Lithium precipitation detection method, electronic equipment, battery pack and energy storage product

Abstract

The embodiment of the invention provides a lithium precipitation detection method, which comprises the following steps: acquiring to-be-processed data of a target battery, the to-be-processed data comprising real state data of the target battery at a plurality of historical moments in a historical time period before the current moment in the current charging process, and the real state data comprising a total battery potential value and a charging current value; processing the to-be-processed data by using a pre-trained potential prediction model to obtain predicted cathode potential values of the target battery at a plurality of historical moments; the potential prediction model is constructed to be obtained by training on the basis of real state data and real specified potential values of a sample battery at multiple sample moments in a historical charging process, and the real specified potential values comprise a real positive potential value or a real negative potential value; and on the basis of the plurality of obtained predicted negative electrode potential values, whether lithium precipitation occurs in the target battery at a plurality of historical moments is judged, so that the accuracy of lithium precipitation detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of battery management, and particularly to a method for detecting lithium plating, an electronic device, a battery pack, and an energy storage product. Background Art

[0002] Due to advantages such as high energy density, long cycle life, and no memory effect, lithium-ion batteries are widely used in multiple fields such as new energy vehicles, light electric vehicles / tricycles, drones, and energy storage products. However, during the use of the battery, a side reaction of lithium plating may occur, resulting in a reduction in capacity. In severe cases, it may also cause faults such as internal short circuit and thermal runaway, thus affecting the personal safety of users.

[0003] Therefore, how to effectively detect whether lithium plating occurs in the battery and take corresponding measures in a timely manner has become a key issue in the industry. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method for detecting lithium plating, an electronic device, a battery pack, and an energy storage product. The specific technical solutions are as follows:

[0005] In the first aspect of the present application, a method for detecting lithium plating is provided. The method includes: obtaining data to be processed of a target battery; wherein, the data to be processed includes: during the current charging process, true state data of the target battery at multiple historical moments within a historical time period before the current moment, and the true state data includes: full battery potential value and charging current value; processing the data to be processed by using a pre-trained potential prediction model to obtain predicted negative electrode potential values of the target battery at the multiple historical moments; wherein, the potential prediction model is constructed by: being trained based on the true state data and true specified potential values of a sample battery at multiple sample moments during a historical charging process, and the true specified potential values include true positive electrode potential values or true negative electrode potential values; based on the obtained multiple predicted negative electrode potential values, determining whether lithium plating occurs in the target battery at the multiple historical moments.

[0006] Since there is a mapping relationship between the negative electrode potential value of the target battery at a historical moment and the true state data at the historical moment, therefore, the true state data at the historical moment is used to predict the negative electrode potential value at the historical moment. In addition, during the use of the target battery, the negative electrode potential value characterizes whether lithium plating occurs in the target battery. Therefore, multiple predicted negative electrode potential values at historical moments are used to determine whether lithium plating occurs in the target battery at the multiple historical moments, so as to improve the accuracy of lithium plating detection of the target battery.

[0007] In one or more embodiments of the present application, processing the data to be processed by using the pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at the multiple historical moments includes: inputting the data to be processed into the pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at the multiple historical moments; wherein, the true specified potential value includes the true negative electrode potential value; or, inputting the data to be processed into the pre-trained potential prediction model to obtain the predicted positive electrode potential values of the target battery at the multiple historical moments; wherein, the true specified potential value includes the true positive electrode potential value; combining the true full battery potential values of the target battery at the multiple historical moments and the predicted positive electrode potential values to calculate the predicted negative electrode potential values of the target battery at the multiple historical moments.

[0008] Using the potential prediction model to directly predict the negative electrode potential value of the target battery, or predicting the positive electrode potential value of the target battery and combining the full battery potential value to calculate the negative electrode potential value of the target battery, improves the accuracy of the obtained negative electrode potential value and further improves the accuracy of lithium plating detection of the target battery.

[0009] In one or more embodiments of the present application, determining whether lithium plating occurs in the target battery at the multiple historical moments based on the obtained multiple predicted negative electrode potential values includes: calculating the average value of the obtained multiple predicted negative electrode potential values; in response to the average value being greater than the preset threshold, determining that lithium plating does not occur in the target battery at the multiple historical moments; in response to the average value not being greater than the preset threshold, determining that lithium plating occurs in the target battery at the multiple historical moments.

[0010] The average value of the obtained multiple predicted negative electrode potential values accurately represents the negative electrode potential value within the historical time period. Correspondingly, using this average value to detect whether lithium plating will occur in the target battery at multiple historical moments improves the accuracy of the lithium plating detection result.

[0011] In one or more embodiments of the present application, the method further includes: in response to lithium plating occurring in the target battery at the multiple historical moments, using the predicted negative electrode potential values of the target battery at the multiple historical moments to calculate the lithium plating side reaction current of the target battery at the multiple historical moments; combining the lithium plating side reaction currents of the target battery at the multiple historical moments to calculate the total lithium plating amount of the target battery within the historical time period; calculating the product of the total lithium plating amount and the preset ratio to obtain the dead lithium precipitation amount of the target battery within the historical time period.

[0012] Using the predicted negative electrode potential value improves the accuracy of calculating the dead lithium precipitation amount of the target battery within the historical time period, providing a precise basis for the management of the target battery.

[0013] In one or more embodiments of the present application, the method further includes: in response to lithium plating occurring in the target battery at the plurality of historical moments, during the current charging process, changing the charging conditions, and continuing to charge the target battery according to the changed charging conditions; wherein the changing manner includes: reducing the charging rate and / or increasing the battery temperature; and / or, in response to lithium plating not occurring in the target battery at the plurality of historical moments, keeping the current charging conditions unchanged and continuing to charge the target battery; and / or, in response to lithium plating occurring in the target battery at the plurality of historical moments, during the next power supply or charging process, reducing the output power of the target battery, or reducing the charging rate and / or increasing the battery temperature.

[0014] After determining that lithium plating occurs in the target battery during the historical time period, the current charging conditions are further adjusted, and the target battery is controlled to be charged according to the adjusted charging conditions, further reducing the risk of lithium plating occurring in the target battery during the entire charging process. In addition, after determining that lithium plating does not occur in the target battery during the historical time period, the current charging conditions are kept unchanged, and the target battery continues to be charged while completing the charging process of the target battery as soon as possible. If lithium plating occurs in the target battery at a plurality of historical moments, during the next power supply process, the output power of the target battery is reduced to mitigate the impact brought by lithium plating and improve the usage safety of the target battery.

[0015] In one or more embodiments of the present application, the potential prediction model includes at least one of the following: convolutional neural network, densely connected network, recurrent neural network, long short-term memory neural network, model with attention mechanism, and Transformer network.

[0016] Based on the above network, the accuracy of predicting the negative electrode potential value is further improved to improve the accuracy of the lithium plating detection result.

[0017] In one or more embodiments of the present application, the true state data further includes: battery temperature; and / or, the data to be processed further includes: the simulated potential values of the target battery at the plurality of historical moments, and the simulated potential values at the plurality of historical moments are calculated by using a pre-constructed first electrochemical mechanism model of the target battery, and the simulated potential values at the plurality of historical moments include at least one of the following: simulated full battery potential value, simulated positive electrode potential value, and simulated negative electrode potential value; the potential prediction model is constructed by: being trained based on the true state data, simulated potential values, and true specified potential values of the sample battery at a plurality of sample moments during the historical charging process; the simulated potential values at the plurality of sample moments are calculated by using a pre-constructed second electrochemical mechanism model of the sample battery.

[0018] Since the negative electrode potential value of the target battery is affected by temperature, the negative electrode potential value at a historical moment is predicted in combination with the battery temperature, further improving the accuracy of predicting the negative electrode potential value. Since the first electrochemical mechanism model predicts the true potential value of the target battery at a historical moment, the accuracy of predicting the negative electrode potential value is further improved by combining the simulated potential value obtained from the first electrochemical mechanism model, so as to improve the accuracy of the lithium plating detection result.

[0019] In one or more embodiments of the present application, the first electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model; and / or, the second electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model.

[0020] Based on the above electrochemical model, the accuracy of the obtained simulated potential value is improved, so as to further improve the accuracy of predicting the negative electrode potential value and improve the accuracy of the lithium plating detection result.

[0021] In one or more embodiments of the present application, the obtaining of the data to be processed of the target battery includes: when any one of a plurality of preset detection moments is reached, obtaining the data to be processed of the target battery; wherein, the detection interval between every two adjacent detection moments is the same as the duration of the historical time period.

[0022] At each time when the detection moment is reached, it is detected whether lithium plating occurs in the target battery during the historical time period before the detection moment, that is, it is detected whether lithium plating occurs between the previous detection moment and the current detection moment of the target battery. In this way, it is determined in real time whether lithium plating has occurred in the most recent period according to the latest state of the target battery, improving the real-time performance of the detection.

[0023] A second aspect of the present application provides a lithium plating detection device, the device includes: a data to be processed acquisition module configured to acquire the data to be processed of the target battery; wherein, the data to be processed includes: during the current charging process, the true state data of the target battery at a plurality of historical moments within the historical time period before the current moment, and the true state data includes: the full battery potential value and the charging current value; a prediction module configured to process the data to be processed by using a pre-trained potential prediction model to obtain the predicted negative electrode potential value of the target battery at the plurality of historical moments; wherein, the potential prediction model is constructed by: training based on the true state data and the true specified potential value of the sample battery at a plurality of sample moments during the historical charging process, and the true specified potential value includes the true positive electrode potential value or the true negative electrode potential value; a judgment module configured to judge whether lithium plating occurs in the target battery at the plurality of historical moments based on the obtained plurality of predicted negative electrode potential values.

[0024] Since there is a mapping relationship between the negative electrode potential value of the target battery at a historical moment and the real state data at the historical moment, the negative electrode potential value at the historical moment is predicted using the real state data at the historical moment. Additionally, during the use of the target battery, the negative electrode potential value indicates whether lithium plating occurs in the target battery. Therefore, the predicted negative electrode potential values at multiple historical moments are used to determine whether lithium plating occurs in the target battery at multiple historical moments, so as to improve the accuracy of lithium plating detection for the target battery.

[0025] In one or more embodiments of the present application, the prediction module is configured to input the data to be processed into a pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at the multiple historical moments; wherein, the real specified potential value includes the real negative electrode potential value; or, input the data to be processed into a pre-trained potential prediction model to obtain the predicted positive electrode potential values of the target battery at the multiple historical moments; wherein, the real specified potential value includes the real positive electrode potential value; and combine the real full battery potential values of the target battery at the multiple historical moments and the predicted positive electrode potential values to calculate the predicted negative electrode potential values of the target battery at the multiple historical moments.

[0026] Directly predicting the negative electrode potential value of the target battery using the potential prediction model, or predicting the positive electrode potential value of the target battery and combining the full battery potential value to calculate the negative electrode potential value of the target battery, improves the accuracy of the obtained negative electrode potential value, and further improves the accuracy of lithium plating detection for the target battery.

[0027] In one or more embodiments of the present application, the judgment module is configured to calculate the average value of the multiple predicted negative electrode potential values obtained; in response to the average value being greater than a preset threshold, determine that the target battery does not have lithium plating at the multiple historical moments; in response to the average value not being greater than the preset threshold, determine that the target battery has lithium plating at the multiple historical moments.

[0028] The average value of the multiple predicted negative electrode potential values obtained accurately represents the negative electrode potential value within the historical time period. Correspondingly, this average value is used to detect whether lithium plating will occur in the target battery at multiple historical moments, so as to improve the accuracy of the lithium plating detection result.

[0029] In one or more embodiments of the present application, the device further includes: a dead lithium precipitation amount calculation module configured to, in response to lithium precipitation occurring in the target battery at the plurality of historical moments, calculate the lithium precipitation side reaction current of the target battery at the plurality of historical moments by using the predicted negative electrode potential values of the target battery at the plurality of historical moments; calculate the total lithium precipitation amount of the target battery within the historical time period in combination with the lithium precipitation side reaction current of the target battery at the plurality of historical moments; and calculate the product of the total lithium precipitation amount and a preset ratio to obtain the dead lithium precipitation amount of the target battery within the historical time period.

[0030] By using the predicted negative electrode potential values, the accuracy of calculating the dead lithium precipitation amount of the target battery within the historical time period is improved, providing a precise basis for the management of the target battery.

[0031] In one or more embodiments of the present application, the device further includes: a control module configured to, in response to lithium precipitation occurring in the target battery at the plurality of historical moments, change the charging conditions during the current charging process and continue to charge the target battery according to the changed charging conditions; wherein the changing method includes: reducing the charging rate and / or increasing the battery temperature; and / or, in response to no lithium precipitation occurring in the target battery at the plurality of historical moments, keeping the current charging conditions unchanged and continuing to charge the target battery; and / or, in response to lithium precipitation occurring in the target battery at the plurality of historical moments, reducing the output power of the target battery or reducing the charging rate and / or increasing the battery temperature during the next power supply or charging process.

[0032] After determining that lithium precipitation occurs in the target battery within the historical time period, the current charging conditions are adjusted accordingly, and the target battery is controlled to be charged according to the adjusted charging conditions, further reducing the risk of lithium precipitation occurring in the target battery during the entire charging process. Additionally, after determining that no lithium precipitation occurs in the target battery within the historical time period, the current charging conditions are kept unchanged and the target battery continues to be charged, while completing the charging process of the target battery as soon as possible. If lithium precipitation occurs in the target battery at multiple historical moments, during the next power supply process, the output power of the target battery is reduced, for example, the discharge current of the target battery is reduced, to mitigate the impact brought by lithium precipitation and improve the use safety of the target battery.

[0033] In one or more embodiments of the present application, the potential prediction model includes at least one of the following: a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory neural network, a model with an attention mechanism, and a Transformer network.

[0034] Based on the above networks, the accuracy of predicting the negative electrode potential value is further improved to enhance the accuracy of the lithium precipitation detection result.

[0035] In one or more embodiments of the present application, the real state data further includes: battery temperature; and / or, the data to be processed further includes: the simulated potential values of the target battery at the multiple historical moments, and the simulated potential values at the multiple historical moments are calculated by using the pre-constructed first electrochemical mechanism model of the target battery, and the simulated potential values at the multiple historical moments include at least one of the following: simulated full-cell potential value, simulated cathode potential value, and simulated anode potential value; the potential prediction model is constructed by training based on the real state data, simulated potential values, and real specified potential values of the sample battery at multiple sample moments during the historical charging process; the simulated potential values at the multiple sample moments are calculated by using the pre-constructed second electrochemical mechanism model of the sample battery.

[0036] Since the anode potential value of the target battery is affected by temperature, therefore, by combining the battery temperature to predict the anode potential value at the historical moment, the accuracy of predicting the anode potential value is further improved. Since the first electrochemical mechanism model predicts the real potential value of the target battery at the historical moment, therefore, by combining the simulated potential values obtained from the first electrochemical mechanism model, the accuracy of predicting the anode potential value is further improved to improve the accuracy of the lithium plating detection result.

[0037] In one or more embodiments of the present application, the first electrochemical mechanism model is: a single-particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model; and / or, the second electrochemical mechanism model is: a single-particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model.

[0038] Based on the above electrochemical model, the accuracy of the obtained simulated potential values is improved, so as to further improve the accuracy of predicting the anode potential value and improve the accuracy of the lithium plating detection result.

[0039] In one or more embodiments of the present application, the data acquisition module to be processed is configured to acquire the data to be processed of the target battery when any one of the preset multiple detection moments is reached; wherein, the detection interval between every two adjacent detection moments is the same as the duration of the historical time period.

[0040] At each time when the detection moment is reached, it is detected whether lithium plating occurs in the target battery during the historical time period before this detection moment, that is, whether lithium plating occurs in the target battery between the previous detection moment and the current detection moment. In this way, it is determined in real time whether lithium plating has occurred in the most recent period according to the latest state of the target battery, improving the real-time performance of the detection.

[0041] The third aspect of the present application provides an electronic device configured to execute the method according to any one of the first aspects above.

[0042] A fourth aspect of the present application provides a battery pack, which includes a battery module and the electronic device described in the third aspect above.

[0043] A fifth aspect of the present application provides an energy storage product, which includes a battery module and the electronic device described in the third aspect above.

[0044] A sixth aspect of the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0045] A seventh aspect of the present application provides a computer program product containing instructions, which, when running on a computer, causes the computer to execute the method described in any one of the first aspects above.

[0046] Beneficial effects of the embodiments of the present application:

[0047] The lithium plating detection method provided by the embodiments of the present application obtains the data to be processed of the target battery; the data to be processed includes: during the current charging process, the true state data of the target battery at multiple historical moments within the historical time period before the current moment, and the true state data includes: the full battery potential value and the charging current value; then, the data to be processed is processed by using a pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at multiple historical moments; the potential prediction model is constructed as: trained based on the true state data and the true specified potential value of the sample battery at multiple sample moments during the historical charging process, and the true specified potential value is the true positive electrode potential value, or the true negative electrode potential value; furthermore, based on the obtained multiple predicted negative electrode potential values, it is determined whether lithium plating occurs in the target battery at multiple historical moments.

[0048] Since there is a mapping relationship between the negative electrode potential value of the target battery at the historical moment and the true state data at the historical moment, the negative electrode potential value at the historical moment is predicted by using the true state data at the historical moment. In addition, during the use of the target battery, the negative electrode potential value indicates whether lithium plating occurs in the target battery. Therefore, the predicted negative electrode potential values at multiple historical moments are used to determine whether lithium plating occurs in the target battery at multiple historical moments, so as to improve the accuracy of lithium plating detection of the target battery. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other embodiments based on these drawings.

[0050] Figure 1 Flow chart of a lithium plating detection method provided by an embodiment of the present application;

[0051] Figure 2A Schematic diagram of the true negative electrode potential value of a battery (referred to as a battery to be utilized) provided by an embodiment of the present application;

[0052] Figure 2B Schematic diagram of the predicted negative electrode potential value of a battery to be utilized obtained by using a trained potential prediction model provided by an embodiment of the present application;

[0053] Figure 3 Flow chart of another lithium plating detection method provided by an embodiment of the present application;

[0054] Figure 4 Flow chart of another lithium plating detection method provided by an embodiment of the present application;

[0055] Figure 5 Structure diagram of a lithium plating detection device provided by an embodiment of the present application. Detailed implementation manners

[0056] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art based on the present application belong to the scope of protection of the present application.

[0057] Lithium plating in a lithium battery means that during the charging process of the battery, lithium ions are deposited on the surface of the negative electrode to form metallic lithium, and lithium plating occurs under low battery temperature or other improper charging conditions. Lithium plating will cause lithium dendrites to form inside the battery, which may pierce the diaphragm and cause an internal short circuit, and even trigger thermal runaway and safety accidents. In addition, lithium plating will also reduce the number of lithium ions, resulting in battery capacity attenuation and shortening the battery life.

[0058] In order to improve the accuracy of lithium plating detection in a battery, an embodiment of the present application provides a lithium plating detection method, an electronic device, a battery pack, an energy storage product, a device, an equipment and a medium.

[0059] Next, first, the lithium plating detection method provided by the embodiments of the present application will be introduced. In some embodiments of the present application, this method is applied to an electronic device that provides computing services. For example, the electronic device is a battery management system (BMS) of a battery pack, or an energy management system (EMS) of an energy storage product, or a server, including a local server and a cloud server. It can be understood that a battery pack is a product that includes a battery module and a battery management system electrically connected to the battery module, and the battery module includes at least one battery. When the battery module includes multiple batteries, the electrical connection methods between the batteries include: series connection, parallel connection, or hybrid connection. In the present application, hybrid connection means that the electrical connection between the batteries includes series connection and parallel connection.

[0060] As Figure 1 shown, the embodiments of the present application provide a flowchart of a lithium plating detection method, and this method includes the following steps:

[0061] S101: Obtain the data to be processed of the target battery.

[0062] The data to be processed includes: during the current charging process, the true state data of the target battery at multiple historical moments within the historical time period before the current moment. The true state data includes: the full-cell potential value and the charging current value.

[0063] In some embodiments of the present application, the full-cell potential value of the battery represents the potential value of the positive electrode of the battery relative to the negative electrode, the positive electrode potential value represents the potential value of the positive electrode of the battery relative to the reference electrode, and the negative electrode potential value represents the potential value of the negative electrode of the battery relative to the reference electrode.

[0064] It can be understood that the target battery is the battery currently being charged, and the electronic device detects the target battery based on the lithium plating detection method provided by the embodiments of the present application to determine whether lithium plating occurs during the charging process. At this time, the electronic device is the battery management system in the battery pack containing the target battery, or the energy management system in the energy storage product containing the target battery.

[0065] During a complete charging process, the electronic device executes step S101 - S103 one or more times. After obtaining the true state data, the electronic device determines whether the target battery has lithium plating based on the lithium plating detection method provided by the embodiments of the present application. In the present application, the time duration between every two moments of obtaining the true state data is defined as the detection interval. As a specific example of the present application, in some actual usage scenarios, the electronic device detects periodically at a fixed detection interval.

[0066] In some embodiments, the multiple historical moments in step S101 are obtained by uniformly sampling the moments within a historical time period before the current moment. The time duration between every two adjacent historical moments is the same, and the duration can be 1 second, 10 seconds, 100 seconds, 1000 seconds, etc. This application does not make specific limitations on this duration.

[0067] The number of these multiple historical moments is consistent with the number of sample moments used to train the potential prediction model in step S102. Correspondingly, the time duration between every two adjacent sample moments is the same, and this duration is consistent with the time duration between two adjacent historical moments. In this way, when predicting the negative electrode potential value of the target battery, the data input into the potential prediction model is consistent with the acquisition method of the input data during the training of the potential prediction model, improving the accuracy of predicting the negative electrode potential value of the target battery using the potential prediction model.

[0068] S102: Use the pre-trained potential prediction model to process the data to be processed, and obtain the predicted negative electrode potential values of the target battery at multiple historical moments.

[0069] The potential prediction model is constructed by training based on the true state data of the sample battery at multiple sample moments during the historical charging process and the true specified potential values at multiple sample moments. The true specified potential values include the true positive electrode potential value, or include the true negative electrode potential value. The potential prediction model reflects the mapping relationship between the state data of the battery at historical moments and the true specified potential values, and is used to predict the negative electrode potential value of the target battery at historical moments.

[0070] In order to further improve the robustness of the potential prediction model to adapt to the state and working environment of the battery, in one or more embodiments of this application, the true state data of the sample battery at the sample moments and the true specified potential values at the sample moments in multiple different application scenarios are obtained. The state and working environment of the battery include: battery aging state, environmental temperature, environmental humidity, charging scheme, irradiation, etc., to obtain multiple application scenarios. The charging scheme includes constant current charging, constant current constant voltage charging, multi-stage constant current charging, and pulse charging, etc.

[0071] In order to continuously detect whether lithium plating occurs in the target battery during a complete charging process, the duration of the above historical time period is the same as the duration of the above detection interval. In one or more embodiments of the present application, when any detection moment among a plurality of preset detection moments is reached, the electronic device acquires the data to be processed of the target battery and executes according to steps S101 - S103. At each detection moment, it is detected whether lithium plating occurs in the target battery within the historical time period before this moment, that is, it is detected whether lithium plating occurs in the target battery between the previous detection moment and the current detection moment. In this way, it is determined in real time whether lithium plating has occurred in the most recent period according to the latest state of the target battery, improving the real-time performance of the detection.

[0072] Exemplarily, during the charging process of the target battery, the duration of the historical time period is 1 minute, and the true state data of the target battery is collected once every second. That is, a plurality of historical moments are the moments corresponding to each second within the previous minute of the current moment. Correspondingly, the number of historical moments is 60, and it is detected whether lithium plating occurs in the target battery within the previous minute of the current moment each time.

[0073] That is, according to the above example, if the detection interval is 1 minute, during the charging process of the target battery, when the charging duration reaches one minute, the potential prediction model is used to process the true state data of the target battery for each second within the first minute to obtain the predicted negative electrode potential value within the first minute. Then, it is determined whether lithium plating occurs in the target battery within the first minute according to step S103.

[0074] Correspondingly, when the charging duration reaches two minutes, the potential prediction model is used to process the true state data of the target battery for each second within the second minute to obtain the predicted negative electrode potential value within the second minute. Then, it is determined whether lithium plating occurs in the target battery within the second minute according to step S103.

[0075] And so on until the charging process of the target battery ends. For example, the target battery is charged to a fully charged state, or the charging process is interrupted.

[0076] It can be understood that since the above detection method uses the true state data of the battery during charging, and this true state data is obtained through the battery management system or the energy management system, lithium plating detection of the battery is realized in real time without disassembling the battery pack, achieving non-destructive detection. The lithium plating detection method of the embodiments of the present application realizes online, real-time, and non-destructive two-electrode battery lithium plating diagnosis. And due to real-time detection, manufacturers can select different time periods for detection in different scenarios according to actual needs, adapting to rapid lithium plating detection and regular inspections.

[0077] S103: Based on the obtained multiple predicted negative electrode potential values, determine whether lithium plating occurs in the target battery at multiple historical moments.

[0078] In some embodiments of the present application, the negative electrode potential value is used to characterize whether lithium plating occurs in the target battery. The true state data at multiple historical moments are used to predict the negative electrode potential value, and it is determined whether lithium plating occurs in the target battery at multiple historical moments.

[0079] Since there are multiple predicted negative electrode potential values at multiple historical moments, in some embodiments of the present application, the average value of the multiple predicted negative electrode potential values is calculated, and according to the magnitude relationship between the average value and a preset threshold, it is determined whether lithium plating occurs in the target battery at multiple historical moments. For example, if the average value is greater than the preset threshold, it is determined that lithium plating does not occur in the target battery at multiple historical moments; if the average value is not greater than the preset threshold, it is determined that lithium plating occurs in the target battery at multiple historical moments. As some examples of the present application, the preset threshold is 0V, or, in order to improve the fault tolerance rate of detection, the preset threshold is set to other values near 0V. For example, the preset threshold is 0.01V, 0.03V, 0.05V, or 0.1V. In this way, by setting the preset threshold and comparing the predicted negative electrode potential with the preset threshold, real-time, online, and non-destructive lithium plating detection is achieved, improving the safety and reliability of lithium-ion batteries and helping to reduce the risk of internal short circuit and thermal runaway in the early stage of the battery.

[0080] The average value of the obtained multiple predicted negative electrode potential values more accurately characterizes the negative electrode potential value within the historical time period. Correspondingly, using this average value to detect whether lithium plating will occur in the target battery at multiple historical moments improves the accuracy of the lithium plating detection result.

[0081] In some embodiments of the present application, the maximum value and the minimum value among the multiple predicted negative electrode potential values are removed, and the average value of the remaining predicted negative electrode potential values is calculated to obtain the above-mentioned average value.

[0082] Since lithium plating will cause the reduction of the thermal stability boundary of the battery, and the thermal stability boundary reflects the safe temperature boundary during the use of the battery. Therefore, in one or more embodiments of the present application, after it is determined that lithium plating occurs in the target battery at multiple historical moments, the output power of the target battery is reduced. For example, the discharge current of the target battery is reduced so that the temperature of the target battery during operation is lower than the above-mentioned safe temperature boundary to slow down the impact of lithium plating and improve the use safety of the target battery.

[0083] In one or more embodiments of the present application, after it is determined that lithium plating occurs in the target battery at multiple historical moments, during the current charging process, the charging conditions are changed, and the target battery is charged continuously according to the changed charging conditions. The adjustment methods include: reducing the charging rate and / or increasing the battery temperature.

[0084] In some embodiments of the present application, the battery temperature is characterized by the ambient temperature. The ambient temperature is increased, and the battery temperature is increased by heat transfer to reduce the degree of lithium plating of the target battery subsequently. It can be understood that in some other embodiments of the present application, the battery temperature is characterized by the battery's own temperature.

[0085] In some embodiments of the present application, an electrical device (such as an energy storage product, an electric vehicle) includes a heating component for heating the battery. In these electrical devices, the battery is heated by the heating component to increase the battery temperature, so as to reduce the degree of lithium plating of the target battery subsequently.

[0086] In addition, the degree of lithium plating of the target battery subsequently is reduced by reducing the charging rate. Therefore, when it is determined that the target battery has lithium plated at multiple historical moments, the charging conditions are adjusted by reducing the charging rate and / or increasing the battery temperature, thereby reducing the degree of lithium plating of the target battery subsequently.

[0087] In one or more embodiments of the present application, if it is determined that the target battery has not lithium plated at multiple historical moments, the current charging conditions are maintained, and the target battery continues to be charged.

[0088] It can be understood that the initial charging rate of the target battery is set according to actual requirements. In one or more embodiments of the present application, during a charging process, according to the above processing, multiple operations of reducing the charging rate may be performed. Therefore, in some embodiments, the target battery starts charging at the maximum charging rate to shorten the charging time of the target battery. At the same time, combined with the lithium plating detection method of the present application, the charging conditions are adjusted to reduce the risk of lithium plating of the target battery.

[0089] It can be understood that for electrical devices without a battery temperature control component, such as headphones, mobile phones, tablet computers, etc., the charging conditions are adjusted by reducing the charging rate; for some electrical devices with a battery temperature control component, such as energy storage products, electric vehicles, the battery temperature is increased by the battery temperature control component to adjust the charging conditions, or the charging conditions are adjusted by reducing the charging rate, or the charging conditions are adjusted by increasing the battery temperature and reducing the charging rate.

[0090] In some implementation manners, the charging rate is reduced according to a preset gradient. For example, the charging rate is reduced to 95%, 90%, 85%, or 80% of the current charging rate. In some other implementation manners, the battery temperature is increased according to a preset gradient. For example, the battery temperature is increased to 150%, 200%, or 250% of the current battery temperature.

[0091] In some other implementation manners, the preset charging rate is decreased based on the current charging rate. For example, the charging rate is decreased by 0.2C, 0.5C or 1C. In still some other implementation manners, the preset temperature is increased based on the current battery temperature. For example, the battery temperature is increased by 5°C, 8°C, 10°C, 15°C or 20°C.

[0092] For the above step S102, in some embodiments of the present application, it is implemented by one of the following methods:

[0093] Method 1: Predict the negative electrode potential values of the target battery at multiple historical moments to obtain the predicted negative electrode potential values of the target battery at multiple historical moments. That is, the output data of the potential prediction model represents the negative electrode potential values.

[0094] In this method, the potential prediction model is constructed by training based on the true state data of the sample battery at multiple sample moments and the true negative electrode potential values at multiple sample moments during the historical charging process.

[0095] Input the true state data of the sample battery at multiple sample moments into the potential prediction model with an initial structure to obtain the predicted negative electrode potential values of the sample battery at multiple sample moments. Furthermore, based on the difference between the obtained predicted negative electrode potential values and the true negative electrode potential values of the sample battery at multiple sample moments, calculate the loss value, and adjust the model parameters of the potential prediction model with the initial structure based on the loss value until the convergence condition is reached to obtain the trained potential prediction model.

[0096] See Figure 2A and Figure 2B , Figure 2A which is a schematic diagram of the true negative electrode potential value of a battery (referred to as the battery to be utilized) provided by an embodiment of the present application. Figure 2B is a schematic diagram of the predicted negative electrode potential value of the battery to be utilized obtained by using the trained potential prediction model. Figure 2A and Figure 2B In Figure 2A and Figure 2B , the abscissa represents the charging duration, with the unit of second (s), and the ordinate represents the negative electrode potential value, with the unit of volt (V). It can be seen from

[0097] that the difference between the predicted negative electrode potential value and the true negative electrode potential value of the potential prediction model provided by the embodiment of the present application is small, and the accuracy of the negative electrode potential value predicted by the potential prediction model is high. Method 2: Predict the positive electrode potential values of the target battery at multiple historical moments to obtain the predicted positive electrode potential values of the target battery at multiple historical moments. Then, combine the true full battery potential values of the target battery at multiple historical moments to calculate the predicted negative electrode potential values of the target battery at multiple historical moments. That is, the output data of the potential prediction model represents the positive electrode potential values.

[0098] For example, the difference between the predicted positive electrode potential value at each historical moment and the true full cell potential value at that historical moment is calculated to obtain the predicted negative electrode potential value at that historical moment.

[0099] In this method, the potential prediction model is constructed by training based on the true state data of the sample battery at multiple sample moments and the true positive electrode potential values at multiple sample moments during the historical charging process.

[0100] The true state data of the sample battery at multiple sample moments is input into the potential prediction model with an initial structure to obtain the predicted positive electrode potential values of the sample battery at multiple sample moments. Furthermore, based on the difference between the obtained predicted positive electrode potential values and the true positive electrode potential values of the sample battery at multiple sample moments, a loss value is calculated, and the model parameters of the potential prediction model with the initial structure are adjusted based on the loss value until the convergence condition is reached, and a trained potential prediction model is obtained.

[0101] Regarding the above step S102, in one or more embodiments of the present application, the full cell potential values and charging current values of the target battery at multiple historical moments are input into a pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at multiple historical moments.

[0102] In one or more embodiments of the present application, in addition to using the full cell potential values and charging current values of the target battery at multiple historical moments, other information is combined to predict the negative electrode potential values of the target battery at multiple historical moments to further improve the accuracy of the predicted negative electrode potential values.

[0103] In some embodiments of the present application, the true state data of the target battery at each historical moment further includes: the temperature of the target battery at that historical moment. Since the negative electrode potential value of the target battery is affected by temperature, therefore, the temperature of the target battery is combined to predict the negative electrode potential value at the historical moment, further improving the accuracy of the predicted negative electrode potential value. It can be understood that the temperature of the sample battery at multiple sample moments is also used when training the potential prediction model.

[0104] and / or

[0105] Using a pre - constructed electrochemical mechanism model of the target battery (referred to as the first electrochemical mechanism model), calculate the simulated potential values of the target battery at multiple historical moments. The simulated potential values include at least one of the following: simulated full - cell potential value, simulated cathode potential value, and simulated anode potential value. Input the real - state data of the target battery at multiple historical moments and the calculated simulated potential values at multiple historical moments into a pre - trained potential prediction model to calculate the predicted anode potential values of the target battery at multiple historical moments. That is, the data to be processed for the target battery also includes the simulated potential values of the target battery at multiple historical moments.

[0106] The electrochemical mechanism model is understood as a simulation model of the battery. Technicians construct a corresponding electrochemical mechanism model (i.e., the first electrochemical mechanism model) according to the specification parameters such as the size and material of the target battery. In some embodiments of the present application, after constructing the first electrochemical mechanism model, input the current voltage, remaining charge, and current charging conditions of the target battery into the first electrochemical mechanism model for simulation calculation to obtain the potential values of the target battery at historical moments (i.e., simulated potential values).

[0107] Since the first electrochemical mechanism model predicts the potential values of the target battery at historical moments, therefore, combining the simulated potential values obtained from the first electrochemical mechanism model further improves the accuracy of predicting the anode potential values. It can be understood that when training the potential prediction model, the simulated potential values of the sample battery at multiple sample moments are also used.

[0108] In some embodiments of the present application, based on the real - state data, real potential values, and simulated potential values of the sample battery at multiple sample moments during the historical charging process, a potential prediction model is trained. Input the real - state data and simulated potential values of the sample battery at multiple sample moments into the potential prediction model with an initial structure to obtain the predicted potential values of the sample battery at multiple sample moments. Furthermore, based on the difference between the obtained predicted potential values and the real specified potential values of the sample battery at multiple sample moments, calculate the loss value, and adjust the model parameters of the potential prediction model with the initial structure based on the loss value until the convergence condition is reached to obtain the trained potential prediction model.

[0109] The simulated potential values of the sample battery are calculated using the electrochemical mechanism model of the sample battery (referred to as the second electrochemical mechanism model). Technicians construct the corresponding electrochemical mechanism model (i.e., the second electrochemical mechanism model) according to the specification parameters such as the size and material of the sample battery. The calculation method of the simulated potential values of the sample battery at multiple sample times refers to the relevant introduction of calculating the simulated potential values of the target battery at historical times in the above embodiments. The types of the simulated potential values of the sample battery at multiple sample times are the same as those of the target battery at multiple historical times. That is, if the simulated potential values of the sample battery at multiple sample times include the simulated full-cell potential value, then the simulated potential values of the target battery at multiple historical times also include the simulated full-cell potential value; if the simulated potential values of the sample battery at multiple sample times include the simulated negative electrode potential value, then the simulated potential values of the target battery at multiple historical times also include the simulated negative electrode potential value; if the simulated potential values of the sample battery at multiple sample times include the simulated positive electrode potential value, then the simulated potential values of the target battery at multiple historical times also include the simulated positive electrode potential value.

[0110] In an actual scenario, the specifications of the target battery and the sample battery are the same. Correspondingly, the second electrochemical mechanism model and the first electrochemical mechanism model are the same electrochemical mechanism model. Technicians match the target battery, select the same positive electrode material, negative electrode material, electrolyte, separator and other materials as the target battery, and use the same process to assemble a three-electrode battery, which is the sample battery.

[0111] Similarly, in order to further improve the robustness of the potential prediction model to adapt to the state and working environment of the battery, the true negative electrode potential values of the sample battery at the sample time under a variety of different application scenarios are obtained, and the simulated potential values of the sample battery under these different application scenarios are calculated using the second electrochemical mechanism model to train the potential prediction model with the initial structure. The state and working environment of the battery include: battery aging state, ambient temperature, ambient humidity, charging scheme, irradiation, etc., to obtain a variety of different application scenarios. The charging scheme includes constant current charging, constant current constant voltage charging, multi-stage constant current charging, pulse charging, etc.

[0112] In one or more embodiments of the present application, the potential prediction model mentioned above is a model based on a deep learning algorithm. For example, the above potential prediction model includes one or more of a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory neural network, a model with an attention mechanism, or a Transformer, etc.

[0113] A mapping relationship is established between the simulated potential values of the two-electrode full-cell potential value, current, temperature, and electrochemical mechanism model, and the true positive electrode potential value and true negative electrode potential value through a deep learning algorithm model, so as to detect the lithium plating situation of the battery.

[0114] In one or more embodiments of the present application, the aforementioned first electrochemical mechanism model and second electrochemical mechanism model are electrochemical mechanism models including the lithium plating side reaction and the thermal field model. For example, they are single-particle models, quasi-two-dimensional models, or multi-dimensional multi-field electrochemical models, etc.

[0115] In one or more embodiments of the present application, for a target battery that has been in use in an actual scenario, after it has been used for a period of time, it is regarded as a sample battery, and relevant data is collected in the manner described in the above embodiments, and the aforementioned potential prediction model is incrementally trained based on the collected data. In this way, using the battery data under real working conditions, the models in the present application are updated to continuously improve the accuracy of model prediction.

[0116] In one or more embodiments of the present application, after determining that lithium plating occurs in a target battery at multiple historical moments, the amount of dead lithium precipitation at multiple historical moments is further determined.

[0117] After obtaining the predicted negative electrode potential value at each historical moment, the lithium plating side reaction current density is calculated through the Butler-Volmer equation or the Tafel formula. The Butler-Volmer equation is shown as the following formula:

[0118]

[0119] j is the lithium plating side reaction current density, k0 is the reaction rate constant, c e is the electrolyte concentration, F is the Faraday constant, α is the negative electrode transfer coefficient, R is the gas constant, T is the battery temperature, and η is the negative electrode potential value.

[0120] After calculating the lithium plating side reaction current density at each historical moment, the lithium plating side reaction current at each historical moment is calculated through the following formula.

[0121]

[0122] i is the lithium plating side reaction current, r is the radius of the negative electrode particle, L is twice the length of the negative electrode plate, W is the width of the negative electrode plate, D is the thickness of the negative electrode plate, and epss is the negative electrode solid phase porosity.

[0123] Combining the lithium plating side reaction currents at each historical moment, the total lithium plating amount within the historical time period is obtained through the ampere-hour integration method.

[0124]

[0125] A and B are respectively the starting time point and the ending time point of the historical time period, and Q loss is the total lithium plating amount caused by the lithium plating side reaction.

[0126] The total amount of lithium deposition includes the reversible lithium deposition amount and the dead lithium deposition amount. Reversible lithium will re-embed into the battery during charge and discharge processes, without causing battery capacity loss. Dead lithium, however, is difficult to participate in the reaction again, resulting in battery capacity loss and affecting battery life. In addition, dendrite-like dead lithium formed under some working conditions will pierce the separator, causing internal short-circuit faults and even thermal runaway faults.

[0127] After calculating the total amount of lithium deposition, obtain the ratio of the pre-determined dead lithium deposition amount in the total amount of lithium deposition. Furthermore, calculate the product of the total amount of lithium deposition and this ratio to obtain the dead lithium deposition amount.

[0128] Pre-obtain batteries under various different working conditions such as different ambient temperatures, charge-discharge rates, different aging conditions, different ambient humidities, etc., and after disassembling them, determine the dead lithium deposition amount within a certain period under different working conditions through techniques such as mass spectrometry titration and nuclear magnetic resonance. In addition, for each working condition, calculate the total amount of lithium deposition within the same period under this working condition according to the above method of calculating the total amount of lithium deposition. Furthermore, calculate the ratio of the dead lithium deposition amount to the total amount of lithium deposition under the same working condition.

[0129] It can be understood that after obtaining the total amount of lithium deposition of the target battery, obtain the ratio under the working condition of the target battery, and calculate the product of this ratio and the total amount of lithium deposition of the target battery to obtain the dead lithium deposition amount of the target battery. The following formula:

[0130]

[0131] Q l0ss2 represents the dead lithium deposition amount, and β is the ratio of the dead lithium deposition amount in the total amount of lithium deposition.

[0132] Based on the above processing, through the calculation of the dead lithium deposition amount and combined with the prediction of the negative electrode potential value, online, in-situ, and non-destructive lithium deposition detection and dead lithium quantification are realized.

[0133] See Figure 3 , Figure 3 which is a flowchart of a lithium deposition detection method provided by an embodiment of the present application.

[0134] This flowchart is divided into two major parts: an offline training part and an online application part.

[0135] The offline training part includes the following steps:

[0136] Step 1: Obtain three-electrode battery data. Corresponding to the above embodiment, obtain the real state data of the sample battery at multiple sample times, and the specified real potential values at multiple sample times.

[0137] Step 2: Construct an electrochemical mechanism model that includes the lithium plating side reaction and the thermal field model and generate simulation data. Corresponding to the above embodiments, construct a second electrochemical mechanism model and calculate the simulated potential values of the sample battery at multiple sample times.

[0138] Step 3: Divide the three-electrode battery data and the simulation data into data segments. That is, divide the obtained data according to the detection interval in the above embodiments to obtain the input data and label data for training the potential prediction model. The above data includes: the real state data of the sample battery at multiple sample times, the specified real potential value, and the simulated potential value. The real state data and the simulated potential value are used as input data, and the specified real potential value is used as the corresponding label data.

[0139] Step 4: Construct a deep learning algorithm to establish the mapping relationship between the two-electrode battery data, the simulation data, and the negative electrode potential value. That is, use the divided data segments to train the potential prediction model.

[0140] The online application part includes the following steps:

[0141] Step 5: Collect the actual scenario operation data of the battery. That is, in the above embodiments, obtain the data to be processed of the target battery.

[0142] Step 6: Use the trained deep learning algorithm. That is, use the pre-trained potential prediction model to process the data to be processed of the target battery to obtain the predicted negative electrode potential values of the target battery at multiple historical times.

[0143] Step 7: Judge the lithium plating state and calculate the amount of dead lithium precipitation. That is, based on the obtained predicted negative electrode potential values, judge whether lithium plating occurs in the target battery at multiple historical times and calculate the amount of dead lithium precipitation.

[0144] Step 8: Accumulate the actual operation data of the target battery in one or more scenarios.

[0145] Step 9: Update the deep learning algorithm online.

[0146] Steps 8 and 9 are the incremental training of the model in the above embodiments.

[0147] See Figure 4 , Figure 4 which is the flowchart of the lithium plating detection method provided by the embodiments of the present application, including the following steps:

[0148] S401: Obtain the voltage, current, and temperature data of the target battery.

[0149] That is, in the above embodiments, through the battery management system or the energy management system, obtain the real state data of the target battery at multiple historical times.

[0150] S402: Obtain the simulated full-cell potential value, simulated negative electrode potential value, and simulated positive electrode potential value calculated by the electrochemical mechanism model.

[0151] That is, obtain the simulated potential values of the target battery at multiple historical moments calculated by the first electrochemical mechanism model.

[0152] S403: Predict the negative electrode potential value.

[0153] That is, use the pre-trained potential prediction model to process the real-state data and simulated potential values of the target battery to obtain the predicted negative electrode potential values of the target battery at multiple historical moments.

[0154] S404: Determine whether the predicted negative electrode potential value is greater than the system preset value. If it is greater, execute S401 and S402; if it is not greater, execute S405.

[0155] S405: Determine that lithium plating occurs in the target battery, output the lithium plating state, and calculate the amount of dead lithium precipitation.

[0156] That is, based on the obtained predicted negative electrode potential values, determine whether lithium plating occurs in the target battery at multiple historical moments. If lithium plating does not occur, continue to charge the target battery according to the current charging conditions, and continue to detect lithium plating of the target battery at the detection interval. If lithium plating occurs, output the lithium plating state and calculate the amount of dead lithium precipitation.

[0157] In addition, if lithium plating occurs, adjust the charging conditions during the current charging process of the target battery in the manner described in the above embodiments.

[0158] Based on the same inventive concept, the embodiments of the present application also provide a lithium plating detection device. Refer to Figure 5 , Figure 5 which is a structural diagram of a lithium plating detection device provided by the embodiments of the present application. The device includes: a to-be-processed data acquisition module 501 that acquires the to-be-processed data of the target battery; the to-be-processed data includes: during the current charging process, the real-state data of the target battery at multiple historical moments within the historical time period before the current moment, and the real-state data includes: the full-cell potential value and the charging current value; a prediction module 502 that uses the pre-trained potential prediction model to process the to-be-processed data to obtain the predicted negative electrode potential values of the target battery at multiple historical moments. The potential prediction model is constructed as: trained based on the real-state data and real specified potential values of the sample battery at multiple sample moments during the historical charging process; the real specified potential value includes the real positive electrode potential value, or includes the real negative electrode potential value; a judgment module 503 that determines whether lithium plating occurs in the target battery at multiple historical moments based on the obtained multiple predicted negative electrode potential values.

[0159] Since there is a mapping relationship between the negative electrode potential value of the target battery at a historical moment and the real state data at the historical moment, the negative electrode potential value at the historical moment is predicted using the real state data at the historical moment. Additionally, during the use of the target battery, the negative electrode potential value characterizes whether lithium plating occurs in the target battery. Therefore, the predicted negative electrode potential values at multiple historical moments are used to determine whether lithium plating occurs in the target battery at multiple historical moments, so as to improve the accuracy of lithium plating detection for the target battery.

[0160] In one or more embodiments of the present application, the above-mentioned prediction module 502 inputs the data to be processed into a pre-trained potential prediction model to obtain the predicted negative electrode potential values of the target battery at multiple historical moments; the true specified potential value is the true negative electrode potential value; or, the above-mentioned prediction module 502 inputs the data to be processed into a pre-trained potential prediction model to obtain the predicted positive electrode potential values of the target battery at multiple historical moments; the true specified potential value is the true positive electrode potential value; then, in combination with the true full battery potential values and the predicted positive electrode potential values of the target battery at multiple historical moments, the predicted negative electrode potential values of the target battery at multiple historical moments are calculated.

[0161] Directly predicting the negative electrode potential value of the target battery using the potential prediction model, or predicting the positive electrode potential value of the target battery and combining the full battery potential value of the target battery to calculate the predicted negative electrode potential value of the target battery improves the accuracy of the obtained negative electrode potential value and further improves the accuracy of lithium plating detection for the target battery.

[0162] In one or more embodiments of the present application, the above-mentioned judgment module 503 calculates the average value of the multiple predicted negative electrode potential values obtained; in response to the average value being greater than the preset threshold, it is determined that no lithium plating occurs in the target battery at multiple historical moments; in response to the average value not being greater than the preset threshold, it is determined that lithium plating occurs in the target battery at multiple historical moments.

[0163] The average value of the multiple predicted negative electrode potential values obtained accurately characterizes the negative electrode potential value during the historical time period. Correspondingly, this average value is used to detect whether lithium plating will occur in the target battery at multiple historical moments to improve the accuracy of the lithium plating detection result.

[0164] In one or more embodiments of the present application, the above-mentioned device further includes: a dead lithium precipitation amount calculation module. In response to lithium plating occurring in the target battery at multiple historical moments, it uses the predicted negative electrode potential values of the target battery at multiple historical moments to calculate the lithium plating side reaction current of the target battery at multiple historical moments; then, in combination with the lithium plating side reaction current of the target battery at multiple historical moments, it calculates the total lithium plating amount of the target battery during the historical time period; furthermore, it calculates the product of the total lithium plating amount and the preset ratio to obtain the dead lithium precipitation amount of the target battery during the historical time period.

[0165] By using the predicted negative electrode potential value, the accuracy of calculating the amount of dead lithium deposited in the target battery during the historical time period is improved, providing a more accurate basis for the management of the target battery.

[0166] In one or more embodiments of the present application, the above device further includes: a control module, in response to lithium deposition occurring in the target battery at multiple historical moments, during the current charging and / or subsequent charging processes, changing the charging conditions, and charging the target battery according to the changed charging conditions. Changing the charging conditions includes: reducing the charging rate and / or increasing the battery temperature. And / or, the control module, in response to no lithium deposition occurring in the target battery at multiple historical moments, keeps the current charging conditions unchanged and continues to charge the target battery. And / or, the control module, in response to lithium deposition occurring in the target battery at multiple historical moments, reduces the output power of the target battery during the next power supply process.

[0167] When it is determined that lithium deposition occurs in the target battery during the historical time period, the current charging conditions are adjusted accordingly, and the target battery is controlled to be charged according to the adjusted charging conditions, so as to reduce the risk of lithium deposition occurring during the charging process of the target battery. Additionally, when it is determined that no lithium deposition occurs in the target battery during the historical time period, the current charging conditions are kept unchanged, and the target battery continues to be charged while completing the charging process of the target battery as soon as possible. If lithium deposition occurs in the target battery at multiple historical moments, during the next charging and / or discharging process, the output power of the target battery is reduced, or it is charged with the adjusted charging conditions, so as to mitigate the impact brought by lithium deposition and improve the usage safety of the target battery.

[0168] In one or more embodiments of the present application, the potential prediction model includes at least one of the following: a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory neural network, a model with an attention mechanism, and a Transformer network.

[0169] Based on the above network, the accuracy of predicting the negative electrode potential value is further improved to enhance the accuracy of the lithium deposition detection result.

[0170] In one or more embodiments of the present application, the true state data of the target battery further includes: the battery temperature; and / or, the data to be processed further includes: the simulated potential values of the target battery at multiple historical moments, and the simulated potential values at multiple historical moments are calculated using a pre-constructed first electrochemical mechanism model of the target battery. The simulated potential values at multiple historical moments include at least one of the following: the simulated full-cell potential value, the simulated positive electrode potential value, and the simulated negative electrode potential value; the potential prediction model is constructed by training based on the true state data, simulated potential values, and true specified potential values of the sample battery at multiple sample moments during the historical charging process; the simulated potential values at multiple sample moments are calculated using a pre-constructed second electrochemical mechanism model of the sample battery.

[0171] Since the negative electrode potential value of the target battery is affected by temperature, the negative electrode potential value at a historical moment is predicted in combination with the battery temperature, further improving the accuracy of predicting the negative electrode potential value. Since the first electrochemical mechanism model predicts the true potential value of the target battery at a historical moment, the accuracy of predicting the negative electrode potential value is further improved by combining the simulated potential value obtained from the first electrochemical mechanism model, so as to improve the accuracy of the lithium plating detection result.

[0172] In one or more embodiments of the present application, the first electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model; and / or, the second electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model.

[0173] Based on the above electrochemical model, the accuracy of obtaining the simulated potential value is improved, and the accuracy of predicting the negative electrode potential value is further improved, so as to improve the accuracy of the lithium plating detection result.

[0174] In one or more embodiments of the present application, the above-mentioned data to be processed acquisition module 501 acquires the data to be processed of the target battery when any one of a plurality of preset detection moments is reached. In some embodiments of the present application, the detection interval between every two adjacent detection moments is the same as the duration of the historical time period.

[0175] At each time when the detection moment is reached, it is detected whether lithium plating occurs in the target battery during the historical time period before this detection moment, that is, whether lithium plating occurs in the target battery between the previous detection moment and the current detection moment. In this way, it is determined in real time whether lithium plating occurs in the most recent period according to the latest state of the target battery, improving the real-time performance of the detection.

[0176] Based on the same inventive concept, an embodiment of the present application further provides an electronic device, and the electronic device is used to execute the lithium plating detection method described in any one of the above embodiments.

[0177] Based on the same inventive concept, an embodiment of the present application further provides a battery pack, including a battery module and the electronic device described in the above embodiment.

[0178] Based on the same inventive concept, an embodiment of the present application further provides an energy storage product, the energy storage product includes a battery module and an electronic device, and the electronic device is used to execute the lithium plating detection method described in any one of the above embodiments.

[0179] Based on the same inventive concept, in another embodiment provided by the present application, a computer-readable storage medium is further provided, and a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above lithium plating detection methods are implemented.

[0180] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0181] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0182] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for electronic devices, battery packs, charging devices, energy storage products, computer-readable storage media, and computer program products, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0183] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application are all included in the protection scope of the present application.

Claims

1. A lithium precipitation detection method, characterized in that: The method comprises: Obtaining the data to be processed of the target battery; wherein the data to be processed includes: the real state data of the target battery at multiple historical moments in the historical time period before the current moment during the current charging process, and the real state data includes: the full battery potential value and the charging current value; Processing the data to be processed using a pre-trained potential prediction model to obtain predicted negative electrode potential values ​​of the target battery at the multiple historical moments; The potential prediction model is constructed as follows: the model is trained based on the real state data of the sample battery at multiple sample moments in the historical charging process and the real specified potential value, wherein the real specified potential value includes the real positive electrode potential value or the real negative electrode potential value; Based on the obtained multiple predicted negative electrode potential values, it is determined whether lithium plating occurs in the target battery at the multiple historical moments.

2. The method according to claim 1, characterized in that The method of processing the data to be processed by using a pre-trained potential prediction model to obtain predicted negative electrode potential values ​​of the target battery at the multiple historical moments includes: Inputting the data to be processed into a pre-trained potential prediction model to obtain predicted negative electrode potential values ​​of the target battery at the multiple historical moments; Wherein, the real specified potential value includes the real negative electrode potential value; or, Inputting the data to be processed into a pre-trained potential prediction model to obtain predicted positive electrode potential values ​​of the target battery at the multiple historical moments; Wherein, the real specified potential value includes the real positive electrode potential value; The predicted negative electrode potential values ​​of the target battery at the multiple historical moments are calculated by combining the actual full-battery potential values ​​of the target battery at the multiple historical moments and the predicted positive electrode potential values.

3. The method according to claim 1, characterized in that The determining, based on the obtained multiple predicted negative electrode potential values, whether lithium deposition occurs in the target battery at the multiple historical moments includes: an average value of a plurality of the predicted negative electrode potential values ​​obtained by calculation; In response to the average value being greater than a preset threshold, determining that lithium plating does not occur in the target battery at the multiple historical moments; In response to the average value being not greater than the preset threshold, it is determined that lithium plating occurs in the target battery at the multiple historical moments.

4. The method according to claim 1, characterized in that: The method further comprises: In response to lithium deposition occurring in the target battery at the multiple historical moments, using predicted negative electrode potential values ​​of the target battery at the multiple historical moments, calculating the lithium deposition side reaction current of the target battery at the multiple historical moments; Calculate the total lithium deposition amount of the target battery in the historical time period in combination with the lithium deposition side reaction current of the target battery at the multiple historical moments; The product of the total lithium deposition amount and the preset ratio is calculated to obtain the dead lithium deposition amount of the target battery in the historical time period.

5. The method according to claim 1, characterized in that The method further comprises: In response to lithium deposition occurring in the target battery at the plurality of historical moments, during the current charging process, changing the charging condition, and continuing to charge the target battery according to the changed charging condition; The changing methods include: reducing the charging rate and / or increasing the battery temperature; and / or, In response to the target battery not undergoing lithium deposition at the multiple historical moments, keeping the current charging condition unchanged, and continuing to charge the target battery; and / or, In response to lithium plating of the target battery at the multiple historical moments, during the next power supply or charging process, the output power of the target battery is reduced, or the charging rate is reduced and / or the battery temperature is increased.

6. The method according to claim 1, characterized in that The potential prediction model includes at least one of the following: a convolutional neural network, a densely connected network, a recurrent neural network, a long short-term memory neural network, a model of an attention mechanism, and a Transformer network.

7. The method according to any one of claims 1 to 6, characterized in that: The real status data also includes: battery temperature; and / or, The data to be processed also includes: simulated potential values ​​of the target battery at the multiple historical moments, the simulated potential values ​​at the multiple historical moments are calculated using a pre-built first electrochemical mechanism model of the target battery, and the simulated potential values ​​at the multiple historical moments include at least one of the following: a simulated full battery potential value, a simulated positive electrode potential value, and a simulated negative electrode potential value; The potential prediction model is constructed as follows: the model is trained based on the real state data, simulated potential values ​​and real specified potential values ​​of the sample battery at multiple sample moments in the historical charging process; The simulated potential values ​​at the plurality of sample moments are calculated using a pre-constructed second electrochemical mechanism model of the sample battery.

8. The method according to claim 7, characterized in that The first electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model; and / or, The second electrochemical mechanism model is: a single particle model, a quasi-two-dimensional model, or a multi-dimensional multi-field electrochemical model.

9. The method according to any one of claims 1 to 6, characterized in that: The step of obtaining the data to be processed of the target battery includes: When any of the preset multiple detection moments is reached, the data to be processed of the target battery is obtained; The detection interval between every two adjacent detection moments is the same as the duration of the historical time period.

10. An electronic device, characterized in that: The electronic device is used to execute the method according to any one of claims 1 to 9.

11. A battery pack, characterized in that: The battery pack comprises a battery module and the electronic device as claimed in claim 10.

12. An energy storage product, characterized in that: The energy storage product comprises a battery module and the electronic device as claimed in claim 10.

Images