Lithium battery pack health state prediction system based on big data statistics

Abstract

The invention relates to the technical field of battery pack health state prediction systems, in particular to a lithium battery pack health state prediction system based on big data statistics, which comprises a battery detection module, an environment detection module, a battery information storage module, a control module and a communication module, the battery detection module is used for detection; the environment detection module is used for detecting and obtaining the current environment temperature and transmitting the current environment temperature to the control module. The battery information storage module is used for storing the maximum delivery capacity of the battery, the delivery internal resistance of the battery and the delivery optimal working temperature of the battery, and transmitting to the control module; the control module calculates the total number of times of the remaining life of the battery according to data acquired by the battery detection module, the environment detection module and the battery information storage module; the communication module transmits the total number of battery remaining life times to a user side. By combining a plurality of data sources, the prediction model can dynamically adapt to the real-time change of the battery, and the prediction accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery pack health status prediction systems, and in particular to a lithium battery pack health status prediction system based on big data statistics. Background Art

[0002] The lithium battery pack health status prediction system refers to the real-time monitoring and prediction of the battery health status by collecting and analyzing a large amount of data generated by the lithium battery pack during use (such as battery voltage, current, temperature, number of charge and discharge cycles, etc.), using big data analysis technology and statistical models. Through in-depth analysis of historical data and real-time data, the system identifies the battery pack's decay mode, potential faults and its remaining life, thereby achieving accurate assessment and early warning of the battery pack's health status. Through this prediction system, potential problems can be discovered in advance, battery management strategies can be optimized, battery life can be extended, and safety and reliability during use can be ensured.

[0003] The application document with publication number CN114565172A discloses a battery remaining life prediction model construction and battery remaining life prediction method, including: obtaining characteristic data of each historical usage cycle of a sample battery and the corresponding battery capacity, the characteristic data being characteristic data characterizing the health status of the sample battery; inputting the characteristic data into an initial model to obtain an output result; training the initial model based on the relationship between the output result and the characteristic data of the next historical usage cycle to obtain a characteristic data prediction model; inputting the characteristic data into another initial model to obtain an output result; training the initial model based on the relationship between the output result and the battery capacity to obtain a battery capacity prediction model; cascading the output end of the characteristic data prediction model with the input end of the battery capacity prediction model to construct a battery remaining life prediction model.

[0004] Existing technologies usually rely on historical data and statistical models for prediction, but they are mostly based on static models or simple mathematical relationships and lack comprehensive processing of real-time data. Summary of the invention

[0005] The purpose of the present invention is to provide a dynamic prediction method. In view of the above-mentioned shortcomings, a lithium battery pack health status prediction system based on big data statistics is proposed.

[0006] The present invention adopts the following technical solution: A lithium battery pack health status prediction system based on big data statistics, the system comprising a battery detection module, an environmental detection module, a battery information storage module, a control module and a communication module; the battery detection module is used to detect and obtain the current battery internal resistance, the current battery capacity, the current battery temperature, the total number of charge and discharge cycles used by the current battery and the current discharge capacity, and transmit them to the control module; the environmental detection module is used to detect and obtain the current ambient temperature, and transmit it to the control module; the battery information storage module is used to store the maximum capacity of the battery when it leaves the factory, the internal resistance of the battery when it leaves the factory and the optimal operating temperature of the battery when it leaves the factory, and transmit them to the control module; the control module calculates the total number of times the battery's remaining life is obtained based on the data obtained by the battery detection module, the environmental detection module and the battery information storage module, and transmits the total number of times the battery's remaining life is obtained to the communication module; the communication module transmits the total number of times the battery's remaining life is obtained to the user end.

[0007] Optionally, the control module derives a temperature sensitivity index based on the optimal operating temperature of the battery leaving the factory and the current battery temperature, derives an internal resistance change index based on the internal resistance of the battery leaving the factory and the current internal resistance of the battery, derives an internal resistance influence coefficient based on the current battery capacity, the maximum capacity of the battery leaving the factory, the internal resistance change index, the internal resistance of the battery leaving the factory and the total number of charge and discharge cycles of the current battery, derives a discharge depth based on the current discharge capacity and the maximum capacity of the battery leaving the factory, derives a cycle number influence coefficient based on the current battery capacity, the maximum capacity of the battery leaving the factory and the total number of charge and discharge cycles of the current battery, derives a cycle number influence index based on the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the total number of charge and discharge cycles of the current battery and the discharge depth, derives the total number of remaining battery life based on the current battery capacity, the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the cycle number influence index, the internal resistance influence coefficient, the internal resistance change index, the internal resistance of the battery leaving the factory, the temperature sensitivity index, the current battery temperature, the optimal operating temperature of the battery leaving the factory and the current ambient temperature.

[0008] Optionally, the battery detection module includes an internal resistance detection submodule, a capacity detection submodule, a temperature detection submodule and a charge and discharge cycle detection submodule; the internal resistance detection submodule is used to detect and obtain the current battery internal resistance, and transmit it to the control module; the capacity detection submodule is used to detect and obtain the current battery capacity, and transmit it to the control module; The temperature detection submodule is used to detect and obtain the current battery temperature, and transmit it to the control module; the charge and discharge cycle detection submodule is used to detect and obtain the total number of charge and discharge cycles currently used by the battery and the current discharge capacity used, and transmit them to the control module.

[0009] Optionally, the charge and discharge cycle detection submodule includes a charge and discharge state judgment unit, a counting unit and a capacity detection unit; the charge and discharge state judgment unit is used to monitor the voltage and current of the battery, and judge whether the battery is in a charging or discharging state according to the voltage and current of the battery; the counting unit is used to count the charging and discharging of the battery and obtain the total number of charge and discharge cycles currently used by the battery, and transmit it to the control module; the capacity detection unit is used to detect and obtain the capacity currently used for discharge, and transmit it to the control module.

[0010] Optionally, when the control module calculates the total number of times the remaining battery life is to be consumed, the following formula is satisfied: ; Where Rul is the total number of times the battery has remaining life, C cr is the current battery capacity, C pre is the maximum capacity of the battery when it leaves the factory, α is the cycle number influence coefficient, cd is the cycle number influence index, β is the internal resistance influence coefficient, ΔR is the internal resistance change index, R pre is the internal resistance of the battery when it leaves the factory. is the temperature sensitive index, T cr is the current battery temperature, T ref is the optimal operating temperature of the battery when it leaves the factory, T e is the current ambient temperature, and floor() is the rounding function.

[0011] The beneficial effects achieved by the present invention are: By combining multiple data sources (battery data, environmental data, factory data, etc.), the prediction model can dynamically adapt to the real-time changes of the battery, improving the accuracy of the prediction; In addition to considering basic parameters such as battery capacity and internal resistance, multiple factors such as temperature sensitivity index and cycle number influence coefficient are also introduced to comprehensively evaluate the battery health status; Based on the actual operating conditions of the battery (such as charge and discharge cycles, battery internal resistance, ambient temperature, etc.), a multi-dimensional analysis is conducted, and the influence of internal and external factors is comprehensively considered to obtain a more accurate remaining life prediction result.

[0012] To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and description and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the overall structure of the present invention; Figure 2 It is a structural schematic diagram of the battery detection module in the present invention; Figure 3 It is a structural schematic diagram of the charge-discharge cycle detection submodule in the present invention; Figure 4 A relationship diagram between the temperature sensitive indicator and the current battery temperature in the present invention; Figure 5 This is a schematic diagram of the overall structure of Embodiment 2 of the present invention; Figure 6 This is a relationship diagram between the total number of charge and discharge cycles remaining in the battery and the current battery resistance in the second embodiment of the present invention. DETAILED DESCRIPTION

[0014] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual dimensions. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0015] Embodiment 1: This embodiment provides a lithium battery pack health status prediction system based on big data statistics, combined with Figures 1 to 4 shown.

[0016] A lithium battery pack health status prediction system based on big data statistics, the system comprising a battery detection module, an environmental detection module, a battery information storage module, a control module and a communication module; the battery detection module is used to detect and obtain the current battery internal resistance, the current battery capacity, the current battery temperature, the total number of charge and discharge cycles used by the current battery and the current discharge capacity, and transmit them to the control module; the environmental detection module is used to detect and obtain the current ambient temperature, and transmit it to the control module; the battery information storage module is used to store the maximum capacity of the battery when it leaves the factory, the internal resistance of the battery when it leaves the factory and the optimal operating temperature of the battery when it leaves the factory, and transmit them to the control module; the control module calculates the total number of times the battery's remaining life is obtained based on the data obtained by the battery detection module, the environmental detection module and the battery information storage module, and transmits the total number of times the battery's remaining life is obtained to the communication module; the communication module transmits the total number of times the battery's remaining life is obtained to the user end.

[0017] Optionally, the control module derives a temperature sensitivity index based on the optimal operating temperature of the battery leaving the factory and the current battery temperature, derives an internal resistance change index based on the internal resistance of the battery leaving the factory and the current internal resistance of the battery, derives an internal resistance influence coefficient based on the current battery capacity, the maximum capacity of the battery leaving the factory, the internal resistance change index, the internal resistance of the battery leaving the factory and the total number of charge and discharge cycles of the current battery, derives a discharge depth based on the current discharge capacity and the maximum capacity of the battery leaving the factory, derives a cycle number influence coefficient based on the current battery capacity, the maximum capacity of the battery leaving the factory and the total number of charge and discharge cycles of the current battery, derives a cycle number influence index based on the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the total number of charge and discharge cycles of the current battery and the discharge depth, derives the total number of remaining battery life, that is, the remaining charge and discharge times, based on the current battery capacity, the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the cycle number influence index, the internal resistance influence coefficient, the internal resistance change index, the internal resistance of the battery leaving the factory, the temperature sensitivity index, the current battery temperature, the optimal operating temperature of the battery leaving the factory and the current ambient temperature.

[0018] Optionally, the battery detection module includes an internal resistance detection submodule, a capacity detection submodule, a temperature detection submodule and a charge and discharge cycle detection submodule; the internal resistance detection submodule is used to detect and obtain the current battery internal resistance, and transmit it to the control module; the capacity detection submodule is used to detect and obtain the current battery capacity, and transmit it to the control module; The temperature detection submodule is used to detect and obtain the current battery temperature, and transmit it to the control module; the charge and discharge cycle detection submodule is used to detect and obtain the total number of charge and discharge cycles currently used by the battery and the current discharge capacity used, and transmit them to the control module.

[0019] Optionally, the charge and discharge cycle detection submodule includes a charge and discharge state judgment unit, a counting unit and a capacity detection unit; the charge and discharge state judgment unit is used to monitor the voltage and current of the battery, and judge whether the battery is in a charging or discharging state according to the voltage and current of the battery; the counting unit is used to count the charging and discharging of the battery and obtain the total number of charge and discharge cycles currently used by the battery, and transmit it to the control module; the capacity detection unit is used to detect and obtain the capacity currently used for discharge, and transmit it to the control module.

[0020] Optionally, when the control module calculates the total number of times the remaining battery life is to be consumed, the following formula is satisfied: ; Where Rul is the total number of times the battery has remaining life, C cr is the current battery capacity, C preis the maximum capacity of the battery when it leaves the factory, α is the cycle number influence coefficient, cd is the cycle number influence index, β is the internal resistance influence coefficient, ΔR is the internal resistance change index, R pre is the internal resistance of the battery when it leaves the factory. is the temperature sensitive index, T cr is the current battery temperature, T ref is the optimal operating temperature of the battery when it leaves the factory, T e is the current ambient temperature, and floor() is the rounding function.

[0021] Optionally, the control module satisfies the following formula when calculating: .

[0022] .

[0023] .

[0024] .

[0025] .

[0026] .

[0027] Among them, N cy is the total number of charge and discharge cycles currently used by the battery, fd is the depth of discharge; C fd is the capacity used for current discharge; R cr is the current internal resistance of the battery.

[0028] Specifically, floor is a rounding-down function; the units of the current battery capacity, the maximum capacity of the battery when it leaves the factory, and the capacity currently used for discharge are all ampere-hours, and the maximum capacity of the battery when it leaves the factory is obtained by those skilled in the art by querying the factory parameters of the battery; the units of the internal resistance of the battery when it leaves the factory and the current internal resistance of the battery are both ohms, and the internal resistance of the battery when it leaves the factory is obtained by those skilled in the art by querying the factory parameters of the battery.

[0029] The above units are only examples, and those skilled in the art may set different units according to actual needs when implementing this solution.

[0030] When the control module calculates the total number of times the battery's remaining life is reached, refer to the following program code: import math # Input data C_cr = # Current battery capacity (specific value required) C_pre = # Maximum capacity of the battery when it leaves the factory (specific value required) N_cy = # The total number of charge and discharge cycles currently used by the battery (specific value must be provided) fd = # discharge depth (need to provide specific value) R_cr = # Current battery internal resistance (specific value required) R_pre = # Internal resistance of the battery when it leaves the factory (specific value required) T_cr = # Current battery temperature (specific value required) T_ref = # The optimal operating temperature of the battery when it leaves the factory (specific value must be provided) T_e = # Current ambient temperature (specific value required) # Calculate each parameter cd = C_pre * math.exp(-alpha * N_cy + fd) # cd is the index affected by the number of cycles # Cycle times influence coefficient alpha alpha = -math.log(C_cr / C_pre) / N_cy # Internal resistance change rate delta_R = abs(R_cr - R_pre) / R_pre # Internal resistance influence coefficient beta beta = -math.log(C_cr / C_pre) / (delta_R + (delta_R / N_cy)) # Temperature sensitivity index δ delta = abs(T_cr - T_ref) / abs(T_e - T_ref) # Calculation of Rul Rul = math.floor( (C_cr - 0.8 * C_pre) / (-alpha * cd - beta * delta_R / R_pre - 0.02 * math.exp(-delta *(T_cr - T_ref))) * delta ) # Output results print("cd =", cd) print("alpha =", alpha) print("delta_R =", delta_R) print("beta =", beta) print("delta =", delta) print("Rul =", Rul) This embodiment solves the problem that traditional prediction systems can only analyze static data. This application goes beyond the limitations of existing technologies by combining diversified data sources, real-time monitoring and comprehensive analysis, and provides a more accurate, real-time and adaptable battery remaining life prediction system.

[0031] Embodiment 2: This embodiment includes all the contents of Embodiment 1, and provides a lithium battery pack health status prediction system based on big data statistics, combined with Figure 5 and Figure 6 shown.

[0032] A lithium battery pack health status prediction system based on big data statistics, the system also includes a battery health judgment module and an alarm module; The battery information storage module is also used to store the safety value of the battery internal resistance and transmit it to the control module; The control module obtains the internal resistance change rate according to the current battery internal resistance, the internal resistance of the battery at the factory and the total number of charge and discharge cycles currently used by the battery, obtains an indicator for predicting the total number of charge and discharge cycles remaining for the battery according to the safety value of the battery internal resistance, the current battery internal resistance and the internal resistance change rate, obtains an internal resistance prediction indicator according to the current battery internal resistance, the internal resistance change rate and the indicator for predicting the total number of charge and discharge cycles remaining for the battery, and transmits the internal resistance prediction indicator to the battery health judgment module; The battery health judgment module obtains information about whether the battery health status is good or bad according to the internal resistance prediction index, and transmits the information about whether the battery health status is good or bad to the communication module and the alarm module; The communication module transmits information about whether the battery health status is good or bad to the user end; The alarm module implements an alarm based on the information that the battery health status is poor or good.

[0033] Specifically, the battery health judgment module refers to the following principles when making judgments: when the internal resistance prediction index is greater than or equal to the selection threshold of the internal resistance prediction index, it indicates that the battery health state is poor; when the internal resistance prediction index is less than the selection threshold of the internal resistance prediction index, it indicates that the battery health state is good; the selection threshold of the internal resistance prediction index is set by technical personnel in this field.

[0034] Optionally, when the control module calculates the internal resistance prediction index, the following formula is satisfied: .

[0035] .

[0036] .

[0037] Among them, R yc is the internal resistance prediction index, R rate is the internal resistance change rate, N future To predict the total number of charge and discharge cycles remaining in the battery; R safe is the safe value of the battery internal resistance.

[0038] Specifically, the unit of the safe value of the battery internal resistance is ohm.

[0039] When the control module calculates the internal resistance prediction index, it refers to the following program code: # Define known parameters R_cr = # Current battery internal resistance (specific value required) R_pre = # Internal resistance of the battery before leaving the factory (specific value required) R_safe = # Safety value of battery internal resistance (specific value required) N_cy = # The total number of charge and discharge cycles of the current battery (specific value must be provided) # Calculate the internal resistance change rate R_rate R_rate = (R_cr - R_pre) / N_cy # Calculate and predict the total number of charge and discharge cycles remaining for the battery N_future N_future = (R_safe - R_cr) / R_rate # Calculate the internal resistance prediction index R_yc R_yc = R_cr + R_rate * N_future # Output results print("Internal resistance change rate R_rate =", R_rate) print("Predict the total number of charge and discharge cycles remaining for the battery N_future =", N_future) print("Internal resistance prediction index R_yc =", R_yc) The above units are only examples, and those skilled in the art may set different units according to actual needs when implementing this solution.

[0040] This embodiment solves the problem of the relatively single nature of traditional prediction systems. Through real-time data monitoring, intelligent analysis and multi-dimensional prediction, it improves the accuracy of battery life prediction while also enhancing safety and reliability. By comprehensively considering multiple factors such as internal resistance changes and temperature sensitivity, and combining alarm and health assessment modules, it can achieve early fault warning, real-time health monitoring, and accurate life prediction, ensuring that users obtain information about the battery health status in a timely manner and reducing the occurrence of battery failures and safety accidents.

[0041] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention description and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A lithium battery pack health status prediction system based on big data statistics, characterized in that: The system includes a battery detection module, an environment detection module, a battery information storage module, a control module and a communication module; The battery detection module is used to detect and obtain the current battery internal resistance, current battery capacity, current battery temperature, the total number of charge and discharge cycles currently used by the battery and the current discharge capacity used, and transmit them to the control module; The environment detection module is used to detect and obtain the current environment temperature and transmit it to the control module; The battery information storage module is used to store the maximum capacity of the battery before leaving the factory, the internal resistance of the battery before leaving the factory, and the optimal operating temperature of the battery before leaving the factory, and transmit them to the control module; The control module calculates the total number of times the battery's remaining life is available based on the data acquired by the battery detection module, the environment detection module, and the battery information storage module, and transmits the total number of times the battery's remaining life is available to the communication module; The communication module transmits the total number of times the battery's remaining life span is to the user end.

2. A lithium battery pack health status prediction system based on big data statistics as claimed in claim 1, characterized in that: The control module obtains a temperature sensitive index according to the optimal working temperature of the battery leaving the factory and the current battery temperature, obtains an internal resistance change index according to the internal resistance of the battery leaving the factory and the current internal resistance of the battery, obtains an internal resistance influence coefficient according to the current battery capacity, the maximum capacity of the battery leaving the factory, the internal resistance change index, the internal resistance of the battery leaving the factory and the total number of charge and discharge cycles currently used by the battery, obtains a discharge depth according to the current discharge capacity and the maximum capacity of the battery leaving the factory, obtains a cycle number influence coefficient according to the current battery capacity, the maximum capacity of the battery leaving the factory and the total number of charge and discharge cycles currently used by the battery, obtains a cycle number influence index according to the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the total number of charge and discharge cycles currently used by the battery and the discharge depth, and obtains the total number of remaining battery life according to the current battery capacity, the maximum capacity of the battery leaving the factory, the cycle number influence coefficient, the cycle number influence index, the internal resistance influence coefficient, the internal resistance change index, the internal resistance of the battery leaving the factory, the temperature sensitive index, the current battery temperature, the optimal working temperature of the battery leaving the factory and the current ambient temperature.

3. A lithium battery pack health status prediction system based on big data statistics as claimed in claim 2, characterized in that: The battery detection module includes an internal resistance detection submodule, a capacity detection submodule, a temperature detection submodule and a charge and discharge cycle detection submodule; The internal resistance detection submodule is used to detect and obtain the current battery internal resistance and transmit it to the control module; The capacity detection submodule is used to detect and obtain the current battery capacity and transmit it to the control module; The temperature detection submodule is used to detect and obtain the current battery temperature and transmit it to the control module; The charge-discharge cycle detection submodule is used to detect and obtain the total number of charge-discharge cycles currently used by the battery and the current discharge capacity used, and transmit them to the control module.

4. A lithium battery pack health status prediction system based on big data statistics as claimed in claim 3, characterized in that: The charge-discharge cycle detection submodule includes a charge-discharge state judgment unit, a counting unit and a capacity detection unit; The charge and discharge state judgment unit is used to monitor the voltage and current of the battery, and judge whether the battery is in a charging or discharging state according to the voltage and current of the battery; The counting unit is used to count the charging and discharging of the battery and obtain the total number of charge and discharge cycles currently used by the battery, and transmit it to the control module; The capacity detection unit is used to detect and obtain the capacity currently used for discharge, and transmit it to the control module.

5. The lithium battery pack health status prediction system based on big data statistics as claimed in claim 2, characterized in that: When the control module calculates the total number of times the remaining battery life lasts, the following formula is satisfied: ； Where Rul is the total number of times the battery has remaining life, C cr is the current battery capacity, C pre is the maximum capacity of the battery when it leaves the factory, α is the cycle number influence coefficient, cd is the cycle number influence index, β is the internal resistance influence coefficient, ΔR is the internal resistance change index, R pre is the internal resistance of the battery when it leaves the factory. is the temperature sensitive index, T cr is the current battery temperature, T ref is the optimal operating temperature of the battery when it leaves the factory, T e is the current ambient temperature, and floor() is the rounding function.

Images