Method and system for judging charging time abnormity of lithium ion battery

Abstract

The embodiment of the invention provides a method and system for judging the charging time abnormity of a lithium ion battery, and the method comprises the steps: obtaining effective charging cycle data containing the charging time, and extracting the charging feature data of effective charging cycle from the effective charging cycle data; constructing a gradient boosting algorithm-based regression model of each battery type, and training the corresponding gradient boosting algorithm-based regression model by using the charging characteristic data of the effective charging cycle to obtain the gradient boosting algorithm-based regression model trained by each battery type; and acquiring real-time charging data of a target lithium-ion battery, inputting the real-time charging data in the charging process of the target lithium-ion battery into the correspondingly trained regression model based on the gradient lifting algorithm, and judging whether the charging time in the charging process of the target lithium-ion battery is abnormal or not.

Description

Technical Field

[0001] The embodiments of the present specification relate to the technical field of power batteries, and in particular to a method and system for determining abnormal charging time of a lithium-ion battery. Background Art

[0002] In the current prior art, to determine whether a lithium-ion battery has charging abnormalities during charging, the following methods are generally used:

[0003] Charging time estimation method: Estimate the remaining charging time based on the charging current;

[0004] Abnormal charging time: The expected charging time is calculated based on the battery capacity and charging rate. If the actual charging time is significantly longer or shorter than the expected time, there may be an abnormality.

[0005] The current existing technology has relatively simple logical rules and requires a lot of manual judgment. It is unable to identify data with little difference. For batteries of different capacities, multiple inspection methods need to be designed. There is no way to accurately and efficiently identify abnormal battery charging time. In scenarios where a large number of batteries need to be monitored, it is impossible to achieve comprehensive promotion. Therefore, there is an urgent need for a method that can quickly and efficiently identify abnormal battery charging time. In actual scenarios, the current is basically a variable value, and there is no way to estimate the time accurately and reliably. The existing technology requires a lot of manpower and has a low accuracy rate, so it cannot be promoted. For multiple battery models, there are many rules that need to be designed, which are relatively complex, and the judgment rules for abnormalities are relatively simple and insufficient.

[0006] Lithium-ion battery charging time abnormal warning can avoid potential safety problems in the battery system, such as overcharging. At the same time, it can also determine abnormal health status of batteries and charging equipment failures, and can be handled in time to avoid danger. Abnormal charging time affects the efficiency of operations and easily causes overcharging of the battery, endangering the safety of the battery. Summary of the invention

[0007] In view of this, the embodiments of this specification provide a method and system for determining abnormal charging time of a lithium-ion battery. One or more embodiments of this specification also relate to a method for determining abnormal charging time of a lithium-ion battery, a system for determining abnormal charging time of a lithium-ion battery, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects existing in the prior art.

[0008] According to a first aspect of an embodiment of this specification, a method for determining whether a lithium-ion battery charging time is abnormal is provided, comprising:

[0009] Acquire effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extract charging characteristic data of the effective charging cycle from the effective charging cycle data;

[0010] Constructing a regression model based on a gradient boosting algorithm for each battery type, and using the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm, to obtain a trained regression model based on the gradient boosting algorithm for each battery type;

[0011] The battery type of the target lithium electronic battery and the real-time charging data during the charging process are obtained, and according to the battery type of the target lithium electronic battery, a corresponding trained regression model based on the gradient boosting algorithm is obtained, and the real-time charging data during the charging process of the target lithium electronic battery is input into the trained regression model based on the gradient boosting algorithm to determine whether there is an abnormality in the charging time during the charging process of the target lithium electronic battery.

[0012] Preferably, obtaining effective charging cycle data of each lithium-ion battery of each battery type during the charging process includes:

[0013] Determine the cell type of each lithium-ion battery;

[0014] Obtaining historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle;

[0015] According to the charging conditions set for each battery type, charging cycle data meeting the charging conditions are extracted from the historical charging cycle data set of each lithium-ion battery of each battery type, and the charging cycle data meeting the charging conditions are used as valid charging cycle data.

[0016] Preferably, the charging conditions set for each battery type include at least:

[0017] The starting SOC of each charging cycle in the historical charging cycle data is less than a first SOC threshold, and the ending SOC is greater than and a second SOC threshold; wherein the first SOC threshold is less than the second SOC threshold;

[0018] According to the set collection time interval, the number of charging samples of each charging cycle in the historical charging cycle data is greater than the set sample threshold;

[0019] The charging current of each charging cycle in the historical charging cycle data is greater than a set current threshold or the charging time is greater than a set charging time threshold.

[0020] Preferably, the charging characteristic data of the effective charging cycle includes:

[0021] Starting SOC, ending SOC, average current during charging time, average current of multiple segmented samples, initial charging temperature, maximum charging temperature, ending charging temperature, initial charging voltage, maximum voltage of segmented samples and ending charging voltage.

[0022] Preferably, the charging characteristic data of the effective charging cycle of each battery type is used to train the corresponding regression model based on the gradient boosting algorithm, and the trained regression model based on the gradient boosting algorithm for each battery type is obtained, which includes:

[0023] Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, eliminating abnormal effective charging cycle data while retaining normal effective charging cycle data;

[0024] The corresponding regression model based on the gradient boosting algorithm is retrained using the charging characteristic data of the normal effective charging cycle of each battery type to obtain a trained regression model based on the gradient boosting algorithm for each battery type.

[0025] Preferably, using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, eliminating abnormal effective charging cycle data, while retaining normal effective charging cycle data includes:

[0026] Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, and using the 2σ principle to obtain abnormal charging characteristic data and normal charging characteristic data;

[0027] According to the abnormal charging characteristic data, effective charging cycle data corresponding to the abnormal charging characteristic data is obtained, and the effective charging cycle data is used as the abnormal effective charging cycle data; at the same time, according to the normal charging characteristic data, effective charging cycle data corresponding to the normal charging characteristic data is obtained, and the effective charging cycle data is used as the normal effective charging cycle data;

[0028] The charging characteristic data of the abnormal effective charging cycle data is eliminated, while the charging characteristic data of the normal effective charging cycle data is retained.

[0029] According to a second aspect of an embodiment of this specification, a system for determining abnormal charging time of a lithium-ion battery is provided, comprising:

[0030] An acquisition module, used to acquire effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extract charging characteristic data of the effective charging cycle from the effective charging cycle data;

[0031] A model building and training module is used to build a regression model based on the gradient boosting algorithm for each battery type, and use the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm to obtain a trained regression model based on the gradient boosting algorithm for each battery type;

[0032] The abnormality judgment module is used to obtain the battery type of the target lithium electronic battery and the real-time charging data during the charging process, and obtain the corresponding trained regression model based on the gradient boosting algorithm according to the battery type of the target lithium electronic battery, and input the real-time charging data during the charging process of the target lithium electronic battery into the trained regression model based on the gradient boosting algorithm to judge whether there is an abnormality in the charging time during the charging process of the target lithium electronic battery.

[0033] Preferably, the acquisition module is specifically used to determine the battery type of each lithium-ion battery; acquire the historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle; according to the charging conditions set for each battery type, extract the charging cycle data that meets the charging conditions from the historical charging cycle data set of each lithium-ion battery of each battery type, and use the charging cycle data that meets the charging conditions as the valid charging cycle data.

[0034] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0035] Memory and processor;

[0036] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method for determining abnormal charging time of a lithium-ion battery are implemented.

[0037] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the method for determining abnormal charging time of a lithium-ion battery are implemented.

[0038] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for determining abnormal charging time of a lithium-ion battery.

[0039] The method and system for judging abnormal charging time of lithium-ion batteries provided in the embodiments of the present specification are as follows: obtaining effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extracting charging characteristic data of the effective charging cycle from the effective charging cycle data; constructing a regression model based on the gradient boosting algorithm for each battery type, and using the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm to obtain a trained regression model based on the gradient boosting algorithm for each battery type; obtaining the battery type of the target lithium-ion battery and the real-time charging data during the charging process, and obtaining a corresponding trained regression model based on the gradient boosting algorithm according to the battery type of the target lithium-ion battery, and inputting the real-time charging data of the target lithium-ion battery during the charging process into the trained regression model based on the gradient boosting algorithm to judge whether there is abnormality in the charging time of the target lithium-ion battery during the charging process. This solves the problem of judging the abnormal charging time of the battery during the charging process, and uses big data and model methods, combined with historical data, after data cleaning, feature extraction, and model training, after obtaining the model, it can be combined with subsequent collected data to automatically and accurately predict the abnormal charging power during the battery charging process. This method can achieve a high accuracy rate and can predict the abnormal charging time of different batteries during the charging process. It does not require much manual participation, greatly improves the prediction accuracy and reduces manual labor, improves economy and efficiency, effectively avoids time anomalies in the charging process, avoids the phenomenon of battery health affected by battery overcharging, and also avoids the situation where work efficiency is affected by abnormal charging time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a method for determining abnormal charging time of a lithium-ion battery provided by an embodiment of this specification;

[0041] Figure 2 It is a schematic diagram of a system for judging abnormal charging time of a lithium-ion battery provided by an embodiment of this specification;

[0042] Figure 3 is a schematic diagram of all sample data in a training set provided by an embodiment of this specification;

[0043] Figure 4 This is a schematic diagram of normal sample data in a training set provided by an embodiment of this specification;

[0044] Figure 5 It is a schematic diagram of the architecture of a gradient boosting algorithm model provided by an embodiment of this specification;

[0045] Figure 6 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0046] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0047] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0048] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0049] First, the terms involved in one or more embodiments of this specification are explained.

[0050] SOC (State of Charge): It is used to reflect the current capacity of the battery. Its value is defined as the ratio of the remaining capacity to the battery capacity, usually expressed as a percentage. Its value range is 0 to 1. When "SOC = 0", it means that the battery is fully discharged. When "SOC = 1", it means that the battery is fully charged.

[0051] The embodiment of this specification provides a flow chart of a method for judging abnormal charging time of lithium-ion batteries, which can effectively solve the above problems. By using the method of big data and models, combined with historical data, after data cleaning, feature extraction, and model training, after obtaining the model, it can be combined with subsequent collected data to automatically and accurately predict the abnormal charging power during the battery charging process.

[0052] In this specification, a method and system for determining abnormal charging time of a lithium-ion battery are provided. This specification also relates to a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0053] Figure 1 A flow chart of a method for determining abnormal charging time of a lithium-ion battery according to an embodiment of the present specification is shown, comprising:

[0054] Step S101: acquiring effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extracting charging characteristic data of the effective charging cycle from the effective charging cycle data;

[0055] In an embodiment of the present invention, obtaining effective charging cycle data of each lithium-ion battery of each battery type during the charging process includes:

[0056] Determine the cell type of each lithium-ion battery;

[0057] Obtaining historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle;

[0058] Specifically, the starting SOC is the starting charging capacity; the ending SOC is the ending charging capacity; the charging time is the difference between the starting SOC recording time and the ending SOC recording time. For example, if the starting SOC recording time is 8 am and the ending SOC recording time is 1 pm, the charging time is 5 hours.

[0059] Specifically, the charging current at least includes a maximum charging current, a minimum charging current and an average charging current; the charging temperature at least includes a maximum charging temperature, a minimum charging temperature and an average charging temperature; and the charging voltage at least includes a maximum charging voltage, a minimum charging voltage and an average charging voltage.

[0060] According to the charging conditions set for each battery type, charging cycle data meeting the charging conditions are extracted from the historical charging cycle data set of each lithium-ion battery of each battery type, and the charging cycle data meeting the charging conditions are used as valid charging cycle data.

[0061] In an embodiment of the present invention, the charging conditions set for each battery type include at least:

[0062] The starting SOC of each charging cycle in the historical charging cycle data is less than a first SOC threshold, and the ending SOC is greater than and a second SOC threshold; wherein the first SOC threshold is less than the second SOC threshold;

[0063] According to the set collection time interval, the number of charging samples of each charging cycle in the historical charging cycle data is greater than the set sample threshold;

[0064] The charging current of each charging cycle in the historical charging cycle data is greater than a set current threshold or the charging time is greater than a set charging time threshold.

[0065] In an embodiment of the present invention, the charging characteristic data of the effective charging cycle includes:

[0066] Starting SOC, ending SOC, average current during charging time, average current of multiple segmented samples, initial charging temperature, maximum charging temperature, ending charging temperature, initial charging voltage, maximum voltage of segmented samples and ending charging voltage.

[0067] Furthermore, the average current of the multiple segment samples includes the average current of the [0, 0.5] segment samples, the average current of the [0.5, 0.8] segment samples, and the average current of the [0.8, 1] segment samples.

[0068] Furthermore, the highest voltage of the segment samples refers to the highest voltage of the [0.8, 1] segment samples.

[0069] In the embodiment of the present invention, the step S101 specifically includes:

[0070] Step S1011, obtaining data;

[0071] This step includes the charging cycle data of all batteries. It is necessary to obtain the charging cycle data of all batteries during the corresponding charging process, mainly including the battery capacity and the SOC, current, temperature, cell voltage and other data during the charging process.

[0072] Step S1012: data cleaning;

[0073] In this step, invalid charging cycle data, such as null values ​​and abnormal values, must be eliminated first, and obvious abnormal data must be eliminated, leaving available data for the next step of processing.

[0074] Step S1013, extracting effective charging cycle data;

[0075] Extract charging cycle data that meets the requirements and set valid charging cycle data. Valid charging cycle data needs to include the following conditions;

[0076] 1) Contains SOC (60-80 interval), that is, the SOC in the charging cycle data contains at least 60%-80%;

[0077] 2) The number of charging samples is greater than 100, that is, the number of samples is greater than 100 according to the sampling time interval;

[0078] 3) Eliminate slow charging data (maximum charging current is less than 150).

[0079] According to the above three conditions, a round of screening is performed on the data obtained in step S1012 to obtain valid charging cycle data.

[0080] Step S1014: extracting features;

[0081] In this step, features are extracted from the data of the effective charging cycles extracted in step S1013. The features are shown in Table 1.

[0082] Table 1: Feature table

[0083]

[0084] Among them, [0,0.5], [0.5,0.8], and [0.8,1] represent three intervals of sample segmentation characteristic data obtained after all sample ratios 1 are segmented at 0.5 and 0.8, and the average current of the sample characteristic data in each interval is calculated.

[0085] Step S1015: Data classification

[0086] Classify according to battery type, for example, according to battery capacity, and divide different data groups according to different capacities. The capacity of the battery cell is a key indicator that affects the battery charging capacity. The charging capacity of batteries with different capacities varies greatly.

[0087] Furthermore, battery types with different capacities correspond to a regression model based on the gradient boosting algorithm, that is, three battery types have three regression models based on the gradient boosting algorithm.

[0088] Step S102: constructing a regression model based on the gradient boosting algorithm for each battery type, and using the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm, to obtain a trained regression model based on the gradient boosting algorithm for each battery type;

[0089] In an embodiment of the present invention, the charging characteristic data of the effective charging cycle of each battery type is used to train the corresponding regression model based on the gradient boosting algorithm, and the trained regression model based on the gradient boosting algorithm for each battery type is obtained, which includes:

[0090] Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, eliminating abnormal effective charging cycle data while retaining normal effective charging cycle data;

[0091] The corresponding regression model based on the gradient boosting algorithm is retrained using the charging characteristic data of the normal effective charging cycle of each battery type to obtain a trained regression model based on the gradient boosting algorithm for each battery type.

[0092] In an embodiment of the present invention, the charging characteristic data of the effective charging cycle of each battery type is used to train its corresponding regression model based on the gradient boosting algorithm, and abnormal effective charging cycle data is eliminated, while retaining normal effective charging cycle data, including:

[0093] Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, and using the 2σ principle to obtain abnormal charging characteristic data and normal charging characteristic data;

[0094] According to the abnormal charging characteristic data, effective charging cycle data corresponding to the abnormal charging characteristic data is obtained, and the effective charging cycle data is used as the abnormal effective charging cycle data; at the same time, according to the normal charging characteristic data, effective charging cycle data corresponding to the normal charging characteristic data is obtained, and the effective charging cycle data is used as the normal effective charging cycle data;

[0095] The charging characteristic data of the abnormal effective charging cycle data is eliminated, while the charging characteristic data of the normal effective charging cycle data is retained.

[0096] In the embodiment of the present invention, the step S102 specifically includes:

[0097] Step S1021, dividing the training set, the test set and the validation set;

[0098] In this step, all data are randomly divided into training set, test set and validation set in a ratio of 7:2:1.

[0099] Gradient Boosting is an ensemble learning algorithm. Figure 5 As shown in Figure 1, multiple weak learners (usually decision trees) are combined into a strong learner. It performs well in many machine learning tasks and has the following advantages:

[0100] 1. High prediction performance: Gradient boosting has been widely used in many machine learning competitions and practical applications, and has performed well in prediction performance. It is usually able to produce accurate prediction models with low bias and high generalization ability.

[0101] 2. Handling complex relationships: Gradient boosting can capture complex nonlinear relationships between features. By combining multiple decision tree models, it can learn more complex feature interactions and nonlinear relationships, thereby improving the model's expressiveness.

[0102] 3. Robustness: Gradient boosting is robust to outliers and noisy data. Due to the integration of multiple weak learners, it has relatively little impact on individual wrong predictions and can reduce the risk of overfitting of the model.

[0103] Step S1022, first model training;

[0104] In this step, all data are trained for the first time, and then the 2σ principle is used to eliminate anomalies, such as Figure 3 The red dots are abnormal charging cycle data, and the blue dots are normal charging cycle data. Collect data that meets the requirements, such as Figure 4 Normal effective charging cycle data shown.

[0105] Step S1023: model training;

[0106] In this step, the normal and effective charging cycle data screened out in step S1022 is used for retraining to obtain a trained regression model based on the gradient boosting algorithm.

[0107] When training the regression model, in order to eliminate the interference of abnormal points, after the first training is completed, the 2sigma principle is used to screen out healthy points, and then these points are used to retrain to obtain the final regression model based on the gradient boosting algorithm.

[0108] After the final regression model based on the gradient boosting algorithm is obtained, the final regression model based on the gradient boosting algorithm is tested using the test set samples to verify the prediction accuracy of the final regression model based on the gradient boosting algorithm.

[0109] Step S103: Obtain the battery type of the target lithium-ion battery and the real-time charging data during the charging process, and obtain a corresponding trained regression model based on the gradient boosting algorithm according to the battery type of the target lithium-ion battery, and input the real-time charging data during the charging process of the target lithium-ion battery into the trained regression model based on the gradient boosting algorithm to determine whether there is any abnormality in the charging time during the charging process of the target lithium-ion battery.

[0110] In this step, the trained regression model based on the gradient boosting algorithm is applied to the subsequent actual lithium-ion battery charging data to determine whether there is an abnormality in the charging time of the lithium-ion battery.

[0111] In summary, the embodiment of the present invention effectively improves the accuracy and speed of abnormal power judgment by applying the regression model to the charging power judgment of actual data. For batteries of different models, it is only necessary to distinguish the capacity of the battery without distinguishing the batch of the battery, etc., to judge the data, which greatly improves efficiency, reduces labor, and is conducive to large-scale production.

[0112] Corresponding to the above method embodiment, this specification also provides a system embodiment for determining abnormal charging time of a lithium-ion battery. Figure 2 A schematic diagram of a system for determining abnormal charging time of a lithium-ion battery according to an embodiment of the present specification is shown. Figure 2 As shown, the system includes:

[0113] An acquisition module 201 is used to acquire effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extract charging characteristic data of the effective charging cycle from the effective charging cycle data;

[0114] In the embodiment of the present invention, the acquisition module 201 is specifically used to determine the battery type of each lithium-ion battery; obtain the historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle; according to the charging conditions set for each battery type, the charging cycle data that meets the charging conditions are extracted from the historical charging cycle data set of each lithium-ion battery of each battery type, and the charging cycle data that meets the charging conditions is used as the valid charging cycle data.

[0115] A model building and training module 202 is used to build a regression model based on a gradient boosting algorithm for each battery type, and train the corresponding regression model based on the gradient boosting algorithm using the charging characteristic data of the effective charging cycle of each battery type to obtain a trained regression model based on the gradient boosting algorithm for each battery type;

[0116] The abnormality judgment module 203 is used to obtain the battery type of the target lithium electronic battery and the real-time charging data during the charging process, and obtain the corresponding trained regression model based on the gradient boosting algorithm according to the battery type of the target lithium electronic battery, and input the real-time charging data during the charging process of the target lithium electronic battery into the trained regression model based on the gradient boosting algorithm to judge whether there is an abnormality in the charging time during the charging process of the target lithium electronic battery.

[0117] The above is a schematic scheme of a system for judging abnormal charging time of a lithium-ion battery in this embodiment. It should be noted that the technical scheme of the system for judging abnormal charging time of a lithium-ion battery and the technical scheme of the method for judging abnormal charging time of a lithium-ion battery are of the same conception, and the details not described in detail in the technical scheme of the system for judging abnormal charging time of a lithium-ion battery can be referred to the description of the technical scheme of the method for judging abnormal charging time of a lithium-ion battery.

[0118] Figure 6 The block diagram of a computing device 400 according to one embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.

[0119] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0120] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0121] Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.

[0122] The processor 420 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for determining abnormal charging time of a lithium-ion battery.

[0123] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for determining abnormal charging time of a lithium-ion battery belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned method for determining abnormal charging time of a lithium-ion battery.

[0124] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for determining abnormal charging time of a lithium-ion battery.

[0125] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned method for judging abnormal charging time of a lithium-ion battery belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned method for judging abnormal charging time of a lithium-ion battery.

[0126] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for determining abnormal charging time of a lithium-ion battery.

[0127] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the method for judging abnormal charging time of a lithium-ion battery described above belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the method for judging abnormal charging time of a lithium-ion battery described above.

[0128] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0130] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for determining abnormal charging time of a lithium-ion battery, characterized in that: include: Acquire effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extract charging characteristic data of the effective charging cycle from the effective charging cycle data; Constructing a regression model based on a gradient boosting algorithm for each battery type, and using the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm, to obtain a trained regression model based on the gradient boosting algorithm for each battery type; The battery type of the target lithium electronic battery and the real-time charging data during the charging process are obtained, and according to the battery type of the target lithium electronic battery, a corresponding trained regression model based on the gradient boosting algorithm is obtained, and the real-time charging data during the charging process of the target lithium electronic battery is input into the trained regression model based on the gradient boosting algorithm to determine whether there is an abnormality in the charging time during the charging process of the target lithium electronic battery.

2. The method according to claim 1, characterized in that Obtaining valid charge cycle data for each lithium-ion cell of each battery type during the charging process includes: Determine the cell type of each lithium-ion cell; Obtaining historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle; According to the charging conditions set for each battery type, charging cycle data meeting the charging conditions are extracted from the historical charging cycle data set of each lithium-ion battery of each battery type, and the charging cycle data meeting the charging conditions are used as valid charging cycle data.

3. The method according to claim 2, characterized in that The charging conditions set for each battery type include at least: The starting SOC of each charging cycle in the historical charging cycle data is less than a first SOC threshold, and the ending SOC is greater than and a second SOC threshold; wherein the first SOC threshold is less than the second SOC threshold; According to the set collection time interval, the number of charging samples of each charging cycle in the historical charging cycle data is greater than the set sample threshold; The charging current of each charging cycle in the historical charging cycle data is greater than a set current threshold or the charging time is greater than a set charging time threshold.

4. The method according to claim 3, characterized in that The charging characteristic data of the effective charging cycle includes: Starting SOC, ending SOC, average current during charging time, average current of multiple segmented samples, initial charging temperature, maximum charging temperature, ending charging temperature, initial charging voltage, maximum voltage of segmented samples and ending charging voltage.

5. The method according to claim 4, characterized in that Using the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm, the trained regression model based on the gradient boosting algorithm for each battery type is obtained, including: Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, eliminating abnormal effective charging cycle data while retaining normal effective charging cycle data; The corresponding regression model based on the gradient boosting algorithm is retrained using the charging characteristic data of the normal effective charging cycle of each battery type to obtain a trained regression model based on the gradient boosting algorithm for each battery type.

6. The method according to claim 5, characterized in that The charging characteristic data of the effective charging cycle of each battery type is used to train its corresponding regression model based on the gradient boosting algorithm, and abnormal effective charging cycle data is eliminated, while retaining normal effective charging cycle data, including: Using the charging characteristic data of the effective charging cycle of each battery type to train its corresponding regression model based on the gradient boosting algorithm, and using the 2σ principle to obtain abnormal charging characteristic data and normal charging characteristic data; According to the abnormal charging characteristic data, effective charging cycle data corresponding to the abnormal charging characteristic data is obtained, and the effective charging cycle data is used as the abnormal effective charging cycle data; at the same time, according to the normal charging characteristic data, effective charging cycle data corresponding to the normal charging characteristic data is obtained, and the effective charging cycle data is used as the normal effective charging cycle data; The charging characteristic data of the abnormal effective charging cycle data is eliminated, while the charging characteristic data of the normal effective charging cycle data is retained.

7. A system for determining abnormal charging time of a lithium-ion battery, characterized in that: include: An acquisition module, used to acquire effective charging cycle data including charging time of each lithium-ion battery of each battery type during the charging process, and extract charging characteristic data of the effective charging cycle from the effective charging cycle data; A model building and training module is used to build a regression model based on the gradient boosting algorithm for each battery type, and use the charging characteristic data of the effective charging cycle of each battery type to train the corresponding regression model based on the gradient boosting algorithm to obtain a trained regression model based on the gradient boosting algorithm for each battery type; The abnormality judgment module is used to obtain the battery type of the target lithium electronic battery and the real-time charging data during the charging process, and obtain the corresponding trained regression model based on the gradient boosting algorithm according to the battery type of the target lithium electronic battery, and input the real-time charging data during the charging process of the target lithium electronic battery into the trained regression model based on the gradient boosting algorithm to judge whether there is an abnormality in the charging time during the charging process of the target lithium electronic battery.

8. The system according to claim 7, characterized in that The acquisition module is specifically used to determine the battery type of each lithium-ion battery; acquire the historical charging cycle data of each lithium-ion battery during the charging process; the historical charging cycle data at least includes the starting SOC, ending SOC, charging time, charging current, charging temperature and charging voltage of each charging cycle; according to the charging conditions set for each battery type, extract the charging cycle data that meets the charging conditions from the historical charging cycle data set of each lithium-ion battery of each battery type, and use the charging cycle data that meets the charging conditions as the effective charging cycle data.

9. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of a method for determining abnormal charging time of a lithium-ion battery as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method for determining abnormal charging time of a lithium-ion battery as claimed in any one of claims 1 to 6.

Images