Estimation method and device of state of charge of sodium-ion battery and readable storage medium

Abstract

The invention relates to the technical field of sodium-ion batteries, and discloses a sodium-ion battery state-of-charge estimation method and device and a readable storage medium. The method comprises the following steps: acquiring the state of the sodium-ion battery and determining an initial charge state; collecting actual operation data, preprocessing the actual operation data to obtain battery data, and determining battery change data according to the battery data; determining the actual available capacity and the corrected internal resistance of the sodium ion battery according to the temperature data; determining a charge state estimation value according to the initial charge state, the actual available capacity and the current data; according to the battery data, the battery change data, the actual available capacity and the corrected internal resistance, utilizing a pre-trained feedforward neural network to predict a charge state correction value; and determining a final charge state according to the charge state estimation value and the charge state correction value. The precision, the real-time performance and the adaptability of sodium ion battery state-of-charge estimation are effectively improved, and the requirements of various application scenes are met.

Description

Technical Field

[0001] This application relates to the field of sodium-ion battery technology, specifically to a method, apparatus, and readable storage medium for estimating the state of charge of a sodium-ion battery. Background Technology

[0002] Sodium-ion batteries, as an energy storage device with high safety and environmental friendliness, offer lower costs and longer lifespans, meeting the energy balance requirements of new power grids and addressing energy fluctuations. In recent years, they have gradually begun to replace lithium-ion batteries, gaining increasing attention and application. Accurate estimation of the state of charge (SOC) is crucial in the research, development, production, and practical application of sodium-ion batteries, directly impacting the safety, reliability, and efficiency of the battery system. Currently, commonly used methods for estimating battery SOC include the ampere-hour integration method and the open-circuit voltage method.

[0003] While the ampere-hour integration method is simple in principle, its state of charge (SOC) value can only be calibrated when the battery is at a low or high initial SOC, resulting in some error in the intermediate stage of initial SOC estimation. Due to the presence of current errors, the estimation error of SOC accumulates, leading to significant inaccuracies in battery status assessment. Furthermore, the ampere-hour integration method is greatly affected by factors such as current measurement accuracy and initial SOC setting, making it prone to inaccurate estimation data.

[0004] The open-circuit voltage method requires the battery to be stationary for an extended period to obtain a stable open-circuit voltage. Based on the relationship between the battery's open-circuit voltage (OCV) and its charge level, the relationship between the battery's OCV and its state of charge (SOC) is indirectly fitted to obtain an estimated SOC. However, the open-circuit voltage method cannot meet the real-time estimation requirements of dynamic usage scenarios.

[0005] Furthermore, the ampere-hour integration method and open-circuit voltage method are primarily based on lithium-ion battery design. However, sodium-ion batteries exhibit more complex temperature-dependent characteristics compared to lithium-ion batteries. The battery capacity and charge / discharge efficiency of sodium-ion batteries change significantly with temperature, leading to larger errors in estimating their state of charge (SOC). Methods suitable for lithium-ion batteries cannot effectively manage the operating state of sodium-ion batteries to ensure their safe and efficient performance.

[0006] Existing SOC estimation methods cannot meet the requirements of high accuracy, real-time performance, and adaptability in practical applications of sodium-ion batteries. Therefore, it is urgent to design a method for estimating the state of charge of sodium-ion batteries to solve the above problems. Summary of the Invention

[0007] To address the aforementioned issues, this application provides a method, apparatus, and readable storage medium for estimating the state of charge (SOC) of a sodium-ion battery, thereby overcoming the drawback that existing battery SOC estimation methods are unsuitable for application to sodium-ion batteries.

[0008] The embodiments of this application adopt the following technical solutions: In a first aspect, this application provides a method for estimating the state of charge of a sodium-ion battery, comprising: Obtain the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state. The actual operating data of the sodium-ion battery is collected, and the actual operating data is preprocessed to obtain battery data. Based on the battery data, the battery change data is determined. The battery data includes voltage data, current data, and temperature data, and the battery change data includes voltage change rate, current change rate, and power change. Determine the actual usable capacity and corrected internal resistance of sodium-ion batteries based on temperature data; The estimated state of charge is determined based on the initial state of charge, actual available capacity, and current data. Based on battery data, battery change data, actual usable capacity and corrected internal resistance, a pre-trained feedforward neural network is used to predict the corrected state of charge value. The final state of charge of the sodium-ion battery is determined based on the estimated state of charge and the corrected state of charge.

[0009] Secondly, this application also provides a device for estimating the state of charge of a sodium-ion battery, comprising: The acquisition unit is used to acquire the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state. The data acquisition unit is used to collect actual operating data of the sodium-ion battery, preprocess the actual operating data to obtain battery data, and determine battery change data based on the battery data. The battery data includes voltage data, current data, and temperature data, and the battery change data includes voltage change rate, current change rate, and power change. The correction unit is used to determine the actual usable capacity of the sodium-ion battery and correct its internal resistance based on temperature data. The estimation unit is used to determine the estimated state of charge based on the initial state of charge, actual available capacity, and current data. The prediction unit is used to predict the state of charge correction value using a pre-trained feedforward neural network based on battery data, battery change data, actual available capacity and corrected internal resistance. The calculation unit is used to determine the final state of charge of the sodium-ion battery based on the estimated state of charge and the corrected state of charge.

[0010] Thirdly, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for estimating the state of charge of a sodium-ion battery.

[0011] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when instructed by a processor, implements the steps of the above-described method for estimating the state of charge of a sodium-ion battery.

[0012] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: This application obtains battery data and battery change data by real-time acquisition of actual operating data of sodium-ion batteries and preprocessing the data. Based on temperature data, the actual usable capacity and internal resistance are determined. The final state of charge of the sodium-ion battery is determined by combining an estimation model based on the ampere-hour integral method and a pre-trained feedforward neural network.

[0013] The entire estimation process is based on real-time collected actual operating data for processing and calculation. It can quickly respond to changes in battery status and adapt to the estimation of the state of charge of sodium-ion batteries under different states and operating conditions, ensuring the accuracy of the state of charge estimation of sodium-ion batteries.

[0014] By integrating multiple parameters, the characteristics of sodium-ion batteries under different operating conditions are fully considered, effectively improving the estimation accuracy and meeting the real-time requirements of applications such as electric vehicles and energy storage systems.

[0015] The method proposed in this application effectively solves the problem of error accumulation in the ampere-hour integration method and overcomes the drawback of the open-circuit voltage method in failing to meet the real-time estimation requirements under dynamic usage scenarios, making the estimation results more accurate and stable. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a method for estimating the state of charge of a sodium-ion battery according to an embodiment of this application is shown. Figure 2 A schematic diagram of a sodium-ion battery state-of-charge estimation device according to an embodiment of this application is shown. Figure 3 A schematic diagram of the resulting electronic device according to an embodiment of this application is shown. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] This application aims to address the shortcomings of existing technologies such as the ampere-hour integration method and open-circuit voltage method, which are primarily applicable to lithium-ion batteries and cannot meet the real-time estimation requirements of sodium-ion batteries due to their high temperature dependence and dynamic usage scenarios. To solve these problems, Figure 1 This application illustrates a method for estimating the state of charge (SOC) of a sodium-ion battery according to one embodiment of the present application. Figure 1 As can be seen, this embodiment includes steps S110 to S160: Step S110: Obtain the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state.

[0019] A sodium-ion battery, the state of which needs to be estimated, was selected for the experiment. A high-precision battery testing system was used to monitor the battery's state in real time. The states included fully charged, fully discharged, and start-up states. The initial state of charge (SBC) of the sodium-ion battery was determined and recorded based on its SBC status. The initial SBC record of the sodium-ion battery is as follows: For example, the initial state of charge. .

[0020] Therefore, in some optional embodiments, step S110, obtaining the state of the sodium-ion battery and determining the initial state of charge of the sodium-ion battery based on the state, includes: detecting the state of the sodium-ion battery in real time through a battery testing system; wherein the state includes a fully charged state, a fully discharged state, and a start-up state; and recording the initial state of charge of the sodium-ion battery.

[0021] Step S120: Collect actual operating data of sodium-ion battery, preprocess the actual operating data to obtain battery data, and determine battery change data based on the battery data; wherein, battery data includes voltage data, current data and temperature data, and battery change data includes voltage change rate, current change rate and power change amount.

[0022] The battery testing system simultaneously acquires actual voltage and current data from sodium-ion batteries and uses a temperature sensor to monitor the actual surface temperature of the batteries in real time. The system transmits various data to a computing module via a data acquisition card for processing. For example, it performs charge and discharge operations on the sodium-ion batteries and simultaneously acquires various actual operating data and cycle counts. .

[0023] The battery testing system collects the terminal voltage of the sodium-ion battery as actual voltage data and the charging and discharging current of the sodium-ion battery as actual current data based on a preset sampling interval. For example, the preset sampling interval is 100ms.

[0024] Median filtering was used to preprocess the actual voltage and current data to obtain the voltage and current data respectively.

[0025] For the collected actual voltage data, the median of n consecutive sampling points (n is an odd number greater than or equal to 3) is taken as the current voltage data. For example: the actual voltage data of 5 consecutive sampling points are as follows... , , , , The current voltage data is .

[0026] For the collected actual current data, the median of n consecutive sampling points (n is an odd number greater than or equal to 3) is taken as the current current data. For example: the actual current data of 5 consecutive sampling points are as follows... , , , , The current current data is .

[0027] In this way, abnormal pulse interference is removed from the actual voltage and current data.

[0028] The surface temperature of the sodium-ion battery is collected as actual temperature data using a temperature sensor at a preset sampling interval. For example, the preset sampling interval is 100ms.

[0029] The actual temperature data is preprocessed using a moving average filter to obtain the temperature data.

[0030] For the collected actual temperature data, a 5-point moving average filter is used to average the actual temperature data of the current sampling point and the previous 4 sampling points to obtain the smoothed current temperature data. For example: the actual temperature data of the current sampling point and the previous 4 sampling points are as follows: , , , , The current temperature data is .

[0031] This effectively improves the stability and reliability of temperature data.

[0032] After preprocessing the actual voltage and current data, the voltage change rate, current change rate, and power change can be further determined. These three change data are used as battery change data.

[0033] For the rate of change of voltage For the rate of change of current, For the change in power, ;in, This indicates the preset time interval between two sampling points.

[0034] Therefore, in some optional embodiments, step S120, collecting actual operating data of the sodium-ion battery, preprocessing the actual operating data to obtain battery data, and determining battery change data based on the battery data, includes: collecting actual voltage data and actual current data of the sodium-ion battery through a battery testing system based on a preset sampling interval, preprocessing the actual voltage data and actual current data using median filtering to obtain voltage data and current data respectively; collecting actual temperature data of the sodium-ion battery through a temperature sensor based on a preset sampling interval, preprocessing the actual temperature data using moving average filtering to obtain temperature data; determining the voltage change rate based on the voltage data of two adjacent sampling points, determining the current change rate based on the current data of two adjacent sampling points, and determining the power change amount based on the voltage data and current data of two adjacent sampling points.

[0035] Step S130: Determine the actual usable capacity and corrected internal resistance of the sodium-ion battery based on the temperature data.

[0036] Based on the temperature data obtained after preprocessing, the rated capacity of the battery is corrected using a pre-established temperature-capacity correction model to obtain the corrected actual usable capacity.

[0037] The temperature-capacity correction model is as follows: ;Formula (1).

[0038] in, Indicates the actual available capacity. Indicates the battery's rated capacity. Indicates the temperature coefficient. This indicates the current temperature data. Indicates the standard temperature.

[0039] Furthermore, based on the temperature data obtained after preprocessing, and according to the pre-established temperature-battery internal resistance relationship, the corrected internal resistance of the sodium-ion battery can also be determined. .

[0040] The relationship between temperature and battery internal resistance is as follows: ;Formula (2).

[0041] in, This indicates a correction of internal resistance. This indicates the fitting relationship.

[0042] The pre-established temperature-battery internal resistance relationship can be obtained through experimental calibration. A sodium-ion battery is placed in a constant-temperature environment and allowed to stand until it reaches thermal stability. A small current pulse of preset amplitude is applied to the sodium-ion battery, and the equivalent internal resistance under this constant-temperature environment is calculated based on the voltage and current changes. The constant-temperature environment is modified, and the above process is repeated under the same initial state of charge of the sodium-ion battery and the same standing time. Multiple sets of data points corresponding to the constant-temperature environment and the equivalent internal resistance are obtained. These data points are then fitted to obtain the temperature-battery internal resistance relationship. The relationship between sodium-ion batteries may take the form of linear, piecewise linear, polynomial, or exponential relationships, depending on the specific experimental calibration results.

[0043] Therefore, in some optional embodiments, step S130, determining the actual usable capacity and corrected internal resistance of the sodium-ion battery based on temperature data, includes: correcting the rated capacity of the sodium-ion battery using a pre-established temperature-capacity correction model based on the temperature data to obtain the actual usable capacity; wherein, the temperature-capacity correction model is: ;in, Indicates the actual available capacity. Indicates the battery's rated capacity. Indicates the temperature coefficient. This indicates the current temperature data. The standard temperature is represented; based on the temperature data, the corrected internal resistance of the sodium-ion battery is determined according to the pre-established temperature-battery internal resistance relationship; wherein, the temperature-battery internal resistance relationship is: ;in, This indicates a correction of internal resistance. This indicates the fitting relationship.

[0044] Step S140: Determine the estimated state of charge based on the initial state of charge, actual available capacity, and current data.

[0045] Based on the initial state of charge, actual available capacity, and current data, the estimated value of the state of charge is determined using an estimation model based on the ampere-hour integral method.

[0046] Based on the ampere-hour integration method, an adaptive current correction factor is introduced. This factor is dynamically adjusted according to the actual and historical data of the sodium-ion battery to compensate for the influence of current measurement errors and the nonlinear characteristics of the battery on the integration results. The typical range of the adaptive current correction factor is [0.98, 1.02], with a default value of 1.0. However, under extreme conditions (e.g., low temperature (not higher than -10℃), high-rate discharge (not less than 1P), and sodium-ion battery aging degree not less than 80% SOH), the range of the adaptive current correction factor is extended to [0.95, 1.05] to avoid overcorrection leading to amplified state-of-charge deviation. Factors affecting the value of the adaptive current correction factor include current measurement error (±1%). For example, when an abnormal change in the sodium-ion battery current is detected, the adaptive current correction factor is appropriately increased to compensate for potential current measurement errors.

[0047] The estimation model based on the ampere-hour integral method is as follows: ;Formula (3).

[0048] in, This represents the estimated state of charge. Indicates the initial state of charge. This represents the adaptive current correction factor. This indicates the current current data. This indicates the actual available capacity.

[0049] Therefore, in some optional implementations, step S140, determining the estimated state of charge (SOC) based on the initial SOC, actual available capacity, and current data, includes: determining the estimated SOC using an estimation model based on the ampere-hour integral method based on the initial SOC, actual available capacity, and current data; wherein the estimation model based on the ampere-hour integral method is: ;in, This represents the estimated state of charge. Indicates the initial state of charge. This represents the adaptive current correction factor. This indicates the current current data. This indicates the actual available capacity.

[0050] Step S150: Based on battery data, battery change data, actual available capacity and corrected internal resistance, a pre-trained feedforward neural network is used to predict the state of charge correction value.

[0051] Voltage data Current data Temperature data Actual available capacity Correcting internal resistance Voltage change rate Current change rate Power change The pre-trained feedforward neural network outputs a state-of-charge correction value, which serves as the input to the pre-trained feedforward neural network. .

[0052] The feedforward neural network employs a multi-layer feedforward neural network with three hidden layers. The number of nodes in the input layer of this feedforward neural network is consistent with the number of input features, which is determined to be eight. The number of nodes in each hidden layer of this feedforward neural network are 16, 16, and 8, respectively. The number of nodes in the output layer of this feedforward neural network is one, which is the output state of charge correction value.

[0053] The feedforward neural network is pre-trained using a large number of training samples. During training, the Adam optimization algorithm is used to adjust the weights and thresholds of the feedforward neural network, and the mean squared error (MSE) is selected as the loss function. After pre-training with training samples, the feedforward neural network can learn the complex mapping relationship between the input and output features of sodium-ion batteries under different operating conditions.

[0054] Therefore, in some optional implementations, step S150, predicting the state-of-charge correction value using a pre-trained feedforward neural network based on battery data, battery change data, actual available capacity, and corrected internal resistance, includes: The feedforward neural network includes an input layer, multiple hidden layers, and an output layer. The feedforward neural network is pre-trained using training samples. During the training process, the Adam optimization algorithm is used to adjust the weights and thresholds of the network, and the loss function is the mean squared error. Battery data, battery change data, actual usable capacity, and corrected internal resistance are input into the pre-trained feedforward neural network, and the state of charge correction value is output based on the pre-trained feedforward neural network.

[0055] Step S160: Determine the final state of charge of the sodium-ion battery based on the estimated state of charge and the corrected state of charge.

[0056] The final state of charge (SOC) is obtained by adding the estimated SOC obtained from the estimation model based on the ampere-hour integral method and the corrected SOC output from the pre-trained feedforward neural network. .

[0057] Therefore, in some optional embodiments, step S160, determining the final state of charge of the sodium-ion battery based on the estimated state of charge and the corrected state of charge, includes: determining the final state of charge of the sodium-ion battery based on the sum of the estimated state of charge and the corrected state of charge.

[0058] In addition, the method in this application embodiment may also include a model update and optimization stage.

[0059] The measured usable capacity of sodium-ion batteries is collected periodically, and the measured usable capacity is compared with the calculated actual usable capacity to determine the deviation between the two. Based on this deviation, the parameters in the temperature-capacity correction model are adjusted, and the pre-trained feedforward neural network is fine-tuned using the latest incremental data. Fine-tuning methods can include gradient descent or the Adam optimization algorithm.

[0060] For example: after each preset number of charge-discharge cycles (e.g., 50), the measured usable capacity of the battery is measured and the deviation from the actual usable capacity is calculated. Based on the deviation, the temperature coefficient in the temperature-capacity correction model is adjusted. Adjustments were made to account for the difference between the actual available capacity and the measured available capacity.

[0061] Simultaneously, the pre-trained feedforward neural network is fine-tuned using the latest incremental data (e.g., 50 times). During the fine-tuning process, most of the weights and thresholds obtained from pre-training remain unchanged, and only the parts related to the incremental data are fine-tuned, so that the feedforward neural network can better adapt to the latest situation of sodium-ion batteries and further improve the output accuracy of the state of charge correction value.

[0062] Therefore, in some optional implementations, the method further includes: measuring the measured usable capacity of the sodium-ion battery after each preset number of charge-discharge cycles; updating the temperature coefficient of the temperature-capacity correction model based on the deviation between the measured usable capacity and the actual usable capacity; and fine-tuning the pre-trained feedforward neural network with incremental data from the preset number of charge-discharge cycles.

[0063] The method proposed in this application will be further described below through specific embodiments.

[0064] The experiment used a sodium-ion battery for which the voltage and current data needed to be estimated, and a high-precision battery testing system was used to monitor the battery's state in real time. Simultaneously, the battery testing system was used to acquire the battery's actual voltage and current data in real time, and a temperature sensor was used to monitor the actual temperature data of the sodium-ion battery in real time. Various real-time data were transmitted to the computing module for processing via a data acquisition card.

[0065] The sodium-ion battery was subjected to charge-discharge experiments at different temperatures (-20℃, 0℃, 25℃, 45℃, 60℃), different charge-discharge rates (0.5C, 1C, 2C, 3C), and different cycle numbers (50, 100, 200, 300 cycles). In one experiment, the sodium-ion battery was charged and discharged under the aforementioned operating conditions.

[0066] For example, in an experiment at 25°C and 1C charge / discharge rate, the battery testing system used a 100ms sampling interval to collect the terminal voltage of the sodium-ion battery as the actual voltage data, the charging and discharging current of the sodium-ion battery as the actual current data, and a temperature sensor to monitor the battery surface temperature as the actual temperature data, and recorded the number of cycles. .

[0067] A few abnormal spikes appeared in the collected actual voltage data. A median filtering algorithm was used to take the median of five consecutive sampling points as the current voltage data. The actual current data was processed in the same way as the actual voltage data. For the collected actual temperature data, a 5-point moving average filter was used, which involves averaging the actual temperature data of the current sampling point and the previous four sampling points to obtain the smoothed current temperature data.

[0068] The voltage change rate is obtained by calculating the voltage and current data from two consecutive sampling points. Current change rate Simultaneously calculate the power change. These battery change data serve as input to the subsequent pre-trained feedforward neural network.

[0069] Based on the temperature data, a pre-established temperature-capacity correction formula is used: The rated capacity of sodium-ion batteries is revised.

[0070] For example, the rated capacity of the battery =10Ah, =0.002 / ℃, =20℃, current temperature data =25℃, then the corrected actual usable capacity =10.1Ah.

[0071] Based on temperature data and a pre-established temperature-battery internal resistance relationship: Determine the corrected internal resistance of the sodium-ion battery.

[0072] The estimation part includes two aspects: one is the estimation model based on the ampere-hour integral method, and the other is the pre-trained feedforward neural network.

[0073] Among them, the estimation model based on the ampere-hour integral method includes: initial state of charge. =100%, calculated by integration based on current data. During the integration process, the adaptive current correction factor is dynamically adjusted using an adaptive algorithm. .

[0074] For example, in the initial stage of charging and discharging, based on the historical and actual conditions of sodium-ion batteries, The initial setting is 1.0. Subsequently, as the charging and discharging process progresses, an adaptive algorithm is used to adjust the settings based on voltage changes, temperature changes, and current fluctuations of the sodium-ion battery. Adjustments should be made. For example, if abnormal changes in the current of the sodium-ion battery are detected, the current should be increased appropriately. The value is used to compensate for potential current measurement errors. The estimated state of charge is obtained through an estimation model based on the ampere-hour integral method. .

[0075] The feedforward neural network part employs a multi-layer feedforward neural network with three hidden layers. The input layer has 8 nodes (including data from three batteries, data on three battery changes, actual usable capacity, and corrected internal resistance), the hidden layers have 16, 16, and 8 nodes respectively, and the output layer has 1 node (i.e., the state-of-charge correction value). ).

[0076] A large amount of training data was used to pre-train the feedforward neural network. During pre-training, the Adam optimization algorithm was used to adjust the weights and thresholds of the feedforward neural network, and the mean squared error (MSE) was selected as the loss function. After multiple training iterations, the feedforward neural network was able to accurately learn the mapping relationship between input features and output features.

[0077] The estimation model based on the ampere-hour integral method is obtained and the output of the pre-trained feedforward neural network Add them together to obtain the final state of charge. .

[0078] Every 50 charge-discharge cycles (i.e. when After reaching 50 cycles, the measured usable capacity of the sodium-ion battery is measured and compared with the actual usable capacity. For example, after the 50th cycle, the measured usable capacity is 9.2 Ah, while the actual usable capacity is 9.5 Ah, with a deviation of [missing value]. C =9.5-9.2=0.3Ah. Based on this deviation, the temperature coefficient α in the temperature-capacity correction model is adjusted.

[0079] At the same time, the pre-trained feedforward neural network is fine-tuned again using the incremental data from the latest 50 iterations.

[0080] Figure 2 An apparatus for estimating the state of charge of a sodium-ion battery according to an embodiment of this application is shown, from... Figure 2 It can be seen that the sodium-ion battery state-of-charge estimation device 200 includes: The acquisition unit 210 is used to acquire the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state. The acquisition unit 220 is used to acquire actual operating data of sodium-ion batteries, preprocess the actual operating data to obtain battery data, and determine battery change data based on the battery data; wherein, the battery data includes voltage data, current data and temperature data, and the battery change data includes voltage change rate, current change rate and power change amount; Correction unit 230 is used to determine the actual usable capacity of the sodium-ion battery and correct the internal resistance based on temperature data; The estimation unit 240 is used to determine the estimated state of charge based on the initial state of charge, actual available capacity, and current data. Prediction unit 250 is used to predict the state of charge correction value using a pre-trained feedforward neural network based on battery data, battery change data, actual available capacity and corrected internal resistance. The calculation unit 260 is used to determine the final state of charge of the sodium-ion battery based on the estimated state of charge and the corrected state of charge.

[0081] In some optional embodiments, in the above-described apparatus, the acquisition unit 210 is used to detect the state of the sodium-ion battery in real time through a battery testing system; wherein the state includes a fully charged state, a fully discharged state, and a start-up state; and to record the initial state of charge of the sodium-ion battery.

[0082] In some optional embodiments, in the above-described apparatus, the acquisition unit 220 is used to acquire actual voltage data and actual current data of the sodium-ion battery through a battery testing system based on a preset sampling interval, and preprocess the actual voltage data and actual current data using median filtering to obtain voltage data and current data respectively; acquire actual temperature data of the sodium-ion battery through a temperature sensor based on a preset sampling interval, and preprocess the actual temperature data using moving average filtering to obtain temperature data; determine the voltage change rate based on the voltage data of two adjacent sampling points, determine the current change rate based on the current data of two adjacent sampling points, and determine the power change based on the voltage data and current data of two adjacent sampling points.

[0083] In some optional embodiments, in the above-described apparatus, the correction unit 230 is used to correct the rated capacity of the sodium-ion battery based on temperature data using a pre-established temperature-capacity correction model to obtain the actual usable capacity; wherein, the temperature-capacity correction model is: ;in, Indicates the actual available capacity. Indicates the battery's rated capacity. Indicates the temperature coefficient. This indicates the current temperature data. The standard temperature is represented; based on the temperature data, the corrected internal resistance of the sodium-ion battery is determined according to the pre-established temperature-battery internal resistance relationship; wherein, the temperature-battery internal resistance relationship is: ;in, This indicates a correction of internal resistance. This indicates the fitting relationship.

[0084] In some optional embodiments, in the above apparatus, the estimation unit 240 is used to determine an estimated state of charge (SOC) value based on an estimation model using the ampere-hour integral method, according to the initial SOC, actual available capacity, and current data; wherein the estimation model based on the ampere-hour integral method is: ;in, This represents the estimated state of charge. Indicates the initial state of charge. This represents the adaptive current correction factor. This indicates the current current data. This indicates the actual available capacity.

[0085] In some optional embodiments, in the above-described apparatus, the feedforward neural network includes: an input layer, multiple hidden layers, and an output layer; a prediction unit 250 is used to pre-train the feedforward neural network using training samples, and during the training process, the Adam optimization algorithm is used to adjust the weights and thresholds of the network, and the loss function is the mean square error; battery data, battery change data, actual available capacity, and corrected internal resistance are input into the pre-trained feedforward neural network, and the state of charge correction value is output based on the pre-trained feedforward neural network.

[0086] In some alternative embodiments, in the above-described apparatus, the calculation unit 260 is used to determine the final state of charge of the sodium-ion battery based on the sum of the estimated state of charge and the corrected state of charge.

[0087] In some optional embodiments, the above-mentioned device further includes a fine-tuning unit for measuring the measured usable capacity of the sodium-ion battery after each preset number of charge-discharge cycles; updating the temperature coefficient of the temperature-capacity correction model based on the deviation between the measured usable capacity and the actual usable capacity; and fine-tuning the pre-trained feedforward neural network with incremental data from the preset number of charge-discharge cycles.

[0088] It should be noted that the sodium-ion battery state of charge estimation device 200 described above can implement the aforementioned sodium-ion battery state of charge estimation method, which will not be elaborated further.

[0089] Figure 3 This invention illustrates a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3As shown, the electronic device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used for communication with external devices via a network connection. When executed by the processor, the computer program implements the functions or steps of a method for estimating the state of charge of a sodium-ion battery.

[0090] In one embodiment, the electronic device provided in this application includes a memory and a processor. The memory stores a database and a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the aforementioned method for estimating the state of charge of a sodium-ion battery.

[0091] The above is as stated in this application. Figure 2 The method for estimating the state of charge of a sodium-ion battery disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0092] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the aforementioned method for estimating the state of charge of a sodium-ion battery.

[0093] It should be noted that the functions or steps that the above-mentioned electronic devices or computer-readable storage media can achieve can be referred to the relevant descriptions in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0094] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0095] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0096] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for estimating the state of charge of a sodium-ion battery, characterized in that, include: Obtain the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state. The actual operating data of the sodium-ion battery is collected, and the actual operating data is preprocessed to obtain battery data. Based on the battery data, the battery change data is determined. The battery data includes voltage data, current data, and temperature data, and the battery change data includes voltage change rate, current change rate, and power change. Determine the actual usable capacity and corrected internal resistance of sodium-ion batteries based on temperature data; The estimated state of charge is determined based on the initial state of charge, actual available capacity, and current data. Based on battery data, actual usable capacity, actual internal resistance, and battery change data, a pre-trained feedforward neural network is used to predict the state of charge correction value. The final state of charge of the sodium-ion battery is determined based on the estimated state of charge and the corrected state of charge.

2. The method according to claim 1, characterized in that, The process of acquiring the state of the sodium-ion battery and determining the initial state of charge of the sodium-ion battery based on the state includes: The state of the sodium-ion battery is monitored in real time through a battery testing system, which includes fully charged state, fully discharged state, and start-up state. Record the initial state of charge of the sodium-ion battery.

3. The method according to claim 1, characterized in that, The process involves collecting actual operating data from the sodium-ion battery, preprocessing the actual operating data to obtain battery data, and determining battery change data based on the battery data, including: The actual voltage and actual current data of sodium-ion batteries are collected by the battery testing system based on a preset sampling interval. Median filtering is used to preprocess the actual voltage and actual current data to obtain the voltage and current data respectively. The actual temperature data of the sodium-ion battery is collected by a temperature sensor based on a preset sampling interval. The actual temperature data is preprocessed by a moving average filter to obtain the temperature data. The voltage change rate is determined based on the voltage data of two adjacent sampling points, the current change rate is determined based on the current data of two adjacent sampling points, and the power change is determined based on the voltage and current data of two adjacent sampling points.

4. The method according to claim 1, characterized in that, The process of determining the actual usable capacity and corrected internal resistance of a sodium-ion battery based on temperature data includes: Based on temperature data, the rated capacity of the sodium-ion battery is corrected using a pre-established temperature-capacity correction model to obtain the actual usable capacity; the temperature-capacity correction model is as follows: ； in, Indicates the actual available capacity. Indicates the battery's rated capacity. Indicates the temperature coefficient. This indicates the current temperature data. Indicates standard temperature; Based on temperature data, the corrected internal resistance of the sodium-ion battery is determined according to a pre-established temperature-battery internal resistance relationship; wherein, the temperature-battery internal resistance relationship is: ； in, This indicates a correction of internal resistance. This indicates the fitting relationship.

5. The method according to claim 1, characterized in that, The process of determining the estimated state of charge based on the initial state of charge, actual available capacity, and current data includes: Based on the initial state of charge, actual available capacity, and current data, the estimated state of charge is determined using an estimation model based on the ampere-hour integral method; the estimation model based on the ampere-hour integral method is as follows: ； in, This represents the estimated state of charge. Indicates the initial state of charge. This represents the adaptive current correction factor. This indicates the current current data. This indicates the actual available capacity.

6. The method according to claim 1, characterized in that, The step of predicting the state-of-charge correction value using a pre-trained feedforward neural network based on battery data, battery change data, actual usable capacity, and corrected internal resistance includes: A feedforward neural network consists of an input layer, multiple hidden layers, and an output layer. The feedforward neural network is pre-trained using training samples. During the training process, the Adam optimization algorithm is used to adjust the weights and thresholds of the network, and the loss function is the mean squared error. Battery data, battery change data, actual available capacity, and corrected internal resistance are input into a pre-trained feedforward neural network, which then outputs a state-of-charge correction value based on the pre-trained feedforward neural network.

7. The method according to claim 1, characterized in that, Determining the final state of charge (SOC) of the sodium-ion battery based on the estimated SOC and the corrected SOC includes: The final state of charge of the sodium-ion battery is determined by the sum of the estimated state of charge and the corrected state of charge.

8. The method according to claim 4, characterized in that, The method further includes: After each preset number of charge-discharge cycles, the actual usable capacity of the sodium-ion battery is measured. The temperature coefficient of the temperature-capacity correction model is updated based on the deviation between the measured available capacity and the actual available capacity. The pre-trained feedforward neural network is fine-tuned using incremental data from a preset number of charge-discharge cycles.

9. A device for estimating the state of charge of a sodium-ion battery, characterized in that, include: The acquisition unit is used to acquire the state of the sodium-ion battery and determine the initial state of charge of the sodium-ion battery based on the state. The data acquisition unit is used to collect actual operating data of the sodium-ion battery, preprocess the actual operating data to obtain battery data, and determine battery change data based on the battery data. The battery data includes voltage data, current data, and temperature data, and the battery change data includes voltage change rate, current change rate, and power change. The correction unit is used to determine the actual usable capacity of the sodium-ion battery and correct its internal resistance based on temperature data. The estimation unit is used to determine the estimated state of charge based on the initial state of charge, actual available capacity, and current data. The prediction unit is used to predict the state of charge correction value using a pre-trained feedforward neural network based on battery data, battery change data, actual available capacity and corrected internal resistance. The calculation unit is used to determine the final state of charge of the sodium-ion battery based on the estimated state of charge and the corrected state of charge.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is instructed by the processor, it implements the steps of the method for estimating the state of charge of a sodium-ion battery as described in any one of claims 1 to 8.

Images