Operating Data Analysis and Processing Method, System, Device, Medium and Product for Power Battery

Abstract

The present application discloses a method, system, device, medium and product for analyzing and processing operation data of a power battery, relating to the technical field of new energy vehicles. The method includes obtaining operation data of a target power battery, performing data cleaning and data fusion on the operation data of the target power battery to obtain fusion data of the target power battery; splitting the fusion data of the target power battery successively according to the time length and sampling frequency to obtain low-frequency data of the target power battery; using a regression learning algorithm to interpolate the low-frequency current of the target power battery to obtain interpolated low-frequency current data of the target power battery; and inputting the interpolated low-frequency current data of the target power battery into an electro-thermal coupling optimization model to obtain interpolated voltage data and interpolated temperature data of the target power battery. The present application improves the quality of the obtained operation data of the power battery and realizes the complete acquisition of the full life cycle data of the power battery.

Description

Technical Field

[0001] The present application relates to the technical field of new energy vehicles, and particularly to a method, system, device, medium and product for analyzing and processing operation data of a power battery. Background Art

[0002] Under the pressure of the environment and energy, new energy electric vehicles have become the mainstream of the industry development, and the accompanying safety problems of electric vehicles have also received increasing attention. It has become a common consensus in the industry to carry out safety early warning of power batteries through big data analysis methods and improve the safety performance of power batteries of electric vehicles.

[0003] At present, there are many ways or scenarios to obtain vehicle power battery-related data around the operation scenarios of new energy vehicles. For example, vehicle-side operation monitoring platforms, vehicle charging data collection at the charging pile end during vehicle charging, monitoring data obtained during vehicle trading transfer or vehicle evaluation and detection during daily use, etc. However, due to interference during data collection or transmission, the vehicle power battery-related data obtained in each scenario often has more or less data anomaly problems, resulting in uneven quality of the original data, which brings great inconvenience to subsequent data mining and analysis. At the same time, due to limitations in scenarios and technologies, the data in each scenario is relatively limited and the data quality is uneven, and it is impossible to achieve a complete acquisition of the data process of the entire life cycle of the power battery.

[0004] Therefore, there is an urgent need for a method for analyzing and processing operation data of a power battery to solve the above problems. Summary of the Invention

[0005] The purpose of the present application is to provide a method, system, device, medium and product for analyzing and processing operation data of a power battery, improve the quality of the obtained operation data of the power battery, and achieve a complete acquisition of the data of the entire life cycle of the power battery.

[0006] To achieve the above purpose, the present application provides the following solution: A method for analyzing and processing operation data of a power battery, comprising:

[0007] Obtain operation data of a target power battery; the operation data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and SOC under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during the charging process; the power battery detection data includes: voltage, current, temperature, and SOC under power battery detection;

[0008] Respectively perform data cleaning on the operation data of the target power battery to obtain the cleaned operation data of the target power battery;

[0009] Perform data fusion processing on the operation data of the target power battery after cleaning to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC.

[0010] Segment the fusion data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery; the low-frequency data is the fusion data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC.

[0011] Interpolate the low-frequency current of the target power battery using a regression learning algorithm to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data obtained by interpolating the low-frequency current data.

[0012] Input the interpolated low-frequency current data of the target power battery into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing the initial electro-thermal coupling model using sample data and an objective function; the initial electro-thermal coupling model is constructed based on battery development test data, the equivalent circuit model of the battery pack, and the thermal simulation model of the battery pack.

[0013] Optionally, the data cleaning method includes duplicate value processing and out-of-limit value processing.

[0014] Optionally, segmenting the fusion data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery specifically includes:

[0015] Segment the fusion data of the target power battery according to a preset time length to obtain multiple first-level segments of the fusion data of the target power battery;

[0016] Segment each first-level segment according to different sampling frequencies to obtain multiple second-level segments of the fusion data of the target power battery;

[0017] For any second-level segment, count the proportion of the number of second-level segments with the minimum sampling frequency in the corresponding first-level segment;

[0018] Judge whether the proportion is less than a preset threshold. If so, use the second-level segment with the minimum sampling frequency as the low-frequency data of the target power battery.

[0019] Optionally, the expression of the equivalent circuit model of the battery pack is:

[0020] ;

[0021] Among them, denote the derivative with respect to time; denote the derivative with respect to time; denote the electrochemical polarization resistance of the battery; denote the electrochemical polarization capacitance of the battery; and respectively denote the voltage division of two parallel networks; denote the battery current; denote the concentration polarization resistance of the battery; denote the concentration polarization capacitance of the battery; denote the battery terminal voltage; is the ohmic internal resistance of the battery, is the open-circuit voltage of the battery;

[0022] The expression of the thermal simulation model of the battery pack is:

[0023] ;

[0024] wherein, denote the specific heat capacity of the battery cell; denote the mass of the battery cell; denote the i th change in temperature of the battery cell, denote the i th heat generation of the battery cell, denote the i th heat dissipation of the battery cell.

[0025] Optionally, the optimization process of the electro-thermal coupling optimization model specifically includes:

[0026] Obtain sample data; the sample data is the high-frequency current and high-frequency SOC of the sample power battery;

[0027] Input the sample data into the initial electro-thermal coupling model, and output the predicted voltage data and predicted temperature data of the sample power battery;

[0028] Construct an objective function based on the predicted voltage data of the sample power battery, the predicted temperature data of the sample power battery, the true voltage data of the sample power battery, and the true temperature data of the sample power battery, and adjust the model parameters of the initial electro-thermal coupling model according to the objective function to obtain the electro-thermal coupling optimization model.

[0029] Optionally, the objective function has the following expression:

[0030] ;

[0031] wherein,x is sample data; j is the sample sequence; J represents the total number of sample data; p is the parameter to be optimized; when p represents voltage, is the true value of the voltage data of the sample power battery, is the predicted value of the voltage data of the sample power battery; when p represents temperature, is the true value of the temperature data of the sample power battery, is the predicted value of the temperature data of the sample power battery; P scale is the value range of the model parameters in the electro-thermal coupling optimization model.

[0032] In a second aspect, the present application provides an operating data analysis and processing system for a power battery. The operating data analysis and processing system for the power battery is used to implement the operating data analysis and processing method for the power battery. The operating data analysis and processing system for the power battery includes:

[0033] A data acquisition unit, configured to acquire the operating data of a target power battery; the operating data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and SOC under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during the charging process; the power battery detection data includes: voltage, current, temperature, and SOC under power battery detection;

[0034] A data cleaning unit, configured to respectively perform data cleaning on the operating data of the target power battery to obtain the cleaned operating data of the target power battery;

[0035] A data fusion unit, configured to respectively perform data fusion processing on the cleaned operating data of the target power battery to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC;

[0036] A data splitting unit, configured to split the fusion data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery; the low-frequency data is the fusion data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC;

[0037] The interpolated low-frequency current data determination unit is configured to interpolate the low-frequency current of the target power battery by using a regression learning algorithm to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data obtained by interpolating the low-frequency current data.

[0038] The interpolated voltage data and interpolated temperature data determination unit is configured to input the interpolated low-frequency current data of the target power battery into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing the initial electro-thermal coupling model by using sample data and an objective function; the initial electro-thermal coupling model is constructed based on battery development test data, an equivalent circuit model of the battery pack, and a thermal simulation model of the battery pack.

[0039] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for analyzing and processing the operation data of the power battery described in any one of the above.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for analyzing and processing the operation data of the power battery described in any one of the above is implemented.

[0041] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for analyzing and processing the operation data of the power battery described in any one of the above is implemented.

[0042] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0043] The present application discloses a method, system, device, medium, and product for analyzing and processing the operation data of a power battery. By performing data cleaning and data fusion on the operation data of the target power battery, the data quality is initially improved; then, the fused data is segmented to obtain the low-frequency data of the target power battery, and then, a regression learning algorithm is used to interpolate the low-frequency current of the target power battery to obtain the interpolated low-frequency current data of the target power battery, and the data is cleaned and filled again, improving the data quality and achieving the complete acquisition of the full-life cycle data of the power battery; finally, the interpolated low-frequency current data of the target power battery is input into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery, further improving the operation data quality of the target power battery. Description of the Drawings

[0044] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 Schematic flowchart of the method for analyzing and processing the operation data of a power battery provided by an embodiment of the present application;

[0046] Figure 2 Schematic diagram of the parameter coupling relationship between the electrothermal models provided by an embodiment of the present application;

[0047] Figure 3 Schematic diagram of the functional modules of a system for analyzing and processing the operation data of a power battery provided by an embodiment of the present application;

[0048] Figure 4 Schematic diagram of the structure of a computer device provided by an embodiment of the present application.

[0049] Reference numerals:

[0050] Data acquisition unit - 1, data cleaning unit - 2, data fusion unit - 3, data splitting unit - 4, unit for determining interpolated low - frequency current data - 5, unit for determining interpolated voltage data and interpolated temperature data - 6. Detailed implementation manners

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0052] To make the above - mentioned objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific implementation manners.

[0053] In an exemplary embodiment, as Figure 1 shown, a method for analyzing and processing the operation data of a power battery is provided, including the following steps S1 to S6. Among them:

[0054] Step S1, obtain the operation data of the target power battery; the operation data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and state of charge (SOC) under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during the charging process; the power battery detection data includes: voltage, current, temperature, and SOC under the power battery detection.

[0055] Specifically, the vehicle monitoring data refers to the operation data of the power battery included in the vehicle monitoring data collected in accordance with the GB / T32960 standard, such as current, SOC, temperature, voltage, etc.; the vehicle charging process monitoring data refers to the data collected by the charging pile management platform during the vehicle charging process for monitoring the charging process, including charging current, charging voltage, SOC, temperature, etc.; the power battery detection data refers to the process data of the vehicle user's periodic state detection and evaluation of the vehicle power battery during use, including dynamic data during the detection process, such as current, voltage, temperature, etc., and static analysis data of the detection results, including information such as the current capacity health of the battery and voltage difference.

[0056] Step S2, perform data cleaning on the operation data of the target power battery respectively to obtain the cleaned operation data of the target power battery.

[0057] Specifically, the data cleaning methods include duplicate value processing and out-of-limit value processing.

[0058] Step S3, perform data fusion processing on the cleaned operation data of the target power battery respectively to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC.

[0059] Specifically, the vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data are integrated. Each original operation data is usually time-series data including voltage, current, SOC information, etc. When integrating the data, the data is integrated according to the definition of the data attribute field name (attribute fields such as voltage, current, SOC) and the time tag order. At the same moment, if there are multiple data sources for the same attribute field and the values of the multiple data sources are different, the average value of each value is taken as the data value of the corresponding attribute field after fusion at the current moment; if there is only one data source for the same attribute field at the same moment, this one data source is taken as the data value of the corresponding attribute field at the current moment. For example, when the attribute field is current, at time T1, the current in the vehicle monitoring data is 1A, the current in the vehicle charging process monitoring data is 2A, and the current in the power battery detection data is 2.5A, then the average value is (1 + 2 + 2.5) / 3 = 1.83A, and the fused current at time T1 is 1.83A; if at time T1, the current in the vehicle monitoring data is 0A, the current in the vehicle charging process monitoring data is 2A, and the current in the power battery detection data is 0A, then the fused current at time T1 is recorded as 2A.

[0060] Step S4: Segment the fused data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery; the low-frequency data is the fused data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC.

[0061] As an optional implementation manner, step S4 specifically includes:

[0062] Step S41: Segment the fused data of the target power battery according to the preset time length to obtain multiple first-level segments of the fused data of the target power battery. Specifically, according to the time tag of the power battery operation data, the data is segmented. Starting from the first-frame data time point, each segment is divided every half year (that is, the preset time length is half a year), and is recorded as a first-level segment.

[0063] Step S42: Segment each first-level segment according to different sampling frequencies to obtain multiple second-level segments of the fused data of the target power battery. Specifically, for each first-level segment, identify the data sampling frequencies included in each segment according to the data time tag. If there are more than two data sampling frequencies in the first-level segment, then according to the different data sampling frequencies, the first-level segment is further segmented, and the data with the same sampling frequency and continuous is segmented into one segment, which is recorded as a second-level segment, and then multiple second-level segments of the fused data of the target power battery are obtained.

[0064] Step S43: For any secondary segment, calculate the proportion of the number of secondary segments with the minimum sampling frequency in the corresponding primary segment.

[0065] Step S44: Determine whether the proportion is less than a preset threshold. If so, regard the secondary segment with the minimum sampling frequency as the low-frequency data of the target power battery. Here, the first preset condition is that the proportion is less than the preset threshold. Specifically, if the proportion of the number of secondary segments with the minimum sampling frequency in the corresponding primary segment is lower than 70% (preset threshold), then regard the corresponding secondary segment with the minimum sampling frequency as the low-frequency data of the target power battery.

[0066] Step S5: Use a regression learning algorithm to interpolate the low-frequency current of the target power battery to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data after interpolating the low-frequency current data.

[0067] Among them, use regression learning algorithms such as artificial neural network regression and gradient boosting machine regression to establish a current regression model, and use the current regression model to interpolate the interpolated low-frequency current data of the target power battery according to the data frequency determined above to obtain the interpolated low-frequency current data of the target power battery. The interpolation filling frequency is determined by the sampling frequency with the largest proportion of the total high-frequency data volume among the data with different sampling frequencies included in the high-frequency data within the primary segment.

[0068] Step S6: Input the interpolated low-frequency current data of the target power battery into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing the initial electro-thermal coupling model using sample data and an objective function; the initial electro-thermal coupling model is constructed based on battery development test data, the equivalent circuit model of the battery pack, and the thermal simulation model of the battery pack.

[0069] Specifically, use battery development test data to construct a simulation model of external characteristic parameters such as electricity and heat of the battery system (i.e., the construction of the initial electro-thermal coupling model) to realize the simulation output of monitoring data such as the voltage and temperature of the power battery monomer. Among them, battery development test data refers to the test process data generated by relevant tests on the power battery during the development stage of the vehicle battery to ensure the performance of the power battery system, including performance tests, safety tests, HPPC test tests, life tests, thermal performance tests, etc. In addition, it also includes battery pack development parameter information, such as battery cell materials, battery pack structure layout forms, thermal management system design parameters, etc.

[0070] Based on the interpolated low-frequency current data of the target power battery, with the help of the electro-thermal coupling optimization model, the voltage data and temperature data of the target power battery at low frequency are simulated and fitted. The voltage sequence of the target power battery is formed through the simulation output of the equivalent circuit model of the battery pack, and the temperature data sequence of the battery pack is generated through the thermal simulation model of the battery pack. Finally, the interpolated voltage data and interpolated temperature data of the target power battery are obtained.

[0071] Equivalent circuit model:

[0072] In this application, the second-order RC equivalent circuit model is taken as an example for detailed description. According to the circuit principle, the second-order RC equivalent circuit model characterizes the relationship between the battery terminal voltage and current. Then, the expression of the equivalent circuit model of the battery pack is as follows:

[0073] (1)

[0074] Among them, represents the derivative with respect to time; represents the derivative with respect to time; represents the battery electrochemical polarization resistance; represents the battery electrochemical polarization capacitance; 、 respectively represent the voltage division of two parallel networks; represents the battery current; represents the battery concentration polarization resistance; represents the battery concentration polarization capacitance; represents the battery terminal voltage; is the battery ohmic internal resistance, is the battery open-circuit voltage. The above parameters are usually determined by querying the mapping relationship table of battery SOC, temperature, and battery health. The format of the mapping relationship table is shown in Table 1:

[0075] Table 1 Mapping relationship table

[0076]

[0077] In Table 1, X1 represents SOC, X2 represents temperature. The values in Table 1 are the values of the parameters to be queried by the model. The parameters that can be queried include 、 、 、 and , and each parameter is queried through its corresponding mapping relationship table. The mapping relationship table is calculated based on the HPPC test data under different SOC and different temperature conditions in the battery development test data; the open-circuit voltage It is a non-linear function related to SOC and can usually be determined by fitting the test data of the SOC-OCV curve in the battery performance test.

[0078] Battery pack electrical simulation model:

[0079] It is determined by the series-parallel form of the battery pack system and the number of series-connected single cells. If a single battery cell consists of multiple parallel-connected battery cores, the equivalent circuit model of the single battery cell is processed in parallel according to circuit theory; if each single battery cell consists of a single battery core and all single cells are connected in series to form a battery pack system, the voltage and current of the battery pack are calculated according to the following formulas:

[0080] (2)

[0081] (3)

[0082] Among them, I p represents the current of the battery pack; U p represents the voltage of the battery pack; I j represents the j th current of a single battery cell; U j represents the j th terminal voltage of a single battery cell; n is the number of series-connected single battery cells in the battery pack.

[0083] Battery pack thermal simulation model:

[0084] The thermal simulation model of the battery pack includes a single battery cell heat generation model and a battery heat dissipation model, and the expression of the thermal simulation model of the battery pack is:

[0085] (4)

[0086] Among them, represents the specific heat capacity of a single battery cell; represents the mass of a single battery cell; represents the i th temperature change of a single battery cell, represents the i th heat generation of a single battery cell, represents the i th heat dissipation of a single battery cell.

[0087] According to the battery heat generation principle, the heat generation of a single battery cell includes: Joule heat, reaction heat, polarization heat and side reaction heat. The battery heat generation is calculated by the bernardi battery heat generation formula , and its formula is as follows:

[0088] (5)

[0089] Among them, q is the heat generation rate per unit volume of the battery, I is the current, R is the internal resistance, T is the temperature, dU / dT is the derivative of the open circuit voltage with respect to temperature.‌

[0090] The heat dissipation of a single battery cell includes: conduction heat dissipation, convective heat dissipation, radiative heat dissipation, etc. Conduction heat dissipation occurs at the contact interface between the battery and other components, and its heat transfer expression is as follows:

[0091] (6)

[0092] Among them, q a is the heat conducted per unit area and unit time; k is the thermal conductivity of the object; represents the temperature difference between the battery and the object being heat-conducted; represents the distance between the battery and the object being heat-conducted.

[0093] Convective heat dissipation mainly refers to the heat exchange between the battery and the cooling system pipeline. Its convective heat transfer follows Newton's law, and the calculation formula is as follows:

[0094] (7)

[0095] Among them, q b is the heat transfer amount between the battery surface and the cooling medium per unit area and unit time; T c represents the battery surface temperature; T d represents the cooling medium surface temperature; h is the convective heat transfer coefficient.

[0096] Radiative heat dissipation, thermal radiation is the process by which an object dissipates heat outward in the form of electromagnetic radiation due to its own temperature. The higher the temperature, the greater the energy radiated. Since the battery operating temperature does not usually reach a high level under normal circumstances, the heat dissipated by radiative heat dissipation is negligible. Therefore, the radiative heat dissipation can be ignored when calculating the heat dissipation.

[0097] Based on the definitions of the above heat generation and heat dissipation formulas and the different positions of each single battery cell in the battery system, the calculation formula for the temperature change of the single battery cell is determined according to the principles of fluid mechanics and thermodynamics as follows:

[0098] (8)

[0099] Among them, is a variable related to the SOC, which can be determined by developing test data; the ohmic internal resistance R 0, the electrochemical polarization internal resistance R 1, and the concentration polarization internal resistance R 2 can be identified and determined through the test data of the development test. represents the temperature difference between the i th battery cell and other adjacent k th battery cells with conduction heat dissipation relationship; represents the distance between the i th battery cell and other adjacent k th battery cells with conduction heat dissipation relationship; g represents the number of other adjacent battery cells with conduction heat dissipation relationship with the i th battery cell; represents the current temperature of the i th battery cell; represents the ambient temperature of the battery cell; represents the surface temperature of the cooling medium; represents the contact area between the i th battery cell and the ambient air; represents the contact area between the i th battery cell and the cooling medium.

[0100] Battery pack electro-thermal coupling model:

[0101] It is established by coupling the equivalent circuit model and the thermal simulation model of the battery pack. The equivalent circuit model inputs the output terminal voltage, electromotive force, etc. into the thermal simulation model of the battery pack. At the same time, the thermal simulation model of the battery pack inputs the simulated battery temperature into the equivalent circuit model. The equivalent circuit model determines the parameters of its equivalent circuit model according to the temperature input and based on the mapping relationship table, and simulates and generates voltage data. The schematic diagram of the parameter coupling relationship between the electro-thermal models is as Figure 2 shown. In addition, other equivalent circuit models, thermal simulation models, or machine learning simulation models such as neural networks can also be used to construct a data simulation model to obtain the battery pack electro-thermal coupling model.

[0102] As an optional implementation manner, in step S6, the optimization process of the electro-thermal coupling optimization model specifically includes:

[0103] Step S61, obtaining sample data; the sample data is the high-frequency current and high-frequency SOC of the sample power battery.

[0104] Step S62: Input the sample data into the initial electro-thermal coupling model, and output the predicted voltage data and predicted temperature data of the sample power battery.

[0105] Step S63: Construct an objective function based on the predicted voltage data of the sample power battery, the predicted temperature data of the sample power battery, the true voltage data of the sample power battery, and the true temperature data of the sample power battery, and adjust the model parameters of the initial electro-thermal coupling model according to the objective function to obtain an electro-thermal coupling optimized model. By extracting the high-frequency data in the sample data, the parameters of the initial electro-thermal coupling model are corrected, realizing the optimization of the initial electro-thermal coupling model by high-frequency high-quality data, so that the electro-thermal coupling optimized model can more accurately output the voltage data and temperature data of the power battery. Extract all the calibratable parameters in the initial electro-thermal coupling model to form a parameter vector to be optimized, and use the objective function to realize parameter optimization.

[0106] As an optional implementation manner, in step S63, the objective function has the following expression:

[0107] (9)

[0108] where, x is the sample data, here it is the current data; j is the sample sequence; J represents the total number of sample data; p is the parameter to be optimized; when p represents voltage, is the true voltage data of the sample power battery, is the predicted voltage data of the sample power battery; when p represents temperature, is the true temperature data of the sample power battery, is the predicted temperature data of the sample power battery, where the true voltage data and predicted voltage data of the sample power battery, and the true temperature data and predicted temperature data of the sample power battery are the voltage data and temperature data calculated by the electro-thermal coupling optimized model; P scale is the value range of the model parameters in the electro-thermal coupling optimized model.

[0109] As an optional implementation manner, in step S63, use the particle swarm optimization algorithm, simulated annealing algorithm or genetic algorithm for parameter optimization to obtain a parameter sequence that minimizes the difference between the true value and the model output value within the parameter value range p opt .

[0110] As an optional implementation manner, it further includes step S7:

[0111] Integrate the high-frequency data with the interpolated voltage data and the interpolated temperature data of the target power battery, and integrate them together according to the time tag order to form a data set covering the entire life cycle of the battery.

[0112] Advantages of this application:

[0113] In this application, by performing data cleaning and data fusion on the operation data of the target power battery in multiple scenarios, the data quality is initially improved; then, the fused data is segmented to obtain the low-frequency data of the target power battery, and then a regression learning algorithm is used to interpolate the low-frequency current of the target power battery to obtain the interpolated low-frequency current data of the target power battery. The data is cleaned and filled again to improve the data quality, and the complete acquisition of the data throughout the life cycle of the power battery is realized for subsequent data analysis and mining applications; finally, the interpolated low-frequency current data of the target power battery is input into the electro-thermal coupling optimization model to obtain the interpolated voltage data and the interpolated temperature data of the target power battery. Among them, the electro-thermal coupling optimization model is optimized and adjusted by using the high-quality high-frequency data in the fused data of the target power battery, further improving the quality of the operation data of the target power battery.

[0114] Based on the same inventive concept, an embodiment of this application also provides an operation data analysis and processing system for a power battery for implementing the operation data analysis and processing method of the power battery involved above. The solution provided by this system to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the operation data analysis and processing system for a power battery provided below can refer to the limitations on the operation data analysis and processing method of the power battery in the above text, and will not be repeated here.

[0115] In an exemplary embodiment, as Figure 3 shown, an operation data analysis and processing system for a power battery is provided, including: a data acquisition unit 1, a data cleaning unit 2, a data fusion unit 3, a data segmentation unit 4, an interpolated low-frequency current data determination unit 5, and an interpolated voltage data and interpolated temperature data determination unit 6.

[0116] The data acquisition unit 1 is used to acquire the operation data of the target power battery; the operation data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and SOC under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during the charging process; the power battery detection data includes: voltage, current, temperature, and SOC under power battery detection.

[0117] A data cleaning unit 2, configured to perform data cleaning on the operation data of the target power battery respectively, so as to obtain the cleaned operation data of the target power battery.

[0118] A data fusion unit 3, configured to perform data fusion processing on the cleaned operation data of the target power battery respectively, so as to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC.

[0119] A data segmentation unit 4, configured to segment the fusion data of the target power battery in sequence according to the time length and sampling frequency, so as to obtain the low-frequency data of the target power battery; the low-frequency data is the fusion data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC.

[0120] An interpolated low-frequency current data determination unit 5, configured to interpolate the low-frequency current of the target power battery by using a regression learning algorithm, so as to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data obtained by interpolating the low-frequency current data.

[0121] An interpolated voltage data and interpolated temperature data determination unit 6, configured to input the interpolated low-frequency current data of the target power battery into an electro-thermal coupling optimization model, so as to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing an initial electro-thermal coupling model by using sample data and an objective function; the high-frequency data is the fusion data whose sampling frequency meets the second preset condition; the high-frequency data includes: high-frequency voltage, high-frequency current, high-frequency temperature, and high-frequency SOC; the initial electro-thermal coupling model is constructed based on battery development test data, an equivalent circuit model of the battery pack, and a thermal simulation model of the battery pack.

[0122] As an optional implementation manner, the operation data analysis and processing system of the power battery can be integrally deployed in the cloud, integrate the high-frequency data with the interpolated voltage data and interpolated temperature data of the target power battery, and integrate them together according to the time tag sequence to form a data set covering the entire life cycle of the battery, and store it in the cloud.

[0123] In an exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the operation data analysis and processing method of the power battery.

[0124] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for analyzing and processing the operation data of a power battery is implemented.

[0125] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, a method for analyzing and processing the operation data of a power battery is implemented.

[0126] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for analyzing and processing the operation data of a power battery is implemented.

[0127] Those skilled in the art can understand that Figure 4 the structure shown in

[0128] is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0129] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0130] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0131] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0132] In this article, specific examples are used to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for analyzing and processing operation data of a power battery, characterized in that The method for analyzing and processing the operation data of the power battery includes: Obtaining the operation data of the target power battery; the operation data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and SOC under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during charging; the power battery detection data includes: voltage, current, temperature, and SOC under power battery detection; Respectively perform data cleaning on the operation data of the target power battery to obtain the cleaned operation data of the target power battery; Perform data fusion processing on the cleaned operation data of the target power battery to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC; Slice the fusion data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery; the low-frequency data is the fusion data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC; Use the regression learning algorithm to interpolate the low-frequency current of the target power battery to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data after interpolating the low-frequency current data; Input the interpolated low-frequency current data of the target power battery into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing the initial electro-thermal coupling model using sample data and the objective function; the initial electro-thermal coupling model is constructed based on the battery development test data, the equivalent circuit model of the battery pack, and the thermal simulation model of the battery pack; During data fusion, data fusion is performed according to the definition of the data attribute field name and the time tag order. At the same moment, if there are multiple data sources for the same attribute field and the values of the multiple data sources are different, then the average value of each value is taken as the data value of the corresponding attribute field after fusion at the current moment; if there is only one data source for the same attribute field at the same moment, then this one data source is used as the data value of the corresponding attribute field at the current moment; Slicing the fusion data of the target power battery in sequence according to the time length and sampling frequency to obtain the low-frequency data of the target power battery specifically includes: slicing the fusion data of the target power battery according to the preset time length to obtain multiple first-level segments of the fusion data of the target power battery; slicing each first-level segment according to different sampling frequencies to obtain multiple second-level segments of the fusion data of the target power battery; for any second-level segment, statistically calculate the proportion of the number of the second-level segment with the smallest sampling frequency in the corresponding first-level segment; determine whether the proportion is less than the preset threshold, and if so, use the second-level segment with the smallest sampling frequency as the low-frequency data of the target power battery; The expression of the thermal simulation model of the battery pack is: ； Among them, represents the specific heat capacity of the battery cell; represents the mass of the battery cell; represents the i temperature change of the th battery cell; i represents the heat generation of the th battery cell; i represents the heat dissipation of the th battery cell; represents the battery current; is a variable related to SOC; R0 is the ohmic internal resistance, R1 is the electrochemical polarization internal resistance, R2 is the concentration polarization internal resistance, represents the temperature difference between the i th battery cell and the other adjacent k th battery cell with a conduction heat dissipation relationship; represents the distance between the i th battery cell and the other adjacent k th battery cell with a conduction heat dissipation relationship; g represents the number of other adjacent battery cells with a conduction heat dissipation relationship with the i th battery cell; h is the convective heat transfer coefficient; represents the current temperature of the i th battery cell; represents the ambient temperature of the battery cell; represents the surface temperature of the cooling medium; represents the i contact area between the th battery cell and the ambient air; i represents the contact area between the th battery cell and the cooling medium.

2. The method for analyzing and processing the operation data of the power battery according to claim 1, wherein The data cleaning method includes duplicate value processing and out-of-limit value processing.

3. The method for analyzing and processing the operation data of the power battery according to claim 1, wherein, The expression of the equivalent circuit model of the battery pack is as follows: ； Among them, represents the derivative with respect to time; represents the derivative with respect to time; represents the electrochemical polarization resistance of the battery; represents the electrochemical polarization capacitance of the battery; and respectively represent the partial voltages of two parallel networks; represents the battery current; represents the concentration polarization resistance of the battery; represents the concentration polarization capacitance of the battery; represents the battery terminal voltage; is the ohmic internal resistance of the battery, is the open-circuit voltage of the battery.

4. The method for analyzing and processing the operation data of the power battery according to claim 1, wherein, The optimization process of the electro-thermal coupling optimization model specifically includes: Obtaining sample data; the sample data is the high-frequency current and high-frequency SOC of the sample power battery; Inputting the sample data into the initial electro-thermal coupling model to output the predicted voltage data and predicted temperature data of the sample power battery; Constructing an objective function based on the predicted voltage data of the sample power battery, the predicted temperature data of the sample power battery, the true voltage data of the sample power battery, and the true temperature data of the sample power battery, and adjusting the model parameters of the initial electro-thermal coupling model according to the objective function to obtain the electro-thermal coupling optimization model.

5. The method for analyzing and processing the operation data of the power battery according to claim 4, wherein, Objective function The expression of which is: ； Among them, x is sample data; j is a sample sequence; J represents the total number of sample data; p is a parameter to be optimized; when p represents voltage, is the true value of the voltage data of the sample power battery, is the predicted value of the voltage data of the sample power battery; when p represents temperature, is the true value of the temperature data of the sample power battery, is the predicted value of the temperature data of the sample power battery; P scale is the value range of the model parameters in the electro-thermal coupling optimization model.

6. An operating data analysis and processing system for a power battery, characterized in that The operation data analysis and processing system of the power battery is used to implement the operation data analysis and processing method of the power battery according to any one of claims 1-5. The operation data analysis and processing system of the power battery includes: A data acquisition unit for acquiring the operation data of the target power battery; the operation data includes: vehicle monitoring data, vehicle charging process monitoring data, and power battery detection data; the vehicle monitoring data includes: voltage, current, temperature, and SOC under vehicle monitoring; the vehicle charging process monitoring data includes: voltage, current, temperature, and SOC during charging; the power battery detection data includes: voltage, current, temperature, and SOC under power battery detection; A data cleaning unit for respectively cleaning the operation data of the target power battery to obtain the cleaned operation data of the target power battery; A data fusion unit for respectively performing data fusion processing on the cleaned operation data of the target power battery to obtain the fusion data of the target power battery; the fusion data includes: fused voltage, fused current, fused temperature, and fused SOC; A data segmentation unit for successively segmenting the fusion data of the target power battery according to the time length and sampling frequency to obtain the low-frequency data of the target power battery; the low-frequency data is the fusion data whose sampling frequency meets the first preset condition, and the low-frequency data includes: low-frequency voltage, low-frequency current, low-frequency temperature, and low-frequency SOC; An interpolated low-frequency current data determination unit for interpolating the low-frequency current of the target power battery using a regression learning algorithm to obtain the high-frequency current data of the target power battery; the high-frequency current data is the current data after interpolating the low-frequency current data; An interpolated voltage data and interpolated temperature data determination unit for inputting the interpolated low-frequency current data of the target power battery into the electro-thermal coupling optimization model to obtain the interpolated voltage data and interpolated temperature data of the target power battery; the electro-thermal coupling optimization model is obtained by optimizing the initial electro-thermal coupling model using sample data and an objective function; the initial electro-thermal coupling model is constructed based on battery development test data, the equivalent circuit model of the battery pack, and the thermal simulation model of the battery pack. When performing data fusion, data fusion is carried out according to the definition of data attribute field names and the order of time tags. At the same moment, if there are multiple data sources for the same attribute field and the values of the multiple data sources are different, the average value of each value is taken as the data value of the corresponding attribute field after fusion at the current moment; if there is only one data source for the same attribute field at the same moment, then this one data source is taken as the data value of the corresponding attribute field at the current moment. The fused data of the target power battery is sequentially segmented according to the time length and sampling frequency to obtain the low-frequency data of the target power battery, specifically including: segmenting the fused data of the target power battery according to a preset time length to obtain multiple first-level segments of the fused data of the target power battery; segmenting each first-level segment according to different sampling frequencies to obtain multiple second-level segments of the fused data of the target power battery; for any second-level segment, counting the proportion of the number of the second-level segments with the minimum sampling frequency in the corresponding first-level segment; determining whether the proportion is less than a preset threshold, and if so, taking the second-level segment with the minimum sampling frequency as the low-frequency data of the target power battery. The expression of the thermal simulation model of the battery pack is: ； Wherein, represents the specific heat capacity of a battery cell; represents the mass of a battery cell; represents the i th temperature change of a battery cell, represents the i th heat generation of a battery cell, represents the i th heat dissipation of a battery cell, represents the battery current, represents the battery temperature; is a variable related to SOC; R0 is the ohmic internal resistance, R1 is the electrochemical polarization internal resistance, R2 is the concentration polarization internal resistance, represents the i th temperature difference between the k th other adjacent battery cell that has a conduction heat dissipation relationship with the th battery cell; i represents the k th distance between the i th other adjacent battery cell that has a conduction heat dissipation relationship with the h is the convective heat transfer coefficient; represents the i th current temperature of a battery cell; represents the ambient temperature of the battery cell; represents the surface temperature of the cooling medium; represents the i th contact area between a battery cell and the ambient air; represents the i th contact area between a battery cell and the cooling medium.

7. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for analyzing and processing the operation data of the power battery according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for analyzing and processing the operation data of the power battery according to any one of claims 1-5.

9. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for analyzing and processing the operation data of the power battery according to any one of claims 1-5.

Images