Battery charge state estimation method, device, equipment, medium and product

Abstract

The invention discloses a battery charge state estimation method, device and equipment, a storage medium and a program product. The method comprises the following steps: determining a reference charge state at a current moment according to a charge state at a previous moment; if the reference state of charge is within a preset state of charge range, determining a state of charge estimation result at the current moment based on a pre-trained state of charge estimation model according to battery operation data associated at the current moment; the preset state-of-charge range is a state-of-charge range matched with a non-voltage platform area of the battery; the battery operation data comprises operation state data of the battery at a plurality of continuous moments. According to the technical scheme, the problem of low estimation accuracy of the state of charge is solved, the state of charge is predicted at the moment of the non-voltage platform area by identifying the non-voltage platform area of the battery and based on the model estimation mode, accurate estimation of the state of charge of the lithium ion battery in the whole operation period is facilitated, and the reliability of state of charge prediction is ensured.

Description

Technical Field

[0001] The present invention relates to the field of battery management technology, and in particular to a method, device, electronic equipment, storage medium and program product for estimating a battery state of charge. Background Art

[0002] The state of charge (SOC) can be used to reflect the remaining capacity of the battery, which is the ratio of the current remaining charge of the battery to the rated charge.

[0003] At present, there are many types of state of charge estimation methods for lithium-ion batteries, including estimation methods based on physicochemical properties, estimation methods based on Kalman filtering, and estimation methods based on neural networks. Existing neural network-based estimation methods usually require obtaining a large amount of lithium-ion battery operating status data as sample data, using the sample data as the input of the neural network, using the state of charge corresponding to the sample data as the supervision of the neural network, and training the neural network so that the neural network learns the mapping relationship between the operating status data and the state of charge. The trained neural network model can be used to estimate unknown state of charge.

[0004] However, the neural network model cannot learn all operating states indiscriminately. For example, in the voltage platform area, it is difficult for the neural network model to achieve accurate estimation of the state of charge. Summary of the invention

[0005] The present invention provides a battery state of charge estimation method, device, electronic device, storage medium and program product to solve the problem of low accuracy of state of charge estimation. By identifying the non-voltage platform area of ​​the battery, the state of charge is predicted at the moment of the non-voltage platform area based on a model estimation method, which is conducive to accurate estimation of the state of charge of the lithium-ion battery during the full operation cycle and ensures the reliability of the state of charge prediction.

[0006] According to one aspect of the present invention, a method for estimating a battery state of charge is provided, the method comprising:

[0007] According to the state of charge at the previous moment, based on the ampere-hour integration method, the reference state of charge at the current moment is determined;

[0008] If the reference state of charge is within a preset state of charge range, the state of charge estimation result at the current moment is determined according to the battery operation data associated with the current moment and based on a pre-trained state of charge estimation model; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments.

[0009] According to another aspect of the present invention, there is provided a device for estimating a battery state of charge, the device comprising:

[0010] A reference state determination module, used to determine the reference state of charge at the current moment based on the state of charge at the previous moment and based on the ampere-hour integration method;

[0011] An estimation result determination module is used to determine the state of charge estimation result at the current moment based on the battery operation data associated with the current moment and a pre-trained state of charge estimation model if the reference state of charge is within a preset state of charge range; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; and the battery operation data includes the operation state data of the battery at multiple consecutive moments.

[0012] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0013] 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 state of charge estimation method described in any embodiment of the present invention.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the battery state of charge estimation method described in any embodiment of the present invention when executed.

[0015] 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 estimating the battery state of charge according to any embodiment of the present invention is implemented.

[0016] The technical solution of the embodiment of the present invention determines the reference state of charge at the current moment based on the ampere-hour integration method according to the state of charge at the previous moment; if the reference state of charge is within the preset state of charge range, the state of charge estimation result at the current moment is determined based on the battery operation data associated with the current moment and the pre-trained state of charge estimation model; the preset state of charge range is the state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments. This solution solves the problem of low accuracy of state of charge estimation by identifying the non-voltage platform area of ​​the battery and predicting the state of charge at the moment of the non-voltage platform area based on the model estimation method, which is conducive to realizing accurate estimation of the state of charge during the full operation cycle of the lithium-ion battery and ensuring the reliability of the state of charge prediction.

[0017] 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

[0018] 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.

[0019] Figure 1 is a flow chart of a method for estimating a battery state of charge provided according to Embodiment 1 of the present invention;

[0020] Figure 2 is a flow chart of a method for estimating a battery state of charge provided according to a second embodiment of the present invention;

[0021] Figure 3 is a schematic structural diagram of a battery state of charge estimation device provided according to Embodiment 3 of the present invention;

[0022] Figure 4 It is a structural schematic diagram of an electronic device for implementing the battery state of charge estimation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] It should be noted that the terms "first", "second", 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 interchangeable 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 of their variations 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0025] Embodiment 1

[0026] Figure 1 A flowchart of a method for estimating the state of charge of a battery is provided for the first embodiment of the present invention. This embodiment is applicable to the operation and maintenance management scenario of lithium-ion batteries. The method can be performed by a device for estimating the state of charge of a battery. The device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0027] S110 , determining a reference state of charge at the current moment according to the state of charge at the previous moment based on an ampere-hour integration method.

[0028] This solution can be executed by a battery management system, which can obtain the operating status data and state of charge of the battery at historical moments. The operating status data may include information such as voltage, current, temperature, throughput, and health status. The battery management system can determine the state of charge at the current moment based on the state of charge at the previous moment based on the ampere-hour integration method. The state of charge estimated by the ampere-hour integration method depends on the accuracy of current acquisition. As the system operation time increases, the error will gradually accumulate, affecting the prediction result of the state of charge. Therefore, the state of charge at the current moment calculated by the ampere-hour integration method is not accurate enough. The battery management system can use the state of charge calculated by the ampere-hour integration method as the reference state of charge at the current moment, providing a basis for subsequent more accurate estimates.

[0029] S120. If the reference state of charge is within a preset state of charge range, the state of charge estimation result at the current moment is determined according to the battery operation data associated with the current moment and based on a pre-trained state of charge estimation model; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments.

[0030] It is understandable that the voltage plateau region is the region where the battery maintains a relatively stable voltage during charge and discharge. For example, under constant current discharge conditions, the change in the working voltage of the battery can be divided into three stages: at the initial stage of discharge, the voltage drops rapidly; subsequently, the discharge curve gradually becomes stable and enters the voltage plateau region; at the end of discharge, the discharge curve shows a linear downward trend. The operating state of the battery in the voltage plateau region is stable, and it is difficult to extract obvious data features from the operating state data at multiple moments. In the non-voltage plateau region, however, there is a relatively obvious change trend in the operating state of the battery, so it is easy to extract data change features based on the operating state data at multiple moments.

[0031] Existing state of charge estimation methods usually rely on simplified physical models and are difficult to fully reflect the complex non-linear electrochemical characteristics inside the battery. In cases such as low temperature environments and battery aging, there are often large deviations in the state of charge estimation results. In contrast, neural networks, with their powerful non-linear mapping capabilities, can more efficiently learn and simulate the complex change laws of the battery state of charge. However, for the voltage plateau region of the battery, the mapping ability of neural networks is limited, and it is difficult to accurately capture the change in battery SOC. Therefore, the ampere-hour integration method can be combined to calculate the state of charge in the voltage plateau region, so as to ensure reliable state of charge estimation results in the voltage plateau region.

[0032] For the voltage plateau region and the non-voltage plateau region, the battery is usually within a specific state of charge range. For example, in a lithium iron phosphate battery, the low state of charge (about SOC < 25%), medium state of charge (about 55% < SOC < 65%), and high state of charge (about SOC > 90%) regions are non-voltage plateau regions. Therefore, the battery management system can preset the state of charge range corresponding to the non-voltage plateau region, and evaluate whether it is in the voltage plateau region at the current moment based on the reference state of charge and the preset state of charge range. Among them, the preset state of charge range can be an interval or the union of multiple intervals.

[0033] If the reference state of charge is within the preset state of charge range, it indicates that the current moment is in the non-voltage plateau region. The battery management system can determine the state of charge estimation result at the current moment based on the battery operation data associated with the current moment and the pre-trained state of charge estimation model. Specifically, the battery operation data includes the operation state data of the battery at multiple consecutive moments. The multiple consecutive moments can be consecutive moments composed of the current moment and a preset number of moments before the current moment, or consecutive moments composed of the current moment, a preset number of moments before the current moment, and a preset number of moments after the current moment.

[0034] The battery management system can input the battery operation data associated with the current moment into the state of charge estimation model. The state of charge estimation model can be used to characterize the relationship between the battery operation data and the state of charge. According to the output of the state of charge estimation model, the battery management system can determine the state of charge estimation result at the current moment.

[0035] The technical solution of the embodiment of the present invention determines the reference state of charge at the current moment based on the ampere-hour integration method according to the state of charge at the previous moment; if the reference state of charge is within the preset state of charge range, the state of charge estimation result at the current moment is determined based on the battery operation data associated with the current moment and the pre-trained state of charge estimation model; the preset state of charge range is the state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments. This solution solves the problem of low accuracy of state of charge estimation by identifying the non-voltage platform area of ​​the battery and predicting the state of charge at the moment of the non-voltage platform area based on the model estimation method, which is conducive to realizing accurate estimation of the state of charge during the full operation cycle of the lithium-ion battery and ensuring the reliability of the state of charge prediction.

[0036] Embodiment 2

[0037] Figure 2 This is a flow chart of a method for estimating a battery state of charge provided in Embodiment 2 of the present invention. This embodiment refines the above embodiment. Figure 2 As shown, the method includes:

[0038] S201, determining whether the charge state at the previous moment meets a preset validity detection condition.

[0039] The battery management system can pre-set validity detection conditions to evaluate whether the state of charge at the previous moment can be used as a basis for estimating the state of charge at the current moment. The validity detection conditions may include conditions such as the state of charge at the previous moment is not empty and the state of charge at the previous moment is within the state of charge range matched by the battery. If the state of charge at the previous moment meets the preset validity detection conditions, the battery management system can continue to execute S202. If the state of charge at the previous moment does not meet the preset validity detection conditions, the battery management system can execute S204 to further determine whether the current moment is a stationary point.

[0040] S202: Determine whether an error condition of the ampere-hour integration method is met based on the throughput at the previous moment and the throughput at the current moment.

[0041] If the state of charge at the previous moment meets the preset validity detection condition, the battery management system can obtain the operating status data at the previous moment and the operating status data at the current moment, and determine whether the error condition of the ampere-hour integration method is met based on the throughput in the operating status data. In this solution, the error condition of the ampere-hour integration method is that the throughput change is less than or equal to the preset capacity threshold. The battery management system can calculate the difference between the throughput at the previous moment and the throughput at the current moment to obtain the throughput change. The preset capacity threshold can be set based on the battery capacity. For example, the preset capacity threshold can be twice the battery capacity. If the error condition of the ampere-hour integration method is met, the battery management system can continue to execute S203. If the error condition of the ampere-hour integration method is not met, the battery management system can execute S210.

[0042] S203 , determining a first reference state of charge at a current moment according to the state of charge at a previous moment based on an ampere-hour integration method.

[0043] The first reference state of charge is a reference state of charge determined based on an ampere-hour integration method. The calculation formula of the first reference state of charge can be expressed as: Among them, SOC ri Indicates the first reference state of charge at the current moment, SOC i-1 Indicates the state of charge at the previous moment, C N represents the battery capacity, i represents the time index, η represents the charge and discharge efficiency, I represents the battery current, and τ represents the integral variable.

[0044] The battery management system can calculate the first reference state of charge at the current moment based on the above calculation formula and the state of charge at the previous moment.

[0045] S204: Determine whether the current moment is a stationary point according to the running status data at the current moment.

[0046] The battery management system can extract the current current from the current operating status data to determine whether the current current is less than the set current threshold. At the same time, the battery management system can also obtain the duration of the current less than the preset current threshold.

[0047] If the current at the current moment is less than the preset current threshold, and the duration of the current less than the preset current threshold is greater than or equal to the preset duration threshold, the current moment is determined to be a stationary point. If the current at the current moment is greater than or equal to the preset current threshold, or the duration of the current less than the preset current threshold is less than the preset duration threshold, the current moment is determined not to be a stationary point.

[0048] If the current moment is a stationary point, the battery management system may continue to execute S205 ; if the current moment is not a stationary point, the battery management system may execute S210 .

[0049] S205: Acquire the state of charge matched at the stationary point as a second reference state of charge at the current moment.

[0050] Different from the first reference state of charge, the second reference state of charge is a reference state of charge determined based on the relationship between the state of charge and the circuit voltage. If the current moment is a static point, the battery management system can determine the battery open circuit voltage (OCV) corresponding to the static point, obtain the state of charge matching the static point based on the correlation between the state of charge and the open circuit voltage, and use the state of charge corresponding to the static point as the second reference state of charge at the current moment. It is easy to understand that the correlation between the battery open circuit voltage and the state of charge can be obtained based on the experimental data of the battery, and the correlation between the battery open circuit voltage and the state of charge is usually expressed as a nonlinear relationship.

[0051] S206: Determine whether the first reference state of charge is within a preset state of charge range.

[0052] If the reference state of charge is within the preset state of charge range, the battery management system may continue to execute S207 ; if the reference state of charge is not within the preset state of charge range, the battery management system may continue to execute S208 .

[0053] S207. Determine the state of charge estimation result at the current moment according to the battery operation data associated with the current moment and based on a pre-trained state of charge estimation model; the battery operation data includes operation state data of the battery at multiple consecutive moments.

[0054] In this solution, the battery operation data includes the battery operation status data at multiple consecutive moments, and the operation status data includes voltage, current, temperature, throughput and health status. The state of charge estimation model can predict the state of charge more accurately and reliably based on the multi-dimensional operation status data.

[0055] Based on the above scheme, the state of charge estimation model includes a first convolution unit, a time domain convolution unit, a multi-head attention unit, a gated recurrent unit, a second convolution unit, a residual unit and a fully connected unit;

[0056] Among them, the first convolution unit, the time domain convolution unit, the multi-head attention unit, the gated recurrent unit and the second convolution unit are connected in sequence;

[0057] The first convolution unit is used to extract features from the running status data at each moment to obtain the first data features matched at each moment; the time domain convolution unit is used to determine the second data features according to the running status features matched at each moment; the multi-head attention unit is used to determine the third data features of multiple dimensions according to the second data features; the gated loop unit is used to determine the fourth data features according to the third data features of multiple dimensions; the second convolution unit is used to extract features from the fourth data features to obtain the fifth data features; the residual unit is used to merge the running status data with the fifth data features to obtain the merged features; the fully connected unit is used to determine the charge state of the battery at the current moment according to the merged features.

[0058] The multi-head attention unit can be a neural network unit constructed based on a multi-head attention mechanism with linear complexity. The state of charge is affected by multiple factors, such as temperature, current, and historical charge and discharge status. The operating status data at different times have different effects on the state of charge. The attention mechanism allows the state of charge estimation model to automatically adjust the weight at each moment, focusing on the most critical information for state of charge prediction, while ignoring redundant information, which greatly improves the prediction accuracy, adaptability, and robustness to abnormal data of the state of charge estimation model.

[0059] The gated recurrent unit can be constructed based on a gated recurrent network (Gated Recurrent Network, GRU). The gated recurrent unit and the multi-head attention unit have high computational efficiency in processing time series data. Compared with the long short-term memory network, the gated recurrent unit has fewer parameters and lower computational complexity, so the state of charge estimation model has a significant advantage in reasoning speed. The temporal convolution unit is constructed based on a temporal convolutional network (Temporal Convolutional Network, TCN), which can further improve the parallel computing efficiency of the state of charge estimation model. The temporal convolution unit can effectively capture the dependencies of various time dimensions through dilated convolution, while keeping the state of charge estimation model lightweight, while improving the speed and accuracy of training and reasoning.

[0060] S208: Using the reference state of charge as a state of charge estimation result at the current moment.

[0061] For the moment in the voltage platform region, the battery management system can directly use the reference state of charge as the state of charge estimation result at the current moment.

[0062] S209: Determine whether the second reference state of charge is within a preset state of charge range.

[0063] If the second reference state of charge is within the preset state of charge range, S207 is executed; if the second reference state of charge is not within the preset state of charge range, S210 is executed.

[0064] S210: Update the current moment to the previous moment, and update the next moment to the current moment.

[0065] After obtaining the current state of charge, the battery management system may record the current state of charge, update the current moment to the previous moment, update the next moment to the current moment, and return to execute S201 to estimate the state of charge at subsequent moments.

[0066] If the error condition of the ampere-hour integration method is not met, the current moment is not a stationary point, or the second reference state of charge is not within the preset state of charge range, it means that the operating status data at the current moment does not meet the requirements and the state of charge at the current moment cannot be accurately estimated. The battery management system can update the current moment to the previous moment, update the next moment to the current moment, and return to execute S201 to start the state of charge estimation at the new moment.

[0067] The technical solution of the embodiment of the present invention determines the reference state of charge at the current moment based on the ampere-hour integration method according to the state of charge at the previous moment; if the reference state of charge is within the preset state of charge range, the state of charge estimation result at the current moment is determined based on the battery operation data associated with the current moment and the pre-trained state of charge estimation model; the preset state of charge range is the state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments. This solution solves the problem of low accuracy of state of charge estimation by identifying the non-voltage platform area of ​​the battery and predicting the state of charge at the moment of the non-voltage platform area based on the model estimation method, which is conducive to realizing accurate estimation of the state of charge during the full operation cycle of the lithium-ion battery and ensuring the reliability of the state of charge prediction.

[0068] Embodiment 3

[0069] Figure 3 This is a schematic diagram of the structure of a battery state of charge estimation device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0070] A reference state determination module 310, for determining a reference state of charge at a current moment based on the state of charge at a previous moment and based on an ampere-hour integration method;

[0071] The estimation result determination module 320 is used to determine the state of charge estimation result at the current moment based on the battery operation data associated with the current moment and a pre-trained state of charge estimation model if the reference state of charge is within a preset state of charge range; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; and the battery operation data includes the operation state data of the battery at multiple consecutive moments.

[0072] In this solution, the reference state determination module 310 includes:

[0073] An error condition judgment unit, used to determine whether an error condition of the ampere-hour integration method is satisfied according to the throughput at a previous moment and the throughput at a current moment; the error condition of the ampere-hour integration method is that the throughput change is less than or equal to a preset capacity threshold;

[0074] The reference state determination unit is used to determine a first reference state of charge at a current moment based on the ampere-hour integration method according to the state of charge at a previous moment if the error condition of the ampere-hour integration method is met.

[0075] On the basis of the above solution, the error condition judgment unit is specifically used to:

[0076] Determine whether the charge state at the previous moment meets the preset validity detection condition;

[0077] If the preset validity detection condition is met, it is determined whether the error condition of the ampere-hour integration method is met based on the throughput at the previous moment and the throughput at the current moment.

[0078] Optionally, the error condition judgment unit is further used to:

[0079] After determining whether the charge state at the previous moment meets the preset validity detection condition, if the preset validity detection condition is not met, determining whether the current moment is a stationary point according to the running state data at the current moment;

[0080] If the current moment is a stationary point, the state of charge matching the stationary point is obtained as the second reference state of charge at the current moment.

[0081] In a feasible solution, the operating status data includes voltage, current, temperature, throughput and health status.

[0082] Based on the above scheme, the state of charge estimation model includes a first convolution unit, a time domain convolution unit, a multi-head attention unit, a gated recurrent unit, a second convolution unit, a residual unit and a fully connected unit;

[0083] Among them, the first convolution unit, the time domain convolution unit, the multi-head attention unit, the gated recurrent unit and the second convolution unit are connected in sequence;

[0084] The first convolution unit is used to extract features from the running status data at each moment to obtain the first data features matched at each moment; the time domain convolution unit is used to determine the second data features according to the running status features matched at each moment; the multi-head attention unit is used to determine the third data features of multiple dimensions according to the second data features; the gated loop unit is used to determine the fourth data features according to the third data features of multiple dimensions; the second convolution unit is used to extract features from the fourth data features to obtain the fifth data features; the residual unit is used to merge the running status data with the fifth data features to obtain the merged features; the fully connected unit is used to determine the charge state of the battery at the current moment according to the merged features.

[0085] The battery state of charge estimation device provided in the embodiment of the present invention can execute the battery state of charge estimation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0086] Embodiment 4

[0087] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement an embodiment of the present invention is shown. The electronic device 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 electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. 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 required herein.

[0088] like Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0089] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0090] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a method for estimating the battery state of charge.

[0091] In some embodiments, the method for estimating the battery state of charge may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the method for estimating the battery state of charge described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to perform the method for estimating the battery state of charge in any other appropriate manner (e.g., by means of firmware).

[0092] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can 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.

[0093] The 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 battery state of charge estimation 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 as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0094] 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 combination 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 (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. 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).

[0096] 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: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0097] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0098] 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.

[0099] 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 estimating a battery state of charge, characterized in that: The method comprises: According to the state of charge at the previous moment, based on the ampere-hour integration method, the reference state of charge at the current moment is determined; If the reference state of charge is within a preset state of charge range, the state of charge estimation result at the current moment is determined according to the battery operation data associated with the current moment and based on a pre-trained state of charge estimation model; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; the battery operation data includes the operation state data of the battery at multiple consecutive moments.

2. The method according to claim 1, characterized in that The step of determining the reference state of charge at the current moment based on the state of charge at the previous moment and based on the ampere-hour integration method includes: Determine whether an error condition of the ampere-hour integration method is met according to the throughput at the previous moment and the throughput at the current moment; the error condition of the ampere-hour integration method is that the throughput change is less than or equal to a preset capacity threshold; If the error condition of the ampere-hour integration method is met, the first reference state of charge at the current moment is determined based on the ampere-hour integration method according to the state of charge at the previous moment.

3. The method according to claim 2, characterized in that The determining whether the error condition of the ampere-hour integration method is satisfied according to the throughput at the previous moment and the throughput at the current moment includes: Determine whether the charge state at the previous moment meets the preset validity detection condition; If the preset validity detection condition is met, it is determined whether the error condition of the ampere-hour integration method is met based on the throughput at the previous moment and the throughput at the current moment.

4. The method according to claim 3, characterized in that After determining whether the state of charge at the previous moment meets the preset validity detection condition, the method further includes: If the preset validity detection condition is not met, determine whether the current moment is a stationary point based on the running status data at the current moment; If the current moment is a stationary point, the state of charge matching the stationary point is obtained as the second reference state of charge at the current moment.

5. The method according to claim 1, characterized in that The operating status data includes voltage, current, temperature, throughput, and health status.

6. The method according to claim 5, characterized in that The state of charge estimation model includes a first convolution unit, a time domain convolution unit, a multi-head attention unit, a gated recurrent unit, a second convolution unit, a residual unit and a fully connected unit; Among them, the first convolution unit, the time domain convolution unit, the multi-head attention unit, the gated recurrent unit and the second convolution unit are connected in sequence; The first convolution unit is used to extract features from the running status data at each moment to obtain the first data features matched at each moment; the time domain convolution unit is used to determine the second data features according to the running status features matched at each moment; the multi-head attention unit is used to determine the third data features of multiple dimensions according to the second data features; the gated loop unit is used to determine the fourth data features according to the third data features of multiple dimensions; the second convolution unit is used to extract features from the fourth data features to obtain the fifth data features; the residual unit is used to merge the running status data with the fifth data features to obtain the merged features; the fully connected unit is used to determine the charge state of the battery at the current moment according to the merged features.

7. A battery state of charge estimation device, characterized in that: The device comprises: A reference state determination module, used to determine the reference state of charge at the current moment based on the state of charge at the previous moment and based on the ampere-hour integration method; An estimation result determination module is used to determine the state of charge estimation result at the current moment based on the battery operation data associated with the current moment and a pre-trained state of charge estimation model if the reference state of charge is within a preset state of charge range; the preset state of charge range is a state of charge range that matches the non-voltage platform area of ​​the battery; and the battery operation data includes the operation state data of the battery at multiple consecutive moments.

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 state of charge estimation method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for estimating the battery state of charge according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for estimating the battery state of charge according to any one of claims 1 to 6.

Images