Battery management method, device, equipment and storage medium based on multi-dimensional parameters

Abstract

The present application provides a battery management method, apparatus, device, and storage medium based on multidimensional parameters. The multidimensional parameter-based battery management method includes: obtaining multidimensional parameters collected in real time by multiple sets of sensors installed in a battery pack; inputting the multidimensional parameters into an integrated multi-source state assessment model for analysis to determine the multidimensional comprehensive state of each battery cell; and determining to coordinately adjust each battery cell in the battery pack based on the multidimensional comprehensive state of each battery cell. By analyzing the multidimensional data of the battery cells, the safety of each battery cell is improved, aiming to increase the service life of the battery pack.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery management, and in particular relates to a battery management method, device, equipment and storage medium based on multi-dimensional parameters. Background Art

[0002] Traditional BMS (Battery Management Systems) typically rely on single parameters (such as voltage and temperature) or simple models to assess the state of a battery cell. These systems fail to fully reflect the state of health (SOH) and safety (SOS) of the battery cell, potentially overlooking early signs of aging or hidden faults. Furthermore, manufacturing variations and uneven aging of the battery cells within a battery pack can lead to inconsistent parameters, accelerating capacity decay and increasing the risk of thermal runaway, compromising battery pack safety. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a battery management method, apparatus, device and storage medium based on multi-dimensional parameters, which improves the safety of each battery cell by analyzing multi-dimensional data of the battery cell, aiming to increase the service life of the battery pack.

[0004] The present invention provides a multi-dimensional parameter-based battery management method, including:

[0005] Obtain multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack;

[0006] Inputting the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell;

[0007] Based on the multi-dimensional comprehensive status of each battery cell, determine the coordinated adjustment of each battery cell in the battery pack.

[0008] In one embodiment, the multi-source state assessment model includes: a dual-channel estimation layer, a weighted fusion strategy layer, and an output multi-dimensional state layer.

[0009] In one embodiment, the dual-channel estimation layer includes a filtering channel and a learning channel;

[0010] The inputting of the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell includes:

[0011] After the multi-dimensional parameters are input into the multi-source state assessment model, the state of the battery cell at the next moment is predicted in the filtering channel using the state transfer equation and the observation equation, the predicted battery cell state is updated with the multi-dimensional parameters measured by the sensor at the next moment, and a real-time dynamic prediction result of the state of each battery cell is output;

[0012] In the learning channel, the multi-dimensional parameters are analyzed by a deep feedforward neural network to output the dynamic change results of the state of each battery cell in the short term;

[0013] In the weighted fusion strategy layer, the real-time dynamic prediction result is weightedly fused with the dynamic change result of the battery cell state in the short term to obtain a multi-dimensional comprehensive state prediction result, and the output layer outputs the multi-dimensional comprehensive state.

[0014] In one embodiment, the weighted fusion strategy layer includes a set credibility index for indicating the relative credibility of the filtering channel and the learning channel. The weighted fusion strategy layer performs a weighted fusion process of real-time dynamic prediction results and short-term dynamic change results, which is expressed as follows:

[0015] ;

[0016] in, is the credibility indicator, is the filter channel output; is the learning channel output, It is the result of weighted fusion of the filtering channel output and the learning channel output, which is a multi-dimensional comprehensive state.

[0017] In one embodiment, determining to coordinately adjust each battery cell in the battery pack based on the multi-dimensional comprehensive status of each battery cell includes:

[0018] The multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function for analysis, and the global optimum is achieved in the local adjustment of each battery cell.

[0019] In one embodiment, the multi-objective collaborative optimization function is expressed as:

[0020]

[0021] in, , , is the weight coefficient, which needs to be dynamically adjusted according to the security level. is the health level of the i-th battery cell, is the safety level of the i-th battery cell; The charging and discharging power adjustment value of the i-th battery cell is used to punish excessive adjustments and prevent frequent fluctuations.

[0022] In one embodiment, the multi-dimensional comprehensive state of each battery cell is input into a multi-objective collaborative optimization function for analysis to obtain that each battery cell achieves global optimization in local adjustment, including:

[0023] After the multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function, each battery cell is taken as the target and the charge and discharge power adjustment amount of each battery cell is used as the adjustment strategy. An analysis is performed based on the distributed optimization rules to maximize the multi-objective collaborative optimization function, and all corresponding battery cells reach the global optimum in local adjustments.

[0024] A second aspect of an embodiment of the present application provides a battery management device based on multi-dimensional parameters, including:

[0025] An acquisition module is used to obtain multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack;

[0026] An analysis module is used to input the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell;

[0027] The determination module is used to determine the coordinated adjustment of each battery cell in the battery pack based on the multi-dimensional comprehensive status of each battery cell.

[0028] In one embodiment, the multi-source state assessment model includes: a dual-channel estimation layer, a weighted fusion strategy layer, and an output multi-dimensional state layer.

[0029] In one embodiment, the dual-channel estimation layer includes a filtering channel and a learning channel;

[0030] The analysis module includes:

[0031] A first output unit is configured to input the multi-dimensional parameters into the multi-source state assessment model, predict the state of the battery cell at the next moment using the state transfer equation and the observation equation in the filtering channel, update the predicted battery cell state with the multi-dimensional parameters measured by the sensor at the next moment, and output a real-time dynamic prediction result of the state of each battery cell;

[0032] A second output unit is configured to analyze the multidimensional parameters in the learning channel through a deep feedforward neural network and output a short-term dynamic change result of the state of each battery cell;

[0033] The fusion unit is used to perform weighted fusion on the real-time dynamic prediction result and the dynamic change result of the cell state in the short term in the weighted fusion strategy layer to obtain a multi-dimensional comprehensive state prediction result, and the output layer outputs the multi-dimensional comprehensive state.

[0034] In one embodiment, the weighted fusion strategy layer includes a set credibility index for indicating the relative credibility of the filtering channel and the learning channel. The weighted fusion strategy layer performs a weighted fusion process of real-time dynamic prediction results and short-term dynamic change results, which is expressed as follows:

[0035] ;

[0036] in, is the credibility indicator, is the filter channel output; is the learning channel output, It is the result of weighted fusion of the filtering channel output and the learning channel output, which is a multi-dimensional comprehensive state.

[0037] In one embodiment, the determining module is specifically configured to:

[0038] The multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function for analysis, and the global optimum is achieved in the local adjustment of each battery cell.

[0039] In one embodiment, the multi-objective collaborative optimization function is expressed as:

[0040]

[0041] in, , , is the weight coefficient, which needs to be dynamically adjusted according to the security level. is the health level of the i-th battery cell, is the safety level of the i-th battery cell; The charging and discharging power adjustment value of the i-th battery cell is used to punish excessive adjustments and prevent frequent fluctuations.

[0042] In one embodiment, the determining module is specifically configured to:

[0043] After the multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function, each battery cell is taken as the target and the charge and discharge power adjustment amount of each battery cell is used as the adjustment strategy. An analysis is performed based on the distributed optimization rules to maximize the multi-objective collaborative optimization function, and all corresponding battery cells reach the global optimum in local adjustments.

[0044] A third aspect of an embodiment of the present application provides a battery management device based on multi-dimensional parameters, including: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the steps of the method described in the first aspect above are implemented.

[0045] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0046] The beneficial effects of the embodiments of the present application include obtaining multidimensional parameters collected in real time by multiple sets of sensors installed in the battery pack; inputting these multidimensional parameters into an integrated multi-source state assessment model for analysis to determine the multidimensional comprehensive state of each battery cell; and determining the coordinated adjustment of each battery cell in the battery pack based on the multidimensional comprehensive state of each battery cell. By analyzing the multidimensional data of the battery cells, the safety of each battery cell is improved, aiming to extend the service life of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A schematic diagram of the implementation flow of a multi-dimensional parameter-based battery management method provided in one embodiment of the present application;

[0049] Figure 2 A schematic diagram of a battery management device based on multi-dimensional parameters provided in one embodiment of the present application;

[0050] Figure 3 A schematic diagram of a battery management device based on multi-dimensional parameters provided in one embodiment of the present application. DETAILED DESCRIPTION

[0051] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0053] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0054] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0055] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0056] In the description of the embodiments of the present application, the term "multi-frame" refers to two or more (including two).

[0057] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0058] An embodiment of the present invention provides a battery management method based on multidimensional parameters. By obtaining multidimensional parameters collected in real time by multiple groups of sensors installed in the battery pack, the multidimensional parameters are input into an integrated multi-source state assessment model for analysis to determine the multidimensional comprehensive state of each battery cell. Based on the multidimensional comprehensive state of each battery cell, a coordinated adjustment strategy for the battery pack is determined, aiming to solve the problem of low data storage efficiency in existing high-capacity energy storage wireless systems.

[0059] See also Figure 1 As shown, Figure 1 The battery management method based on multi-dimensional parameters provided in this embodiment of the present application is implemented by a battery management system based on multi-dimensional parameters. Figure 1 Description in . Figure 1 It can be seen that the battery management method based on multi-dimensional parameters provided in the embodiment of the present application includes the following steps S110 to S130. The details are as follows:

[0060] S110: Acquire multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack.

[0061] The multi-dimensional parameters include the voltage of each battery cell and the battery pack voltage, the battery pack charge and discharge current, the temperature of each battery cell and the ambient temperature.

[0062] Specifically, the battery voltage sensor is used to collect the voltage of each battery cell and the voltage of the entire group to ensure accurate data sampling and that the voltage sampling frequency meets real-time monitoring requirements (such as more than 10 samples per second).

[0063] The battery current sensor is used to measure the charge and discharge current of the battery pack, enabling real-time monitoring of the current size and direction.

[0064] By placing temperature sensors on the surface of battery cells and key positions of battery packs, the temperature of each battery cell and the environment are collected to achieve temperature difference monitoring.

[0065] All sensors transmit the collected data to the BMS main control unit through a high-speed, low-latency data bus to ensure the timeliness and integrity of the data.

[0066] S120: Inputting the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell.

[0067] A multi-source state assessment model includes a dual-channel estimation layer, a weighted fusion strategy layer, and a multi-dimensional state output layer. The dual-channel estimation layer includes a filtering channel and a learning channel. The filtering channel is used to estimate the state of battery cells using real-time physical estimation rules that provide strong robustness and interpretability.

[0068] Exemplarily, the filtering channel includes a state-space model. This model sets battery state variables (such as state of charge and state of health) and constructs state transition equations and observation equations based on a battery dynamic model (such as an equivalent circuit model (RC) or a dual-RC model). After multidimensional parameters are input into the multi-source state assessment model, the filtering channel uses the state transition equations and observation equations to predict the cell state at the next moment. The predicted cell state is then updated with the multidimensional parameters measured by the sensor at the next moment, outputting a real-time dynamic prediction of each cell state. This allows for dynamic state estimation of multidimensional parameters such as voltage, current, and temperature for each cell, improving data stability and accuracy.

[0069] Specifically, the state transfer equation is expressed as: ;in, represents the state transition function, represents the control input vector, represents the system noise, which obeys the normal distribution, Represents the cell state vector at the current moment, Represents the predicted state of the battery cell at the next moment. This equation describes the state of the battery cell at time t , how to control input and process noise Under the influence, it evolves to the state of the battery cell at the next moment t+1 .

[0070] The observation equation is expressed as: ;in, represents the observation function, represents the measurement noise, Represents the observation value vector measured by the sensor at the current moment. This equation describes how to map it to a physical quantity that can be measured by the sensor through the observation function.

[0071] After the multi-dimensional parameters are input into the multi-source state assessment model, in the filtering channel, the state of the battery cell at the next moment is first predicted based on the state transfer equation, and then the sensor observation value at the current moment is compared with the predicted value. Under the guidance of the observation equation, the prediction result is updated and corrected, and the real-time dynamic estimation value of the state of each battery cell is output.

[0072] The learning channel can provide trend-oriented compensation prediction results. Exemplarily, the learning channel includes a battery performance evolution trend model built using historical operating data. This model can capture the complex, nonlinear patterns of cell state changes. Specifically, the model includes a deep feedforward neural network that focuses on short-term state estimation. The inputs to this deep feedforward neural network include collected multidimensional parameters, and the outputs include short-term dynamic changes in cell state (such as capacity decay rate or internal resistance increase). After inputting these multidimensional parameters into the multi-source state assessment model, the deep feedforward neural network analyzes them and outputs short-term dynamic changes in each cell state. The network model, trained with extensive historical operating data, learns the performance decay patterns, fault signs, and dynamic changes in cell state under different operating conditions, predicting short-term dynamic changes in cell state and performance anomaly trends.

[0073] The weighted fusion strategy layer is used to perform weighted fusion on the real-time dynamic prediction results output by the dual-channel estimation layer and the dynamic change results of the cell state in the short term to obtain a multi-dimensional comprehensive state prediction result, which is then output by the output layer.

[0074] Exemplarily, the weighted fusion strategy layer includes a set credibility index for indicating the relative trust between the filtering channel and the learning channel; by introducing the set credibility index into the weighted fusion strategy layer, the credibility distribution between the filtering channel and the learning channel is dynamically adjusted.

[0075] The process of weighted fusion of real-time dynamic prediction results and short-term dynamic change results is expressed as:

[0076] ;

[0077] in, , is a credibility indicator, which can be dynamically learned by the model and represents the degree of trust in the filtering channel; It is the real-time dynamic prediction result output by the filtering channel; is the short-term dynamic change result of the learning channel output, The result of weighted fusion of the filter channel output and the learning channel output is a multi-dimensional integrated state. This is achieved by dynamically balancing the real-time estimation results of the filter channel output with the predicted results of the learning channel output.

[0078] S130: Based on the multi-dimensional comprehensive status of each battery cell, determine to coordinately adjust each battery cell in the battery pack.

[0079] Specifically, the predicted multi-dimensional comprehensive status of each battery cell is mapped to the health level and safety level of each battery cell.

[0080] Exemplarily, based on the multi-dimensional comprehensive state of each battery cell, it is determined to coordinately adjust each battery cell in the battery pack, including: inputting the multi-dimensional comprehensive state of each battery cell into a multi-objective collaborative optimization function for analysis, and obtaining the global optimum of each battery cell in local adjustment.

[0081] Specifically, the multi-objective collaborative optimization function is expressed as:

[0082]

[0083] in, , , is the weight coefficient, which needs to be dynamically adjusted according to the security level. is the health level of the i-th battery cell, is the safety level of the i-th battery cell; The charging and discharging power adjustment value of the i-th battery cell is used to punish excessive adjustments and prevent frequent fluctuations.

[0084] Specifically, after inputting the multi-dimensional comprehensive state of each battery cell into a multi-objective collaborative optimization function, the distributed optimization rule analyzes each battery cell as a target and the charge and discharge power adjustment amount of each battery cell as the adjustment strategy, maximizing the multi-objective collaborative optimization function. The corresponding battery cells achieve a global optimum through local adjustments, ensuring that no cells are overloaded. This process achieves comprehensive, real-time adjustment of the battery pack state, ensuring the safe and stable operation of each battery cell.

[0085] From the above analysis, it can be seen that the multi-dimensional parameter-based battery management method provided in the embodiment of the present application includes: obtaining multi-dimensional parameters collected in real time by multiple groups of sensors installed in the battery pack; inputting the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell; and based on the multi-dimensional comprehensive state of each battery cell, determining to coordinately adjust each battery cell in the battery pack. By analyzing the multi-dimensional data of the battery cell, the safety of each battery cell is improved, aiming to increase the service life of the battery pack.

[0086] See Figure 2 , Figure 2 Schematic diagram of a battery management device based on multi-dimensional parameters provided in one embodiment of the present application. The battery management device based on multi-dimensional parameters includes modules or units for executing Figure 1 Each step in the corresponding embodiment. Please refer to Figure 1 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 2 The battery management device 200 based on multi-dimensional parameters includes:

[0087] An acquisition module 210 is used to acquire multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack;

[0088] An analysis module 220 is configured to input the multi-dimensional parameters into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell;

[0089] The determination module 230 is configured to determine to coordinately adjust the battery cells in the battery pack based on the multi-dimensional comprehensive status of the battery cells.

[0090] In one embodiment, the multi-source state assessment model includes: a dual-channel estimation layer, a weighted fusion strategy layer, and an output multi-dimensional state layer.

[0091] In one embodiment, the dual-channel estimation layer includes a filtering channel and a learning channel;

[0092] The analysis module 220 includes:

[0093] A first output unit is configured to input the multi-dimensional parameters into the multi-source state assessment model, predict the state of the battery cell at the next moment using the state transfer equation and the observation equation in the filtering channel, update the predicted battery cell state with the multi-dimensional parameters measured by the sensor at the next moment, and output a real-time dynamic prediction result of the state of each battery cell;

[0094] A second output unit is configured to analyze the multidimensional parameters in the learning channel through a deep feedforward neural network and output a short-term dynamic change result of the state of each battery cell;

[0095] The fusion unit is used to perform weighted fusion on the real-time dynamic prediction result and the dynamic change result of the cell state in the short term in the weighted fusion strategy layer to obtain a multi-dimensional comprehensive state prediction result, and the output layer outputs the multi-dimensional comprehensive state.

[0096] In one embodiment, the weighted fusion strategy layer includes a set credibility index for indicating the relative credibility of the filtering channel and the learning channel. The weighted fusion strategy layer performs a weighted fusion process of real-time dynamic prediction results and short-term dynamic change results, which is expressed as follows:

[0097] ;

[0098] in, is the credibility indicator, is the filter channel output; is the learning channel output, It is the result of weighted fusion of the filtering channel output and the learning channel output, which is a multi-dimensional comprehensive state.

[0099] In one embodiment, the determining module 230 is specifically configured to:

[0100] The multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function for analysis, and the global optimum is achieved in the local adjustment of each battery cell.

[0101] In one embodiment, the multi-objective collaborative optimization function is expressed as:

[0102]

[0103] in, , , is the weight coefficient, which needs to be dynamically adjusted according to the security level. is the health level of the i-th battery cell, is the safety level of the i-th battery cell; The charging and discharging power adjustment value of the i-th battery cell is used to punish excessive adjustments and prevent frequent fluctuations.

[0104] In one embodiment, the determining module 230 is specifically configured to:

[0105] After the multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function, each battery cell is taken as the target and the charge and discharge power adjustment amount of each battery cell is used as the adjustment strategy. An analysis is performed based on the distributed optimization rules to maximize the multi-objective collaborative optimization function, and all corresponding battery cells reach the global optimum in local adjustments.

[0106] See Figure 3 , Figure 3 A schematic diagram of a battery management device based on multi-dimensional parameters provided by an embodiment of the present application. Figure 3 It can be seen that the battery management device 300 based on multi-dimensional parameters includes: a processor 310, a memory 320, and a computer program 330 stored in the memory 320 and executable on the processor 310; when the processor 310 executes the computer program 330, the steps in the above-mentioned embodiments of the battery management method based on multi-dimensional parameters are implemented, such as Figure 1 Alternatively, when the processor 310 executes the computer program 330, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 2 The functions of the modules 210 to 230 are shown.

[0107] Exemplarily, computer program 330 may be divided into one or more modules / units, one or more of which are stored in memory 320 and executed by processor 310 to implement the present application. One or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 330 in a multi-dimensional parameter-based battery management device. For example, computer program 330 may be divided into an acquisition module, an analysis module, and a determination module.

[0108] The multi-dimensional parameter-based battery management device provided in this embodiment may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 3 This is only an example of a battery management device based on multi-dimensional parameters and does not constitute a limitation of the battery management device based on multi-dimensional parameters. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the battery management device based on multi-dimensional parameters may also include input and output devices, network access devices, buses, etc.

[0109] The processor 310 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0110] The memory 320 can be an internal storage unit of the multi-dimensional parameter-based battery management device, such as a hard drive or memory of the multi-dimensional parameter-based battery management device. The memory 320 can also be an external storage device of the multi-dimensional parameter-based battery management device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the multi-dimensional parameter-based battery management device can include both the internal storage unit and an external storage device. The memory 320 is used to store computer programs and other programs and data required by the multi-dimensional parameter-based battery management device. The memory 320 can also be used to temporarily store data that has been output or is about to be output.

[0111] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0112] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0113] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0114] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0116] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0117] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0118] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0120] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A battery management method based on multi-dimensional parameters, characterized in that: include: Obtain multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack; The multi-dimensional parameters are input into an integrated multi-source state assessment model for analysis to determine the multi-dimensional comprehensive state of each battery cell, wherein the multi-source state assessment model includes: a dual-channel estimation layer, a weighted fusion strategy layer, and an output multi-dimensional state layer; the dual-channel estimation layer includes a filtering channel and a learning channel; After the multi-dimensional parameters are input into the multi-source state assessment model, the state of the battery cell at the next moment is predicted by the state transfer equation and the observation equation in the filtering channel, the predicted battery cell state and the multi-dimensional parameters measured by the sensor at the next moment are updated, and the real-time dynamic prediction result of each battery cell state is output; in the learning channel, the multi-dimensional parameters are analyzed by a deep feedforward neural network, and the dynamic change result of each battery cell state in the short term is output; in the weighted fusion strategy layer, the real-time dynamic prediction result and the dynamic change result of the battery cell state in the short term are weightedly fused to obtain a multi-dimensional comprehensive state prediction result, and the multi-dimensional comprehensive state is output by the output layer; The multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function for analysis, and the global optimum is achieved in the local adjustment of each battery cell; the multi-objective collaborative optimization function is expressed as: U i =α·H i +β·S i -γ·|ΔP i | Among them, α, β, and γ are weight coefficients, which need to be dynamically adjusted according to the security level. i is the health level of the ith battery cell, S i is the safety level of the i-th battery cell; |ΔP i | is the charge and discharge power adjustment value of the i-th battery cell, which is used to punish excessive adjustments and prevent frequent fluctuations.

2. The battery management method based on multi-dimensional parameters according to claim 1, characterized in that: The weighted fusion strategy layer includes a set credibility index, which is used to represent the relative trust of the filtering channel and the learning channel. The weighted fusion strategy layer performs a weighted fusion process on the real-time dynamic prediction results and the short-term dynamic change results, which can be expressed as: S f =α·S K +(1-α)·S M ; Among them, α is the credibility index, S K is the filter channel output; S M is the learning channel output, S f It is the result of weighted fusion of the filtering channel output and the learning channel output, which is a multi-dimensional comprehensive state.

3. The battery management method based on multi-dimensional parameters according to claim 2, characterized in that: The multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function for analysis to obtain the global optimum of each battery cell in the local adjustment, including: After the multi-dimensional comprehensive state of each battery cell is input into the multi-objective collaborative optimization function, each battery cell is taken as the target and the charge and discharge power adjustment amount of each battery cell is used as the adjustment strategy. An analysis is performed based on the distributed optimization rules to maximize the multi-objective collaborative optimization function, and all corresponding battery cells reach the global optimum in local adjustments.

4. A battery management device based on multi-dimensional parameters, characterized in that: include: An acquisition module is used to obtain multi-dimensional parameters collected in real time by multiple sets of sensors installed in the battery pack; An analysis module is used to input the multidimensional parameters into an integrated multi-source state assessment model for analysis to determine the multidimensional comprehensive state of each battery cell. The multi-source state assessment model includes: a dual-channel estimation layer, a weighted fusion strategy layer, and an output multidimensional state layer; the dual-channel estimation layer includes a filtering channel and a learning channel; after the multidimensional parameters are input into the multi-source state assessment model, the battery cell state at the next moment is predicted in the filtering channel by the state transfer equation and the observation equation, the predicted battery cell state is updated with the multidimensional parameters measured by the sensor at the next moment, and the real-time dynamic prediction result of each battery cell state is output; in the learning channel, the multidimensional parameters are analyzed by a deep feedforward neural network, and the dynamic change result of each battery cell state in the short term is output; in the weighted fusion strategy layer, the real-time dynamic prediction result is weightedly fused with the dynamic change result of the battery cell state in the short term to obtain a multidimensional comprehensive state prediction result, and the multidimensional comprehensive state is output by the output layer; The determination module is used to input the multi-dimensional comprehensive state of each battery cell into the multi-objective collaborative optimization function for analysis, so as to obtain the global optimum of each battery cell in the local adjustment; the multi-objective collaborative optimization function is expressed as: U i =α·H i +β·S i -γ·|ΔP i | Among them, α, β, and γ are weight coefficients, which need to be dynamically adjusted according to the security level. i is the health level of the ith battery cell, S i is the safety level of the i-th battery cell; |ΔP i | is the charge and discharge power adjustment value of the i-th battery cell, which is used to punish excessive adjustments and prevent frequent fluctuations.

5. A battery management device based on multi-dimensional parameters, characterized in that: include: A processor, a memory, and a computer program stored in the memory and running on the processor; When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images