Lithium battery charging time prediction method

Abstract

The invention discloses a method for predicting the charging time of a lithium battery, and relates to the technical field of lithium batteries, and the method is used for obtaining the operation parameters of the lithium battery in the charging process in real time through a sensor and extracting the parameters of charging equipment. According to the lithium battery charging time prediction method, the current lithium battery storage capacity is determined through the historical charging condition of the lithium battery by preprocessing the data, and the established time evaluation model is analyzed and optimized by using the historical influence data; and then real-time data is introduced into the time evaluation model, the required charging time is predicted in real time, and the health of the lithium battery is evaluated, so that the accuracy of charging time prediction is improved, and by comprehensively considering various operation parameters of the lithium battery and output parameters of charging equipment and adopting the advanced time evaluation model, the charging time prediction accuracy is improved. The charging time can be predicted more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium batteries, and in particular to a method for predicting charging time of a lithium battery. Background Art

[0002] Lithium batteries use lithium metal or lithium alloys as their negative electrode materials and a non-aqueous electrolyte solution. They boast advantages such as high energy density, low self-discharge, long service life, and no memory effect. They are widely used in mobile phones, electric vehicles, energy storage systems, and other fields. However, charging time is crucial for lithium batteries. Properly controlling the charging time can prevent overcharging, which can damage the battery structure, shorten its lifespan, and even pose safety risks. It can also prevent undercharging, which can affect device endurance and performance, thereby ensuring efficient and stable battery operation.

[0003] The reference patent name is: A battery charging time prediction method, device and battery (patent publication number: CN116930766A, patent publication date: 2023-10-24). The battery charging time prediction method includes: obtaining the temperature and remaining power of the target battery at the beginning of the preset charging time; determining the first time required for the temperature change step and the second time required for the remaining power change step in the preset charging time based on the temperature and remaining power; determining the temperature and remaining power at the end of the preset charging time based on the temperature, remaining power, first time and second time, and using the temperature and remaining power at the end of the preset charging time as the battery initial state parameters for the next time of the preset charging time; if the remaining power corresponding to the battery initial state parameters is greater than or equal to the target power, determining the total charging time of the target battery according to each charging time.

[0004] Based on the description in the above-mentioned document, when existing lithium batteries are charged, the charging time will vary due to changes in various factors. In the real-time charging process, for example, changes in temperature affect the charging rate, and changes in pressure in the lithium battery affect the chemical reaction rate in the lithium battery, which can easily lead to inaccurate predictions. For this reason, the present invention provides a method for predicting the charging time of a lithium battery. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a lithium battery charging time prediction method, which solves the problem that when the existing lithium battery is charging, the charging time will vary due to changes in various factors. In the real-time charging process, for example, changes in temperature affect the charging rate, and changes in pressure in the lithium battery affect the chemical reaction rate in the lithium battery, which can easily lead to inaccurate predictions.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for predicting charging time of a lithium battery, specifically comprising the following steps:

[0007] A1. During the charging process of the lithium battery, the operating parameters of the lithium battery during the charging process are obtained in real time through sensors, and the parameters of the charging equipment are extracted;

[0008] A2. Receive the transmitted data, extract historical data, and pre-process the data. Determine the current lithium battery storage capacity based on the lithium battery's historical charging status. Analyze and optimize the established time assessment model using historical influencing data. Then, introduce real-time data into the time assessment model to predict the required charging time in real time. This also enables the health assessment of the lithium battery and transmits the results.

[0009] A3. The obtained results are displayed through the display interface, and the corresponding strategy is matched according to the health assessment situation to implement the processing operation.

[0010] Preferably, the operation of preprocessing the data in A2 is:

[0011] B1. Preprocess the collected data, including data cleaning, filtering and normalization operations;

[0012] B2. Data cleaning is to remove outliers and noise data that appear during the collection process. The filtering operation uses a low-pass filter method to smooth the data curve and reduce data fluctuations. Normalization is to convert data of different dimensions into the required range.

[0013] B3. And implement data classification operations on the processed data according to different nodes.

[0014] Preferably, the data classification operation implemented according to different nodes in B3 is:

[0015] b31. Using the processed data as the category title of the first node according to real-time data and historical data;

[0016] b32. Perform a serial number tagging operation on the acquisition sensor, using the data of any item in the first node as the classification title of the second node according to the corresponding serial number content, and using the data of any item in the second node as the classification title of the third node according to different categories, and using the data of any item in the third node as the classification title of the fourth node according to the acquisition time node;

[0017] b33, and matching the data according to the classification title content of the first node, the second node, the third node and the fourth node, and then filling in the matching values.

[0018] Preferably, in A2, the current storage capacity of the lithium battery is determined based on the historical charging status of the lithium battery:

[0019] C1. Extract the historical charging data of lithium batteries with similar dates, and extract the historical charging data under the sequential time nodes;

[0020] C2. Calculate the capacity change rate using the capacity data of the fully charged lithium battery at adjacent time nodes, and predict the storage capacity of the current lithium battery before charging based on the capacity change rate.

[0021] Preferably, the formula for calculating the capacity change rate in C2 is:

[0022] J=[(M m -M m-1 ) / M m + (M m-1 -M m-2 ) / M m-1 +…+(M2-M1) / M2] / (m-1);

[0023] J is the capacity change rate, and M m Represents the storage capacity of the mth lithium battery in the extracted historical charging data, and M m >M m-1 , and M m The charging time node is at M m-1 Before the charging time node, m-1 represents the number of lithium battery capacity change rates at a single adjacent time node;

[0024] And it is predicted that the storage capacity of the current lithium battery before charging is:

[0025] P=M1×(1-J)-N n ;

[0026] P is the storage capacity of the current lithium battery before charging, M1 is the storage capacity of the current lithium battery before charging, N n The current lithium battery storage remaining capacity at the nth time node.

[0027] Preferably, the analysis operation of various historical impact data in A2 is:

[0028] D1. Extract historical temperature data and analyze it to determine the basic charging rate at different ambient temperatures, thereby obtaining a matching table;

[0029] D2. Determine the chemical reaction rate under different pressures by extracting and analyzing historical chemical reaction data;

[0030] D3. By extracting the energy consumed during the operation of the cooling system and calculating the efficiency factor of the cooling system, the current basic charging rate is corrected to obtain the actual charging rate;

[0031] D4. The corrected actual charging rate is introduced into the time evaluation model for optimization.

[0032] Preferably, the operation of analyzing the historical temperature data in D1 is:

[0033] d11. Extract the basic charging rate data under each temperature data in the historical data, and set the current temperature data as T uv , T uv Refers to the vth collection at the uth temperature value, and the number of times any temperature data is collected is the same;

[0034] d12, then according to the current temperature data T uv Extract the basic charging rate data, and the value with the most occurrences in the basic charging rate is the current temperature data T uv The basic charging rate is marked as R r ;

[0035] d13. Then, determine the temperature change range based on the change in the basic charging rate, and then create a matching table with different temperature change ranges as row titles and basic charging rate content as column titles, and fill the corresponding basic charging rate values into the result column where the row title and column title extend and intersect.

[0036] Preferably, the operation of determining the chemical reaction rate under different pressures in D2 is:

[0037] d21. Extract the chemical reaction rate data of lithium batteries under various pressure data in the historical data, and extract the temperature data T uv At the same time, determine the number of times the current different pressure data appear, and the pressure data with the largest number of occurrences is the pressure data at the current temperature, marked as F f , and then extract the pressure data F f Determine the current chemical reaction rate and label it as V h ,

[0038] d22. Based on the change in the pressure data value, the temperature change range is obtained, and then the pressure change range is obtained based on the chemical reaction rate, so that the pressure value is determined based on the temperature value, and the chemical reaction rate is determined based on the pressure value.

[0039] Preferably, the operation of correcting the current basic charging rate after calculating the efficiency factor of the cooling system in D3 is:

[0040] d31. Extract the energy data generated by charging the lithium battery during the period corresponding to the temperature data, and then extract the energy data consumed by the cooling equipment;

[0041] d32. The efficiency factor is calculated using the energy data generated by lithium battery charging and the energy consumed by the cooling equipment. The calculation formula is:

[0042] β = (E x ×t) / E y ;

[0043] β is the efficiency factor, E x is the power of the cooling equipment, t is the operating time, E y Energy data generated by charging lithium batteries;

[0044] d33, and rely on the efficiency factor to achieve the correction operation of the basic charging rate, and the correction formula is:

[0045] R g =R r ×V h -E x ×β;

[0046] R g is the actual charging rate, R r is the basic charging rate, V h is the chemical reaction rate, E x is the power of the cooling equipment, and β is the efficiency factor.

[0047] Preferably, the operation of introducing real-time data into the time evaluation model and predicting the required charging time in real time in A2 is:

[0048] Based on the current real-time temperature data and the various data predicted in the time evaluation model, the charging time is calculated based on the actual charging rate;

[0049] The calculation formula for charging time is: t=P / R g , P is the storage capacity of the current lithium battery before charging;

[0050] The health assessment of lithium batteries is achieved by extracting the safety thresholds of various factors, and performing real-time prediction and monitoring of various data when the lithium battery is charging. When the real-time data exceeds the safety threshold, an early warning strategy is generated and transmitted.

[0051] The present invention provides a method for predicting the charging time of a lithium battery. Compared with the prior art, it has the following advantages:

[0052] 1. This lithium battery charging time prediction method preprocesses data, determines the current lithium battery storage capacity based on the historical charging conditions of the lithium battery, and uses historical influencing data to analyze and optimize the established time assessment model. It then introduces real-time data into the time assessment model and predicts the required charging time in real time, and implements an assessment operation on the health of the lithium battery, thereby improving the accuracy of the charging time prediction. By comprehensively considering multiple operating parameters of the lithium battery and the output parameters of the charging equipment, and adopting advanced time assessment models, it can more accurately predict the charging time.

[0053] 2. The lithium battery charging time prediction method preprocesses the collected data, including data cleaning, filtering and normalization operations, and matches the data according to the classification title content of the first node, the second node, the third node and the fourth node, and then fills the matched values to achieve data optimization operations, and realizes more effective data processing through multi-node classification, which facilitates subsequent data extraction and traceability operations, and improves the efficiency of subsequent data applications.

[0054] 3. The lithium battery charging time prediction method extracts the historical charging data of the lithium battery on similar dates, extracts the historical charging data at the sequential time nodes, calculates the capacity change rate of the capacity data of the lithium battery after full charge at the adjacent time nodes, and predicts the storage capacity of the current lithium battery before charging based on the capacity change rate, thereby predicting the current storage capacity of the lithium battery in real time according to the charging situation, so as to facilitate the subsequent accurate prediction of the charging time.

[0055] 4. The lithium battery charging time prediction method extracts historical temperature data for analysis to determine the basic charging rate at different ambient temperatures, thereby obtaining a matching table. The method extracts historical chemical reaction data for analysis to determine the chemical reaction rate under different pressures. The method extracts the energy consumed during the operation of the cooling system, calculates the efficiency factor of the cooling system, and then corrects the current basic charging rate to obtain the actual charging rate. The corrected actual charging rate is introduced into the time evaluation model for optimization, and prediction operations are implemented for various influencing factors to obtain an accurate actual charging rate, thereby obtaining more accurate data to optimize the time evaluation model, so as to facilitate the subsequent adaptive prediction of real-time charging time data and improve efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is an operational flow chart of the charging time prediction method of the present invention;

[0057] Figure 2 This is an operational flow chart of data preprocessing of the present invention;

[0058] Figure 3 This is an operational flow chart for analyzing various impact data of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] See also Figure 1-Figure 3 , the present invention provides two technical solutions:

[0061] Example 1: A method for predicting charging time of a lithium battery, comprising the following steps:

[0062] A1. During the charging process of the lithium battery, the operating parameters of the lithium battery during the charging process are obtained in real time through sensors, and the parameters of the charging equipment are extracted;

[0063] A2. Receive the transmitted data, extract historical data, and pre-process the data. Determine the current lithium battery storage capacity based on the lithium battery's historical charging status. Analyze and optimize the established time assessment model using historical influencing data. Then, introduce real-time data into the time assessment model to predict the required charging time in real time. This also enables the health assessment of the lithium battery and transmits the results.

[0064] A3. The obtained results are displayed through the display interface, and the corresponding strategy is matched according to the health assessment situation to implement the processing operation.

[0065] Among them, by preprocessing the data, the current lithium battery storage capacity is determined through the historical charging conditions of the lithium battery, and the historical influencing data is used to analyze and optimize the established time assessment model. Then, real-time data is introduced into the time assessment model and the required charging time is predicted in real time. The health of the lithium battery is evaluated, thereby improving the accuracy of the charging time prediction. By comprehensively considering the various operating parameters of the lithium battery and the output parameters of the charging equipment, and adopting advanced time assessment models, the charging time can be predicted more accurately.

[0066] In the embodiment of the present invention, the data preprocessing operation in A2 is:

[0067] B1. Preprocess the collected data, including data cleaning, filtering and normalization operations;

[0068] B2. Data cleaning is to remove outliers and noise data that appear during the collection process. The filtering operation uses a low-pass filter method to smooth the data curve and reduce data fluctuations. Normalization is to convert data of different dimensions into the required range.

[0069] B3. And implement data classification operations on the processed data according to different nodes.

[0070] In the embodiment of the present invention, the data classification operation implemented in B3 according to different nodes is as follows:

[0071] b31. Using the processed data as the category title of the first node according to real-time data and historical data;

[0072] b32. Perform a serial number tagging operation on the acquisition sensor, using the data of any item in the first node as the classification title of the second node according to the corresponding serial number content, and using the data of any item in the second node as the classification title of the third node according to different categories, and using the data of any item in the third node as the classification title of the fourth node according to the acquisition time node;

[0073] b33, and matching the data according to the classification title content of the first node, the second node, the third node and the fourth node, and then filling in the matching values.

[0074] Among them, the collected data is preprocessed, including data cleaning, filtering and normalization operations, and the data is matched according to the classification title content of the first node, the second node, the third node and the fourth node, and then the matched values are filled in, so as to achieve data optimization operations, and more effective data processing is achieved through multi-node classification, which facilitates subsequent data extraction and traceability operations, and improves the efficiency of subsequent data applications.

[0075] In the embodiment of the present invention, in A2, the current storage capacity of the lithium battery is determined based on the historical charging status of the lithium battery:

[0076] C1. Extract the historical charging data of lithium batteries with similar dates, and extract the historical charging data under the sequential time nodes;

[0077] C2. Calculate the capacity change rate using the capacity data of the fully charged lithium battery at adjacent time nodes, and predict the storage capacity of the current lithium battery before charging based on the capacity change rate.

[0078] In the embodiment of the present invention, the formula for calculating the capacity change rate in C2 is:

[0079] J=[(M m -M m-1 ) / M m + (Mm-1 -M m-2 ) / M m-1 +…+(M2-M1) / M2] / (m-1);

[0080] J is the capacity change rate, and M m Represents the storage capacity of the mth lithium battery in the extracted historical charging data, and M m >M m-1 , and M m The charging time node is at M m-1 Before the charging time node, m-1 represents the number of lithium battery capacity change rates at a single adjacent time node;

[0081] And it is predicted that the storage capacity of the current lithium battery before charging is:

[0082] P=M1×(1-J)-N n ;

[0083] P is the storage capacity of the current lithium battery before charging, M1 is the storage capacity of the current lithium battery before charging, N n The current lithium battery storage remaining capacity at the nth time node.

[0084] Among them, by extracting the historical charging data of lithium batteries on similar dates, the historical charging data at various sequential time nodes are extracted, and the capacity data of the lithium battery after full charge at adjacent time nodes are calculated to obtain the capacity change rate. The storage capacity of the current lithium battery before charging is predicted based on the capacity change rate, thereby predicting the current storage capacity of the lithium battery in real time according to the charging situation, so as to facilitate the subsequent accurate prediction of the charging time.

[0085] In the embodiment of the present invention, the analysis operation of various historical impact data in A2 is:

[0086] D1. Extract historical temperature data and analyze it to determine the basic charging rate at different ambient temperatures, thereby obtaining a matching table;

[0087] D2. Determine the chemical reaction rate under different pressures by extracting and analyzing historical chemical reaction data;

[0088] D3. By extracting the energy consumed during the operation of the cooling system and calculating the efficiency factor of the cooling system, the current basic charging rate is corrected to obtain the actual charging rate;

[0089] D4. The corrected actual charging rate is introduced into the time evaluation model for optimization.

[0090] In the embodiment of the present invention, the operation of analyzing the historical temperature data in D1 is:

[0091] d11. Extract the basic charging rate data under each temperature data in the historical data, and set the current temperature data as T uv , T uv Refers to the vth collection at the uth temperature value, and the number of times any temperature data is collected is the same;

[0092] d12, then according to the current temperature data T uv Extract the basic charging rate data, and the value with the most occurrences in the basic charging rate is the current temperature data T uv The basic charging rate is marked as R r ;

[0093] d13. Then, determine the temperature change range based on the change in the basic charging rate, and then create a matching table with different temperature change ranges as row titles and basic charging rate content as column titles, and fill the corresponding basic charging rate values into the result column where the row title and column title extend and intersect.

[0094] In the embodiment of the present invention, the operation of determining the chemical reaction rate under different pressures in D2 is:

[0095] d21. Extract the chemical reaction rate data of lithium batteries under various pressure data in the historical data, and extract the temperature data T uv At the same time, determine the number of times the current different pressure data appear, and the pressure data with the largest number of occurrences is the pressure data at the current temperature, marked as F f , and then extract the pressure data F f Determine the current chemical reaction rate and label it as V h ,

[0096] d22. Based on the change in the pressure data value, the temperature change range is obtained, and then the pressure change range is obtained based on the chemical reaction rate, so that the pressure value is determined based on the temperature value, and the chemical reaction rate is determined based on the pressure value.

[0097] In the embodiment of the present invention, the operation of correcting the current basic charging rate after calculating the efficiency factor of the cooling system in D3 is:

[0098] d31. Extract the energy data generated by charging the lithium battery during the period corresponding to the temperature data, and then extract the energy data consumed by the cooling equipment;

[0099] d32. The efficiency factor is calculated using the energy data generated by lithium battery charging and the energy consumed by the cooling equipment. The calculation formula is:

[0100] β = (E x ×t) / Ey ;

[0101] β is the efficiency factor, E x is the power of the cooling equipment, t is the operating time, E y Energy data generated by charging lithium batteries;

[0102] d33, and rely on the efficiency factor to achieve the correction operation of the basic charging rate, and the correction formula is:

[0103] R g =R r ×V h -E x ×β;

[0104] R g is the actual charging rate, R r is the basic charging rate, V h is the chemical reaction rate, E x is the power of the cooling equipment, and β is the efficiency factor.

[0105] Among them, by extracting historical temperature data for analysis, the basic charging rate at different ambient temperatures is determined, and a matching table is obtained. By extracting historical chemical reaction data for analysis, the chemical reaction rate under different pressures is determined. By extracting the energy consumed during the operation of the cooling system, the efficiency factor of the cooling system is calculated, and then the current basic charging rate is corrected to obtain the actual charging rate. The actual charging rate obtained after correction is introduced into the time evaluation model for optimization operation, and the prediction operation of various influencing factors is realized to obtain an accurate actual charging rate, thereby obtaining more accurate data to optimize the time evaluation model, so as to facilitate the subsequent adaptive prediction of real-time charging time data and improve efficiency and accuracy.

[0106] In the embodiment of the present invention, the operation of introducing real-time data into the time evaluation model and predicting the required charging time in real time in A2 is as follows:

[0107] Based on the current real-time temperature data and the various data predicted in the time evaluation model, the charging time is calculated based on the actual charging rate;

[0108] The calculation formula for charging time is: t=P / R g , P is the storage capacity of the current lithium battery before charging;

[0109] The health assessment of lithium batteries is achieved by extracting the safety thresholds of various factors, and performing real-time prediction and monitoring of various data when the lithium battery is charging. When the real-time data exceeds the safety threshold, an early warning strategy is generated and transmitted.

[0110] The difference between Example 2 and Example 1 is that the same charging operation is performed on multiple lithium batteries, and the operation of predicting the charging time of multiple lithium batteries is realized by relying on the existing lithium battery charging time prediction method and the lithium battery charging time prediction method of the present invention. The time required to complete the prediction operation and the prediction accuracy are recorded by comparing the predicted time with the actual charging time. The specific results are shown in Table 1:

[0111] Table 1 Prediction results

[0112]

[0113] In summary, after the lithium battery charging time prediction method of the present invention is applied, the time taken to complete the prediction operation is shorter, and the accuracy of the final prediction matching result is higher, so it can be better applied in actual operation.

[0114] At the same time, the contents not described in detail in this specification belong to the existing technology well known to those skilled in the art.

[0115] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0116] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting charging time of a lithium battery, characterized by: The specific steps include: A1. During the charging process of the lithium battery, the operating parameters of the lithium battery during the charging process are obtained in real time through sensors, and the parameters of the charging equipment are extracted; A2. Receive the transmitted data, extract historical data, and pre-process the data. Determine the current lithium battery storage capacity based on the lithium battery's historical charging status. Analyze and optimize the established time assessment model using historical influencing data. Then, introduce real-time data into the time assessment model to predict the required charging time in real time. This also enables the health assessment of the lithium battery and transmits the results. A3. The obtained results are displayed through the display interface, and the corresponding strategy is matched according to the health assessment situation to implement the processing operation.

2. A lithium battery charging time prediction method according to claim 1, characterized in that: The data preprocessing operation in A2 is: B1. Preprocess the collected data, including data cleaning, filtering and normalization operations; B2. Data cleaning is to remove outliers and noise data that appear during the collection process. The filtering operation uses a low-pass filter method to smooth the data curve and reduce data fluctuations. Normalization is to convert data of different dimensions into the required range. B3. And implement data classification operations on the processed data according to different nodes.

3. The method for predicting charging time of a lithium battery according to claim 2, wherein: The data classification operation implemented in B3 according to different nodes is as follows: b31. Using the processed data as the category title of the first node according to real-time data and historical data; b32. Perform a serial number tagging operation on the acquisition sensor, using the data of any item in the first node as the classification title of the second node according to the corresponding serial number content, and using the data of any item in the second node as the classification title of the third node according to different categories, and using the data of any item in the third node as the classification title of the fourth node according to the acquisition time node; b33, and matching the data according to the classification title content of the first node, the second node, the third node and the fourth node, and then filling in the matching values.

4. The method for predicting charging time of a lithium battery according to claim 1, wherein: In A2, the current storage capacity of the lithium battery is determined based on the historical charging status of the lithium battery: C1. Extract the historical charging data of lithium batteries with similar dates, and extract the historical charging data under the sequential time nodes; C2. Calculate the capacity change rate using the capacity data of the fully charged lithium battery at adjacent time nodes, and predict the storage capacity of the current lithium battery before charging based on the capacity change rate.

5. The method for predicting charging time of a lithium battery according to claim 4, wherein: The formula for calculating the capacity change rate in C2 is: J=[(M m -M m-1 ) / M m +(M m-1 -M m-2 ) / M m-1 +…+(M2-M1) / M2] / (m-1); J is the capacity change rate, and M m Represents the storage capacity of the mth lithium battery in the extracted historical charging data, and M m >M m-1 , and M m The charging time node is at M m-1 Before the charging time node, m-1 represents the number of lithium battery capacity change rates at a single adjacent time node; And it is predicted that the storage capacity of the current lithium battery before charging is: P=M1×(1-J)-N n 4 P is the storage capacity of the current lithium battery before charging, M1 is the storage capacity of the current lithium battery before charging, N n The current lithium battery storage remaining capacity at the nth time node.

6. A lithium battery charging time prediction method according to claim 5, characterized in that: The analysis of various historical impact data in A2 is as follows: D1. Extract historical temperature data and analyze it to determine the basic charging rate at different ambient temperatures, thereby obtaining a matching table; D2. Determine the chemical reaction rate under different pressures by extracting and analyzing historical chemical reaction data; D3. By extracting the energy consumed during the operation of the cooling system and calculating the efficiency factor of the cooling system, the current basic charging rate is corrected to obtain the actual charging rate; D4. The corrected actual charging rate is introduced into the time evaluation model for optimization.

7. A lithium battery charging time prediction method according to claim 6, characterized in that: The operation of analyzing the historical temperature data in D1 is: d11. Extract the basic charging rate data under each temperature data in the historical data, and set the current temperature data as T uv , T uv Refers to the vth collection at the uth temperature value, and the number of times any temperature data is collected is the same; d12, then according to the current temperature data T uv Extract the basic charging rate data, and the value with the most occurrences in the basic charging rate is the current temperature data T uv The basic charging rate is marked as R r ; d13. Then, determine the temperature change range based on the change in the basic charging rate, and then create a matching table with different temperature change ranges as row titles and basic charging rate content as column titles, and fill the corresponding basic charging rate values into the result column where the row title and column title extend and intersect.

8. A lithium battery charging time prediction method according to claim 7, characterized in that: The operation of determining the chemical reaction rate under different pressures in D2 is: d21. Extract the chemical reaction rate data of lithium batteries under various pressure data in the historical data, and extract the temperature data T uv At the same time, determine the number of times the current different pressure data appear, and the pressure data with the largest number of occurrences is the pressure data at the current temperature, marked as F f , and then extract the pressure data F f Determine the current chemical reaction rate and label it as V h , d22. Based on the change in the pressure data value, the temperature change range is obtained, and then the pressure change range is obtained based on the chemical reaction rate, so that the pressure value is determined based on the temperature value, and the chemical reaction rate is determined based on the pressure value.

9. The method for predicting charging time of a lithium battery according to claim 8, wherein: After the efficiency factor of the cooling system is calculated in D3, the operation of correcting the current basic charging rate is as follows: d31. Extract the energy data generated by charging the lithium battery during the period corresponding to the temperature data, and then extract the energy data consumed by the cooling equipment; d32. The efficiency factor is calculated using the energy data generated by lithium battery charging and the energy consumed by the cooling equipment. The calculation formula is: β=(E x ×t) / E y ; β is the efficiency factor, E x is the power of the cooling equipment, t is the operating time, E y Energy data generated by charging lithium batteries; d33, and rely on the efficiency factor to achieve the correction operation of the basic charging rate, and the correction formula is: R g =R r ×V h -E x ×β; R g is the actual charging rate, R r is the basic charging rate, V h is the chemical reaction rate, E x is the power of the cooling equipment, and β is the efficiency factor.

10. A lithium battery charging time prediction method according to claim 9, characterized in that: The operation of introducing real-time data into the time evaluation model and predicting the required charging time in real time in A2 is as follows: Based on the current real-time temperature data and the various data predicted in the time evaluation model, the charging time is calculated based on the actual charging rate; The calculation formula for charging time is: t=P / R g , P is the storage capacity of the current lithium battery before charging; The health assessment of lithium batteries is achieved by extracting the safety thresholds of various factors, and performing real-time prediction and monitoring of various data when the lithium battery is charging. When the real-time data exceeds the safety threshold, an early warning strategy is generated and transmitted.

Images