Battery SOC intelligent monitoring and management method based on precise electric quantity algorithm

Abstract

The invention relates to a battery SOC intelligent monitoring and management method based on a precise electric quantity algorithm, and belongs to the technical field of battery power generation management, and the method comprises the steps: obtaining the voltage, current, temperature and historical data of a battery in real time, and calculating an initial SOC value through an ampere-hour integral method; when the SOC is greater than or equal to 90% in a charging state, generating a first correction factor based on a voltage hysteresis characteristic and a temperature coefficient, and dynamically reducing an ampere-hour integral weight; in the discharge state and when SOC is smaller than or equal to 20%, a second correction factor is generated in combination with the polarization voltage and the temperature attenuation coefficient, and the Kalman filtering weight is increased; and fusing the correction factors through a gradient descent optimization algorithm, performing closed-loop feedback, and outputting a calibrated SOC value. According to the method, through dynamic weight distribution, a nonlinear compensation model and a closed-loop self-optimization mechanism, the problems that an extreme SOC interval is large in estimation error and a traditional method is poor in adaptability are solved, and the precision and reliability of battery management are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery power generation management, and in particular to a battery SOC intelligent monitoring and management method based on a precise power algorithm. Background Art

[0002] In the field of battery SOC estimation, traditional methods typically combine the ampere-hour integration method with a filtering algorithm. However, these methods face the problem of error accumulation caused by capacity decay, temperature sensitivity, and nonlinear characteristics in extreme SOC ranges (such as voltage hysteresis and polarization effects). Existing solutions use fixed-weight algorithm fusion to dynamically adapt to battery aging and operating condition fluctuations, insufficiently compensate for coupling distortion in high and low SOC ranges, and lack real-time feedback capabilities in open-loop calibration mechanisms, resulting in a significant decrease in estimation accuracy in extreme scenarios. Achieving dynamic weight allocation, precise compensation for nonlinear characteristics, and closed-loop self-optimization remains a bottleneck that urgently needs to be overcome. Summary of the Invention

[0003] To achieve the above objectives, the present invention provides a battery SOC intelligent monitoring and management method based on a precise power algorithm, comprising the following steps: Acquire the voltage, current and temperature of the battery in real time, and calculate the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; The dynamic weight allocation algorithm is used to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively, thereby correcting the initial SOC value, wherein: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, thereby increasing the weight of the Kalman filter algorithm to a second preset value; The first correction factor and the second correction factor are dynamically integrated through a gradient descent optimization algorithm to generate a calibrated SOC value, and the SOC value is fed back to the power prediction module of the battery management system.

[0004] Furthermore, the step of obtaining the voltage, current and temperature of the battery in real time and calculating the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery includes: Dynamically screen outliers in real-time sampled voltage, current, and temperature data, perform standard deviation analysis on continuously sampled data using a sliding time window, remove data that exceeds the preset fluctuation range, and perform interpolation processing; generating nonlinear capacity decay data based on the number of cycles, average discharge depth, and capacity decay trend in the historical charge and discharge data, wherein the actual capacity is related to the square root of the number of cycles and the square of the average discharge depth; Based on the current temperature threshold and charge and discharge current direction, the corresponding ampere-hour integral calculation mode is dynamically selected: under low-temperature discharge conditions, a temperature compensation coefficient is introduced to correct the nominal capacity, and under normal temperature charging conditions, the nominal capacity is directly used for calculation, and the calculation results of the corresponding intervals are integrated through the weight coefficient.

[0005] Furthermore, the step of generating nonlinear capacity decay data according to the number of cycles, average discharge depth and capacity decay trend in the historical charge and discharge data includes: Extracting the cycle number and average discharge depth of the battery as input variables, and constructing a nonlinear functional relationship based on historical capacity decay data, wherein the actual capacity value is inversely proportional to the square root of the cycle number and directly proportional to the square of the average discharge depth; Calibrate the attenuation coefficient in the nonlinear functional relationship according to the battery type, wherein the attenuation coefficient includes a first coefficient reflecting the cycle aging rate and a second coefficient reflecting the influence of deep discharge; The calibrated attenuation coefficient, the number of cycles obtained in real time, and the average discharge depth are substituted into the nonlinear function relationship to dynamically calculate the current actual capacity value, which is used as the capacity reference parameter of the ampere-hour integration method to obtain nonlinear capacity attenuation data.

[0006] Furthermore, when the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value, including: In the charging state, the voltage hysteresis curve is dynamically calibrated based on the battery's charge and discharge history data. The voltage hysteresis curve reflects the voltage difference between the charge and discharge paths in the current cycle; When the initial SOC value is ≥90%, the charging voltage value is collected in real time and compared with the calibrated charging path hysteresis curve. If the difference between the current voltage and the calibration curve exceeds the preset threshold, the compensation method is triggered; The compensation method is used to dynamically shift and correct the hysteresis curve based on the magnitude and direction of the deviation difference in combination with real-time temperature data, wherein the temperature coefficient is calibrated through the hysteresis voltage offset experiment of the battery at different temperatures; The difference between the corrected hysteresis curve voltage and the real-time voltage is used as a basic compensation amount, multiplied by the temperature coefficient to generate a first correction factor, and the weight of the ampere-hour integration method is dynamically adjusted to a first preset value based on the numerical range of the first correction factor.

[0007] Furthermore, when the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient to increase the weight of the Kalman filter algorithm to a second preset value. The steps include: Continuously monitor the initial SOC value in the discharge state, and activate the polarization voltage dynamic compensation mode when the initial SOC value is detected to drop to 20% or below; Collect discharge current data in real time and calculate the current change gradient per unit time. At the same time, match the pre-calibrated temperature attenuation coefficient based on battery temperature and historical discharge data. The temperature attenuation coefficient reflects the nonlinear growth characteristics of the battery's internal resistance as the temperature decreases. Inputting the current change gradient and the temperature attenuation coefficient into a predefined nonlinear coupling function to generate a polarization voltage compensation amount, wherein the nonlinear coupling function satisfies: when the current change gradient increases or the temperature attenuation coefficient increases, the compensation amount increases exponentially; According to the absolute value range of the polarization voltage compensation amount, the weight of the Kalman filter algorithm is increased from the initial value to the second preset value in sections.

[0008] Furthermore, the steps of dynamically fusing the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feeding the SOC value back to a power prediction module of a battery management system include: Constructing a fusion error function with the first correction factor and the second correction factor as input variables, wherein the error function includes an absolute error between a current SOC estimate and a reference value and a sliding window statistic of historical error data; Iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on a gradient descent optimization algorithm, wherein the weight coefficient is adjusted according to the negative gradient direction of the error function in each iteration until the error converges to a preset threshold range; The compensation amounts of the first correction factor and the second correction factor are dynamically weighted and fused according to the optimized weight coefficient to generate a calibrated SOC value, and the weight coefficient of the current iteration and the error convergence state are fed back to the parameter self-learning module of the battery management system.

[0009] Furthermore, the step of iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on a gradient descent optimization algorithm includes: Set the initial weight coefficients, where the initial weight of the first correction factor is ω1, the initial weight of the second correction factor is ω2, and ω1+ω2=1; Calculating the output value of the fusion error function based on the current weight coefficient, and calculating the partial derivative of the error function with respect to ω1 and ω2, and determining the negative gradient direction of the error function; Update the weight coefficient along the negative gradient direction according to the preset learning rate, so that ω1'=ω1-μ·∂E / ∂ω1, ω2'=ω2-μ·∂E / ∂ω2, where μ is the learning rate, ∂E / ∂ω1 and ∂E / ∂ω2 are the partial derivatives of the error function with respect to the weight coefficient; Determine whether the updated error function value is less than the preset convergence threshold. If not, repeat the steps until the error converges. When the error converges, the current weight coefficient is locked as the optimal weight distribution scheme, and the historical iteration data is stored in the optimization parameter database of the battery management system.

[0010] The present invention also proposes a battery SOC intelligent monitoring and management device based on a precise power algorithm, comprising: An acquisition unit is used to obtain the voltage, current and temperature of the battery in real time, and calculate the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; A calculation unit is used to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively using a dynamic weight allocation algorithm, thereby correcting the initial SOC value, wherein: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, thereby increasing the weight of the Kalman filter algorithm to a second preset value; A feedback unit is used to dynamically fuse the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feed the SOC value back to the power prediction module of the battery management system.

[0011] The present invention also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned battery SOC intelligent monitoring and management method based on the precise power algorithm when executing the computer program.

[0012] The present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned battery SOC intelligent monitoring and management method based on a precise power algorithm.

[0013] The battery SOC intelligent monitoring and management method based on a precise power algorithm provided by the present invention has the following beneficial effects: (1) Through dynamic weight allocation and nonlinear voltage hysteresis / polarization compensation model, the estimation error in high / low SOC range (≥90% or ≤20%) is significantly reduced, and the accuracy in extreme scenarios is improved; (2) Dynamically adjust algorithm weights and compensation parameters based on battery aging status and real-time operating conditions (temperature, current change rate) to adapt to different battery attenuation levels and complex environmental fluctuations; (3) By fusing multiple correction factors through the gradient descent algorithm and feeding them back to the self-learning module, dynamic calibration of SOC estimation parameters is achieved, thus reducing the error accumulation rate in long-term use; (4) Dynamic cleaning of abnormal data and nonlinear modeling of capacity attenuation can reduce the input error of the ampere-hour integration method and improve the benchmark accuracy of the initial SOC value. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 1 is a flow chart of a method for intelligently monitoring and managing battery SOC based on a precise power algorithm in one embodiment of the present invention; Figure 2 This is a structural block diagram of a battery SOC intelligent monitoring and management device based on a precise power algorithm in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0015] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] Reference Figure 1 , which is a flow chart of a battery SOC intelligent monitoring and management method based on a precise power algorithm proposed by the present invention, the method includes the following steps: S1, obtaining the voltage, current and temperature of the battery in real time, and calculating the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; S2, using a dynamic weight allocation algorithm to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively, thereby correcting the initial SOC value, wherein: S21, when the battery is in a charging state and the initial SOC value is ≥90%, introducing a voltage hysteresis characteristic compensation model, using the product of the battery's temperature coefficient and the voltage change rate as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; S22, when the battery is in a discharged state and the initial SOC value is ≤20%, activating the polarization voltage compensation model, combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient to generate a second correction factor, and increasing the weight of the Kalman filter algorithm to a second preset value; S3, dynamically fusing the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feeding the SOC value back to a power prediction module of the battery management system.

[0018] In one embodiment, the step of acquiring the voltage, current, and temperature of the battery in real time and calculating the initial SOC value of the battery using the ampere-hour integration method in combination with historical charge and discharge data of the battery includes: Dynamically screen outliers in real-time sampled voltage, current, and temperature data, perform standard deviation analysis on continuously sampled data using a sliding time window, remove data that exceeds the preset fluctuation range, and perform interpolation processing; generating nonlinear capacity decay data based on the number of cycles, average discharge depth, and capacity decay trend in the historical charge and discharge data, wherein the actual capacity is related to the square root of the number of cycles and the square of the average discharge depth; Based on the current temperature threshold and charge and discharge current direction, the corresponding ampere-hour integral calculation mode is dynamically selected: under low-temperature discharge conditions, a temperature compensation coefficient is introduced to correct the nominal capacity, and under normal temperature charging conditions, the nominal capacity is directly used for calculation, and the calculation results of the corresponding intervals are integrated through the weight coefficient.

[0019] In the specific implementation process, the sliding window standard deviation analysis is as follows: Set the sliding time window length to N=10 (corresponding to a 100ms sampling period), and store 10 consecutive groups of original sampling values ​​of voltage U, current I, and temperature T in the window. The standard deviation calculation formula is: ,in, is the kth sample value in the window, is the mean of the data in the window, is the standard deviation of the data within the window.

[0020] The method for determining and processing abnormal values ​​in the sampled voltage, current and temperature data is as follows: If the current sampling value satisfy , it is determined to be an abnormal point. According to the formula, it can be seen that Corresponding to the collected data and interpolation processing, it is understood as interpolation compensation, According to this formula, we can understand that the interpolation process is to use The average of the two normal sampling values ​​before and after is used to replace the abnormal value.

[0021] Case 1: The impact of different window lengths on data quality;

[0022] The generation of nonlinear capacity decay data is essentially the construction of nonlinear capacity decay modeling, specifically extracting the number of cycles and average discharge depth of the battery as input variables, and constructing a nonlinear function relationship based on historical capacity decay data, wherein the actual capacity value is inversely proportional to the square root of the number of cycles and directly proportional to the square of the average discharge depth; calibrating the attenuation coefficient in the nonlinear function relationship according to the battery type, wherein the attenuation coefficient includes a first coefficient reflecting the cycle aging rate and a second coefficient reflecting the influence of deep discharge; substituting the calibrated attenuation coefficient and the number of cycles and average discharge depth obtained in real time into the nonlinear function relationship, dynamically calculating the current actual capacity value, and using it as the capacity reference parameter of the ampere-hour integration method to obtain nonlinear capacity decay data.

[0023] The model is constructed using the formula , where Indicates the nominal capacity of the battery when it leaves the factory (for example, 50Ah). Indicates the cumulative number of charge and discharge cycles of the battery. Indicates the historical average discharge depth.

[0024] Case 2: Capacity fading model fitting comparison

[0025] Conclusion, through Reflecting the decreasing effect of cyclic aging rate (fast decay in the early stage and slow decline in the later stage), through Enhance the accelerated decay effect of deep discharge.

[0026] Based on the current temperature threshold and the direction of charge and discharge current, the corresponding ampere-hour integral calculation mode is dynamically selected. Under low-temperature discharge conditions, the temperature compensation coefficient is introduced to correct the nominal capacity. Under normal temperature charging conditions, the nominal capacity is directly used for calculation, and the calculation results of the corresponding intervals are integrated through the weight coefficient. Among them, the calculation formula is dynamically switched to: Low temperature discharge mode in, Indicates the Coulomb efficiency, which is 0.98. Indicates the temperature compensation coefficient, the coefficient is 0.005 / ℃, Indicates the absolute value of the ambient temperature.

[0027] Normal temperature charging mode

[0028] The above weight coefficient fusion calculation refers to the case when the temperature is in the transition range (-5℃ < T ≤ 5℃), and the weight coefficient ω is used for hybrid calculation. , where the weight coefficient ω is distributed linearly according to temperature .

[0029] Case 3: Comparison of SOC initial value calculation errors at different temperatures

[0030] In one embodiment, when the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the battery's temperature coefficient and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value, including: In the charging state, the voltage hysteresis curve is dynamically calibrated based on the battery's charge and discharge history data. The voltage hysteresis curve reflects the voltage difference between the charge and discharge paths in the current cycle; When the initial SOC value is ≥90%, the charging voltage value is collected in real time and compared with the calibrated charging path hysteresis curve. If the difference between the current voltage and the calibration curve exceeds the preset threshold, the compensation method is triggered; The compensation method is used to dynamically shift and correct the hysteresis curve based on the magnitude and direction of the deviation difference in combination with real-time temperature data, wherein the temperature coefficient is calibrated through the hysteresis voltage offset experiment of the battery at different temperatures; The difference between the corrected hysteresis curve voltage and the real-time voltage is used as a basic compensation amount, multiplied by the temperature coefficient to generate a first correction factor, and the weight of the ampere-hour integration method is dynamically adjusted to a first preset value based on the numerical range of the first correction factor.

[0031] In the specific implementation process, the voltage hysteresis curve is dynamically calibrated based on the battery's charge and discharge history data. The historical data is collected by extracting the voltage SOC data of the most recent K=5 complete charge and discharge cycles, and recording the voltage values ​​of the charge (Chg) and discharge (Dchg) paths respectively. The dynamic calibration formula is:

[0032] As shown in this formula, when SOC=90%, the average hysteresis voltage difference of 5 cycles is 0.12V.

[0033] The voltage hysteresis curve reflects the voltage difference between the charge and discharge paths in the current cycle, but the curve needs to be smoothed and the exponentially weighted moving average (EWMA) is used to update the hysteresis curve to suppress noise interference. For example, Case 4; Case 4: Schematic diagram of dynamic hysteresis curve calibration

[0034] Conclusion,Dynamic calibration adapts to the problem of hysteresis characteristic offset caused by battery aging and reduces the error increasing with cycles.

[0035] If it is detected that the difference between the current voltage and the calibration curve exceeds a preset threshold, the compensation method is triggered, and the voltage deviation is calculated as follows: ,in is the measured charging voltage, is the SOC reference voltage corresponding to the calibration curve; the condition for triggering the compensation method is ,when When the battery polarization effect causes the voltage to be positively biased, When , the electrolyte concentration gradient causes a negative voltage bias, refer to Case 5; Case 5: Typical deviations in different SOC ranges

[0036] The compensation method is used to dynamically shift and correct the hysteresis curve based on the magnitude and direction of the deviation difference in combination with real-time temperature data. In the step of calibrating the temperature coefficient through the hysteresis voltage offset experiment of the battery at different temperatures, the dynamic shift correction method is as follows: Curve translation formula In one example, the sample data is as follows

[0037] The example calculation shows that when T = -10°C, the curve shifts upward by 2.00×(−10−25) = −70 mv.

[0038] In the step of using the difference between the corrected hysteresis curve voltage and the real-time voltage as a basic compensation amount, multiplying it by the temperature coefficient to generate a first correction factor, and dynamically adjusting the weight of the ampere-hour integration method to a first preset value based on the numerical range of the first correction factor, the first correction factor is calculated as:

[0039] In this formula, Indicates the rate of voltage change; The numerical range of the first correction factor, and the adjustment rule for dynamically adjusting the weight of the ampere-hour integration method to the first preset value are:

[0040] In one embodiment, when the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, and the weight of the Kalman filter algorithm is increased to a second preset value, including: Continuously monitor the initial SOC value in the discharge state, and activate the polarization voltage dynamic compensation mode when the initial SOC value is detected to drop to 20% or below; Collect discharge current data in real time and calculate the current change gradient per unit time. At the same time, match the pre-calibrated temperature attenuation coefficient based on battery temperature and historical discharge data. The temperature attenuation coefficient reflects the nonlinear growth characteristics of the battery's internal resistance as the temperature decreases. Inputting the current change gradient and the temperature attenuation coefficient into a predefined nonlinear coupling function to generate a polarization voltage compensation amount, wherein the nonlinear coupling function satisfies: when the current change gradient increases or the temperature attenuation coefficient increases, the compensation amount increases exponentially; According to the absolute value range of the polarization voltage compensation amount, the weight of the Kalman filter algorithm is increased from the initial value to the second preset value in sections.

[0041] In the specific implementation process, after the polarization voltage dynamic compensation mode is activated, the current change gradient calculation is performed The time interval is 5s. For example, when the current drops from 10A to 5A, the gradient is -1A / s. The matching pre-calibrated temperature attenuation coefficient is as follows:

[0042] The predefined nonlinear coupling function generates polarization voltage compensation in the following way: , where is the polarization intensity coefficient, is the reference temperature.

[0043] In one embodiment, the steps of dynamically fusing the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feeding the SOC value back to a power prediction module of a battery management system include: Constructing a fusion error function with the first correction factor and the second correction factor as input variables, wherein the error function includes an absolute error between a current SOC estimate and a reference value and a sliding window statistic of historical error data; Iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on a gradient descent optimization algorithm, wherein the weight coefficient is adjusted according to the negative gradient direction of the error function in each iteration until the error converges to a preset threshold range; The compensation amounts of the first correction factor and the second correction factor are dynamically weighted and fused according to the optimized weight coefficient to generate a calibrated SOC value, and the weight coefficient of the current iteration and the error convergence state are fed back to the parameter self-learning module of the battery management system.

[0044] In a specific implementation process, the step of iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on the gradient descent optimization algorithm includes: Set the initial weight coefficients, where the initial weight of the first correction factor is ω1, the initial weight of the second correction factor is ω2, and ω1+ω2=1; Calculating the output value of the fusion error function based on the current weight coefficient, and calculating the partial derivative of the error function with respect to ω1 and ω2, and determining the negative gradient direction of the error function; Update the weight coefficient along the negative gradient direction according to the preset learning rate, so that ω1'=ω1-μ·∂E / ∂ω1, ω2'=ω2-μ·∂E / ∂ω2, where μ is the learning rate, ∂E / ∂ω1 and ∂E / ∂ω2 are the partial derivatives of the error function with respect to the weight coefficient; Determine whether the updated error function value is less than the preset convergence threshold. If not, repeat the steps until the error converges. When the error converges, the current weight coefficient is locked as the optimal weight distribution scheme, and the historical iteration data is stored in the optimization parameter database of the battery management system.

[0045] Reference Attachment Figure 2 The present invention also proposes a battery SOC intelligent monitoring and management device based on a precise power algorithm, comprising: An acquisition unit is used to obtain the voltage, current and temperature of the battery in real time, and calculate the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; The calculation unit is used to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively using a dynamic weight allocation algorithm, thereby correcting the initial SOC value, wherein: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, thereby increasing the weight of the Kalman filter algorithm to a second preset value; A feedback unit is used to dynamically fuse the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feed the SOC value back to the power prediction module of the battery management system.

[0046] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design 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 computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0047] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0048] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0049] In summary, the battery voltage, current, temperature, and historical data are acquired in real time, and the initial SOC value is calculated using the ampere-hour integration method. When the battery is in the charging state and the SOC is ≥90%, a first correction factor is generated based on the voltage hysteresis characteristic and the temperature coefficient, dynamically reducing the ampere-hour integration weight. When the battery is in the discharging state and the SOC is ≤20%, a second correction factor is generated by combining the polarization voltage and the temperature attenuation coefficient to increase the Kalman filter weight. The correction factors are integrated through a gradient descent optimization algorithm and closed-loop feedback, outputting the calibrated SOC value. Through dynamic weight allocation, a nonlinear compensation model, and a closed-loop self-optimization mechanism, this invention addresses the large estimation errors in extreme SOC intervals and the poor adaptability of traditional methods, significantly improving the accuracy and reliability of battery management.

[0050] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0051] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0052] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A battery SOC intelligent monitoring and management method based on a precise power algorithm, characterized by: The following steps are involved: Acquire the voltage, current and temperature of the battery in real time, and calculate the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; The dynamic weight allocation algorithm is used to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively, thereby correcting the initial SOC value, wherein: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, thereby increasing the weight of the Kalman filter algorithm to a second preset value; The first correction factor and the second correction factor are dynamically integrated through a gradient descent optimization algorithm to generate a calibrated SOC value, and the SOC value is fed back to the power prediction module of the battery management system.

2. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 1 is characterized in that: The step of obtaining the voltage, current, and temperature of the battery in real time and calculating the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery includes: Dynamically screen outliers in real-time sampled voltage, current, and temperature data, perform standard deviation analysis on continuously sampled data using a sliding time window, remove data that exceeds the preset fluctuation range, and perform interpolation processing; generating nonlinear capacity decay data based on the number of cycles, average discharge depth, and capacity decay trend in the historical charge and discharge data, wherein the actual capacity is related to the square root of the number of cycles and the square of the average discharge depth; Based on the current temperature threshold and charge and discharge current direction, the corresponding ampere-hour integral calculation mode is dynamically selected: under low-temperature discharge conditions, a temperature compensation coefficient is introduced to correct the nominal capacity, and under normal temperature charging conditions, the nominal capacity is directly used for calculation, and the calculation results of the corresponding intervals are integrated through the weight coefficient.

3. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 2 is characterized in that: The step of generating nonlinear capacity decay data according to the number of cycles, average discharge depth, and capacity decay trend in the historical charge and discharge data comprises: Extracting the cycle number and average discharge depth of the battery as input variables, and constructing a nonlinear functional relationship based on historical capacity decay data, wherein the actual capacity value is inversely proportional to the square root of the cycle number and directly proportional to the square of the average discharge depth; Calibrate the attenuation coefficient in the nonlinear functional relationship according to the battery type, wherein the attenuation coefficient includes a first coefficient reflecting the cycle aging rate and a second coefficient reflecting the influence of deep discharge; The calibrated attenuation coefficient, the number of cycles obtained in real time, and the average discharge depth are substituted into the nonlinear function relationship to dynamically calculate the current actual capacity value, which is used as the capacity reference parameter of the ampere-hour integration method to obtain nonlinear capacity attenuation data.

4. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 1 is characterized in that: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value, including: In the charging state, the voltage hysteresis curve is dynamically calibrated based on the battery's charge and discharge history data. The voltage hysteresis curve reflects the voltage difference between the charge and discharge paths in the current cycle; When the initial SOC value is ≥90%, the charging voltage value is collected in real time and compared with the calibrated charging path hysteresis curve. If the difference between the current voltage and the calibration curve exceeds the preset threshold, the compensation method is triggered; The compensation method is used to dynamically shift and correct the hysteresis curve based on the magnitude and direction of the deviation difference in combination with real-time temperature data, wherein the temperature coefficient is calibrated through the hysteresis voltage offset experiment of the battery at different temperatures; The difference between the corrected hysteresis curve voltage and the real-time voltage is used as a basic compensation amount, multiplied by the temperature coefficient to generate a first correction factor, and the weight of the ampere-hour integration method is dynamically adjusted to a first preset value based on the numerical range of the first correction factor.

5. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 1 is characterized in that: When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient to increase the weight of the Kalman filter algorithm to a second preset value, including the following steps: Continuously monitor the initial SOC value in the discharge state, and activate the polarization voltage dynamic compensation mode when the initial SOC value is detected to drop to 20% or below; Collect discharge current data in real time and calculate the current change gradient per unit time. At the same time, match the pre-calibrated temperature attenuation coefficient based on battery temperature and historical discharge data. The temperature attenuation coefficient reflects the nonlinear growth characteristics of the battery's internal resistance as the temperature decreases. Inputting the current change gradient and the temperature attenuation coefficient into a predefined nonlinear coupling function to generate a polarization voltage compensation amount, wherein the nonlinear coupling function satisfies: when the current change gradient increases or the temperature attenuation coefficient increases, the compensation amount increases exponentially; According to the absolute value range of the polarization voltage compensation amount, the weight of the Kalman filter algorithm is increased from the initial value to the second preset value in sections.

6. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 1 is characterized in that: The steps of dynamically fusing the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feeding the SOC value back to a power prediction module of a battery management system include: Constructing a fusion error function with the first correction factor and the second correction factor as input variables, wherein the error function includes an absolute error between a current SOC estimate and a reference value and a sliding window statistic of historical error data; Iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on a gradient descent optimization algorithm, wherein the weight coefficient is adjusted according to the negative gradient direction of the error function in each iteration until the error converges to a preset threshold range; The compensation amounts of the first correction factor and the second correction factor are dynamically weighted and fused according to the optimized weight coefficient to generate a calibrated SOC value, and the weight coefficient of the current iteration and the error convergence state are fed back to the parameter self-learning module of the battery management system.

7. The battery SOC intelligent monitoring and management method based on the precise power algorithm according to claim 1 is characterized in that: The step of iteratively optimizing the weight distribution of the first correction factor and the second correction factor based on a gradient descent optimization algorithm includes: Set the initial weight coefficients, where the initial weight of the first correction factor is ω1, the initial weight of the second correction factor is ω2, and ω1+ω2=1; Calculating the output value of the fusion error function based on the current weight coefficient, and calculating the partial derivative of the error function with respect to ω1 and ω2, and determining the negative gradient direction of the error function; Update the weight coefficient along the negative gradient direction according to the preset learning rate, so that ω1'=ω1-μ·∂E / ∂ω1, ω2'=ω2-μ·∂E / ∂ω2, where μ is the learning rate, ∂E / ∂ω1 and ∂E / ∂ω2 are the partial derivatives of the error function with respect to the weight coefficient; Determine whether the updated error function value is less than the preset convergence threshold. If not, repeat the steps until the error converges. When the error converges, the current weight coefficient is locked as the optimal weight distribution scheme, and the historical iteration data is stored in the optimization parameter database of the battery management system.

8. A battery SOC intelligent monitoring and management device based on a precise power algorithm, characterized in that: include: An acquisition unit is used to obtain the voltage, current and temperature of the battery in real time, and calculate the initial SOC value of the battery using the ampere-hour integration method in combination with the historical charge and discharge data of the battery; The calculation unit is used to adjust the calculation weights of the ampere-hour integration method and the Kalman filter algorithm respectively using a dynamic weight allocation algorithm, thereby correcting the initial SOC value, wherein: When the battery is in a charging state and the initial SOC value is ≥90%, a voltage hysteresis characteristic compensation model is introduced, and the product of the temperature coefficient of the battery and the voltage change rate is used as a first correction factor to adjust the weight of the ampere-hour integration method to a first preset value; When the battery is in a discharged state and the initial SOC value is ≤20%, the polarization voltage compensation model is activated, and a second correction factor is generated by combining the nonlinear relationship between the current change gradient and the temperature attenuation coefficient, thereby increasing the weight of the Kalman filter algorithm to a second preset value; A feedback unit is used to dynamically fuse the first correction factor and the second correction factor through a gradient descent optimization algorithm to generate a calibrated SOC value, and feed the SOC value back to the power prediction module of the battery management system.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the battery SOC intelligent monitoring and management method based on the precise power algorithm as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the battery SOC intelligent monitoring and management method based on a precise power algorithm according to any one of claims 1 to 7 are implemented.

Images