Battery predictive maintenance method, device and storage medium

Abstract

The present invention provides a battery predictive maintenance method, device and storage medium. First, the battery type and battery historical operation data are obtained; then the application environment data corresponding to the battery type is selected; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is the meteorological data that affects the battery life; the structural environment data is the operation data of other structures or equipment in the working system where the battery is located; then, the expected operation state of the battery in the target period is calculated according to the historical operation data, the application environment data and the state estimation model; finally, the battery maintenance strategy is formulated according to the expected operation state. By considering the structure and meteorology of the battery type to reflect the application environment of different types of batteries, combining the historical operation data and the state estimation model, the expected operation state of the battery is accurately predicted, so as to formulate the corresponding battery maintenance strategy. The present invention can be applied to a variety of batteries such as power batteries and energy storage batteries.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery maintenance, and in particular relates to a battery predictive maintenance method, device and storage medium. Background Art

[0002] Predictive maintenance of batteries is a technology that predicts the health status and remaining service life of batteries by monitoring their performance indicators and usage conditions. The purpose of this technology is to identify and take maintenance measures in advance before the battery performance deteriorates to the point where it affects use, thereby avoiding unexpected failures, extending the battery life, and ensuring the safe operation of the equipment.

[0003] Conventional battery predictive maintenance usually performs predictive maintenance on a single type of battery. Different types of batteries have different application scenarios and different life characteristics, so existing battery predictive maintenance methods are difficult to adapt to different types of batteries. Summary of the invention

[0004] In view of this, the present invention provides a battery predictive maintenance method, device and storage medium, aiming to solve the problem that the existing battery predictive maintenance method is difficult to adapt to different types of batteries.

[0005] A first aspect of an embodiment of the present invention provides a battery predictive maintenance method, characterized by comprising:

[0006] Obtain battery type and battery historical operation data;

[0007] Select the application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is the meteorological data that affects the battery life; the structural environment data is the operating data of other structures or equipment in the working system where the battery is located;

[0008] Calculate the expected operating state of the battery during the target period based on historical operating data, application environment data and state estimation model;

[0009] Develop a battery maintenance strategy based on the expected operating status of the battery within the target period.

[0010] A second aspect of an embodiment of the present invention provides a battery predictive maintenance device, comprising:

[0011] The acquisition module is used to obtain the battery type and battery historical operation data;

[0012] A selection module is used to select application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is the meteorological data that affects the battery life; the structural environment data is the operating data of other structures or equipment in the working system where the battery is located;

[0013] A calculation module, used to calculate the expected operating state of the battery within the target period based on historical operating data, application environment data and a state estimation model;

[0014] The maintenance module is used to formulate a battery maintenance strategy based on the expected operating status of the battery within a target period.

[0015] A third aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the battery predictive maintenance method of the first aspect above are implemented.

[0016] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the battery predictive maintenance method of the first aspect above are implemented.

[0017] The battery predictive maintenance method, device and storage medium provided by the embodiment of the present invention first obtain the battery type and the historical battery operation data; then select the application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is the meteorological data that affects the battery life; the structural environment data is the operation data of other structures or equipment in the working system where the battery is located; then the expected operation state of the battery in the target time period is calculated based on the historical operation data, the application environment data and the state estimation model; finally, the battery maintenance strategy is formulated based on the expected operation state of the battery in the target time period. By considering the structural environment and meteorological environment of the battery type to reflect the application environment of different types of batteries, combining the historical operation data and the state estimation model, the expected operation state of the battery is accurately predicted, so as to formulate the corresponding battery maintenance strategy. The present invention can be applied to a variety of batteries such as power batteries and energy storage batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative labor.

[0019] Figure 1is a flowchart of an implementation method of a battery predictive maintenance method provided by an embodiment of the present invention;

[0020] Figure 2 It is a structural schematic diagram of a battery predictive maintenance method and device provided by an embodiment of the present invention;

[0021] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0023] Figure 1 FIG. 1 is a flowchart of the implementation of the battery predictive maintenance method provided by the embodiment of the present invention. Figure 1 As shown, in some embodiments, a battery predictive maintenance method includes:

[0024] S110, obtaining battery type and battery historical operation data;

[0025] In the embodiment of the present invention, the battery type can be classified according to the chemical type; for example, lithium battery, nickel metal hydride battery, lead acid battery, photovoltaic battery, etc. It can also be classified according to the purpose; for example, power battery, energy storage battery, backup battery, etc., which are not limited here. The battery historical operation data includes the voltage, current, temperature, humidity, etc. of the historical period.

[0026] S120, selecting application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is meteorological data that affects the battery life; the structural environment data is operating data of other structures or equipment in the working system where the battery is located;

[0027] In some embodiments, S120 includes: acquiring historical meteorological data, historical structural data, and structural update information of the battery; determining meteorological environment data according to the battery type and historical meteorological data; and determining structural environment data according to the historical structural data and structural update data.

[0028] In some embodiments, meteorological data includes temperature, humidity, radiation, and wind speed; structural environmental data includes physical structure integrity, environmental control equipment data, and external joint work equipment data.

[0029] Different types of batteries have different trends in life attenuation in different application environments, and the corresponding predictive maintenance is also different.

[0030] For example, on-board power lithium batteries are deployed in electric vehicles. Since electric vehicles travel on routes with different conditions, their weather environment will fluctuate greatly. In 24 hours, the car can travel hundreds or even thousands of kilometers. Due to the rapid changes in the region, the temperature and humidity of the battery fluctuate greatly and do not have periodic characteristics. At this time, it is inaccurate to only predict the future condition of the battery according to the changing characteristics of the battery's historical data for predictive maintenance.

[0031] In addition, the cooling methods of on-board power lithium batteries mainly adopt three types: air cooling, liquid cooling and direct cooling. Different cooling structures, cooling methods and cooling strategies have different effects on the operation of the battery.

[0032] In addition, conventional electric vehicles are usually used to a certain extent before being charged, and the battery charge and discharge conversion times are relatively small. When the electric vehicle where the on-board power battery is located is a hybrid vehicle, in order to meet the requirements of cruising range and climbing power, more complex algorithms are usually planned. In some cases, the car driver charges the battery, or the battery and fuel cell complement each other. This leads to a significant increase in the number of battery charge and discharge conversions and a faster life decay.

[0033] For example, energy storage batteries for new energy microgrids, especially those for large photovoltaic power stations or large wind farms, are usually deployed outdoors to save space and operation and maintenance costs. They are affected by outdoor temperature, humidity, radiation, and wind speed. When they are outdoors for a long time, their shells are easily damaged or aged. Energy storage batteries also have different cooling structures, cooling methods, and cooling strategies. In addition, the life attenuation of energy storage batteries alone to smooth out wind and solar power and energy storage batteries and other energy storage devices (such as supercapacitors) to smooth out wind and solar power is completely different.

[0034] Therefore, in the embodiment of the present invention, meteorological environment data is obtained to consider the impact of weather on various types of batteries. At the same time, the changes in the meteorological environment caused by the cooling equipment, dehumidifier and other environmental control equipment equipped with the battery, the integrity of the physical structure such as the shell, and the help of the external joint working equipment equipped with this type of battery on life attenuation are considered, so as to more accurately predict the life change of the battery and facilitate predictive maintenance.

[0035] In order to facilitate calculation, some data are specifically quantified. In meteorological data, temperature, humidity, radiation, and wind speed can be directly taken. The structure, type, and control strategy of environmental control equipment data are relatively complex, so the environmental control equipment data is specifically quantified as environmental changes, that is, changes in temperature, humidity, radiation, and wind speed. The physical structure integrity can be specifically a percentage, for example, 98% or more can be set as slightly damaged, 95%-98% can be set as moderately damaged, and below 95% can be set as severely damaged. The types of external joint working equipment are also complex, so the external joint working equipment data is quantified as the parameters of the impact of the external joint working equipment on the battery, for example, the number of times the external joint working equipment helps the battery to reduce charging and discharging, the peak power reduction after the external joint working equipment absorbs the peak power (if the external equipment causes a certain parameter to increase, the parameter value is a negative number), and the reduction in the thermal load of the battery after the external equipment shares the power, etc., which are not limited here.

[0036] In the embodiment of the present invention, the above data can be directly input by the user as the final quantitative value, or the user can select the information of the external joint working equipment and the environmental control equipment in the drop-down menu, and then query the database based on this information to obtain the corresponding quantitative value.

[0037] In some embodiments, the method further includes: when the environmental control device data is updated, determining the meteorological environment data according to the updated data of the environmental control device data, the battery type and the historical meteorological data.

[0038] S130, calculating an estimated operating state of the battery within a target period of time according to historical operating data, application environment data, and a state estimation model;

[0039] In some embodiments, S130 includes: calculating a first correlation matrix between the battery's operating data and meteorological environment data; calculating a second correlation matrix between the application environment data and the structural environment data; calculating a third correlation matrix between the battery's operating data and the structural environment data; inputting historical operating data, application environment data, the first correlation matrix, the second correlation matrix, and the third correlation matrix into a state estimation model to determine the expected operating state of the battery within the target period.

[0040] In the embodiment of the present invention, the influence of various types of data on the battery is not isolated, but interrelated. For example, under the same battery over-discharge degree, the battery life decay may be different. For lithium batteries, the battery capacity decay rate is 2.54% after 100 cycles of slight over-discharge at 25°C, and the battery capacity decay rate is 28.46% after 100 cycles of slight over-discharge at 60°C. Therefore, the present invention considers the correlation between various types of data, calculates three correlation matrices, combines historical operation data and application environment data, and inputs them into the trained input state estimation model to obtain the expected operation state.

[0041] In an embodiment of the present invention, the target time period may be any time period after the current time period, and the state estimation model may be a neural network model, a deep learning model, etc., which are not limited here.

[0042] In some embodiments, calculating a first association matrix between the operating data of the battery and the meteorological environment data includes: calculating a first association matrix between the operating data of the battery and the meteorological environment data according to a pre-established first knowledge graph; wherein the first knowledge graph represents an association relationship between each item of operating data of the battery and each item of meteorological environment data;

[0043] Calculating a second association matrix between application environment data and structural environment data includes: calculating a second association matrix between application environment data and structural environment data based on a pre-established second knowledge graph; wherein the second knowledge graph represents the association relationship between each application environment data and each structural environment data.

[0044] Calculating the third association matrix between the operating data and the structural environment data of the battery, including: calculating the third association matrix between the operating data and the structural environment data of the battery according to a pre-established third knowledge graph; wherein the third knowledge graph represents the association relationship between each item of the operating data of the battery and each item of the structural environment data.

[0045] In an embodiment of the present invention, the first knowledge graph is determined based on the experimental data of the battery, and is specifically composed of multiple triplets of operation data-associated value-meteorological environment data. The second knowledge graph is determined based on the influence of other equipment such as cooling equipment on meteorological data, and is specifically composed of multiple triplets of equipment-associated value-meteorological environment data. The third knowledge graph is determined based on the influence of other equipment such as cooling equipment on battery operation, and is specifically composed of multiple triplets of equipment-associated value-battery operation data.

[0046] S140, formulating a battery maintenance strategy according to the expected operating status of the battery within the target period.

[0047] In an embodiment of the present invention, predictive maintenance is performed by evaluating possible faults according to the expected operating status of the battery within the target period, formulating a schedule for regular inspections and tests, and formulating a monitoring plan for key parameters such as battery voltage, current, temperature, and internal resistance.

[0048] In some embodiments, the state estimation model is a federated learning model; the federated learning model includes a charging sub-model, a discharging sub-model, a shelving sub-model, a judgment sub-model, a cycle sub-model, and a conclusion sub-model; the method also includes: editing the structure of each sub-model in response to a user's editing operation.

[0049] In an embodiment of the present invention, a user may edit some parameters of a model, and then perform training based on the parameters edited by the user to train other parameters of the model.

[0050] The present invention creates six process sub-models in the database, namely, charging, discharging, shelving, judging, circulating, and concluding. For each sub-model, we establish different data structures and store them separately through the database structure.

[0051] For the charging sub-model: users can set the charging current, termination voltage, charging time, etc.

[0052] For discharge sub-model: users can set discharge current, termination voltage, discharge duration, etc.

[0053] For the shelving sub-model: users can set the shelving time (shelving is the process of keeping the battery idle for a period of time during battery maintenance).

[0054] For the judgment sub-model: the user can set the discharge capacity, battery voltage, and discharge time parameters, and each parameter can be set to four judgment logics: >, ≥, <, ≤.

[0055] For the loop sub-model: the user can set up to 30 steps for repeated execution, and the number of loop executions can be set up to 10 times.

[0056] For the conclusion sub-model: users can set two parameters: qualified and unqualified.

[0057] After the user defines the model in the database, he can add up to 50 operating steps (i.e. charging, discharging, etc., each step corresponds to a sub-model) at will. The steps are model sequences with multiple set parameters. In the application software, they will be executed in sequence according to the set parameters.

[0058] In the embodiment of the present invention, steps can be added at will, and the added step types can be selected and configured in the above six models. After editing the steps, all data will be stored in the database, indexed by maintenance ID and model ID, and classified storage is adopted in the database, that is, different models are stored in different table structures, and battery information can be added and deleted, so each battery has 5 preset step models. As long as the user adds a battery, then this battery has 5 editable step models. After editing once, you can directly select and use it from the menu next time without repeated editing.

[0059] In the embodiments of the present invention, the battery is often operated under normal conditions, and few failures occur, which may result in little data being collected and a limited number of failure categories. In addition, due to issues such as data privacy, a small number of failure sample data are more difficult to share, forming data islands. Current battery predictive maintenance is limited by the adequacy of data and cannot achieve good results. In particular, the present invention is applicable to batteries of various types and models. If the amount of data for each type of battery is small, the accuracy of the trained state estimation model will also be low, so the present invention introduces federated learning. Federated learning generally includes the following steps:

[0060] 1. Initialization: Select an initial model architecture and initialize the model parameters on the central server. This initial model can be sent to each participant.

[0061] 2. Local training: Each participant trains the model using their own dataset. This step is performed on the participant's local device, so there is no need to share data. Participants may perform multiple rounds of training until the model's performance reaches a certain threshold or the number of training rounds reaches a preset upper limit.

[0062] 3. Update aggregation: Participants send their model updates (such as weight updates or gradients) to a central server. These updates are usually differentially private to preserve privacy.

[0063] 4. Model update: The central server receives model updates from various participants and uses some aggregation algorithm (such as weighted average) to merge these updates to generate a new global model.

[0064] 5. Model distribution: The updated global model is sent back to each participant. The participants use this new model to replace their local models and prepare for the next round of training.

[0065] 6. Repeated iterations: This process is repeated, and each round improves the performance of the global model while keeping the data local and not violating data privacy regulations.

[0066] 7. Stopping condition: When the performance of the global model reaches the predetermined target, or the number of training rounds reaches the preset upper limit, the federated learning process stops.

[0067] 8. Model evaluation: Finally, the central server may use a validation set or a test set to evaluate the performance of the final model to ensure the accuracy and generalization ability of the model.

[0068] That is, the software of the present invention can be deployed in various user terminals and central servers. After any user terminal performs a battery predictive maintenance, some new data will inevitably be introduced in the process. The local model of the user terminal can update the model based on these data, and the update is transmitted to the model of the central server. After integration by the central server, it is transmitted to other user terminals.

[0069] Since the present invention quantifies each parameter, if a certain predictive maintenance is predictive maintenance of a power lithium battery, the historical operation data, meteorological environment data, and structural environment data of the power lithium battery (the amount of change in meteorological environment data, the number of times the external joint working equipment helps the battery to reduce charge and discharge, the amount of peak power reduction after the external joint working equipment absorbs peak power, etc.) are updated, and the update can be transmitted to the energy storage lithium battery in the form of federated learning, that is, the impact of the updated power lithium battery meteorology on the battery operation, the impact of the number of times the charge and discharge is reduced, etc. on the battery is transmitted to the energy storage lithium battery. This allows different types of battery data to assist in learning and jointly establish a more accurate model.

[0070] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0071] Figure 2 Schematic diagram of the structure of the battery predictive maintenance method and device provided by the embodiment of the present invention. Figure 2 As shown, in some embodiments, a battery predictive maintenance method device 2 includes:

[0072] An acquisition module 210 is used to acquire the battery type and the battery historical operation data;

[0073] The selection module 220 is used to select application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is the meteorological data that affects the battery life; the structural environment data is the operating data of other structures or equipment in the working system where the battery is located;

[0074] A calculation module 230, for calculating the expected operating state of the battery within a target period based on historical operating data, application environment data and a state estimation model;

[0075] The maintenance module 240 is used to formulate a battery maintenance strategy according to the expected operating status of the battery within a target period of time.

[0076] Optionally, a selection module 220 is used to obtain historical meteorological data, historical structural data and structural update information of the battery; determine meteorological environment data based on the battery type and historical meteorological data; and determine structural environment data based on historical structural data and structural update data.

[0077] Optionally, meteorological data include temperature, humidity, radiation, and wind speed; structural environmental data include physical structure integrity, environmental control equipment data, and external joint working equipment data.

[0078] Optionally, the apparatus further includes: an updating module, for determining meteorological environment data according to the updated data of the environmental control device data, the battery type and the historical meteorological data when the environmental control device data is updated.

[0079] Optionally, the calculation module 230 is used to calculate the first correlation matrix between the battery's operating data and the meteorological environment data; calculate the second correlation matrix between the application environment data and the structural environment data; calculate the third correlation matrix between the battery's operating data and the structural environment data; input the historical operating data, the application environment data, the first correlation matrix, the second correlation matrix, and the third correlation matrix into the state estimation model to determine the expected operating state of the battery within the target period.

[0080] Optionally, the calculation module 230 is used to calculate a first association matrix between the operation data of the battery and the meteorological environment data according to a pre-established first knowledge graph; wherein the first knowledge graph represents the association relationship between each operation data of the battery and each meteorological environment data;

[0081] Optionally, the calculation module 230 is used to calculate a second association matrix between the application environment data and the structural environment data based on a pre-established second knowledge graph; wherein the second knowledge graph represents the association relationship between each application environment data and each structural environment data.

[0082] Optionally, the calculation module 230 is used to calculate a third association matrix between the battery's operating data and structural environmental data based on a pre-established third knowledge graph; wherein the third knowledge graph represents the association relationship between each item of the battery's operating data and each item of structural environmental data.

[0083] Optionally, the state estimation model is a federated learning model; the federated learning model includes a charging sub-model, a discharging sub-model, a shelving sub-model, a judgment sub-model, a cycle sub-model, and a conclusion sub-model; the device also includes: an editing module for editing the structure of each sub-model in response to a user's editing operation.

[0084] The battery predictive maintenance method and device provided in this embodiment can be used to execute the above method embodiments. The implementation principles and technical effects are similar and will not be described in detail in this embodiment.

[0085] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 3 provided by one embodiment of the present invention includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned battery predictive maintenance method embodiments are implemented, for example Figure 2 Alternatively, when the processor 30 executes the computer program 32, the functions of each module / unit in the above-mentioned system embodiments are implemented, for example Figure 3 The functions of each module are shown.

[0086] Exemplarily, the computer program 32 may be divided into one or more modules / units, one or more modules / units are stored in the memory 31, and are executed by the processor 30 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the electronic device 3.

[0087] The electronic device 3 may be a terminal or a server. The terminal may be a mobile phone, MCU, ECU, industrial computer, etc., which are not limited here. The server may be a physical server, a cloud server, etc., which are not limited here. The electronic device 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation of the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0088] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or 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, etc.

[0089] The memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit of the electronic device 3 and an external storage device. The memory 31 is used to store computer programs and other programs and data required by the electronic device. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0090] An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned battery predictive maintenance method embodiment are implemented.

[0091] The computer readable storage medium stores a computer program 32, which includes program instructions. When the program instructions are executed by the processor 30, all or part of the processes in the above-mentioned embodiment method are implemented. The computer program 32 can also be used to instruct related hardware to complete. The computer program 32 can be stored in a computer readable storage medium. When the computer program 32 is executed by the processor 30, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program 32 includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0092] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0093] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0094] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] 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 to be beyond the scope of the present invention.

[0097] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, 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.

[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0100] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0101] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A battery predictive maintenance method, characterized in that: include: Obtain battery type and battery historical operation data; Select application environment data corresponding to the battery type; wherein the application environment data includes meteorological environment data and structural environment data; the meteorological environment data is meteorological data that affects the battery life; the structural environment data is operating data of other structures or equipment in the working system where the battery is located; Calculating an estimated operating state of the battery within a target period of time according to the historical operating data, the application environment data and the state estimation model; Develop a battery maintenance strategy based on the expected operating status of the battery during the target period; Calculating the expected operating state of the battery within a target period according to the historical operating data, the application environment data and the state estimation model, including: Calculating a first correlation matrix between the operating data of the battery and the application environment data includes: Calculate a first association matrix between the operating data of the battery and the application environment data according to a pre-established first knowledge graph; wherein the first knowledge graph represents an association relationship between each item of operating data of the battery and each item of meteorological environment data; Calculating a second association matrix between the application environment data and the structure environment data includes: Calculate a second association matrix between the application environment data and the structural environment data according to a pre-established second knowledge graph; wherein the second knowledge graph represents an association relationship between each application environment data and each structural environment data; Calculating a third correlation matrix between the operating data of the battery and the structural environment data includes: According to a pre-established third knowledge graph, a third association matrix between the operation data of the battery and the structural environment data is calculated; wherein the third knowledge graph represents the association relationship between each operation data of the battery and each structural environment data; The historical operation data, the application environment data, the first correlation matrix, the second correlation matrix, and the third correlation matrix are input into a state estimation model to determine an expected operation state of the battery within a target period.

2. The battery predictive maintenance method according to claim 1, characterized in that: Select the application environment data corresponding to the battery type, including: Obtain historical meteorological data, historical structural data and structural update information of the battery; Determining the meteorological environment data according to the battery type and historical meteorological data; The structural environment data is determined according to the historical structural data and the structural update data.

3. The battery predictive maintenance method according to claim 2, characterized in that: The meteorological data includes temperature, humidity, radiation, and wind speed; the structural environment data includes physical structure integrity, environmental control equipment data, and external joint working equipment data.

4. The battery predictive maintenance method according to claim 1, characterized in that: The method further comprises: When the environmental control device data is updated, the meteorological environment data is determined according to the updated data of the environmental control device data, the battery type and the historical meteorological data.

5. The battery predictive maintenance method according to claim 1, characterized in that: The state estimation model is a federated learning model; the federated learning model includes a charging sub-model, a discharging sub-model, a shelving sub-model, a judgment sub-model, a cycle sub-model, and a conclusion sub-model; the method further includes: In response to the user's editing operation, the structure of each sub-model is edited.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the battery predictive maintenance method as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the battery predictive maintenance method as described in any one of claims 1 to 5 above are implemented.

Images