Quick positioning method and positioning system for underground heat supply pipe gallery leakage

Abstract

The embodiment of the invention provides a quick positioning method and positioning system for underground heat supply pipe gallery leakage, and belongs to the technical field of pipeline leakage positioning. The rapid positioning method comprises the steps that sensors are installed and arranged according to the density parameter of a heat supply pipeline in the underground heat supply pipe gallery, and the sensors comprise an infrared sensor and a humidity sensor; the sensors are installed and arranged according to the density parameters of the heat supply pipeline, the real-time data of the infrared sensors and the humidity sensors are obtained, then the early warning parameters of the current heat supply pipeline are obtained according to the real-time data, and then the early warning parameter predicted value of the heat supply pipeline at the next moment can be obtained; and finally performing early warning diagnosis on the leakage condition of the heat supply pipeline according to the early warning value of the early warning parameter. The mode that the heat supply pipeline is subjected to early warning diagnosis through the early warning parameter predicted value of the heat supply pipeline at the next moment is adopted, and the precision and the effect of monitoring the heat supply pipeline can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline leakage location, and particularly to a method and a system for quickly locating leakage in an underground heat supply pipe gallery. Background Art

[0003] At present, the inspection of underground heat supply pipe galleries is mostly carried out manually with leak detection instruments in hand. Manual inspection takes a long time, has great difficulty, low accuracy, and it is not easy to detect minor leaks. In addition, with the development of robot technology, some regions have used multi-sensor robots including visual sensors to inspect underground pipe galleries. By extracting features from visible light images, the color difference value and brightness difference value of the image data are obtained, and the set difference threshold value of the image and the image brightness difference threshold value are set. By comparing the actual image difference with the set threshold value, it can be detected whether the pipeline is damaged. However, for heat supply pipelines, with thermal insulation cotton wrapped outside, traditional visual sensors are difficult to capture minor leaks. Therefore, the traditional inspection method has low accuracy and poor effect.

[0004] The inventors of the present application found in the process of implementing the present invention that the above-mentioned solutions in the prior art have the defects of low detection accuracy and poor effect. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method and a system for quickly locating leakage in an underground heat supply pipe gallery, and the method and the system for quickly locating leakage in the underground heat supply pipe gallery have the functions of high detection accuracy and good effect.

[0006] To achieve the above purpose, on the one hand, an embodiment of the present invention provides a method for quickly locating leakage in an underground heat supply pipe gallery, including:

[0007] Install and set sensors according to the density parameter of the heat supply pipeline in the underground heat supply pipe gallery, wherein the sensors include an infrared sensor and a humidity sensor;

[0008] Obtain the real-time data of the infrared sensor and the humidity sensor;

[0009] Obtain the early warning parameter of the current heat supply pipeline according to the real-time data of the infrared sensor and the humidity sensor;

[0010] Obtain the predicted value of the early warning parameter of the heat supply pipeline at the next moment according to the early warning parameter of the current heat supply pipeline;

[0011] Carry out early warning diagnosis on the heat supply pipeline according to the predicted value of the early warning parameter of the heat supply pipeline at the next moment.

[0012] Optionally, installing sensors according to the density parameter of the heat supply pipeline in the underground heat supply pipe gallery includes:

[0013] Obtain the sum of the cross-sectional areas of the heating pipelines per unit length, the number of pipeline connection structures, and the sum of the pipeline bending angles in the current underground heating pipeline gallery;

[0014] Obtain the total number of infrared sensors in the current underground heating pipeline gallery according to formula (1),

[0015]

[0016] where N is the total number of infrared sensors, λ s is the pipeline cross-sectional area parameter, S 0 is the sum of the cross-sectional areas of the pipelines per unit length, λ p is the pipeline connection structure coefficient, P 0 is the number of pipeline connection structures per unit length, λ d is the pipeline bending parameter, D 0 is the sum of the pipeline bending angles per unit length, δ is the sensor density in the warning area, L d is the total length of the heating pipelines in the warning area;

[0017] Install the infrared sensors and the humidity sensors on the heating pipelines in the underground heating pipeline gallery according to the total number of the infrared sensors.

[0018] Optionally, obtaining the sum of the cross-sectional areas of the heating pipelines per unit length, the number of pipeline connection structures, and the sum of the pipeline bending angles in the current underground heating pipeline gallery includes:

[0019] Randomly segment the heating pipelines in the current underground heating pipeline gallery;

[0020] Obtain the sum of the cross-sectional areas of the heating pipelines per unit length in the current underground heating pipeline gallery according to formula (2),

[0021]

[0022] where S k is the cross-sectional area sum of the pipeline at the k-th randomly segmented position, n is the total number of segments of the heating pipeline, and k is an integer number;

[0023] Obtain the number of pipeline connection structures per unit length in the current underground heating pipeline gallery according to formula (3),

[0024]

[0025] where P k is the number of pipeline connection structures within the k-th segment;

[0026] Obtain the sum of the pipeline bending angles per unit length in the current underground heating pipeline gallery according to formula (4),

[0027]

[0028] Among them, D k is the sum of the pipeline bending angles within the k-th segment.

[0029] Optionally, obtaining the early warning parameters of the current heating pipeline according to the real-time data of the infrared sensor and the humidity sensor includes:

[0030] Obtain the real-time image collected by the infrared sensor and evenly divide the real-time image;

[0031] Obtain the temperature data of each partition in the real-time image;

[0032] Obtain the maximum temperature difference in the real-time image according to formula (5),

[0033] ΔT = T max - T min , (5)

[0034] where ΔT is the maximum temperature difference in the real-time image, T max is the maximum temperature in the real-time image, and T min is the minimum temperature in the real-time image;

[0035] Obtain the average temperature of all partitions in the real-time image according to formula (6),

[0036]

[0037] where T var is the average temperature of all partitions in the real-time image, T c is the temperature of the c-th partition in the real-time image, m is the number of partitions of the real-time image, and c is an integer number;

[0038] Obtain the humidity difference of the current heating pipeline according to formula (7),

[0039] ΔRH = RH g - RH c , (7)

[0040] where ΔRH is the humidity difference of the current heating pipeline, RH g is the reading of the pipeline humidity sensor, and RH c is the reading of the reference humidity sensor.

[0041] Optionally, obtaining the predicted value of the early warning parameters of the heating pipeline at the next moment according to the early warning parameters of the current heating pipeline includes:

[0042] Obtain the historical early warning parameters of the heating pipeline;

[0043] Build a GEW-LSTM heat supply pipeline leakage prediction model;

[0044] Train the GEW-LSTM heat supply pipeline leakage prediction model with the historical warning parameters;

[0045] Input the warning parameters of the current heat supply pipeline into the trained GEW-LSTM heat supply pipeline leakage prediction model to obtain the predicted value of the warning parameters of the heat supply pipeline at the next moment.

[0046] Optionally, training the GEW-LSTM heat supply pipeline leakage prediction model with the historical warning parameters includes:

[0047] Normalize the historical warning parameters of the heat supply pipeline and divide them into a training set and a validation set;

[0048] Obtain the forget gate information in the GEW-LSTM heat supply pipeline leakage prediction model according to formula (8),

[0049] f t =σ(W f ×[h t-1 ,x t +b f ), (8)

[0050] where f t is the forget gate information in the GEW-LSTM heat supply pipeline leakage prediction model, σ() is the sigmoid activation function, W f is the weight of the forget gate, b f is the bias of the forget gate, h t-1 is the hidden state of the previous time step, and x t is the input of the current time step;

[0051] Obtain the input gate information in the GEW-LSTM heat supply pipeline leakage prediction model according to formula (9),

[0052] i t =σ(W i ×[h t-1 ,x t +b i ), (9)

[0053] where i t is the input gate information in the GEW-LSTM heat supply pipeline leakage prediction model, W i is the weight of the input gate, and b i is the bias of the input gate;

[0054] Obtain the candidate unit state according to formula (10).

[0055]

[0056] wherein is the candidate unit state, tanh() is the activation function, and W c is the weight of the update unit, and b c is the bias of the update unit;

[0057] Obtain the unit state at the current moment according to formula (11).

[0058]

[0059] wherein C t is the unit state at the current moment, and C t-1 is the unit state of the previous time;

[0060] Obtain the output gate information in the GEW-LSTM heating pipeline leakage prediction model according to formula (12).

[0061] o t = σ(W o × [h t-1 , x t + b o ), (12)

[0062] wherein o t is the output gate information in the GEW-LSTM heating pipeline leakage prediction model, W o is the weight of the output gate, and b o is the bias of the output gate;

[0063] Obtain the output of the GEW-LSTM heating pipeline leakage prediction model according to formula (13).

[0064] h t = o t × tanh(C t ), (13)

[0065] wherein h t is the output of the GEW-LSTM heating pipeline leakage prediction model.

[0066] Optionally, predicting and diagnosing the heating pipeline according to the predicted value of the early warning parameter of the heating pipeline at the next moment includes:

[0067] Obtain the early warning parameter threshold of the heating pipeline at the next moment;

[0068] Obtain the leakage risk score based on the predicted value of the warning parameter of the heat supply pipeline at the next moment and the warning parameter threshold;

[0069] Determine the inspection plan according to the leakage risk score.

[0070] Optionally, obtaining the warning parameter threshold of the heat supply pipeline at the next moment includes:

[0071] Obtain the maximum temperature difference warning threshold of the heat supply pipeline according to formula (14),

[0072]

[0073] where ΔT T is the maximum temperature difference warning threshold of the heat supply pipeline, is the environmental impact correction coefficient of the maximum temperature difference, ΔT i is the maximum temperature difference during normal operation of the heat supply pipeline at the i-th moment, S is the total number of samples during normal operation of the heat supply pipeline, and i is an integer number;

[0074] Obtain the average temperature warning threshold of the heat supply pipeline according to formula (15),

[0075]

[0076] where, is the average temperature warning threshold of the heat supply pipeline, is the environmental impact correction coefficient of the average temperature, is the average temperature during normal operation of the heat supply pipeline at the i-th moment;

[0077] Obtain the humidity difference warning threshold of the heat supply pipeline according to formula (16),

[0078]

[0079] where ΔRH T is the humidity difference warning threshold of the heat supply pipeline, is the environmental impact correction coefficient of the humidity difference, ΔRH i is the humidity difference during normal operation of the heat supply pipeline at the i-th moment.

[0080] Optionally, obtaining the leakage risk score based on the predicted value of the warning parameter of the heat supply pipeline at the next moment and the warning parameter threshold includes:

[0081] Obtain the first correction threshold, second correction threshold, third correction threshold, and fourth correction threshold of the maximum temperature difference according to the maximum temperature difference warning threshold of the heat supply pipeline;

[0082] Obtain the maximum temperature difference leakage risk score based on the predicted value of the maximum temperature difference of the heating pipeline at the next moment, the first correction threshold of the maximum temperature difference, the second correction threshold of the maximum temperature difference, the third correction threshold of the maximum temperature difference, and the fourth correction threshold of the maximum temperature difference;

[0083] Obtain the first correction threshold of the average temperature, the second correction threshold of the average temperature, the third correction threshold of the average temperature, and the fourth correction threshold of the average temperature according to the warning threshold of the average temperature of the heating pipeline;

[0084] Obtain the average temperature leakage risk score based on the predicted value of the average temperature of the heating pipeline at the next moment, the first correction threshold of the average temperature, the second correction threshold of the average temperature, the third correction threshold of the average temperature, and the fourth correction threshold of the average temperature;

[0085] Obtain the first correction threshold of the humidity difference, the second correction threshold of the humidity difference, the third correction threshold of the humidity difference, and the fourth correction threshold of the humidity difference according to the warning threshold of the humidity difference of the heating pipeline;

[0086] Obtain the humidity difference leakage risk score based on the predicted value of the humidity difference of the heating pipeline at the next moment, the first correction threshold of the humidity difference, the second correction threshold of the humidity difference, the third correction threshold of the humidity difference, and the fourth correction threshold of the humidity difference;

[0087] Obtain the leakage risk score of the heating pipeline at the next moment according to formula (17),

[0088] F = F TD + F TB + F RH , (17)

[0089] where F is the leakage risk score of the heating pipeline at the next moment, F TD is the maximum temperature difference leakage risk score, F TB is the average temperature leakage risk score, F RH is the humidity difference leakage risk score.

[0090] On the other hand, the present invention also provides a rapid positioning system for leakage of an underground heating pipe gallery, including:

[0091] A plurality of sensors, respectively used for being installed on the heating pipelines in the underground heating pipe gallery;

[0092] A data processing module, connected to the plurality of sensors, and used for executing any one of the above rapid positioning methods.

[0093] Through the above technical solutions, the method and system for quickly locating leaks in the underground heat supply pipe gallery provided by the present invention install sensors according to the density parameters of the heat supply pipes, obtain real-time data from the infrared sensors and humidity sensors, and then obtain the warning parameters of the current heat supply pipes based on this real-time data. Furthermore, the predicted values of the warning parameters of the heat supply pipes at the next moment can be obtained. Finally, the leakage conditions of the heat supply pipes are warned and diagnosed based on the warning parameter prediction values at the next moment. By using the predicted values of the warning parameters of the heat supply pipes at the next moment to warn and diagnose the heat supply pipes, the accuracy and effectiveness of monitoring the heat supply pipes can be effectively improved.

[0094] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. They are used together with the following specific implementation to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0096] Figure 1 is a flowchart of a method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0097] Figure 2 is a flowchart of installing sensors in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0098] Figure 3 is a flowchart of obtaining unit parameters in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0099] Figure 4 is a flowchart of obtaining warning parameters in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0100] Figure 5 is a flowchart of obtaining predicted values of warning parameters in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0101] Figure 6 is a flowchart of training a prediction model in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0102] Figure 7 is a flowchart of determining an inspection plan in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0103] Figure 8It is a flowchart for obtaining an early warning threshold in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention;

[0104] Figure 9 It is a flowchart for obtaining a leakage risk score in the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention. Specific embodiments

[0105] The following will describe in detail the specific embodiments of the embodiments of the present invention with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining and illustrating the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0106] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be regarded as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0107] Figure 1 It is a flowchart of the method for quickly locating leaks in an underground heat supply pipe gallery according to an embodiment of the present invention. In Figure 1 it, the quick location method may include:

[0108] In step S10, sensors are installed according to the density parameters of the heat supply pipes in the underground heat supply pipe gallery, where the sensors include an infrared sensor and a humidity sensor. Specifically, for the underground heat supply pipe gallery, it may include a newly planned heat supply pipe gallery and an already completed underground heat supply pipe gallery. For the newly planned heat supply pipe gallery, relevant parameters of the pipe density can be directly recorded during the construction period, while for the already completed underground heat supply pipe gallery, subsequent manual entry is required for surveying and mapping to record relevant parameters. Specifically, the density parameters may include the sum of the cross-sectional areas of the pipes per unit length, the number of connection structures per unit length, and the sum of the bending angles per unit length. The installation quantity and positions of the infrared sensor and the humidity sensor can be determined according to the specific values of the above density parameters to ensure an efficient and accurate data collection scheme.

[0109] In step S11, real-time data of the infrared sensor and the humidity sensor are obtained.

[0110] In step S12, early warning parameters of the current heat supply pipe are obtained according to the real-time data of the infrared sensor and the humidity sensor. Among them, after obtaining the real-time data of the infrared sensor and the humidity sensor, they are converted to obtain the early warning parameters of the current heat supply pipe.

[0111] In step S13, the predicted value of the warning parameter of the heat supply pipeline at the next moment is obtained according to the warning parameter of the current heat supply pipeline. Among them, for the predicted value of the warning parameter of the heat supply pipeline at the next moment, the method of training a prediction model with historical data can be adopted.

[0112] In step S14, warning diagnosis is performed on the heat supply pipeline according to the predicted value of the warning parameter of the heat supply pipeline at the next moment. Among them, after obtaining the predicted value of the warning parameter of the heat supply pipeline at the next moment, it is possible to make a judgment in combination with the corresponding threshold value to determine whether there is a leakage risk in the heat supply pipeline at the next moment, and then give a warning.

[0113] In steps S10 to S14, first install sensors for the density parameters of the heat supply pipeline and obtain the real-time data of the sensors. Then, obtain the warning parameter of the current heat supply pipeline according to the real-time data, and at the same time train the warning parameter prediction model of the heat supply pipeline in combination with historical data, so as to obtain the predicted value of the warning parameter of the heat supply pipeline at the next moment. Finally, according to the warning parameter prediction value and the corresponding threshold value, the leakage situation of the heat supply pipeline can be warned and diagnosed, and whether to give a warning is determined according to the diagnosis result.

[0114] The traditional inspection method of the heat supply pipe gallery uses a multi-sensor robot including a visual sensor to inspect the underground pipe gallery. Features are extracted from visible light images to obtain the color difference value and brightness difference value of the image data, and the set difference threshold value of the image and the image brightness difference threshold value are set. Comparing the actual image difference with the set threshold value can detect whether the pipeline is damaged. However, for heat supply pipelines, with thermal insulation cotton wrapped outside, it is difficult for traditional visual sensors to capture tiny leaks. Therefore, the traditional inspection method has low accuracy and poor effect. In this embodiment of the present invention, the method of warning and diagnosing the heat supply pipeline by using the predicted value of the warning parameter of the heat supply pipeline at the next moment can effectively improve the accuracy and effect of monitoring the heat supply pipeline.

[0115] In this embodiment of the present invention, after obtaining data such as the pipeline density parameter of the underground pipe gallery, the installation quantity of the sensors of the underground pipe gallery can be determined, and the specific steps can be as Figure 2 shown. Specifically, in Figure 2 , the quick positioning method may further include:

[0116] In step S100, obtain the cross-sectional area sum of the unit length pipeline of the heat supply pipeline in the current underground heat supply pipe gallery, the number of pipeline connection structures, and the pipeline bending angle sum. Among them, the obtaining steps of the above parameters of the heat supply pipeline can be as Figure 3 shown. Specifically, in Figure 3 , the parameter obtaining steps may include:

[0117] In step S1000, the heating pipelines in the current underground heating pipe gallery are randomly segmented. Among them, the segmentation methods include but are not limited to equal-interval segmentation, etc.

[0118] In step S1001, according to formula (2), the sum of the cross-sectional areas of the pipelines per unit length in the current underground heating pipe gallery is obtained.

[0119]

[0120] where S k is the sum of the cross-sectional areas of the pipelines at the k-th randomly segmented position, n is the total number of segments of the heating pipelines, and k is an integer number.

[0121] In step S1002, according to formula (3), the number of pipeline connection structures per unit length in the current underground heating pipe gallery is obtained.

[0122]

[0123] where P k is the number of pipeline connection structures within the k-th segment.

[0124] In step S1003, according to formula (4), the sum of the pipeline bending angles per unit length in the current underground heating pipe gallery is obtained.

[0125]

[0126] where D k is the sum of the pipeline bending angles within the k-th segment.

[0127] In step S101, according to formula (1), the total number of infrared sensors in the current underground heating pipe gallery is obtained.

[0128]

[0129] where N is the total number of infrared sensors, λ s is the pipeline cross-sectional area parameter, with the unit of 1 / m 2 , S 0 is the sum of the cross-sectional areas of the pipelines per unit length, with the unit of m 2 , λ p is the pipeline connection structure coefficient, P 0 is the number of pipeline connection structures per unit length, λ d is the pipeline bending parameter, with the unit of 1 / degree, D 0 is the sum of the pipeline bending angles per unit length, with the unit of degree, δ is the sensor density in the warning area, with the unit of 1 / m, and L d is the total length of the heating pipelines in the warning area, with the unit of m.

[0130] In step S102, infrared sensors and humidity sensors are installed on the heating pipelines in the underground heating pipe gallery according to the total number of infrared sensors. After obtaining the total number of infrared sensors, the infrared sensors are set directly below the heating pipelines to ensure that the relative positions of the images of each section of the heating pipeline with respect to the infrared sensors are approximately the same. Referring to the installation quantity of the infrared sensors, the humidity sensors are installed correspondingly near the heating pipelines, and reference humidity sensors are installed at other positions of the heating pipelines.

[0131] In steps S100 to S102, first obtain the cross-sectional area sum per unit length of the heating pipelines, the number of pipeline connection structures, and the sum of the pipeline bending angles in the current underground heating pipe gallery, then determine the total number of infrared sensors to be installed according to the above pipeline density parameters, and finally install the infrared sensors and humidity sensors according to the total number of infrared sensors, so as to achieve the installation of the sensors, and then the temperature, humidity parameters, etc. of the heating pipelines corresponding to the detection ranges of each sensor can be accurately and conveniently obtained.

[0132] In this embodiment of the present invention, after the sensors are installed on the heating pipelines, the warning parameters of the heating pipelines within the monitoring area of each sensor can be obtained. Specifically, the obtaining steps can be as Figure 4 shown. Specifically, in Figure 4 , this rapid positioning method may further include:

[0133] In step S120, obtain the real-time image collected by the infrared sensor and evenly divide the real-time image.

[0134] In step S121, obtain the temperature data of each partition in the real-time image.

[0135] In step S122, obtain the maximum temperature difference in the real-time image according to formula (5),

[0136] ΔT=T max -T min , (5)

[0137] where ΔT is the maximum temperature difference in the real-time image, T max is the maximum temperature in the real-time image, and T min is the minimum temperature in the real-time image.

[0138] In step S123, obtain the average temperature of all partitions in the real-time image according to formula (6),

[0139]

[0140] where T var is the average temperature of all partitions in the real-time image, and T c$T_c$ is the temperature of the $c$-th partition in the real-time image, $m$ is the number of partitions of the real-time image, and $c$ is an integer numbering.

[0141] In step S124, the humidity difference of the current heating pipeline is obtained according to formula (7).

[0142] $\Delta RH = RH$ g $- RH$ c , (7)

[0143] where $\Delta RH$ is the humidity difference of the current heating pipeline, $RH$ g is the reading of the pipeline humidity sensor, and $RH$ c is the reading of the reference humidity sensor.

[0144] In this embodiment of the present invention, for the prediction of the warning parameters of the heating pipeline, the historical data of the heating pipeline can be used to train the prediction model, and the prediction model is used to predict the warning parameters of the heating pipeline at the next moment. Specifically, the steps can be as Figure 5 shown. Specifically, in Figure 5 , the fast positioning method can further include:

[0145] In step S130, the historical warning parameters of the heating pipeline are obtained. Among them, the historical warning parameters can include the warning parameter values of the heating pipeline at consecutive equally spaced moments.

[0146] In step S131, a GEW-LSTM heating pipeline leakage prediction model is constructed.

[0147] In step S132, the historical warning parameters are used to train the GEW-LSTM heating pipeline leakage prediction model. Among them, the training steps for the GEW-LSTM heating pipeline leakage prediction model can include the steps as Figure 6 shown. Specifically, in Figure 6 , the model training steps can include:

[0148] In step S1320, the historical warning parameters of the heating pipeline are normalized, and a training set and a validation set are divided. Among them, the training set is used to train the model, and the validation set is used to validate the model.

[0149] In step S1321, the forgetting gate information in the GEW-LSTM heating pipeline leakage prediction model is obtained according to formula (8).

[0150] $f$ t $= \sigma(W$ f $\times [h$ t-1 , $x$ t $] + b$ f ), (8)

[0151] Among them, f t is the forgetting gate information in the GEW-LSTM heat supply pipeline leakage prediction model, σ() is the sigmoid activation function, W f is the weight of the forgetting gate, b f is the bias of the forgetting gate, h t-1 is the hidden state of the previous time step, and x t is the input of the current time step.

[0152] In step S1322, the input gate information in the GEW-LSTM heat supply pipeline leakage prediction model is obtained according to formula (9),

[0153] i t = σ(W i × [h t-1 , x t + b i ), (9)

[0154] Among them, i t is the input gate information in the GEW-LSTM heat supply pipeline leakage prediction model, W i is the weight of the input gate, and b i is the bias of the input gate.

[0155] In step S1323, the candidate cell state is obtained according to formula (10),

[0156]

[0157] Among them, is the candidate cell state, tanh() is the activation function, W c is the weight of the update cell, and b c is the bias of the update cell.

[0158] In step S1324, the cell state at the current moment is obtained according to formula (11),

[0159]

[0160] Among them, C t is the cell state at the current moment, and C t-1 is the cell state of the previous time.

[0161] In step S1325, the output gate information in the GEW-LSTM heat supply pipeline leakage prediction model is obtained according to formula (12),

[0162] o t = σ(W o × [h t-1 , x t + b o ), (12)

[0163] Among them, o t is the output gate information in the GEW-LSTM heat supply pipeline leakage prediction model, and W o is the weight of the output gate, and b o is the bias of the output gate.

[0164] In step S1326, obtain the output of the GEW-LSTM heat supply pipeline leakage prediction model according to formula (13),

[0165] h t = o t ×tanh(C t ), (13)

[0166] Among them, h t is the output of the GEW-LSTM heat supply pipeline leakage prediction model, that is, the hidden state for updating the current time step.

[0167] In step S133, input the warning parameter of the current heat supply pipeline into the trained GEW-LSTM heat supply pipeline leakage prediction model to obtain the predicted value of the warning parameter of the heat supply pipeline at the next moment.

[0168] In steps S130 to S133, first obtain the historical warning parameters of the heat supply pipeline, construct the GEW-LSTM heat supply pipeline leakage prediction model, and train the prediction model with the historical warning parameters. Then obtain the warning parameters of the current heat supply pipeline and input them into the trained prediction model to obtain the predicted value of the warning parameter of the heat supply pipeline at the next moment.

[0169] In this embodiment of the present invention, after obtaining the predicted value of the warning parameter of the heat supply pipeline at the next moment, the leakage state of the heat supply pipeline at the next moment can be predicted to achieve early warning. Specifically, the warning steps can be as Figure 7 shown in the steps. Specifically, in Figure 7 , the quick positioning method may further include:

[0170] In step S140, obtain the warning parameter threshold of the heat supply pipeline at the next moment. Among them, the acquisition of the warning parameter threshold of the heat supply pipeline at the next moment can be obtained in combination with the historical data when the heat supply pipeline operates normally. Specifically, the acquisition steps can be as Figure 8 shown. Specifically, in Figure 8 , the acquisition steps of the warning parameter threshold may include:

[0171] In step S1400, obtain the maximum temperature difference warning threshold of the heat supply pipeline according to formula (14),

[0172]

[0173] Among them, ΔT T is the maximum temperature difference warning threshold of the heating pipeline, is the environmental impact correction coefficient of the maximum temperature difference, and ΔT i is the maximum temperature difference during the normal operation of the heating pipeline at the i-th moment, S is the total number of samples during the normal operation of the heating pipeline, and i is an integer number.

[0174] In step S1401, the average temperature warning threshold of the heating pipeline is obtained according to formula (15),

[0175]

[0176] Among them, is the average temperature warning threshold of the heating pipeline, is the environmental impact correction coefficient of the average temperature, is the average temperature of the heating pipeline at the i-th moment during normal operation.

[0177] In step S1402, the humidity difference warning threshold of the heating pipeline is obtained according to formula (16),

[0178]

[0179] Among them, ΔRH T is the humidity difference warning threshold of the heating pipeline, is the environmental impact correction coefficient of the humidity difference, and ΔRH i is the humidity difference of the heating pipeline at the i-th moment during normal operation.

[0180] In step S141, the leakage risk score is obtained according to the predicted value of the warning parameter and the warning parameter threshold of the heating pipeline at the next moment. Among them, the leakage risk score of the heating pipeline at the next moment can be determined according to the predicted value and threshold of each warning parameter. Specifically, the determination steps can be as Figure 9 shown. Specifically, in Figure 9 the calculation steps of this leakage risk score can include:

[0181] In step S1410, the first correction threshold of the maximum temperature difference, the second correction threshold of the maximum temperature difference, the third correction threshold of the maximum temperature difference, and the fourth correction threshold of the maximum temperature difference are obtained according to the maximum temperature difference warning threshold of the heating pipeline. Among them, the first correction threshold of the maximum temperature difference, the second correction threshold of the maximum temperature difference, the third correction threshold of the maximum temperature difference, and the fourth correction threshold of the maximum temperature difference correspond to 1.05α dT ΔT T 、1.1α dT ΔT T 、1.2αdT ΔT T and 1.3α dT ΔT T , α dT is the correction parameter for the maximum temperature difference leakage risk threshold.

[0182] In step S1411, the maximum temperature difference leakage risk score is obtained based on the predicted value of the maximum temperature difference of the heat supply pipeline at the next moment, the first correction threshold of the maximum temperature difference, the second correction threshold of the maximum temperature difference, the third correction threshold of the maximum temperature difference, and the fourth correction threshold of the maximum temperature difference. Among them, the maximum temperature difference leakage risk score can include:

[0183] When ΔT′≥1.05α dT ΔT T , the leakage risk assessment of the heat supply pipeline is 1 point;

[0184] When ΔT′≥1.1α dT ΔT T , the leakage risk assessment of the heat supply pipeline is 2 points;

[0185] When ΔT′≥1.2α dT ΔT T , the leakage risk assessment of the heat supply pipeline is 3 points;

[0186] When ΔT′≥1.3α dT ΔT T , the leakage risk assessment of the heat supply pipeline is 4 points;

[0187] In other cases, the leakage risk assessment of the heat supply pipeline is 0 points, where ΔT ′ is the predicted value of the maximum temperature difference of the heat supply pipeline at the next moment.

[0188] In step S1412, the first correction threshold of the average temperature, the second correction threshold of the average temperature, the third correction threshold of the average temperature, and the fourth correction threshold of the average temperature are obtained according to the warning threshold of the average temperature of the heat supply pipeline. Among them, the first correction threshold of the average temperature, the second correction threshold of the average temperature, the third correction threshold of the average temperature, and the fourth correction threshold of the average temperature respectively correspond to and α bT is the correction parameter for the average temperature leakage risk threshold.

[0189] In step S1413, the average temperature leakage risk score is obtained based on the predicted value of the average temperature of the heat supply pipeline at the next moment, the first correction threshold of the average temperature, the second correction threshold of the average temperature, the third correction threshold of the average temperature, and the fourth correction threshold of the average temperature. Among them, for the average temperature leakage risk score, it can include:

[0190] When The risk assessment of heat supply pipeline leakage is 1 point;

[0191] When The risk assessment of heat supply pipeline leakage is 2 points;

[0192] When The risk assessment of heat supply pipeline leakage is 3 points;

[0193] When The risk assessment of heat supply pipeline leakage is 4 points;

[0194] In other cases, the risk assessment of heat supply pipeline leakage is 0 point, where is the predicted average temperature value of the heat supply pipeline at the next moment.

[0195] In step S1414, the first humidity difference correction threshold, the second humidity difference correction threshold, the third humidity difference correction threshold, and the fourth humidity difference correction threshold are obtained according to the humidity difference warning threshold of the heat supply pipeline. Among them, the first humidity difference correction threshold, the second humidity difference correction threshold, the third humidity difference correction threshold, and the fourth humidity difference correction threshold respectively correspond to 1.05α sT ΔRH T 、1.1α sT ΔRH T 、1.2α sT ΔRH T and 1.3α sT ΔRH T ,α sT is the humidity difference leakage risk threshold correction parameter.

[0196] In step S1415, the humidity difference leakage risk score is obtained according to the predicted humidity difference value of the heat supply pipeline at the next moment and the first humidity difference correction threshold, the second humidity difference correction threshold, the third humidity difference correction threshold, and the fourth humidity difference correction threshold. Among them, the humidity difference leakage risk score can include:

[0197] When ΔRH′≥1.05α sT ΔRH T ,the risk assessment of heat supply pipeline leakage is 1 point;

[0198] When ΔRH′≥1.1α sT ΔRH T ,the risk assessment of heat supply pipeline leakage is 2 points;

[0199] When ΔRH′≥1.2α sT ΔRH T ,the risk assessment of heat supply pipeline leakage is 3 points;

[0200] When ΔRH′≥1.3α sT ΔRH T, the risk assessment of heat supply pipeline leakage is 4 points;

[0201] In other cases, the risk assessment of heat supply pipeline leakage is 0 points, where ΔRH′ is the predicted value of the humidity difference of the heat supply pipeline at the next moment.

[0202] In step S1416, the leakage risk score of the heat supply pipeline at the next moment is obtained according to formula (17),

[0203] F = F TD + F TB + F RH , (17)

[0204] where F is the leakage risk score of the heat supply pipeline at the next moment, F TD is the leakage risk score of the maximum temperature difference, F TB is the leakage risk score of the average temperature, F RH is the leakage risk score of the humidity difference.

[0205] In step S142, the inspection plan is determined according to the leakage risk score. Among them, after obtaining the leakage risk score, the leakage risk can be further determined. Specifically, if the leakage risk score is less than 3 points, the leakage risk is considered to be between 0% - 25%, which is a low leakage risk; if the leakage risk score is greater than or equal to 3 points and less than 7 points, the leakage risk is considered to be between 25% - 50%, which is a medium leakage risk; if the leakage risk assessment score is greater than or equal to 7 points and less than 10 points, the leakage risk is considered to be between 50% - 75%, which is a high leakage risk; if the leakage risk score is greater than or equal to 10 points, the leakage risk is considered to be between 75% - 100%, which is an extremely high leakage risk. Further, different response plans are set for different leakage risks. Specifically, it can include:

[0206] 1. When the leakage risk is between 0% - 25%, normal robot inspection is carried out;

[0207] 2. When the leakage risk is between 25% - 50%, the inspection frequency of this area is increased separately, and a robot is sent to conduct inspection within 8 hours;

[0208] 3. When the leakage risk is between 50% - 75%, a robot is immediately sent to this area for detection. After confirming that there is a leakage in this area, personnel are immediately sent for repair;

[0209] 4. When the leakage risk is higher than 75%. Personnel are immediately sent for repair. For the areas where the leakage risk is between 50% - 100%, the inspection robot collects high-precision regional infrared images, and after data processing, it is input into the GEW-LSTM heat supply pipeline leakage classification early warning model for result correction to improve the accuracy of leakage identification.

[0210] In steps S140 to S142, first obtain the warning parameter threshold of the heating pipeline at the next moment, compare the predicted value of the warning parameter of the heating pipeline at the next moment with the warning parameter threshold, then the leakage risk score can be obtained, and finally, according to the leakage risk score, determine the inspection plan of the robot, so as to realize reliable warning diagnosis of the heating pipeline.

[0211] On the other hand, the present invention also provides a rapid positioning system for leakage of an underground heating pipe gallery. Specifically, the rapid positioning system may include a plurality of sensors and a data processing module. Specifically, the plurality of sensors are respectively used to be installed on the heating pipelines in the underground heating pipe gallery, and the data processing module is connected to the plurality of sensors and is used to execute any one of the above rapid positioning methods.

[0212] Through the above technical solutions, the rapid positioning method and positioning system for leakage of the underground heating pipe gallery provided by the present invention install and set sensors according to the density parameters of the heating pipelines, obtain the real-time data of the infrared sensors and humidity sensors, and then obtain the warning parameters of the current heating pipeline according to the real-time data, and further obtain the predicted value of the warning parameters of the heating pipeline at the next moment. Finally, according to the warning value of the warning parameters, the leakage condition of the heating pipeline is warned and diagnosed; the method of warning and diagnosing the heating pipeline by using the predicted value of the warning parameters of the heating pipeline at the next moment can effectively improve the accuracy and effect of monitoring the heating pipeline.

[0213] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0214] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0215] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0216] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0217] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0218] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0219] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0220] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising the element.

[0221] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for quickly locating leakage in an underground heating pipe gallery, characterized in that: include: Installing and setting sensors according to density parameters of heating pipes in the underground heating pipe gallery, wherein the sensors include infrared sensors and humidity sensors; Acquire real-time data of the infrared sensor and the humidity sensor; Acquire the current warning parameters of the heating pipeline according to the real-time data of the infrared sensor and the humidity sensor; Obtaining a predicted value of the warning parameter of the heating pipeline at the next moment according to the current warning parameter of the heating pipeline; Perform early warning diagnosis on the heating pipeline according to the predicted value of the early warning parameter of the heating pipeline at the next moment.

2. The rapid positioning method according to claim 1, characterized in that: Sensors installed according to the density parameters of heating pipes in underground heating corridors include: Obtain the sum of the cross-sectional areas per unit length of the heating pipelines in the current underground heating pipeline gallery, the number of pipeline connection structures, and the sum of the pipeline bending angles; According to formula (1), the total number of infrared sensors of the current underground heating corridor is obtained. Where N is the total number of infrared sensors, λ s is the pipe cross-sectional area parameter, S0 is the pipe cross-sectional area per unit length, and λ p is the pipe connection structure coefficient, P0 is the number of pipe connection structures per unit length, λ d is the pipe bending parameter, D0 is the pipe bending angle per unit length, δ is the sensor density in the warning area, and L d The total length of heating pipeline for early warning area; The infrared sensors and the humidity sensors are installed on the heating pipes in the underground heating corridor according to the total number of the infrared sensors.

3. The rapid positioning method according to claim 2, characterized in that: Obtaining the sum of the cross-sectional area per unit length of the heating pipeline in the current underground heating pipeline gallery, the number of pipeline connection structures, and the sum of the pipeline bending angles includes: Randomly segmenting the heating pipes in the current underground heating pipe gallery; According to formula (2), the sum of the unit length pipe cross-sectional areas of the heating pipes in the current underground heating pipe gallery is obtained: Among them, S k is the sum of the cross-sectional areas of the pipeline at random positions in the kth segment, n is the total number of segments of the heating pipeline, and k is an integer number; According to formula (3), the number of pipe connection structures per unit length of the heating pipe in the current underground heating pipe gallery is obtained. Among them, P k is the number of pipeline connection structures in the kth segment; According to formula (4), the sum of the bending angles per unit length of the heating pipeline in the current underground heating pipeline gallery is obtained: Among them, D k is the sum of the pipe bending angles in the kth segment.

4. The rapid positioning method according to claim 1, characterized in that: Acquiring the current warning parameters of the heating pipeline according to the real-time data of the infrared sensor and the humidity sensor includes: Acquire the real-time image collected by the infrared sensor, and evenly divide the real-time image; Acquire temperature data of each partition in the real-time image; According to formula (5), the maximum temperature difference in the real-time image is obtained: ΔT=T max -T min , (5) Wherein, ΔT is the maximum temperature difference in the real-time image, T max is the maximum temperature in the real-time image, T min is the minimum temperature value in the real-time image; According to formula (6), the average temperature of all subareas in the real-time image is obtained. Among them, T var is the average temperature of all subareas in the real-time image, T c is the temperature of the cth partition in the real-time image, m is the number of partitions of the real-time image, and c is an integer number; According to formula (7), the humidity difference of the current heating pipeline is obtained: ΔRH=RH g -RH c , (7) Among them, ΔRH is the humidity difference of the current heating pipe, RH g is the reading of the pipeline humidity sensor, RH c is the reading of the reference humidity sensor.

5. The rapid positioning method according to claim 1, characterized in that: Obtaining a predicted value of the warning parameter of the heating pipeline at the next moment according to the current warning parameter of the heating pipeline includes: Obtaining historical warning parameters of the heating pipeline; Construct a GEW-LSTM heating pipeline leakage prediction model; The GEW-LSTM heating pipeline leakage prediction model is trained using the historical warning parameters; The current warning parameters of the heating pipeline are input into the trained GEW-LSTM heating pipeline leakage prediction model to obtain the predicted value of the warning parameters of the heating pipeline at the next moment.

6. The rapid positioning method according to claim 5, characterized in that: Using the historical warning parameters to train the GEW-LSTM heating pipeline leakage prediction model includes: Normalizing the historical warning parameters of the heating pipeline and dividing them into a training set and a verification set; According to formula (8), the forget gate information in the GEW-LSTM heating pipeline leakage prediction model is obtained. f t =σ(W f ×[h t-1 ,x t ]+b f ), (8) Among them, f t is the forget gate information in the GEW-LSTM heating pipeline leakage prediction model, σ() is the sigmoid activation function, W f is the weight of the forget gate, b f is the bias of the forget gate, h t-1 is the hidden state of the previous time step, x t is the input of the current time step; According to formula (9), the input gate information in the GEW-LSTM heating pipeline leakage prediction model is obtained. i t =σ(W i ×[h t-1 ,x t ]+b i ), (9) Among them, i t Input gate information into the GEW-LSTM heating pipeline leakage prediction model, W i is the weight of the input gate, b i is the bias of the input gate; According to formula (10), the candidate unit state is obtained. in, is the candidate unit state, tanh() is the activation function, W c is the weight of the update unit, b c is the bias of the update unit; According to formula (11), the current unit state is obtained: Among them, C t is the unit state at the current moment, C t-1 is the last unit status; According to formula (12), the output gate information in the GEW-LSTM heating pipeline leakage prediction model is obtained. the t =σ(W o ×[h t-1 ,x t ]+b o ), (12) Among them, t is the output gate information in the GEW-LSTM heating pipeline leakage prediction model, W o is the weight of the output gate, b o is the bias of the output gate; According to formula (13), the output of the GEW-LSTM heating pipeline leakage prediction model is obtained. h t =o t ×tanh(C t ), (13) Among them, h t This is the output of the GEW-LSTM heating pipeline leakage prediction model.

7. The rapid positioning method according to claim 1, characterized in that: Performing early warning diagnosis on the heating pipeline according to the predicted value of the early warning parameter of the heating pipeline at the next moment includes: Obtaining the warning parameter threshold of the heating pipeline at the next moment; Obtaining a leakage risk score according to the predicted value of the warning parameter of the heating pipeline at the next moment and the warning parameter threshold; An inspection plan is determined based on the leakage risk score.

8. The rapid positioning method according to claim 7, characterized in that: Obtaining the warning parameter threshold of the heating pipeline at the next moment includes: According to formula (14), the maximum temperature difference warning threshold of the heating pipeline is obtained. Where, ΔT T is the maximum temperature difference warning threshold of the heating pipeline, is the environmental impact correction factor of the maximum temperature difference, ΔT i is the maximum temperature difference of the heating pipeline when it is operating normally at the i-th moment, S is the total number of samples when the heating pipeline is operating normally, and i is an integer number; According to formula (15), the average temperature warning threshold of the heating pipeline is obtained. in, is the average temperature warning threshold of the heating pipeline, is the environmental impact correction factor for the average temperature, is the average temperature of the heating pipeline during normal operation at the i-th moment; According to formula (16), the humidity difference warning threshold of the heating pipeline is obtained: Where ΔRH T is the humidity difference warning threshold of the heating pipeline, is the environmental impact correction factor of humidity difference, ΔRH i is the humidity difference when the heating pipeline operates normally at the i-th moment.

9. The rapid positioning method according to claim 8, characterized in that: Obtaining a leakage risk score according to the predicted value of the early warning parameter of the heating pipeline at the next moment and the threshold of the early warning parameter includes: According to the maximum temperature difference warning threshold of the heating pipeline, a first maximum temperature difference correction threshold, a second maximum temperature difference correction threshold, a third maximum temperature difference correction threshold and a fourth maximum temperature difference correction threshold are obtained; Obtain a maximum temperature difference leakage risk score according to the maximum temperature difference prediction value of the heating pipeline at the next moment and a maximum temperature difference first correction threshold, a maximum temperature difference second correction threshold, a maximum temperature difference third correction threshold, and a maximum temperature difference fourth correction threshold; According to the average temperature warning threshold of the heating pipeline, a first correction threshold of the average temperature, a second correction threshold of the average temperature, a third correction threshold of the average temperature and a fourth correction threshold of the average temperature are obtained; Obtain an average temperature leakage risk score according to the average temperature prediction value of the heating pipeline at the next moment and the average temperature first correction threshold, the average temperature second correction threshold, the average temperature third correction threshold and the average temperature fourth correction threshold; According to the humidity difference warning threshold of the heating pipe, a first humidity difference correction threshold, a second humidity difference correction threshold, a third humidity difference correction threshold and a fourth humidity difference correction threshold are obtained; Obtaining a humidity difference leakage risk score according to the humidity difference prediction value of the heating pipeline at the next moment and the first humidity difference correction threshold, the second humidity difference correction threshold, the third humidity difference correction threshold and the fourth humidity difference correction threshold; According to formula (17), the leakage risk score of the heating pipeline at the next moment is obtained. F=F TD +F TB +F RH , (17) Wherein, F is the leakage risk score of the heating pipeline at the next moment, F TD Score the maximum temperature difference leakage risk, F TB The average temperature leakage risk score, F RH The humidity differential leakage risk is scored.

10. A rapid positioning system for underground heating pipe gallery leakage, characterized in that: include: Multiple sensors are respectively used to be installed on heating pipes in the underground heating pipe gallery; A data processing module is connected to the plurality of sensors and is used to execute the rapid positioning method as described in any one of claims 1-9.

Images