Battery pack temperature control method and device of energy storage power station, electronic equipment and storage medium

Abstract

The application provides a battery pack temperature control method and device of an energy storage power station, electronic equipment and a storage medium, and relates to the technical field of energy storage power station thermal management. The battery pack temperature control method of the energy storage power station comprises the following steps: determining at least two target battery packs corresponding to the energy storage power station, and obtaining target temperature data sets corresponding to the at least two target battery packs respectively; obtaining, based on the target temperature data sets, an inversion temperature field corresponding to the at least two target battery packs respectively through heat source inversion, and performing cross mapping on the equivalent internal resistance ratio between the at least two target battery packs and the heat source distribution corresponding thereto respectively to obtain at least two mapping temperature fields, and fusing the inversion temperature field and the mapping temperature field to obtain an expansion temperature field corresponding to the at least two target battery packs respectively; fusing the at least two expansion temperature fields to obtain a target temperature field; and generating temperature control instructions corresponding to the at least two target battery packs based on the target temperature field.

Description

Technical Field

[0001] This application relates to the field of thermal management technology for energy storage power stations, and in particular to a method, device, electronic equipment, and storage medium for controlling the temperature of battery packs in an energy storage power station. Background Technology

[0002] With the continuous growth of electricity consumption, the installed capacity of electrochemical energy storage power stations is constantly expanding. As a key facility for smoothing fluctuations in renewable energy output and improving the grid's peak-shaving and frequency-regulating capabilities, the deployment scale of electrochemical energy storage power stations is increasing daily. Energy storage power stations are typically composed of a large number of battery packs connected in series and parallel. During charging and discharging, the battery packs generate heat due to internal electrochemical reactions and the Joule heating effect, requiring temperature control. Traditional temperature control schemes often use a limited number of temperature sensors discretely arranged on or inside the battery pack for point-based temperature measurement to construct a battery pack temperature field. The battery pack temperature control system analyzes and processes this temperature field to generate temperature control commands, thereby controlling the temperature control equipment to perform corresponding temperature adjustment operations.

[0003] However, due to limitations in sensor cost, installation space, and battery structure, the number of temperature sensors that can be installed on each battery pack is extremely limited. Typically, measurement points are only placed at a few critical locations such as the cell surface, terminals, and module gaps. This sparse distribution of measurement points leads to significant reconstruction errors in the constructed temperature field, making it difficult to accurately reflect the true temperature distribution inside the battery pack. This further weakens the reliability of the temperature field reconstruction, thereby reducing the accuracy of battery pack temperature monitoring and the timeliness of temperature control response in energy storage power stations.

[0004] Although energy storage power stations contain a large number of battery packs, the sensor arrangements for each battery pack are usually identical, with highly overlapping measurement points. This results in a significant amount of redundant information among multiple sets of data, preventing effective complementarity. How to fully utilize the temperature measurement resources of multiple battery packs in an energy storage power station, overcome the physical limitations of sparse measurement points in a single set, achieve higher-precision reconstruction of the battery pack temperature field, and thus improve the accuracy and timeliness of temperature control response, is a pressing technical problem to be solved in the field of thermal management for energy storage power stations. Summary of the Invention

[0005] To improve the accuracy of temperature monitoring and the timeliness of temperature control response for battery packs in energy storage power stations, this application provides a method, device, electronic equipment, and storage medium for temperature control of battery packs in energy storage power stations.

[0006] This application provides a battery pack temperature control method for an energy storage power station, which adopts the following technical solution: A battery pack temperature control method for an energy storage power station includes: determining at least two target battery packs corresponding to the energy storage power station, and acquiring target temperature datasets corresponding to the at least two target battery packs respectively, wherein the locations of temperature sensors installed on the at least two target battery packs are staggered; based on the target temperature datasets, obtaining inversion temperature fields corresponding to the at least two target battery packs respectively through heat source inversion, and performing cross-mapping based on the determined equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields; fusing the inversion temperature fields and the mapped temperature fields to obtain extended temperature fields corresponding to the at least two target battery packs respectively; fusing the at least two extended temperature fields to obtain the target temperature field; and generating temperature control commands corresponding to the at least two target battery packs based on the target temperature fields.

[0007] According to some embodiments, the above-mentioned determination of at least two target battery packs corresponding to the energy storage power station and acquisition of target temperature datasets corresponding to at least two target battery packs respectively includes: acquiring equipment information and operating condition information corresponding to multiple battery packs corresponding to the energy storage power station; determining the charge and discharge frequencies corresponding to multiple battery packs based on the equipment information; determining the degradation amount corresponding to multiple battery packs based on the charge and discharge frequencies and a preset battery degradation dataset; selecting multiple preliminary battery packs from multiple battery packs based on multiple degradation amounts; and performing secondary screening on the multiple preliminary battery packs according to the operating condition information to obtain at least two target battery packs and acquire target temperature datasets corresponding to at least two target battery packs respectively.

[0008] According to some embodiments, the aforementioned operating condition information includes the battery pack's operating current, operating voltage, and ambient temperature. The process of performing secondary screening on multiple preliminary battery packs based on the operating condition information to obtain at least two target battery packs, and acquiring target temperature datasets corresponding to each of the at least two target battery packs, includes: using ambient temperature to select multiple candidate battery packs at the same ambient temperature from the multiple preliminary battery packs; and based on operating current and operating voltage, selecting at least two target battery packs at the same operating current and operating voltage from the multiple candidate battery packs, and acquiring target temperature datasets corresponding to each of the at least two target battery packs.

[0009] According to some embodiments, the above-mentioned method of obtaining the inversion temperature fields corresponding to at least two target battery packs based on the target temperature dataset and through heat source inversion includes: inputting the target temperature dataset into a preset heat source inversion model to obtain the heat source distribution corresponding to at least two target battery packs, wherein the preset heat source inversion model is an artificial neural network model or a physical information neural network model; substituting the heat source distribution into a preset heat conduction forward problem model for solution to construct the inversion temperature fields corresponding to at least two target battery packs.

[0010] According to some embodiments, the above-mentioned cross-mapping based on the determined equivalent internal resistance ratio between at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields includes: determining the equivalent internal resistance of at least two target battery packs based on the historical steady-state operating data of at least two target battery packs; calculating the ratio between the equivalent internal resistances of at least two target battery packs to obtain the equivalent internal resistance ratio; and using the equivalent internal resistance ratio as a scaling factor, cross-mapping the heat source distributions of at least two target battery packs to the preset heat conduction models corresponding to at least two target battery packs to obtain the mapped temperature fields corresponding to at least two target battery packs.

[0011] According to some embodiments, the above-mentioned fusion of the inverted temperature field and the mapped temperature field to obtain the extended temperature fields corresponding to at least two target battery packs further includes: obtaining the actual measurement point temperature and the corresponding mapped predicted temperature of at least two target battery packs; calculating the absolute deviation value between the mapped predicted temperature and the actual measurement point temperature; and retaining the at least two extended temperature fields corresponding to them when at least two absolute deviation values ​​are less than a preset absolute difference value.

[0012] According to some embodiments, the above-mentioned process of fusing at least two extended temperature fields to obtain a target temperature field includes: acquiring measured location point information, mapped location point information, and inverted location point information corresponding to at least two extended temperature fields respectively; determining the data confidence level corresponding to each of the measured location point information, mapped location point information, and inverted location point information; and performing weighted fusion of at least two extended temperature fields based on the data confidence level to obtain the target temperature field.

[0013] According to some embodiments, the above-mentioned determination of the data confidence levels corresponding to the measured location point information, the mapped location point information, and the inverted location point information includes: determining the first uncertainty information corresponding to the measured location point information, the second uncertainty information corresponding to the mapped location point information, and the third uncertainty information corresponding to the inverted location point information; determining the first confidence level corresponding to the measured location point information based on the first uncertainty information; determining the second confidence level corresponding to the mapped location point information based on the second uncertainty information; and determining the third confidence level corresponding to the inverted location point information based on the third uncertainty information, wherein the first confidence level is higher than the second confidence level, and the second confidence level is higher than the third confidence level.

[0014] According to some embodiments, after fusing at least two extended temperature fields to obtain a target temperature field, the method further includes: extracting the temperatures at multiple measured locations in the target temperature field and the temperatures at multiple actual measurement points corresponding to at least two target battery packs; calculating the differences between the temperatures at the multiple measured locations and the temperatures at the multiple actual measurement points to obtain multiple residual information; calculating the mean of the multiple residual information to obtain mean residual information; and shifting the target temperature field as a whole by the mean residual information to obtain a corrected target temperature field.

[0015] According to some embodiments, after shifting the target temperature field as a whole to the mean residual information to obtain the corrected target temperature field, the above-mentioned battery pack temperature control method of the energy storage power station further includes: using a Kalman filter algorithm or a wavelet denoising algorithm to smooth the corrected target temperature field in order to suppress local abnormal fluctuations.

[0016] According to some embodiments, the above-mentioned generation of temperature control commands corresponding to at least two target battery packs based on the target temperature field includes: determining the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend inside at least two battery packs based on the temperature distribution and change trend in the target temperature field; and generating temperature control commands based on the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend.

[0017] According to some embodiments, the target temperature dataset mentioned above includes temperature data collected within a preset time window, spatial coordinate information of the measuring points corresponding to the temperature sensors, and collection timing information.

[0018] This application provides a battery pack temperature control device for an energy storage power station, which adopts the following technical solution: A battery pack temperature control device for an energy storage power station includes: a battery pack determination module, an extended temperature field construction module, a target temperature field construction module, and an instruction generation module. The battery pack determination module is used to determine at least two target battery packs corresponding to the energy storage power station and acquire target temperature datasets corresponding to the at least two target battery packs, wherein the locations of the temperature sensors installed on the at least two target battery packs are staggered. The extended temperature field construction module is used to obtain inverted temperature fields corresponding to the at least two target battery packs based on the target temperature datasets and through heat source inversion, and to perform cross-mapping based on the equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields, and to fuse the inverted temperature fields and mapped temperature fields to obtain extended temperature fields corresponding to the at least two target battery packs. The target temperature field construction module is used to fuse the at least two extended temperature fields to obtain a target temperature field. The instruction generation module is used to generate temperature control instructions corresponding to the at least two target battery packs based on the target temperature fields.

[0019] According to some embodiments, the battery pack determination module described above is specifically used for: acquiring equipment information and operating condition information corresponding to multiple battery packs corresponding to the energy storage power station; determining the charging and discharging frequencies corresponding to the multiple battery packs based on the equipment information; determining the degradation amount corresponding to the multiple battery packs based on the charging and discharging frequencies and a preset battery degradation dataset; selecting multiple preliminary battery packs from the multiple battery packs based on the multiple degradation amounts; and performing secondary screening on the multiple preliminary battery packs according to the operating condition information to obtain at least two target battery packs, and acquiring target temperature datasets corresponding to the at least two target battery packs.

[0020] According to some embodiments, the above-mentioned operating condition information includes the battery pack's operating current, operating voltage, and ambient temperature. The battery pack determination module is specifically used to: use the ambient temperature to select multiple candidate battery packs that are at the same ambient temperature from multiple preliminary battery packs; based on the operating current and operating voltage, select at least two target battery packs that are at the same operating current and operating voltage from multiple candidate battery packs, and obtain target temperature datasets corresponding to at least two target battery packs respectively.

[0021] According to some embodiments, the above-mentioned extended temperature field construction module is specifically used to: input the target temperature dataset into a preset heat source inversion model to obtain the heat source distribution corresponding to at least two target battery packs respectively, wherein the preset heat source inversion model is an artificial neural network model or a physical information neural network model; substitute the heat source distribution into a preset heat conduction forward problem model for solution, and construct the inversion temperature field corresponding to at least two target battery packs respectively.

[0022] According to some embodiments, the above-mentioned extended temperature field construction module is specifically used to: determine the equivalent internal resistance of at least two target battery packs based on the historical steady-state operating data of at least two target battery packs respectively; calculate the ratio between the equivalent internal resistances of at least two target battery packs respectively to obtain the equivalent internal resistance ratio; and cross-map the heat source distribution of at least two target battery packs to the preset heat conduction model corresponding to at least two target battery packs using the equivalent internal resistance ratio as a scaling factor to obtain the mapped temperature field corresponding to at least two target battery packs respectively.

[0023] According to some embodiments, the above-mentioned extended temperature field construction module is further used to: obtain the actual measurement point temperature and the corresponding mapped predicted temperature of at least two target battery packs respectively; calculate the absolute deviation value between the mapped predicted temperature and the actual measurement point temperature; and retain the at least two extended temperature fields corresponding to them when at least two absolute deviation values ​​are less than a preset absolute difference value.

[0024] According to some embodiments, the target temperature field construction module described above is specifically used to: acquire measured location point information, mapped location point information, and inverted location point information corresponding to at least two extended temperature fields respectively; determine the data confidence level corresponding to each of the measured location point information, mapped location point information, and inverted location point information; and perform weighted fusion on at least two extended temperature fields based on the data confidence level to obtain the target temperature field.

[0025] According to some embodiments, the target temperature field construction module described above is specifically used to: determine the first uncertainty information corresponding to the measured location point information, the second uncertainty information corresponding to the mapped location point information, and the third uncertainty information corresponding to the inverted location point information; determine the first confidence level corresponding to the measured location point information based on the first uncertainty information; determine the second confidence level corresponding to the mapped location point information based on the second uncertainty information; and determine the third confidence level corresponding to the inverted location point information based on the third uncertainty information, wherein the first confidence level is higher than the second confidence level, and the second confidence level is higher than the third confidence level.

[0026] According to some embodiments, after fusing at least two extended temperature fields to obtain the target temperature field, the battery pack temperature control device of the energy storage power station further includes: a data extraction module, a residual determination module, a mean residual determination module, and a temperature field correction module. The data extraction module is used to extract the temperatures at multiple measured locations in the target temperature field and the temperatures at multiple actual measurement points corresponding to at least two target battery packs. The residual determination module is used to calculate the difference between the temperatures at multiple measured locations and the temperatures at multiple actual measurement points to obtain multiple residual information. The mean residual determination module is used to calculate the mean of the multiple residual information to obtain mean residual information. The temperature field correction module is used to shift the target temperature field as a whole by the mean residual information to obtain a corrected target temperature field.

[0027] According to some embodiments, after shifting the target temperature field as a whole to the mean residual information to obtain the corrected target temperature field, the battery pack temperature control device of the energy storage power station further includes: a temperature field processing module, wherein the temperature field processing module is used to smooth the corrected target temperature field using a Kalman filter algorithm or a wavelet denoising algorithm to suppress local abnormal fluctuations.

[0028] According to some embodiments, the above-mentioned instruction generation module is used to determine the location of temperature hotspots, temperature gradient distribution and overall temperature rise trend inside at least two battery packs based on the temperature distribution and change trend in the target temperature field; and to generate temperature control instructions based on the location of temperature hotspots, temperature gradient distribution and overall temperature rise trend.

[0029] According to some embodiments, the target temperature dataset mentioned above includes temperature data collected within a preset time window, spatial coordinate information of the measuring points corresponding to the temperature sensors, and collection timing information.

[0030] This application provides an electronic device that adopts the following technical solution: An electronic device comprising: processor; The memory stores a computer program, which, when executed by the processor, causes the processor to perform the battery pack temperature control method of the aforementioned energy storage power station.

[0031] This application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the aforementioned battery pack temperature control method for an energy storage power station.

[0032] This application provides a battery pack temperature control system, which adopts the following technical solution: A battery pack temperature control system is provided to implement the aforementioned battery pack temperature control method in an energy storage power station. The system includes: a temperature control data acquisition module for acquiring temperature data from at least two target battery packs in the energy storage power station; a main control module connected to the temperature data acquisition module for analyzing and processing the received temperature data and generating temperature control commands based on the analysis results; and an execution module connected to the main control module for receiving the temperature control commands and controlling the temperature control equipment in the energy storage power station to perform corresponding temperature adjustment operations.

[0033] According to some embodiments, the main control module mentioned above includes: a data receiving unit connected to the temperature control data acquisition module for receiving temperature data; a temperature field construction unit connected to the data receiving unit for reconstructing the target temperature field corresponding to the battery pack in the energy storage power station based on the temperature data; and a decision unit connected to the temperature field construction unit for analyzing and processing the target temperature field and generating temperature control commands based on the analysis and processing results.

[0034] According to the above embodiments provided in this application, by screening at least two target battery packs with complementary temperature measurement characteristics, an extended temperature field is constructed based on heat source inversion and cross-pack mapping. After confidence-weighted fusion and residual correction, a high-precision target temperature field is obtained. Finally, a precise temperature control command is generated based on the target temperature field, thereby improving the accuracy of temperature field construction and thus improving the accuracy of battery pack temperature monitoring and the timeliness of temperature control response in energy storage power stations. Attached Figure Description

[0035] Figure 1This is a block diagram of the battery pack temperature control method of the energy storage power station according to an embodiment of this application; Figure 2 This is a block diagram of the battery pack temperature control device of the energy storage power station according to an embodiment of this application; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of this application.

[0036] Explanation of reference numerals in the attached figures: 20: Battery pack temperature control device for energy storage power station; 201: Battery pack determination module; 202: Extended temperature field construction module; 203: Target temperature field construction module; 204: Instruction generation module; 30: Electronic equipment; 301: Processor; 302: Bus; 303: Memory; 304: Transceiver. Detailed Implementation

[0037] The following is in conjunction with the appendix Figures 1-3 This application will be described in further detail.

[0038] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] This application provides a battery pack temperature control method for an energy storage power station, which can be executed by an electronic device. The electronic device can be a server, which can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed device, or a cloud server that provides cloud computing services. The server can be installed on the ground power station operation and maintenance terminal.

[0040] Reference Figure 1 A battery pack temperature control method for an energy storage power station includes steps S101, S102, S103, and S104, wherein... S101, determine at least two target battery packs corresponding to the energy storage power station, and obtain the target temperature datasets corresponding to the at least two target battery packs respectively.

[0041] In some embodiments, at least two target temperature datasets are acquired by corresponding temperature sensors, and when at least two target battery packs are constructed using virtual models and the virtual models overlap, the locations of the temperature sensors installed on the at least two target battery packs are staggered. The target temperature dataset is a set of temperature data collected within a preset time window that reflects the real-time thermal state of the corresponding battery pack. The length of the preset time window can be dynamically adjusted according to the thermal response characteristics of the battery pack. The target temperature dataset contains temperature information as well as spatial coordinate information and acquisition time sequence information of each measuring point.

[0042] All battery packs in the energy storage power station are equipped with temperature sensors. The temperature sensors are installed in key heat-sensitive areas such as the surface of the battery cells, the terminals, and the gaps between modules. In some cases, the temperature sensors for at least two target battery packs are staggered. For example, in the case of at least two target battery packs including a first target battery pack and a second target battery pack, the temperature sensors for the first target battery pack are installed on the first, third, and fifth sub-cells, while the temperature sensors for the second target battery pack are installed on the second, fourth, and sixth sub-cells.

[0043] Energy storage power stations typically contain dozens to hundreds of battery packs. Not all battery packs are suitable as a reference object for temperature field construction. Therefore, it is necessary to select representative target battery packs. Then, electronic equipment obtains the equipment information and operating condition information corresponding to multiple battery packs in the energy storage power station, and uses preset screening rules to determine at least two target battery packs based on the equipment information and operating condition information.

[0044] S102, based on the target temperature dataset, and by inverting the heat source, obtain the inversion temperature fields corresponding to at least two target battery packs respectively, and perform cross mapping based on the determined equivalent internal resistance ratio between at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields, and fuse the inversion temperature fields and mapped temperature fields to obtain the extended temperature fields corresponding to at least two target battery packs respectively.

[0045] In some embodiments, the target temperature dataset includes temperature data collected within a preset time window, spatial coordinate information of the measurement points corresponding to the temperature sensor, and acquisition time sequence information; the extended temperature field is a virtual field that maps discrete temperature measurement point data into a continuous spatial temperature distribution. The extended temperature field not only covers the actual measurement points of the sensor, but also derives temperature estimates for non-measurement point locations through a physical model.

[0046] The electronic device takes the target temperature dataset as input, uses a pre-set heat source inversion model, and combines the thermal property parameters and boundary conditions of the battery pack to invert and calculate the heat source distribution in the non-measuring point area, thereby constructing the inversion temperature fields corresponding to at least two target battery packs. Subsequently, the electronic device uses the equivalent internal resistance ratio between different target battery packs to cross-map the heat source distribution to obtain the mapped temperature fields corresponding to at least two target battery packs. Then, the electronic device fuses the mapped temperature fields and inversion temperature fields corresponding to at least two target battery packs to obtain the extended temperature fields corresponding to at least two target battery packs.

[0047] S103, at least two extended temperature fields are fused to obtain the target temperature field.

[0048] In some embodiments, since the extended temperature field corresponding to each target battery pack is constructed based on its own measured data and thermal model, the extended temperature fields of different target battery packs differ in terms of spatial coverage and data accuracy. Therefore, the electronic device needs to perform weighted fusion of each extended temperature field to eliminate local biases and improve the spatial continuity and accuracy of the overall temperature field. In the process of fusing at least two extended temperature fields, the electronic device performs weighted fusion based on the data source and corresponding data confidence of each location point of the extended temperature field corresponding to at least two target battery packs, thereby obtaining the globally optimal target temperature field. Among these, sensor measured points are given higher weights, while mapped location points are given relatively lower weights, and inverted location points are given even lower weights.

[0049] S104, based on the target temperature field, generates temperature control commands corresponding to at least two target battery packs.

[0050] In some embodiments, the electronic device determines the temperature hotspots, temperature gradient distribution, and overall temperature rise trend inside the battery pack based on the temperature distribution and trend at various points in the target temperature field. Based on this, it generates targeted temperature control commands and sends these commands to the battery management system of the energy storage power station. This allows the battery management system to dynamically adjust the operating parameters of the cooling system according to the temperature control commands, achieving precise temperature control of the energy storage power station. By selecting multiple target battery packs with complementary temperature measurement characteristics, constructing an extended temperature field based on heat source inversion and cross-packet mapping, and obtaining a high-precision target temperature field after confidence-weighted fusion and residual correction, a precise temperature control command is finally generated. This improves the accuracy of temperature field construction, thereby enhancing the accuracy of battery pack temperature monitoring and the timeliness of temperature control response in the energy storage power station.

[0051] Step S101: Determine at least two target battery packs corresponding to the energy storage power station, and obtain target temperature datasets corresponding to the at least two target battery packs respectively, including: obtaining equipment information and operating condition information corresponding to multiple battery packs corresponding to the energy storage power station; determining the charge and discharge frequencies corresponding to multiple battery packs based on the equipment information; determining the degradation amount corresponding to multiple battery packs based on the charge and discharge frequencies and a preset battery degradation dataset; selecting multiple preliminary battery packs from multiple battery packs based on multiple degradation amounts; and performing secondary screening on the multiple preliminary battery packs according to the operating condition information to obtain at least two target battery packs, and obtaining target temperature datasets corresponding to the at least two target battery packs respectively.

[0052] In some embodiments, device information may include static parameters such as battery pack model, capacity, internal resistance, installation location, and charge / discharge record information; operating condition information may include dynamic parameters such as current charge / discharge status, ambient temperature, and historical operating data.

[0053] The electronic device generates an information acquisition command and sends it to the battery temperature control system of the energy storage power station. The battery temperature control system responds to the command by sending the device information and operating condition information corresponding to each of the multiple battery packs to the electronic device. Subsequently, the electronic device analyzes the device information to obtain the charge / discharge records for each battery pack, and calculates the charge / discharge frequency for each battery pack based on these records.

[0054] Next, the electronic device retrieves a preset battery degradation dataset and compares the charge / discharge frequency with the preset battery degradation dataset to determine the corresponding degradation amount. Subsequently, the electronic device uses the degradation amount as a screening criterion to initially screen multiple battery packs with the same thermal risk or typical degradation characteristics from multiple battery packs.

[0055] Subsequently, the electronic device performs a secondary screening of multiple preliminary battery packs based on the operating current, operating voltage, and ambient temperature information contained in the operating condition information, and obtains at least two target battery packs. Then, the electronic device generates an information acquisition instruction and sends the information acquisition instruction to the battery temperature control system to obtain the target temperature datasets corresponding to the at least two target battery packs.

[0056] In some embodiments, when the operating condition information includes the battery pack's operating current, operating voltage, and ambient temperature, a secondary screening is performed on multiple preliminary battery packs based on the operating condition information to obtain at least two target battery packs, and target temperature datasets corresponding to the at least two target battery packs are obtained respectively. This includes: using the ambient temperature to screen multiple candidate battery packs that are at the same ambient temperature from multiple battery packs; and based on the operating current and operating voltage, screening at least two target battery packs that are at the same operating current and operating voltage from multiple candidate battery packs, and obtaining target temperature datasets corresponding to the at least two target battery packs respectively.

[0057] In some embodiments, the electronic device first filters out multiple candidate battery packs at the same ambient temperature to ensure that the multiple candidate battery packs have the same thermal boundary conditions, thereby eliminating the interference of ambient temperature differences on the screening results. Subsequently, the electronic device filters out at least two target battery packs at the same electrical load state based on the operating current and operating voltage, and obtains the target temperature datasets corresponding to at least two target battery packs respectively. Thus, through a secondary screening mechanism, and using temperature and electrical load as boundary conditions, it avoids temperature assessment deviations caused by individual differences, and improves the accuracy of target temperature field construction and the pertinence of temperature control strategies.

[0058] Step S102, based on the target temperature dataset, and by heat source inversion, obtain the inversion temperature fields corresponding to at least two target battery packs respectively, including: inputting the target temperature dataset into the preset heat source inversion model to obtain the heat source distribution corresponding to at least two target battery packs respectively; substituting the heat source distribution into the preset heat conduction forward problem model for solution, and constructing the inversion temperature fields corresponding to at least two target battery packs respectively.

[0059] In some embodiments, the preset heat source inversion model refers to a mathematical model of the spatial distribution of heat sources inside the battery pack, obtained by solving the inverse heat conduction problem based on temperature observation data from the surface or finite internal measurement points of the battery pack. This model can be constructed based on the heat conduction equation and optimization algorithm. The heat source distribution is the spatial distribution of heat generated inside the battery pack due to electrochemical reactions and the Joule effect. The inverted temperature field is the battery pack temperature distribution field obtained by solving the forward heat conduction problem (i.e., finding the temperature distribution given the heat source distribution) based on the internal heat source distribution obtained from the heat source inversion model. The mapped temperature field is the temperature distribution field obtained by mapping the heat source distribution of one target battery pack to the preset heat conduction model of another target battery pack based on the equivalent internal resistance ratio.

[0060] The electronic device takes the target temperature dataset as input and uses a preset heat source inversion model to deduce the heat source distribution inside the battery pack. Then, it obtains the heat source distribution corresponding to at least two target battery packs. The preset inversion model can be an artificial neural network model, a physical information neural network model, etc. Subsequently, the electronic device substitutes the heat source distribution into the heat conduction forward problem model. The heat conduction problem model can be a multi-dimensional heat transfer model, an equivalent thermal network model, etc., thereby accurately reconstructing the three-dimensional temperature distribution inside the battery pack and solving for the inversion temperature field corresponding to each target battery pack.

[0061] In some embodiments, the preset heat source inversion model can be an artificial neural network (ANN) model, a physical information neural network (PINN) model, or a genetic algorithm inversion model, etc.

[0062] Taking the Physical Information Neural Network (PINN) model as an example, this model uses the heat conduction equation of the target battery pack as a physical constraint embedded in the loss function of the neural network. It takes the temperature data collected by a limited number of temperature sensors arranged on the target battery pack as input, and solves the spatial distribution q(x, y, z) of the heat source inside the target battery pack through forward propagation and backward iterative optimization. That is, the heat generation rate distribution per unit volume (unit: W / m³). The temperature data is spatiotemporal temperature data containing spatial coordinates (x, y, z) and time t.

[0063] After obtaining the heat source distribution, it is substituted into a preset forward thermal conduction problem model for solution to obtain the temperature distribution inside the battery pack, i.e., the inverted temperature field. The preset forward thermal conduction problem model can be a multidimensional heat transfer model (such as a three-dimensional thermal conduction finite element model), an equivalent thermal path model (ETN), or a computational fluid dynamics (CFD) model, etc.

[0064] The general form of the three-dimensional heat conduction equation is:

[0065] Where ρ is the battery density (kg / m³), and c p Specific heat capacity at constant pressure (J / (kg)) K), k x k y k z Thermal conductivity (W / (m)) in the x, y, and z directions, respectively. K), q is the internal heat source intensity (W / m³), T is the temperature (K), and t is the time (s).

[0066] By solving the above equations, the temperature values ​​at various points inside the battery pack can be obtained, i.e., the inverted temperature field T.inv (x, y, z).

[0067] In some embodiments, spatial distribution of heat sources Parameterization is performed by representing the internal heat sources of the target battery pack as functions of spatial coordinates. ,in, Let be the parameter vector to be solved. It can be parameterized using Gaussian process regression or radial basis function neural networks, i.e.:

[0068] in, Let j be the j-th basis function (such as the Gaussian kernel function or radial basis function). represents the corresponding coefficients to be solved, and M is the number of basis functions.

[0069] The Physical Information Neural Network (PINN) iteratively optimizes the solution of the parameter vector by minimizing a loss function that includes the residuals of the heat conduction equation and the fitting error of the measured temperature data. Thus, the spatial distribution of heat sources can be determined. .

[0070] In some embodiments, cross-mapping is performed based on the determined equivalent internal resistance ratio between at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields. This includes: determining the equivalent internal resistance of at least two target battery packs based on the historical steady-state operating data of at least two target battery packs; calculating the ratio between the equivalent internal resistances of at least two target battery packs to obtain the equivalent internal resistance ratio; and using the equivalent internal resistance ratio as a scaling factor, cross-mapping the heat source distributions of at least two target battery packs to the preset heat conduction models corresponding to at least two target battery packs to obtain the mapped temperature fields corresponding to at least two target battery packs.

[0071] In some embodiments, the equivalent internal resistance is the equivalent resistance value when the battery pack as a whole is equivalent to a lumped parameter circuit model; the equivalent internal resistance ratio is the ratio between the equivalent internal resistance of the second target battery pack and the equivalent internal resistance of the first target battery pack among at least two target battery packs, and the equivalent internal resistance ratio is used to characterize the difference in heat source intensity caused by the difference in internal resistance between different battery packs.

[0072] The electronic device generates an information acquisition command and sends it to the storage module of the battery temperature control system. The storage module responds to the information acquisition command and sends the historical steady-state operating data corresponding to at least two target battery packs to the electronic device. Based on the acquired historical steady-state operating data corresponding to each target battery pack, the electronic device determines the equivalent internal resistance corresponding to each target battery pack and calculates the ratio of the equivalent internal resistances to obtain the equivalent internal resistance ratio. The historical steady-state operating data refers to the voltage and current data of the battery pack when it reaches thermal and electrical steady state under constant charging and discharging current.

[0073] Subsequently, the electronic device uses the equivalent internal resistance ratio as a scaling factor to scale and correct the heat source distribution of the first target battery pack among the at least two target battery packs. This modified heat source distribution is then mapped onto a preset heat conduction model of the second target battery pack among the at least two target battery packs for solution, yielding the mapped temperature field. The physical principle is that the Joule heating rate of a battery pack is proportional to its internal resistance, i.e., P = I²R. For battery packs with the same structure and operating current, their spatial distribution of heat generation is similar, but the heat generation intensity is proportional to the internal resistance. Therefore, the heat source distribution can be scaled using the internal resistance ratio, mapping the heat source information of one battery pack onto another.

[0074] In some embodiments, in step S102, the inverted temperature field and the mapped temperature field are fused to obtain extended temperature fields corresponding to at least two target battery packs respectively. The method further includes: obtaining the actual measurement point temperature and the corresponding mapped predicted temperature of at least two target battery packs respectively; calculating the absolute deviation value between the mapped predicted temperature and the actual measurement point temperature; and retaining the at least two extended temperature fields corresponding to them if at least two absolute deviation values ​​are less than a preset absolute difference value.

[0075] In some embodiments, after obtaining at least two extended temperature fields, the electronic device can verify the reliability of the extended temperature fields by temperature comparison verification to ensure their accuracy. That is, the electronic device obtains the actual measurement point temperature corresponding to at least two target battery packs, and at the same time, obtains the mapped predicted temperature corresponding to the location point of the actual measurement point temperature of each target battery pack. The electronic device calculates the absolute difference between the actual measurement point temperature and the mapped predicted temperature that have a positional correspondence to obtain an absolute deviation value. Subsequently, the electronic device compares the absolute deviation value with a preset absolute difference value. If it is determined that the absolute deviation value is less than the preset absolute difference value, it indicates that the extended temperature field has a high degree of confidence and can be used as a reliable basis for subsequent temperature control strategy formulation. Then, at least two extended temperature fields are retained.

[0076] In some embodiments, to fuse the inverted temperature field and the mapped temperature field to determine the extended temperature field corresponding to each target battery pack, the inverted temperature field and the mapped temperature field can be weighted and averaged to obtain the extended temperature field. For example:

[0077] Here, α is the weighting coefficient, ranging from 0 to 1. This weighting coefficient can be subjectively set by technicians based on the accuracy of the inversion model and the mapping model, respectively. For example, when the accuracy of the inversion model is high, α can be set to 0.7, that is, the weight of the inversion temperature field is 0.7, and the weight of the mapping temperature field is 0.3.

[0078] In some embodiments, the actual measurement point temperature corresponding to each target battery pack is obtained, along with the mapped predicted temperature at the corresponding location in the mapped temperature field. The absolute deviation between the mapped predicted temperature and the actual measurement point temperature is calculated.

[0079] Among them, (x) i , y i , z i Let T be the coordinates of the i-th measured point. map To map the temperature value of the temperature field at that point, T meas This represents the actual temperature at the measurement point.

[0080] After calculating the absolute deviation values ​​for all measured points, the maximum or average value is compared with a preset absolute difference. If the absolute deviation value is less than the preset absolute difference (e.g., the preset absolute difference is 2℃), it indicates that the mapped temperature field has high confidence, and the corresponding extended temperature field can be retained and participate in subsequent fusion. Conversely, if the deviation exceeds the preset threshold, it is necessary to check the mapping model parameters or reselect the target battery pack.

[0081] Step S103 involves fusing at least two extended temperature fields to obtain a target temperature field, including: acquiring measured location point information, mapped location point information, and inverted location point information corresponding to at least two extended temperature fields respectively; determining the data confidence level corresponding to each of the measured location point information, mapped location point information, and inverted location point information; and performing weighted fusion of at least two extended temperature fields based on the data confidence level to obtain the target temperature field.

[0082] In some embodiments, the extended temperature field contains different types of temperature information, such as actual temperature information collected by the acquisition terminal, temperature information obtained by inversion from measured data, and mapped temperature information based on equivalent internal resistance correction. Different types of temperature information have different spatial resolutions and confidence levels. Therefore, when fusing at least two extended temperature fields, the spatial coverage and confidence levels of each data source need to be considered comprehensively.

[0083] Therefore, the electronic device evaluates the reliability weight of each data source at its corresponding spatial location based on measured location information, mapped location information, and inverted location information. The evaluation process involves assigning corresponding weight coefficients to the measured, mapped, and inverted data according to the data source type and historical error statistics of each location point. Specifically, measured data is given a higher weight, while the weight coefficients for mapped and inverted data are dynamically adjusted based on their historical error statistics. The weight coefficients of different types of temperature information are determined as the data confidence level of the corresponding location point in the extended temperature field. Subsequently, based on the data confidence level, the electronic device performs a weighted summation of the temperature data of each location point in at least two extended temperature fields, and uses the weighted summation result as the final fused temperature of that location point, thereby obtaining the target temperature field.

[0084] In some embodiments, for any point (x, y, z) in space, if the point has temperature estimates in multiple extended temperature fields, then a weighted sum is performed using the confidence levels of each temperature field at that point as weights:

[0085] Where N is the number of target battery packs (i.e., the number of extended temperature fields), C i T represents the confidence level of the i-th extended temperature field at that point. ext,i Let be the temperature value of the i-th extended temperature field at that point.

[0086] This confidence-weighted fusion strategy allows high-precision data sources (such as measured data) to contribute more to the fusion results, while low-precision data sources (such as inverted data) contribute less, thus obtaining the globally optimal target temperature field.

[0087] In some embodiments, determining the data confidence levels corresponding to the measured location point information, the mapped location point information, and the inverted location point information respectively includes: determining the first uncertainty information corresponding to the measured location point information, the second uncertainty information corresponding to the mapped location point information, and the third uncertainty information corresponding to the inverted location point information; determining the first confidence level corresponding to the measured location point information based on the first uncertainty information; determining the second confidence level corresponding to the mapped location point information based on the second uncertainty information; and determining the third confidence level corresponding to the inverted location point information based on the third uncertainty information.

[0088] In some embodiments, the first uncertainty is the deviation between the measured temperature data and the reference standard temperature, or the measurement error range determined based on the sensor's historical calibration records; the second uncertainty is the residual statistics of the mapped temperature and the measured temperature in the overlapping region, or the goodness-of-fit index of the mapping model in the local region; the third uncertainty is the root mean square error between the inverted temperature field and the measured data in the global range; the first confidence level is higher than the second confidence level, and the second confidence level is higher than the third confidence level, such as the first confidence level ranging from 0.8 to 1.0, the second confidence level ranging from 0.5 to 0.8, and the third confidence level ranging from 0.1 to 0.5.

[0089] The electronic device determines the first uncertainty of the measured location point information as the deviation between the acquired measured temperature data and the reference standard temperature, or the measurement error range determined based on the sensor's historical calibration records. It then determines the second uncertainty of the mapped location point information as the residual statistics of the acquired mapped temperature and the measured temperature in the overlapping region, or the goodness-of-fit index of the mapping model in a local region. Finally, it determines the third uncertainty of the inverted location point information as the root mean square error between the retrieved temperature field and the measured data over the global range. Subsequently, the electronic device converts the first, second, and third uncertainties into corresponding first, second, and third confidence levels, respectively, according to a preset mapping relationship between uncertainty and confidence level. The preset mapping relationship between uncertainty and confidence level is an inverse proportional function.

[0090] In some embodiments, the preset mapping relationship between uncertainty and confidence can be in the form of an inverse proportional function:

[0091] Where C is the confidence level, u is the uncertainty, and k is the proportionality coefficient.

[0092] In step S104, after fusing at least two extended temperature fields to obtain the target temperature field, the above-mentioned battery pack temperature control method for the energy storage power station further includes: extracting the temperatures at multiple measured locations in the target temperature field and the temperatures at multiple actual measurement points corresponding to at least two target battery packs; calculating the differences between the temperatures at multiple measured locations and the temperatures at multiple actual measurement points to obtain multiple residual information; calculating the mean of the multiple residual information to obtain mean residual information; and shifting the target temperature field as a whole by the mean residual information to obtain the corrected target temperature field.

[0093] In some embodiments, considering that although shifting the target temperature field as a whole to the mean residual information eliminates systematic bias, local high-frequency noise or sensor drift may still remain. Therefore, methods such as Kalman filtering or wavelet denoising algorithms can be further introduced to smooth the corrected target temperature field, so as to suppress local abnormal fluctuations and improve the spatial continuity and stability of the temperature field data. That is, the electronic device extracts the temperature of multiple measured locations and the actual measurement point temperature corresponding to at least two target battery packs from the target temperature field; then, the electronic device calculates the difference between the temperature of the measured locations with positional correspondence and the actual measurement point temperature to obtain residual information; then, the average of multiple residual information is calculated to obtain mean residual information, and the target temperature field is shifted as a whole to this mean residual information to eliminate systematic bias, thereby obtaining the final target temperature field.

[0094] In some embodiments, after shifting the target temperature field as a whole by the mean residual information to obtain the corrected target temperature field, the above-mentioned battery pack temperature control method for energy storage power stations further includes: using a Kalman filter algorithm or a wavelet denoising algorithm to smooth the corrected target temperature field in order to suppress local abnormal fluctuations.

[0095] Step S104: Based on the target temperature field, generate temperature control commands corresponding to at least two target battery packs, including: determining the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend inside at least two battery packs according to the temperature distribution and change trend in the target temperature field; and generating temperature control commands based on the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend.

[0096] In some embodiments, the electronic device analyzes and processes the temperature conditions in the target temperature field, identifies the temperature distribution and trends within the target temperature field, and determines the locations of temperature hotspots, temperature gradient distribution, and overall temperature rise trends within at least two target battery packs. Subsequently, based on these analysis results, temperature control commands are generated, such as adjusting the coolant flow rate, fan speed, or the start / stop status of the cooling unit, to precisely reduce the temperature in the hotspot areas, equalize the temperature gradient, and suppress the overall temperature rise trend. Finally, the temperature control commands are sent to the battery pack temperature control system; the battery pack temperature control system receives the temperature control commands and, based on these commands, adjusts the temperature of the cooling systems corresponding to at least two battery packs.

[0097] This application provides a battery pack temperature control device for an energy storage power station, which adopts the following technical solution: Reference Figure 2A battery pack temperature control device 20 for an energy storage power station includes: a battery pack determination module 201, an extended temperature field construction module 202, a target temperature field construction module 203, and an instruction generation module 204. The battery pack determination module 201 is used to determine at least two target battery packs corresponding to the energy storage power station and acquire target temperature datasets corresponding to the at least two target battery packs, wherein the temperature sensors installed on the at least two target battery packs are staggered. The extended temperature field construction module 202 is used to obtain inverted temperature fields corresponding to the at least two target battery packs based on the target temperature datasets and through heat source inversion, and to perform cross-mapping based on the equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields, and to fuse the inverted temperature fields and mapped temperature fields to obtain extended temperature fields corresponding to the at least two target battery packs. The target temperature field construction module 203 is used to fuse the at least two extended temperature fields to obtain a target temperature field. The instruction generation module 204 is used to generate temperature control instructions corresponding to the at least two target battery packs based on the target temperature fields.

[0098] In some embodiments, the battery pack determination module 201 described above is specifically used for: acquiring equipment information and operating condition information corresponding to multiple battery packs corresponding to the energy storage power station; determining the charging and discharging frequencies corresponding to the multiple battery packs based on the equipment information; determining the degradation amount corresponding to the multiple battery packs based on the charging and discharging frequencies and a preset battery degradation dataset; selecting multiple preliminary battery packs from the multiple battery packs based on the multiple degradation amounts; and performing secondary screening on the multiple preliminary battery packs according to the operating condition information to obtain at least two target battery packs, and acquiring target temperature datasets corresponding to the at least two target battery packs respectively.

[0099] In some embodiments, the aforementioned operating condition information includes the battery pack's operating current, operating voltage, and ambient temperature. The aforementioned battery pack determination module 201 is specifically used to: use the ambient temperature to select multiple candidate battery packs that are at the same ambient temperature from multiple preliminary battery packs; based on the operating current and operating voltage, select at least two target battery packs that are at the same operating current and operating voltage from multiple candidate battery packs, and obtain target temperature datasets corresponding to the at least two target battery packs respectively.

[0100] In some embodiments, the extended temperature field construction module 202 described above is specifically used to: input the target temperature dataset into a preset heat source inversion model to obtain heat source distributions corresponding to at least two target battery packs respectively, wherein the preset heat source inversion model is an artificial neural network model or a physical information neural network model; substitute the heat source distributions into a preset heat conduction forward problem model for solution, and construct the inversion temperature fields corresponding to at least two target battery packs respectively.

[0101] In some embodiments, the extended temperature field construction module 202 described above is specifically used to: determine the equivalent internal resistance of at least two target battery packs based on the historical steady-state operating data of at least two target battery packs respectively; calculate the ratio between the equivalent internal resistances of at least two target battery packs respectively to obtain the equivalent internal resistance ratio; and cross-map the heat source distribution of at least two target battery packs respectively to the preset heat conduction model corresponding to at least two target battery packs using the equivalent internal resistance ratio as a scaling factor to obtain the mapped temperature field corresponding to at least two target battery packs respectively.

[0102] In some embodiments, the extended temperature field construction module 202 described above is further configured to: obtain the actual measurement point temperature and the corresponding mapped predicted temperature of at least two target battery packs respectively; calculate the absolute deviation value between the mapped predicted temperature and the actual measurement point temperature; and retain at least two extended temperature fields corresponding to at least two target battery packs if at least two absolute deviation values ​​are less than a preset absolute difference value.

[0103] In some embodiments, the target temperature field construction module 203 described above is specifically used to: acquire measured location point information, mapped location point information, and inverted location point information corresponding to at least two extended temperature fields respectively; determine the data confidence level corresponding to each of the measured location point information, mapped location point information, and inverted location point information; and perform weighted fusion on at least two extended temperature fields based on the data confidence level to obtain the target temperature field.

[0104] In some embodiments, the target temperature field construction module 203 described above is specifically used to: determine the first uncertainty information corresponding to the measured location point information, the second uncertainty information corresponding to the mapped location point information, and the third uncertainty information corresponding to the inverted location point information; determine the first confidence level corresponding to the measured location point information based on the first uncertainty information; determine the second confidence level corresponding to the mapped location point information based on the second uncertainty information; and determine the third confidence level corresponding to the inverted location point information based on the third uncertainty information, wherein the first confidence level is higher than the second confidence level, and the second confidence level is higher than the third confidence level.

[0105] In some embodiments, after fusing at least two extended temperature fields to obtain a target temperature field, the battery pack temperature control device 20 of the energy storage power station further includes: a data extraction module, a residual determination module, a mean residual determination module, and a temperature field correction module. The data extraction module is used to extract the temperatures at multiple measured locations in the target temperature field and the temperatures at multiple actual measurement points corresponding to at least two target battery packs. The residual determination module is used to calculate the difference between the temperatures at multiple measured locations and the temperatures at multiple actual measurement points to obtain multiple residual information. The mean residual determination module is used to calculate the mean of the multiple residual information to obtain mean residual information. The temperature field correction module is used to shift the target temperature field as a whole by the mean residual information to obtain a corrected target temperature field.

[0106] In some embodiments, after shifting the target temperature field as a whole to the mean residual information to obtain the corrected target temperature field, the battery pack temperature control device 20 of the energy storage power station further includes: a temperature field processing module, wherein the temperature field processing module is used to smooth the corrected target temperature field using a Kalman filter algorithm or a wavelet denoising algorithm to suppress local abnormal fluctuations.

[0107] In some embodiments, the instruction generation module 204 described above is used to determine the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend inside at least two battery packs based on the temperature distribution and change trend in the target temperature field; and to generate temperature control instructions based on the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend.

[0108] In some embodiments, the target temperature dataset mentioned above includes temperature data collected within a preset time window, spatial coordinate information of the measuring points corresponding to the temperature sensors, and acquisition timing information.

[0109] In some embodiments, the battery pack determination module 201 may include logic circuits or be implemented by a central processing unit, digital signal processor, or field-programmable gate array (FPGA) included in an electronic device; the extended temperature field construction module 202 may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device; the target temperature field construction module 203 may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device; and the instruction generation module 204 may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device.

[0110] In some embodiments, the data extraction module may include logic circuits or be implemented by a central processing unit, digital signal processor, or field-programmable gate array (FPGA) included in an electronic device; the residual determination module may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device; the mean residual determination module may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device; the temperature field correction module may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device; and the temperature field processing module may include logic circuits or be implemented by a central processing unit, digital signal processor, or FPGA included in an electronic device.

[0111] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0112] This application discloses an electronic device, including: a processor; and a memory storing a computer program, which, when executed by the processor, causes the processor to execute the battery pack temperature control method of the energy storage power station described above.

[0113] For example, refer to Figure 3 , Figure 3 The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of the present invention.

[0114] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in this disclosure. Processor 301 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0115] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0116] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other storage medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0117] The memory 303 stores application code that executes the present invention and is controlled by the processor 301. The processor 301 executes the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0118] Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0119] This application discloses a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, the processor executes a battery pack temperature control method for an energy storage power station.

[0120] This application provides a battery pack temperature control system, which adopts the following technical solution: A battery pack temperature control system is provided to implement the aforementioned battery pack temperature control method in an energy storage power station. The system includes: a temperature control data acquisition module for acquiring temperature data from at least two target battery packs in the energy storage power station; a main control module connected to the temperature data acquisition module for analyzing and processing the received temperature data and generating temperature control commands based on the analysis results; and an execution module connected to the main control module for receiving the temperature control commands and controlling the temperature control equipment in the energy storage power station to perform corresponding temperature adjustment operations.

[0121] In some embodiments, the main control module includes: a data receiving unit connected to the temperature control data acquisition module for receiving temperature data; a temperature field construction unit connected to the data receiving unit for reconstructing the target temperature field corresponding to the battery pack in the energy storage power station based on the temperature data; and a decision unit connected to the temperature field construction unit for analyzing and processing the target temperature field and generating temperature control commands based on the analysis and processing results.

[0122] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0123] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for temperature control of a battery pack in an energy storage power station, characterized in that, include: Identify at least two target battery packs corresponding to the energy storage power station, and obtain target temperature datasets corresponding to the at least two target battery packs respectively, wherein the locations of the temperature sensors installed on the at least two target battery packs are staggered. Based on the target temperature dataset, the inversion temperature fields corresponding to the at least two target battery packs are obtained by heat source inversion, and at least two mapped temperature fields are obtained by cross mapping based on the determined equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions, and the inversion temperature fields and the mapped temperature fields are fused to obtain the extended temperature fields corresponding to the at least two target battery packs. At least two of the extended temperature fields are fused to obtain the target temperature field; Based on the target temperature field, temperature control commands corresponding to the at least two target battery packs are generated.

2. The method according to claim 1, characterized in that, The determination of at least two target battery packs corresponding to the energy storage power station includes: Obtain the equipment information and operating condition information corresponding to the multiple battery packs of the energy storage power station; Based on the device information, the charging and discharging frequencies corresponding to the plurality of battery packs are determined respectively; Based on the charging and discharging frequency and the preset battery degradation dataset, the degradation amount corresponding to each of the multiple battery packs is determined; Based on the multiple attenuation values, multiple preliminary battery packs are selected from the multiple battery packs; Based on the operating condition information, the plurality of preliminary battery packs are subjected to secondary screening to obtain at least two target battery packs.

3. The method according to claim 2, characterized in that, The operating condition information includes the battery pack's operating current, operating voltage, and ambient temperature. The process of performing a secondary screening on the plurality of preliminary battery packs based on the operating condition information to obtain at least two target battery packs includes: Using the ambient temperature, multiple candidate battery packs at the same ambient temperature are selected from the multiple preliminary battery packs. Based on the operating current and the operating voltage, at least two target battery packs with the same operating current and operating voltage are selected from the plurality of candidate battery packs.

4. The method according to claim 1, characterized in that, The step of obtaining the inversion temperature fields corresponding to the at least two target battery packs based on the target temperature dataset and through heat source inversion includes: The target temperature dataset is input into a preset heat source inversion model to obtain the heat source distribution corresponding to the at least two target battery packs, wherein the preset heat source inversion model is an artificial neural network model or a physical information neural network model; The heat source distribution is substituted into a preset forward thermal conduction problem model for solution, and the inversion temperature fields corresponding to the at least two target battery packs are constructed respectively.

5. The method according to claim 1, characterized in that, The method involves cross-mapping based on the determined equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields, including: Based on the historical steady-state operating data corresponding to the at least two target battery packs, the equivalent internal resistance corresponding to the at least two target battery packs is determined. Calculate the ratio between the equivalent internal resistances corresponding to the at least two target battery packs respectively to obtain the equivalent internal resistance ratio; Using the equivalent internal resistance ratio as a scaling factor, the heat source distributions corresponding to the at least two target battery packs are cross-mapped to the preset heat conduction model corresponding to the at least two target battery packs to obtain the mapped temperature fields corresponding to the at least two target battery packs.

6. The method according to claim 1, characterized in that, The step of fusing the inverted temperature field with the mapped temperature field to obtain the extended temperature fields corresponding to the at least two target battery packs further includes: Obtain the actual measurement point temperature and its corresponding mapped predicted temperature for each of the at least two target battery packs; Calculate the absolute deviation between the mapped predicted temperature and the actual measured temperature; If at least two of the absolute deviation values ​​are less than a preset absolute difference, the corresponding at least two extended temperature fields are retained.

7. The method according to claim 1, characterized in that, The process of fusing at least two of the extended temperature fields to obtain the target temperature field includes: Acquire at least two measured location point information, mapped location point information, and inverted location point information corresponding to the extended temperature fields, respectively; Based on the measured location point information, the mapped location point information, and the inverted location point information, determine their respective data confidence levels; Based on the data confidence level, the at least two extended temperature fields are weighted and fused to obtain the target temperature field.

8. The method according to claim 7, characterized in that, The step of determining the data confidence level corresponding to the measured location point information, the mapped location point information, and the inverted location point information includes: Determine the first uncertainty information corresponding to the measured location point information, the second uncertainty information corresponding to the mapped location point information, and the third uncertainty information corresponding to the inverted location point information; Based on the first uncertainty information, determine the first confidence level corresponding to the measured location point information; Based on the second uncertainty information, determine the second confidence level corresponding to the mapped location point information; Based on the third uncertainty information, a third confidence level is determined corresponding to the inversion location point information, wherein the first confidence level is higher than the second confidence level, and the second confidence level is higher than the third confidence level.

9. The method according to claim 1, characterized in that, After fusing at least two of the extended temperature fields to obtain the target temperature field, the method further includes: Extract the temperatures at multiple measured locations in the target temperature field and the temperatures at multiple measured points corresponding to the at least two target battery packs; The temperature difference between the multiple measured locations and the multiple actual measured points is calculated to obtain multiple residual information; The mean of the multiple residual information is calculated to obtain the mean residual information; The target temperature field is shifted as a whole by the mean residual information to obtain the corrected target temperature field.

10. The method according to claim 9, characterized in that, After shifting the target temperature field as a whole by the mean residual information to obtain the corrected target temperature field, the method further includes: The corrected target temperature field is smoothed using a Kalman filter algorithm or a wavelet denoising algorithm to suppress local abnormal fluctuations.

11. The method according to claim 1, characterized in that, The step of generating temperature control commands corresponding to the at least two target battery packs based on the target temperature field includes: Based on the temperature distribution and trend in the target temperature field, determine the location of temperature hotspots, temperature gradient distribution, and overall temperature rise trend inside the at least two battery packs; Temperature control commands are generated based on the location of the temperature hotspots, the temperature gradient distribution, and the overall temperature rise trend.

12. The method according to claim 1, characterized in that, The target temperature dataset includes temperature data collected within a preset time window, spatial coordinate information of the measuring points corresponding to the temperature sensors, and data collection timing information.

13. A battery pack temperature control device for an energy storage power station, characterized in that, include: The battery pack determination module is used to determine at least two target battery packs corresponding to the energy storage power station and to obtain target temperature datasets corresponding to the at least two target battery packs respectively. The at least two target temperature datasets are respectively collected by corresponding temperature sensors. When virtual models are constructed for the at least two target battery packs and the at least two virtual models are overlapped, the location points of the temperature sensors installed on the at least two target battery packs are staggered. An extended temperature field construction module is used to obtain the inversion temperature fields corresponding to the at least two target battery packs based on the target temperature dataset and through heat source inversion, and to perform cross mapping based on the determined equivalent internal resistance ratio between the at least two target battery packs and their corresponding heat source distributions to obtain at least two mapped temperature fields, and to fuse the inversion temperature fields and the mapped temperature fields to obtain the extended temperature fields corresponding to the at least two target battery packs. A target temperature field construction module is used to fuse at least two of the extended temperature fields to obtain a target temperature field; The instruction generation module is used to generate temperature control instructions corresponding to the at least two target battery packs based on the target temperature field.

14. The apparatus according to claim 13, characterized in that, The extended temperature field construction module is further used for: The target temperature dataset is input into a preset heat source inversion model to obtain the heat source distribution corresponding to the at least two target battery packs respectively, wherein the preset heat source inversion model is an artificial neural network model or a physical information neural network model; The heat source distribution is then substituted into a preset forward thermal conduction problem model for solution, thereby constructing the inversion temperature fields corresponding to the at least two target battery packs.

15. An electronic device, characterized in that, include: processor; A memory storing a computer program that, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-12.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the processor performs the method according to any one of claims 1-12.

17. A battery pack temperature control system, characterized in that, For implementing the method according to any one of claims 1-12, the battery pack temperature control system comprises: Temperature control data acquisition module, used to acquire temperature data of at least two target battery packs in the energy storage power station; The main control module is connected to the temperature data acquisition module and is used to analyze and process the received temperature data, and generate temperature control commands based on the analysis and processing results. The execution module, connected to the main control module, is used to receive the temperature control command and control the temperature control equipment in the energy storage power station to perform corresponding temperature adjustment operations.

18. The system according to claim 17, characterized in that, The main control module includes: A data receiving unit, connected to the temperature control data acquisition module, is used to receive the temperature data; A temperature field construction unit, connected to the data receiving unit, is used to reconstruct the target temperature field corresponding to the battery pack in the energy storage power station based on the temperature data. The decision unit, connected to the temperature field construction unit, is used to analyze and process the target temperature field and generate the temperature control command based on the analysis and processing results.

Images