Method, device and equipment for predicting remaining service life of battery, medium and product

Abstract

The invention relates to the technical field of ships, and discloses a battery remaining service life prediction method, device and equipment, a medium and a product. The method comprises the following steps: acquiring current battery state data, and acquiring a current battery state according to the current battery state data through a pre-trained target battery state division model; according to the current battery state, if it is determined that the battery is in a degradation period, obtaining current battery degradation data; and through a pre-trained residual life prediction model, according to the current battery degradation data, obtaining a battery residual service life prediction value. According to the scheme of the embodiment, the battery health state is judged according to the battery state data, and the remaining service life is predicted when the battery is determined to be in the degradation period, so that the accuracy of predicting the remaining service life of the ship battery can be improved.

Description

Technical Field

[0001] The present invention relates to the field of ship technology, and in particular to a method, device, equipment, medium and product for predicting the remaining service life of a battery. Background Art

[0002] As the use of lithium batteries in unmanned boats continues to grow, it is critical to accurately predict the remaining service life of these batteries. Remaining service life prediction can not only optimize resource utilization, but also improve operational reliability and minimize maintenance costs, which can ensure the efficiency and life of the battery drive system.

[0003] At present, the existing battery remaining service life prediction methods usually use pre-trained machine learning models to predict the remaining battery service life based on the real-time status data of the battery. However, in the existing technology, the battery health status is not distinguished. In real scenarios, the battery status will gradually degrade as the usage time increases. The existing technology lacks consideration of the dimensional characteristics of the battery health status, which easily leads to poor accuracy in the prediction of the remaining battery service life. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and product for predicting the remaining service life of a battery, which can improve the accuracy of predicting the remaining service life of a ship battery.

[0005] According to one aspect of the present invention, a method for predicting remaining battery life is provided, comprising:

[0006] Acquire current battery status data, and acquire the current battery status according to the current battery status data through a pre-trained target battery status classification model;

[0007] If it is determined that the battery is in a degradation period according to the current battery state, obtaining current battery degradation data;

[0008] The remaining service life prediction value of the battery is obtained according to the current battery degradation data through the pre-trained remaining service life prediction model.

[0009] According to another aspect of the present invention, there is provided a device for predicting remaining battery life, comprising:

[0010] A battery status acquisition module is used to acquire current battery status data and acquire the current battery status according to the current battery status data through a pre-trained target battery status classification model;

[0011] A battery degradation data acquisition module, configured to acquire current battery degradation data if it is determined that the battery is in a degradation cycle according to the current battery state;

[0012] The life prediction module is used to obtain a predicted value of the remaining service life of the battery according to the current battery degradation data through a pre-trained remaining service life prediction model.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the battery remaining service life prediction method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a processor to implement the battery remaining service life prediction method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for predicting the remaining service life of a battery according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention obtains the current battery status data and obtains the current battery status according to the current battery status data through a pre-trained target battery status classification model; if it is determined that the battery is in a degradation cycle according to the current battery status, the current battery degradation data is obtained; and a battery remaining service life prediction value is obtained according to the current battery degradation data through a pre-trained remaining service life prediction model. By determining the battery health status according to the battery status data and predicting the remaining service life when it is determined that the battery is in a degradation cycle, the accuracy of the remaining service life prediction of the ship battery can be improved.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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 description of the embodiments. 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 creative work.

[0022] Figure 1 is a flowchart of a method for predicting remaining battery life provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a schematic diagram of the network structure of the remaining life prediction model provided according to the first embodiment of the present invention;

[0024] Figure 3 is a structural schematic diagram of a battery remaining service life prediction device provided according to Embodiment 2 of the present invention;

[0025] Figure 4 It is a structural schematic diagram of an electronic device for implementing the method for predicting the remaining service life of a battery according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1A flowchart of a method for predicting the remaining service life of a battery is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the remaining service life of a lithium battery used in an unmanned boat is predicted. The method can be executed by a battery remaining service life prediction device, which can be implemented in the form of hardware and / or software. Typically, the battery remaining service life prediction device can be configured in an electronic device on a ship, such as a computer device or a server. Figure 1 As shown, the method includes:

[0030] S110, obtaining current battery status data, and obtaining the current battery status according to the current battery status data through a pre-trained target battery status classification model.

[0031] In this embodiment, the lithium batteries used in ships, such as unmanned boats, can be monitored in real time to obtain corresponding battery status data. The battery status data may include battery charging time, discharge voltage, charge and discharge temperature, etc. Afterwards, a sliding window can be used to divide the battery status data into status data segments of the same length, and each status data segment can be input into a pre-trained target battery status partitioning model in turn, and the corresponding battery status output by the target battery status partitioning model can be obtained. For example, the size of the sliding window can be 50 and the step size can be 1.

[0032] It should be noted that this embodiment divides the complete life cycle of the battery into three stages, namely, a healthy cycle, a degradation cycle, and an unhealthy cycle. Correspondingly, the battery status may include a healthy state, a degraded state, and an unhealthy state. For a battery, as the usage time and the number of charge and discharge times gradually increase, it goes through a healthy cycle, a degradation cycle, and an unhealthy cycle in sequence. In the healthy cycle, the battery status data will not change significantly, but when it begins to enter the degradation cycle, the battery status data will change to varying degrees.

[0033] Among them, the target battery state division model can be established based on the long short-term memory network method. For example, an initial battery state division model can be established according to the long short-term memory network method and preset model parameters; then, the initial battery state division model can be trained using training samples with pre-labeled state labels until a target battery state division model that meets the training termination condition is obtained. For example, the training termination condition can be that the loss function value is less than or equal to a preset loss threshold.

[0034] S120: If it is determined that the battery is in a degradation period according to the current battery state, current battery degradation data is obtained.

[0035] Specifically, if it is determined that the current battery state is a degraded state, or if it is determined that the battery has triggered the degraded state multiple times in a row based on the current battery state and the historical battery state, it can be determined that the battery is in a degradation cycle. At this time, the battery degradation data can be collected.

[0036] The battery degradation data may be status data related to the battery life. Optionally, the battery degradation data may include at least one of the discharge capacity, charge capacity, charge time, temperature and internal resistance. As the battery usage time increases, various battery degradation data will increase or decrease to a certain extent. By analyzing the battery degradation data accordingly, the remaining battery life can be predicted.

[0037] Optionally, determining, according to the current battery state, that the battery is in a degradation period may include:

[0038] Obtaining a historical battery status corresponding to the battery;

[0039] According to the historical battery status and the current battery status, if it is detected that the number of times that the battery is continuously in a degraded state within a set time period is greater than or equal to a preset number threshold, it is determined that the battery is in a degradation cycle.

[0040] In this embodiment, a mechanism combining a continuous trigger mechanism and a time period limit can be used to determine whether the battery is in a degradation cycle. Specifically, the battery status determined each time can be stored in a specified database, and after obtaining the current battery status, the historical battery status corresponding to the battery is read from the database, for example, the battery status of a certain length of time or a certain number of times adjacent to the current determination. Then, based on the historical battery status and the current battery status, if it is detected that the battery is continuously in a degraded state within a set time, and the number of times it is continuously in a degraded state is greater than or equal to a preset number threshold, it can be determined that the battery is currently in a degradation cycle.

[0041] The advantage of the above setting is that it can improve the accuracy and robustness of judging whether the battery is in a degradation period, and can improve the accuracy of predicting the remaining service life of the battery.

[0042] S130. Obtain a predicted value of the remaining service life of the battery according to the current battery degradation data using a pre-trained remaining service life prediction model.

[0043] The remaining life prediction model may include a convolutional neural network (CNN) layer, an encoding layer, a fully connected layer, a long short-term memory network (LSTM) layer, and a time series network layer. For example, the network structure of the remaining life prediction model may be as follows: Figure 2As shown in the figure. The encoding layer uses the Transformer encoder for multimodal interaction to understand the relationship between different channels and determine the relative importance of each channel; the fully connected layer is used for multimodal fusion, which allows different features in the same sensor channel to have different weights to enhance feature fusion and obtain the independent contribution value of each feature; the LSTM layer is used for time domain information extraction to understand the global time relationship between different time steps in the input window; the time series network layer is used for time domain information enhancement, and the importance of the features of each time step in the sequence is evaluated by the weighted average sum of the hidden states of each time step.

[0044] Optionally, the remaining life prediction model can use a loss function that combines the mean absolute error (MAE), the root mean square error (RMSE) and the mean absolute percentage error (MAPE). In this embodiment, the remaining service life RUL of the battery i j It can be defined as:

[0045] .

[0046] Among them, EOL i Indicates the total charge and discharge cycle. A charge and discharge cycle consists of one charging process and one discharging process. FPC i Indicates the charge-discharge cycle at the beginning of the degradation cycle, i indicates the index of the cell unit, j indicates the charge-discharge cycle index, i.e. the jth charge-discharge cycle. For example, if the total charge-discharge cycle is 100, the charge-discharge cycle at the beginning of the degradation cycle is 40, and the current charge-discharge cycle j is 70, then the remaining battery life is (100-70) / (100-40)=0.5.

[0047] Based on the above definition of the remaining battery life, the loss function of the remaining life prediction model can be expressed as L = L MAE +L RMSE +L MAPE ,in,

[0048] ;

[0049] ;

[0050] .

[0051] Among them, HS i Indicates the actual battery status, Indicates the predicted battery status. Different battery status can be identified by different values.

[0052] In this embodiment, by adopting the definition of the remaining battery service life, a more accurate measurement of the battery health status can be achieved, and the accuracy of the remaining battery service life prediction can be improved.

[0053] Specifically, first, an initial remaining life prediction model can be established based on preset model parameters; then, the initial remaining life prediction model can be trained using historical battery degradation data pre-labeled with remaining life labels until the loss function value is less than the preset loss threshold, thereby obtaining a trained remaining life prediction model. Finally, the current battery degradation data can be input into the pre-trained remaining life prediction model, and the battery remaining life prediction value output by the remaining life prediction model can be obtained.

[0054] The technical solution of the embodiment of the present invention obtains the current battery status data and obtains the current battery status according to the current battery status data through a pre-trained target battery status classification model; if it is determined that the battery is in a degradation cycle according to the current battery status, the current battery degradation data is obtained; and a battery remaining service life prediction value is obtained according to the current battery degradation data through a pre-trained remaining service life prediction model. By determining the battery health status according to the battery status data and predicting the remaining service life when it is determined that the battery is in a degradation cycle, the accuracy of the remaining service life prediction of the ship battery can be improved.

[0055] In an optional implementation of this embodiment, before obtaining the current battery state according to the current battery state data by using the pre-trained target battery state classification model, the following may also be included:

[0056] Acquire historical battery status data matching each charge and discharge cycle period corresponding to each battery cell unit, and generate a training sample set based on the historical battery status data;

[0057] Based on the long short-term memory network method, an initial battery state division model is established, and based on the binary cross entropy loss function, the initial battery state division model is trained according to the training sample set to obtain a trained target battery state division model.

[0058] In this embodiment, the status data range corresponding to each battery status can be pre-set. When there are multiple battery status data, the corresponding status data range can be set for each battery status data. Therefore, after obtaining the historical battery status data, the historical battery status data can be numerically compared with the corresponding status data range to obtain the battery status label corresponding to each historical battery status data, thereby completing the automatic labeling of the historical battery status data. Furthermore, the historical battery status data and the corresponding battery status label can be used as a training sample to generate a training sample set.

[0059] Specifically, when generating the model, first, an initial battery state division model can be established based on the long short-term memory network method and preset model parameters; then, the initial battery state division model can be iteratively trained using a training sample set until the loss function value of the binary cross entropy loss function is less than or equal to a preset threshold, thereby obtaining a trained target battery state division model.

[0060] The target battery state classification model may include two layers of LSTM modules, after which a fully connected layer with an activation function is used to classify the state. Secondly, the model uses binary cross entropy as a loss function to quantify the difference between the predicted battery state and the actual battery state. For example, the binary cross entropy loss function L BCE It can be expressed as:

[0061] .

[0062] Optionally, generating a training sample set according to the historical battery status data may include:

[0063] According to the charge and discharge cycle period matched by each of the historical battery status data, as well as the preset health degree division ratio and the preset total charge and discharge cycle period, obtaining the status label corresponding to each of the historical battery status data;

[0064] The training sample set is generated according to each of the historical battery status data and the corresponding status label.

[0065] In this embodiment, the preset total charge and discharge cycle period can be divided based on the preset health division ratio to obtain the charge and discharge cycle period range corresponding to each battery state; then, the charge and discharge cycle period matching each historical battery state data can be numerically compared with the charge and discharge cycle period range corresponding to each battery state to determine which range it falls in, thereby determining the battery state corresponding to each historical battery state data. Thus, a corresponding state label can be assigned to each determined historical battery state data according to the battery state corresponding to it. Among them, the battery state corresponds to the state label one by one. Finally, each historical battery state data and the corresponding state label can be used as a training sample to obtain the final training sample set.

[0066] Among them, the state label can be defined as:

[0067] .

[0068] Among them, HS i j Indicates the status label corresponding to the battery status data of the jth charge and discharge cycle of the i-th battery unit, p represents the preset health degree division ratio, 0 represents the status label corresponding to the healthy state, 1 / 2 represents the status label corresponding to the degraded state, and 1 represents the status label corresponding to the unhealthy state.

[0069] The solution of this embodiment proposes a method for predicting the remaining service life of unmanned boat lithium batteries by combining CNN and LSTM, and improves the prediction robustness and accuracy by obtaining the spatiotemporal relationship between each feature data. Secondly, a method for predicting the beginning degradation cycle of lithium batteries is proposed, which can provide more accurate data information for the prediction of the remaining service life of lithium batteries.

[0070] Embodiment 2

[0071] Figure 3 This is a schematic diagram of the structure of a battery remaining service life prediction device provided by Embodiment 2 of the present invention. Figure 3 As shown, the device includes: a battery status acquisition module 210, a battery degradation data acquisition module 220 and a life prediction module 230; wherein,

[0072] A battery status acquisition module 210 is used to acquire current battery status data and acquire the current battery status according to the current battery status data through a pre-trained target battery status classification model;

[0073] The battery degradation data acquisition module 220 is used to acquire the current battery degradation data if it is determined that the battery is in a degradation cycle according to the current battery state;

[0074] The life prediction module 230 is used to obtain a predicted value of the remaining service life of the battery according to the current battery degradation data through a pre-trained remaining service life prediction model.

[0075] The technical solution of the embodiment of the present invention obtains the current battery status data and obtains the current battery status according to the current battery status data through a pre-trained target battery status classification model; if it is determined that the battery is in a degradation cycle according to the current battery status, the current battery degradation data is obtained; and a battery remaining service life prediction value is obtained according to the current battery degradation data through a pre-trained remaining service life prediction model. By determining the battery health status according to the battery status data and predicting the remaining service life when it is determined that the battery is in a degradation cycle, the accuracy of the remaining service life prediction of the ship battery can be improved.

[0076] Optionally, the battery remaining service life prediction device further includes:

[0077] A sample generation module is used to obtain historical battery status data matching each charge and discharge cycle period corresponding to each battery cell unit, and generate a training sample set based on the historical battery status data;

[0078] The model training module is used to establish an initial battery state partition model based on a long short-term memory network method, and to perform model training on the initial battery state partition model according to the training sample set based on a binary cross entropy loss function to obtain a trained target battery state partition model.

[0079] Optionally, a sample generation module is specifically used to obtain a status label corresponding to each of the historical battery status data according to the charge and discharge cycle period matched by each of the historical battery status data, as well as a preset health degree division ratio and a preset total charge and discharge cycle period;

[0080] The training sample set is generated according to each of the historical battery status data and the corresponding status label.

[0081] Optionally, a battery degradation data acquisition module 220 is specifically used to acquire a historical battery state corresponding to the battery;

[0082] According to the historical battery status and the current battery status, if it is detected that the number of times that the battery is continuously in a degraded state within a set time period is greater than or equal to a preset number threshold, it is determined that the battery is in a degradation cycle.

[0083] Optionally, the remaining life prediction model includes a convolutional neural network layer, an encoding layer, a fully connected layer, a long short-term memory network layer and a time series network layer, and the remaining life prediction model adopts a loss function that combines the mean absolute error, the root mean square error and the mean absolute percentage error.

[0084] Optionally, the battery degradation data includes at least one of discharge capacity, charge capacity, charge time, temperature and internal resistance.

[0085] The battery remaining service life prediction device provided in the embodiment of the present invention can execute the battery remaining service life prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0086] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0087] Embodiment 3

[0088] Figure 4 A schematic diagram of the structure of an electronic device 30 that can be used to implement an embodiment of the present invention is shown. The electronic device 30 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0089] like Figure 4 As shown, the electronic device 30 includes at least one processor 31, and a memory connected to the at least one processor 31, such as a read-only memory (ROM) 32, a random access memory (RAM) 33, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 31 can perform various appropriate actions and processes according to the computer program stored in the read-only memory 32 or the computer program loaded from the storage unit 38 to the random access memory 33. In the RAM 33, various programs and data required for the operation of the electronic device 30 can also be stored. The processor 31, the ROM 32 and the RAM 33 are connected to each other through a bus 34. The input / output (I / O) interface 35 is also connected to the bus 34.

[0090] A number of components in the electronic device 30 are connected to the I / O interface 35, including: an input unit 36, such as a keyboard, a mouse, etc.; an output unit 37, such as various types of displays, speakers, etc.; a storage unit 38, such as a disk, an optical disk, etc.; and a communication unit 39, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0091] The processor 31 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 31 include, but are not limited to, a central processing unit, a graphics processing unit, various dedicated artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any appropriate processors, controllers, microcontrollers, etc. The processor 31 executes the various methods and processes described above, such as a battery remaining service life prediction method.

[0092] In some embodiments, the battery remaining service life prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 38. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 30 via the ROM 32 and / or the communication unit 39. When the computer program is loaded into the RAM 33 and executed by the processor 31, one or more steps of the battery remaining service life prediction method described above may be performed. Alternatively, in other embodiments, the processor 31 may be configured to execute the battery remaining service life prediction method in any other appropriate manner (e.g., by means of firmware).

[0093] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays, application specific integrated circuits, application specific standard products, systems on a chip, load programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0095] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0096] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 30 having: a display device (e.g., a cathode ray tube or a liquid crystal display) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device 30. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0097] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area networks, wide area networks, blockchain networks, and the Internet.

[0098] A computing system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server.

[0099] This embodiment may also include a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the battery remaining service life prediction method provided by any embodiment of the present invention.

[0100] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0101] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting remaining battery life, characterized in that: include: Acquire current battery status data, and acquire the current battery status according to the current battery status data through a pre-trained target battery status classification model; If it is determined that the battery is in a degradation period according to the current battery state, obtaining current battery degradation data; The remaining service life prediction value of the battery is obtained according to the current battery degradation data through the pre-trained remaining service life prediction model.

2. The method according to claim 1, characterized in that: Before obtaining the current battery state according to the current battery state data by using the pre-trained target battery state classification model, the method further includes: Acquire historical battery status data matching each charge and discharge cycle period corresponding to each battery cell unit, and generate a training sample set based on the historical battery status data; Based on the long short-term memory network method, an initial battery state division model is established, and based on the binary cross entropy loss function, the initial battery state division model is trained according to the training sample set to obtain a trained target battery state division model.

3. The method according to claim 2, characterized in that Generating a training sample set according to the historical battery status data includes: According to the charge and discharge cycle period matched by each of the historical battery status data, as well as the preset health degree division ratio and the preset total charge and discharge cycle period, obtaining the status label corresponding to each of the historical battery status data; The training sample set is generated according to each of the historical battery status data and the corresponding status label.

4. The method according to claim 1, characterized in that: Determining, according to the current battery state, that the battery is in a degradation period includes: Obtaining a historical battery status corresponding to the battery; According to the historical battery status and the current battery status, if it is detected that the number of times that the battery is continuously in a degraded state within a set time period is greater than or equal to a preset number threshold, it is determined that the battery is in a degradation cycle.

5. The method according to claim 1, characterized in that The remaining life prediction model includes a convolutional neural network layer, an encoding layer, a fully connected layer, a long short-term memory network layer and a time series network layer. The remaining life prediction model adopts a loss function that combines the mean absolute error, the root mean square error and the mean absolute percentage error.

6. The method according to claim 1, characterized in that The battery degradation data includes at least one of discharge capacity, charge capacity, charge time, temperature, and internal resistance.

7. A battery remaining service life prediction device, characterized in that: include: A battery status acquisition module is used to acquire current battery status data and acquire the current battery status according to the current battery status data through a pre-trained target battery status classification model; A battery degradation data acquisition module, configured to acquire current battery degradation data if it is determined that the battery is in a degradation cycle according to the current battery state; The life prediction module is used to obtain a predicted value of the remaining service life of the battery according to the current battery degradation data through a pre-trained remaining service life prediction model.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor, and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the battery remaining service life prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the battery remaining service life prediction method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for predicting the remaining service life of a battery according to any one of claims 1 to 6.

Images