Charging safety monitoring and early warning method and system for lithium battery

By analyzing the charging data and gas concentration of lithium batteries, and automatically repairing the faults using the charging diagnosis model, the problem of lack of automatic fault repair in the existing technology is solved, the accuracy and automation of lithium battery charging safety monitoring is improved, and safety hazards are reduced .

CN119070422AActive Publication Date: 2024-12-03江西省允福亨新能源有限责任公司
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411044762.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-12-03
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

The existing lithium battery charging safety monitoring methods only provide risk warnings and fail to achieve automatic fault repair, resulting in a large amount of manual intervention and increasing safety hazards.

Method used

By collecting the monitoring charging data, gas concentration and test data of lithium batteries, the pre-trained charging diagnostic model is used for analysis, the fault categories are divided and automatic repair is carried out, including the calculation of monitoring voltage, current, temperature and internal resistance slope, and the charging is automatically adjusted. Parameters to fix the fault.

Benefits of technology

It improves the accuracy and automation of lithium battery charging safety monitoring, reduces manual intervention, reduces safety risks, and ensures the stability and safety of the charging process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119070422A_ABST
    Figure CN119070422A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of battery safety monitoring, and discloses a charging safety monitoring and early warning method and system for a lithium battery. The method comprises the following steps: collecting monitoring charging data of a lithium battery in unit time; analyzing and processing the monitoring charging data collected in each unit time to obtain monitoring processing data, and adding the monitoring processing data to a monitoring slope set; collecting charging test data of the lithium battery; processing the charging test data to obtain a charging test data set; collecting the concentration of the monitored gas once in unit time, and adding the concentration of the monitored gas into a gas concentration set; analyzing and processing the gas concentration set to obtain an equation derivative set; through multi-dimensional data acquisition and processing and automatic repair of faults supporting automatic adjustment, human intervention and potential safety hazards are effectively reduced, and the safety and automation degree of the lithium battery charging process are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of battery safety monitoring, and more specifically, to a charging safety monitoring and early warning method and system for a lithium battery. Background Art

[0002] As lithium batteries are widely used in electric vehicles, portable electronic devices and energy storage systems, the issue of charging safety has become particularly important. During the charging process, if lithium batteries are overcharged, short-circuited internally or in a harsh external environment, they may overheat, catch fire or even explode. Therefore, it is crucial to establish an effective charging safety monitoring and early warning system to monitor the battery status in real time and issue an alarm in a timely manner.

[0003] In order to improve the accuracy of lithium battery charging safety warning, the existing patent application with publication number CN116466237A proposes a lithium battery charging safety monitoring and early warning method and system, including: obtaining multi-dimensional lithium battery charging data streams, performing data cleaning and integration, obtaining multi-dimensional standard lithium battery charging data streams, and identifying fault parameters to obtain charging fault clue information. Based on the charging fault clue information, a charging safety risk analysis model is constructed. The target lithium battery is monitored for charging safety using a sensor group to obtain a real-time charging operation data stream. The real-time charging operation data stream is input into the charging safety risk analysis model for analysis to obtain lithium battery charging risk diagnosis information. Risk warning operation and maintenance of the target lithium battery is performed based on the lithium battery charging risk diagnosis information.

[0004] Although the above method can meet most scenarios, research and practical application of the above method and existing technology have found that the above method and existing technology have at least the following defects:

[0005] There is only risk warning, but no automatic repair of faults that support automatic adjustment and recovery, resulting in a large amount of manual intervention still required after the warning;

[0006] In view of this, the present invention proposes a lithium battery charging safety monitoring and early warning method and system to solve the above problems. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a charging safety monitoring and early warning method for a lithium battery, comprising:

[0008] Collect monitoring and charging data of lithium batteries per unit time;

[0009] Analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set;

[0010] Collect charging test data of lithium batteries;

[0011] Processing the charging test data to obtain a charging test data set;

[0012] Collect the monitored gas concentration once per unit time, and add the monitored gas concentration to the gas concentration set;

[0013] Analyze and process the gas concentration set to obtain the equation derivative set;

[0014] Inputting charging diagnostic data into a pre-trained charging diagnostic model to obtain a charging diagnostic value; the charging diagnostic data includes a monitoring slope set and an equation derivative set;

[0015] The charging diagnosis values ​​are divided into automatic adjustment categories and non-automatic adjustment categories, and faults in the automatic adjustment category are automatically repaired.

[0016] Further, the monitoring of charging data includes monitoring charging voltage, monitoring charging current, monitoring battery temperature and monitoring charging internal resistance;

[0017] The method of obtaining the monitoring processing data and adding the monitoring processing data to the monitoring slope set includes:

[0018] The slopes of the monitored charging data are calculated respectively to obtain the monitored voltage slope, the monitored current slope, the monitored temperature slope and the monitored internal resistance slope;

[0019] The calculation method of the monitoring voltage slope is:

[0020]

[0021] VK is the monitoring voltage slope, V1 is the voltage at the beginning of the unit time, V2 is the voltage at the end of the unit time, and unitTime is the unit time;

[0022] Calculate the monitoring current slope, monitoring temperature slope and monitoring internal resistance slope using the same calculation method for the monitoring voltage slope; add the monitoring voltage slope to the monitoring voltage slope set; add the monitoring current slope to the monitoring current slope set; add the monitoring temperature slope to the monitoring temperature slope set; add the monitoring internal resistance slope to the monitoring internal resistance slope set;

[0023] The monitoring voltage slope set, monitoring current slope set, monitoring temperature slope set, and monitoring internal resistance slope set are added to the monitoring slope set.

[0024] Further, the charging test data includes a charging test voltage, a charging test current, a test battery temperature and a charging test internal resistance; the charging test data set includes a test voltage slope set, a test current slope set, a test temperature slope set and a test internal resistance slope set;

[0025] The method for obtaining the test voltage slope set is:

[0026] The charging test voltage is divided into U test voltage parts according to the first unit time, where U is a positive number greater than 1, and the test voltage slope is calculated for each test voltage part using the same calculation method as the monitoring voltage slope, and the test voltage slope is added to the test voltage slope set; the first unit time is the same as the unit time;

[0027] The test current slope set, the test temperature slope set and the test internal resistance slope set are obtained by the method for obtaining the test voltage slope set; the test voltage slope set, the test current slope set, the test temperature slope set and the test internal resistance slope set are added to the charging test data set.

[0028] Further, the monitored gas concentrations include oxygen concentration, carbon dioxide concentration, carbon monoxide concentration, hydrogen concentration and volatile compound concentration;

[0029] adding oxygen concentration to the first concentration set, adding carbon dioxide concentration to the second concentration set, adding carbon monoxide concentration to the third concentration set, adding hydrogen concentration to the fourth concentration set, and adding volatile compound concentration to the fifth concentration set; the gas concentration sets include the first concentration set, the second concentration set, the third concentration set, the fourth concentration set, and the fifth concentration set;

[0030] Performing linear regression fitting on the elements in the gas concentration set respectively to obtain a first concentration equation, a second concentration equation, a third concentration equation, a fourth concentration equation and a fifth concentration equation;

[0031] The method for obtaining the first concentration equation includes:

[0032] The first concentration equation obtained by linear regression fitting is f(O)=β×t+Y;

[0033] β is the regression coefficient of the first concentration equation, t is time, and Y is the intercept of the first concentration equation, and β and Y are calculated by the least squares method;

[0034] The second concentration equation f(CO2), the third concentration equation f(CO), the fourth concentration equation f(H) and the fifth concentration equation f(VOC) are obtained in the same manner as the first concentration equation.

[0035] Furthermore, the method for obtaining the set of equation derivatives includes:

[0036] The derivative of f(O) is obtained by differentiating the first equation f′(O), the derivative of f(CO2) is obtained by differentiating the second equation f′(CO2), the derivative of f(CO) is obtained by differentiating the third equation f′(CO), the derivative of f(H) is obtained by differentiating the fourth equation f′(H), and the derivative of f(VOC) is obtained by differentiating the fifth equation f′(VOC);

[0037] Substitute the oxygen concentrations in the first concentration set into f′(O) to form the first equation derivative set; substitute the carbon dioxide concentrations in the second concentration set into f′(C02) to form the second equation derivative set; substitute the carbon monoxide concentrations in the third concentration set into f′(CO) to form the third equation derivative set; substitute the hydrogen concentrations in the fourth concentration set into f′(H) to form the fourth equation derivative set; substitute the volatile compound concentrations in the fifth concentration set into f′(VOC) to form the fifth equation derivative set;

[0038] A first set of derivatives of equations, a second set of derivatives of equations, a third set of derivatives of equations, a fourth set of derivatives of equations, and a fifth set of derivatives of equations are added to the set of derivatives of equations.

[0039] Furthermore, the training method of the charging diagnosis model includes:

[0040] A charging diagnosis data set is collected in advance, the charging diagnosis data set includes charging diagnosis data and charging diagnosis values ​​corresponding to the charging diagnosis data, the charging diagnosis data set is divided into a training set and a test set, a classifier is constructed, the charging diagnosis data in the training set is used as the input of a charging diagnosis model, and the charging diagnosis values ​​in the training set are used as the output of the charging diagnosis model, and the sum of the prediction accuracies of all predicted charging diagnosis values ​​is minimized as the training goal; the training is stopped when the sum of the prediction accuracies reaches convergence; the charging diagnosis model is a gradient boosting tree model;

[0041] The calculation formula for prediction accuracy is: L m =(Y m -S m ) 2 , L m is the prediction accuracy, Y m is the predicted charging diagnosis value corresponding to the mth group of charging diagnosis data, S m is the actual charging diagnosis value corresponding to the mth group of charging diagnosis data.

[0042] Furthermore, the method of dividing the charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories, and automatically repairing the faults in the automatic adjustment category includes:

[0043] S111: Obtain current charging diagnosis value;

[0044] S112: Determine whether the current charging diagnosis value is 0; if the current charging diagnosis value is 0, end the current process; otherwise, execute S113;

[0045] S113: Classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories;

[0046] The method for classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories includes:

[0047] Classify the charging diagnosis values ​​in advance, add the charging diagnosis values ​​that support automatic adjustment to the automatic adjustment category, and add the charging diagnosis values ​​other than 0 to the non-automatic adjustment category; for example, add 3 and 4 to the automatic adjustment category;

[0048] S114: If the current charging diagnosis value belongs to the automatic adjustment category, execute S145; if the current charging diagnosis value belongs to the non-automatic adjustment category, execute S146;

[0049] S115: Automatically handle the current fault;

[0050] S116: Immediately cut off the charging power supply and issue an alarm.

[0051] Furthermore, the method for automatically processing the current fault includes:

[0052] S1151: Count the number of currently monitored voltage slopes and centralized monitored voltage slopes, recorded as VN; count the number of currently monitored current slopes and centralized monitored current slopes, recorded as IN;

[0053] S1152: Obtain the VNth test voltage slope from the test voltage slope set; obtain the INth test voltage slope from the test current slope set;

[0054] S1153: Obtain the V corresponding to the VNth monitoring voltage slope start ; The V start is the voltage at the beginning of the unit time corresponding to the VNth monitored voltage slope; obtains the I corresponding to the INth monitored current slope start ; said I start is the current at the beginning of the unit time corresponding to the INth monitored current slope;

[0055] S1154: Calculate the corrected voltage value and the corrected current value;

[0056] The modified voltage value calculation method includes:

[0057] V new =VK normal ×unitTime+V start;

[0058] unitTime is the unit time, VK normal To test the voltage slope, V new is the corrected voltage value;

[0059] The modified current value calculation method includes:

[0060] I new =IK normal ×unitTime+I start ;

[0061] unitTime is the unit time, IK normal To test the current slope, I new is the corrected current value;

[0062] S1155: Use the voltage regulator to adjust the charging voltage to V new ; Use the current regulator to adjust the charging current to I new .

[0063] Furthermore, it also includes:

[0064] After the charger is connected to the power supply and before the current starts to be transmitted to the lithium battery, the lithium battery voltage is collected and marked as the first detection voltage; and the charging mode of the next stage is formulated according to the first detection voltage;

[0065] The method for formulating a charging mode for the next stage according to the first detection voltage includes:

[0066] S101: Preset low voltage threshold YZ1;

[0067] S102: compare the first detection voltage with YZ1; if the first detection voltage is less than or equal to YZ1, execute S103; if the first detection voltage is greater than YZ1, switch the charging mode to the CC-CV charging mode, and end the current judgment process;

[0068] S103: Preset trickle charge threshold: preset trickle time threshold TIME1, trickle detection interval TIME2;

[0069] S104: Calculate the maximum number of detection times NUM; NUM is the ratio of the trickle time threshold to the trickle detection interval;

[0070] S105: Switch the charging mode to the trickle charging mode; the trickle charging mode is that the charger uses a current lower than a preset trickle charging threshold to charge the lithium battery; set a timing time, the initial value of which is 0, and the timing time starts when the trickle charging starts; preset i, the initial value of i is 1, i∈{1, 2, ..., NUM};

[0071] S106: When the timing reaches TIME2, the current lithium battery voltage is compared with YZ1 for the i-th time; if the current lithium battery voltage is less than or equal to YZ1, S107 is executed; if the current lithium battery voltage is greater than YZ1, the current lithium battery voltage is within the normal range, the charging mode is switched to the CC-CV charging mode, and the current judgment process ends;

[0072] S107: Let i=i+1, and set the timing time to 0; if i is less than or equal to NUM, execute S106; if i is greater than NUM, stop charging and alarm.

[0073] A lithium battery charging safety monitoring and early warning system, implementing the lithium battery charging safety monitoring and early warning method, comprising:

[0074] The first acquisition module is used to collect monitoring and charging data of the lithium battery within a unit time;

[0075] A first processing module is used to analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set;

[0076] The second acquisition module is used to collect charging test data of the lithium battery;

[0077] A second processing module is used to process the charging test data to obtain a charging test data set;

[0078] The third acquisition module is used to collect the monitored gas concentration once per unit time and add the monitored gas concentration to the gas concentration set;

[0079] The third processing module is used to analyze and process the gas concentration set to obtain the equation derivative set;

[0080] A charging diagnosis module, inputting charging diagnosis data into a pre-trained charging diagnosis model to obtain a charging diagnosis value; the charging diagnosis data includes a monitoring slope set and an equation derivative set;

[0081] The diagnosis processing module is used to classify the charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories, and automatically repair the faults in the automatic adjustment category.

[0082] The technical effects and advantages of the lithium battery charging safety monitoring and early warning method and system of the present invention are as follows:

[0083] The battery voltage is tested before formal charging, and the charging mode for the next stage is automatically formulated according to the detected voltage, avoiding direct charging of batteries with abnormal voltage, optimizing the charging process, and thus reducing safety hazards; multiple sensors are used to collect multi-dimensional data such as charging voltage, current, temperature, internal resistance, and gas concentration, and combined with the charging diagnosis model to obtain charging diagnosis values, thereby improving the accuracy of charging safety monitoring and early warning; the charging diagnosis values ​​are divided into automatic adjustment categories and non-automatic adjustment categories, and faults that support automatic adjustment are automatically repaired in combination with charging test data; this effectively reduces human intervention and potential safety hazards, and improves the safety and automation of the lithium battery charging process. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 This is a schematic diagram of a lithium battery charging safety monitoring and early warning system according to Embodiment 1 of the present invention;

[0085] Figure 2 This is a flow chart of a lithium battery charging safety monitoring and early warning method according to Embodiment 1 of the present invention;

[0086] Figure 3 This is a schematic diagram of a lithium battery charging safety monitoring and early warning system according to Embodiment 2 of the present invention;

[0087] Figure 4 This is a schematic diagram of an electronic device according to Embodiment 4 of the present invention;

[0088] Figure 5 This is a schematic diagram of a storage medium according to Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0089] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0090] Example 1

[0091] See also Figure 1 As shown, a lithium battery charging safety monitoring and early warning system described in this embodiment includes a first acquisition module, a first processing module, a second acquisition module, a second processing module, a third acquisition module, a third processing module, a charging diagnosis module and a diagnosis processing module; the above modules are electrically connected to realize data transmission between modules.

[0092] The first acquisition module is used to collect the monitoring charging data of the lithium battery within a unit time; the monitoring charging data includes monitoring the charging voltage, monitoring the charging current, monitoring the battery temperature and monitoring the charging internal resistance, and the monitoring charging data is obtained through corresponding sensors.

[0093] The monitoring charging data is collected in real time at the beginning of the CC charging stage and stops when the lithium battery is fully charged, and the monitoring charging data per unit time is collected each time.

[0094] The first processing module is used to analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set.

[0095] The method of obtaining the monitoring processing data and adding the monitoring processing data to the monitoring slope set includes:

[0096] The slopes of the monitored charging data are calculated respectively to obtain the monitored voltage slope, the monitored current slope, the monitored temperature slope and the monitored internal resistance slope.

[0097] The calculation method of the monitoring voltage slope is:

[0098]

[0099] Among them, VK is the monitoring voltage slope, V1 is the voltage at the beginning of the unit time, V2 is the voltage at the end of the unit time, and unitTime is the unit time.

[0100] The monitoring current slope, monitoring temperature slope and monitoring internal resistance slope are calculated in the same manner as the calculation method for the monitoring voltage slope.

[0101] Add the monitored voltage slope to the monitored voltage slope set; add the monitored current slope to the monitored current slope set; add the monitored temperature slope to the monitored temperature slope set; add the monitored internal resistance slope to the monitored internal resistance slope set.

[0102] The monitoring voltage slope set, monitoring current slope set, monitoring temperature slope set, and monitoring internal resistance slope set are added to the monitoring slope set.

[0103] It should be noted that each collected monitoring charging data is added to the monitoring slope set after processing; the monitoring slope set is expressed as follows:

[0104] {{VK1...VK k}, {IK1...VI k}, {TK1...TK k}, {RK1...RK k}};

[0105] It should be noted that {VK1...VK k} is the monitoring voltage slope set, VK k is the kth monitored voltage slope in the monitored voltage slope set; {IK1...IK k} is the monitoring current slope set, IK k is the kth monitoring current slope in the monitoring current slope set; {Tk1...Tk k} is the monitoring temperature slope set, Tk k is the kth monitored temperature slope in the monitored temperature slope set; {Rk1...Rk k} is the monitoring internal resistance slope set, Rk k The kth monitored internal resistance slope in the internal resistance slope monitoring set.

[0106] The second acquisition module is used to collect charging test data of the lithium battery.

[0107] The charging test data is the test data collected by the lithium battery manufacturer when charging the lithium batteries that have passed the quality inspection before the lithium batteries leave the factory; the charging test data is collected in real time from the beginning of the CC charging stage until the lithium battery is fully charged; the charging test data includes the charging test voltage, the charging test current, the test battery temperature and the charging test internal resistance; the charging test data is provided by the lithium battery manufacturer.

[0108] The second processing module is used to process the charging test data to obtain a charging test data set; the charging test data set includes a test voltage slope set, a test current slope set, a test temperature slope set and a test internal resistance slope set.

[0109] The method for obtaining the test voltage slope set is:

[0110] The charging test voltage is divided into U test voltage parts according to the first unit time, where U is a positive number greater than 1. The test voltage slope is calculated for each test voltage part in the same way as the monitoring voltage slope, and the test voltage slope is added to the test voltage slope set. It should be noted that the first unit time is the same as the unit time.

[0111] The test current slope set, the test temperature slope set and the test internal resistance slope set are obtained by the method for obtaining the test voltage slope set; the test voltage slope set, the test current slope set, the test temperature slope set and the test internal resistance slope set are added to the charging test data set.

[0112] The third acquisition module is used to collect the monitored gas concentration once per unit time and add the monitored gas concentration to the gas concentration set; the monitored gas concentration includes oxygen concentration, carbon dioxide concentration, carbon monoxide concentration, hydrogen concentration and volatile compound concentration.

[0113] The monitoring gas concentration is collected in real time at the beginning of the CC charging stage and stops when the lithium battery is fully charged, and the monitoring gas concentration per unit time is collected each time; the monitoring gas concentration is obtained by a corresponding sensor;

[0114] The gas concentration sets include a first concentration set, a second concentration set, a third concentration set, a fourth concentration set, and a fifth concentration set.

[0115] The method of adding the monitoring gas concentration to the gas concentration set comprises:

[0116] The oxygen concentration is added to the first concentration set, the carbon dioxide concentration is added to the second concentration set, the carbon monoxide concentration is added to the third concentration set, the hydrogen concentration is added to the fourth concentration set, and the volatile compound concentration is added to the fifth concentration set.

[0117] The gas concentration set is expressed as follows:

[0118] {{O1...O f},{(CO2)1...(CO2) f}, {CO1...CO f}, {H1...H f}, {VOC1...VOC f}};

[0119] It should be noted that {O1...O f} is a first concentration set, which is a set corresponding to oxygen concentration, O f is the fth first concentration in the first concentration set; {(CO2)1...(CO2) f} is a second concentration set, and the second concentration set is a set corresponding to the carbon dioxide concentration, (CO2) f is the fth second concentration in the second concentration set; {CO1...CO f} is a third concentration set, and the third concentration set is a set corresponding to the carbon monoxide concentration, CO f is the fth third concentration in the third concentration set; {H1...H f} is a fourth concentration set, and the fourth concentration set is a set corresponding to the hydrogen concentration, H f is the fth fourth concentration in the fourth concentration set; {VOC1…VOC f} is a fifth concentration set, and the fifth concentration set is a set corresponding to the concentration of volatile compounds, H f is the fth fifth concentration in the fifth concentration set;

[0120] Volatile compounds are a class of organic chemicals that evaporate easily at room temperature; they have high vapor pressure and low water solubility, and can quickly change from liquid or solid to gas and enter the air; lithium battery electrolytes contain organic solvents such as ethylene carbonate (EC) and dimethyl carbonate (DMC); under abnormal conditions such as overcharging, high temperature or internal short circuit, these solvents will decompose and release volatile compounds.

[0121] The third processing module is used to analyze and process the gas concentration set to obtain a set of equation derivatives.

[0122] It should be noted that as the charging time increases, the elements in the gas concentration set also increase, and each set of equation derivatives obtained after analyzing and processing the gas concentration set will overwrite the set of equation derivatives obtained from the previous analysis and processing.

[0123] For example, real-time data collection is performed from the beginning of the CC charging stage. The current time is the 10th unit time, that is, there are 10 oxygen concentrations in the first concentration set. Since the 10th oxygen concentration is added to the first concentration set, after linear regression fitting of the first concentration set, the first concentration equation obtained may be different from the first concentration equations of the first 9 oxygen concentrations, which may lead to an increase in the error of the equation derivative set obtained by subsequent analysis and processing. Therefore, the current first equation derivative set is used to cover the first equation derivative set obtained by the previous analysis and processing. Similarly, the current equation derivative set is used to cover the equation derivative set obtained by one analysis and processing.

[0124] The method for obtaining the set of equation derivatives includes:

[0125] Linear regression fitting is performed on the elements in the gas concentration set to obtain a first concentration equation, a second concentration equation, a third concentration equation, a fourth concentration equation and a fifth concentration equation.

[0126] The method for obtaining the first concentration equation includes:

[0127] The first concentration equation obtained by linear regression fitting is f(O)=β×t+Y;

[0128] Wherein β is the regression coefficient of the first concentration equation, t is time, and Y is the intercept of the first concentration equation. The β and Y are calculated by the least squares method. The specific calculation method is as follows:

[0129]

[0130] Where G is the number of elements in the first concentration set, O g is the gth oxygen concentration in the first concentration set, t g O g The corresponding time point.

[0131] The method for obtaining the second concentration equation includes:

[0132] The second concentration equation obtained by linear regression fitting is f(CO2)=6×t+ε;

[0133] Wherein δ is the regression coefficient of the second concentration equation, t is time, E is the intercept of the second concentration equation, and the δ and ε are calculated by the least squares method. The specific calculation method is as follows:

[0134]

[0135] Where G is the number of elements in the second concentration set, (CO2) g is the gth carbon dioxide concentration in the second concentration set, t g (CO2) g The corresponding time point.

[0136] The method for obtaining the third concentration equation includes:

[0137] The third concentration equation obtained by linear regression fitting is f(CO)=ζ×t+η;

[0138] Wherein ζ is the regression coefficient of the third concentration equation, t is the time, and η is the intercept of the third concentration equation. The ζ and η are calculated by the least squares method. The specific calculation method is as follows:

[0139]

[0140] Where G is the number of elements in the third concentration set, CO g is the gth carbon monoxide concentration in the third concentration set, t g For CO g The corresponding time point.

[0141] The method for obtaining the fourth concentration equation includes:

[0142] The fourth concentration equation obtained by linear regression fitting is f(H)=λ×t+μ;

[0143] Wherein λ is the regression coefficient of the fourth concentration equation, t is time, and μ is the intercept of the fourth concentration equation. The λ and μ are calculated by the least squares method. The specific calculation method is as follows:

[0144]

[0145] Where G is the number of elements in the fourth concentration set, H g is the gth hydrogen concentration in the fourth concentration set, t g H g The corresponding time point.

[0146] The method for obtaining the fifth concentration equation includes:

[0147] The fifth concentration equation obtained by linear regression fitting is f(VOC)=ω×t+φ;

[0148] Wherein ω is the regression coefficient of the fifth concentration equation, t is the time, φ is the intercept of the fifth concentration equation, and the ω and φ are calculated by the least squares method, and the specific calculation method is as follows:

[0149]

[0150] Where G is the number of elements in the fifth concentration set, VOC g is the gth volatile compound concentration in the fifth concentration set, t g For VOC g The corresponding time point.

[0151] The second concentration equation f(CO2), the third concentration equation f(CO), the fourth concentration equation f(H) and the fifth concentration equation f(VOC) are obtained in the same manner as the first concentration equation.

[0152] Among them, the first concentration equation is the equation corresponding to the first concentration set, the second concentration equation is the equation corresponding to the second concentration set, the third concentration equation is the equation corresponding to the third concentration set, the fourth concentration equation is the equation corresponding to the fourth concentration set, and the fifth concentration equation is the equation corresponding to the fifth concentration set.

[0153] The derivative of f(O) is obtained by differentiating the first equation f′(O), the derivative of f(CO2) is obtained by differentiating the second equation f′(CO2), the derivative of f(CO) is obtained by differentiating the third equation f′(CO), the derivative of f(H) is obtained by differentiating the fourth equation f′(H), and the derivative of f(VOC) is obtained by differentiating the fifth equation f′(VOC).

[0154] It should be noted that a common method for finding derivatives is to use a mathematical library provided in a programming language, such as SymPy in Python.

[0155] Substitute the oxygen concentrations in the first concentration set into f′(O) to form the first equation derivative set; substitute the carbon dioxide concentrations in the second concentration set into f′(CO2) to form the second equation derivative set; substitute the carbon monoxide concentrations in the third concentration set into f′(CO) to form the third equation derivative set; substitute the hydrogen concentrations in the fourth concentration set into f′(H) to form the fourth equation derivative set; substitute the volatile compound concentrations in the fifth concentration set into f′(VOC) to form the fifth equation derivative set.

[0156] A first set of derivatives of equations, a second set of derivatives of equations, a third set of derivatives of equations, a fourth set of derivatives of equations, and a fifth set of derivatives of equations are added to the set of derivatives of equations.

[0157] The set of derivatives of the equations is expressed as follows:

[0158] {{f′(O)1...f′(O) n}, {f′(CO2)1...f′(CO2) n}, {f′(CO)1...f′(CO) n}, {f′(H)1...f′(H) n}, {f′(VOC)1...f′(VOC) n}};

[0159] It should be noted that {f′(O)1...f′(O) n} is the derivative set of the first equation, f′(O) n is the nth first equation derivative in the first equation derivative set; {f′(CO2)1…f′(CO2) n} is the derivative set of the second equation, f′(C02) n is the nth second equation derivative in the second equation derivative set; {f′(CO)1...f′(CO) n} is the set of derivatives of the third equation, f′(CO) n is the nth third-party derivative in the third-party derivative set; {f′(H)1...f′(H) n} is the derivative set of the fourth equation, f′(H) n is the nth derivative of the fourth equation in the fourth equation derivative set; {f′(VOC)1...f′(VOC) n} is the derivative set of the fifth equation, f′(VOC) n is the nth derivative of the fifth equation in the fifth equation derivative set.

[0160] It should be noted that the derivative reflects the trend of the equation; if the derivative is greater than 0 and the larger the derivative value, the faster the equation increases; if the derivative is equal to 0, the equation is a straight line; if the derivative is less than 0 and the smaller the derivative value, the faster the equation decreases.

[0161] The charging diagnosis module inputs the charging diagnosis data into a pre-trained charging diagnosis model to obtain a charging diagnosis value; the charging diagnosis data includes a monitoring slope set and an equation derivative set.

[0162] The charging diagnosis value includes 0, 1, 2, 3, and 4; 0 indicates normal, 1 indicates short circuit, 2 indicates electrolyte leakage, 3 indicates that the voltage exceeds the safety threshold, and 4 indicates that the current exceeds the safety threshold;

[0163] For example, if the voltage slope monitoring center monitors the voltage slope decrease amplitude that exceeds the preset voltage slope decrease threshold, the current slope monitoring center monitors the current slope decrease amplitude that exceeds the preset current slope decrease threshold, the internal resistance slope monitoring center monitors the internal resistance slope decrease amplitude that exceeds the preset internal resistance slope decrease threshold, and the temperature slope monitoring center monitors the temperature slope increase amplitude that exceeds the preset temperature slope increase threshold, then it indicates that a short circuit occurs during charging of the lithium battery.

[0164] For example, if the decrease in the value of the first equation derivative in the first equation derivative set exceeds the preset first equation derivative decrease threshold, the increase in the value of the second equation derivative in the second equation derivative set exceeds the preset second equation derivative increase threshold, the increase in the value of the third equation derivative in the third equation derivative set exceeds the preset third equation derivative increase threshold, the increase in the value of the fourth equation derivative in the fourth equation derivative set exceeds the preset fourth equation derivative increase threshold, and the increase in the value of the fifth equation derivative in the fifth equation derivative set exceeds the preset fifth equation derivative increase threshold, it indicates that the lithium battery electrolyte has leaked; electrolyte leakage causes chemical reactions inside the battery, resulting in the consumption of oxygen and the production of carbon dioxide, carbon monoxide, hydrogen and volatile compounds, and monitoring gas concentration changes will reflect electrolyte leakage more quickly and accurately.

[0165] The training method of the charging diagnosis model includes:

[0166] A charging diagnostic data set is collected in advance, wherein the charging diagnostic data set includes charging diagnostic data and charging diagnostic values ​​corresponding to the charging diagnostic data. The charging diagnostic data set is divided into a training set and a test set, a classifier is constructed, the charging diagnostic data in the training set is used as the input of a charging diagnostic model, and the charging diagnostic values ​​in the training set are used as the output of the charging diagnostic model, and minimizing the sum of the prediction accuracies of all predicted charging diagnostic values ​​is used as a training goal; training is stopped when the sum of the prediction accuracies converges; the charging diagnostic model is a gradient boosting tree model.

[0167] The calculation formula for prediction accuracy is: L m =(Y m -S m ) 2 , where Lm is the prediction accuracy, Y m is the predicted charging diagnosis value corresponding to the mth group of charging diagnosis data, S m is the actual charging diagnosis value corresponding to the mth group of charging diagnosis data.

[0168] The diagnosis processing module is used to classify the charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories, and automatically repair the faults in the automatic adjustment category.

[0169] The method of dividing the charging diagnosis values ​​into an automatic adjustment category and a non-automatic adjustment category and automatically repairing the faults of the automatic adjustment category includes:

[0170] S111: Obtain current charging diagnosis value;

[0171] S112: Determine whether the current charging diagnosis value is 0; if the current charging diagnosis value is 0, end the current process; otherwise, execute S113;

[0172] S113: Classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories;

[0173] The method for classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories includes:

[0174] Classify the charging diagnosis values ​​in advance, add the charging diagnosis values ​​that support automatic adjustment to the automatic adjustment category, and add the charging diagnosis values ​​other than 0 to the non-automatic adjustment category; for example, add 3 and 4 to the automatic adjustment category;

[0175] S114: If the current charging diagnosis value belongs to the automatic adjustment category, execute S145; if the current charging diagnosis value belongs to the non-automatic adjustment category, execute S146;

[0176] S115: Automatically handle the current fault;

[0177] S116: Immediately cut off the charging power supply and issue an alarm.

[0178] The method for automatically processing the current fault includes:

[0179] S1151: Count the number of currently monitored voltage slopes and centralized monitored voltage slopes, recorded as VN; count the number of currently monitored current slopes and centralized monitored current slopes, recorded as IN;

[0180] S1152: Obtain the VNth test voltage slope from the test voltage slope set; obtain the INth test voltage slope from the test current slope set;

[0181] S1153: Obtain the V corresponding to the VNth monitoring voltage slope start ; The V start is the voltage at the beginning of the unit time corresponding to the VNth monitored voltage slope; obtains the I corresponding to the INth monitored current slope start ; said I start is the current at the beginning of the unit time corresponding to the INth monitored current slope;

[0182] S1154: Calculate the corrected voltage value and the corrected current value;

[0183] The modified voltage value calculation method comprises:

[0184] V new =VK normal ×unitTime+V start ;

[0185] Among them, unitTime is the unit time, VK normal To test the voltage slope, V new is the corrected voltage value;

[0186] The modified current value calculation method includes:

[0187] I new =IK normal ×unitTime+I start ;

[0188] Among them, unitTime is the unit time, IK normal To test the current slope, I new is the corrected current value;

[0189] S1155: Use the voltage regulator to adjust the charging voltage to V new ; Use the current regulator to adjust the charging current to I new .

[0190] It should be noted that after the charging diagnostic values ​​are divided into automatic adjustment categories and non-automatic adjustment categories, and the faults in the automatic adjustment categories are automatically repaired, the charging data and gas concentration monitoring per unit time continue to be collected, and the collection is stopped when the lithium battery is fully charged.

[0191] Example 2

[0192] See also Figure 3 As shown, this embodiment provides a distributed intelligent power equipment fault remote diagnosis system, which also includes:

[0193] The voltage acquisition module is used to collect the voltage of the lithium battery after the charger is connected to the power supply and before the charger starts to transmit current to the lithium battery, and mark it as the first detection voltage.

[0194] The first detection voltage is obtained by measuring the terminal voltage of the lithium battery through an ADC (analog-to-digital converter) inside the charger.

[0195] The mode setting module is used to set the charging mode of the next stage according to the first detection voltage.

[0196] The method for formulating a charging mode for the next stage according to the first detection voltage includes:

[0197] S101: Preset low voltage threshold YZ1;

[0198] S102: Compare the first detection voltage with YZ1; if the first detection voltage is less than or equal to YZ1, the lithium battery voltage is lower than the normal range, and S103 is executed; if the first detection voltage is greater than YZ1, the lithium battery voltage is within the normal range, the charging mode is switched to the CC-CV charging mode, and the current judgment process ends;

[0199] S103: preset trickle charge threshold; preset trickle time threshold TIME1, trickle detection interval TIME2; wherein the trickle charge threshold is usually less than 0.1C, C is the rate unit of the lithium battery capacity; the trickle time threshold is the maximum duration of trickle charge, the larger the lithium battery capacity, the larger the trickle time threshold, and the specific trickle time threshold is set by those skilled in the art according to the lithium battery capacity. For example, if the lithium battery capacity is 3000mA, the 0.1C trickle charge threshold is 300mA, and the trickle time threshold is 2 hours.

[0200] S104: Calculate the maximum number of detection times NUM; NUM is the ratio of the trickle time threshold to the trickle detection interval.

[0201] S105: Switch the charging mode to the trickle charging mode; the trickle charging mode is that the charger uses a current lower than a preset trickle charging threshold to charge the lithium battery; set a timing time, the initial value is 0, and the timing time starts when the trickle charging starts; preset i, the initial value of i is 1, i∈{1, 2, ..., NUM}.

[0202] S106: When the timing time reaches TIME2 (for example, the current detection time is 2:10, the trickle detection interval is 20 minutes, and the next detection time is 2:30), the current lithium battery voltage is compared with YZ1 for the i-th time; if the current lithium battery voltage is less than or equal to YZ1, S107 is executed; if the current lithium battery voltage is greater than YZ1, the current lithium battery voltage is within the normal range, the charging mode is switched to the CC-CV charging mode, and the current judgment process ends;

[0203] S107: Let i=i+1, and set the timing time to 0; if i is less than or equal to NUM, execute S106; if i is greater than NUM, stop charging and alarm.

[0204] It should be noted that the purpose of formulating the next stage charging mode is to prevent the lithium battery with abnormal voltage from being directly charged using the CC-CV charging mode to avoid safety hazards; in addition, formulating a reasonable charging mode based on the first detection voltage of the lithium battery is helpful to extend the life of the lithium battery.

[0205] When i is greater than NUM, the lithium battery voltage has not returned to the normal range, which is regarded as a lithium battery failure, so charging is stopped and an alarm is sounded; the CC-CV charging mode is a charging mode usually followed in the lithium battery charging process; CC is constant current, and CV is constant voltage; the CC-CV charging mode includes a CC charging stage and a CV charging stage; the CC charging stage uses a constant current to charge the lithium battery, and the lithium battery voltage will gradually increase with the charging time; when the lithium battery voltage reaches the preset rated voltage, it enters the CV charging stage; the CV charging stage maintains the preset rated voltage to charge the lithium battery, and the charging current will gradually decrease with the charging time; when the lithium battery is fully charged, charging is stopped.

[0206] Example 3

[0207] See also Figure 2 As shown, this embodiment provides a lithium battery charging safety monitoring and early warning method, which also includes:

[0208] Collect monitoring and charging data of lithium batteries per unit time;

[0209] Analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set;

[0210] Collect charging test data of lithium batteries;

[0211] Processing the charging test data to obtain a charging test data set;

[0212] Collect the monitored gas concentration once per unit time, and add the monitored gas concentration to the gas concentration set;

[0213] Analyze and process the gas concentration set to obtain the equation derivative set;

[0214] Inputting charging diagnostic data into a pre-trained charging diagnostic model to obtain a charging diagnostic value; the charging diagnostic data includes a monitoring slope set and an equation derivative set;

[0215] The charging diagnosis values ​​are divided into automatic adjustment categories and non-automatic adjustment categories, and faults in the automatic adjustment category are automatically repaired.

[0216] Example 4

[0217] See also Figure 4 As shown, the present application also provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, a charging safety monitoring and early warning method for a lithium battery as described above may be executed.

[0218] The method or system according to the embodiment of the present application can also be used Figure 4 The electronic device architecture shown in FIG. Figure 4 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store a lithium battery charging safety monitoring and early warning method provided in the present application. Further, the electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0219] Example 5

[0220] See also Figure 5 As shown, the present application also provides a computer-readable storage medium 600. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a charging safety monitoring and early warning method for a lithium battery according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0221] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: a charging safety monitoring and early warning method and system for lithium batteries. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0222] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0223] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A lithium battery charging safety monitoring and early warning method, characterized in that: include: Collect monitoring and charging data of lithium batteries per unit time; Analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set; Collect charging test data of lithium batteries; Processing the charging test data to obtain a charging test data set; Collect the monitored gas concentration once per unit time, and add the monitored gas concentration to the gas concentration set; Analyze and process the gas concentration set to obtain the equation derivative set; Inputting charging diagnostic data into a pre-trained charging diagnostic model to obtain a charging diagnostic value; the charging diagnostic data includes a monitoring slope set and an equation derivative set; The charging diagnosis values ​​are divided into automatic adjustment categories and non-automatic adjustment categories, and faults in the automatic adjustment category are automatically repaired.

2. A lithium battery charging safety monitoring and early warning method according to claim 1, characterized in that: The monitoring of charging data includes monitoring charging voltage, monitoring charging current, monitoring battery temperature and monitoring charging internal resistance; The method of obtaining the monitoring processing data and adding the monitoring processing data to the monitoring slope set includes: The slopes of the monitored charging data are calculated respectively to obtain the monitored voltage slope, the monitored current slope, the monitored temperature slope and the monitored internal resistance slope; The calculation method of the monitoring voltage slope is: VK is the monitoring voltage slope, V1 is the voltage at the beginning of the unit time, V2 is the voltage at the end of the unit time, and unitTime is the unit time; Calculate the monitoring current slope, monitoring temperature slope and monitoring internal resistance slope using the same calculation method for the monitoring voltage slope; add the monitoring voltage slope to the monitoring voltage slope set; add the monitoring current slope to the monitoring current slope set; add the monitoring temperature slope to the monitoring temperature slope set; add the monitoring internal resistance slope to the monitoring internal resistance slope set; The monitoring voltage slope set, monitoring current slope set, monitoring temperature slope set, and monitoring internal resistance slope set are added to the monitoring slope set.

3. A lithium battery charging safety monitoring and early warning method according to claim 2, characterized in that: The charging test data includes a charging test voltage, a charging test current, a test battery temperature and a charging test internal resistance; the charging test data set includes a test voltage slope set, a test current slope set, a test temperature slope set and a test internal resistance slope set; The method for obtaining the test voltage slope set is: The charging test voltage is divided into U test voltage parts according to the first unit time, where U is a positive number greater than 1, and the test voltage slope is calculated for each test voltage part using the same calculation method as the monitoring voltage slope, and the test voltage slope is added to the test voltage slope set; the first unit time is the same as the unit time; The test current slope set, the test temperature slope set and the test internal resistance slope set are obtained by the method for obtaining the test voltage slope set; Add the test voltage slope set, test current slope set, test temperature slope set, and test internal resistance slope set to the charging test data set.

4. A lithium battery charging safety monitoring and early warning method according to claim 3, characterized in that: The monitored gas concentrations include oxygen concentration, carbon dioxide concentration, carbon monoxide concentration, hydrogen concentration and volatile compound concentration; adding oxygen concentration to the first concentration set, adding carbon dioxide concentration to the second concentration set, adding carbon monoxide concentration to the third concentration set, adding hydrogen concentration to the fourth concentration set, and adding volatile compound concentration to the fifth concentration set; the gas concentration sets include the first concentration set, the second concentration set, the third concentration set, the fourth concentration set, and the fifth concentration set; Performing linear regression fitting on the elements in the gas concentration set respectively to obtain a first concentration equation, a second concentration equation, a third concentration equation, a fourth concentration equation and a fifth concentration equation; The method for obtaining the first concentration equation includes: The first concentration equation obtained by linear regression fitting is f(O)=β×t+γ; β is the regression coefficient of the first concentration equation, t is time, and Y is the intercept of the first concentration equation, and β and Y are calculated by the least squares method; The second concentration equation f(CO2), the third concentration equation f(CO), the fourth concentration equation f(H) and the fifth concentration equation f(VOC) are obtained in the same manner as the first concentration equation.

5. A lithium battery charging safety monitoring and early warning method according to claim 4, characterized in that: The method for obtaining the set of equation derivatives includes: The derivative of f(O) is obtained by differentiating the first equation f′(O), the derivative of f(CO2) is obtained by differentiating the second equation f′(CO2), the derivative of f(CO) is obtained by differentiating the third equation f′(CO), the derivative of f(H) is obtained by differentiating the fourth equation f′(H), and the derivative of f(VOC) is obtained by differentiating the fifth equation f′(VOC); Substitute the oxygen concentrations in the first concentration set into f′(O) to form a first equation derivative set; substitute the carbon dioxide concentrations in the second concentration set into f′(CO2) to form a second equation derivative set; substitute the carbon monoxide concentrations in the third concentration set into f′(CO) to form a third equation derivative set; substitute the hydrogen concentrations in the fourth concentration set into f′(H) to form a fourth equation derivative set; substitute the volatile compound concentrations in the fifth concentration set into f′(VOC) to form a fifth equation derivative set; A first set of derivatives of equations, a second set of derivatives of equations, a third set of derivatives of equations, a fourth set of derivatives of equations, and a fifth set of derivatives of equations are added to the set of derivatives of equations.

6. A lithium battery charging safety monitoring and early warning method according to claim 5, characterized in that: The training method of the charging diagnosis model includes: A charging diagnostic data set is collected in advance, wherein the charging diagnostic data set includes charging diagnostic data and charging diagnostic values ​​corresponding to the charging diagnostic data. The charging diagnostic data set is divided into a training set and a test set, a classifier is constructed, the charging diagnostic data in the training set is used as the input of a charging diagnostic model, and the charging diagnostic values ​​in the training set are used as the output of the charging diagnostic model, and minimizing the sum of the prediction accuracies of all predicted charging diagnostic values ​​is used as a training goal; training is stopped when the sum of the prediction accuracies converges; the charging diagnostic model is a gradient boosting tree model.

7. A lithium battery charging safety monitoring and early warning method according to claim 6, characterized in that: The method of dividing the charging diagnosis values ​​into an automatic adjustment category and a non-automatic adjustment category and automatically repairing the faults of the automatic adjustment category includes: S111: Obtain current charging diagnosis value; S112: Determine whether the current charging diagnosis value is 0; if the current charging diagnosis value is 0, end the current process; otherwise, execute S113; S113: Classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories; The method for classifying charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories includes: Classify charging diagnosis values ​​in advance, add charging diagnosis values ​​that support automatic adjustment to the automatic adjustment category, and add charging diagnosis values ​​other than 0 to the non-automatic adjustment category; S114: If the current charging diagnosis value belongs to the automatic adjustment category, execute S145; if the current charging diagnosis value belongs to the non-automatic adjustment category, execute S146; S115: Automatically handle the current fault; S116: Immediately cut off the charging power supply and issue an alarm.

8. A lithium battery charging safety monitoring and early warning method according to claim 7, characterized in that: The method for automatically processing the current fault includes: S1151: Count the number of currently monitored voltage slopes and centralized monitored voltage slopes, recorded as VN; count the number of currently monitored current slopes and centralized monitored current slopes, recorded as IN; S1152: Obtain the VNth test voltage slope from the test voltage slope set; obtain the INth test voltage slope from the test current slope set; S1153: Obtain the V corresponding to the VNth monitoring voltage slope start ; The V start is the voltage at the beginning of the unit time corresponding to the VNth monitored voltage slope; obtains the I corresponding to the INth monitored current slope start ; said I start is the current at the beginning of the unit time corresponding to the lNth monitored current slope; S1154: Calculate the corrected voltage value and the corrected current value; The modified voltage value calculation method includes: V new =VK normal ×unitTime+V start ; unitTime is the unit time, VK normal To test the voltage slope, V new is the corrected voltage value; The modified current value calculation method includes: I new =I normal ×unitTime+I start ; unitTime is the unit time, IK normal To test the current slope, I new is the corrected current value; S1155: Use the voltage regulator to adjust the charging voltage to V new ; Use the current regulator to adjust the charging current to I new .

9. A lithium battery charging safety monitoring and early warning method according to claim 8, characterized in that: Also includes: After the charger is connected to the power supply and before the current starts to be transmitted to the lithium battery, the lithium battery voltage is collected and marked as the first detection voltage; and formulating a charging mode for the next stage according to the first detection voltage; The method for formulating a charging mode for the next stage according to the first detection voltage includes: S101: Preset low voltage threshold YZ1; S102: compare the first detection voltage with YZ1; if the first detection voltage is less than or equal to YZ1, execute S103; if the first detection voltage is greater than YZ1, switch the charging mode to the CC-CV charging mode, and end the current judgment process; S103: preset trickle charge threshold; preset trickle time threshold TIME1, trickle detection interval TIME2; S104: Calculate the maximum number of detection times NUM; NUM is the ratio of the trickle time threshold to the trickle detection interval; S105: Switch the charging mode to the trickle charging mode; the trickle charging mode is that the charger uses a current lower than a preset trickle charging threshold to charge the lithium battery; set a timing time, the initial value of which is 0, and the timing time starts when the trickle charging starts; preset i, the initial value of i is 1, i∈{1, 2, ..., NUM}; S106: When the timing reaches TIME2, the current lithium battery voltage is compared with YZ1 for the i-th time; if the current lithium battery voltage is less than or equal to YZ1, S107 is executed; if the current lithium battery voltage is greater than YZ1, the current lithium battery voltage is within the normal range, the charging mode is switched to the CC-CV charging mode, and the current judgment process ends; S107: Let i=i+1, and set the timing time to 0; if i is less than or equal to NUM, execute S106; if i is greater than NUM, stop charging and alarm.

10. A lithium battery charging safety monitoring and early warning system, implementing a lithium battery charging safety monitoring and early warning method according to any one of claims 1 to 9, characterized in that: include: The first acquisition module is used to collect monitoring and charging data of the lithium battery within a unit time; A first processing module is used to analyze and process the monitoring charging data collected per unit time to obtain monitoring processing data, and add the monitoring processing data to the monitoring slope set; The second acquisition module is used to collect charging test data of the lithium battery; A second processing module is used to process the charging test data to obtain a charging test data set; The third acquisition module is used to collect the monitored gas concentration once per unit time and add the monitored gas concentration to the gas concentration set; The third processing module is used to analyze and process the gas concentration set to obtain the equation derivative set; A charging diagnosis module, inputting charging diagnosis data into a pre-trained charging diagnosis model to obtain a charging diagnosis value; the charging diagnosis data includes a monitoring slope set and an equation derivative set; The diagnosis processing module is used to classify the charging diagnosis values ​​into automatic adjustment categories and non-automatic adjustment categories, and automatically repair the faults in the automatic adjustment category.

Citation Information

Patent Citations

  • Rechargeable battery short circuit prediction device and rechargeable battery short circuit prediction method

    CN111108403A

  • Power battery safety monitoring device and self-adaptive control method

    CN115207577A

  • Charging safety monitoring and early warning method and system for lithium battery

    CN116466237A

  • Battery management based on internal optical sensing

    US20150303723A1