A Smart Determination Method for Buried Heating Pipeline Network Defect Types Based on Unmanned Aerial Vehicles

Abstract

This invention relates to the field of pipeline inspection technology, and more particularly to an intelligent method for determining the type of defects in underground heating pipeline networks based on unmanned aerial vehicles (UAVs). The method includes: collecting data on the pipeline network layout and past defect locations of the underground heating pipeline; determining predicted defect locations and establishing heat conduction channels; collecting pipeline network map data along the pipeline network layout using thermal imaging methods via UAVs, generating ground heat dissipation characterization values; applying instantaneous heating to branch pipelines, collecting point map data for each abnormal point and each heat conduction channel; inputting the point map data of the abnormal points into the instantaneous heating model to generate defect locations and determine the defect type; calculating the remaining life of each defect location, or determining the defect location as a leak location; determining the risk level of each defect location and determining the corresponding treatment method. This invention effectively prevents pipeline leaks while improving the accuracy of determining the type of defects in underground heating pipeline networks.

Description

Technical Field

[0001] This invention relates to the field of pipeline inspection technology, and in particular to an intelligent method for determining the type of defects in underground heating pipelines based on unmanned aerial vehicles (UAVs). Background Technology

[0002] Underground heating pipelines are the transmission channels of urban centralized heating systems, undertaking the key function of delivering heat energy from heat sources to residential buildings, commercial buildings, and industrial facilities. They are directly related to the comfort of residents' lives in winter and the stability of industrial production, and are one of the core infrastructures to ensure the normal operation of cities. However, as the service life increases, the pipeline network is prone to various defects due to factors such as corrosion, external disturbances, and material aging. For a long time, defect detection of underground heating pipelines has relied on traditional technologies, but these technologies are difficult to meet the needs of efficient operation and maintenance in modern cities. With its high mobility and multi-payload adaptability, drones can break through the spatial limitations of ground detection and improve detection efficiency.

[0003] For example, Chinese Patent Application Publication No. CN105372263A discloses an eddy current heating-based infrared imaging detection device and method for detecting pipeline defects. This invention discloses an eddy current heating-based infrared imaging detection device and method for detecting pipeline defects. The device consists of an induction heating unit, an image acquisition unit, and an image processing unit. The eddy current heating probe of the induction heating unit performs non-contact localized micro-heating on the buried pipeline under test, generating eddy currents that heat the pipe wall and radiate infrared rays. An infrared thermal imager, assisted by an infrared laser pointer, is aimed at the pipeline under test and acquires images. The acquired images are transmitted to a computer via an image transmission interface. After processing on the computer, the presence, shape, and actual size of defects in the pipeline are determined. This invention can be used in conjunction with a pipeline inspection robot for real-time online inspection of buried steel structure pipelines.

[0004] It is evident that the existing technology still has the following problems:

[0005] Heating pipes can easily lead to uneven heating and insufficient temperature rise, resulting in inaccurate measurement results. Heating long pipes sequentially can also cause missed detections. Summary of the Invention

[0006] To address this, the present invention provides an intelligent method for determining the type of defects in underground heating pipelines based on unmanned aerial vehicles (UAVs), which overcomes the problems in the prior art where uneven heating and insufficient temperature rise during pipeline heating lead to inaccurate measurement structures, and the potential for missed detections when heating long pipelines sequentially.

[0007] To achieve the above objectives, this invention provides an intelligent method for determining the defect type of underground heating pipelines based on unmanned aerial vehicles (UAVs), comprising:

[0008] Collect the pipeline network route and past defect locations of the underground heating pipeline, and determine the predicted defect locations of the underground heating pipeline based on the past defect locations and pipeline information, and establish heat conduction channels.

[0009] The buried heating pipeline network map data is collected by using a drone to collect thermal imaging data along the pipeline network, and ground heat dissipation characterization values ​​are generated based on ambient temperature and pipeline medium temperature.

[0010] By combining the pipeline network map data and the ground heat dissipation characterization value, abnormal points are generated. For branch pipelines where the number of abnormal points exceeds a preset number, instantaneous heating is applied. Point map data of each abnormal point and each heat conduction channel are collected.

[0011] A transient temperature rise model is generated based on the point map data of each of the heat conduction channels. The point map data of the abnormal points are input into the transient temperature rise model to generate defect points and determine the defect type. The remaining life corresponding to each defect point is calculated according to the defect type, or the defect point is determined to be a leakage point.

[0012] Based on the pipeline information and remaining life of each defect location, the corresponding defect risk value is calculated to determine the risk level of each defect location and the corresponding treatment method.

[0013] The preset quantity is positively correlated with the length of the branch pipe where the abnormal point is located.

[0014] Furthermore, the process of determining the predicted defect locations of the buried heating pipeline includes,

[0015] Collect pipeline information at the locations of past defects;

[0016] Several characteristic points are marked on the underground heating pipeline;

[0017] The pipeline information of each feature point is matched one-to-one with the pipeline information of each past defect point, and the similarity is calculated.

[0018] The predicted defect locations are determined based on the similarity and the preset similarity.

[0019] The preset similarity is negatively correlated with the length of the branch pipe where the feature point is located, and the pipe information includes pipe diameter, pipe wall thickness, pipe burial depth and insulation layer thickness.

[0020] Furthermore, the process of establishing the heat conduction channel includes,

[0021] Determine the surface area directly above the pipeline corresponding to the defect location;

[0022] A borehole area is created by drilling vertically from the surface area directly above the pipeline.

[0023] A high thermal conductivity medium is injected into the drilled area and then backfilled.

[0024] Furthermore, the process of generating ground heat dissipation characterization values ​​based on ambient temperature and pipe medium temperature includes,

[0025] The ambient temperature of the ground surface area directly above the pipeline was collected by drones traveling along the pipeline network.

[0026] Collect the temperature of the medium in the buried heating pipeline;

[0027] By combining the ambient temperature and the temperature of the pipe medium, ground heat dissipation characterization values ​​corresponding to different pipe diameters are generated.

[0028] Furthermore, the process of collecting the location map data of each of the abnormal points and each of the heat conduction channels includes,

[0029] The initial pipeline medium temperature is generated by combining the pipeline network map data and the ground heat dissipation characterization value;

[0030] Based on the initial pipeline medium temperature, abnormal points are determined, and branch pipelines with more than the preset number of abnormal points are subjected to instantaneous heating.

[0031] Under the condition of instantaneous temperature rise, point map data of each of the abnormal points and each of the heat conduction channels are collected;

[0032] The branch pipe is a pipe loop consisting of corresponding supply and return water pipes, and the instantaneous temperature rise is to increase the supply water temperature of the branch pipe.

[0033] Furthermore, the process of generating defect locations includes,

[0034] A sudden temperature rise model is generated based on the point map data of each of the aforementioned heat conduction channels;

[0035] The location map data of the abnormal points are input into the instantaneous heating model to generate a predicted pipeline temperature;

[0036] The predicted pipe temperature and the experimental pipe temperature under instantaneous heating conditions are combined to determine whether the abnormal point is a defect point.

[0037] Furthermore, the temperature rise value is determined based on the temperature values ​​of the defect location before and after the instantaneous temperature rise, and the defect type of the defect location is determined based on the temperature rise value.

[0038] Further, the remaining lifetime corresponding to each defect location is calculated based on the defect type, wherein,

[0039] If the defect type is carbonization of the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the safe pipe wall thickness, the internal corrosion rate of the pipe, and the service life of the pipe.

[0040] If the defect type is damage to the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the pipe safety wall thickness, the internal corrosion rate, the external corrosion rate, and the pipe's service life.

[0041] Furthermore, the risk level of each defect location is determined sequentially based on the defect risk value and several preset risk values.

[0042] Furthermore, the corresponding processing method includes,

[0043] If the risk level of the defect location is the first leakage risk level, then it is determined that the operation requirements are met and operation continues;

[0044] If the risk level of the defect location is the second leakage risk level, then it is determined to increase the number of drone inspections.

[0045] If the risk level of the defect location is the third leakage risk level, then it is determined that the pipeline segment corresponding to the defect location should be treated.

[0046] Compared with existing technologies, the beneficial effects of this invention are as follows: By collecting data on the pipeline network layout and past defect locations of buried heating pipelines, this invention determines the predicted defect locations of buried heating pipelines and establishes heat conduction channels based on past defect locations and pipeline information. Effective preventive monitoring measures are implemented in advance at locations where pipeline defects are prone to occur. Past defect locations include information such as defect type, causes, and environmental parameters. By training or optimizing the judgment model using this data, the system can more accurately identify the defect characteristics of specific pipeline sections. Traditional detection often requires extensive, carpet-style inspections or frequent excavation verification of large-scale pipeline networks due to a lack of precise targets, resulting in high costs. By predicting defect locations, monitoring resources can be tilted towards high-risk areas, effectively preventing pipeline leaks while improving the accuracy of determining the defect type of buried heating pipeline networks.

[0047] Furthermore, this invention reduces inaccurate data detection caused by excessive pipeline burial depth by establishing a heat conduction channel above the predicted defect point. It also reduces the impact of small data changes due to low soil thermal conductivity on analysis results, and minimizes the influence of other heat sources on pipeline detection from the surface or above the pipeline. The heat conduction channel directly constructs a shortcut for heat transfer from the pipeline defect point to the surface detection equipment, reducing heat loss in the soil, overcoming differences in soil thermal conductivity, amplifying the identifiability of defect data, and amplifying the temperature change at the defect point to 3℃-5℃ at the detection end. This eliminates the problem of different data representations for the same defect due to soil type differences, avoids heat dissipation interference from other facilities above the pipeline, and ensures that the heat changes captured by the sensor are specifically directed at the target defect point, further improving the accuracy of determining the defect type of the buried heating pipeline network.

[0048] Furthermore, this invention employs instantaneous heating for branch pipes with an abnormal number exceeding a preset limit. Based on the increase in medium temperature within the branch pipe caused by instantaneous heating, the defect type at the defect location is determined according to the change in temperature. Instantaneous heating can actively amplify the heat exchange effect of the defect by increasing the temperature difference between the medium and the outside environment. After heating, the temperature difference between the hot water at the leak point and the surrounding soil increases significantly, the heat loss rate increases, and the characteristic changes from fuzzy fluctuations to significant step differences, allowing for clear and accurate determination of pipeline defects. Instantaneous heating actively increases the signal strength, making the amplitude of the defect characteristic signal far exceed environmental interference. The controllability of the heating process can form standardized detection conditions, reducing the inconsistency of detection data caused by natural environmental fluctuations (such as diurnal temperature differences and weather changes), making defect characteristics at different times and in different areas comparable. While improving the stability of the judgment model, it further improves the accuracy of determining the defect type of the buried heating pipeline network.

[0049] Furthermore, this invention calculates the corresponding defect risk value based on pipeline information and remaining life at each defect location to determine the risk level of each defect location and the corresponding treatment method. Through multi-dimensional data fusion, it achieves accurate quantification of defect risk, reduces judgment bias, and adopts differentiated treatment methods for defect locations with different risk levels. This process is essentially a dynamic verification of defect type determination. The determination of defect type no longer relies on a single detection result, but is continuously corrected through actual verification data, which gradually improves the system's ability to identify complex defects. The multi-dimensional fusion judgment method can reduce the overall misjudgment rate of underground heating pipeline defect types by 25% to 30%, especially significantly improving the accuracy of early minor defects. This provides a more reliable decision-making basis for the preventive maintenance of the pipeline network and further improves the accuracy of determining the defect type of underground heating pipeline network. Attached Figure Description

[0050] Figure 1This is a flowchart illustrating the intelligent method for determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs) according to the present invention.

[0051] Figure 2 A logic diagram for determining the predicted defect locations of buried heating pipelines in an embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of the process for generating ground heat dissipation characterization values ​​according to an embodiment of the present invention;

[0053] Figure 4 A logic diagram for determining the risk level of defect locations in an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0055] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0056] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0057] Please see Figure 1 The diagram shown is a flowchart illustrating the intelligent method for determining the type of defects in underground heating pipelines based on unmanned aerial vehicles (UAVs) according to the present invention. An embodiment of the present invention provides an intelligent method for determining the type of defects in underground heating pipelines based on unmanned aerial vehicles (UAVs), comprising:

[0058] Step S1: Collect the pipeline network route and past defect locations of the underground heating pipeline. Based on the past defect locations and pipeline information, determine the predicted defect locations of the underground heating pipeline and establish a heat conduction channel. The pipeline information includes the pipeline diameter, pipeline wall thickness, pipeline burial depth, and insulation layer thickness.

[0059] Step S2: Use a drone to collect network map data of buried heating pipelines along the pipeline network using thermal imaging method, and generate ground heat dissipation characterization values ​​based on ambient temperature and pipeline medium temperature.

[0060] Step S3: Combine the pipeline network map data and the ground heat dissipation characterization value to generate abnormal points, take instantaneous heating measures for branch pipelines where the number of abnormal points exceeds the preset number, and collect the point map data of each abnormal point and each heat conduction channel.

[0061] Step S4: Generate an instantaneous heating model based on the point map data of each heat conduction channel, input the point map data of abnormal points into the instantaneous heating model to generate defect points and determine the defect type, and calculate the remaining life corresponding to each defect point according to the defect type, or determine the defect point as a leakage point.

[0062] Step S5: Based on the pipeline information and remaining life of each defect location, calculate the corresponding defect risk value to determine the risk level of each defect location and the corresponding treatment method.

[0063] The preset quantity is positively correlated with the length of the branch pipe where the abnormal point is located.

[0064] It is understandable that the longer the branch pipe where the abnormal point is located, the more points where defects may occur. Therefore, the preset number is positively correlated with the length of the branch pipe where the abnormal point is located. Optional,

[0065] Understandably, a heat conduction channel is established above the heating pipeline. A GIS system is used to locate the predicted defect point directly above it. Pipeline parameters are clarified, and surface obstacles (such as building foundations, vegetation, and municipal facilities) and underground concealed works (such as other pipelines and cables) are recorded. An underground pipeline detector (such as RD8000) is used to confirm that there are no intersecting pipelines to avoid construction conflicts. The thermal conductivity of the soil is sampled and tested. If the soil has low thermal conductivity (less than 0.5 W / (m·K)), a filling material with a higher thermal conductivity (greater than or equal to 10 W / (m·K)) needs to be selected. A hole is drilled directly above the predicted defect point, with the vertical distance between the bottom of the hole and the outer wall of the pipeline controlled at 10-50 cm. A high thermal conductivity material is filled into the hole, and the filling must be compacted to ensure that the material is in close contact with the pipeline insulation layer.

[0066] Understandably, when using instantaneous heating, the temperature increase is generally 5℃-15℃, and the heating time is generally 20 minutes to 30 minutes.

[0067] Specifically, this invention collects data on the network layout and past defect locations of buried heating pipelines. Based on these past defect locations and pipeline information, it determines the predicted defect locations of the buried heating pipelines and establishes heat conduction channels. Effective preventive monitoring measures are implemented in advance at locations prone to pipeline defects. Past defect locations include information such as defect type, causes, and environmental parameters. By training or optimizing the judgment model using this data, the system can more accurately identify the defect characteristics of specific pipeline sections. Traditional detection methods often require extensive, carpet-like inspections of large-scale pipeline networks or frequent excavation verification due to a lack of precise targets, resulting in high costs. By predicting defect locations, monitoring resources can be directed towards high-risk areas, effectively preventing pipeline leaks while improving the accuracy of determining the defect types of buried heating pipeline networks.

[0068] Please see Figure 2 As shown, this is a logic diagram for determining the predicted defect locations of buried heating pipelines according to an embodiment of the present invention. In step S1, the process of determining the predicted defect locations of buried heating pipelines includes...

[0069] Collect pipeline information on past defect locations;

[0070] Several characteristic points were marked on the underground heating pipeline;

[0071] The pipeline information of each feature point is matched one-to-one with the pipeline information of each past defect point, and the similarity is calculated.

[0072] The target matching degree MP of the pipeline information YB = (YB1, YB2, ..., YBj, ..., YBm) of the feature points and the pipeline information EB = (EB1, EB2, ..., EBj, ..., EBm) of the past defect points; where j = 1, 2, ..., m; similarity: MP = ∑mj=1YBj*EBj / (sqrt(∑mj=1(YBj)2)*sqrt(∑mj=1(EBj)2)).

[0073] The predicted defect locations are determined based on the similarity score and the preset similarity score.

[0074] If the similarity is greater than or equal to the preset similarity, the feature point corresponding to the similarity is determined to be the predicted defect point.

[0075] If the similarity is less than the preset similarity, the feature point corresponding to the similarity is determined not to be the predicted defect point.

[0076] In one specific embodiment, a preset similarity of 0.8 is set. If the similarity is 0.94, which is greater than the preset similarity, the feature point corresponding to the similarity is determined to be the predicted defect point.

[0077] If the similarity is 0.72, which is less than the preset similarity, then the feature point corresponding to the similarity is determined not to be a predicted defect point.

[0078] Among them, the preset similarity is negatively correlated with the length of the branch pipe where the feature point is located.

[0079] It is understandable that the longer the branch pipe where the feature point is located, the greater the probability of leakage. To increase the accuracy of the judgment, the preset similarity is negatively correlated with the length of the branch pipe where the feature point is located. Preferably, the preset similarity value ranges from 0.75 to 0.95.

[0080] Technical effect

[0081] Specifically, in step S1, the process of establishing a heat conduction channel includes,

[0082] Identify the surface area directly above the pipeline corresponding to the defect location;

[0083] A borehole area is created by drilling vertically from the surface area to directly above the pipeline.

[0084] Inject a high thermal conductivity medium into the borehole area and backfill.

[0085] Specifically, this invention reduces inaccurate data detection caused by excessive pipeline burial depth by establishing a heat conduction channel above the predicted defect point. It also reduces the impact of small data changes due to low soil thermal conductivity on analysis results, and minimizes the influence of other heat sources on pipeline detection from the surface or above the pipeline. The heat conduction channel directly constructs a shortcut for heat transfer from the pipeline defect point to the surface detection equipment, reducing heat loss in the soil, overcoming differences in soil thermal conductivity, amplifying the identifiability of defect data, and amplifying temperature changes at the defect point to 3℃-5℃ at the detection end. This eliminates the problem of different data representations for the same defect due to soil type differences, avoids heat dissipation interference from other facilities above the pipeline, and ensures that the heat changes captured by the sensor are specifically directed at the target defect point, further improving the accuracy of determining the defect type of the buried heating pipeline network.

[0086] Please see Figure 3 As shown, this is a schematic diagram of the process for generating ground heat dissipation characterization values ​​according to an embodiment of the present invention. In step S2, the process of generating ground heat dissipation characterization values ​​based on ambient temperature and pipe medium temperature includes,

[0087] Step S201: Collect the ambient temperature of the ground surface area directly above the pipeline by using a drone to travel along the pipeline network.

[0088] Step S202: Collect the temperature of the medium in the buried heating pipeline;

[0089] Step S203: Combine the ambient temperature and the pipe medium temperature to generate ground heat dissipation characterization values ​​corresponding to different pipe diameters.

[0090] Specifically, the ground heat dissipation characteristic value = k(ambient temperature - pipe medium temperature), where ambient temperature (unit: °C), pipe medium temperature (unit: °C), and k is the heat dissipation coefficient (unit: W / (m²)). 2 ·℃), optional, for ordinary insulation layer pipes (such as polyurethane insulation, thickness 50-100mm), k is taken as 0.5~2W / (m 2 For high-efficiency insulated pipes (such as composite insulation layers with a thickness > 100 mm), k is taken as 0.1~0.5 W / (m). 2 (·℃), when calculating with the above formula, only the numerical value is taken.

[0091] Technical effect

[0092] Specifically, in step S3, the process of collecting the location map data of each abnormal point and each heat conduction channel includes,

[0093] The initial pipeline medium temperature is generated by combining pipeline network map data and ground heat dissipation characterization values.

[0094] It is understandable that the initial pipe medium temperature = ground heat dissipation characterization value / k + pipe network map data.

[0095] Anomaly points are determined based on the initial pipeline medium temperature, and instantaneous heating is applied to branch pipelines where the number of anomaly points exceeds the preset number.

[0096] It is understandable that if the initial pipe medium temperature is greater than the pipe medium temperature, then the pipe area corresponding to the initial pipe medium temperature is determined to be an abnormal point.

[0097] Under conditions of instantaneous temperature rise, point map data of each abnormal point and each heat conduction channel were collected;

[0098] Among them, the branch pipes are pipe loops composed of corresponding supply and return water pipes, and the instantaneous temperature rise is to increase the supply water temperature of the branch pipes.

[0099] Technical effect

[0100] Specifically, in step S4, the process of generating defect locations includes,

[0101] A transient temperature rise model is generated based on the point map data of each heat conduction channel;

[0102] Input the location map data of the abnormal points into the instantaneous heating model to generate a predicted pipeline temperature;

[0103] The predicted pipeline temperature and the experimental pipeline temperature under instantaneous heating conditions are combined to determine whether the abnormal point is a defect point.

[0104] Specifically, if the predicted pipe temperature is greater than the experimental pipe temperature under instantaneous heating conditions, the abnormal point is determined to be a defect point.

[0105] Technical effect

[0106] Specifically, in step S4, the temperature rise value is determined based on the temperature values ​​of the defect location before and after the instantaneous temperature rise, and the defect type of the defect location is determined based on the temperature rise value.

[0107] If the temperature rise is less than the first preset temperature rise, the pipe insulation layer at the defect location is determined to be carbonized.

[0108] If the temperature rise is greater than or equal to the first preset temperature rise and less than the second preset temperature rise, the pipe insulation layer at the defect location is determined to be damaged.

[0109] If the temperature rise is greater than or equal to the second preset temperature rise, the pipe at the defect location is determined to be leaking.

[0110] In one specific embodiment, the first preset temperature rise value is set to 3°C and the second preset temperature rise value is set to 5°C. If the temperature rise value is 2.4°C, which is less than the first preset temperature rise value, it is determined that the pipe insulation layer at the defect location is carbonized.

[0111] If the temperature rise is 3.6℃, ​​which is greater than the first preset temperature rise but less than the second preset temperature rise, then the pipe insulation layer at the defect location is determined to be damaged.

[0112] If the temperature rise is 7.5℃, which is greater than or equal to the second preset temperature rise, then the pipeline at the defect location is determined to be leaking.

[0113] Among them, the first preset temperature rise value and the second preset temperature rise value are negatively correlated with the length of the branch pipe where the defect point is located, and the first preset temperature rise value is less than the second preset temperature rise value.

[0114] Understandably, the longer the branch pipe where the defect point is located, the greater the risk of pipe defects and leaks, and the more defect points there are. Therefore, the first and second preset temperature rise values ​​are negatively correlated with the length of the branch pipe where the defect point is located. Optionally, the range of the first preset temperature rise value is 2℃ to 3℃, and the range of the second preset temperature rise value is 4℃ to 6℃.

[0115] Specifically, this invention employs instantaneous heating for branch pipes with an abnormal number exceeding a preset limit. Based on the increase in medium temperature within the branch pipe caused by instantaneous heating, the defect type at the defect location is determined according to the change in temperature. Instantaneous heating actively amplifies the heat exchange effect of the defect by increasing the temperature difference between the medium and the outside environment. After heating, the temperature difference between the hot water at the leak point and the surrounding soil increases significantly, the heat loss rate increases, and the characteristic changes from fuzzy fluctuations to significant step differences, allowing for a clear and accurate determination of pipeline defects. Instantaneous heating actively enhances the signal strength, making the amplitude of the defect characteristic signal far exceed environmental interference. The controllability of the heating process can form standardized detection conditions, reducing inconsistencies in detection data caused by natural environmental fluctuations (such as diurnal temperature differences and weather changes), making defect characteristics from different times and regions comparable. While improving the stability of the judgment model, it further improves the accuracy of determining the defect type of buried heating pipeline networks.

[0116] Specifically, in step S4, the remaining lifetime corresponding to each defect location is calculated based on the defect type, wherein...

[0117] If the defect type is carbonization of the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the safe pipe wall thickness, the internal corrosion rate of the pipe, and the service life of the pipe.

[0118] If the defect type is damage to the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the pipe safety wall thickness, the internal corrosion rate, the external corrosion rate, and the pipe's service life.

[0119] It is understandable that the safe wall thickness of a pipeline is the minimum wall thickness required for the pipeline to operate normally.

[0120] Specifically, if the defect type is carbonization of the pipe insulation layer, then the remaining life corresponding to the defect location = (pipe wall thickness - pipe safe wall thickness) / pipe internal corrosion rate - pipe service life, where pipe wall thickness (unit: mm), pipe safe wall thickness (unit: mm), pipe internal corrosion rate (unit: mm / year), pipe service life (unit: years), and the remaining life corresponding to the defect location (unit: years).

[0121] Specifically, if the defect type is damage to the pipe insulation layer, then the remaining life corresponding to the defect location = (pipe wall thickness - pipe safe wall thickness) / (internal corrosion rate + external corrosion rate) - years of pipe service, where pipe wall thickness (unit: mm), pipe safe wall thickness (unit: mm), internal corrosion rate (unit: mm / year), external corrosion rate (unit: mm / year), years of pipe service (unit: years), and the remaining life corresponding to the defect location (unit: years).

[0122] In a specific embodiment, the wall thickness of the buried heating pipeline is set to 10mm, the safe wall thickness is 7mm, the internal corrosion rate is 0.3mm / year, the service life of the pipeline is 6 years, and the defect type is determined to be carbonization of the pipeline insulation layer. Then, the remaining life corresponding to the defect point = (pipeline wall thickness - safe wall thickness) / internal corrosion rate - service life of the pipeline = (10-7) / 0.3-6 = 4 years.

[0123] Specifically, based on the pipeline information and remaining life at each defect location, the corresponding defect risk value is calculated: R = w δ ×F δ +w T ×F T +w D ×F D +w A ×F A +w H ×F H , where w δ w T w D w A w H w represents the weighted value corresponding to each risk factor. δ +w T +w D +w A +w H =1. Since wall thickness directly determines the pipeline's corrosion and explosion resistance, it is the most critical risk factor. Aging is the main cause of pipeline defects. Short remaining life means a significant decline in material performance. Large-diameter pipes have high structural complexity, and the probability of defects increases linearly with increasing pipe diameter. The insulation layer affects the corrosion rate and thermal stability, indirectly but continuously impacting the risk. Burial depth affects the timeliness of defect detection and repair, indirectly amplifying the consequences of the risk. Generally, w is taken as... δ The value is 0.3, w T It is 0.25, w D The value is 0.15, w A The value is 0.15, w H It is 0.15; F δ Pipeline wall thickness risk factor Where loss rate = (design wall thickness - pipe wall thickness) / design wall thickness, design wall thickness (unit: mm), pipe wall thickness (unit: mm), F T Remaining life risk factor Among them, remaining life (unit: years), design life (unit: years), F D Pipe diameter risk factor Wherein, pipe diameter (unit: mm), DN1200 is the large diameter threshold, F ARisk factors for insulation layer thickness Among them, the insulation layer thickness (unit: mm), the design thickness (unit: mm), and F H Pipeline burial depth risk factors The deviation is the pipeline burial depth minus 1.5 (the optimal burial depth is 1.5m, and the risk reaches the upper limit when the deviation is 2m), and R is the defect risk value. All calculations in the above formulas use numerical values.

[0124] In a specific embodiment, the pipe diameter is set to 600mm, the pipe wall thickness to 8mm, the designed wall thickness to 10mm, the pipe burial depth to 2.5m, the insulation layer thickness to 30mm, the designed thickness to 50mm, the remaining service life to 8 years, and the designed service life to 30 years. Then the defect risk value is...

[0125] 0.075 + 0.12 + 0.075 + 0.06 + 0.1825 = 0.51.

[0126] Please see Figure 4 As shown, it is a logic diagram for determining the risk level of defect locations in an embodiment of the present invention. In step S5, the risk level of each defect location is determined sequentially based on the defect risk value and several preset risk values.

[0127] If the defect risk value is less than the first preset risk value, then the risk level of the defect location corresponding to the defect risk value is determined as the first leakage risk level;

[0128] If the defect risk value is greater than or equal to the first preset risk value and less than the second preset risk value, then the risk level of the defect location corresponding to the defect risk value is determined to be the second leakage risk level.

[0129] If the defect risk value is greater than the second preset risk value, then the risk level of the defect location corresponding to the defect risk value is determined to be the third leakage risk level.

[0130] In a specific embodiment, a first preset risk value is set to 0.3 and a second preset risk value is set to 0.6. If the defect risk value of 0.24 is less than the first preset risk value, then the risk level of the defect point corresponding to the defect risk value is determined to be the first leakage risk level.

[0131] If the defect risk value of 0.51 is greater than the first preset risk value and less than the second preset risk value, then the risk level of the defect location corresponding to the defect risk value is determined to be the second leakage risk level.

[0132] If the defect risk value of 0.68 is greater than the second preset risk value, then the risk level of the defect location corresponding to the defect risk value is determined to be the third leakage risk level.

[0133] Specifically, both the first and second preset risk values ​​are positively correlated with the pipe diameter, and the first preset risk value is less than the second preset risk value.

[0134] It is understandable that the larger the pipe diameter, the more fluid flows through it, the stronger the corrosion on the pipe wall, the more joints there are, the more uneven the distribution of medium pressure, the more prone to joint leakage, and the greater its own weight, the more significantly affected by soil settlement. Therefore, both the first and second preset risk values ​​are positively correlated with the pipe diameter.

[0135] Preferably, the first preset risk value ranges from 0.2 to 0.4, and the second preset risk value ranges from 0.6 to 0.8.

[0136] Technical effect

[0137] Specifically, in step S5, the corresponding processing method includes,

[0138] If the risk level of the defect location is the first leakage risk level, then it is determined that the operation requirements are met and operation continues;

[0139] If the risk level of the defect location is the second leakage risk level, then it is determined to increase the number of drone inspections.

[0140] If the risk level of the defect location is the third leakage risk level, then it is determined that the pipeline segment corresponding to the defect location should be treated.

[0141] Specifically, this invention calculates the corresponding defect risk value based on pipeline information and remaining life at each defect location to determine the risk level of each defect location and the corresponding treatment method. Through multi-dimensional data fusion, it achieves accurate quantification of defect risk, reduces judgment bias, and adopts differentiated treatment methods for defect locations with different risk levels. This process is essentially a dynamic verification of defect type determination. The determination of defect type no longer relies on a single detection result, but is continuously corrected through actual verification data, which gradually improves the system's ability to identify complex defects. The multi-dimensional fusion judgment method can reduce the overall misjudgment rate of underground heating pipeline defect types by 25% to 30%, especially significantly improving the identification accuracy of early minor defects, providing a more reliable decision-making basis for the preventive maintenance of the pipeline network, and further improving the accuracy of determining the defect type of underground heating pipeline network.

[0142] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0143] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligently determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs), characterized in that, include: Collect the pipeline network route and past defect locations of the underground heating pipeline, and determine the predicted defect locations of the underground heating pipeline based on the past defect locations and pipeline information, and establish heat conduction channels. The buried heating pipeline network map data is collected by using a drone to collect thermal imaging data along the pipeline network, and ground heat dissipation characterization values ​​are generated based on ambient temperature and pipeline medium temperature. By combining the pipeline network map data and the ground heat dissipation characterization value, abnormal points are generated. For branch pipelines where the number of abnormal points exceeds a preset number, instantaneous heating is applied. Point map data of each abnormal point and each heat conduction channel are collected. A transient temperature rise model is generated based on the point map data of each of the heat conduction channels. The point map data of the abnormal points are input into the transient temperature rise model to generate defect points and determine the defect type. The remaining life corresponding to each defect point is calculated according to the defect type, or the defect point is determined to be a leakage point. Based on the pipeline information and remaining life of each defect location, the corresponding defect risk value is calculated to determine the risk level of each defect location and the corresponding treatment method. The preset quantity is positively correlated with the length of the branch pipe where the abnormal point is located.

2. The intelligent method for determining the defect type of underground heating pipeline network based on UAVs according to claim 1, characterized in that, The process of determining the predicted defect locations of the buried heating pipeline includes, Collect pipeline information at the locations of past defects; Several characteristic points are marked on the underground heating pipeline; The pipeline information of each feature point is matched one-to-one with the pipeline information of each past defect point, and the similarity is calculated. The predicted defect locations are determined based on the similarity and the preset similarity. The preset similarity is negatively correlated with the length of the branch pipe where the feature point is located, and the pipe information includes pipe diameter, pipe wall thickness, pipe burial depth and insulation layer thickness.

3. The intelligent method for determining the defect type of underground heating pipeline network based on UAVs according to claim 2, characterized in that, The process of establishing a heat conduction channel includes, Determine the surface area directly above the pipeline corresponding to the defect location; A borehole area is created by drilling vertically from the surface area directly above the pipeline. A high thermal conductivity medium is injected into the drilled area and then backfilled.

4. The intelligent method for determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs) according to claim 3, characterized in that, The process of generating ground heat dissipation characterization values ​​based on ambient temperature and pipeline medium temperature includes, The ambient temperature of the ground surface area directly above the pipeline was collected by drones traveling along the pipeline network. Collect the temperature of the medium in the buried heating pipeline; By combining the ambient temperature and the temperature of the pipe medium, ground heat dissipation characterization values ​​corresponding to different pipe diameters are generated.

5. The intelligent method for determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs) according to claim 4, characterized in that, The process of collecting the location map data of each of the aforementioned abnormal points and each of the aforementioned heat conduction channels includes, The initial pipeline medium temperature is generated by combining the pipeline network map data and the ground heat dissipation characterization value; Based on the initial pipeline medium temperature, abnormal points are determined, and branch pipelines with more than the preset number of abnormal points are subjected to instantaneous heating. Under the condition of instantaneous temperature rise, point map data of each of the abnormal points and each of the heat conduction channels are collected; The branch pipe is a pipe loop consisting of corresponding supply and return water pipes, and the instantaneous temperature rise is to increase the supply water temperature of the branch pipe.

6. The intelligent method for determining the defect type of underground heating pipeline network based on UAVs according to claim 5, characterized in that, The process of generating defect locations includes: A sudden temperature rise model is generated based on the point map data of each of the aforementioned heat conduction channels; The location map data of the abnormal points are input into the instantaneous heating model to generate a predicted pipeline temperature; The predicted pipe temperature and the experimental pipe temperature under instantaneous heating conditions are combined to determine whether the abnormal point is a defect point.

7. The intelligent method for determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs) according to claim 6, characterized in that, The temperature rise value is determined based on the temperature values ​​of the defect location before and after the instantaneous temperature rise, and the defect type of the defect location is determined based on the temperature rise value.

8. The intelligent method for determining the defect type of underground heating pipeline network based on UAVs according to claim 7, characterized in that, The remaining lifetime corresponding to each defect location is calculated based on the defect type, wherein... If the defect type is carbonization of the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the safe pipe wall thickness, the internal corrosion rate of the pipe, and the service life of the pipe. If the defect type is damage to the pipe insulation layer, the remaining life corresponding to the defect location is determined by the pipe wall thickness, the pipe safety wall thickness, the internal corrosion rate, the external corrosion rate, and the pipe's service life.

9. The intelligent method for determining the defect type of underground heating pipeline network based on unmanned aerial vehicles (UAVs) according to claim 8, characterized in that, The risk level of each defect location is determined sequentially based on the defect risk value and several preset risk values.

10. The intelligent method for determining the defect type of underground heating pipeline network based on UAVs according to claim 9, characterized in that, The corresponding processing method includes, If the risk level of the defect location is the first leakage risk level, then it is determined that the operation requirements are met and operation continues; If the risk level of the defect location is the second leakage risk level, then it is determined to increase the number of drone inspections. If the risk level of the defect location is the third leakage risk level, then it is determined that the pipeline segment corresponding to the defect location should be treated.

Images