An emergency power supply lithium battery power prediction method, system, device and medium

Abstract

An emergency power supply lithium battery power prediction method, system, device and medium, comprising: based on the power of the lithium battery to be predicted after charging is completed, screening geometric features from a pre-constructed feature set using a correlation coefficient method and determining the importance of each geometric feature; for each geometric feature, a data-driven method is used to calculate the single-feature predicted power corresponding to each geometric feature; based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, the power of the lithium battery to be predicted is calculated; wherein the feature set is composed of geometric features determined by the charging and discharging characteristics of the lithium battery; the present application can effectively reduce the data volume, simplify the calculation and improve the prediction efficiency by screening geometric features from the feature set, and can quickly realize the prediction of the charging power of the lithium battery.

Description

Technical Field

[0001] This invention relates to the field of lithium battery life prediction technology, specifically to a method, system, device, and medium for predicting the power capacity of emergency power supply lithium batteries. Background Technology

[0002] Emergency communication systems play an increasingly important role in responding to various major natural disasters, large-scale public events, major power supply activities, and various emergency drills. As a primary means of emergency power supply, emergency lithium batteries provide the main energy source for communication systems, and the battery capacity is crucial for fulfilling the intended functions of the communication system. During the lithium battery's cyclic charging and discharging process, data characterizing the battery's operating condition, such as current, voltage, and temperature, are collected. By extracting the time-domain or frequency-domain characteristics of the data and combining them with machine learning or a failure physics model combined with machine learning, the remaining lifespan of the lithium battery can be predicted. As the number of lithium battery charge-discharge cycles increases, the amount of data characterizing the battery's operating condition increases significantly, leading to increasingly complex calculations. Summary of the Invention

[0003] To address the problem in existing technologies where the amount of data required to characterize lithium battery operating conditions increases significantly with the number of charge-discharge cycles, leading to increasingly complex calculations, this invention proposes a method for predicting the power capacity of emergency power supply lithium batteries, comprising:

[0004] Based on the predicted charge level of the lithium battery after charging, geometric features are screened from a pre-constructed feature set using the correlation coefficient method, and the importance of each geometric feature is determined.

[0005] For each geometric feature, a data-driven method is used to calculate the single-feature predicted power for each geometric feature.

[0006] Based on the importance of each geometric feature and the single feature prediction of each geometric feature, the power of the lithium battery to be predicted is calculated.

[0007] The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries.

[0008] Preferably, the construction of the feature set includes:

[0009] The validity is determined based on the interval between adjacent charge-discharge cycles, and the number of charge-discharge cycles for extracting geometric features is obtained.

[0010] Geometric features are extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles from which the geometric features are extracted.

[0011] A feature set is constructed by combining the geometric features extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for extracting the geometric features with the battery charge level after the end of charging, which corresponds to the number of charge-discharge cycles for extracting the geometric features.

[0012] Preferably, the step of determining the validity based on the interval between adjacent charge-discharge cycles to obtain the number of charge-discharge cycles for extracting geometric features includes:

[0013] The interval between two adjacent charge-discharge cycles is compared with a set threshold for the interval between adjacent cycles. When the interval between two adjacent charge-discharge cycles is less than or equal to the set threshold for the interval between adjacent cycles, the number of charge-discharge cycles for extracting geometric features is obtained.

[0014] Preferably, extracting the geometric features from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles from which the geometric features are extracted includes:

[0015] Based on the charging voltage curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length of the line connecting the constant current start point to the constant current end point and the length from the start to the end of constant current charging are extracted.

[0016] Based on the charging current curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the constant voltage charging process current curve and the area on the horizontal axis are extracted.

[0017] The lengths of the two points of maximum curvature are extracted from the discharge voltage curve corresponding to the number of charge-discharge cycles based on the extracted geometric features.

[0018] Based on the discharge temperature curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length from the maximum curvature point to the temperature fixed point and the slope from the maximum curvature point to the temperature fixed point are extracted from the temperature curve.

[0019] Preferably, the step of filtering geometric features from a pre-constructed feature set and determining the importance of each geometric feature based on the predicted charge level of the lithium battery after charging includes:

[0020] Based on the predicted charge level and geometric characteristics of the lithium battery after charging, the correlation coefficients of each geometric characteristic are calculated using the correlation coefficient calculation formula.

[0021] The correlation coefficients of each geometric feature are compared with a set threshold. If the correlation coefficients of each geometric feature are less than the set threshold, the geometric feature corresponding to the correlation coefficient of each geometric feature is removed; otherwise, the correlation coefficients of each geometric feature and the geometric feature are retained.

[0022] The importance of each geometric feature is calculated based on the correlation coefficient of the selected geometric features and the importance calculation formula.

[0023] Preferably, the correlation coefficient is calculated as follows:

[0024]

[0025] In the formula, For the first Geometric features, The battery level at the end of each charging cycle. For the first The correlation coefficient of each geometric feature Number the geometric features.

[0026] Preferably, the importance calculation formula is as follows:

[0027]

[0028] In the formula, Geometric features Its importance in the final power generation forecast Geometric features The correlation coefficient, It is a positive integer. Number the geometric features.

[0029] Preferably, the step of calculating the predicted capacity of the lithium battery based on the importance of each geometric feature and the single feature prediction corresponding to each geometric feature includes:

[0030] Based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, combined with the lithium battery power calculation formula, the power of the lithium battery to be predicted is calculated.

[0031] Preferably, the formula for calculating the lithium battery capacity is as follows:

[0032]

[0033] In the formula, The capacity of the lithium battery. Geometric features Its importance in the final power generation forecast For single-feature prediction of power consumption, Number the geometric features. It is a positive integer.

[0034] Based on the same inventive concept, this invention also proposes an emergency power supply lithium battery power prediction system, comprising:

[0035] The geometric feature screening module is used to screen geometric features from a pre-built feature set based on the power level of the lithium battery to be predicted after charging and to determine the importance of each geometric feature.

[0036] The single-feature prediction power module is used to calculate the single-feature prediction power corresponding to each geometric feature using a data-driven method.

[0037] The lithium battery power prediction module is used to predict the power of the lithium battery to be predicted based on the importance of each geometric feature and the single feature corresponding to each geometric feature.

[0038] The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries.

[0039] Preferably, it also includes a feature set construction module:

[0040] The validity judgment submodule is used to judge the validity based on the interval between adjacent charge and discharge cycles, and obtain the number of charge and discharge cycles for extracting geometric features;

[0041] The geometric feature extraction submodule extracts geometric features based on the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for which the geometric features are extracted.

[0042] The feature set construction submodule constructs a feature set by combining the geometric features extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for extracting geometric features with the battery charge level after the end of charging, which corresponds to the number of charge-discharge cycles for extracting geometric features.

[0043] Preferably, the validity determination submodule is specifically used for:

[0044] The interval between two adjacent charge-discharge cycles is compared with a set threshold for the interval between adjacent cycles. When the interval between two adjacent charge-discharge cycles is less than or equal to the set threshold for the interval between adjacent cycles, the number of charge-discharge cycles for extracting geometric features is obtained.

[0045] Preferably, the geometric feature extraction submodule is specifically used for:

[0046] Based on the charging voltage curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length of the line connecting the constant current start point to the constant current end point and the length from the start to the end of constant current charging are extracted.

[0047] Based on the charging current curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the constant voltage charging process current curve and the area on the horizontal axis are extracted.

[0048] The lengths of the two points of maximum curvature are extracted from the discharge voltage curve corresponding to the number of charge-discharge cycles based on the extracted geometric features.

[0049] Based on the discharge temperature curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length from the maximum curvature point to the temperature fixed point and the slope from the maximum curvature point to the temperature fixed point are extracted from the temperature curve.

[0050] Preferably, the geometric feature filtering module is specifically used for:

[0051] Based on the predicted charge level and geometric characteristics of the lithium battery after charging, the correlation coefficients of each geometric characteristic are calculated using the correlation coefficient calculation formula.

[0052] The correlation coefficients of each geometric feature are compared with a set threshold. If the correlation coefficients of each geometric feature are less than the set threshold, the geometric feature corresponding to the correlation coefficient of each geometric feature is removed; otherwise, the correlation coefficients of each geometric feature and the geometric feature are retained.

[0053] The importance of each geometric feature is calculated based on the correlation coefficient of the selected geometric features and the importance calculation formula.

[0054] Preferably, the lithium battery power prediction module is specifically used for:

[0055] Based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, combined with the lithium battery power calculation formula, the power of the lithium battery to be predicted is calculated.

[0056] Furthermore, the present invention also proposes a computer device, comprising:

[0057] One or more processors;

[0058] A processor is used to execute one or more programs;

[0059] When the one or more programs are executed by the one or more processors, the above-described emergency power supply lithium battery power prediction method is implemented.

[0060] Furthermore, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the above-mentioned emergency power supply lithium battery power prediction method.

[0061] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0062] An emergency power supply lithium battery capacity prediction method, system, device, and medium are disclosed, comprising: based on the capacity of the lithium battery after charging is completed, selecting geometric features from a pre-constructed feature set using the correlation coefficient method and determining the importance of each geometric feature; calculating the single-feature predicted capacity corresponding to each geometric feature using a data-driven method; and calculating the capacity of the lithium battery to be predicted based on the importance of each geometric feature and the single-feature predicted capacity corresponding to each geometric feature; wherein the feature set is composed of geometric features determined by the charging and discharging characteristics of the lithium battery; this invention effectively reduces the amount of data, simplifies calculation, and improves prediction efficiency by selecting geometric features from the feature set, and can quickly predict the charging capacity of lithium batteries;

[0063] This invention takes into account the charging and discharging process, extracts geometric features from current, voltage and temperature signals, and can fully characterize the battery's operating condition information, ensuring the effectiveness and accuracy of the prediction results.

[0064] This invention improves the accuracy of battery power prediction by proposing the impact of charging intervals on battery power prediction. Attached Figure Description

[0065] Figure 1 This is a flowchart of an emergency power supply lithium battery power prediction method according to the present invention;

[0066] Figure 2 This is a diagram illustrating the geometric feature set construction process of the present invention.

[0067] Figure 3(a) shows the F1-F3 geometric feature extraction diagram of the present invention;

[0068] Figure 3(b) shows the F4-F6 geometric feature extraction diagram of the present invention;

[0069] Figure 4 This is the power prediction map based on geometric feature weights according to the present invention;

[0070] Figure 5 Figure for extracting feature F2 of the charging process of the present invention (battery #5);

[0071] Figure 6 The figure showing the extraction of discharge process feature F6 (battery #5) of the present invention;

[0072] Figure 7 This is a graph showing the relationship between the cycle interval time and the battery capacity of the battery #5 according to the present invention. Detailed Implementation

[0073] This invention provides a geometric method for predicting the capacity of lithium batteries, specifically including two aspects: constructing a geometric feature set and predicting capacity based on geometric feature weights. As batteries age, the measured voltage, current, and temperature will change. This invention is applicable to battery capacity prediction under the following conditions: during charging, a constant current charging strategy is initially adopted, and when the battery terminal voltage reaches its maximum value, it switches to constant voltage charging; during discharging, a constant current discharging method is used. To better understand this invention, the following description, in conjunction with the accompanying drawings and embodiments, further illustrates the content of this invention.

[0074] Example 1:

[0075] This invention provides a method for predicting the power level of an emergency power supply lithium battery, the specific implementation process of which is as follows: Figure 1 As shown, it includes:

[0076] Step 1: Based on the predicted charge level of the lithium battery after charging, use the correlation coefficient method to filter geometric features from the pre-built feature set and determine the importance of each geometric feature.

[0077] Step 2: For each geometric feature, use the data-driven method to calculate the single-feature predicted power for each geometric feature.

[0078] Step 3: Based on the importance of each geometric feature and the single feature prediction of each geometric feature, calculate the power of the lithium battery to be predicted;

[0079] The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries.

[0080] The construction of the geometric feature set includes:

[0081] The geometric feature set is extracted from training data or historical data, including geometric features of the current curve, voltage curve, and temperature curve during the charging and discharging process. The feature set construction process is as follows: Figure 2 As shown, it mainly includes three steps: feature extraction validity judgment, feature extraction, and feature set construction.

[0082] Feature extraction effectiveness assessment:

[0083] Generally speaking, a longer interval between two consecutive charge / discharge cycles helps the battery recover its stored capacity. Therefore, the effectiveness of feature extraction should be determined before performing feature extraction.

[0084] Assuming the number of charge-discharge cycles of the training battery pack is K, when the time threshold between two adjacent cycles is... The time interval between the k-th (k=1,2,…K) iteration and the (k-1)-th iteration is .like Then the k-th iteration can be used for geometric feature extraction; if If the k-th iteration cannot be used for geometric feature extraction, except when k=1.

[0085] Geometric feature extraction:

[0086] Based on the characteristics of charging and discharging, voltage and current curves are selected for the charging process; voltage and temperature curves are selected for the discharging process. In this embodiment, a total of six geometric features are extracted. Three of these are for the charging process: the length F1 of the line connecting the constant current start point to the constant current end point in the charging voltage curve, the length F2 from the start to the end of constant current charging, and the area F3 of the current curve and the horizontal axis during constant voltage charging. Three of these are for the discharging process: the length F4 of the two points of maximum curvature in the discharging voltage curve, the length F5 from the point of maximum curvature to the temperature constant point in the temperature curve, and its slope F6, as shown in Figures 3(a) and 3(b).

[0087] Feature set construction:

[0088] After selecting the eligible charge-discharge cycles, extract six features using the method described above to form a training feature set. Assuming the selected number of charge-discharge cycles after screening is N, where N ≤ K, the constructed feature set is as follows:

[0089]

[0090] in, express , The remaining charge level after each charging cycle. This indicates that the geometric features extracted from the previous charge and discharge cycle are used to predict the battery's charge capacity for the current charge / discharge cycle.

[0091] In step 1, based on the predicted charge level of the lithium battery after charging, geometric features are selected from a pre-built feature set using the correlation coefficient method, and the importance of each geometric feature is determined, including:

[0092] Power prediction based on geometric feature weights:

[0093] The energy prediction process based on geometric feature weights includes three steps: geometric feature selection, importance calculation, and energy prediction. Figure 4 As shown.

[0094] Geometric feature selection:

[0095] For the six selected geometric features, the correlation coefficients with the battery capacity Cap were calculated, and a threshold θ was set, where 0.5 ≤ θ < 1.

[0096]

[0097] In the formula, For the first Geometric features, The battery level at the end of each charging cycle. For the first The correlation coefficient of each geometric feature Geometric features are numbered; this example uses six geometric features. If... Then feature F i Remove from the feature set, if Then keep F i and record The value of .

[0098] Importance calculation:

[0099] The importance of the selected features in the final prediction is determined based on the selected features and the calculated correlation coefficients.

[0100]

[0101] In the formula, Geometric features Weighting in the final power generation forecast Geometric features The correlation coefficient, Geometric features The correlation coefficient, Number the geometric features.

[0102] In step 2, the data-driven method is used to calculate the single-feature predicted power for each geometric feature, including:

[0103] For each geometric feature, battery capacity prediction is performed using a data-driven method, such as support vector machines. The predicted battery capacity for feature Fi is... .

[0104] Step 3, calculating the capacity of the lithium battery to be predicted based on the importance of each geometric feature and the single-feature prediction capacity corresponding to each geometric feature, includes:

[0105] Lithium battery capacity prediction:

[0106] Combining the importance of features in the final prediction The final predicted lithium battery capacity is obtained. for:

[0107]

[0108] In the formula, The capacity of the lithium battery. Geometric features Its importance in the final power generation forecast For single-feature prediction of power consumption, Number the geometric features. It is a positive integer.

[0109] Example 2:

[0110] The following specific example verifies the emergency power supply lithium battery power prediction method provided by this invention.

[0111] Geometric feature extraction:

[0112] The example of geometric feature extraction used experimental data on lithium-ion battery charging and discharging processes provided by NASA Ames Research Center. The experimental system consisted of a lithium-ion battery, charger, load, electrochemical impedance spectroscopy equipment for battery health monitoring, sensors, a data acquisition system, and a computer. The sensors collected voltage, current, and temperature signals.

[0113] The experiment was conducted at room temperature using three different operating modes: charging, discharging, and impedance. Charging was performed at a constant current of 1.5A until the battery voltage reached 4.2V, then charging continued in a constant voltage mode until the charging current dropped to 20 mA. The experiment was stopped when the battery reached the end-of-life standard of 30% capacity degradation, decreasing from 2 Ahr to 0.4 Ahr. This example uses a size 5 battery, denoted as battery #5, as the case data. The batteries used included: batteries 5, 6, 7, and 18, and their respective operating parameters are shown in the table below:

[0114]

[0115] Table 1. Test lithium batteries and related parameters

[0116] Taking battery #5 as an example, three charging-related features, F1, F2, and F3, as shown in Figure 3(a), are extracted from the current and voltage curves during the charging process. The explanations of features F1, F2, and F3 are given in Figure 3(a). Taking length feature F2 as an example, its extracted geometric features are as follows... Figure 5 As shown, the geometric features exhibit a clear trend of change.

[0117] Three discharge-related features, F4, F5, and F6, as shown in Figure 3(b), were extracted from the voltage and temperature curves of the discharge process. The original voltage and temperature curves of battery #5 and the trend of geometric feature F6 are shown below. Figure 6 As shown.

[0118] The length feature F4, length feature F5, and slope feature F6 are extracted from the discharge voltage and temperature curves during the discharge process. Feature F6 is as follows: Figure 6As shown, it can be observed that geometric feature F6 has a clear trend of change.

[0119] Taking battery #5 as an example, such as Figure 7 As shown, if the interval between adjacent charge / discharge cycles is too long, the battery capacity will recover some of its value compared to the previous cycle. To avoid the impact of the recovered battery capacity on the prediction results, this embodiment removes charge / discharge cycles with excessively long intervals from the dataset.

[0120] Lithium battery remaining power prediction:

[0121] According to the method provided in this invention, an analysis is performed on the correlation between six geometric features (F1~F6) of battery #5 and battery capacity. The calculated correlation coefficients are assumed to be shown in the table below (example, assumed values):

[0122]

[0123] Table 2 Correlation Analysis between Geometric Features and Battery Capacity

[0124] Assuming a screening threshold θ = 0.80, five features pass the screening, designated F1, F2, F3, F4, and F6. The weight coefficients for each geometric feature are shown in the table below.

[0125]

[0126] Table 3. Feature Prediction Power Weighting Coefficients After Screening

[0127] Subsequent calculations can be performed by introducing a data-driven approach to predict the battery capacity of a single feature, obtaining the predicted battery capacity values ​​for the five selected geometric features. Finally, the battery capacity is predicted according to the lithium battery capacity calculation formula.

[0128] Example 3:

[0129] An emergency power supply lithium battery power prediction system includes:

[0130] The geometric feature screening module is used to screen geometric features from a pre-built feature set based on the power level of the lithium battery to be predicted after charging and to determine the importance of each geometric feature.

[0131] The single-feature prediction power module is used to calculate the single-feature prediction power corresponding to each geometric feature using a data-driven method.

[0132] The lithium battery power prediction module is used to predict the power of the lithium battery to be predicted based on the importance of each geometric feature and the single feature corresponding to each geometric feature.

[0133] The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries.

[0134] It also includes a feature set construction module:

[0135] The validity judgment submodule is used to judge the validity based on the interval between adjacent charge and discharge cycles, and obtain the number of charge and discharge cycles for extracting geometric features;

[0136] The geometric feature extraction submodule extracts geometric features based on the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for which the geometric features are extracted.

[0137] The feature set construction submodule constructs a feature set by combining the geometric features extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for extracting geometric features with the battery charge level after the end of charging, which corresponds to the number of charge-discharge cycles for extracting geometric features.

[0138] The validity judgment submodule is specifically used for:

[0139] The interval between two adjacent charge-discharge cycles is compared with a set threshold for the interval between adjacent cycles. When the interval between two adjacent charge-discharge cycles is less than or equal to the set threshold for the interval between adjacent cycles, the number of charge-discharge cycles for extracting geometric features is obtained.

[0140] The geometric feature extraction submodule is specifically used for:

[0141] Based on the charging voltage curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length of the line connecting the constant current start point to the constant current end point and the length from the start to the end of constant current charging are extracted.

[0142] Based on the charging current curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the constant voltage charging process current curve and the area on the horizontal axis are extracted.

[0143] The lengths of the two points of maximum curvature are extracted from the discharge voltage curve corresponding to the number of charge-discharge cycles based on the extracted geometric features.

[0144] Based on the discharge temperature curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length from the maximum curvature point to the temperature fixed point and the slope from the maximum curvature point to the temperature fixed point are extracted from the temperature curve.

[0145] The geometric feature filtering module is specifically used for:

[0146] Based on the predicted charge level and geometric characteristics of the lithium battery after charging, the correlation coefficients of each geometric characteristic are calculated using the correlation coefficient calculation formula.

[0147] The correlation coefficients of each geometric feature are compared with a set threshold. If the correlation coefficients of each geometric feature are less than the set threshold, the geometric feature corresponding to the correlation coefficient of each geometric feature is removed; otherwise, the correlation coefficients of each geometric feature and the geometric feature are retained.

[0148] The importance of each geometric feature is calculated based on the correlation coefficient of the selected geometric features and the importance calculation formula.

[0149] The correlation coefficient is calculated as follows:

[0150]

[0151] In the formula, For the first Geometric features, The battery level at the end of each charging cycle. For the first The correlation coefficient of each geometric feature The geometric features are numbered; this example uses six geometric features.

[0152] The formula for calculating importance is as follows:

[0153]

[0154] In the formula, Geometric features Weighting in the final power generation forecast Geometric features The correlation coefficient, Geometric features The correlation coefficient.

[0155] The lithium battery power prediction module is specifically used for:

[0156] Based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, combined with the lithium battery power calculation formula, the power of the lithium battery to be predicted is calculated.

[0157] The formula for calculating lithium battery capacity is as follows:

[0158]

[0159] In the formula, The capacity of the lithium battery. Geometric features Its importance in the final power generation forecast For single-feature prediction of power consumption, Number the geometric features. It is a positive integer.

[0160] Example 4:

[0161] Based on the same inventive concept, in another embodiment of the present invention, a computer device is provided. This computer device includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used to execute the steps of an emergency power supply lithium battery power prediction method.

[0162] Example 5:

[0163] Based on the same inventive concept, in another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the emergency power supply lithium battery power prediction method in the above embodiment.

[0164] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0166] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0167] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0168] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for predicting the power capacity of an emergency power supply lithium battery, characterized in that, include: Based on the predicted charge level of the lithium battery after charging, geometric features are screened from a pre-constructed feature set using the correlation coefficient method, and the importance of each geometric feature is determined. For each geometric feature, a data-driven method is used to calculate the single-feature predicted power for each geometric feature. Based on the importance of each geometric feature and the single feature prediction of each geometric feature, the power of the lithium battery to be predicted is calculated. The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries; The process of filtering geometric features from a pre-built feature set based on the predicted charge level of the lithium battery after charging, and determining the importance of each geometric feature, includes: Based on the predicted charge level and geometric characteristics of the lithium battery after charging, the correlation coefficients of each geometric characteristic are calculated using the correlation coefficient calculation formula. The correlation coefficients of each geometric feature are compared with a set threshold. If the correlation coefficients of each geometric feature are less than the set threshold, the geometric feature corresponding to the correlation coefficient of each geometric feature is removed; otherwise, the correlation coefficients of each geometric feature and the geometric feature are retained. The importance of each geometric feature is calculated based on the correlation coefficient of the selected geometric features and the importance calculation formula. The formula for calculating the importance level is as follows: In the formula, Geometric features Its importance in the final power generation forecast Geometric features The correlation coefficient, It is a positive integer. Number the geometric features. For the first Geometric features, For the first The correlation coefficient of each geometric feature Number the geometric features; The calculation of the predicted capacity of the lithium battery based on the importance of each geometric feature and the single feature prediction corresponding to each geometric feature includes: Based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, combined with the lithium battery power calculation formula, the power of the lithium battery to be predicted is calculated. The formula for calculating the capacity of the lithium battery is as follows: In the formula, The capacity of the lithium battery. Geometric features Its importance in the final power generation forecast For single-feature prediction of power consumption, Number the geometric features. It is a positive integer.

2. The method according to claim 1, characterized in that, The construction of the feature set includes: The validity is determined based on the interval between adjacent charge-discharge cycles, and the number of charge-discharge cycles for extracting geometric features is obtained. Geometric features are extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles from which the geometric features are extracted. A feature set is constructed by combining the geometric features extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for extracting the geometric features with the battery charge level after the end of charging, which corresponds to the number of charge-discharge cycles for extracting the geometric features.

3. The method according to claim 2, characterized in that, The validity determination based on the interval between adjacent charge-discharge cycles, to obtain the number of charge-discharge cycles for extracting geometric features, includes: The interval between two adjacent charge-discharge cycles is compared with a set threshold for the interval between adjacent cycles. When the interval between two adjacent charge-discharge cycles is less than or equal to the set threshold for the interval between adjacent cycles, the number of charge-discharge cycles for extracting geometric features is obtained.

4. The method according to claim 2, characterized in that, Extracting geometric features from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles from which the geometric features are extracted includes: Based on the charging voltage curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length of the line connecting the constant current start point to the constant current end point and the length from the start to the end of constant current charging are extracted. Based on the charging current curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the constant voltage charging process current curve and the area on the horizontal axis are extracted. The lengths of the two points of maximum curvature are extracted from the discharge voltage curve corresponding to the number of charge-discharge cycles based on the extracted geometric features. Based on the discharge temperature curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length from the maximum curvature point to the temperature fixed point and the slope from the maximum curvature point to the temperature fixed point are extracted from the temperature curve.

5. An emergency power supply lithium battery power prediction system according to any one of claims 1-4, characterized in that, include: The geometric feature screening module is used to screen geometric features from a pre-built feature set based on the power level of the lithium battery to be predicted after charging and to determine the importance of each geometric feature. The single-feature prediction power module is used to calculate the single-feature prediction power corresponding to each geometric feature using a data-driven method. The lithium battery power prediction module is used to predict the power of the lithium battery to be predicted based on the importance of each geometric feature and the single feature corresponding to each geometric feature. The feature set is composed of geometric features determined by the charging and discharging characteristics of lithium batteries; The geometric feature filtering module is specifically used for: Based on the predicted charge level and geometric characteristics of the lithium battery after charging, the correlation coefficients of each geometric characteristic are calculated using the correlation coefficient calculation formula. The correlation coefficients of each geometric feature are compared with a set threshold. If the correlation coefficients of each geometric feature are less than the set threshold, the geometric feature corresponding to the correlation coefficient of each geometric feature is removed; otherwise, the correlation coefficients of each geometric feature and the geometric feature are retained. The importance of each geometric feature is calculated based on the correlation coefficient of the selected geometric features and the importance calculation formula.

6. The system according to claim 5, characterized in that, It also includes a feature set construction module: The validity judgment submodule is used to judge the validity based on the interval between adjacent charge and discharge cycles, and obtain the number of charge and discharge cycles for extracting geometric features; The geometric feature extraction submodule extracts geometric features based on the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for which the geometric features are extracted. The feature set construction submodule constructs a feature set by combining the geometric features extracted from the current, voltage, and temperature curves corresponding to the number of charge-discharge cycles for extracting geometric features with the battery charge level after the end of charging, which corresponds to the number of charge-discharge cycles for extracting geometric features.

7. The system according to claim 6, characterized in that, The validity judgment submodule is specifically used for: The interval between two adjacent charge-discharge cycles is compared with a set threshold for the interval between adjacent cycles. When the interval between two adjacent charge-discharge cycles is less than or equal to the set threshold for the interval between adjacent cycles, the number of charge-discharge cycles for extracting geometric features is obtained.

8. The system according to claim 6, characterized in that, The geometric feature extraction submodule is specifically used for: Based on the charging voltage curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length of the line connecting the constant current start point to the constant current end point and the length from the start to the end of constant current charging are extracted. Based on the charging current curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the constant voltage charging process current curve and the area on the horizontal axis are extracted. The lengths of the two points of maximum curvature are extracted from the discharge voltage curve corresponding to the number of charge-discharge cycles based on the extracted geometric features. Based on the discharge temperature curve corresponding to the number of charge-discharge cycles of the extracted geometric features, the length from the maximum curvature point to the temperature fixed point and the slope from the maximum curvature point to the temperature fixed point are extracted from the temperature curve.

9. The system according to claim 5, characterized in that, The lithium battery power prediction module is specifically used for: Based on the importance of each geometric feature and the single-feature predicted power corresponding to each geometric feature, combined with the lithium battery power calculation formula, the power of the lithium battery to be predicted is calculated.

10. A computer device, characterized in that, include: One or more processors; A processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, an emergency power supply lithium battery power prediction method as described in any one of claims 1-4 is implemented.

11. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements a method for predicting the power level of an emergency power supply lithium battery as described in any one of claims 1 to 4.

Images