Lithium plating layer detection method of battery, lithium plating layer detection system and vehicle

Abstract

The invention provides a battery lithium coating detection method and system, a vehicle, computer equipment and a computer readable storage medium. The lithium coating detection method comprises the following steps: acquiring an original database, wherein the original database comprises historical working data of a battery; configuring a neural network model based on the original database; acquiring online data, wherein the online data comprises real-time working data of the battery; and inputting the online data into the neural network model and outputting real-time lithium plating layer state data so as to detect whether the lithium plating layer exists in the battery or not. Whether the lithium coating exists in the battery or not is detected through the neural network model, the detection process of the lithium coating is simplified, the detection precision of the lithium coating is improved, the detection method can continuously monitor the state of the battery, normal use and operation of the battery are not affected, the safety of the vehicle is further improved, and the safety of the vehicle is improved. And the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicles, and in particular to the field of battery systems for new energy vehicles. More specifically, the present invention relates to a method for detecting lithium plating on a battery, a lithium plating detection system, a vehicle using the lithium plating detection system, a computer device for implementing the lithium plating detection method, and a computer-readable storage medium for executing the lithium plating detection method. Background Art

[0002] In recent years, new energy vehicles have become increasingly common in our lives. In new energy vehicles, lithium batteries are usually used as a power source. During the use of lithium batteries, especially during the charge and discharge cycle, lithium plating may be generated. Lithium plating refers to a layer of metallic lithium formed by the deposition of lithium ions on the negative electrode of the battery (usually a graphite negative electrode). Lithium plating may cause needle-shaped lithium to form inside the battery, which may pierce the battery's diaphragm, causing a short circuit, and then lead to safety hazards such as battery overheating, fire or explosion. In addition, the lithium plating cannot participate in the charge and discharge reaction of the battery. Therefore, the continuous accumulation of lithium plating may lead to a decline in battery performance, reduce the effective capacity of the battery, and shorten the cycle life of the battery.

[0003] Therefore, the detection of lithium plating of lithium batteries is conducive to discovering battery safety hazards in advance, improving battery safety, and further improving the safety and reliability of vehicles. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems existing in the above-mentioned prior art and provide a method for detecting the lithium plating layer of a battery, so as to detect the lithium plating layer of the battery in a cost-effective and reliable manner.

[0005] To this end, according to one aspect of the present invention, a method for detecting lithium plating of a battery is provided, the method comprising: obtaining an original database, the original database comprising historical operating data of the battery; configuring a neural network model based on the original database; obtaining online data, the online data comprising real-time operating data of the battery; inputting the online data into the neural network model and outputting real-time lithium plating status data to detect whether the battery has lithium plating.

[0006] According to the above technical concept, the present invention may further include any one or more of the following optional forms.

[0007] In some optional forms, obtaining the original database includes: obtaining data related to the historical behavior of the battery through a second-order resistance-capacitance battery model.

[0008] In some optional forms, the data related to the historical behavior of the battery includes at least one of the ambient temperature, surface temperature, current, initial voltage, and initial battery capacity of the battery.

[0009] In some optional forms, obtaining the original database includes: obtaining historical lithium plating state data of the battery through a three-electrode test based on data related to historical behavior of the battery.

[0010] In some optional forms, the historical operating data and the real-time operating data of the battery have the same variables.

[0011] In some optional forms, obtaining the online data includes: obtaining the online data through a battery management system.

[0012] In some optional forms, configuring the neural network model based on the original database includes: constructing and training the neural network model using the feature vector sequence of the historical working data in the original database as the neural network model input and using the real-time lithium plating status data as the neural network model output.

[0013] In some optional forms, the neural network model is a long short-term memory network model.

[0014] According to another aspect of the present invention, a lithium plating detection system for a battery is provided, the lithium plating detection system comprising: a first acquisition module, the first acquisition module being configured to acquire an original database comprising historical operating data of the battery; a processing module, the processing module being configured to configure a neural network model based on the original database; a second acquisition module, the second acquisition module being configured to acquire online data comprising real-time operating data of the battery; and a detection module, the detection module being configured to input the online data into the neural network model and output real-time lithium plating status data to detect whether the battery has lithium plating.

[0015] In some optional forms, the first acquisition module is configured to acquire data related to the historical behavior of the battery through a second-order resistance-capacitance battery model.

[0016] In some optional forms, the first acquisition module is configured to acquire historical lithium plating state data of the battery through a three-electrode test based on data related to historical behavior of the battery.

[0017] In some optional forms, the second acquisition module is configured to: acquire the online data through a battery management system.

[0018] In some optional forms, the processing module is configured to: construct and train a neural network model using the feature vector sequence of the historical working data in the original database as a neural network model input and using the real-time lithium plating status data as a neural network model output.

[0019] According to yet another aspect of the present invention, a vehicle is provided, comprising the above-mentioned lithium plating detection system for a battery, wherein the lithium plating detection system is integrated with a battery management system of the vehicle.

[0020] In certain optional forms, the battery management system is configured to perform an adjustment action when the lithium plating detection system detects the presence of lithium plating on the battery, the adjustment action including at least one of adjusting the charging rate, performing balanced charging, and adjusting temperature management.

[0021] According to another aspect of the present invention, a computer device is provided, comprising a memory, a processor, and instructions stored in the memory and executable by the processor, wherein the processor implements the above-mentioned battery lithium plating detection method when executing the instructions.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium has computer-executable instructions stored thereon, and the computer-executable instructions are used to execute the above-mentioned method for detecting lithium plating of a battery.

[0023] The present invention uses a neural network model to detect whether a battery has a lithium plating layer, which simplifies the lithium plating detection process and improves the detection accuracy of the lithium plating layer. In addition, this detection method can continuously monitor the battery status without affecting the normal use and operation of the battery, further improving the safety of the vehicle and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features and advantages of the present invention will be better understood through the following detailed description of the optional embodiments in conjunction with the accompanying drawings, in which:

[0025] Figure 1 is a flow chart of a method for detecting lithium plating of a battery according to one embodiment of the present invention;

[0026] Figure 2 is a flow chart of a method for detecting lithium plating of a battery according to another embodiment of the present invention;

[0027] Figure 3 is a circuit diagram of a second-order resistance-capacitance battery model according to one embodiment of the present invention;

[0028] Figure 4is a schematic diagram of a three-electrode battery according to one embodiment of the present invention;

[0029] Figure 5 is a graph of three-electrode test results according to one embodiment of the present invention;

[0030] Figure 6 is a schematic diagram of a lithium plating detection system for a battery according to an embodiment of the present invention; and

[0031] Figure 7 is a schematic diagram of a computer device according to one embodiment of the present invention. DETAILED DESCRIPTION

[0032] The making and using of the embodiments are discussed in detail below. However, it should be understood that the specific embodiments discussed are merely illustrative of specific ways to make and use the invention, and are not intended to limit the scope of the invention.

[0033] In addition, the flowcharts and block diagrams in the accompanying drawings illustrate possible implementations of the architecture, functionality, and operations of the methods and systems according to various embodiments of the present invention. It should be noted that the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two blocks shown in succession may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved.

[0034] During the charge and discharge process, a vehicle's lithium battery may produce lithium plating, which affects the battery's life. Currently, a three-electrode test method is commonly used to detect whether a battery has lithium plating. The three-electrode test is only applicable to specific three-electrode batteries. Such three-electrode batteries typically include a positive electrode, a negative electrode, and a reference electrode that is used to measure the potential difference in the battery and does not participate in the battery's charge and discharge process. Such three-electrode batteries are typically used for the research and evaluation of lithium batteries in laboratory environments and cannot be used in actual lithium battery systems in vehicles. Therefore, using the three-electrode test, it is impossible to determine the real-time lithium plating status of the vehicle's battery during the charge and discharge process.

[0035] Reference Figure 1 , Figure 1 A flow chart of a method for detecting lithium plating of a battery according to an embodiment of the present invention is shown.

[0036] A method for detecting lithium plating of a battery according to one embodiment of the present invention may include the following steps.

[0037] Step S110: Acquire an original database for constructing a neural network model, where the original database may include historical operating data of the battery.

[0038] Step S120: configuring a neural network model based on the acquired original database.

[0039] Step S130: Acquire online data related to the real-time operating data of the battery.

[0040] Step S140: inputting the acquired online data into the configured neural network model and outputting real-time lithium plating status data to detect whether the battery has lithium plating.

[0041] In this way, according to the lithium plating detection method of the present invention, the lithium plating detection process can be simplified and the detection accuracy of the lithium plating can be improved by using a neural network model. The configured neural network model can realize real-time status detection of the lithium plating without affecting the normal use and operation of the battery, reducing the detection time of the lithium plating, improving the safety of the battery, and improving the user experience.

[0042] In certain embodiments, the battery's historical operating data and real-time operating data may share the same variables. That is, the battery's historical operating data and real-time operating data contain the same measured variables. This provides consistent information to the neural network model, ensuring that the data used during lithium plating detection is comparable. This facilitates training and testing of the neural network model based on the historical and real-time operating data, thereby improving the reliability and accuracy of the lithium plating detection process.

[0043] In some embodiments, the neural network model can be a long short-term memory network (Long Short-Term Memory networks, LSTM) model. The LSTM model can solve the gradient vanishing problem in traditional cyclic neural networks (Recurrent Neural Network, RNN), so long sequences can be better processed, which may have input data of varying lengths during lithium plating detection. The LSTM model can flexibly adjust its internal state to adapt to different input sequence lengths, thereby improving the detection accuracy of lithium plating. It is understandable that the neural network model is not limited thereto, and other neural network models can be selected depending on different needs.

[0044] Reference Figure 2 , Figure 2 is a flow chart of a method for detecting lithium plating of a battery according to another embodiment of the present invention.

[0045] A method for detecting lithium plating of a battery according to another embodiment of the present invention may include the following steps.

[0046] Step S211: obtaining data related to the historical behavior of the battery through a second-order resistance-capacitance battery model (hereinafter referred to as a second-order RC battery model).

[0047] The second-order RC battery model used in this embodiment can be as follows Figure 3 The second-order RC equivalent circuit model shown in the figure is composed of two RC network structures and a resistor in series. Figure 3 Middle,U OC represents the open circuit voltage of the battery, R represents the internal resistance of the battery, R1 represents the electrochemical polarization resistance, R2 represents the concentration polarization resistance, C1 represents the electrochemical polarization capacitance, C2 represents the concentration polarization capacitance, i represents the load current, U L Indicates the battery terminal voltage that can be directly measured.

[0048] Through this second-order RC battery model, data related to the historical behavior of the battery can be obtained for configuring the neural network model as listed in Table 1.

[0049] Table 1 Data related to the historical behavior of the battery obtained through the second-order RC battery model

[0050]

[0051]

[0052] Step S212: obtaining historical lithium plating state data of the battery through a three-electrode test based on data related to the historical behavior of the battery.

[0053] After obtaining the above data related to the historical behavior of the battery, the historical lithium plating state data of the battery can be obtained by three-electrode testing. The three-electrode battery used in this embodiment can be as follows: Figure 4 The three-electrode battery shown in the figure, in which the positive electrode 1 can be made of lithium iron phosphate material, the negative electrode 2 can be made of graphite material, and the reference electrode 3 can be made of lithium metal material. Based on the Z-shaped stacking method of the soft-pack battery, the positive electrode 1, the diaphragm, the reference electrode 3, the diaphragm, and the negative electrode 2 are assembled in this order and the tab 4 of the reference electrode 3 is led out. The tab 4 can be led out from the top, sides or bottom of the battery. Figure 4 It is shown in Figure 4The situation shown in the left direction. During the test, the battery is charged with a larger current when it is in a low state of charge (for example, in the range of 0% to 10%), and with a smaller current when it is in a high state of charge (for example, in the range of 90% to 100%), so as to reduce the risk of lithium plating of the negative electrode graphite at the end of charging and ensure the overall performance of the battery. In some embodiments, the charging current may be, for example, in the range of 0.2C to 1.5C, the above-mentioned larger current may be, for example, 1.2C, the smaller current may be, for example, 0.3C, and the test temperature is 25±2°C. It should be noted that C is used to indicate the rate of battery charge and discharge capability, 1C indicates the current intensity when the battery is fully charged and discharged for one hour, and may also be the current of the battery's nominal capacity. As Figure 5 The three-electrode test results shown in the figure show that during the battery charging process, if the lithium ions released from the positive electrode 1 are not embedded in the negative electrode 2 in time, the excess lithium ions will be reduced on the surface of the negative electrode 2. The reference electrode 3 is used to monitor the actual potential of the negative electrode 2 during the battery charging process. If the lowest potential of the negative electrode reaches 0V or below, it can be determined that the battery has a lithium plating layer. Figure 5 The lowest potential of the negative electrode of the battery is at point A. At this time, the SOC (battery state of charge) is about 93%, and the negative electrode potential is about -0.05V, which is below 0V. Therefore, it can be judged that there is lithium plating in the battery when the SOC is around 93%.

[0054] Step S220: constructing and training a neural network model using the feature vector sequence of the historical working data in the original database as the neural network model input and the real-time lithium plating state data as the neural network model output.

[0055] After obtaining the above-mentioned historical operating data, the construction and training of the neural network model can be started. In some embodiments, the feature vector sequence of the historical operating data in the original database can be used as the input of the neural network model. This feature vector sequence reflects the state of the battery system at different time points. The neural network model can learn the relationship between different time points through the patterns and trends in the feature vector sequence, thereby more accurately capturing the battery state evolution. In addition, by training the neural network model, the relationship between the historical operating data and the lithium plating state data can be understood, which can be used for battery system optimization, etc.

[0056] Step S231: obtaining online data related to the real-time operating data of the battery through the battery management system (BMS).

[0057] Step S240: inputting the online data into the configured neural network model and outputting real-time lithium plating status data to detect whether the battery has lithium plating.

[0058] The configured neural network model can be used in a real-time decision support system. By inputting the current real-time working data, the model can generate lithium plating status data corresponding to the real-time working data. Based on the generated lithium plating status data, the lithium plating status data can be updated in the battery management system to complete the lithium plating detection process of the battery. In addition, the detection result can be used as a detection benchmark for the lithium plating status data before the next cycle of lithium plating detection process.

[0059] In this way, the accuracy of lithium plating detection of the battery can be further improved. After detecting the presence of lithium plating in the battery, the vehicle's battery management system can obtain the status information of the lithium battery when lithium plating exists, such as charging rate, charging temperature, etc., and perform adjustment actions on the lithium battery based on the obtained status information, such as adjusting the charging rate, adjusting temperature management, etc., so as to further improve the safety of the vehicle and improve the user experience.

[0060] Reference Figure 6 , Figure 6 A schematic diagram of a lithium plating detection system for a battery according to an embodiment of the present invention is shown.

[0061] The battery lithium plating detection system according to this embodiment includes a first acquisition module 110, a processing module 120, a second acquisition module 130, and a detection module 140. The first acquisition module 110 is used to acquire a raw database including historical operating data of the battery, the processing module 120 configures a neural network model based on the raw database, the second acquisition module 130 is used to acquire online data including real-time operating data of the battery, and the detection module 140 is used to input the online data into the neural network model and output real-time lithium plating status data to detect whether the battery has lithium plating.

[0062] The specific functions of the lithium plating detection system 100 can be referred to the aforementioned Figure 1 The description in the implementation mode will not be repeated here.

[0063] In certain embodiments, the first acquisition module 110 can acquire data related to the battery's historical behavior using a second-order RC battery model. Furthermore, the first acquisition module 110 can also acquire historical lithium plating status data of the battery through a three-electrode test based on the data related to the battery's historical behavior. In certain embodiments, the processing module 120 can construct and train a neural network model using a sequence of feature vectors of historical operating data in a raw database as input and real-time lithium plating status data as output. The second acquisition module 130 can acquire online data through a battery management system.

[0064] The specific functions of the lithium plating detection system 100 can be referred to the aforementioned Figures 2 to 5 The description in the implementation mode will not be repeated here.

[0065] Additionally, the lithium plating detection system of the present invention can be integrated with a vehicle's battery management system. This allows the vehicle's battery management system to more comprehensively monitor the health of the battery. In addition to general battery status estimation (e.g., battery state of charge, state of health, power state, etc.), lithium plating detection can provide a more accurate understanding of the battery's operating status and, when lithium plating is detected, timely and appropriate measures can be taken to optimize battery performance and extend battery life.

[0066] In certain embodiments, when the lithium plating detection system detects the presence of lithium plating on a battery, the battery management system may perform regulatory actions. These regulatory actions may include: adjusting the battery's charging rate, such as reducing the battery's charging rate to prevent overcharging; implementing balanced charging in the lithium battery to minimize voltage differences between individual battery cells; and regulating temperature management to ensure that the battery is within an appropriate temperature range, such as -20°C to 60°C. It will be appreciated that the regulatory actions may be modified as needed and are not limited thereto.

[0067] Reference Figure 7 , Figure 7 FIG. 1 is a schematic diagram of a computer device according to an embodiment of the present invention.

[0068] The present invention also provides a computer device 200, such as Figure 7 As shown, the computer device 200 may include a memory 210 and a processor 220. Instructions 211 may be stored in the memory 210 and executed by the processor 220. When executing the instructions 211, the processor 220 implements the lithium plating detection method of the battery according to the above embodiment.

[0069] The computer device 200 of this embodiment can be a notebook, a desktop computer, a cloud server, etc. It is understood that the components included in the computer device 200 are not limited to the memory 210 and the processor 220, and can vary depending on different needs. For example, the computer device 200 can also include multiple components connected to its input / output interface ( Figure 7 (not shown) including but not limited to: input units, such as a keyboard, a mouse, etc.; output units, such as a display, a speaker, etc.; storage units, such as a semiconductor storage device, a magnetic surface storage device, an optical storage device, etc.; and communication units, such as a network card, a wireless communication transceiver, etc.

[0070] In some embodiments, the memory 210 may include, for example, a random access memory (RAM) or a read-only memory (ROM). The memory 210 may be used to store instructions, programs, codes, and other programs and data required by the computer device 200, but is not limited thereto.

[0071] In addition, the processor 220 can be a central processing unit (CPU) or other general-purpose processors, such as a digital signal processing (DSP), a field programmable gate array (FPGA), a programmable logic array (PLA), etc.

[0072] In an exemplary embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium has computer-executable instructions stored thereon. The computer-executable instructions are used to execute the lithium plating detection method for a battery according to the above embodiment.

[0073] Alternatively, the computer-readable storage medium according to the present embodiment may be a ROM, a RAM, a semiconductor storage device, a magnetic surface storage device, an optical storage device, and the like.

[0074] The lithium plating detection method of the battery of the present invention detects whether the battery has a lithium plating layer through a neural network model, which can realize real-time detection of the lithium plating state, improve the detection accuracy of the lithium plating layer, improve the safety performance of the battery, and is cost-effective and has high detection efficiency. In addition, the detection method of the present invention is not limited to use in new energy vehicles, and can also be applied to other types of vehicles such as hybrid vehicles as needed to detect whether the battery of the vehicle has a lithium plating layer and improve the safety performance of the vehicle. In addition, the detection method of the present invention can be used for various types of lithium batteries, such as lithium iron phosphate batteries, ternary lithium batteries, etc.

[0075] It should be understood that the embodiment shown in the figure only shows an optional configuration of the lithium plating detection system of the battery according to the present invention. However, it is only illustrative and not restrictive. Other configurations may also be adopted without departing from the spirit and scope of the present invention.

[0076] The technical content and technical features of the present invention have been disclosed above. However, it is understood that, based on the creative ideas of the present invention, those skilled in the art may make various changes and improvements to the above-disclosed concepts, all of which fall within the scope of protection of the present invention. The description of the above embodiments is illustrative and not restrictive. The scope of protection of the present invention is determined by the claims.

Claims

1. A method for detecting lithium plating of a battery, characterized in that: The lithium plating layer detection method comprises: Acquiring an original database (S110), wherein the original database includes historical operating data of the battery; Configuring a neural network model based on the original database (S120); Acquiring online data (S130), wherein the online data includes real-time operating data of the battery; The online data is input into the neural network model and real-time lithium plating state data is output to detect whether the battery has lithium plating (S140; S240).

2. The lithium plating detection method of a battery according to claim 1, wherein Acquiring the original database includes: acquiring data related to the historical behavior of the battery through a second-order resistance-capacitance battery model (S211).

3. The lithium plating detection method of a battery according to claim 2, wherein The data related to the historical behavior of the battery includes at least one of the ambient temperature, surface temperature, current, initial voltage, and initial battery capacity of the battery.

4. The lithium plating detection method of a battery according to claim 2, wherein Acquiring the original database includes: acquiring historical lithium plating state data of the battery through a three-electrode test based on data related to historical behavior of the battery (S212).

5. The method for detecting lithium plating of a battery according to claim 1, wherein The historical operating data and the real-time operating data of the battery have the same variables.

6. The method for detecting lithium plating of a battery according to claim 1, wherein: Acquiring online data includes: acquiring the online data through a battery management system (S231).

7. The method for detecting lithium plating of a battery according to claim 1, wherein: Configuring the neural network model based on the original database includes: using the feature vector sequence of the historical working data in the original database as the neural network model input and using the real-time lithium plating state data as the neural network model output to construct and train the neural network model (S220).

8. The method for detecting lithium plating of a battery according to any one of claims 1 to 7, wherein: The neural network model is a long short-term memory network model.

9. A battery lithium plating detection system, characterized in that: The lithium plating detection system comprises: A first acquisition module (110), the first acquisition module (110) is configured to acquire an original database, the original database including historical operating data of the battery; a processing module (120), the processing module (120) being configured to configure a neural network model based on the original database; A second acquisition module (130), the second acquisition module (130) is configured to acquire online data, the online data including real-time operating data of the battery; A detection module (140) is configured to input the online data into the neural network model and output real-time lithium plating status data to detect whether the battery has lithium plating.

10. The battery lithium plating detection system according to claim 9, characterized in that: The first acquisition module (110) is configured to acquire data related to the historical behavior of the battery through a second-order resistance-capacitance battery model.

11. The battery lithium plating detection system according to claim 10, characterized in that: The first acquisition module (110) is configured to acquire historical lithium plating state data of the battery through a three-electrode test based on data related to historical behavior of the battery.

12. The battery lithium plating detection system according to claim 9, characterized in that: The second acquisition module (130) is configured to acquire the online data through a battery management system.

13. The battery lithium plating detection system according to claim 9, characterized in that: The processing module (120) is configured to construct and train the neural network model using the feature vector sequence of the historical working data in the original database as a neural network model input and the real-time lithium plating state data as a neural network model output.

14. A vehicle, characterized in that: The vehicle comprises the lithium plating detection system for a battery according to any one of claims 9 to 13, wherein the lithium plating detection system is integrated with a battery management system of the vehicle.

15. The vehicle according to claim 14, characterized in that The battery management system is configured to perform an adjustment action when the lithium plating detection system detects the presence of lithium plating on the battery. The adjustment action includes at least one of adjusting a charging rate, performing balanced charging, and adjusting temperature management.

16. A computer device, characterized in that: The computer device (200) includes a memory (210), a processor (220), and instructions (211) stored in the memory (210) and executable by the processor (220), wherein when the processor (220) executes the instructions (211), the method for detecting lithium plating of a battery according to any one of claims 1 to 8 is implemented.

17. A computer-readable storage medium, characterized in that The computer-readable storage medium has computer-executable instructions stored thereon, and the computer-executable instructions are used to execute the lithium plating detection method for a battery according to any one of claims 1 to 8.

Images