Intelligent management method and system for general sodium ion battery for electric vehicle and large-scale energy storage

Abstract

The invention provides an intelligent management method and system for an electric vehicle and a large-scale energy storage universal sodium-ion battery, and relates to the technical field of battery management, and the method comprises the steps: carrying out the equalizing charging of a target sodium-ion battery; collecting operation data of the target sodium ion battery in the synchronous working state; preprocessing the operation data to obtain a preprocessed signal; performing feature extraction on the preprocessed signals to obtain operation features corresponding to the signals, and performing feature fusion on the operation features to obtain fusion features; inputting the fusion features into a trained battery state evaluation model to obtain an evaluation result; formulating a management strategy according to the evaluation result, and controlling the charging and discharging process of the target sodium ion battery according to the management strategy. The performance, the safety and the service life of the sodium-ion battery can be remarkably improved, and a powerful guarantee is provided for efficient operation of an electric vehicle and a large-scale energy storage system.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and in particular to an intelligent management method and system for electric vehicles and general sodium-ion batteries for large-scale energy storage. Background Art

[0002] With the rapid development of renewable energy and electric vehicles, the demand for efficient, safe and economical energy storage technology is increasing. Sodium-ion batteries have become a promising energy storage technology due to their abundant resources and low cost. As an emerging energy storage technology, sodium-ion batteries have received increasing attention in the field of electric vehicles and large-scale energy storage in recent years. Compared with traditional lithium-ion batteries, sodium-ion batteries have the following significant advantages:

[0003] (1) Rich resources: Sodium is abundant in the earth's crust, widely distributed, and relatively cheap, which gives sodium-ion batteries a clear advantage in material cost.

[0004] (2) Environmentally friendly: The production and recycling process of sodium ion batteries has little impact on the environment and meets the requirements of sustainable development.

[0005] (3) High safety: Sodium-ion batteries have good stability under overcharge, over-discharge and high temperature conditions, reducing the risk of thermal runaway.

[0006] However, sodium-ion batteries face challenges in practical applications in terms of charge and discharge efficiency, lifespan, safety, etc. Therefore, it is particularly important to develop an intelligent management method to optimize the performance of sodium-ion batteries. Summary of the invention

[0007] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent management method and system for universal sodium-ion batteries for electric vehicles and large-scale energy storage, which can significantly improve the performance, safety and service life of sodium-ion batteries, and provide a strong guarantee for the efficient operation of electric vehicles and large-scale energy storage systems.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] An intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage, comprising:

[0010] Performing balanced charging on the target sodium ion battery so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state;

[0011] Collecting operating data of the target sodium ion battery in a synchronous working state; the operating data includes: voltage signal, current signal, temperature signal and charge and discharge state signal;

[0012] Preprocessing the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal, and a charge and discharge state preprocessing signal;

[0013] Extracting features of the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal, and the charge-discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and fusing each of the operation features to obtain a fusion feature;

[0014] Inputting the fusion features into a trained battery state assessment model to obtain an assessment result;

[0015] A management strategy is formulated according to the evaluation result, and the charging and discharging process of the target sodium ion battery is controlled according to the management strategy.

[0016] Preferably, the target sodium ion battery is balanced charged so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state, comprising:

[0017] Obtaining an equivalent circuit of a target sodium ion battery, and calculating the open circuit voltage data of a single cell according to the equivalent circuit;

[0018] Determine the curve relationship between open circuit voltage data and state of charge;

[0019] Reconstructing the curve relationship to obtain consistency parameters of the single battery; the consistency parameters include a battery capacity estimation value and an initial state of charge estimation value;

[0020] Tracking the consistency parameter by a mean shift tracking algorithm to obtain a tracking result;

[0021] The working state of each single battery is adjusted according to the tracking result.

[0022] Preferably, obtaining the open circuit voltage data of the single cell according to the equivalent circuit calculation includes:

[0023] Determine the ratio of the terminal voltage of the single cell to the terminal voltage of the battery pack as the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack according to the equivalent circuit;

[0024] The open circuit voltage data of the battery pack is obtained by using a recursive least squares algorithm with a forgetting factor;

[0025] The open circuit voltage data of the battery pack is multiplied by the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack to obtain the open circuit voltage data of the single cell.

[0026] Preferably, the calculation formula of the recursive least squares algorithm with forgetting factor is:

[0027]

[0028] θ k =θ k-1 +K k ε k ;

[0029]

[0030] Among them, K k is the update gain, y k is the terminal voltage of the battery pack, is the regression vector, is the transposed matrix of the regression vector, ε k is the prediction error, P k is the error covariance at the current moment, P k-1 is the error covariance of the previous moment, λ k is the forgetting factor, I is the current, is the open circuit voltage data of the battery pack at the current moment, It is the open circuit voltage data of the battery pack at the previous moment.

[0031] Preferably, adjusting the working state of each single battery according to the tracking result includes:

[0032] Analyze the tracking results to identify the single cells in the battery pack whose performance deviation is greater than a preset threshold, determine the single cells greater than the preset threshold as target adjustment cells, and collect the performance deviation of the target adjustment cells;

[0033] The target adjustment battery is supplementarily charged or continuously discharged according to the performance deviation to balance the charge state of the entire battery pack, and the charge and discharge current is dynamically adjusted according to a preset adjustment strategy.

[0034] Preferably, the operation data is preprocessed to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal, including:

[0035] For each signal in the obtained operation data, signal amplification and denoising are performed in sequence to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

[0036] Preferably, the step of denoising the battery temperature preprocessing signal includes:

[0037] Shifting each signal in the operation data to obtain a shifted signal;

[0038] Performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0039] Determine the filtering threshold according to the decomposition scale and length of the signal;

[0040] Constructing a denoising function according to the filtering threshold;

[0041] The noise of the shifted signal is removed by using the denoising function to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

[0042] Preferably, the formula of the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the translated signal, and d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

[0043] Preferably, the operating characteristics include: average voltage, voltage fluctuation amplitude, instantaneous voltage change rate, average current, current fluctuation amplitude, instantaneous current change rate, charge and discharge cycle, average temperature, temperature fluctuation amplitude, instantaneous temperature change rate, charge state, health state, charge and discharge efficiency and charge and discharge time.

[0044] An intelligent management system for electric vehicles and general sodium-ion batteries for large-scale energy storage, comprising:

[0045] A balanced charging module, used for performing balanced charging on a target sodium ion battery so that each single cell in a battery pack of the target sodium ion battery is in a synchronous working state;

[0046] A data acquisition module, used to collect operating data of the target sodium ion battery in a synchronous working state; the operating data includes: voltage signal, current signal, temperature signal and charge and discharge state signal;

[0047] A preprocessing module, used to preprocess the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal;

[0048] A feature extraction module is used to extract features from the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and to fuse each of the operation features to obtain a fusion feature;

[0049] An evaluation module, used for inputting the fusion features into a trained battery state evaluation model to obtain an evaluation result;

[0050] A management module is used to formulate a management strategy according to the evaluation result, and control the charging and discharging process of the target sodium ion battery according to the management strategy.

[0051] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0052] The present invention provides an intelligent management method and system for a sodium ion battery for electric vehicles and large-scale energy storage. The method comprises: performing balanced charging on a target sodium ion battery so that each single cell in a battery pack of the target sodium ion battery is in a synchronous working state; collecting operation data of the target sodium ion battery in the synchronous working state; the operation data comprises: a voltage signal, a current signal, a temperature signal and a charge and discharge state signal; preprocessing the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal; performing feature extraction on the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and performing feature fusion on each of the operation features to obtain fusion features; inputting the fusion features into a trained battery state evaluation model to obtain an evaluation result; formulating a management strategy according to the evaluation result, and controlling the charge and discharge process of the target sodium ion battery according to the management strategy. The present invention can significantly improve the performance, safety and service life of sodium-ion batteries through balanced charging, real-time data collection, feature extraction and fusion, and intelligent management strategy formulation, providing a strong guarantee for the efficient operation of electric vehicles and large-scale energy storage systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0054] Figure 1 A flow chart of a method provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of the system structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0057] The purpose of the present invention is to provide an intelligent management method and system for sodium-ion batteries used in electric vehicles and large-scale energy storage. Through balanced charging, real-time data acquisition, feature extraction and fusion, and intelligent management strategy formulation, the performance, safety, and service life of sodium-ion batteries can be significantly improved, providing a strong guarantee for the efficient operation of electric vehicles and large-scale energy storage systems.

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0059] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides an intelligent management method for electric vehicles and general sodium ion batteries for large-scale energy storage, including:

[0060] Step 100: performing balanced charging on the target sodium ion battery so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state;

[0061] Step 200: collecting operating data of a target sodium ion battery in a synchronous working state; the operating data includes: a voltage signal, a current signal, a temperature signal, and a charge and discharge state signal;

[0062] Step 300: preprocessing the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal;

[0063] Step 400: extracting features of the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal, and the charge and discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and fusing each operation feature to obtain a fusion feature;

[0064] Step 500: input the fusion features into the trained battery state assessment model to obtain the assessment result;

[0065] Step 600: Formulate a management strategy based on the evaluation results, and control the charge and discharge process of the target sodium-ion battery according to the management strategy.

[0066] Specifically, this embodiment is intended to meet the needs of electric vehicles and large-scale renewable energy storage systems. Sodium-ion batteries use the migration of sodium ions between positive and negative electrodes to achieve charging and discharging. Compared with traditional lithium-ion batteries, sodium-ion batteries have lower raw material costs and richer resource reserves, and are particularly suitable for large-scale production and application. The battery system is designed to have high energy density and long cycle life, and can provide efficient power support in electric vehicles. At the same time, it can effectively balance the load of the power grid in large-scale energy storage applications, store excess renewable energy (such as wind and solar energy), and release electricity during peak demand, thereby promoting the use of sustainable energy and the stability of the power system. Through intelligent management methods, the battery system can monitor and optimize the charging and discharging process in real time, ensure that the battery operates in the best condition, and improve overall performance and safety.

[0067] Preferably, the target sodium ion battery is balanced charged so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state, comprising:

[0068] Obtaining an equivalent circuit of a target sodium ion battery, and calculating the open circuit voltage data of a single cell according to the equivalent circuit;

[0069] Determine the curve relationship between open circuit voltage data and state of charge;

[0070] Reconstructing the curve relationship to obtain consistency parameters of the single battery; the consistency parameters include a battery capacity estimation value and an initial state of charge estimation value;

[0071] Tracking the consistency parameter by a mean shift tracking algorithm to obtain a tracking result;

[0072] The working state of each single battery is adjusted according to the tracking result.

[0073] Specifically, this embodiment first obtains the equivalent circuit model of the target sodium-ion battery, and uses the model to calculate the open circuit voltage data of each single cell. Next, the curve relationship between the open circuit voltage data and the state of charge (SOC) is determined through experiments or data analysis, and then the curve is reconstructed to extract the consistency parameters of the single cell, including the battery capacity estimation value and the initial state of charge estimation value. Subsequently, the mean shift tracking algorithm is applied to track these consistency parameters in real time to obtain the current state information of each single cell. Finally, according to the tracking results, the charging and discharging strategies of each single cell are adjusted, such as supplementing the battery with lower voltage, or discharging the battery with higher voltage, to ensure that all single cells remain synchronized during the charging process to achieve the purpose of balanced charging. Through this series of steps, the overall performance and service life of the battery pack can be effectively improved.

[0074] Preferably, obtaining the open circuit voltage data of the single cell according to the equivalent circuit calculation includes:

[0075] Determine the ratio of the terminal voltage of the single cell to the terminal voltage of the battery pack as the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack according to the equivalent circuit;

[0076] The open circuit voltage data of the battery pack is obtained by using a recursive least squares algorithm with a forgetting factor;

[0077] The open circuit voltage data of the battery pack is multiplied by the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack to obtain the open circuit voltage data of the single cell.

[0078] Preferably, the calculation formula of the recursive least squares algorithm with forgetting factor is:

[0079]

[0080] θ k =θ k-1 +K k ε k ;

[0081]

[0082] Among them, K k is the update gain, y k is the terminal voltage of the battery pack, is the regression vector, is the transposed matrix of the regression vector, ε k is the prediction error, P k is the error covariance at the current moment, P k-1 is the error covariance of the previous moment, λ k is the forgetting factor, I is the current, is the open circuit voltage data of the battery pack at the current moment, It is the open circuit voltage data of the battery pack at the previous moment.

[0083] Preferably, adjusting the working state of each single battery according to the tracking result includes:

[0084] Analyze the tracking results to identify the single cells in the battery pack whose performance deviation is greater than a preset threshold, determine the single cells greater than the preset threshold as target adjustment cells, and collect the performance deviation of the target adjustment cells;

[0085] The target adjustment battery is supplementarily charged or continuously discharged according to the performance deviation to balance the charge state of the entire battery pack, and the charge and discharge current is dynamically adjusted according to a preset adjustment strategy.

[0086] Furthermore, the specific steps of adjusting the working state in this embodiment are as follows:

[0087] 1. Identify the target adjustment battery. The tracking results obtained from the mean shift tracking algorithm include the performance deviation of each single battery. This embodiment analyzes the tracking results and identifies the single batteries whose performance deviation is greater than a preset threshold. These batteries are determined as target adjustment batteries.

[0088] 2. Collect performance deviations. Collect performance deviations of the target adjustment battery in detail, including voltage deviation, capacity deviation, state of charge (SOC) deviation, etc.

[0089] 3. Formulate adjustment strategies. According to the collected performance deviation, formulate specific adjustment strategies as follows:

[0090] (1) Supplementary charging: For batteries with low SOC, increase the charging current or extend the charging time.

[0091] (2) Continuous discharge: For batteries with high SOC, increase the discharge current or extend the discharge time.

[0092] 4. Dynamically adjust the charge and discharge current. According to the formulated adjustment strategy, dynamically adjust the target to adjust the battery's charge and discharge current. Use the control module in the battery management system (BMS) to adjust the current in real time to achieve fast response and precise control.

[0093] 5. Execute adjustment strategy: Implement adjustment strategy through execution module to control the battery charging and discharging process, ensuring the safety and effectiveness of adjustment measures.

[0094] 6. Real-time monitoring and feedback: During the adjustment process, the battery voltage, current, temperature and other parameters are monitored in real time to ensure the effectiveness and safety of the adjustment measures. The monitoring data is fed back to the data acquisition module to update the battery status information.

[0095] Preferably, the operation data is preprocessed to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal, including:

[0096] For each signal in the obtained operation data, signal amplification and denoising are performed in sequence to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

[0097] Preferably, the step of denoising the battery temperature preprocessing signal includes:

[0098] Shifting each signal in the operation data to obtain a shifted signal;

[0099] Performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0100] Determine the filtering threshold according to the decomposition scale and length of the signal;

[0101] Constructing a denoising function according to the filtering threshold;

[0102] The noise of the shifted signal is removed by using the denoising function to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

[0103] Preferably, the formula of the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the translated signal, and d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

[0104] Preferably, the operating characteristics include: average voltage, voltage fluctuation amplitude, instantaneous voltage change rate, average current, current fluctuation amplitude, instantaneous current change rate, charge and discharge cycle, average temperature, temperature fluctuation amplitude, instantaneous temperature change rate, charge state, health state, charge and discharge efficiency and charge and discharge time.

[0105] Furthermore, the motion characteristics of this embodiment specifically include:

[0106] 1. Operation characteristics of voltage preprocessing signal

[0107] Average voltage: The average voltage within a certain time window, reflecting the overall voltage level of the battery.

[0108] Voltage fluctuation amplitude: The standard deviation of the voltage signal or the difference between the maximum and minimum values, which indicates the stability of the voltage.

[0109] Instantaneous voltage change rate: The rate at which voltage changes, usually calculated as the derivative of the voltage change, reflects the dynamic response of the battery during the charge and discharge process.

[0110] Voltage hysteresis: The phase difference between voltage and current during the charging and discharging process affects the energy transfer efficiency of the battery.

[0111] 3. Operation characteristics of current preprocessing signal

[0112] Average current: The average current value within a certain time window, reflecting the overall charge and discharge level of the battery.

[0113] Current fluctuation amplitude: The standard deviation of the current signal or the difference between the maximum and minimum values, indicating the stability of the current.

[0114] Instantaneous current change rate: The rate at which current changes, usually calculated as the derivative of the current change, reflects the dynamic response of the battery during the charge and discharge process.

[0115] Charge and discharge cycle: records the number of positive and negative changes in current, reflecting the charge and discharge frequency of the battery.

[0116] 4. Operational characteristics of temperature preprocessing signal

[0117] Average temperature: The average temperature within a certain time window, reflecting the overall temperature level of the battery.

[0118] Temperature fluctuation amplitude: The standard deviation of the temperature signal or the difference between the maximum and minimum values, indicating the stability of the temperature.

[0119] Instantaneous temperature change rate: The rate of temperature change, usually calculated as the derivative of the temperature change, reflects the thermal response of the battery during operation.

[0120] Abnormal temperature detection: By setting the threshold, it detects whether the temperature exceeds the safe range to ensure the safety of the battery.

[0121] 5. Operation characteristics of charge and discharge state preprocessing signal

[0122] State of Charge (SOC): The current charge level of a battery, usually expressed as a percentage, reflecting the remaining capacity of the battery.

[0123] State of Health (SOH): The health of a battery, usually assessed by capacity decay rate or change in internal resistance.

[0124] Charge and discharge efficiency: The energy conversion efficiency during charging and discharging, reflecting the energy loss of the battery.

[0125] Charge and discharge time: Records the duration of charging and discharging to help analyze battery usage patterns.

[0126] Furthermore, after extracting the above-mentioned operation features, this embodiment performs feature fusion to obtain more comprehensive fusion features. The specific steps are as follows:

[0127] 1. Feature weighting: Different weights are given to each feature according to its impact on battery performance, and the weighted average is calculated.

[0128] 2. Principal Component Analysis (PCA): Through dimensionality reduction technology, multiple features are merged into several principal components, retaining most of the information.

[0129] 3. Feature concatenation: concatenate all feature vectors into a large feature vector for use in subsequent machine learning models.

[0130] By extracting and fusing the features of voltage, current, temperature, and charge and discharge status signals, this embodiment can more comprehensively understand the operating status of the battery, thereby improving the intelligence level of the battery management system.

[0131] Specifically, in step 500, this embodiment first needs to prepare the feature vectors that have undergone feature extraction and fusion processing. These fused features should contain information in multiple dimensions such as voltage, current, temperature, and charge and discharge status. Next, these fused features are input into a pre-trained battery status assessment model, which is an algorithm based on machine learning or deep learning, such as support vector machine (SVM), random forest, neural network, etc. The model will infer based on the input features and output the battery health status assessment results, including key indicators such as the battery's state of charge (SOC), state of health (SOH), and remaining service life (RUL). These evaluation results will provide an important basis for the formulation of subsequent management strategies.

[0132] Optionally, this embodiment uses a deep neural network (DNN), specifically including:

[0133] 1. Input layer, fused feature vector, including voltage, current, temperature, charge and discharge status, etc. Assume that the dimension of fused features is n.

[0134] 2. Hidden Layer

[0135] In the first hidden layer, the number of neurons is 128; the activation function is ReLU (Rectified Linear Unit).

[0136] The second hidden layer has 64 neurons and the activation function is ReLU.

[0137] The third hidden layer has 32 neurons and the activation function is ReLU.

[0138] 3. Output layer, including output nodes. According to the requirements of the evaluation task, the number of nodes in the output layer can be set to:

[0139] State of Charge (SOC): 1 node, outputs the current SOC value (range 0-100%).

[0140] State of Health (SOH): 1 node, outputs the SOH value (usually a ratio between 0-1).

[0141] Remaining Useful Life (RUL): 1 node that outputs the predicted remaining useful life (in hours or cycles).

[0142] Activation function: For SOC and SOH, a linear activation function is used. For RUL, a linear activation function is used.

[0143] 4. The loss function is the mean square error (MSE), which is used for regression tasks to evaluate the difference between the predicted value and the true value.

[0144] 5. The optimizer uses the Adam optimizer, which is suitable for most deep learning tasks and can adaptively adjust the learning rate.

[0145] Exemplarily, the model training process of this embodiment includes:

[0146] 1. Data preparation: Use historical battery dataset for training. The dataset should contain input features and corresponding labels (SOC, SOH, RUL).

[0147] 2. Model training: Use the training set to train the model and adjust the weights to minimize the loss function.

[0148] 3. Model validation: Use the validation set to evaluate model performance and ensure the generalization ability of the model.

[0149] 4. Model testing: Perform a final evaluation on the test set to ensure the model's performance on unseen data.

[0150] Through the above-mentioned deep neural network structure, this embodiment can effectively input the fusion features into the trained battery status assessment model to obtain accurate assessment results. This structure can capture the complex nonlinear relationship of the battery status and provide a reliable basis for the subsequent management strategy formulation.

[0151] Furthermore, in step 600, this embodiment first analyzes the current state and performance indicators of the battery according to the evaluation results obtained in step 500, and identifies the management measures that need to be taken. For example, if the evaluation results show that the SOC of some single cells is lower than the set threshold, a supplementary charging strategy needs to be formulated; if the temperature of some batteries is too high, it may be necessary to reduce the charging current or suspend charging. Then, based on these analysis results, specific management strategies are formulated, including adjustment of charging and discharging currents, extension or shortening of charging time, and balanced charging schemes for batteries. Finally, these strategies are converted into control instructions through the battery management system (BMS), and the charging and discharging process of the target sodium-ion battery is adjusted in real time to ensure that the battery pack operates in the best state, thereby improving the overall performance and safety.

[0152] Figure 2 A schematic diagram of the system structure provided by an embodiment of the present invention, such as Figure 2 As shown, the present invention also provides an intelligent management system for electric vehicles and general sodium ion batteries for large-scale energy storage, including:

[0153] A balanced charging module, used for performing balanced charging on a target sodium ion battery so that each single cell in a battery pack of the target sodium ion battery is in a synchronous working state;

[0154] A data acquisition module, used to collect operating data of the target sodium ion battery in a synchronous working state; the operating data includes: voltage signal, current signal, temperature signal and charge and discharge state signal;

[0155] A preprocessing module, used to preprocess the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal;

[0156] A feature extraction module is used to extract features from the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and to fuse each of the operation features to obtain a fusion feature;

[0157] An evaluation module, used for inputting the fusion features into a trained battery state evaluation model to obtain an evaluation result;

[0158] A management module is used to formulate a management strategy according to the evaluation result, and control the charging and discharging process of the target sodium ion battery according to the management strategy.

[0159] The beneficial effects of the present invention are as follows:

[0160] (1) The present invention ensures that each single cell is in a synchronous working state by performing balanced charging on the target sodium ion battery, thereby avoiding the overall performance degradation caused by the performance difference of the single cells. This balanced charging can improve the overall energy utilization efficiency and charge and discharge performance of the battery pack.

[0161] (2) The present invention can fully understand the working status of the battery by collecting voltage, current, temperature and charge and discharge status signals. This real-time monitoring helps to detect potential problems in time and ensure that the battery operates within a safe range.

[0162] (3) The present invention pre-processes the collected operating data to remove noise and outliers, thereby improving the accuracy and reliability of the data; by extracting features from voltage, current, temperature, and charge and discharge status signals, it is possible to extract key operating features, providing strong support for subsequent analysis and decision-making.

[0163] (4) The present invention fuses the operating characteristics of each signal, and the obtained fusion characteristics can more comprehensively reflect the health status and performance of the battery. This comprehensive evaluation helps to more accurately judge the actual operating conditions of the battery.

[0164] (5) The present invention can obtain accurate evaluation results by inputting fusion features into the trained battery status evaluation model. The management strategy formulated according to the evaluation results can optimize the charging and discharging process in a targeted manner, extend battery life, and improve safety; according to the real-time evaluation results, the charging and discharging strategy can be dynamically adjusted to ensure that the battery operates in the best state and avoid overcharging, over-discharging, etc.

[0165] (6) The present invention can effectively control the charging and discharging process through an intelligent management method, reduce the cycle loss of the battery, and thus extend the service life of the battery; through real-time monitoring of the battery status, it can promptly detect abnormal conditions (such as overheating, overvoltage, etc.) and take corresponding measures to improve the safety of the battery.

[0166] (7) The present invention is not only applicable to sodium ion batteries, but can also be extended to other types of battery management systems, and has strong adaptability and flexibility.

[0167] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0168] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent management method for electric vehicles and general sodium ion batteries for large-scale energy storage, characterized in that: include: Performing balanced charging on the target sodium ion battery so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state; Collecting operating data of the target sodium ion battery in a synchronous working state; the operating data includes: voltage signal, current signal, temperature signal and charge and discharge state signal; Preprocessing the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal, and a charge and discharge state preprocessing signal; Extracting features of the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal, and the charge-discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and fusing each of the operation features to obtain a fusion feature; Inputting the fusion features into a trained battery state assessment model to obtain an assessment result; A management strategy is formulated according to the evaluation result, and the charging and discharging process of the target sodium ion battery is controlled according to the management strategy.

2. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 1 is characterized in that: The target sodium ion battery is balanced charged so that each single cell in the battery pack of the target sodium ion battery is in a synchronous working state, comprising: Obtaining an equivalent circuit of a target sodium ion battery, and calculating the open circuit voltage data of a single cell according to the equivalent circuit; Determine the curve relationship between open circuit voltage data and state of charge; Reconstructing the curve relationship to obtain consistency parameters of the single battery; the consistency parameters include a battery capacity estimation value and an initial state of charge estimation value; Tracking the consistency parameter by a mean shift tracking algorithm to obtain a tracking result; The working state of each single battery is adjusted according to the tracking result.

3. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 2 is characterized in that: The open circuit voltage data of the single cell is obtained by calculating according to the equivalent circuit, including: Determine the ratio of the terminal voltage of the single cell to the terminal voltage of the battery pack as the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack according to the equivalent circuit; The open circuit voltage data of the battery pack is obtained by using a recursive least squares algorithm with a forgetting factor; The open circuit voltage data of the battery pack is multiplied by the ratio of the open circuit voltage data of the single cell to the open circuit voltage data of the battery pack to obtain the open circuit voltage data of the single cell.

4. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 3 is characterized in that: The calculation formula of the recursive least squares algorithm with forgetting factor is: i k =θ k-1 +K k e k ; Among them, K k is the update gain, y k is the terminal voltage of the battery pack, is the regression vector, is the transposed matrix of the regression vector, ε k is the prediction error, P k is the error covariance at the current moment, P k-1 is the error covariance of the previous moment, λ k is the forgetting factor, I is the current, θ k is the open circuit voltage data of the battery pack at the current moment, θ k-1 It is the open circuit voltage data of the battery pack at the previous moment.

5. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 2 is characterized in that: Adjusting the working state of each single battery according to the tracking result includes: Analyze the tracking results to identify the single cells in the battery pack whose performance deviation is greater than a preset threshold, determine the single cells greater than the preset threshold as target adjustment cells, and collect the performance deviation of the target adjustment cells; The target adjustment battery is supplementarily charged or continuously discharged according to the performance deviation to balance the charge state of the entire battery pack, and the charge and discharge current is dynamically adjusted according to a preset adjustment strategy.

6. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 1 is characterized in that: Preprocessing the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal, and a charge and discharge state preprocessing signal, including: For each signal in the obtained operation data, signal amplification and denoising are performed in sequence to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

7. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 6 is characterized in that: The step of denoising the battery temperature preprocessing signal comprises: Shifting each signal in the operation data to obtain a shifted signal; Performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients; Determine the filtering threshold according to the decomposition scale and length of the signal; Constructing a denoising function according to the filtering threshold; The noise of the shifted signal is removed by using the denoising function to obtain the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal.

8. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 7 is characterized in that: The formula for the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the translated signal, and d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

9. The intelligent management method for electric vehicles and general sodium-ion batteries for large-scale energy storage according to claim 1 is characterized in that: The operating characteristics include: average voltage, voltage fluctuation amplitude, instantaneous voltage change rate, average current, current fluctuation amplitude, instantaneous current change rate, charge and discharge cycle, average temperature, temperature fluctuation amplitude, instantaneous temperature change rate, state of charge, health state, charge and discharge efficiency and charge and discharge time.

10. An intelligent management system for electric vehicles and general sodium-ion batteries for large-scale energy storage, characterized in that: include: A balanced charging module, used for performing balanced charging on a target sodium ion battery so that each single cell in a battery pack of the target sodium ion battery is in a synchronous working state; A data acquisition module, used to collect operating data of the target sodium ion battery in a synchronous working state; the operating data includes: voltage signal, current signal, temperature signal and charge and discharge state signal; A preprocessing module, used to preprocess the operation data to obtain a voltage preprocessing signal, a current preprocessing signal, a temperature preprocessing signal and a charge and discharge state preprocessing signal; A feature extraction module is used to extract features from the voltage preprocessing signal, the current preprocessing signal, the temperature preprocessing signal and the charge and discharge state preprocessing signal respectively to obtain operation features corresponding to each signal, and to fuse each of the operation features to obtain a fusion feature; An evaluation module, used for inputting the fusion features into a trained battery state evaluation model to obtain an evaluation result; A management module is used to formulate a management strategy according to the evaluation result, and control the charging and discharging process of the target sodium ion battery according to the management strategy.

Images