A water curtain leakage detection device and method

Abstract

The application relates to the technical field of curtain leakage detection, in particular to a water conservancy curtain leakage detection device and a detection method, which comprises the following steps: acquiring the electric field intensity value of a receiving coil at different heights in a water conservancy curtain leakage detection process at each detection time; analyzing the distribution fluctuation degree of the electric field intensity value of the receiving coil at any height at each detection time, and the difference degree of the response time and the pulse emission time of the electric field intensity change, so as to obtain the first characteristic value of the waveform anomaly and the response delay of the electric field intensity value of the any height position at each detection time; combining the random change characteristics of the electric field intensity value of each height position, obtaining the significant coefficient of the response difference and the disorder characteristics of the electric field intensity at each detection time, and then calculating the leakage severity coefficient of each detection, which is used for leakage detection of the water conservancy curtain at the current detection time. The application can improve the curtain leakage detection precision.

Description

Technical Field

[0001] This application relates to the field of curtain wall leakage detection technology, specifically to a hydraulic curtain wall leakage detection device and detection method. Background Technology

[0002] To prevent safety accidents, leakage detection of the cutoff wall is necessary before excavation. Currently, the main detection methods used in engineering projects include ground-penetrating radar (GPR), isotope tracing, and transient electromagnetic methods. GPR has high system complexity and component costs; the center frequency of the GPR antenna is limited by the interplay between resolution and detection depth. Isotope tracing requires radioactive isotope labeling of groundwater, which can easily cause environmental pollution, thus limiting its use. Transient electromagnetic methods are easy to operate and provide rapid detection, showing broad application prospects. However, actual detection may be affected by random electromagnetic interference and metallic objects, making it difficult to accurately extract leakage characteristics from the electric field response signal. Furthermore, changes in device parameters and the electrical properties of the geological body itself can also affect the detection results, leading to deficiencies in the real-time performance and accuracy of cutoff wall leakage detection.

[0003] Existing rapid analysis methods for curtain wall leakage detection involve generating a transient electromagnetic field by placing polarized electrodes in the launch well, and collecting the response signal using an array of symmetrically distributed non-polarized electrodes. The leakage status of the curtain wall in the foundation pit is determined by superimposing the positive and negative data received above and below the polarized electrodes. However, the collected data may be affected by environmental noise or geological interference, which can influence the detection results. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a device and method for detecting leakage in hydraulic curtain walls. The specific technical solution adopted is as follows: This application provides a method for detecting leakage in hydraulic curtain walls, including the following steps: To obtain the electric field strength values ​​of the receiving coil at different heights during each detection process in the hydraulic curtain leakage detection process; The distribution fluctuation of the electric field strength value of the receiving coil at any height position during each detection is analyzed, as well as the difference between the response time of the electric field strength change and the pulse transmission time during each detection, in order to obtain the first characteristic value of the waveform anomaly and response delay of the electric field strength value at any height position during each detection. By utilizing the discrete fluctuation characteristics between the first feature values ​​corresponding to all height positions during each detection, and combining them with the random variation characteristics of the electric field intensity values ​​at each height position, the significance coefficients of the differences and disorder characteristics of the electric field intensity response during each detection are obtained. Then, by observing the changing trend of the significance coefficients, the leakage severity coefficient for each detection is obtained. Based on the aforementioned leakage severity coefficient, leakage detection is performed on the hydraulic curtain during the current testing period.

[0005] Preferably, for the electric field intensity value at any height position during the i-th detection, all peak points and valley points are extracted, and a window is constructed with each peak point and valley point as the center. The bottom width of the peak and the bottom width of the valley are calculated respectively, and the data in the electric field intensity data that are outside the corresponding intervals of these two types of bottom widths are used as baseline data.

[0006] Preferably, before obtaining the first feature value, the ratio of the absolute value of the data corresponding to each peak point and valley point to the mean of all baseline data is calculated, and the mean of all ratios is used as the value of the fluctuation difference of the electric field intensity at any height position during the i-th detection.

[0007] Preferably, before obtaining the first feature value, the absolute value of the difference between the peak point and the turn-on time, and the absolute value of the difference between the valley point and the turn-off time are calculated respectively. The sum of all absolute values ​​and the ratio of the preset detection time are used as the response delay coefficient of the i-th detection for any height position.

[0008] Preferably, the waveform anomaly of the electric field strength value at any height position during the i-th detection and the first characteristic value of the response delay are... The corresponding calculation formula is: In the formula, The value represents the degree of fluctuation difference in electric field intensity at any given height position during the i-th detection. Let be the response delay coefficient for any given height position in the i-th detection. It is the normalized result of the mean of the kurtosis of the electric field intensity value in each window at any height position during the i-th detection.

[0009] Preferably, before obtaining the significance coefficient, the first-order difference absolute value sequence of the electric field intensity value at each height position is calculated for each detection, and the coefficient of variation of each first-order difference absolute value sequence is calculated. The mean of the coefficients of variation at all heights at each detection is used as the disorder value of the electric field intensity response at each detection.

[0010] Preferably, the formula for calculating the significance coefficient between the difference in electric field intensity response and the disorder characteristics at each detection is as follows: In the formula, denoted as the significance coefficient of the difference in electric field intensity response and disorder characteristics at the i-th detection. Let be the standard deviation of the first feature value corresponding to all height positions at the i-th detection. denoted as the disorder value of the electric field intensity response during the i-th detection.

[0011] Preferably, the process of obtaining the leakage severity coefficient for each detection is as follows: the significance coefficients corresponding to the current detection and the previous N detections are used as inputs to the verification algorithm, the slope estimate is output, and this estimate is used as the leakage severity coefficient for the current detection.

[0012] Preferably, if the leakage severity coefficient obtained from the current detection is greater than or equal to the detection threshold, then there is leakage in the hydraulic curtain; otherwise, there is no leakage.

[0013] This application also provides a hydraulic curtain leakage detection device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described hydraulic curtain leakage detection methods.

[0014] As can be seen from the above, the hydraulic curtain leakage detection device and method provided in this application have at least the following beneficial effects: Considering the influence of random electromagnetic interference, traditional processing methods are difficult to accurately extract the leakage characteristics of the electric field response signal. Therefore, this application deeply analyzes the waveform anomalies and response delay characteristics of the corresponding electric field strength values ​​at different detection locations, and further considers the spatial distribution differences and disorder of the electric field strength response anomalies under the influence of multi-point leakage. Its advantage is that it can reduce the influence of random electromagnetic interference and obtain more accurate curtain leakage characteristics. This application combines predictive analytics to accurately assess the severity of leakage, which helps to compensate for the deficiencies in the real-time performance and accuracy of curtain wall leakage detection. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating the steps of a method for detecting leakage in a hydraulic curtain wall, as provided in this application. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a hydraulic curtain leakage detection device and method proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise specified and limited, terms such as “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes said element. Furthermore, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the hydraulic curtain leakage detection device and detection method provided in this application.

[0020] Please see Figure 1 The diagram illustrates a flowchart of a method for detecting leakage in a hydraulic curtain wall according to an embodiment of this application, including the following steps: S1: Obtain the electric field strength value of the receiving coil at different heights during each test in the process of detecting leakage in the hydraulic curtain.

[0021] Transient electromagnetic method is a detection method based on the principle of electromagnetic induction. It uses a pulsed current field source to excite the ground, and the instant of its switching off and on creates a vortex alternating electromagnetic field. By measuring and analyzing the changing characteristics of this electromagnetic field, the location and extent of leakage in underground foundation structures can be indirectly detected.

[0022] In this embodiment, vertical shafts are respectively set on both sides of the water-stop curtain, with the two shafts located on the same normal line to the curtain and equidistant from it. A transmitting coil is installed at the center height of one shaft, and receiving coils are arranged at equal intervals at multiple heights in the other shaft. The function of the transmitting coil is to emit pulse current, generating a rapidly changing magnetic field at the moment of activation and deactivation. This application sets the detection time to 10ms, and conduction only occurs between 4-7ms. Therefore, there are two transient change moments in the entire process, 4ms and 7ms, which trigger two transient responses, with 4ms being the activation moment and 7ms being the deactivation moment. Then, the response change of electric field intensity is collected by the receiving coil. The sampling frequency is set to 20kHz, and the electric field intensity value of each receiving coil at each detection is obtained. The electric field intensity value represents the electric field intensity at the sampling time. In order to avoid the problem of inconsistent dimensions, the electric field intensity value is normalized by using the global maximum and global minimum values ​​under the historical no-leakage state. The normalization range is [0,1]. The normalization method is the maximum-minimum method. It should be noted that the relevant calculations in this embodiment are all raw physical quantities, without physical units, and are intended for use in practical application scenarios. Implementers can use other existing normalization methods for normalization processing. This embodiment does not restrict this.

[0023] S2: Analyze the distribution fluctuation of the electric field strength value of the receiving coil at any height position during each detection, and the difference between the response time of the electric field strength change and the pulse transmission time during each detection, so as to obtain the first characteristic value of the waveform anomaly and response delay of the electric field strength value at any height position during each detection.

[0024] This embodiment analyzes the transient electromagnetic field excited by coils near the water-stop curtain, especially the response changes during the instantaneous switching on and off of the coils, to determine whether a curtain leakage fault has occurred. However, during actual testing, random electromagnetic interference may occur, altering the signal curve shape or even causing disorder, affecting the accuracy of the test results. The following measures are taken to address this issue.

[0025] First, the water-stop curtain itself is usually made of low-permeability materials such as concrete or clay, which have relatively high resistivity. Once a leakage channel appears, groundwater will fill it, forming a local low-resistivity anomaly in the leakage area. According to the principle of electromagnetic induction, under the excitation of a transient electromagnetic field, the low-resistivity region will induce stronger eddy currents, thus manifesting as an abnormal response in the received signal. Taking the electric field strength value collected by the receiving coil at any height as an example, when the curtain is intact, the change characteristic of the electric field strength value is as follows: it rises rapidly and then falls rapidly near the conduction moment, then tends to level off, and there is a peak near the conduction moment, corresponding to the maximum value of the electric field strength value; then near the turn-off moment, the amplitude first falls rapidly and then rises rapidly, then tends to level off again, and there is a trough near the turn-off moment, corresponding to the minimum value of the electric field strength value. At the same time, the curves of the peak and trough are relatively sharp. When curtain leakage occurs, the transient electromagnetic response distribution of the medium near the leakage location will become abnormal due to the decrease in geological resistivity. This will cause the fluctuation amplitude at the two transient response moments to increase significantly, and the distribution width of the peaks and troughs will increase while the sharpness will decrease.

[0026] Therefore, for the electric field intensity value collected at any height position during the i-th detection, all peaks and valleys are extracted to obtain all peak points and valley points. According to the above analysis, the peak points are located near the turn-on time, and the valley points are located near the turn-off time. Then, with each peak point and valley point as the center, k sampling points are extended forward and backward (k is set to 10 in this embodiment) to construct a window, and the kurtosis of the data within each window is calculated. The normalized result of the mean kurtosis of the electric field intensity value within each window at any height position during the i-th detection is denoted as... In this embodiment, the mean value of the peak electric field intensity values ​​within each window is normalized using the maximum value normalization method. In practical applications, other existing normalization methods can also be used. This embodiment does not impose any special restrictions on this. The smaller the kurtosis, the lower the sharpness of the electric field intensity change. Then, the peak width and trough width are calculated separately. Data in the electric field intensity data that fall outside the corresponding intervals of these two types of widths are considered as baseline data. It should be noted that, taking the peak point or trough point as the center, peaks are searched on both sides until the amplitude decreases or rises to 10% of the corresponding extreme value. This interval is counted as the width. During multiple detections, the electric field intensity baseline position is relatively stable, and the data at each point on the baseline is greater than 0. For all the peak and valley points extracted above, the ratio of the absolute value of the data corresponding to each peak point to the mean of all baseline data, and the ratio of the absolute value of the data corresponding to each valley point to the mean of all baseline data are calculated respectively. The mean of all calculated ratios is taken as the fluctuation difference value. The fluctuation difference value of the electric field intensity at any height position during the i-th detection is denoted as... The result The larger the value, the greater the fluctuation range of the electric field response amplitude. It should be noted that, in this embodiment, to avoid the denominator being zero during the ratio calculation, a very small positive number can be added to the denominator to avoid it being zero. In this embodiment, the value is 0.0001.

[0027] Furthermore, after leakage occurs in the water-stop curtain, the equivalent conductivity of the wall increases, and the response time of the receiving coil to the pulse changes accordingly under different conductivity levels. Specifically, the higher the conductivity, the higher the response time delay. Therefore, the absolute values ​​of the differences between the peak time and the conduction time, and the absolute values ​​of the differences between the valley time and the turn-off time are calculated. These absolute values ​​are typically no greater than 0.1. The sum of all absolute values ​​is then calculated as the ratio of the detection duration of 10 ms to the response delay coefficient. For the electric field intensity value collected at any height position during the i-th detection, the absolute values ​​of the differences between the peak time and the conduction time, and the absolute values ​​of the differences between the valley time and the turn-off time are calculated. The sum of all absolute values ​​is then calculated, and the ratio of this sum to the detection duration of 10 ms is used as the response delay coefficient for the i-th detection at any height position. This response delay coefficient for the i-th detection at any height position is denoted as... In the calculation of the response delay coefficient, dividing by the detection duration of 10ms aims to eliminate dimensions and normalize the result to the interval [0,1]. Implementers can also use other existing normalization methods; this embodiment does not impose any restrictions. The larger the value, the more significant the difference between the response time and the pulse emission time under that detection.

[0028] Therefore, the first characteristic value of the waveform anomaly and response delay of the electric field intensity value at any height position during the i-th detection is calculated. In this embodiment, the calculation formula is as follows: In the formula, The first characteristic value of the waveform anomaly and response delay of the electric field intensity value at any given height position during the i-th detection is given. The value represents the degree of fluctuation difference in electric field intensity at any given height position during the i-th detection. Let be the response delay coefficient for any given height position in the i-th detection. This is the normalized result of the mean kurtosis of the electric field intensity values ​​within each window at any given height position during the i-th detection. It should be noted that adding a very small positive number 0.001 to the denominator is to prevent the denominator from being zero, thus avoiding calculation errors caused by a zero denominator.

[0029] Among them, the results The larger the value, the more significant the waveform anomalies and response delay characteristics of the electric field intensity value collected at any height position during the i-th detection process. In the above formula, it can be understood that... This reflects the degree of abnormal increase in the amplitude of signal fluctuations, parameters The sharpness of the wave crests and troughs was quantified, and their ratio reflected the waveform anomalies of the electric field intensity value. Parameters This quantifies the response delay characteristics under the influence of conductivity changes. This allows for a precise evaluation of the electric field response changes detected at various locations.

[0030] S3: By utilizing the discrete fluctuation characteristics between the first feature values ​​corresponding to all height positions during each detection, and combining them with the random variation characteristics of the electric field strength values ​​at each height position, the significance coefficients of the electric field strength response differences and disorder characteristics during each detection are obtained. Then, by observing the changing trend of the significance coefficients, the leakage severity coefficient for each detection is obtained.

[0031] Furthermore, the presence of multiple leakage points in the watertight curtain leads to a more complex response characteristic of the electric field intensity compared to the case of a single leakage point. Each leakage point forms a local low resistivity anomaly and generates an independent eddy current anomaly response under transient electromagnetic field excitation. These anomaly sources cause the induced electric field signals generated at different locations of the receiving coils in space to interfere with each other, thereby exacerbating the differences and disorder in the electric field intensity response.

[0032] Therefore, considering that actual detection may be affected by environmental electromagnetic interference, directly comparing the differences in electric field strength data is easily influenced by random outliers. However, by analyzing the differences in anomalous characteristics at different detection locations under leakage conditions, the electric field strength difference characteristics affected by multi-point leakage in the curtain can be more accurately assessed. Therefore, the standard deviation of the first characteristic value corresponding to all height positions at the i-th detection time is calculated and denoted as... The result The larger the value, the more significant the spatial distribution of the electric field intensity response anomaly during the detection. Then, the first-order difference absolute value sequence of the electric field intensity values ​​at each height position during the i-th detection is calculated, and the coefficient of variation for each first-order difference absolute value sequence is calculated. The mean of the coefficients of variation at all heights during the i-th detection is taken as the disorder value of the electric field intensity response during the i-th detection, denoted as . The coefficient of variation is the ratio of the standard deviation to the mean of the data within the first-order difference absolute value sequence. The calculation of the standard deviation and mean of the data within the first-order difference absolute value sequence is existing technology and will not be elaborated upon in this embodiment. The larger the value, the more pronounced the disordered variation of the electric field strength. It should be noted that, to avoid the denominator being zero and thus uncalculateable during the calculation of the coefficient of variation, a very small positive number is added to the denominator in this embodiment to prevent it from being zero; in this embodiment, the value is 0.0001.

[0033] Therefore, the significance coefficients of the difference in electric field intensity response and disorder characteristics at the i-th detection are calculated using the following formula: In the formula, denoted as the significance coefficient of the difference in electric field intensity response and disorder characteristics at the i-th detection. Let be the standard deviation of the first feature value corresponding to all height positions at the i-th detection. denoted as the disorder value of the electric field intensity response during the i-th detection.

[0034] Among them, the results This reflects the differences and disorder characteristics in the electric field intensity response under the i-th detection. It is understandable that the parameters... The spatial distribution of electric field response differences under leakage conditions was evaluated. For example, some detection locations close to the leakage point exhibited more pronounced anomalous characteristics in their electric field response, while others farther from the leakage point showed relatively weaker anomalous characteristics, reflecting the differences in anomalous response under multi-point leakage. The absolute value of the first-order difference reflects the severity of the abrupt change in electric field response between adjacent time points. The parameters... This reflects the disordered characteristics of the electric field intensity value under leakage conditions. This is used to comprehensively characterize the spatial heterogeneity and dynamic complexity of the leakage effect.

[0035] Furthermore, as the leakage of the water-stop curtain becomes more severe, the size and number of leakage points gradually increase, and the equivalent electrical conductivity of the curtain wall becomes increasingly higher. This leads to a rapid increase in the significance coefficient. Therefore, in this embodiment, Sen's Slope test algorithm is used to calculate the trend characteristics of the significance coefficient corresponding to the current detection and its N previous detection processes. The output of this algorithm is a slope estimate, which serves as the leakage severity coefficient for the current detection. The larger the leakage severity coefficient, the more severe the leakage state of the water-stop curtain at the corresponding height position. The value of N can range from 7 to 15; in this embodiment, it is set to 10.

[0036] S4: Based on the leakage severity coefficient, perform leakage detection on the hydraulic curtain during the current detection.

[0037] Therefore, based on the above process in this embodiment, by deeply analyzing the waveform anomalies and response delay characteristics of the electric field intensity values ​​at different heights, and further considering the spatial distribution differences and disorder of the electric field intensity response anomalies under the influence of multi-point leakage, and by using predictive analysis to accurately assess the severity of leakage, it is helpful to promptly detect the leakage risk of the water-stop curtain. Based on this, leakage detection of the hydraulic curtain will be further carried out.

[0038] Preferably, in this embodiment, historical data from 100 tests conducted under non-leakage conditions of the hydraulic curtain are selected. The leakage severity coefficient corresponding to each test under non-leakage conditions is calculated using the steps described above. The mean and standard deviation of all leakage severity coefficients under non-leakage conditions are then calculated. The sum of the mean and three times the standard deviation is used as the detection threshold. If the leakage severity coefficient obtained from the current test is greater than or equal to the detection threshold, leakage exists in the hydraulic curtain, requiring the construction team to promptly perform grouting to prevent water inrush during subsequent excavation and ensure construction safety and quality.

[0039] Based on the same inventive concept as the above method, this application also provides a hydraulic curtain leakage detection device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described hydraulic curtain leakage detection methods.

[0040] It is understood that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0041] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0042] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the protection scope of this application.

Claims

1. A method for detecting leakage in hydraulic curtain walls, characterized in that, Includes the following steps: To obtain the electric field strength values ​​of the receiving coil at different heights during each detection process in the hydraulic curtain leakage detection process; The distribution fluctuation of the electric field strength value of the receiving coil at any height position during each detection is analyzed, as well as the difference between the response time of the electric field strength change and the pulse transmission time during each detection, in order to obtain the first characteristic value of the waveform anomaly and response delay of the electric field strength value at any height position during each detection. By utilizing the discrete fluctuation characteristics between the first feature values ​​corresponding to all height positions during each detection, and combining them with the random variation characteristics of the electric field intensity values ​​at each height position, the significance coefficients of the differences and disorder characteristics of the electric field intensity response during each detection are obtained. Then, by observing the changing trend of the significance coefficients, the leakage severity coefficient for each detection is obtained. Based on the aforementioned leakage severity coefficient, leakage detection is performed on the hydraulic curtain during the current detection period; The expression for the first eigenvalue is: In the formula, The value represents the degree of fluctuation difference in electric field intensity at any given height position during the i-th detection. Let be the response delay coefficient for any given height position in the i-th detection. The normalized result is the mean of the kurtosis of the electric field intensity value in each window at any height position during the i-th detection; the response delay coefficient represents the difference between the response time of the electric field intensity change and the pulse emission time; The degree of fluctuation difference indicates the degree of fluctuation in the distribution of electric field strength values ​​during each detection. The formula for calculating the significance coefficient of the difference in electric field intensity response and the disorder characteristics at each detection is as follows: In the formula, denoted as the significance coefficient of the difference in electric field intensity response and disorder characteristics at the i-th detection. Let be the standard deviation of the first feature value corresponding to all height positions at the i-th detection. The disordered value of the electric field intensity response at the i-th detection; the standard deviation of the first characteristic value corresponding to all height positions characterizes the discrete fluctuation characteristic value; the disordered value of the electric field intensity response characterizes the random variation characteristic.

2. The method for detecting leakage in a hydraulic curtain wall as described in claim 1, characterized in that, For any height position at the i-th detection, extract all peak points and valley points, construct windows with each peak point and valley point as the center, and count the bottom width of the peak and the bottom width of the valley respectively. Use the data in the electric field intensity data that are outside the corresponding intervals of these two bottom widths as the baseline data.

3. The method for detecting leakage in a hydraulic curtain wall as described in claim 2, characterized in that, Before obtaining the first feature value, the ratio of the absolute value of the data corresponding to each peak point and valley point to the mean of all baseline data is calculated, and the mean of all ratios is used as the value of the fluctuation difference of electric field intensity at any height position during the i-th detection.

4. The method for detecting leakage in a hydraulic curtain wall as described in claim 3, characterized in that, Before obtaining the first feature value, the absolute value of the difference between the peak point and the turn-on time, and the absolute value of the difference between the valley point and the turn-off time are calculated respectively. The sum of all absolute values ​​and the ratio of the preset detection time are used as the response delay coefficient of the i-th detection for any height position.

5. The method for detecting leakage in a hydraulic curtain wall as described in claim 1, characterized in that, Before obtaining the significance coefficient, the first-order difference absolute value sequence of the electric field intensity value at each height position is calculated for each detection, and the coefficient of variation of each first-order difference absolute value sequence is calculated. The mean of the coefficients of variation at all heights at each detection is taken as the disorder value of the electric field intensity response at each detection.

6. The method for detecting leakage in a hydraulic curtain wall as described in claim 1, characterized in that, The process of obtaining the leakage severity coefficient for each detection is as follows: the significance coefficients corresponding to the current detection and the previous N detections are used as inputs to the test algorithm, the slope estimate is output, and this estimate is used as the leakage severity coefficient for the current detection.

7. The method for detecting leakage in a hydraulic curtain wall as described in claim 1, characterized in that, If the leakage severity coefficient obtained from the current detection is greater than or equal to the detection threshold, then there is leakage in the hydraulic curtain; otherwise, there is no leakage.

8. A leakage detection device for hydraulic curtain walls, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the water curtain leakage detection method as described in any one of claims 1-7.

Images