Leakage detection method and device, leakage detector and readable storage medium

Abstract

The invention provides a leakage detection method and device, a leakage detector and a readable storage medium, and belongs to the field of leakage safety detection. The method comprises the following steps: performing wavelength data conversion on obtained optical fiber sensing data of a to-be-detected area to obtain initial temperature and humidity data, and preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data; recursively partitioning the sample temperature and humidity data to obtain a sample isolation tree, determining a sample isolation depth according to the sample isolation tree, and determining a sample anomaly score according to the sample isolation depth; and determining abnormal data according to the sample abnormal score and a preset abnormal score threshold, and determining a leakage area according to the abnormal data. According to the method, the isolated sample tree is constructed by collecting the temperature and humidity data, the situation of false alarm or missing alarm can be effectively reduced, anomaly analysis is carried out according to the isolation depth, and the accuracy of abnormal data detection can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of leakage safety detection, and particularly relates to a leakage detection method, device, leakage detector and readable storage medium. Background Art

[0002] As a rail transit system, the subway effectively solves the traffic congestion problem caused by the expansion of the city scale and is an important part of the development of underground space. However, in the subway construction plan, since most of the water supply pipes, sewage pipes and heating pipes are buried deep underground, the water transportation pipes inevitably intersect with the rail transit three-dimensionally. Under the long-term influence of factors such as the aging of the pipeline itself, the corrosion of the surrounding environment and the external pressure, the pipeline may crack and leak, resulting in the corrosion of steel bars, affecting the normal operation of related equipment and shortening the service life of the project.

[0003] The current leakage detection methods mainly include technologies such as photogrammetry, laser scanning and fiber optic sensing. Compared with the limitations of photogrammetry by lighting conditions and the low efficiency of laser scanning that requires generating a three-dimensional point cloud model of the tunnel, the fiber optic sensor has higher sensitivity and accuracy compared with other sensors, is particularly suitable for detecting minute changes, and at the same time has excellent anti-electromagnetic interference ability, as well as excellent characteristics such as corrosion resistance, fire resistance, water resistance and long service life, and is suitable for underground engineering leakage detection. However, most of the current leakage detection technologies using fiber optic as the sensing element use fiber optic temperature measurement technology, but the single temperature data is easily affected by the environment, and false alarms or missed alarms may occur when only collecting temperature data for detection. At the same time, the existing methods for detecting whether the sensing data is abnormal usually compare the sensing data at a certain position with the adjacent sensing data, or with the average value of the surrounding sensing data, and the accuracy of judgment is relatively low.

[0004] Therefore, there are problems in the prior art that in the fiber optic sensing leakage detection, using only temperature data for leakage detection is easily interfered by the environment, is prone to false alarms or missed alarms, and at the same time the accuracy of detecting abnormal data is relatively low, which needs to be improved. Summary of the Invention

[0005] In view of this, it is necessary to provide a leakage detection method, device, leakage detector and readable storage medium for solving the technical problems existing in the prior art that in the fiber optic sensing leakage detection, using only temperature data for leakage detection is easily interfered by the environment, is prone to false alarms or missed alarms, and at the same time the accuracy of detecting abnormal data is relatively low.

[0006] To solve the above problems, on the one hand, the present invention provides a leakage detection method, including: Converting the wavelength data of the fiber optic sensing data obtained in the area to be measured to obtain initial temperature and humidity data, and preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data; Perform recursive partitioning on the sample temperature and humidity data to obtain sample isolation trees, determine the sample isolation depth based on the sample isolation trees, and determine the sample anomaly scores based on the sample isolation depth; Determine the abnormal data based on the sample anomaly scores and the preset anomaly score threshold, and determine the leakage area based on the abnormal data.

[0007] In a possible implementation, perform wavelength data conversion on the acquired fiber optic sensing data of the area to be measured to obtain initial temperature and humidity data, including: Perform wavelength data conversion on the acquired fiber optic sensing data of the area to be measured based on the preset temperature sensitivity and preset humidity sensitivity to obtain initial temperature and humidity data.

[0008] In a possible implementation, perform preprocessing on the initial temperature and humidity data to obtain sample temperature and humidity data, including: Perform data denoising and missing value filling on the initial temperature and humidity data in sequence to obtain sample temperature and humidity data.

[0009] In a possible implementation, perform recursive partitioning on the sample temperature and humidity data to obtain sample isolation trees, including: Perform data sampling on the sample temperature and humidity data to obtain sample data to be partitioned; Randomly select partition points within the sample value range of the sample data to be partitioned to perform sample space partitioning on the sample temperature and humidity data to obtain sample subspaces; Iterate the sample space partitioning process until each sample subspace has only one sample or reaches the maximum limit depth to obtain sample isolation trees.

[0010] In a possible implementation, determine the sample isolation depth based on the sample isolation trees, including: Determine the node depths of each sample temperature and humidity data in the corresponding sample isolation trees based on the sample isolation trees; Calculate the average value based on the node depths to obtain the sample isolation depth of each sample temperature and humidity data.

[0011] In a possible implementation, determine the sample anomaly scores based on the sample isolation depth, including: Determine the sample anomaly scores based on the sample isolation depth and the preset anomaly scoring formula; Among them, the preset anomaly scoring formula is:

[0012] Among them, represents the sample anomaly score, represents the sample isolation depth, represents the average sample isolation depth.

[0013] In a possible implementation, abnormal data is determined based on the sample anomaly score and a preset anomaly score threshold, and a leakage area is determined based on the abnormal data, including: Compare the sample anomaly score with the preset anomaly score threshold, and use the sample temperature and humidity data with the sample anomaly score greater than the anomaly score threshold as abnormal data; Determine the leakage area according to the distribution position of the abnormal data.

[0014] On the other hand, the present invention provides a leakage detection device, including: A data preprocessing unit for converting the wavelength data of the fiber optic sensing data of the area to be measured obtained into initial temperature and humidity data, and preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data; An anomaly score evaluation unit for recursively partitioning the sample temperature and humidity data to obtain a sample isolation tree, determining the sample isolation depth according to the sample isolation tree, and determining the sample anomaly score according to the sample isolation depth; A leakage area positioning unit for determining abnormal data according to the sample anomaly score and a preset anomaly score threshold, and determining the leakage area according to the abnormal data.

[0015] On the other hand, the present invention provides a leakage detector, including a processor, a memory, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned leakage detection method is implemented.

[0016] On the other hand, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned leakage detection method is implemented. The beneficial effects of the present invention are as follows: In the leakage detection method provided by the present invention, first, the wavelength data of the fiber optic sensing data of the area to be measured obtained is converted into initial temperature and humidity data, and the initial temperature and humidity data is preprocessed to obtain sample temperature and humidity data; then, the sample temperature and humidity data is recursively partitioned to obtain a sample isolation tree, the sample isolation depth is determined according to the sample isolation tree, and the sample anomaly score is determined according to the sample isolation depth; finally, abnormal data is determined according to the sample anomaly score and a preset anomaly score threshold, and the leakage area is determined according to the abnormal data. The present invention can effectively reduce false alarms or missed alarms by collecting temperature and humidity data to construct an isolated sample tree, and can effectively improve the accuracy of detecting abnormal data by performing anomaly analysis according to the isolation depth. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of an embodiment of the leakage detection method provided by the present invention; Figure 2 It is a schematic flowchart of constructing a sample isolation tree in an embodiment of the present invention; Figure 3 It is a schematic flowchart of determining the isolation depth of a sample in an embodiment of the present invention; Figure 4 It is a schematic flowchart of determining leakage in an embodiment of the present invention; Figure 5 It is a schematic structural diagram of an embodiment of the leakage detection device provided by the present invention; Figure 6 It is a schematic structural diagram of an embodiment of the leakage detector provided by the present invention. Detailed implementation manners

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The descriptions such as "first" and "second" involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0022] References to "embodiments" in this specification mean that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0023] The present invention provides a leakage detection method, device, leakage detector, and readable storage medium, which will be described separately below.

[0024] It should be noted that the leakage detection method provided in this embodiment can be applied to leakage detection systems for various types of pipelines such as water supply pipelines, sewage pipelines, heating pipelines, or drainage pipelines, and can also be applied to leakage detection systems in various scenarios such as dams, reservoirs, water storage tanks, or irrigation flumes. The leakage detection system can be a combination of a temperature and humidity sensing fiber grating and a software system running on a terminal device. The temperature and humidity sensing fiber grating is used to obtain sensing data of the area to be measured, and the terminal device can be a terminal device such as a server, a tablet computer, a laptop computer, a personal computer, a personal digital assistant, or a mobile phone. The specific type of the terminal device is not limited in the embodiments of this application.

[0025] Figure 1 is a schematic flowchart of an embodiment of the leakage detection method provided by the present invention. As Figure 1 shown, the leakage detection method includes: S101. Perform wavelength data conversion on the obtained fiber sensing data of the area to be measured to obtain initial temperature and humidity data, and perform preprocessing on the initial temperature and humidity data to obtain sample temperature and humidity data; S102. Perform recursive partitioning on the sample temperature and humidity data to obtain a sample isolation tree, determine the sample isolation depth according to the sample isolation tree, and determine the sample anomaly score according to the sample isolation depth; S103. Determine abnormal data according to the sample anomaly score and a preset anomaly score threshold, and determine the leakage area according to the abnormal data.

[0026] Among them, step S101 is specifically as follows: Based on a temperature-sensitive fiber sensing array and a temperature and humidity-sensitive fiber sensing array, respectively collect the initial sensing data of the area to be measured affected by temperature and temperature and humidity. After demodulating the initial sensing data based on a demodulator, obtain the fiber sensing data, and perform wavelength data conversion and preprocessing on the obtained fiber sensing data to obtain sample temperature and humidity data.

[0027] Compared with the prior art, the leakage detection method provided by the embodiment of the present invention first performs wavelength data conversion on the obtained fiber optic sensing data of the area to be measured to obtain initial temperature and humidity data, and preprocesses the initial temperature and humidity data to obtain sample temperature and humidity data; then recursively partitions the sample temperature and humidity data to obtain a sample isolation tree, determines the sample isolation depth according to the sample isolation tree, and determines the sample anomaly score according to the sample isolation depth; finally, determines the abnormal data according to the sample anomaly score and a preset anomaly score threshold, and determines the leakage area according to the abnormal data. The present invention can effectively reduce false alarms or missed alarms by collecting temperature and humidity data to construct an isolation sample tree, and can effectively improve the accuracy of detecting abnormal data by performing anomaly analysis based on the isolation depth.

[0028] In some embodiments of the present invention, performing wavelength data conversion on the obtained fiber optic sensing data of the area to be measured to obtain initial temperature and humidity data includes: Performing wavelength data conversion on the obtained fiber optic sensing data of the area to be measured based on a preset temperature sensitivity and a preset humidity sensitivity to obtain initial temperature and humidity data.

[0029] Specifically, in the embodiment, the temperature and humidity changes of the pipeline are sensed by a fiber optic sensor. The fiber optic sensor can be continuously wound along the axial direction of the pipeline and arranged back and forth along the axial direction of the pipeline, or more arrangement methods can be adopted to divide the pipeline surface into several detection areas. The obtained fiber optic sensing data of the area to be measured includes temperature grating wavelength data and humidity grating wavelength data. The initial temperature and humidity data are calculated through the preset humidity sensitivity of the humidity grating and the temperature sensitivity of the temperature and humidity grating. The calculation formula is as follows:

[0030]

[0031] Wherein, is the measured temperature, is the measured humidity, is the temperature sensitivity of the temperature grating, is the temperature sensitivity of the humidity grating, is the humidity sensitivity of the humidity grating, is the wavelength of the current measured temperature grating, is the wavelength of the temperature grating corresponding to the temperature value of when, is the wavelength of the current measured humidity grating, is the wavelength of the humidity grating corresponding to the humidity value of when, is the constant bias term set when calculating the temperature, The constant bias term set for calculating humidity. The above formula calculates the temperature measurement value by measuring the wavelength of the temperature grating, and on this basis, combines the wavelength of the humidity grating to calculate the humidity measurement value.

[0032] In some embodiments of the present invention, preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data, including: Performing data denoising and missing value filling on the initial temperature and humidity data in sequence to obtain sample temperature and humidity data.

[0033] Specifically, after converting the original wavelength data into initial temperature and humidity data, considering that there are some noises and missing values in the data, preprocessing is required to ensure the accuracy and stability of the data. Among them, data denoising can but is not limited to using smoothing methods, filtering methods or outlier detection methods, and missing values can be filled using interpolation methods or the average value of surrounding data to ensure subsequent feature extraction and anomaly detection.

[0034] In some embodiments of the present invention, Figure 2 It is a schematic flow chart for constructing a sample isolation tree according to an embodiment of the present invention, as Figure 2 shown, performing recursive partitioning on the sample temperature and humidity data to obtain a sample isolation tree, including: S201. Randomly select a splitting point within the sample value range of the sample temperature and humidity data to perform sample space partitioning on the sample temperature and humidity data to obtain sample subspaces; S202. Iterate the sample space partitioning process until each sample subspace has only one sample or reaches the maximum limit depth to obtain a sample isolation tree.

[0035] Specifically, in order to improve the accuracy of detecting abnormal data, the embodiment performs anomaly scoring by constructing an isolation tree and using the isolation depth of the sample in the isolation tree. The isolation tree is a binary tree structure based on recursive partitioning, where each leaf node represents a data sample. To construct an isolation tree, N data samples are sampled from the collected sample temperature and humidity data set and placed in the root node. Among them, the data in the data set is not a single one-dimensional data, but has characteristics of multiple dimensions such as temperature and humidity. For a certain dimension attribute and the selected splitting point , where the attribute the maximum value and the minimum value are taken as and respectively, then the randomly selected splitting point satisfies .

[0036] Then the embodiment divides the data into two parts according to the size relationship between the value of the attribute and the splitting point to form a single isolation tree. Among them, the sample attribute The data is partitioned into the left child node of the root node, and the sample attributes of the data are partitioned into the right child node of the root node.

[0037] By repeating the above steps, the space formed by the left and right child nodes of the root node is partitioned respectively until there is only one sample in the child node that cannot be further partitioned or the isolation tree has reached the limit depth , and the isolation forest is formed by repeating sampling and partitioning the samples in different dimensions to form isolation trees.

[0038] In some embodiments of the present invention, Figure 3 is a schematic flow chart for determining the isolation depth of samples in an embodiment of the present invention. As Figure 3 shown, determining the isolation depth of samples according to the sample isolation tree includes: S301. Determine the node depth of each sample's temperature and humidity data in the corresponding sample isolation tree according to the sample isolation tree; S302. Calculate the average value based on the node depth to obtain the isolation depth of each sample's temperature and humidity data.

[0039] Specifically, the isolation forest consists of m sample isolation trees . Let represent the sample of the temperature and humidity data to be measured at the node depth of the isolation tree . The node depth is determined by the path length from the root node to the sample node. The same data has different path lengths in different isolation trees. The isolation depth is the average path length of the same data on different isolation trees in the isolation forest , and its calculation method formula is expressed as:

[0040] In some embodiments of the present invention, determining the sample anomaly score according to the sample isolation depth includes: Determine the sample anomaly score according to the sample isolation depth and a preset anomaly scoring formula; wherein, the preset anomaly scoring formula is:

[0041] wherein, represents the sample anomaly score, represents the sample isolation depth, represents the average sample isolation depth.

[0042] Specifically, the embodiment evaluates the sample anomaly score according to the isolation depth of each sample and the average isolation depth of the samples. The formula for calculating the average isolation depth is:

[0043] in, , is Euler's constant, and its value is 0.5772156649.

[0044] In some embodiments of the present invention, Figure 4 FIG. 1 is a schematic diagram of a flow chart of determining leakage according to an embodiment of the present invention, as shown in FIG. Figure 4 As shown, abnormal data is determined according to the sample abnormality score and the preset abnormality score threshold, and the leakage area is determined according to the abnormal data, including: S401, comparing the sample anomaly score with a preset anomaly score threshold, and treating the sample temperature and humidity data whose sample anomaly score is greater than the anomaly score threshold as abnormal data; S402: Determine the leakage area according to the distribution position of the abnormal data.

[0045] Specifically, when the isolation depth of the sample is smaller, the anomaly score is higher, and the anomaly is more likely to exist. When , the anomaly score approaches 0.5, and there is no obvious outlier at this time. Therefore, the threshold of the anomaly score in the embodiment is set to 0.5. When the temperature and humidity data is judged to be abnormal data, When , the temperature and humidity data are judged to be normal data. Finally, according to the distribution position of the abnormal data, if there is abnormal data on each edge of a certain detection area, then the area is judged to be a leakage area.

[0046] In summary, in order to avoid false alarms or missed alarms and improve detection accuracy, the present invention first performs wavelength data conversion on the acquired optical fiber sensing data of the area to be tested to obtain initial temperature and humidity data, and pre-processes the initial temperature and humidity data to obtain sample temperature and humidity data; then recursively partitions the sample temperature and humidity data to obtain a sample isolation tree, determines the sample isolation depth according to the sample isolation tree, and determines the sample anomaly score according to the sample isolation depth; finally, determines the abnormal data according to the sample anomaly score and a preset anomaly score threshold, and determines the leakage area according to the abnormal data. The present invention constructs an isolated sample tree by collecting temperature and humidity data, which can effectively reduce false alarms or missed alarms, and performs anomaly analysis according to the isolation depth, which can effectively improve the accuracy of detecting abnormal data.

[0047] In order to better implement the leakage detection method in the embodiment of the present invention, based on the leakage detection method, correspondingly, Figure 5 As shown, the present invention also provides a leakage detection device, the leakage detection device 500 comprises: The data preprocessing unit 501 is used to convert the acquired optical fiber sensing data of the test area into wavelength data to obtain initial temperature and humidity data, and preprocess the initial temperature and humidity data to obtain sample temperature and humidity data; Anomaly score evaluation unit 502 is configured to perform recursive partitioning on the sample temperature and humidity data to obtain sample isolation trees, determine the sample isolation depth according to the sample isolation trees, and determine the sample anomaly score according to the sample isolation depth; Leakage area positioning unit 503 is configured to determine abnormal data according to the sample anomaly score and a preset anomaly score threshold, and determine the leakage area according to the abnormal data.

[0048] The leakage detection device 500 provided in the above embodiments can implement the technical solutions described in the above leakage detection method embodiments. The specific implementation principles of the above modules or units can be referred to the corresponding content in the above leakage detection method embodiments, and will not be elaborated here.

[0049] As Figure 6 shown, the present invention also correspondingly provides a leakage detector 600, which includes a sensor 601, a processor 602, a memory 603, and a display 604. Figure 6 Only some components of the leakage detector 600 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0050] In some embodiments, the sensor 601 can be an optical fiber sensing array disposed on the area to be measured and sensitive to temperature and / or temperature and humidity, configured to collect optical fiber sensing data and send it to the processor 602 and the memory 603, and store the collected optical fiber sensing data and the data processed by the processor 602 in the memory 603.

[0051] In some embodiments, the processor 602 can be a central processing unit (CPU), a microprocessor, or other data processing chips, configured to run the program code stored in the memory 603 or process data, such as implementing the leakage detection program of the leakage detection method in the present invention.

[0052] In some embodiments, the memory 603 can be an internal storage unit of the leakage detector 600, such as the hard disk or memory of the leakage detector 600. In some other embodiments, the memory 603 can also be an external storage device of the leakage detector 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the leakage detector 600.

[0053] The display 604 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. in some embodiments. The display 604 is used to display information of the leak detector 600 and to display a visual user interface. The display 604 can also include a sound module or a vibration module in some embodiments. When the processor 602 detects a leak area, it transmits an alarm control signal to the display 604. After receiving the alarm control signal, the display 604 emits an alarm signal through, but not limited to, sound, light, and vibration. The components 601-604 of the leak detector 600 communicate with each other through the system bus.

[0054] In one embodiment, when the processor 602 executes the leak detection program in the memory 603, the following steps can be implemented: Perform wavelength data conversion on the obtained fiber optic sensing data of the area to be measured to obtain initial temperature and humidity data, and perform preprocessing on the initial temperature and humidity data to obtain sample temperature and humidity data; Perform recursive partitioning on the sample temperature and humidity data to obtain a sample isolation tree, determine the sample isolation depth according to the sample isolation tree, and determine the sample anomaly score according to the sample isolation depth; Determine the abnormal data according to the sample anomaly score and the preset anomaly score threshold, and determine the leak area according to the abnormal data.

[0055] It should be understood that when the processor 602 executes the leak detection program in the memory 603, in addition to the above functions, other functions can also be implemented. For specific details, please refer to the description of the corresponding method embodiments above.

[0056] Correspondingly, an embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the leak detection methods provided by the above method embodiments can be implemented.

[0057] Those skilled in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0058] The above has introduced in detail the leakage detection method, device, leakage detector and storage medium provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A leakage detection method, characterized in that: include: Performing wavelength data conversion on the acquired optical fiber sensing data of the area to be tested to obtain initial temperature and humidity data, and preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data; Recursively partitioning the sample temperature and humidity data to obtain a sample isolation tree, determining a sample isolation depth according to the sample isolation tree, and determining a sample anomaly score according to the sample isolation depth; Abnormal data is determined according to the sample abnormality score and a preset abnormality score threshold, and a leakage area is determined according to the abnormal data.

2. The leakage detection method according to claim 1, characterized in that: The step of converting the acquired optical fiber sensing data of the area to be measured into initial temperature and humidity data by performing wavelength data conversion includes: Based on the preset temperature sensitivity and the preset humidity sensitivity, the acquired optical fiber sensing data of the area to be measured is converted into wavelength data to obtain initial temperature and humidity data.

3. The leakage detection method according to claim 1, characterized in that: The preprocessing of the initial temperature and humidity data to obtain sample temperature and humidity data includes: The initial temperature and humidity data are subjected to data denoising and missing value filling in sequence to obtain sample temperature and humidity data.

4. The leakage detection method according to claim 1, characterized in that: The recursive partitioning of the sample temperature and humidity data to obtain a sample isolation tree includes: Sampling the sample temperature and humidity data to obtain sample data to be partitioned; Randomly select a partition point within the sample value range of the sample data to be partitioned to perform sample space partitioning on the sample temperature and humidity data to obtain a sample subspace; The sample space partitioning process is iterated until each of the sample subspaces has only one sample or the maximum limit depth is reached to obtain a sample isolation tree.

5. The leakage detection method according to claim 1, characterized in that: The determining the sample isolation depth according to the sample isolation tree comprises: Determine the node depth of each sample temperature and humidity data in the corresponding sample isolation tree according to the sample isolation tree; The sample isolation depth of each sample temperature and humidity data is obtained by calculating the average value according to the node depth.

6. The leakage detection method according to claim 1, characterized in that: The determining of the sample anomaly score according to the sample isolation depth comprises: Determining a sample anomaly score according to the sample isolation depth and a preset anomaly scoring formula; Among them, the preset abnormality scoring formula is: in, represents the sample anomaly score, represents the sample isolation depth, Represents the average sample isolation depth.

7. The leakage detection method according to claim 1, characterized in that: The determining of abnormal data according to the sample abnormality score and a preset abnormality score threshold, and determining a leakage area according to the abnormal data includes: Compare the sample anomaly score with a preset anomaly score threshold, and take the sample temperature and humidity data whose sample anomaly score is greater than the anomaly score threshold as abnormal data; The leakage area is determined according to the distribution position of the abnormal data.

8. A leakage detection device, characterized in that: include: A data preprocessing unit, used for performing wavelength data conversion on the acquired optical fiber sensing data of the area to be measured to obtain initial temperature and humidity data, and preprocessing the initial temperature and humidity data to obtain sample temperature and humidity data; an anomaly score scoring unit, used for recursively partitioning the sample temperature and humidity data to obtain a sample isolation tree, determining a sample isolation depth according to the sample isolation tree, and determining a sample anomaly score according to the sample isolation depth; The leakage area positioning unit is used to determine abnormal data according to the sample abnormality score and a preset abnormality score threshold, and determine the leakage area according to the abnormal data.

9. A leakage detector, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the leakage detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the leakage detection method according to any one of claims 1 to 7 is implemented.

Images