is dynamically adjusted through expert experience and regression analysis of historical failure data, so as to ensure that the score can accurately reflect the real corrosion development trend. At the same time, using the spatial analysis function of GIS, it is judged whether there is a population density within a certain radius (such as 50 meters) around the pipeline failure point, whether there is a key infrastructure (such as a school, a hospital, a transportation hub) or an environmentally sensitive area (such as a water area), so as to give different weight coefficients.
[0075] 3) The risk assessment module takes the comprehensive score S of each pipe segment as input and maps it into a predefined 5x5 risk matrix. The horizontal axis of the matrix is the total stress energy E band , the vertical axis is the defect level D, and each cell in the matrix corresponds to a final comprehensive risk level (such as extremely high risk, high risk, medium risk, etc.). This process converts complex multi-source information into intuitive and sortable risk priorities, providing indisputable data-driven evidence for the diagnostic decision-making module to generate accurate maintenance strategies.
[0076] The diagnostic decision-making module initiates a hierarchical response mechanism based on the risk assessment results and displays them on the GIS visualization platform, making it easy for staff to quickly locate the problem and providing strong data support for management to develop inspection plans.
[0077] The GIS visualization platform can visually display the risk score of the heating pipeline, the original GIS spatial layout, the topological structure and attribute information. Users can click on any pipe segment on the electronic map to view detailed technical parameters, operating status (such as temperature, pressure, flow) and historical maintenance records, etc.
[0078] In the above GIS-based heating pipe network inspection and fault diagnosis system, the GIS layout information of the heating pipe network can be collected by single-mode sensing optical fiber and temperature sensor, realizing real-time monitoring of the corrosion state and temperature distribution data of the heating pipeline, facilitating timely detection of insulation defects, evaluating insulation effectiveness, and reducing heat loss, thereby improving monitoring efficiency and coverage, facilitating better subsequent inspection and fault diagnosis.
[0079] At the same time, the stress total energy E band The insulation defect level D output by the performance quantification module is weighted and fused, the associated rules in the historical fault database are combined, the dangerous sections with high probability of leakage or rupture are identified in the risk matrix, so that the multi-source information is converted into intuitive and sortable risk priorities, and the fault diagnosis structure is visualized.
[0080] The technical features of the above embodiments can be combined in any manner, and to make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictory, it should be considered that it is within the scope of the present disclosure.
Claims
1. A GIS-based heating pipeline network inspection and fault diagnosis system, characterized in that, It includes a pipeline monitoring module, a correlation module, a performance quantification module, a risk assessment module, and a diagnostic decision-making module; The pipeline monitoring module can collect GIS data of the heating pipeline based on sensor units that are pre-laid tightly along the outer wall of the heating pipeline, and convert the original stress wave data in the GIS data into an acoustic signal spectrum in the time domain. The correlation module can perform signal processing and feature extraction on the acoustic signal spectrum, and analyze the total stress energy E of corrosion in the critical section of the heating pipeline. band To determine whether the heating pipeline is in a period of active corrosion; total stress energy E band The calculation formula is as follows: Where f1 and f2 are the lower and upper limits of the target frequency band, respectively, d f Let f be all consecutive frequency points from f1 to f2, and P(f) be the power spectral density. The performance quantification module can construct a dynamic reference temperature field model based on Fourier's law, simulate the theoretical surface temperature of the heating pipeline under ideal insulation conditions, compare the temperature distribution data with the theoretical surface temperature, calculate the relative heat loss rate, and output the corresponding defect level D. The risk assessment module can output the total stress energy E from the correlation module. band The insulation defect level D output by the performance quantification module is weighted and fused, and the key parameters of the pipeline are incorporated to identify dangerous sections with a high probability of leakage or rupture. The diagnostic decision-making module initiates a tiered response mechanism based on the risk assessment results and displays them on the GIS visualization platform.
2. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 1, characterized in that, The sensor unit includes a single-mode sensing fiber and a temperature sensor. The single-mode sensing fiber is used to detect the original stress wave data of the heating pipeline; the temperature sensor is used to measure the temperature data of the surface of the heating pipeline.
3. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 1, characterized in that, The association module includes a preprocessing unit and a feature-assisted recognition unit; After acquiring the raw stress wave data, the preprocessing unit first uses an adaptive filtering algorithm to specifically eliminate background noise caused by environmental vibration, and then uses wavelet transform to enhance the raw stress wave data and improve the signal-to-noise ratio. The feature-assisted recognition unit can calculate the total stress energy E based on the acoustic feature spectrum and sliding window integral. band .
4. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 1, characterized in that, The performance quantification module includes a model building unit, a calculation unit, and a level determination unit; The model building unit can construct a dynamic reference temperature field model based on Fourier's law; The calculation unit can calculate the relative heat loss rate η based on the degree, area and distribution of the temperature anomaly area output by the model building unit, which is used to measure the heat loss of the heating pipeline. The grade determination unit is constructed based on the K-means clustering analysis algorithm, which can automatically classify the insulation layer defects of heating pipelines into multiple grades based on the relative heat loss rate η and the preset threshold.
5. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 4, characterized in that, The model building unit can also perform pixel-level comparisons between temperature distribution data and the theoretical surface temperature output by the dynamic reference temperature field model.
6. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 4, characterized in that, The formula for calculating the relative heat loss rate η is as follows: Among them, T medium T represents the temperature of the medium inside the heating pipeline. ambient T represents the target temperature of the environment. actual This refers to the real-time temperature of the heating pipeline in the temperature distribution data.
7. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 1, characterized in that, The specific contents of the risk assessment module are as follows: 1) Construct a system based on the total stress energy E band A multidimensional feature set consisting of relative heat loss rate η and defect level D; 2) Using a weighted scoring method, the total stress energy E is... band The three key indicators, namely, relative heat loss rate η and defect level D, are normalized and then weighted and summed to obtain the comprehensive score S. 3) The risk assessment module takes the comprehensive score S of each pipeline segment as input and maps it to a predefined 5x5 risk matrix.
8. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 7, characterized in that, The formula for calculating the comprehensive score S is as follows: S=α·E+β·η+γ·D Where α, β, and γ are weighting coefficients, and α + β + γ = 1.
9. The GIS-based heating pipeline inspection and fault diagnosis system according to claim 1, characterized in that, The horizontal axis of the risk matrix represents the total stress energy E. band The vertical axis represents the defect level D, and each cell in the risk matrix corresponds to a final overall risk level.