Monitoring method and system for immersed user side energy storage equipment

Abstract

The invention discloses a monitoring method and system for immersed user side energy storage equipment, and relates to the technical field of immersed energy storage equipment.The method comprises the steps that model training is conducted through historical monitoring data of the immersed energy storage equipment, a feedback verification model is obtained, and after real-time monitoring data are collected through a data monitoring unit, a feedback verification result is obtained; if it is judged that the collected real-time monitoring data is abnormal according to a set threshold value, a predicted three-dimensional temperature field is generated through a feedback verification model according to the real-time monitoring data, an actual three-dimensional temperature field is generated through a temperature field construction unit, and the temperature field is analyzed through subsequent digital processing and comparative analysis. According to the invention, whether the acquired real-time monitoring data is abnormal by the data monitoring unit or the immersed energy storage equipment is abnormal is verified and judged, when the real-time monitoring data is abnormal, further abnormality diagnosis can be carried out, and the cause of the abnormality can be determined, so that the redundant design of the data monitoring unit is avoided, the hardware cost is saved, and the reliability of the system is improved. And the monitoring accuracy of the immersed energy storage equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of submerged energy storage equipment, and in particular to a monitoring method and system for submerged user-side energy storage equipment. Background Art

[0002] Immersed user-side energy storage equipment is an energy storage system in which energy storage batteries or other energy storage media are completely immersed in insulating coolant. It is mainly deployed in industrial and commercial parks, shopping malls, residences, data centers, etc. to achieve the storage and flexible scheduling of electric energy. Its core feature is that the liquid directly contacts the energy storage unit, achieving efficient heat dissipation, safety protection and system compactness.

[0003] A Chinese invention patent (CN119153819A) discloses an "immersed energy storage battery box and its monitoring method, electronic device and storage medium", which specifically discloses: insulating oil is introduced into the interior of the battery box through an immersion system; the average temperature of the battery module is obtained through a first temperature sensor; when the average temperature is greater than a first preset temperature, the battery management system controls the immersion system to adjust the temperature of the insulating oil to cool the battery module; when the average temperature is greater than a second preset temperature, the battery management system controls the immersion system to adjust the temperature of the insulating oil, and controls the refrigeration system to introduce refrigerant gas into the hollow flow channel to cool the battery module; the conductivity of the insulating oil is detected by a built-in sensor, and when the conductivity of the insulating oil exceeds a first preset value, the insulating oil is replaced; the oil leakage status of the battery box is detected by an external sensor, and an alarm is issued when the battery box leaks oil.

[0004] In the aforementioned disclosed technical solutions, the monitoring of submerged energy storage devices is performed by monitoring data of the energy storage devices through hardware devices. When the monitoring data does not meet the system setting conditions, the energy storage device is determined to be abnormal and corresponding remedial measures are taken. However, this method lacks effective verification and mutual feedback, because the monitoring data abnormality may also be caused by an abnormality in the hardware monitoring device. Conventional redundant design will result in an incompleteness and increased hardware costs. It is very easy to misdiagnose faults and increase the failure rate of hardware devices, affecting the normal use of the submerged energy storage device.

[0005] Therefore, there is an urgent need for a new monitoring method and system for submerged user-side energy storage equipment to solve the above technical problems. Summary of the Invention

[0006] The object of the present invention is to provide a monitoring method and system for an immersion-type user-side energy storage device to solve the problems raised in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring an immersion-type user-side energy storage device, comprising the following steps: S1. Retrieving historical monitoring data from a storage database of the submerged energy storage device using a data retrieval unit, and training a model through a model training module based on the historical monitoring data to obtain a feedback verification model; S2. Using a data monitoring unit to collect real-time monitoring data of the submerged energy storage device. If the real-time monitoring data is abnormal, the real-time monitoring data is input into a feedback verification model, a predicted three-dimensional temperature field is generated through the feedback verification model, and an actual three-dimensional temperature field is generated through a temperature field construction unit based on the real-time monitoring data. S3, digitally processing the generated actual three-dimensional temperature field and the predicted three-dimensional temperature field respectively through a digital processing module to obtain an actual isothermal region function and a predicted isothermal region function; S4. Use the comparison analysis module to perform a similarity comparison between the actual isothermal region function and the predicted isothermal region function, and complete the verification of the abnormal real-time monitoring data based on the similarity comparison result. If the similarity comparison result meets the set threshold, it is determined that the data monitoring unit is abnormal; otherwise, it is determined that the submerged energy storage device is abnormal.

[0008] According to the above technical solution, in step S1, the feedback verification model is constructed based on a deep neural network model, the retrieved historical monitoring data is divided into data sets, and the divided data sets are preprocessed, including normalization and standardization; The coolant inlet temperature data in the input feature , coolant outlet temperature data and ambient temperature data Normalization is performed, and the specific processing method is as follows: ; in, represents the normalized temperature data, , Indicates a certain temperature data in the second monitoring data, and Respectively represent the minimum value and maximum value of a certain type of temperature data in the second monitoring data; The coolant flow data in the input feature is and coolant flow rate data Standardization processing is carried out, and the specific processing methods are as follows: ; in, Indicates the flow data or velocity data after normalization. Indicates a flow rate data or flow velocity data in the second monitoring data, and Respectively represent the mean and standard deviation of a certain type of data in the second monitoring data; The processing of the output features includes expanding the three-dimensional temperature field distribution data into a one-dimensional vector and then performing the same normalization processing as the second monitoring data. The details will not be described in detail here. Any set of historical monitoring data includes first monitoring data and second monitoring data; The second monitoring data is used as the input feature of the feedback verification model, the first monitoring data is used as the output feature of the feedback verification model, and the loss function is defined ; The model training module is based on input features, output features and loss function The deep neural network model is trained to obtain a feedback verification model.

[0009] According to the above technical solution, the historical monitoring data includes three-dimensional temperature field distribution data of the immersion energy storage device, coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data and ambient temperature data; The three-dimensional temperature field distribution data of the immersion energy storage device is the first monitoring data; Coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data and ambient temperature data are second monitoring data; Loss Function ; in, represents the total number of samples in the second monitoring data, represents the loss function of the i-th sample; Among them, the loss function of the i-th sample is Expressed as: ; in, Represents the number of grid points in the three-dimensional temperature field distribution data, j represents the number of j-th grid points in the i-th sample, represents the weight value of the j-th grid point in the first monitoring data, represents the predicted value of the j-th grid point, Represents the true value of the j-th grid point; The retrieved historical monitoring data is divided into a training set, a validation set, and a test set; The model training module trains the deep neural network model through the training set, then verifies the trained model through the validation set, and tests the model through the test set, and finally obtains a feedback verification model.

[0010] According to the above technical solution, in step S2, the temperature data inside the immersion energy storage device collected by the data monitoring unit is defined as the third monitoring data, and the coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data and ambient temperature data collected by the data monitoring unit are defined as the fourth monitoring data; Determine whether there are any abnormalities in the real-time monitoring data by setting threshold conditions; If there is no abnormality, the real-time monitoring data is loaded with the collected timestamp and stored in the storage database; If there is an abnormality, the fourth monitoring data is transmitted to the feedback verification model, and the feedback verification model generates a predicted three-dimensional temperature field based on the fourth monitoring data; The third monitoring data is transmitted to the temperature field construction unit, and an actual three-dimensional temperature field is generated by the temperature field construction unit.

[0011] According to the above technical solution, the temperature data inside the submerged energy storage device is collected through distributed optical fibers; The construction of the actual three-dimensional temperature field includes the following steps: According to the physical layout path of the distributed optical fiber, a mapping relationship between the distributed optical fiber position and the three-dimensional coordinates of the energy storage device is established, and the physical position of each measurement point of the distributed optical fiber is recorded. , where k represents the kth measurement point of the distributed optical fiber; Extracting discrete temperature points from temperature data collected by distributed optical fibers , inferring the temperature of uncovered areas through interpolation algorithms, such as kriging interpolation, radial basis function interpolation, or inverse distance weighting, and selecting the best interpolation parameters through cross-validation; Combined with the heat conduction equation of the immersion energy storage device, such as Fourier's law, and using the temperature data of the distributed optical fiber through the Kalman filter algorithm to correct the model parameters in real time, to correct the interpolation results and ensure that they conform to the actual heat diffusion law, finally combined with the finite element or finite volume method to solve the three-dimensional temperature field, generate the actual three-dimensional temperature field, and obtain the actual three-dimensional temperature field data. .

[0012] According to the above technical solution, in step S3, the digital processing of the actual three-dimensional temperature field and the predicted three-dimensional temperature field includes the following steps: S3-1. Establishing a three-dimensional rectangular coordinate system on the actual three-dimensional temperature field and the predicted three-dimensional temperature field model, and assigning a coordinate value to each coordinate point; S3-2, slice the actual 3D temperature field and the predicted 3D temperature field, that is, select a plane in the 3D space, for example: Plane, establish the corresponding plane rectangular coordinate system, project the actual three-dimensional temperature field and the predicted three-dimensional temperature field onto the same selected plane, and obtain the actual two-dimensional temperature distribution function and predict the two-dimensional temperature distribution function ; S3-3. Solve the target temperature based on the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function, that is, for the target temperature C, solve the equations and , the solution set of the equation is The isotherm on the plane where the temperature is equal to C is expressed as an area function, which is expressed by In the actual three-dimensional temperature field, The actual isothermal region function on the plane is given by In the predicted three-dimensional temperature field, The predicted isothermal region function on the plane, where n represents the The nth isothermal region function on the plane; The actual isothermal region functions are summarized and sorted out to obtain the actual isothermal region function sets and the actual isothermal region function set ; According to the above technical solution, in step S4, the area and perimeter of the actual isothermal region function and the predicted isothermal region function are calculated based on the basic geometric properties of the isothermal region function; When the difference between the area data or perimeter data of a certain region in the actual three-dimensional temperature field and the corresponding area data or perimeter data in the predicted three-dimensional temperature field exceeds the set threshold, it is determined that the data monitoring unit is abnormal. If not, it is determined that the immersion energy storage device is abnormal.

[0013] A monitoring system for an immersive user-side energy storage device includes a storage database, a data retrieval unit, a model training module, a data monitoring unit, an abnormality determination unit, a temperature field construction unit, a digital processing module, and a comparison and analysis module; The storage database is used to store monitoring data of the submerged energy storage device; the data retrieval unit is used to retrieve historical monitoring data from the storage database; the model training module is used to train the model based on the retrieved historical monitoring data to obtain a feedback verification model; the data monitoring unit is used to collect real-time monitoring data of the submerged energy storage device; the abnormality judgment unit is used to judge whether there is an abnormality in the real-time monitoring data; the temperature field construction unit is used to construct the actual three-dimensional temperature field of the submerged energy storage device based on the real-time monitoring data; the feedback verification model generates a predicted three-dimensional temperature field of the submerged energy storage device based on the real-time monitoring data; the digital processing module is used to digitize the actual three-dimensional temperature field and the predicted three-dimensional temperature field to obtain the actual isothermal area function and the predicted isothermal area function; the comparison analysis module is used to perform similarity comparison between the actual isothermal area function and the predicted isothermal area function, and output the comparison result.

[0014] According to the above technical solution, the digital processing module includes a coordinate system establishment unit, a temperature field slicing unit and a function generation unit; The coordinate system establishment unit is used to establish a three-dimensional rectangular coordinate system on the actual three-dimensional temperature field and the predicted three-dimensional temperature field; the temperature field slicing unit is used to slice the actual three-dimensional temperature field and the predicted three-dimensional temperature field, and map them according to the slicing plane to obtain the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function; the function generation unit solves the target temperature based on the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function to obtain the actual isothermal area function and the predicted isothermal area function.

[0015] According to the above technical solution, the system also includes an abnormality warning unit, which is used to determine whether the abnormality of the real-time monitoring data of the submerged energy storage device is due to an abnormality in the submerged energy storage device itself or an abnormality in the data monitoring unit based on the comparison results of the comparison analysis module, and issue a warning.

[0016] Compared with the prior art, the present invention has the following beneficial effects: the present invention trains a model using historical monitoring data of the submerged energy storage device to obtain a feedback verification model; after real-time monitoring data is collected through the data monitoring unit, if the collected real-time monitoring data is judged to be abnormal according to a set threshold, a predicted three-dimensional temperature field is generated based on the real-time monitoring data through the feedback verification model, an actual three-dimensional temperature field is generated through the temperature field construction unit, and subsequent digital processing and comparative analysis are used to verify and determine whether the abnormality in the collected real-time monitoring data is due to an abnormality in the data monitoring unit or the submerged energy storage device itself. This allows further abnormality diagnosis to be performed and the cause of the abnormality to be determined when an abnormality occurs in the real-time monitoring data, thereby avoiding the redundant design of the data monitoring unit, saving hardware costs, and improving the accuracy of submerged energy storage device monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Schematic diagram of the logic flow of the monitoring method of the submerged user-side energy storage device of the present invention; Figure 2 Schematic diagram of the steps of the monitoring method of the submerged user-side energy storage device of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution for a monitoring method of an immersion-type user-side energy storage device, comprising the following steps: S1. Use the data retrieval unit to retrieve historical monitoring data from the storage database of the immersion energy storage device, and divide the retrieved historical monitoring data into data sets. For example, the most recent 1,000 sets of historical monitoring data are retrieved, 70% of the historical monitoring data are divided into a training set, 20% of the historical monitoring data are divided into a validation set, and 10% of the historical monitoring data are divided into a test set. Specifically, the retrieved historical monitoring data is normal monitoring data of the energy storage device, because abnormal monitoring data will affect the output results after model training.

[0020] In this embodiment, any set of historical monitoring data includes first monitoring data and second monitoring data, wherein the first monitoring data is the three-dimensional temperature field distribution data of the immersion energy storage device. Specifically, temperature data is collected through distributed optical fibers. According to the physical layout path of the distributed optical fibers, a mapping relationship between the distributed optical fiber positions and the three-dimensional coordinates of the energy storage device is established. The temperature of the uncovered area is estimated by interpolation algorithm using one-dimensional optical fiber data points. Combined with the heat conduction equation of the energy storage device, such as Fourier's law, the interpolation result is corrected to ensure that it conforms to the actual heat diffusion law. The second monitoring data is the coolant inlet temperature data of the immersion energy storage device. , coolant outlet temperature data , coolant flow data , coolant flow rate data and ambient temperature data , data is collected through sensors.

[0021] According to the divided historical monitoring data training set, the model is trained using the model training module to obtain feedback verification model ; Specifically, the feedback verification model is constructed based on a multi-layer perceptron. The feedback verification model consists of an input layer, a hidden layer, and an output layer. The input layer is used to receive original feature data, the hidden layer is used to perform nonlinear transformation, and the output layer is used to generate a final prediction result.

[0022] In this embodiment, the second monitoring data in the training set is used as the input feature of the feedback verification model training, and the first monitoring data is used as the output feature of the feedback verification model training; The coolant inlet temperature data in the input feature , coolant outlet temperature data and ambient temperature data Normalization is performed, and the specific processing method is as follows: ; in, represents the normalized temperature data, , Indicates a certain temperature data in the second monitoring data, and Respectively represent the minimum value and maximum value of a certain type of temperature data in the second monitoring data; The coolant flow data in the input feature is and coolant flow rate data Standardization processing is carried out, and the specific processing methods are as follows: ; in, Indicates the flow data or velocity data after normalization. Indicates a flow rate data or flow velocity data in the second monitoring data, and Respectively represent the mean and standard deviation of a certain type of data in the second monitoring data; For example, a set of second monitoring data after normalization and standardization is expressed as: [0.3, 0.6, -0.2, 1.1, 0.4], which respectively correspond to the coolant inlet temperature data after normalization and standardization. , coolant outlet temperature data , coolant flow data , coolant flow rate data and ambient temperature data ; The processing of the output features includes expanding the three-dimensional temperature field distribution data into a one-dimensional vector and then performing the same normalization processing as the second monitoring data. The details will not be described in detail here. For example: three-dimensional temperature field distribution data The grid is 30*30*30, which is expanded into a one-dimensional vector with a total of 27,000 dimensions. After normalization, a 27,000-dimensional vector is formed, and each value is between [0,1], corresponding to the temperature data of any grid point after normalization.

[0023] Validating the model in feedback During the training process, after preprocessing the first monitoring data and the second monitoring data, the loss function is defined , specifically: ; in, represents the total number of samples in the second monitoring data, represents the loss function of the i-th sample; Among them, the loss function of the i-th sample is Expressed as: ; in, Represents the number of grid points in the three-dimensional temperature field distribution data, for example: M=27000, j represents the number of j-th grid points in the i-th sample, represents the weight value of the jth grid point in the first monitoring data, and assigns higher weight to the grid points close to the coolant channel. represents the predicted value of the j-th grid point, Represents the true value of the j-th grid point.

[0024] According to the above content, the multi-layer perceptron is trained, and then the trained model is verified by the validation set, and the model is tested by the test set, and finally the feedback verification model is obtained. .

[0025] The present invention trains the model through historical monitoring data and finally obtains a feedback verification model. The purpose is to verify the monitoring data through the feedback verification model when abnormal monitoring data occurs, determine the cause of the abnormality, avoid the occurrence of a single abnormality judgment of the submerged energy storage device, make the monitoring of the submerged energy storage device more complete, and ensure the normal use of the submerged energy storage device.

[0026] S2. Using a data monitoring unit to collect real-time monitoring data of the submerged energy storage device; Specifically, the collected real-time monitoring data includes: temperature data inside the immersion energy storage device collected by distributed optical fiber, coolant inlet temperature data, coolant outlet temperature data, and ambient temperature data collected by temperature sensors, and coolant flow data and coolant flow velocity data collected by flow sensors; the temperature data inside the immersion energy storage device collected by distributed optical fiber is defined as third monitoring data, the coolant inlet temperature data, coolant outlet temperature data, and ambient temperature data collected by temperature sensors, and the coolant flow data and coolant flow velocity data collected by flow sensors are defined as fourth monitoring data; Determine whether there are any abnormalities in the real-time monitoring data by setting threshold conditions; If there is no abnormality, the real-time monitoring data is loaded with the collected timestamp and stored in the storage database; If there is an abnormality, the fourth monitoring data is transmitted to the feedback verification model , validate the model through feedback Generate a predicted three-dimensional temperature field based on the fourth monitoring data, and obtain predicted three-dimensional temperature field data ; Transmitting the third monitoring data to the temperature field construction unit, and generating an actual three-dimensional temperature field through the temperature field construction unit; Specifically: According to the physical layout path of the distributed optical fiber, establish the mapping relationship between the distributed optical fiber position and the three-dimensional coordinates of the energy storage device, and record the physical position of each measurement point of the distributed optical fiber , where k represents the kth measurement point of the distributed optical fiber; Extracting discrete temperature points from temperature data collected by distributed optical fibers , inferring the temperature of uncovered areas through interpolation algorithms, such as kriging interpolation, radial basis function interpolation, or inverse distance weighting, and selecting the best interpolation parameters through cross-validation; Combined with the heat conduction equation of the immersion energy storage device, such as Fourier's law, and using the temperature data of the distributed optical fiber through the Kalman filter algorithm to correct the model parameters in real time, to correct the interpolation results and ensure that they conform to the actual heat diffusion law, finally combined with the finite element or finite volume method to solve the three-dimensional temperature field, generate the actual three-dimensional temperature field, and obtain the actual three-dimensional temperature field data. .

[0027] S3, digitally processing the generated actual three-dimensional temperature field and the predicted three-dimensional temperature field respectively through a digital processing module; Specifically, the following steps are included: S3-1. Establishing a three-dimensional rectangular coordinate system on the actual three-dimensional temperature field and the predicted three-dimensional temperature field model, and assigning a coordinate value to each coordinate point; S3-2, slice the actual 3D temperature field and the predicted 3D temperature field, that is, select a plane in the 3D space, for example: Plane, establish the corresponding plane rectangular coordinate system, project the actual three-dimensional temperature field and the predicted three-dimensional temperature field onto the same selected plane, and obtain the actual two-dimensional temperature distribution function and predict the two-dimensional temperature distribution function ; S3-3. Solve the target temperature based on the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function, that is, for the target temperature C, solve the equations and , the solution set of the equation is The isotherm on the plane where the temperature is equal to C is expressed as an area function, which is expressed by In the actual three-dimensional temperature field, The actual isothermal region function on the plane is given by In the predicted three-dimensional temperature field, The predicted isothermal region function on the plane, where n represents the The nth isothermal region function on a plane; for example, if the predicted two-dimensional temperature distribution function on a plane is , then the prediction isotherm equation is ; Then the predicted isothermal region function is ; The actual isothermal region functions are summarized and sorted out to obtain the actual isothermal region function sets and the actual isothermal region function set ; Through the above technical solution, the actual three-dimensional temperature field and the predicted three-dimensional temperature field are further digitized, and the isothermal area is processed by regional function expression, so that the comparative analysis can be carried out accurately, and the visualization and traceability of the comparative analysis results can be achieved, making the comparative analysis results more valuable for reference and reference.

[0028] S4, using a comparison analysis module to perform a similarity comparison between the actual isothermal region function and the predicted isothermal region function; Furthermore, according to the basic geometric properties of the isothermal region function, further data calculations are performed on the actual isothermal region function and the predicted isothermal region function; Specifically, the area and perimeter of the actual isothermal region function and the predicted isothermal region function are calculated respectively, and both can be solved by using the integral operation method; The area set of the region that forms the actual isothermal region function and perimeter set ; And the set of area of ​​the predicted isothermal region function and perimeter set ; Among them, s represents the area data, d represents the perimeter data, Indicates On the plane, m represents The area data or perimeter data of the mth region on the plane; When the difference between the area data or perimeter data of a certain region in the actual three-dimensional temperature field and the corresponding area data or perimeter data in the predicted three-dimensional temperature field exceeds a set threshold, it is determined that the data monitoring unit is abnormal; if not, it is determined that the immersion energy storage device is abnormal; Through the above technical solution, comparative analysis can be performed on a digital basis, so that the cause of the abnormality can be determined more accurately based on the comparison results, so as to make timely adjustments and avoid misdiagnosis of abnormalities of the submerged energy storage equipment due to abnormalities in the data monitoring unit.

[0029] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for monitoring an immersion-type user-side energy storage device, characterized in that: The following steps are involved: S1. Retrieving historical monitoring data from a storage database of the submerged energy storage device using a data retrieval unit, and training a model through a model training module based on the historical monitoring data to obtain a feedback verification model; S2. Using a data monitoring unit to collect real-time monitoring data of the submerged energy storage device. If the real-time monitoring data is abnormal, the real-time monitoring data is input into a feedback verification model, a predicted three-dimensional temperature field is generated through the feedback verification model, and an actual three-dimensional temperature field is generated through a temperature field construction unit based on the real-time monitoring data. S3, digitally processing the generated actual three-dimensional temperature field and the predicted three-dimensional temperature field respectively through a digital processing module to obtain an actual isothermal region function and a predicted isothermal region function; S4. Use the comparison analysis module to perform a similarity comparison between the actual isothermal region function and the predicted isothermal region function, and complete the verification of the abnormal real-time monitoring data based on the similarity comparison result. If the similarity comparison result meets the set threshold, it is determined that the data monitoring unit is abnormal; otherwise, it is determined that the submerged energy storage device is abnormal.

2. The monitoring method for the submerged user-side energy storage device according to claim 1, characterized in that: In step S1, the feedback verification model is constructed based on a deep neural network model, the retrieved historical monitoring data is divided into data sets, and the divided data sets are preprocessed, including normalization and standardization; Any set of historical monitoring data includes first monitoring data and second monitoring data; The second monitoring data is used as the input feature of the feedback verification model, the first monitoring data is used as the output feature of the feedback verification model, and the loss function is defined ; The model training module is based on input features, output features and loss function The deep neural network model is trained to obtain a feedback verification model.

3. The method for monitoring an immersion-type user-side energy storage device according to claim 2, wherein: The historical monitoring data includes three-dimensional temperature field distribution data of the immersion energy storage device, coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data and ambient temperature data; The three-dimensional temperature field distribution data of the immersion energy storage device is the first monitoring data; Coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data and ambient temperature data are second monitoring data; Loss Function ; in, represents the total number of samples in the second monitoring data, represents the loss function of the i-th sample; Among them, the loss function of the i-th sample is Expressed as: ； in, Represents the number of grid points in the three-dimensional temperature field distribution data, j represents the number of j-th grid points in the i-th sample, represents the weight value of the j-th grid point in the first monitoring data, represents the predicted value of the j-th grid point, Represents the true value of the j-th grid point; The retrieved historical monitoring data is divided into a training set, a validation set, and a test set; The model training module trains the deep neural network model through the training set, then verifies the trained model through the validation set, and tests the model through the test set, and finally obtains a feedback verification model.

4. The method for monitoring an immersion-type user-side energy storage device according to claim 1, wherein: In step S2, the temperature data inside the immersion energy storage device collected by the data monitoring unit is defined as third monitoring data, and the coolant inlet temperature data, coolant outlet temperature data, coolant flow data, coolant flow rate data, and ambient temperature data collected by the data monitoring unit are defined as fourth monitoring data; Determine whether there are any abnormalities in the real-time monitoring data by setting threshold conditions; If there is no abnormality, the real-time monitoring data is loaded with the collected timestamp and stored in the storage database; If there is an abnormality, the fourth monitoring data is transmitted to the feedback verification model, and the feedback verification model generates a predicted three-dimensional temperature field based on the fourth monitoring data; The third monitoring data is transmitted to the temperature field construction unit, and an actual three-dimensional temperature field is generated by the temperature field construction unit.

5. The method for monitoring the submerged user-side energy storage device according to claim 4, wherein: Temperature data inside the submerged energy storage device is collected via distributed optical fibers; The construction of the actual three-dimensional temperature field includes the following steps: S2-1. Establish a mapping relationship between the position of the distributed optical fiber and the three-dimensional coordinates of the energy storage device based on the physical layout path of the distributed optical fiber, and record the physical position of each measurement point of the distributed optical fiber; S2-2, extracting discrete temperature points from the temperature data collected by the distributed optical fiber, inferring the temperature of the uncovered area through the interpolation algorithm, and selecting the optimal interpolation parameters through cross-validation; S2-3. Combining the heat conduction equation of the immersion energy storage device and using the temperature data of the distributed optical fiber through the Kalman filter algorithm to calibrate the model parameters in real time to correct the interpolation results; S2-4. Solve the three-dimensional temperature field by combining the finite element method or the finite volume method to generate the actual three-dimensional temperature field.

6. The method for monitoring the submerged user-side energy storage device according to claim 1, characterized in that: In step S3, the digital processing of the actual three-dimensional temperature field and the predicted three-dimensional temperature field includes the following steps: S3-1. Establishing a three-dimensional rectangular coordinate system on the actual three-dimensional temperature field and the predicted three-dimensional temperature field model, and assigning a coordinate value to each coordinate point; S3-2, slicing the actual 3D temperature field and the predicted 3D temperature field, establishing corresponding plane rectangular coordinate systems, projecting the actual 3D temperature field and the predicted 3D temperature field onto the same selected plane, and obtaining an actual 2D temperature distribution function and a predicted 2D temperature distribution function, respectively; S3-3. Solve for the target temperature based on the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function to obtain the actual isothermal region function and the predicted isothermal region function.

7. The method for monitoring an immersion-type user-side energy storage device according to claim 1, wherein: In step S4, the area and perimeter of the actual isothermal region function and the predicted isothermal region function are calculated based on the basic geometric properties of the isothermal region function; When the difference between the area data or perimeter data of a certain region in the actual three-dimensional temperature field and the corresponding area data or perimeter data in the predicted three-dimensional temperature field exceeds the set threshold, it is determined that the data monitoring unit is abnormal. If not, it is determined that the immersion energy storage device is abnormal.

8. A monitoring system for an immersion user-side energy storage device for executing the monitoring method for an immersion user-side energy storage device according to any one of claims 1 to 7, characterized in that: It includes a storage database, a data retrieval unit, a model training module, a data monitoring unit, an abnormality determination unit, a temperature field construction unit, a digital processing module and a comparison and analysis module; The storage database is used to store monitoring data of the submerged energy storage device; the data retrieval unit is used to retrieve historical monitoring data from the storage database; the model training module is used to train the model based on the retrieved historical monitoring data to obtain a feedback verification model; the data monitoring unit is used to collect real-time monitoring data of the submerged energy storage device; the abnormality judgment unit is used to judge whether there is an abnormality in the real-time monitoring data; the temperature field construction unit is used to construct the actual three-dimensional temperature field of the submerged energy storage device based on the real-time monitoring data; the feedback verification model generates a predicted three-dimensional temperature field of the submerged energy storage device based on the real-time monitoring data; the digital processing module is used to digitize the actual three-dimensional temperature field and the predicted three-dimensional temperature field to obtain the actual isothermal area function and the predicted isothermal area function; the comparison analysis module is used to perform similarity comparison between the actual isothermal area function and the predicted isothermal area function, and output the comparison result.

9. The monitoring system for the submerged user-side energy storage device according to claim 8, characterized in that: The digital processing module includes a coordinate system establishment unit, a temperature field slicing unit and a function generation unit; The coordinate system establishment unit is used to establish a three-dimensional rectangular coordinate system on the actual three-dimensional temperature field and the predicted three-dimensional temperature field; the temperature field slicing unit is used to slice the actual three-dimensional temperature field and the predicted three-dimensional temperature field, and map them according to the slicing plane to obtain the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function; the function generation unit solves the target temperature based on the actual two-dimensional temperature distribution function and the predicted two-dimensional temperature distribution function to obtain the actual isothermal area function and the predicted isothermal area function.

10. The monitoring system for the submerged user-side energy storage device according to claim 8, characterized in that: The system also includes an abnormality warning unit, which is used to determine whether the abnormality of the real-time monitoring data of the submerged energy storage device is due to an abnormality in the submerged energy storage device itself or an abnormality in the data monitoring unit based on the comparison results of the comparison analysis module, and issue an alarm.

Images