A method and system for evaluating the performance of a battery system

Abstract

An embodiment of this specification discloses a method and system for evaluating the performance of a battery system. The battery system includes one or more battery modules, and each of the battery modules includes a plurality of series-connected single cells. The method includes: obtaining battery characteristic parameters of the battery system, where the battery characteristic parameters represent the charging characteristics of the battery system; obtaining a performance evaluation model; and evaluating battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters, where the battery performance parameters represent the health status of one or more battery modules or single cells of the battery system.

Description

Technical Field

[0001] This specification relates to the field of data processing, and particularly to a method and system for evaluating the performance of a battery system. Background Art

[0002] Currently, with the increasing awareness of environmental protection among people, new energy vehicles are developing more and more rapidly. More and more people choose new energy vehicles as their means of transportation for travel. Among them, new energy vehicles use electric energy as the main energy source. Therefore, it is particularly important to estimate the health state of the batteries of new energy vehicles. Summary of the Invention

[0003] One embodiment of this specification provides a method for evaluating the performance of a battery system. The battery system includes one or more battery modules, and each of the battery modules includes a plurality of parallel-connected single cells. The method includes: obtaining battery characteristic parameters of the battery system, where the battery characteristic parameters represent the charging characteristics of the battery system; obtaining a performance evaluation model; and evaluating battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters, where the battery performance parameters represent the health state of the one or more battery modules or single cells of the battery system.

[0004] One embodiment of this specification provides a battery system performance evaluation system. The battery system includes one or more battery modules, and each of the battery modules includes one or more parallel-connected single cells. The system includes: a parameter acquisition module for obtaining battery characteristic parameters of the battery system, where the battery characteristic parameters represent the charging characteristics of the battery system; a model acquisition module for obtaining a performance evaluation model; and a performance evaluation module for evaluating battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters, where the battery performance parameters represent the health state of the one or more battery modules or single cells of the battery system.

[0005] One embodiment of this specification provides a battery system performance evaluation device, including a processor, and the processor is used to execute the battery system performance evaluation method. Brief Description of the Drawings

[0006] This specification will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0007] Figure 1 is a schematic diagram of an application scenario of a battery system performance evaluation system according to some embodiments of this specification;

[0008] Figure 2It is an exemplary flowchart of a battery system performance evaluation method shown in some embodiments of this specification;

[0009] Figure 3 It is an exemplary flowchart of a method for evaluating battery performance parameters of a battery system shown in some embodiments of this specification;

[0010] Figure 4 It is an exemplary flowchart of a performance evaluation model training method shown in some embodiments of this specification;

[0011] Figure 5 It is a module diagram of a battery system performance evaluation system shown in some embodiments of this specification;

[0012] Figure 6 It is a schematic diagram of an application scenario of a performance evaluation model training system shown in some embodiments of this specification. Detailed implementation manners

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0015] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after do not necessarily need to be executed precisely in sequence. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0017] In some embodiments, a battery system (which may also be referred to as a battery pack) may include one or more battery modules, and each battery module may include one or more series-connected single cells and / or battery modules. Each battery module includes one or more parallel-connected single cells. Generally, the remaining life of the battery system can be described by the State of Health (SOH) of the battery system. SOH represents the ratio of the battery capacity that the battery system can currently carry to the original factory-calibrated capacity of the battery system, and can reflect the performance of the battery system. When the SOH drops to a certain value (e.g., 80%), the battery system needs to be retired from the electric vehicle, and the vehicle manufacturer is responsible for battery replacement. Therefore, the prediction of the SOH of the battery system is particularly important.

[0018] In some embodiments of this specification, a method and a system for predicting the health state of a battery system are proposed. Through a machine learning model, the health state of each battery module or single cell in the battery system can be predicted. Further, through the machine learning model, the health state of the battery system can be predicted according to the health state of each battery module or single cell in the battery system. The following is a detailed description of some embodiments of this specification.

[0019] Figure 1 It is a schematic diagram of the application scenario of the battery system performance evaluation system shown in some embodiments of this specification.

[0020] The battery system performance evaluation system 100 can be applied to the technical field of battery systems. Specifically, it can be applied to scenarios that require battery power supply, such as transportation devices like electric vehicles, electric bicycles, and electric motorcycles. Specifically, by obtaining the charging characteristics of the battery system and a performance evaluation model, and according to the performance evaluation model and the charging characteristics of the battery system, the health state of one or more battery modules or single cells of the battery system, and / or the health state of the battery system is evaluated.

[0021] The battery system performance evaluation system 100 may include a server 110, a network 120, a battery system 130, a storage device 140, and a terminal 150. The server 110 may include a processing device.

[0022] In some embodiments, the server 110 can be used to obtain the charging characteristics and performance evaluation model of the battery system, and evaluate the health status of one or more battery modules or single cells of the battery system, and / or the health status of the battery system according to the performance evaluation model. The server 110 can be an independent server or a server group. The server group can be centralized or distributed (e.g., the server 110 can be a distributed system). In some embodiments, the server 110 can be regional or remote. For example, the server 110 can access the information and / or data stored in the storage device 140 through a network. In some embodiments, the server 110 can be directly connected to the storage device 140 to access the information and / or data stored therein. In some embodiments, the server 110 can be executed on a cloud platform. For example, the cloud platform can include one or any combination of private cloud, public cloud, hybrid cloud, community cloud, decentralized cloud, internal cloud, etc.

[0023] In some embodiments, the server 110 may include a processing device. The processing device can process the charging characteristics of the battery system according to the performance evaluation model and evaluate the health status of one or more battery modules or single cells of the battery system, and / or the health status of the battery system. For example, the processing device can determine at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of one or more battery cells or modules according to the performance evaluation model and battery characteristic parameters. In some embodiments, the processing device may include one or more sub-processing devices (e.g., single-core processing device or multi-core multi-core processing device). Merely by way of example, the processing device may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), a physics processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), an editable logic circuit (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc. or any combination thereof.

[0024] Network 120 can facilitate the exchange of data and / or information, which may include battery characteristic parameters of the battery system 130 obtained by the server 110. In some embodiments, one or more components in the battery system performance evaluation system 100 (such as the server 110, the battery system 130, the storage device 140, the terminal 150, etc.) can send data and / or information to other components in the battery system performance evaluation system 100 via the network 120. In some embodiments, the network 120 can be any type of wired or wireless network. For example, the network 120 can include a cable network, a wired network, an optical fiber network, a telecommunications network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc., or any combination of the above. In some embodiments, the network 120 can include one or more network access points. For example, the network 120 can include wired or wireless network access points, such as base stations and / or Internet exchange points 120-1, 120-2, …, through which one or more components of the battery system performance evaluation system 100 can be connected to the network 120 to exchange data and / or information.

[0025] The battery system (which may also be referred to as a battery pack) 130 can be an energy storage device for powering specific devices, such as electric vehicles, hybrid electric vehicles, electric bicycles, electric motorcycles, etc. In some embodiments, the battery system may include one or more battery modules, where each battery module can be obtained by connecting multiple single cells 133 and / or battery modules in series. Further, each battery module can be obtained by connecting multiple single cells in parallel, and the one or more battery modules can operate cooperatively to supply power. In some embodiments, the battery system may only include multiple battery modules, where each battery module is obtained by connecting multiple single cells in series. In some embodiments, the battery system may further include one or more sensors and / or a battery management system (BMS). The single cell can be used to store electrical energy. Each single cell may include a positive terminal and a negative terminal. In some embodiments of this specification, the single cell can be any type of battery, such as a lead-acid single cell, a nickel-metal hydride single cell, a lithium-ion (Li-ion) single cell, etc., and this application does not make any restrictions. The BMS can be used to manage the charging and discharging behavior of the battery system 130, collect data related to the charging and discharging of the battery system 130, transmit the collected data, etc. In some embodiments, the battery system 130 can transmit data through the BMS. In some embodiments, the BMS can transmit data to one or more devices of the battery system performance evaluation system 100, such as the storage device 140, the server 110, and the terminal 150. In some embodiments, the BMS can also transmit data to other devices. For example, when the battery system 130 is charging with a charging device (such as when an electric vehicle is charging at a charging pile), data and / or information can be sent to the server 110 or the storage device 140 through the charging device (such as the charging pile). One or more sensors within the battery system 130 can detect one or more characteristics of the battery system 130. For example, the one or more sensors can include a temperature sensor configured to detect the overall internal temperature of the battery system 130 during charging and discharging and / or the temperature at one or more internal locations. Another example is that the one or more sensors can detect the charging and discharging current, voltage, power, etc. of the battery system 130. The one or more sensors can send the detected data to the BMS.

[0026] The storage device 140 is a source for providing information to the battery system performance evaluation system 100. The storage device 140 can be used to provide information related to the battery system performance evaluation method to the system 100. For example, it can provide battery characteristic parameters of the battery system 130. The storage device 140 can be implemented in a single central server, multiple servers connected via a communication link, or multiple personal devices. The storage device 140 can be generated by multiple personal devices and cloud servers. In some embodiments, the storage device 140 can be used to store the battery characteristic parameters uploaded by the battery system 130 during charging. In some embodiments, the storage device 140 can contain multiple data pools for storing the characteristic parameters of the above-mentioned multiple batteries. In some embodiments, the storage device 140 can store information and / or instructions for the server 110 to execute or use to perform the exemplary methods described in this specification. In some embodiments, the storage device 140 can include a mass storage device, a removable storage device, a volatile read-write memory (e.g., random access memory RAM), a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 140 can be implemented on a cloud platform. For example, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, etc., or any combination thereof.

[0027] In some embodiments, the storage device 140 can be connected to the network 120 to communicate with one or more components of the system 100 (e.g., the server 110, the battery system 130, etc.). One or more components of the battery system performance evaluation system 100 can access the data or instructions stored in the storage device 140 via the network 120. In some embodiments, the storage device 140 can be directly connected to or communicate with one or more components in the battery system performance evaluation system 100 (e.g., the server 110, the battery system 130, etc.). In some embodiments, the storage device 140 can be a part of the server 110.

[0028] The terminal 150 can be various devices with information receiving and / or sending functions. The user can interact with the server 110 through the terminal 150. For example, the user can receive the estimated result of the battery system health status through the terminal 150. For another example, the user can send a request to evaluate the battery system health status through the terminal 150. In some embodiments, the terminal 150 can include a mobile phone 150-1, a tablet computer 150-2, a personal computer 150-3, and other electronic devices, such as in-vehicle devices. In some embodiments, the user can include battery users (e.g., electric vehicle users), battery manufacturers, electric vehicle manufacturers, etc.

[0029] Figure 2is an exemplary flowchart of a battery system performance evaluation method according to some embodiments of this specification. In some embodiments, process 200 can be executed by Figure 1 the server 110 shown in. For example, process 200 can be stored in a storage device (such as storage device 140, the built-in storage unit of server 110, or an external storage device) in the form of a program or instruction, and when the program or instruction is executed, process 200 can be implemented. In some embodiments, process 200 can be executed by the processing device of server 110. As Figure 2 shown, process 200 can include the following steps.

[0030] Step 202, obtain battery characteristic parameters of the battery system (for example, battery system 130), where the battery characteristic parameters represent the charge and discharge characteristics of the battery system. In some embodiments, this step can be executed by the parameter acquisition module 510.

[0031] The battery characteristic parameters can be data generated during the use of the battery system (for example, charging, discharging).

[0032] In some embodiments, the battery characteristic parameters can include charge and discharge characteristic parameters and system characteristic parameters.

[0033] Among them, the charge and discharge characteristic parameters can include relevant data generated when the battery system is charging and / or discharging.

[0034] The system characteristic parameters can include parameters related to the historical data and / or cumulative data of the battery system.

[0035] In some embodiments, the charge and discharge characteristic parameters can include one or more combinations of the initial charging voltage, the characteristic voltage during the charging process, the cut-off charging voltage, the initial charging temperature, the temperature weight during the charging process (which can represent the average temperature during the charging process), the charging current, etc. In some embodiments, the system characteristic parameters can include one or more combinations of the cumulative charge and discharge amount, the cumulative number of charge and discharge times, the driving mileage, etc. During the charging process of a single battery, due to the inherent properties of the material, different charging voltages will be exhibited. The characteristic voltage during the charging process can include the instantaneous or real-time change in the charging voltage during the charging process and / or the average charging voltage during the charging process.

[0036] In some embodiments, the processing device in server 110 can directly or indirectly obtain the battery characteristic parameters of battery system 130 through one or more methods. For example, during the charging process, one or more sensors in battery system 130 can detect at least one of the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, etc. The one or more sensors can send the detected data to the BMS of battery system 130. For another example, the BMS of battery system 130 can obtain at least one of the cumulative charge and discharge amount, cumulative charge and discharge times, driving mileage, etc. of battery system 130. The BMS can directly send the obtained or received battery characteristic parameters to server 110 through network 120. Or, the BMS can send the obtained or received battery characteristic parameters to server 110 through a charging device (e.g., a charging pile).

[0037] Step 204, obtain a performance evaluation model. In some embodiments, this step can be executed by model acquisition module 520.

[0038] In some embodiments, the performance evaluation model can be a trained machine learning model. The performance evaluation model can include any one of a neural network, a transfer learning model, a deep learning model, a Gradient Boosting Decision Tree (GBDT), a support vector machine, an outlier algorithm, a clustering algorithm, a matching model for similarity between features, etc., and is not limited in the embodiments of this specification.

[0039] In some embodiments, an initial model can be obtained, and the initial model can be iteratively trained one or more times according to training samples to obtain a trained performance evaluation model. Among them, the training method of the performance evaluation model is described in detail in Figure 4 and will not be elaborated here. In some embodiments, the training of the performance evaluation model can be executed by server 110 or by an external device of system 100.

[0040] Step 206, evaluate the battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters. The battery performance parameters represent the health status of one or more battery modules or single cells of the battery system. In some embodiments, this step can be executed by performance evaluation module 530.

[0041] In some embodiments, the battery performance parameters can represent the health status of one or more battery modules or single cells in the battery system. Further, the battery performance parameters can also represent the health status of the entire battery system.

[0042] In some embodiments, the battery performance parameters of the battery system may include at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of one or more battery cells or modules. In some embodiments, the battery performance parameters of the battery system may further include at least one of the remaining capacity of the battery system, system capacity offset, system voltage difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life.

[0043] It can be understood that the remaining capacity of one or more battery cells or modules can be expressed as the maximum available capacity after the attenuation of the battery cells or modules. Further, the remaining capacity of the battery system can be expressed as the maximum available capacity after the attenuation of the battery system. Among them, the smaller the gap between the remaining capacity and the rated capacity (i.e., the standard capacity at the time of factory), the higher the health level of the single battery or module and the battery system.

[0044] The capacity offset of a battery cell or module can refer to the difference in the state of charge between the cell or module that does not reach the charge / discharge cut-off voltage and the cell or module that first triggers the charge / discharge cut-off condition when the system is charged to cut-off or discharged to cut-off. It can be understood that the battery system is composed of multiple single batteries, and there is a situation where the operating voltages of these single batteries are inconsistent during charge and discharge. During a complete charge or discharge process, due to the voltage inconsistency between the single batteries, the single batteries with higher / lower voltages will be fully charged / discharged first, thus triggering the charge / discharge cut-off action of the battery management system. At this time, the single battery with a lower voltage is not fully charged due to charge cut-off, or the single battery with a higher voltage is not fully discharged due to discharge cut-off, resulting in a capacity offset. In some embodiments, the capacity offset can evaluate the consistency of multiple battery cells or modules. The smaller the capacity offset, the better the co-charge / discharge performance of the battery system, the higher the consistency, and the stronger the charge / discharge power capability. Similarly, it can be understood that the system capacity offset can be obtained from the average value of the capacity offsets of one or more battery cells or modules in the battery system and can be used to evaluate the overall consistency of the battery system.

[0045] The internal resistance can refer to the direct current resistance (DCR). It can be understood that the relatively larger the internal resistance in a single battery or module, the lower the consistency and the lower the health level in the single battery or module; conversely, the relatively smaller the internal resistance, the higher the consistency and the higher the health level in the single battery or module. It can be understood that the internal resistance consistency of the battery system can reflect the difference in the internal resistances of the single batteries or modules in the battery system. Similarly, the lower the internal resistance consistency of the battery system, the lower the health level; conversely, the higher the health level.

[0046] The internal resistance offset may refer to the difference between the internal resistance of a single cell or module and the average internal resistance (the average internal resistance may be the average value of the internal resistance of all single cells or modules in the battery system). For example, the internal resistance offset of a battery module may refer to the difference between the internal resistance of the battery module and the average internal resistance of all battery modules in the battery system. For another example, the internal resistance offset of a single cell may refer to the difference between the internal resistance of the single cell and the average internal resistance of all single cells in the battery system. In some embodiments, the internal resistance offset may evaluate the consistency of multiple single cells or modules. For example, the smaller the internal resistance offset, the higher the circulating current during the coordinated charging or discharging of multiple batteries or modules in the battery system, and the greater the health level.

[0047] The system voltage difference may refer to the difference between the highest voltage of a single cell or module and the lowest voltage of a single cell or module in a battery system. It is understandable that when the voltage difference of multiple single cells or modules is larger, it means that the matching degree of multiple single cells or modules is lower, and the health of the battery system is lower; conversely, the smaller the voltage difference is, the higher the matching degree of multiple single cells or modules is, and the health of the battery system is higher.

[0048] The self-discharge amount may refer to the percentage of power automatically reduced by one or more single cells or modules in the battery system when not in use. For example, if one or more single cells or modules are fully charged and the capacity decreases by more than 3% every day and night within 1 month, it is considered to be in a low health state; conversely, if the capacity decreases by less than 3% every day and night, it is considered to be in a high health state. In some embodiments, the closer the percentage of self-discharge of one or more single cells or modules in the battery system is, for example, the percentage of self-discharge is about 3%, the higher the self-discharge consistency of the battery system is, and the higher the health state is; conversely, the greater the difference in the percentage of self-discharge power, the lower the self-discharge consistency of the battery system is, and the lower the health state is.

[0049] The temperature state may refer to the temperature currently generated by the battery system. It is understandable that when the temperature of the battery system exceeds a preset temperature threshold (eg, 50° C.) and the higher it is, the lower the health level is; conversely, when it is lower than the preset threshold, the health level is higher.

[0050] The remaining life may refer to the remaining life of the battery system. It is understandable that the longer the remaining life is, the higher the health of the battery system is; otherwise, the lower the health of the battery system is.

[0051] In some embodiments, the processing device in the server 110 may evaluate the battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters. For example, the processing device may input the battery characteristic parameters of the battery system 130 into the trained performance evaluation model to obtain the battery performance parameters output from the performance evaluation model. For example, at least one of the remaining capacity, capacity offset, internal resistance, internal resistance offset, etc. of each single battery or module in the battery system 130, and then determine the health status of each single battery or module in the battery system 130. Thus, single batteries or modules with health problems can be found, making subsequent maintenance more targeted.

[0052] In some embodiments, the processing device may also input the battery characteristic parameters of the battery system 130, and at least one of the remaining capacity, capacity offset, internal resistance, internal resistance offset, etc. of each single battery or module in the battery system 130 into the performance evaluation model to obtain at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature status, remaining life, so as to further determine the health status of the entire battery system. For a detailed description of evaluating the remaining capacity of the battery system according to the performance evaluation model and battery characteristic parameters, please refer to Figure 3 the relevant description in, which will not be elaborated here.

[0053] In some embodiments, the battery system performance evaluation method further includes: issuing a warning prompt based on the battery performance characteristic parameters evaluated in step 206. This step may be executed by the sending model 540.

[0054] The warning prompt may be a communication medium with a prompting function. In some embodiments, the warning prompt may include the warning type, warning level, and the location of the abnormal battery module or single battery.

[0055] Furthermore, the warning type may be a sound warning, a text warning, an image warning, a video warning, etc. The type and implementation method of the warning prompt are not limited in this specification.

[0056] The warning level may rate this warning according to the health degree of the battery system or the abnormal battery module or single battery. It can be understood that the higher the warning level, the more important this warning is. For example, the health degrees are extremely high, relatively high, relatively low, and extremely low, corresponding to warning levels one, two, three, and four respectively.

[0057] In some embodiments, the processing device in the server 110 may issue a warning prompt directly or indirectly based on the battery performance parameters through one or more methods.

[0058] In some embodiments, the server 110 may directly send the estimated battery performance parameters to the terminal 150. In some embodiments, the server 110 may analyze the battery performance parameters, evaluate the health status of the battery system, and send the analysis results to the terminal 150. For example, the server 110 may determine whether the remaining capacity of a single battery, a battery module, or a battery system is less than a capacity threshold. If it is less than the capacity threshold, a warning prompt is sent to the terminal 150 to prompt the user to replace or repair the single battery, the battery module, or the battery system. For another example, the server 110 may determine whether the internal resistance of a single battery or a battery module is greater than an internal resistance threshold. If it is greater than the internal resistance threshold, a warning prompt is sent to the terminal 150 to prompt the user to replace or repair the single battery or the battery module. For another example, the server 110 may determine whether the internal resistance offset of a single battery or a battery module is greater than a first offset threshold. If it is greater than the first offset threshold, a warning prompt is sent to the terminal 150 to prompt the user to replace or repair the single battery or the battery module. For another example, the server 110 may determine whether the capacity offset of a single battery or a battery module is greater than a second offset threshold. If it is greater than the second offset threshold, a warning prompt is sent to the terminal 150 to prompt the user to replace or repair the single battery or the battery module. For another example, the server 110 may determine the maximum internal resistance offset and the minimum internal resistance offset of a single battery or a battery module in the battery system, and determine whether the difference between the maximum internal resistance offset and the minimum internal resistance offset is greater than a first difference threshold. If it is greater than the first difference threshold, a warning prompt is sent to the terminal 150 to prompt the user that the consistency of the battery system is poor. For another example, the server 110 may determine the maximum capacity offset and the minimum capacity offset of a single battery or a battery module in the battery system, and determine whether the difference between the maximum capacity offset and the minimum capacity offset is greater than a second difference threshold. If it is greater than the second difference threshold, a warning prompt is sent to the terminal 150 to prompt the user that the consistency of the battery system is poor. The server 110 may also first determine the first difference between the maximum internal resistance offset and the minimum internal resistance offset, and the second difference between the maximum capacity offset and the minimum capacity offset, and then determine the weighted average of the first difference and the second difference. If the weighted average is greater than a third difference threshold, a warning prompt is sent to the terminal 150 to prompt the user that the consistency of the battery system is poor.

[0059] In some embodiments, the processing device may comprehensively evaluate the remaining capacity, capacity offset, internal resistance, and internal resistance offset of a single battery or a module. For example, each item is scored, and the weighted average of the scores is determined. If the weighted average is less than a score threshold, a warning prompt is sent to the terminal 150 to prompt the user to replace or repair the single battery or the battery module.

[0060] In some embodiments, the warning prompt may include indicating the location of the abnormal battery cell or module. For example, the number or location of the abnormal battery cell or module in the battery system is sent to the terminal 150 by means of sound, text, or image to prompt the user of the abnormal battery cell or module.

[0061] As an example, for multiple battery modules in a battery system, the nominal capacity of each battery module is 105 Ah. The performance evaluation model can output the remaining capacity and capacity offset of each battery module according to the battery characteristic parameters. Among them, the minimum remaining capacity is 87.12 Ah, the maximum remaining capacity is 92.84 Ah, the average value of the remaining capacity of the battery modules is 85.32 Ah, and the capacity difference between each battery module is about 5%. It can be judged that the overall attenuation of the single battery or battery module in the battery system occurs. The minimum offset capacity of the module is 0.16 Ah, the maximum offset capacity of the module is 3.73 Ah, and the difference between the two is 3.57 Ah, which is less than the second difference threshold (for example, 5 Ah). It can be judged that the consistency of the battery system is good. The performance evaluation model can further determine the maximum module capacity, minimum module capacity, maximum offset capacity, and minimum offset capacity according to the output remaining capacity and capacity offset of the module, and comprehensively evaluate that the maximum available capacity of the system is 86.4 Ah. As another example, for multiple battery modules in a battery system, the performance evaluation model can output the internal resistance of each battery module according to the battery characteristic parameters. Among them, the minimum internal resistance of the battery module is 0.154 mΩ, the maximum internal resistance is 0.173 mΩ, the average internal resistance of the module is 0.163 mΩ, and the maximum internal resistance difference between the modules (the ratio of the difference between the maximum internal resistance and the minimum internal resistance to the average internal resistance) is about 12%, which is greater than the threshold of 10%. It can be judged that the consistency of the battery system is poor.

[0062] Figure 3 It is an exemplary flowchart of a method for evaluating battery performance parameters of a battery system according to some embodiments of this specification. In some embodiments, as shown in the figure, process 300 includes step 302 and step 304. The following is a detailed description of process 300.

[0063] In some embodiments, the performance evaluation model can be used to evaluate the health status of each battery cell or module in the battery system, that is, at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of one or more battery cells or modules in step 302. In other embodiments, the performance evaluation model can also be used to evaluate the health status of the entire battery system, that is, at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature status, and remaining life in step 304. Step 302 and step 304 are detailed descriptions of the above-mentioned some embodiments.

[0064] Step 302: Determine at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules according to the performance evaluation model and the battery characteristic parameters.

[0065] In some embodiments, the performance evaluation model can be used to evaluate the health state of one or more individual battery cells or modules included in a battery system. For example, according to the performance evaluation model and the battery characteristic parameters, determine at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules.

[0066] In some embodiments, the input of the performance evaluation model can be the battery characteristic parameters of the battery system, and its output can be at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules included in the system.

[0067] Thus, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules are obtained through the performance evaluation model, and further, the health degree of the one or more battery cells or modules can be evaluated. For a detailed description of this step, reference can be made to the relevant description in step 206, which will not be elaborated here.

[0068] Step 304: Determine at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life according to the performance evaluation model, the battery characteristic parameters, and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules.

[0069] In some embodiments, the performance evaluation model can also be used to evaluate the health degree of the entire battery system. For example, at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life.

[0070] In some embodiments, the input of the performance evaluation model can be the battery characteristic parameters of the battery system and the health characteristics of one or more battery cells or modules output from the model (i.e., at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset), and its output can be at least one of the corresponding remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life, and thus the health state of the battery system can be evaluated based on this.

[0071] Combining step 302 and step 304, in some embodiments, the performance evaluation model may include a first sub-model and a second sub-model. The first sub-model is as described in step 302. By inputting the battery characteristic parameters of the battery system, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of one or more battery cells or modules included in the system are obtained as the output of the first sub-model, and further the health state of one or more battery cells or modules is evaluated. The second sub-model is as described in step 304. After obtaining the health state of the battery cell or module, it can be used as an input together with the battery characteristic parameters of the battery system to obtain the health state of the battery system (for example, at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life) as the output of the second sub-model. Thus, the health state of the battery system and the health state of the battery cell or module can be obtained through the performance evaluation model.

[0072] Figure 4 It is an exemplary flowchart of a performance evaluation model training method according to some embodiments of the present specification. In some embodiments, as shown in the figure, process 400 includes step 402 and step 404. The following is a detailed description of process 400.

[0073] Step 402, obtain training samples and an initial model.

[0074] The initial model can be an original machine learning model, that is, the performance evaluation model before training. It can be understood that the parameters in the initial model are all original parameters, and the initial model can be trained one or more times to update the model parameters to obtain a trained model (for example, the performance evaluation model in step 202).

[0075] The training samples can be training data for training the initial model. In some embodiments, the training samples include labels, which are used as reference data for model training.

[0076] It can be understood that the training samples and the labels therein are associated with the input and output of the performance evaluation model. In some embodiments, the training samples can be the battery characteristic parameters of multiple sample battery systems, and the labels in the samples can include the battery performance parameters of the sample battery systems, for example, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery modules or cells in the sample battery systems, and / or the remaining capacity of the sample battery systems, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life.

[0077] In some embodiments, the training samples may include: the initial charging voltage, charging process characteristic voltage, charging cut-off voltage, initial charging temperature, charging process temperature weight, charging current, cumulative charge-discharge amount, cumulative charge-discharge times of a sample battery system during multiple cycles of charge and discharge experiments, the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of the sample battery system, and the remaining capacity, capacity offset, internal resistance, internal resistance offset of each cell or module of the sample battery system.

[0078] It can be understood that the labels in the training samples are the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of the sample battery system, and the remaining capacity, capacity offset, internal resistance, internal resistance offset of each cell or module in the sample battery system, etc.

[0079] It can be understood that by conducting multiple cycles of charge and discharge experiments on multiple sample battery systems, that is, charging the sample battery system and then discharging the battery system, and when discharging to a certain threshold, conducting a second charge and discharge on the battery system. During each charging, the charging characteristics in the battery system are measured to obtain the above-mentioned initial charging voltage, charging process characteristic voltage, charging cut-off voltage, initial charging temperature, charging process temperature weight, charging current, cumulative charge-discharge amount, cumulative charge-discharge times as training samples.

[0080] Furthermore, during each charge and discharge, the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of the sample battery system, and the remaining capacity, capacity offset, internal resistance, internal resistance offset of each cell or module of the sample battery system, etc. are measured, and their measurement results are used as the labels of the training samples.

[0081] In some other embodiments, the training samples may include the initial charging voltage, charging process characteristic voltage, charging cut-off voltage, initial charging temperature, charging process temperature weight, charging current, cumulative charge-discharge amount, cumulative charge-discharge times, driving mileage of a specific type of battery system during its operation, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of the specific type of battery system.

[0082] It can be understood that the labels in the training samples are at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of the specific type of battery system.

[0083] Among them, a specific type of battery system can be a type of battery system specified according to actual needs. For example, it can be a battery system with the most stable battery performance currently on the market; or, it can be a type of battery system with the largest number of units in use to ensure obtaining sufficient training samples. During the charging and discharging process of this battery system through a charging device (such as a charging pile), the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, cumulative charge and discharge times, driving mileage, etc. of this battery system can be obtained, and they are stored through a network, for example, stored in a database through Network 120.

[0084] Furthermore, during the process of putting a specific type of battery system into the market, while obtaining the above-mentioned charging characteristics, the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life of this battery system will also be determined through a charging device or other online platforms as the labels of the samples.

[0085] Step 404: Train the initial model based on the training samples to obtain the performance evaluation model.

[0086] In some embodiments, the initial model can be trained based on the training samples in one or more ways to obtain a performance evaluation model. For example, training can be performed based on the gradient descent method.

[0087] In some embodiments, the initial model can be trained multiple times based on multiple training samples to continuously update the model parameters of the initial model. For example, the battery characteristic parameters in the training samples can be input into the initial model, the initial model outputs a prediction result, the prediction result is compared with the label data to determine the loss function, and the parameters of the initial model are updated according to the loss function. When the preset conditions are met, the training ends, and the trained initial model is used as the performance evaluation model. In some embodiments, the preset conditions can be model convergence (for example, the loss function value is less than a threshold), or when the number of training times reaches a preset threshold (for example, the number of training times reaches 5000 times), or when the model parameters reach a preset threshold.

[0088] In some embodiments, during the actual use process of the performance evaluation model, the performance evaluation model can be continuously optimized based on new training samples so that the performance evaluation model can be continuously optimized to obtain more accurate evaluation results.

[0089] As an example, for the training process of the first sub-model of the performance evaluation model, the battery characteristic parameters in the training samples can be input into the first initial sub-model. The first initial sub-model outputs at least one of the estimated remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cell or module. The estimated result is compared with the label data (for example, at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cell or module in the training samples), and the loss function is determined. The parameters of the first initial sub-model are updated according to the loss function. As another example, for the training process of the second sub-model of the performance evaluation model, the battery characteristic parameters in the training samples and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cell or module can be input into the second initial sub-model. The second initial sub-model outputs at least one of the estimated remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the battery system. The estimated result is compared with the label data (for example, at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the sample battery system in the training samples), and the loss function is determined. The parameters of the second initial sub-model are updated according to the loss function.

[0090] In some embodiments, the training samples for training the first sub-model and the second sub-model can be the same set of training samples or different sets of training samples. For example, the training samples for training the first sub-model may include at least one of the battery characteristic parameters of the first set of sample battery systems and the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules; the training samples for training the second sub-model may include at least one of the battery characteristic parameters of the second set of sample battery systems, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the battery system. Again, for example, the training samples may include at least one of the battery characteristic parameters of the third set of sample battery systems, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the battery system. The training samples can be used for training the first sub-model and the second sub-model. In the training of the first sub-model, the battery characteristic parameters of the third set of sample battery systems are used as training data, and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules is used as label data; in the training of the second sub-model, the battery characteristic parameters of the third set of sample battery systems and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules are used as training data, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the third set of sample battery systems is used as label data. In some embodiments, the first sub-model and the second sub-model can be jointly trained. For example, the training samples may include at least one of the battery characteristic parameters of the sample battery systems, the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the battery system. The training samples can be used for training the first sub-model and the second sub-model. In the training of the first sub-model, the battery characteristic parameters of the sample battery systems are used as training data, and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules is used as label data; in the training of the second sub-model, the battery characteristic parameters of the sample battery systems and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the battery cells or modules output by the first sub-model during the training process are used as training data, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, remaining life, etc. of the sample battery systems is used as label data.The parameters of the first sub-model and the second sub-model can be updated according to the loss function during the training process of the second sub-model.

[0091] Figure 5 It is a block diagram of a battery system performance evaluation system shown according to some embodiments of this specification.

[0092] Such as Figure 5 As shown, the battery system performance evaluation system 500 may include a parameter acquisition module 510, a model acquisition module 520, and a performance evaluation module 530. The battery system includes one or more battery modules, and each of the battery modules includes one or more single cells.

[0093] The parameter acquisition module 510 can be used to acquire the battery characteristic parameters of the battery system, and the battery characteristic parameters represent the charge and discharge characteristics of the battery system.

[0094] The model acquisition module 520 can be used to acquire a performance evaluation model.

[0095] The performance evaluation module 530 can be used to evaluate the battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters, and the battery performance parameters represent the health status of the one or more battery modules or single cells of the battery system.

[0096] In some embodiments, the battery characteristic parameters include at least one of a charging start voltage, a charging process characteristic voltage, a charging cut-off voltage, a charging start temperature, a charging process temperature weight, a charging current, a cumulative charge and discharge amount, a cumulative charge and discharge times, and a driving mileage.

[0097] In some embodiments, the battery performance parameters include at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules.

[0098] In some embodiments, the battery performance parameters further include at least one of the remaining capacity of the battery system, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life.

[0099] In some embodiments, evaluating the battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters includes: determining at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules according to the performance evaluation model and the battery characteristic parameters; determining at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the battery system according to the performance evaluation model, the battery characteristic parameters, and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of the one or more battery cells or modules.

[0100] In some embodiments, the system further includes: a sending module 540, configured to send a warning prompt based on the battery performance parameters.

[0101] In some embodiments, the warning prompt includes the type of warning prompt, the warning level, and the location of the abnormal battery module or single battery.

[0102] In some embodiments, obtaining the performance evaluation model includes: obtaining training samples and an initial model; training the initial model based on the training samples to obtain the performance evaluation model.

[0103] In some embodiments, the training samples include: the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, cumulative charge and discharge times, the remaining capacity of the battery system, and the remaining capacity, capacity offset, internal resistance, and internal resistance offset of each cell or module of the sample battery system in multiple cycle charge and discharge experiments of the sample battery system.

[0104] In some embodiments, the training samples include: the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, cumulative charge and discharge times, and the remaining capacity of the specific type of battery system during the operation of the specific type of battery system.

[0105] It should be understood, Figure 5The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer-executable instructions and / or included in processor control code. For example, such code is provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the above hardware circuits and software (e.g., firmware).

[0106] It should be noted that the above description of the battery performance evaluation system and its modules is only for convenience of description and does not limit this specification within the scope of the cited embodiments. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it to other modules. For example, in some embodiments, for example, Figure 5 the parameter acquisition module 510, the model acquisition module 520, the performance evaluation module 530, and the sending module 540 disclosed in [reference] can be different modules in a system, or a single module can implement the functions of two or more of the above modules. For example, the parameter acquisition module 510 and the model acquisition module 520 can be two modules, or a single module can have both the parameter acquisition function and the model acquisition function. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0107] Figure 6 is a schematic diagram of the application scenario of the performance evaluation model training system according to some embodiments of this specification.

[0108] The performance evaluation model training system 600 can train a performance evaluation model by implementing the methods and / or processes disclosed in this specification.

[0109] As Figure 6As shown, the system 600 may include a first computing system 620 and a second computing system 630. The first computing system 620 and the second computing system 630 may be the same or different. The first computing system 620 and the second computing system 630 may be the same computing system or different computing systems.

[0110] The first computing system 620 and the second computing system 630 refer to systems with computing capabilities, which may include various computers, such as servers and personal computers, or may also be computing platforms composed of multiple computers connected in various structures.

[0111] The first computing system 620 and the second computing system 630 may include processors that can execute program instructions. The processors may include various common general-purpose central processing units (CPUs), graphics processing units (GPUs), microprocessors, application-specific integrated circuits (ASICs), or other types of integrated circuits. The first computing system 620 and the second computing system 630 may include storage media that can store instructions or data. The storage media may include mass storage, removable storage, volatile read / write memory, read-only memory (ROM), etc., or any combination thereof. The first computing system 620 and the second computing system 630 may also include a network for internal and external connections. The network may be any one or more of a wired network or a wireless network.

[0112] The first computing system 620 may obtain sample data 610 (e.g., the training samples in 402), and the sample data 610 may be data for training a model. A model 622 may be trained in the first computing system 620, and the parameters of the model 622 may be updated to obtain a trained model 632. By way of example, the model 622 may be an initial model (e.g., the initial model in 402), and the model 632 may be a performance evaluation model.

[0113] The second computing system 630 may obtain data 640 (e.g., the battery characteristic parameters of the battery system in 202) and the model 632 (e.g., the performance evaluation model in 204). The second computing system 630 generates a result 650 (e.g., the battery performance parameters of the battery system in 206) based on the model 632. In some embodiments, the server 110 may be implemented based on the second computing system 630.

[0114] A model (e.g., model 622 or / and model 632) may refer to a collection of several methods performed based on a processing device. These methods may include a large number of parameters. When executing the model, the parameters used may be pre-set or can be dynamically adjusted. Some parameters can be obtained through training methods, and some parameters can be obtained during the execution process. For specific descriptions of the model involved in this specification, refer to the relevant parts of this specification. The beneficial effects that the embodiments of this specification may bring include, but are not limited to:

[0115] (1) Use training samples to train a machine learning model to obtain a performance evaluation model, and evaluate the health status of the battery system through this model, so as to obtain the health status of the battery system more accurately.

[0116] (2) Among them, the training samples include data of multiple single cells or modules in the battery system and labels of their health status. Through the trained performance evaluation model, the health of multiple battery cells or modules in the battery system can be further evaluated, so that during subsequent maintenance, it is more targeted and the maintenance efficiency is higher.

[0117] (3) The training samples are obtained by performing multiple cycle charging experiments on the sample battery system and putting a specific type of battery system into the market. Thus, the training samples are more authentic and accurate, and have stronger utilization value. So that the evaluation of the trained performance evaluation model is more accurate and in line with the actual situation.

[0118] It should be noted that the beneficial effects that different embodiments may produce are different. In different embodiments, the beneficial effects that may be produced can be a combination of any one or several of the above, or any other beneficial effects that may be obtained.

[0119] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0120] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0121] In addition, those skilled in the art can understand that various aspects of this specification can be illustrated and described by several patentable types or situations, including any new and useful process, machine, product, or composition of matter, or any new and useful improvement thereof. Accordingly, various aspects of this specification can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can all be referred to as "data block", "module", "engine", "unit", "component", or "system". In addition, various aspects of this specification may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0122] A computer storage medium may contain a propagated data signal containing computer program code, for example, on a baseband or as part of a carrier wave. This propagated signal may have various forms of manifestation, including electromagnetic form, optical form, etc., or a suitable combination of forms. A computer storage medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to achieve communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0123] The computer program codes required for the operations of various parts of this specification can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. This program code can run entirely on the user's computer, or run as an independent software package on the user's computer, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0124] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on an existing server or mobile device.

[0125] Similarly, it should be noted that, in order to simplify the expression of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, multiple features are sometimes merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the individual embodiments disclosed above.

[0126] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of embodiments are, in some examples, modified by the modifiers "about", "approximately" or "substantially". Unless otherwise specified, "about", "approximately" or "substantially" indicate that the said numbers are allowed to have a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are made as precise as possible within the feasible range.

[0127] For each patent, patent application, patent application publication and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and also except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0128] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for evaluating the performance of a battery system, the battery system comprising one or more battery modules, each of the battery modules being obtained by connecting in series a plurality of single cells and / or a plurality of battery modules, and each of the battery modules being obtained by connecting in parallel a plurality of single cells, characterized in that, The method includes: Obtaining battery characteristic parameters of the battery system, where the battery characteristic parameters represent the charge and discharge characteristics of the battery system; Obtaining a performance evaluation model, where the performance evaluation model is a trained machine learning model, and the performance evaluation model includes a first sub-model and a second sub-model; Evaluating battery performance parameters of the battery system according to the performance evaluation model and the battery characteristic parameters, including: Inputting the battery characteristic parameters of the battery system into the first sub-model to obtain at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of each battery cell or battery module as the output of the first sub-model to evaluate the health state of each battery cell or module; Inputting the output of the first sub-model and the battery characteristic parameters of the battery system into the second sub-model to obtain at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the battery system as the output of the second sub-model to evaluate the health state of the entire battery system; The battery performance parameters include at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of each battery cell or battery module, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the battery system.

2. The method according to claim 1, characterized in that, The battery characteristic parameters include at least one of the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, cumulative charge and discharge times, and driving mileage.

3. The method according to claim 1, wherein The method further includes: sending a warning prompt based on the battery performance parameters.

4. The method according to claim 3, characterized in that, The warning prompt includes the warning type, warning level, and the location of the abnormal battery module or single battery cell.

5. The method according to claim 1, characterized in that The performance evaluation model includes a machine learning model obtained by at least one of neural network, support vector machine, transfer learning, outlier algorithm, clustering analysis, and matching of feature similarities.

6. The method according to claim 2, wherein The method for obtaining the performance evaluation model includes: Obtaining training samples and an initial model; Training the initial model based on the training samples to obtain the performance evaluation model.

7. The method according to claim 6, wherein The training samples include: At least one of the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, and cumulative charge and discharge times of the sample battery system in multiple cyclic charge and discharge experiments, at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the battery system, and at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of each single cell or module of the sample battery system.

8. The method according to claim 6, characterized in that The training samples include: At least one of the charging start voltage, charging process characteristic voltage, charging cut-off voltage, charging start temperature, charging process temperature weight, charging current, cumulative charge and discharge amount, cumulative charge and discharge times, and driving mileage of a specific type of battery system during operation, and at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the specific type of battery system.

9. A battery system performance evaluation system, wherein the battery system includes one or more battery modules, each of the battery modules is obtained by connecting in series a plurality of single cells and / or a plurality of battery modules, and each of the battery modules is obtained by connecting in parallel a plurality of single cells, characterized in that, The battery system performance evaluation system includes: A parameter acquisition module for acquiring battery characteristic parameters of the battery system, where the battery characteristic parameters represent the charging characteristics of the battery system; A model acquisition module for acquiring a performance evaluation model, where the performance evaluation model is a trained machine learning model, and the performance evaluation model includes a first sub-model and a second sub-model; A performance evaluation module for Inputting the battery characteristic parameters of the battery system into the first sub-model to obtain at least one of the remaining capacity, capacity offset, internal resistance, and internal resistance offset of each battery cell or battery module as the output of the first sub-model to evaluate the health status of each battery cell or module; Inputting the output of the first sub-model and the battery characteristic parameters of the battery system into the second sub-model to obtain at least one of the remaining capacity, system capacity offset, system pressure difference, self-discharge and consistency, internal resistance consistency, temperature state, and remaining life of the battery system as the output of the second sub-model to evaluate the health status of the entire battery system.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1-8 is implemented.

11. A battery system performance evaluation system, including at least one storage medium and at least one processor, where the at least one storage medium is used to store computer instructions; the at least one processor is used to execute the computer instructions to implement the method according to any one of claims 1-8.

Images