Liquid leakage detection method and device for liquid cooling device

Abstract

This application proposes a method and device for detecting liquid leakage in a liquid cooling device, wherein the method comprises: obtaining the fluorescence intensity and magnetic field gradient of a detection area on the surface of the liquid cooling device; wherein the coolant in the liquid cooling device contains a fluorescent marker and a magnetic marker; based on the fluorescence intensity and magnetic field gradient, determining whether there is a risk of liquid leakage in the detection area; in response to the presence of a risk of liquid leakage in the detection area, obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and magnetic field gradient; and determining the target grid position where the leakage occurs in the detection area based on the leakage probability. The technical solution of this application can improve the detection accuracy and efficiency of liquid cooling device leakage.

Description

Technical Field

[0001] The present application relates to the field of data processing and intelligent sensing and monitoring technology, and in particular to a method and device for detecting liquid leakage in a liquid cooling device. Background Art

[0002] In the related art, leakage detection of a liquid cooling device is generally performed by monitoring changes in resistance or light refraction characteristics caused by leakage of the coolant, which has poor reliability. Summary of the Invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] In a first aspect, the present application proposes a method for detecting leakage of a liquid cooling device, the method comprising: obtaining the fluorescence intensity and magnetic field gradient of a detection area on the surface of the liquid cooling device; wherein the coolant of the liquid cooling device contains a fluorescent marker and a magnetic marker; based on the fluorescence intensity and the magnetic field gradient, determining whether there is a leakage risk in the detection area; in response to the presence of a leakage risk in the detection area, obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient; and determining the target grid position where leakage occurs in the detection area based on the leakage probability.

[0005] In one implementation, determining whether there is a risk of leakage in the detection area based on the fluorescence intensity and the magnetic field gradient includes: obtaining target operating condition parameters; wherein the target operating condition parameters include at least one of the following: coolant flow, coolant pressure, coolant temperature, concentration of the fluorescent marker, and concentration of the magnetic marker; obtaining a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters; and determining that there is a risk of leakage in the detection area in response to the fluorescence intensity being greater than or equal to the target fluorescence intensity threshold and the magnetic field gradient being greater than or equal to the target magnetic field gradient threshold.

[0006] In an optional implementation, obtaining the target fluorescence intensity threshold and target magnetic field gradient threshold corresponding to the target operating condition parameters includes: obtaining a first mapping relationship between different operating condition parameters and fluorescence intensity thresholds; obtaining a second mapping relationship between different operating condition parameters and magnetic field gradient thresholds; obtaining the target fluorescence intensity threshold based on the first mapping relationship and the target operating condition parameters; and obtaining the target magnetic field gradient threshold based on the second mapping relationship and the target operating condition parameters.

[0007] In one implementation, the method further includes: generating leakage event data based on the target operating condition parameters and the target grid position; performing leakage prediction based on the leakage event data and historical leakage event data obtained historically, combined with a leakage location prediction model; wherein the leakage location prediction model has learned the ability to predict the leakage location based on the leakage event data.

[0008] In one implementation, the method of obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient includes: dividing the detection area into a grid to obtain a plurality of grid positions; obtaining a priori probability of leakage at each grid position; establishing a joint likelihood function based on the fluorescence intensity and the magnetic field gradient; and using a Bayesian estimation method to obtain the leakage probability at each grid position based on the joint likelihood function and the priori probability of each grid position.

[0009] In one implementation, before obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient, the method further includes: obtaining vibration data and ambient temperature data of the detection area; inputting the fluorescence intensity, the magnetic field gradient, the vibration data and the ambient temperature data into a pre-trained neural network model to obtain the predicted leakage probability output by the neural network model; wherein, the neural network model has learned the ability to output the leakage probability based on the fluorescence intensity, magnetic field gradient, vibration data and temperature data, and in response to the predicted leakage probability being greater than or equal to a probability threshold, continues to execute the step of obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient.

[0010] In one implementation, the method further includes: obtaining electrophoresis sequence data of the cooling liquid; obtaining a first concentration decay rate of the fluorescent marker and / or a second concentration decay rate of the magnetic marker based on the electrophoresis sequence data; and performing the step of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device in response to the first concentration decay rate being greater than or equal to a first decay rate threshold and / or the second concentration decay rate being greater than or equal to a second decay rate threshold.

[0011] In one implementation, the method further includes: generating leakage event data based on the target operating condition parameters and the target grid position; performing leakage prediction based on the leakage event data and historical leakage event data obtained historically, combined with a leakage location prediction model; wherein the leakage location prediction model has learned the ability to predict the leakage location based on the leakage event data.

[0012] In the second aspect, the present application proposes a liquid leakage detection device for a liquid cooling device, the device comprising: an acquisition module for acquiring the fluorescence intensity and magnetic field gradient of a detection area on the surface of the liquid cooling device; wherein the coolant of the liquid cooling device contains fluorescent markers and magnetic markers; a first processing module for determining whether there is a leakage risk in the detection area based on the fluorescence intensity and the magnetic field gradient; a second processing module for acquiring the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient in response to the presence of a leakage risk in the detection area; and a third processing module for determining the target grid position where leakage occurs in the detection area based on the leakage probability.

[0013] In one implementation, the first processing module can be used to: obtain target operating condition parameters; wherein the target operating condition parameters include at least one of the following: coolant flow, coolant pressure, coolant temperature, concentration of the fluorescent marker, and concentration of the magnetic marker; obtain a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters; in response to the fluorescence intensity being greater than or equal to the target fluorescence intensity threshold, and the magnetic field gradient being greater than or equal to the target magnetic field gradient threshold, determine that there is a risk of leakage in the detection area.

[0014] In an optional implementation, the first processing module can be used to: obtain a first mapping relationship between different operating parameters and fluorescence intensity thresholds; obtain a second mapping relationship between different operating parameters and magnetic field gradient thresholds; obtain the target fluorescence intensity threshold based on the first mapping relationship and the target operating parameters; and obtain the target magnetic field gradient threshold based on the second mapping relationship and the target operating parameters.

[0015] In one implementation, the second processing module can be used to divide the detection area into a grid to obtain a plurality of grid positions; obtain a priori probability of leakage at each of the grid positions; establish a joint likelihood function based on the fluorescence intensity and the magnetic field gradient; and adopt a Bayesian estimation method to obtain the leakage probability at each of the grid positions based on the joint likelihood function and the priori probability of each of the grid positions.

[0016] In one implementation, the device also includes a fourth processing module, which is used to: obtain vibration data and ambient temperature data of the detection area; input the fluorescence intensity, the magnetic field gradient, the vibration data and the ambient temperature data into a pre-trained neural network model to obtain the predicted leakage probability output by the neural network model; wherein, the neural network model has learned the ability to output the leakage probability based on the fluorescence intensity, magnetic field gradient, vibration data and temperature data, and in response to the predicted leakage probability being greater than or equal to a probability threshold, continues to execute the step of obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient.

[0017] In one implementation, the device also includes a fifth processing module, which is used to: obtain electrophoresis sequence data of the cooling liquid; obtain a first concentration decay rate of the fluorescent marker and / or a second concentration decay rate of the magnetic marker based on the electrophoresis sequence data; and execute the step of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device in response to the first concentration decay rate being greater than or equal to a first decay rate threshold and / or the second concentration decay rate being greater than or equal to a second decay rate threshold.

[0018] In an optional implementation, the device also includes a sixth processing module, which is used to: generate leakage event data based on the target operating condition parameters and the target grid position; perform leakage prediction based on the leakage event data and historical leakage event data obtained historically, combined with a leakage location prediction model; wherein the leakage location prediction model has learned the ability to predict the leakage location based on the leakage event data.

[0019] In a third aspect, the present application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the liquid leakage detection method for the liquid cooling device as described in the first aspect.

[0020] In a fourth aspect, the present application proposes a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the first aspect to be implemented.

[0021] In a fifth aspect, the present application proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the liquid leakage detection method for a liquid cooling device as described in the first aspect.

[0022] The present application provides a method, device, equipment, and storage medium for detecting liquid cooling device leakage. These methods can determine whether a detection area is at risk of leakage based on the fluorescence intensity and magnetic field gradient within the detection area. If a leakage risk exists within the detection area, the methods also determine the leakage probability at each location within the detection area based on the fluorescence intensity and magnetic field gradient, and select the location with the highest leakage probability as the target grid location for leakage. This improves the accuracy and efficiency of detecting leakage in liquid cooling devices.

[0023] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0025] Figure 1 1 is a flow chart of a method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application;

[0026] Figure 2 1 is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application;

[0027] Figure 3 1 is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application;

[0028] Figure 4 1 is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application;

[0029] Figure 5 1 is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application;

[0030] Figure 6 Schematic diagram of a dual-marker leakage detection and positioning system provided in an embodiment of the present application;

[0031] Figure 7 This is a schematic structural diagram of another liquid leakage detection device for a liquid cooling device provided in an embodiment of the present application;

[0032] Figure 8 This is a schematic structural diagram of another liquid leakage detection device for a liquid cooling device provided in an embodiment of the present application;

[0033] Figure 9 This is a schematic structural diagram of another liquid leakage detection device for a liquid cooling device provided in an embodiment of the present application;

[0034] Figure 10 This is a schematic structural diagram of another liquid leakage detection device for a liquid cooling device provided in an embodiment of the present application;

[0035] Figure 11 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0037] The following describes a method and device for detecting liquid leakage in a liquid cooling device according to an embodiment of the present application with reference to the accompanying drawings.

[0038] Figure 1 FIG. 1 is a flow chart of a method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application. Figure 1 As shown, the method may include but is not limited to the following steps:

[0039] Step S101: Acquire the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device.

[0040] The cooling liquid of the liquid cooling device contains fluorescent markers and magnetic markers.

[0041] It should be noted that in the embodiments of the present application, the surface of the liquid cooling device can be divided into multiple detection areas, and the liquid leakage detection method for the liquid cooling device provided in any embodiment of the present application can be performed on each detection area.

[0042] Exemplarily, an ultraviolet LED (Light-Emitting Diode) is used to illuminate the detection area to excite possible fluorescent markers, and a photomultiplier tube (PMT) is used to receive the emitted light to obtain the fluorescence intensity of the detection area. A sensor based on giant magnetoresistance (GMR) is pre-arranged to obtain the magnetic field gradient of the detection area based on the sensor.

[0043] In some embodiments, the fluorescent marker may be a rare earth fluorescent complex (e.g., europium (Eu³⁺) or terbium (Tb³⁺)), so that the fluorescent marker can be stably dispersed in the coolant of the liquid cooling device without changing the physical and chemical properties of the coolant fluid.

[0044] It should be noted that the excitation wavelength and emission wavelength of the fluorescent marker are different from the wavelength of the ambient light in the environment where the liquid cooling device is located, so that the accuracy of leakage detection can be guaranteed.

[0045] In some embodiments, the aforementioned magnetic markers may be surface-modified magnetic nanoparticles.

[0046] Step S102: Determine whether there is a risk of liquid leakage in the detection area based on the fluorescence intensity and the magnetic field gradient.

[0047] Exemplarily, if the fluorescence intensity of the detection area is greater than a preset fluorescence intensity threshold, and the magnetic field gradient is greater than a preset magnetic field gradient threshold, it is determined that there is a risk of liquid leakage in the detection area.

[0048] The fluorescence intensity threshold and magnetic field gradient threshold are the fluorescence intensity and magnetic field gradient measured without leakage.

[0049] Step S103: In response to the presence of a liquid leakage risk in the detection area, the leakage probability of each grid position in the detection area is obtained based on the fluorescence intensity and the magnetic field gradient.

[0050] Exemplarily, the detection area is divided into a grid to obtain multiple grid positions. According to the attenuation characteristics of fluorescence intensity and magnetic field gradient with distance, for each grid position, the first deviation of the fluorescence intensity value and the theoretical value of fluorescence intensity and the second deviation of the magnetic field gradient value and the theoretical value of magnetic field gradient are calculated, and the first deviation and the second deviation rate are averagely weighted to obtain the average deviation of each grid position. The smaller the average deviation, the greater the probability of leakage.

[0051] Step S104: determining the target grid position where the leakage occurs within the detection area based on the leakage probability.

[0052] Exemplarily, the position with the highest probability of liquid leakage is determined as the target grid position where the liquid leakage occurs in the detection area.

[0053] In some embodiments, after the target location is determined, a liquid leakage alarm message may be generated and pushed through a terminal device to remind relevant personnel to inspect the target location.

[0054] By implementing the embodiments of the present application, it is possible to determine whether a leakage risk exists in the detection area based on the fluorescence intensity and magnetic field gradient of the detection area. If a leakage risk exists in the detection area, the leakage probability of each location within the detection area is determined based on the fluorescence intensity and magnetic field gradient, and the location with the highest leakage probability is selected as the target grid location for leakage. This can improve the accuracy and efficiency of detecting leakage in liquid cooling devices.

[0055] In some embodiments, a threshold value for determining whether there is a risk of liquid leakage in the detection area can be determined based on the target operating condition parameter. As an example, see Figure 2 , Figure 2 FIG. 1 is a flow chart of another method for detecting leakage of a liquid cooling device provided in an embodiment of the present application. Figure 2 As shown, the method may include but is not limited to the following steps:

[0056] Step S201: Acquire the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device.

[0057] In the embodiment of the present application, step S201 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0058] Step S202: Obtain target operating condition parameters.

[0059] The target operating condition parameters include at least one of the following: coolant flow rate, coolant pressure, coolant temperature, concentration of fluorescent marker, and concentration of magnetic marker.

[0060] Step S203: Obtaining a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters.

[0061] Exemplarily, a fluorescence intensity baseline value and a magnetic field gradient baseline value under normal operating conditions are constructed by statistical regression method, and a target fluorescence intensity threshold value and a target magnetic field gradient threshold value are obtained in combination with a preset standard deviation.

[0062] In an optional implementation, obtaining a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters includes: obtaining a first mapping relationship between different operating condition parameters and the fluorescence intensity threshold; obtaining a second mapping relationship between different operating condition parameters and the magnetic field gradient threshold; obtaining the target fluorescence intensity threshold based on the first mapping relationship and the target operating condition parameters; and obtaining the target magnetic field gradient threshold based on the second mapping relationship and the target operating condition parameters.

[0063] Exemplarily, multiple experiments are carried out under different working conditions to obtain multiple fluorescence intensities and multiple magnetic field gradients when the coolant leaks under each working condition, and then the average of the multiple fluorescence intensities when the coolant leaks under each working condition is obtained as the target fluorescence intensity threshold corresponding to the working condition, and the average of the multiple magnetic field gradients when the coolant leaks under each working condition is obtained as the target magnetic field gradient threshold corresponding to the working condition, so as to establish a first mapping relationship between different working condition parameters and the fluorescence intensity threshold, and a second mapping relationship between different working condition parameters and the magnetic field gradient threshold, so as to obtain the target fluorescence intensity threshold based on the target working condition parameters and the first mapping relationship, and obtain the target magnetic field gradient threshold based on the target working condition parameters and the second mapping relationship.

[0064] Step S204: In response to the fluorescence intensity being greater than or equal to the target fluorescence intensity threshold and the magnetic field gradient being greater than or equal to the target magnetic field gradient threshold, determining that there is a risk of liquid leakage in the detection area.

[0065] Exemplarily, in response to the fluorescence intensity of the detection area being greater than or equal to a target fluorescence intensity threshold and the magnetic field gradient of the detection area being greater than or equal to a target magnetic field gradient threshold, it is determined that there is a risk of liquid leakage in the detection area.

[0066] Step S205: In response to the presence of a liquid leakage risk in the detection area, the leakage probability of each grid position in the detection area is obtained based on the fluorescence intensity and the magnetic field gradient.

[0067] In the embodiment of the present application, step S205 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0068] Step S206: determining the target grid position where the leakage occurs within the detection area based on the leakage probability.

[0069] In the embodiment of the present application, step S206 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0070] By implementing the embodiments of the present application, it is possible to determine whether a leakage risk exists in the detection area based on the target fluorescence intensity threshold and magnetic field intensity threshold corresponding to the target operating condition parameters, and based on the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device. Furthermore, if a leakage risk exists in the detection area, the target grid location where leakage occurs can be determined. The accuracy of leakage detection can be improved by dynamically acquiring thresholds.

[0071] In some embodiments, a Bayesian estimation method can be used to combine the fluorescence intensity and magnetic field gradient of the detection area to obtain the leakage probability at each position in the detection area. As an example, see Figure 3 , Figure 3 This is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application. Figure 3 As shown, the method may include but is not limited to the following steps:

[0072] Step S301: Acquire the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device.

[0073] In the embodiment of the present application, step S301 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0074] Step S302: Determine whether there is a risk of liquid leakage in the detection area based on the fluorescence intensity and the magnetic field gradient.

[0075] In the embodiment of the present application, step S302 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0076] Step S303: In response to the presence of a liquid leakage risk in the detection area, the detection area is divided into a plurality of grid positions.

[0077] Exemplarily, in response to the risk of liquid leakage in the detection area, the detection area is divided into an average grid to obtain a plurality of grid positions.

[0078] Step S304: Obtain the prior probability of leakage at each grid position.

[0079] Exemplarily, the piping structure and historical leakage data of the liquid cooling device in each grid location are obtained to set the initial leakage risk.

[0080] It's understandable that the probability of leakage varies at different locations. For example, the junctions between different components of a liquid cooling system are more likely to leak. Therefore, for each grid location, an initial leakage risk and the prior probability of leakage at that grid location can be derived based on the corresponding liquid cooling system components and component structures, as well as historical leakage data for that grid location.

[0081] Step S305: establishing a joint likelihood function based on the fluorescence intensity and the magnetic field gradient.

[0082] For example, the relationship between the actual fluorescence intensity at each grid position and the fluorescence intensity acquired by the sensor can be expressed as follows:

[0083]

[0084] in, For the The theoretical fluorescence intensity of each grid position, is the initial fluorescence intensity of the leakage point, α is the attenuation coefficient, For the The distance between the grid position and the sensor. Then the likelihood probability of the fluorescence intensity can be expressed as:

[0085]

[0086] in, is the fluorescence intensity, Representative The grid position is the leakage position, is the noise variance of the fluorescence signal.

[0087] The relationship between the actual magnetic field gradient at each grid position and the magnetic field gradient obtained by the sensor can be expressed as follows:

[0088]

[0089] in, is the actual magnetic field gradient at the grid location, is the distance between the grid position and the magnetic sensor, is the attenuation coefficient. The likelihood probability of the magnetic field gradient can be expressed as:

[0090]

[0091] in, is the magnetic field gradient obtained by the sensor, is the noise variance of the magnetic field signal. The joint likelihood function can be expressed as:

[0092]

[0093] Step S306: using a Bayesian estimation method, based on the joint likelihood function and the prior probability of each grid position, to obtain the leakage probability of each grid position.

[0094] Exemplarily, based on the joint likelihood function and the aforementioned prior probability, a Bayesian estimation method is used to calculate the posterior probability of leakage occurring at each grid position as the leakage probability of leakage occurring at the grid position.

[0095] In some embodiments, the leakage probability at each grid position may be interpolated to generate a leakage probability heat map of the detection area, and the leakage probability heat map may be displayed through an interactive device.

[0096] Step S307: determining the target grid position where the leakage occurs within the detection area based on the leakage probability.

[0097] By implementing the embodiments of the present application, a Bayesian estimation method can be used to obtain the leakage probability at different locations in the detection area based on fluorescence intensity and magnetic field gradient, and the target grid location where the leakage occurs can be determined based on the leakage probability. This allows for precise positioning of the leakage location.

[0098] In some embodiments, a neural network model can be used to determine whether the leakage risk determined based on the fluorescence intensity and magnetic field gradient is a misjudgment caused by interference. As an example, see Figure 4 , Figure 4 This is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application. Figure 4 As shown, the method may include but is not limited to the following steps:

[0099] Step S401: Acquire the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device.

[0100] In the embodiment of the present application, step S401 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0101] Step S402: Determine whether there is a risk of liquid leakage in the detection area based on the fluorescence intensity and the magnetic field gradient.

[0102] In the embodiment of the present application, step S402 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0103] Step S403: In response to the presence of a liquid leakage risk in the detection area, vibration data and ambient temperature data of the detection area are acquired.

[0104] Exemplarily, in response to a risk of liquid leakage in the detection area, vibration data of a liquid cooling device in the detection area and ambient temperature data of the detection area are acquired.

[0105] Step S404: input the fluorescence intensity, magnetic field gradient, vibration data and ambient temperature data into a pre-trained neural network model to obtain the predicted leakage probability output by the neural network model.

[0106] Among them, the above-mentioned neural network model has learned the ability to output leakage probability based on fluorescence intensity, magnetic field gradient, vibration data and temperature data.

[0107] For example, data processing is performed on the fluorescence intensity, magnetic field gradient, vibration data and ambient temperature data to convert them into a two-dimensional feature matrix suitable for the input of the neural network model. The neural network model is pre-trained with the two-dimensional matrix data to obtain the predicted leakage probability output by the neural network model.

[0108] In one implementation, the neural network model is pre-trained by following steps A1 to A3:

[0109] Step A1: Obtain sample data.

[0110] The sample data include real leakage samples, vibration interference samples and temperature interference samples.

[0111] Step A2: Divide the sample data into a training set and a validation set, use the training set to train the initial neural network model, and adjust the model parameters through the back propagation algorithm so that the model can accurately distinguish different types of signals.

[0112] Step A3: Use the validation set to evaluate the performance of the model and optimize the model structure and parameters based on the evaluation results.

[0113] Step A4: Repeat steps A2 and A3 until the model performance meets the preset requirements.

[0114] Step S405: In response to the predicted leakage probability being greater than or equal to the probability threshold, the leakage probability of each grid position in the detection area is obtained based on the fluorescence intensity and the magnetic field gradient.

[0115] Exemplarily, in response to the predicted leakage probability output by the neural network model being greater than or equal to a preset probability threshold, the leakage probability of each grid position in the detection area is obtained based on the fluorescence intensity and the magnetic field gradient.

[0116] In the embodiments of the present application, the specific implementation method of obtaining the leakage probability of each grid position in the detection area based on fluorescence intensity and magnetic field gradient can be implemented by any one of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be repeated.

[0117] Step S406: determining the target grid position where the leakage occurs within the detection area based on the leakage probability.

[0118] In the embodiment of the present application, step S406 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0119] By implementing the embodiments of the present application, when a leakage risk is determined in a detection area, a pre-trained neural network model can be used to determine whether the leakage risk is caused by interference. If the leakage risk is determined not to be caused by interference, subsequent detection steps can be continued. This can further improve the accuracy of leakage detection.

[0120] In some embodiments, the leak location can also be determined based on a swarm optimization algorithm. As an example, see Figure 5 , Figure 5 This is a flow chart of another method for detecting liquid leakage in a liquid cooling device provided in an embodiment of the present application. Figure 5 As shown, the method may include but is not limited to the following steps:

[0121] Step S501: Acquire the fluorescence intensity and magnetic field gradient of the monitoring area on the surface of the liquid cooling device.

[0122] In the embodiment of the present application, step S501 can be implemented in any of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0123] Step S502: Determine whether there is a risk of liquid leakage in the monitoring area based on the fluorescence intensity and the magnetic field gradient.

[0124] In the embodiment of the present application, step S502 can be implemented by any of the methods in the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0125] Step S503: In response to the risk of liquid leakage in the monitoring area, a particle swarm optimization algorithm is used to determine the target grid position where the liquid leakage occurs in the monitoring area based on the fluorescence intensity and the magnetic field gradient.

[0126] For example, the detection area is divided into multiple grid locations, and each grid location is used as a computational particle in the particle swarm optimization algorithm. The objective function is constructed based on the relationship between the monitored fluorescence signal intensity, magnetic field gradient data, and the leakage source location. For example, based on the assumed leakage source location, the error between the theoretical signal value calculated using the fluorescence signal intensity attenuation model and the magnetic field distribution model and the actual observed signal value can be expressed as follows:

[0127]

[0128] in, is the mean square error, is the number of sensors, It is The actual observation value of each sensor (e.g., fluorescence intensity or magnetic field gradient, etc. The first is calculated based on the assumed leak source location. For each particle, it is iteratively updated based on the individual optimal and global optimal positions until the preset termination condition is reached. The global optimal position at this time is output, which is the target grid position of the leakage obtained by inversion.

[0129] By implementing the embodiments of the present application, the target grid position of the leak can be obtained by inversion based on the particle swarm optimization algorithm combined with the fluorescence intensity and magnetic field gradient, thereby achieving rapid positioning of the leak.

[0130] In some embodiments, the liquid leakage detection method for a liquid cooling device provided in the embodiments of the present application may further include steps B1 to B3:

[0131] Step B1: Acquire electrophoresis sequence data of the coolant.

[0132] Exemplarily, a sampling loop connected to the liquid cooling device pipeline is established, and the coolant of the liquid cooling device is introduced into the capillary inlet at a constant flow rate through a micro pump, and the liquid in the capillary is subjected to electrophoresis analysis once every preset time period to obtain electrophoresis sequence data.

[0133] Step B2: Acquire a first concentration decay rate of the fluorescent marker and / or a second concentration decay rate of the magnetic marker based on the electrophoresis sequence data.

[0134] Illustratively, based on the electrophoresis sequence data, a peak area quantification method is used to calculate the first concentration sequence data of the fluorescent marker, thereby obtaining a first concentration decay rate of the fluorescent marker based on the concentration sequence data.

[0135] Illustratively, based on the electrophoresis sequence data, the peak area quantification method is used to calculate the second concentration sequence data of the magnetic marker, thereby obtaining the second concentration decay rate of the magnetic marker based on the second concentration sequence data.

[0136] Exemplarily, based on the electrophoresis sequence data, the peak area quantification method is used to calculate the first concentration sequence data and of the fluorescent marker, thereby obtaining the first concentration decay rate of the fluorescent marker based on the concentration sequence data, and obtaining the second concentration decay rate of the magnetic marker based on the second concentration sequence data.

[0137] Step B3: In response to the first concentration decay rate being greater than or equal to the first decay rate threshold and / or the second concentration decay rate being greater than or equal to the second decay rate threshold, executing the step of acquiring the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device.

[0138] Exemplarily, in response to the first concentration decay rate being greater than or equal to the first decay rate threshold, it is determined that there is a risk of leakage in the liquid cooling device, and the steps and subsequent steps of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device in any of the aforementioned embodiments are performed.

[0139] Exemplarily, in response to the second concentration decay rate being greater than or equal to the second decay rate threshold, it is determined that there is a risk of leakage in the liquid cooling device, and the steps and subsequent steps of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device in any of the aforementioned embodiments are performed.

[0140] Exemplarily, in response to the first concentration decay rate being greater than or equal to a first decay rate threshold, and the second concentration decay rate being greater than or equal to a second decay rate threshold, it is determined that there is a risk of leakage in the liquid cooling device, and the steps and subsequent steps of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device in any of the foregoing embodiments are performed.

[0141] By implementing the embodiments of the present application, it is possible to determine whether there is an abnormality in the sealing of the liquid cooling device based on the electrophoresis measurement method, so that when it is determined that the sealing of the liquid cooling device is abnormal, the liquid cooling device can be detected for leakage, thereby reducing monitoring costs.

[0142] In some embodiments, the leakage detection method for a liquid cooling device provided in an embodiment of the present application may further include the following steps: generating leakage event data based on target operating parameters and target grid positions; performing leakage prediction based on the leakage event data and historical leakage event data acquired historically, combined with a leakage position prediction model; wherein the leakage position prediction model has learned the ability to predict the leakage position based on the leakage event data.

[0143] Exemplarily, the target operating condition parameters and target grid position are used as a set of new leakage event data, and are input into a pre-trained leakage position prediction model together with historical leakage data acquired in a historical period to obtain a predicted leakage position output by the leakage position prediction model.

[0144] Exemplarily, the leakage position prediction model may be an LSTM (Long Short-Term Memory) model.

[0145] It is understandable that for liquid cooling devices, leakage usually occurs at the connection points of different components. Therefore, the target component where leakage may occur can be determined based on the above leakage location, so as to perform preventive inspection on the target component and reduce the probability of leakage, thereby ensuring the safe operation of the liquid cooling device.

[0146] In some embodiments, the concentration of the fluorescent marker and / or the concentration of the magnetic marker can be dynamically adjusted according to the circulation amount of the cooling liquid.

[0147] Illustratively, the optimal marker concentration range under different coolant circulation rates is determined experimentally, thereby establishing a third mapping relationship between different coolant circulation rates and fluorescent marker concentrations, as well as a third mapping relationship between different coolant circulation rates and magnetic marker concentrations. A flow meter is installed in the liquid cooling device pipeline to collect the coolant circulation rate in real time, and the concentration of the fluorescent marker and / or the concentration of the magnetic marker is dynamically adjusted according to the above mapping relationship through an automatic dosing device and a marker recovery device (for example, recovering the magnetic marker through a magnetic filter).

[0148] By implementing this embodiment, sudden changes in marker concentration caused by fluctuations in circulation volume can be avoided, thereby ensuring the sensitivity of leakage detection under different working conditions.

[0149] See Figure 6 , Figure 6 Schematic diagram of a dual-marker leakage detection and positioning system provided in an embodiment of the present application. Figure 6As shown, fluorescent and magnetic markers are injected into the coolant reservoir. Optical sensors are deployed to detect fluorescence intensity under ultraviolet excitation, while magnetic sensors are deployed to detect magnetic field gradients. When the optical sensor detects fluorescence intensity exceeding a preset threshold and the magnetic sensor detects a change in the local magnetic field gradient, an edge computing unit is invoked to calculate the leak location using a positioning algorithm and send an alarm to the central monitoring platform. A magnetic filter is also installed at the coolant circuit outlet to circulate and adsorb nanomagnetic particles, reducing material loss and deployment costs.

[0150] See Figure 7 , Figure 7 Schematic diagram of a liquid leakage detection device for a liquid cooling device provided in an embodiment of the present application. Figure 7 As shown, the device 700 includes: an acquisition module 701, which is used to obtain the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device; wherein the cooling liquid of the liquid cooling device contains fluorescent markers and magnetic markers; a first processing module 702, which is used to determine whether there is a risk of leakage in the detection area based on the fluorescence intensity and magnetic field gradient; a second processing module 703, which is used to obtain the leakage probability of each grid position in the detection area based on the fluorescence intensity and magnetic field gradient in response to the presence of a leakage risk in the detection area; and a third processing module 704, which is used to determine the target grid position where leakage occurs in the detection area based on the leakage probability.

[0151] In one implementation, the first processing module 702 can be used to: obtain target operating condition parameters; wherein the target operating condition parameters include at least one of the following: coolant flow, coolant pressure, coolant temperature, concentration of fluorescent markers, and concentration of magnetic markers; obtain a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters; in response to the fluorescence intensity being greater than or equal to the target fluorescence intensity threshold, and the magnetic field gradient being greater than or equal to the target magnetic field gradient threshold, determine that there is a risk of leakage in the detection area.

[0152] In an optional implementation, the first processing module 702 can be used to: obtain a first mapping relationship between different operating parameters and fluorescence intensity thresholds; obtain a second mapping relationship between different operating parameters and magnetic field gradient thresholds; obtain a target fluorescence intensity threshold based on the first mapping relationship and the target operating parameters; and obtain a target magnetic field gradient threshold based on the second mapping relationship and the target operating parameters.

[0153] In one implementation, the second processing module 703 can be used to divide the detection area into a grid to obtain multiple grid positions; obtain the prior probability of leakage at each grid position; establish a joint likelihood function based on fluorescence intensity and magnetic field gradient; and use a Bayesian estimation method to obtain the leakage probability at each grid position based on the joint likelihood function and the prior probability of each grid position.

[0154] In one implementation, the apparatus further includes a fourth processing module. As an example, see Figure 8 , Figure 8 This is a schematic diagram of the structure of another liquid cooling device leakage detection device provided in an embodiment of the present application. Figure 8 As shown, the device 800 also includes a fourth processing module 805, which is used to: obtain vibration data and ambient temperature data of the detection area; input the fluorescence intensity, magnetic field gradient, vibration data and ambient temperature data into a pre-trained neural network model to obtain the predicted leakage probability output by the neural network model; wherein the neural network model has learned to output the leakage probability based on the fluorescence intensity, magnetic field gradient, vibration data and temperature data; in response to the predicted leakage probability being greater than or equal to the probability threshold, the step of obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and magnetic field gradient is continued. Figure 8 Modules 801 to 804 shown in FIG. Figure 7 The modules 701 to 704 shown in FIG. 7 have the same structure and function.

[0155] In one implementation, the apparatus further includes a fifth processing module. As an example, see Figure 9 , Figure 9 This is a schematic diagram of the structure of another liquid cooling device leakage detection device provided in the embodiment of the present application. Figure 9 As shown, the device 900 also includes a fifth processing module 905, which is used to: obtain electrophoresis sequence data of the cooling liquid; obtain a first concentration decay rate of the fluorescent marker and / or a second concentration decay rate of the magnetic marker based on the electrophoresis sequence data; and obtain the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device in response to the first concentration decay rate being greater than or equal to a first decay rate threshold and / or the second concentration decay rate being greater than or equal to a second decay rate threshold. Figure 9 Modules 901 to 904 shown in FIG. Figure 7 The modules 701 to 704 shown in FIG. 7 have the same structure and function.

[0156] In an optional implementation, the above device further includes a sixth processing module. As an example, see Figure 10 , Figure 10 This is a schematic diagram of the structure of another liquid cooling device leakage detection device provided in an embodiment of the present application. Figure 10 As shown, the device 1000 further includes a sixth processing module 1005, which is used to: generate leakage event data based on the target operating condition parameters and the target grid position; perform leakage prediction based on the leakage event data and historical leakage event data obtained in the past, combined with a leakage location prediction model; wherein the leakage location prediction model has learned the ability to predict the leakage location based on the leakage event data. Figure 10 The modules 1001 to 1004 shown in FIG. Figure 7 The modules 701 to 704 shown in FIG. 7 have the same structure and function.

[0157] The device of the present application embodiment can determine whether a leakage risk exists in the detection area based on the fluorescence intensity and magnetic field gradient of the detection area. If a leakage risk exists in the detection area, the leakage probability of each location within the detection area is determined based on the fluorescence intensity and magnetic field gradient, and the location with the highest leakage probability is selected as the target grid location for leakage. This can improve the detection accuracy and efficiency of liquid cooling device leakage.

[0158] It should be noted that the above explanation of the embodiment of the liquid leakage detection method for a liquid cooling device is also applicable to the liquid leakage detection device for a liquid cooling device of this embodiment, and will not be repeated here.

[0159] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 11 , Figure 11 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 11 As shown, the electronic device 1100 includes: a processor 1101, and a memory 1102 communicatively connected to the processor 1101; the memory 1102 stores computer-executable instructions; the processor 1101 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0160] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0161] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0162] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations and do not violate public order and good morals.

[0163] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards.

[0164] It is worth noting that in the embodiments of this application, certain software, components, models, etc. that already exist in the industry may be mentioned. They should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0165] In the description of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0166] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0167] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0168] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0169] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable media include: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0170] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0171] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0172] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0173] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for detecting liquid leakage in a liquid cooling device, characterized in that: include: Acquiring the fluorescence intensity and magnetic field gradient of the detection area on the surface of the liquid cooling device; wherein the cooling liquid of the liquid cooling device contains a fluorescent marker and a magnetic marker; determining whether there is a risk of liquid leakage in the detection area based on the fluorescence intensity and the magnetic field gradient; In response to a liquid leakage risk existing in the detection area, obtaining a liquid leakage probability at each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient; Determining a target grid position where leakage occurs within the detection area based on the leakage probability; The obtaining of the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient includes: Dividing the detection area into grids to obtain a plurality of grid positions; Obtaining a priori probability of leakage occurring at each of the grid locations; establishing a joint likelihood function based on the fluorescence intensity and the magnetic field gradient; The leakage probability of each grid position is obtained by adopting a Bayesian estimation method based on the joint likelihood function and the prior probability of each grid position.

2. The method according to claim 1, characterized in that The determining, based on the fluorescence intensity and the magnetic field gradient, whether there is a risk of liquid leakage in the detection area includes: Obtaining target operating condition parameters; wherein the target operating condition parameters include at least one of the following: coolant flow rate, coolant pressure, coolant temperature, concentration of the fluorescent marker, and concentration of the magnetic marker; Obtaining a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameters; In response to the fluorescence intensity being greater than or equal to the target fluorescence intensity threshold, and the magnetic field gradient being greater than or equal to the target magnetic field gradient threshold, it is determined that there is a risk of liquid leakage in the detection area.

3. The method according to claim 2, characterized in that The obtaining of a target fluorescence intensity threshold and a target magnetic field gradient threshold corresponding to the target operating condition parameter includes: Obtaining a first mapping relationship between different operating parameters and fluorescence intensity thresholds; Acquire a second mapping relationship between different operating condition parameters and magnetic field gradient thresholds; Based on the first mapping relationship and the target operating condition parameter, obtaining the target fluorescence intensity threshold; The target magnetic field gradient threshold is acquired based on the second mapping relationship and the target operating condition parameter.

4. The method according to claim 2, characterized in that The method further comprises: generating liquid leakage event data based on the target operating condition parameter and the target grid position; Based on the leakage event data and historical leakage event data obtained in the past, leakage prediction is performed in combination with a leakage location prediction model; wherein the leakage location prediction model has learned the ability to predict the leakage location based on the leakage event data.

5. The method according to claim 1, wherein Before obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient, the method further includes: Acquiring vibration data and ambient temperature data of the detection area; inputting the fluorescence intensity, the magnetic field gradient, the vibration data, and the ambient temperature data into a pre-trained neural network model to obtain a predicted leakage probability output by the neural network model; wherein the neural network model has learned to output the leakage probability based on the fluorescence intensity, magnetic field gradient, vibration data, and temperature data; In response to the predicted leakage probability being greater than or equal to a probability threshold, the step of obtaining the leakage probability of each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient is continued.

6. The method according to claim 1, characterized in that Before obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device, the method further includes: Acquiring electrophoresis sequence data of the coolant; Acquiring a first concentration decay rate of the fluorescent marker and / or a second concentration decay rate of the magnetic marker based on the electrophoresis sequence data; In response to the first concentration decay rate being greater than or equal to a first decay rate threshold and / or the second concentration decay rate being greater than or equal to a second decay rate threshold, the step of obtaining the fluorescence intensity and magnetic field gradient of the surface detection area of ​​the liquid cooling device is performed.

7. A liquid leakage detection device for a liquid cooling device, characterized in that: include: An acquisition module, configured to acquire the fluorescence intensity and magnetic field gradient of a detection area on the surface of a liquid cooling device; wherein the cooling liquid of the liquid cooling device contains a fluorescent marker and a magnetic marker; a first processing module, configured to determine whether there is a risk of liquid leakage in the detection area based on the fluorescence intensity and the magnetic field gradient; a second processing module, configured to, in response to a liquid leakage risk existing in the detection area, obtain a liquid leakage probability at each grid position in the detection area based on the fluorescence intensity and the magnetic field gradient; A third processing module is configured to determine a target grid position where leakage occurs within the detection area based on the leakage probability; The second processing module is specifically configured to: Dividing the detection area into grids to obtain a plurality of grid positions; Obtaining a priori probability of leakage occurring at each of the grid locations; establishing a joint likelihood function based on the fluorescence intensity and the magnetic field gradient; The leakage probability of each grid position is obtained by adopting a Bayesian estimation method based on the joint likelihood function and the prior probability of each grid position.

8. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method according to any one of claims 1 to 6.

Images