Performance determination method and device of sodium ion battery, storage medium and program product
By obtaining the structural information of sodium ion batteries and using graph neural networks and long-term memory network models to predict performance, the problem of performance degradation of sodium ion batteries in low temperature environments is solved, the prediction accuracy and material optimization efficiency are improved, and the system complexity is reduced Sex and cost.
Patent Information
- Application Number
- CN202410952946.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-12
AI Technical Summary
The performance of sodium ion batteries is sensitive to temperature changes, especially in low temperature environments, which leads to a decrease in battery capacity and power density, low prediction accuracy in prior art, and thermal management and material optimization methods increase system complexity and cost.
By obtaining the structural information of the electrode material and electrolyte of the sodium ion battery, a neighbor diagram is generated, and the performance indicators are predicted by combining the graph neural network and long-term memory network models, the performance status is determined and the control strategy is formulated to improve the accuracy of performance prediction.
It improves the accuracy of performance prediction of sodium ion batteries at different temperatures, reduces the cost of material research and development and temperature adaptability, and ensures the stability and high performance of the batteries under different environmental conditions.
Smart Images

Figure CN118940614A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sodium ion batteries, and in particular to a method, device, storage medium and program product for determining performance of a sodium ion battery. Background Art
[0002] With the transformation of the global energy structure and the rapid development of the new energy industry, sodium-ion batteries, as a storage technology with broad application prospects, have gradually attracted attention. However, the performance of sodium-ion batteries is easily affected by temperature changes, especially in low temperature environments, where their ion conduction efficiency will drop significantly, resulting in reduced battery capacity and power density, limiting their scope of application.
[0003] At present, the temperature adaptability of sodium-ion batteries is improved mainly through two ways: thermal management and material optimization. Thermal management technology controls the battery operating temperature within the optimal range through external heating or cooling devices. However, this method will increase the complexity and cost of the system. Material optimization technology is to develop new electrode materials and electrolyte formulations to enable them to maintain stability and high performance over a wide temperature range. However, the material research and development process requires a lot of experiments and tests, and it is difficult to predict the performance of materials at different temperatures. The prediction accuracy of sodium-ion battery performance is low.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a method, device, storage medium and program product for determining the performance of a sodium ion battery, aiming to solve the technical problem of low prediction accuracy of the performance of a sodium ion battery.
[0006] To achieve the above objectives, the present application proposes a method for determining the performance of a sodium ion battery, the method comprising:
[0007] Obtaining structural information of electrode materials and electrolytes of sodium ion batteries, wherein the structural information includes atomic information and chemical bond information;
[0008] generating an adjacency graph according to the structural information, wherein the nodes of the adjacency graph are the atomic information, and the connecting edges of the adjacency graph are the chemical bond information;
[0009] The first performance indicator of the sodium ion battery is determined according to the connection relationship between each node and the nodes in the adjacency graph.
[0010] In one embodiment, the method further comprises:
[0011] Acquiring performance data of a sodium ion battery in a charge and discharge cycle at different ambient temperatures, wherein the performance data includes ambient temperature and charge and discharge parameters of the battery;
[0012] Inputting the performance data into a preset temperature performance prediction model to predict a second performance indicator of the sodium ion battery;
[0013] Based on the first performance indicator and the second performance indicator, a performance state of the sodium ion battery is determined.
[0014] In one embodiment, before the step of inputting the performance data into a preset temperature performance prediction model to predict the second performance indicator of the sodium ion battery, the step further includes:
[0015] Acquiring training data, wherein the training data includes performance reference data and performance reference indicators;
[0016] The performance reference data is used as input data, and the performance reference index is used as output data, and a preset long short-term memory network model is trained to obtain the temperature performance prediction model.
[0017] In one embodiment, the step of determining the first performance indicator of the sodium ion battery according to the connection relationship between each node and the nodes in the adjacency graph includes:
[0018] Inputting the adjacency graph into a graph neural network model, wherein the graph neural network model is used to determine a first performance indicator of the sodium ion battery according to a connection relationship between each node and nodes in the adjacency graph;
[0019] Obtain a first performance indicator of the sodium ion battery output by the graph neural network model.
[0020] In one embodiment, after the step of determining the performance state of the sodium ion battery based on the first performance indicator and the second performance indicator, the step further includes:
[0021] A control strategy of the sodium ion battery is determined according to the current performance state of the sodium ion battery, wherein different performance states correspond to different control strategies, and the control strategy includes a charge and discharge strategy and / or a temperature control strategy.
[0022] In one embodiment, the step of determining the control strategy of the sodium ion battery according to the current performance state of the sodium ion battery includes:
[0023] Determine a reward function of a plurality of control strategies to be determined corresponding to a current performance state;
[0024] According to the reward function, evaluating the expected reward values that can be obtained by the multiple control strategies to be determined;
[0025] The control strategy of the sodium ion battery is determined according to the expected reward value.
[0026] In one embodiment, the step of determining the control strategy of the sodium ion battery according to the current performance state of the sodium ion battery includes:
[0027] When the current performance state of the sodium ion battery includes temperature abnormality, determining a temperature control strategy for the sodium ion battery;
[0028] When the current performance state of the sodium ion battery includes abnormal charging and discharging speed, a charging and discharging strategy of the sodium ion battery is determined.
[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a sodium ion battery performance determination device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the sodium ion battery performance determination method as described above.
[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for determining the performance of a sodium ion battery as described above are implemented.
[0031] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the sodium ion battery performance determination method as described above.
[0032] The present application provides a method for determining the performance of a sodium ion battery, by obtaining the structural information of the electrode material and electrolyte of the sodium ion battery, the structural information including atomic information and chemical bond information; generating an adjacency graph based on the structural information, the nodes of the adjacency graph being atomic information, and the connecting edges of the adjacency graph being chemical bond information; determining the first performance indicator of the sodium ion battery based on the connection relationship between each node and the nodes in the adjacency graph. The performance of the sodium ion battery is predicted through the structural information of the sodium ion battery, the prediction accuracy of the performance of the sodium ion battery is improved, and it is convenient to quickly identify the electrode material and electrolyte with the best performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0035] Figure 1 A schematic diagram of a process flow provided in Example 1 of a method for determining the performance of a sodium ion battery of the present application;
[0036] Figure 2 A schematic diagram of a method flow chart provided for step S30 of Embodiment 1 of the method for determining the performance of a sodium ion battery of the present application;
[0037] Figure 3 A schematic diagram of a flow chart provided for Embodiment 2 of the method for determining the performance of a sodium ion battery of the present application;
[0038] Figure 4 A schematic diagram of a process flow provided in Example 3 of the method for determining the performance of a sodium ion battery of the present application;
[0039] Figure 5 A schematic diagram of a process flow provided for Embodiment 4 of the method for determining the performance of a sodium ion battery of the present application;
[0040] Figure 6 A schematic diagram of a process flow provided in Example 5 of the method for determining the performance of a sodium ion battery of the present application;
[0041] Figure 7 A schematic diagram of a process flow provided for Embodiment 6 of the method for determining the performance of a sodium ion battery of the present application;
[0042] Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the method for determining the performance of a sodium ion battery in an embodiment of the present application.
[0043] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0046] As a new type of energy storage technology, sodium batteries have attracted much attention due to their advantages such as low cost and abundant resources. However, the performance of sodium batteries is very sensitive to temperature changes. The conductivity efficiency of sodium ions will drop significantly in low temperature environments, which directly affects the performance and life of the battery. At present, improving the temperature management technology of sodium-ion batteries tends to increase manufacturing and operating costs, as well as system complexity, while improving temperature adaptability.
[0047] In view of the above problems, the present application proposes a method for determining the performance of a sodium ion battery, which predicts the performance of the sodium ion battery through the structural information of the sodium ion battery, improves the prediction accuracy of the sodium ion battery performance, and facilitates the rapid identification of the best performing electrode materials and electrolytes.
[0048] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication and program running functions. In order to more clearly explain this technical solution, this application uses the intelligent sodium-ion battery management and material optimization system as the execution entity.
[0049] Based on this, the first embodiment of the present application provides a method for determining the performance of a sodium ion battery, referring to Figure 1 In this embodiment, the method for determining the performance of a sodium ion battery includes steps S10 to S30:
[0050] Step S10, obtaining structural information of the electrode material and the electrolyte of the sodium ion battery, wherein the structural information includes atomic information and chemical bond information.
[0051] It should be noted that sodium-ion batteries are electrochemical batteries that use the movement of sodium ions between positive and negative electrodes to store and release electrical energy. Electrode materials are important components of sodium-ion batteries, and they are responsible for storing and releasing electrical energy. The electrolyte is an ionic conductive medium in sodium-ion batteries, which is responsible for transferring sodium ions between electrodes while maintaining the chemical stability of sodium-ion batteries. Atomic information includes the position, type, and connection method of all atoms in the electrode material and the electrolyte, reflecting the crystal structure, defects, and interface properties of the electrode material. Chemical bond information indicates how atoms are connected together through chemical bonds, including bond lengths and bond types such as ionic bonds, covalent bonds, etc., reflecting the electronic structure and chemical reactions of the electrode material.
[0052] Optionally, the atomic information and chemical bond information of the electrode materials and the electrolyte are obtained by experimental techniques such as X-ray diffraction, scanning electron microscopy, transmission electron microscopy and X-ray photoelectron spectroscopy.
[0053] For example, a sodium ion electrode material sample is prepared and placed in an X-ray diffraction instrument for scanning. The X-ray diffraction pattern will show the crystal structure of the electrode material, including atomic information such as lattice parameters, crystal orientation and grain size. The electrode material sample is prepared into a thin slice and placed in a transmission electron microscope sample stage for transmission observation. The transmission electron microscope image will provide atomic-level structural information of the material, including chemical bond information such as atomic arrangement, chemical bond type and chemical bond length.
[0054] Optionally, quantum mechanical calculations and molecular dynamics simulations can be used to predict and verify the experimental results, providing information on the structural evolution at the atomic scale, including the structural changes of electrode materials and electrolytes during the charge and discharge processes.
[0055] For example, quantum mechanics software such as VASP (Vienna Ab initio Simulation Package) and Quantum Espresso are used to calculate the electronic structure of electrode materials and electrolytes, showing changes in the electronic structure of electrode materials during charge and discharge, including atomic-scale structural information such as electronic energy band structure and bonding energy. Molecular dynamics software such as LAMMPS (Large-scale Atomic / Molecular Massively Parallel Simulation) and GROMACS (GROningen MAchine for Chemical Simulations) are used to perform long-term dynamic simulations of electrode materials and electrolytes, simulating the structural evolution during charge and discharge, and showing the migration path of ions in the electrolyte and the interface formation process, including ion migration, phase change, interface formation, etc.
[0056] Step S20, generating an adjacency graph according to the structural information, wherein the nodes of the adjacency graph are the atomic information, and the connecting edges of the adjacency graph are the chemical bond information.
[0057] It should be noted that the adjacency graph represents the atomic arrangement and chemical bond network of the electrode material and electrolyte. Graph analysis tools can be used to capture local and global features in the structure of the electrode material and electrolyte, and use them to predict the performance data of the electrode material and electrolyte at different ambient temperatures, which constitute the first performance indicator.
[0058] Step S30, determining a first performance indicator of the sodium ion battery according to the connection relationship between each node and the nodes in the adjacency graph.
[0059] It should be noted that the first performance index is used to indicate the performance of the electrode material and electrolyte of the sodium ion battery at different ambient temperatures, including the specific capacity of the electrode material, structural stability, conductivity, sodium ion diffusion rate, electrochemical stability of the electrolyte, etc.
[0060] In addition, it should be noted that the ambient temperature has a significant impact on performance indicators such as conductivity and electrochemical activity. For example, an increase in temperature will increase the thermal motion of atoms or molecules, thereby increasing the mobility of charge carriers and the mobility of sodium ions, and thus increasing the conductivity of electrode materials and electrolytes. However, excessively high temperatures may cause structural changes or phase changes in electrode materials, reduce the conductivity of electrode materials, or cause decomposition or evaporation of the electrolyte, thereby reducing the electrochemical activity of the electrolyte.
[0061] In one possible implementation, refer to Figure 2 , step S30 may include steps A301-A302:
[0062] Step A301, inputting the adjacency graph into a graph neural network model, wherein the graph neural network model is used to determine a first performance indicator of the sodium ion battery according to the connection relationship between each node and the nodes in the adjacency graph;
[0063] It should be noted that the Graph Neural Network (GNN) is a deep learning model that specializes in processing graph structure data. The graph neural network layer is the basic unit of the graph neural network model, representing the propagation and processing of information in the graph structure. Each layer contains some neurons that are responsible for processing the connection relationship between each node and node in the adjacency graph. The layers are connected to each other by updating and transmitting the connection relationship between each node and node.
[0064] Exemplarily, starting from the adjacent connection edges, the information between each node and the adjacent nodes is determined. This information includes the information of the adjacent nodes and the connection information between them, such as the type and length of the connection edge. Then, the information of all adjacent nodes is aggregated to the current node through an aggregation function. The aggregation function can be a simple summation or a more complex function, such as a weighted summation or an average summation. Finally, the aggregated node is used to update the current node.
[0065] Optionally, in a multi-layer network, nodes are passed between each layer, and each layer updates the nodes to help the model learn deeper representations in the adjacency graph structure.
[0066] Step A302, obtaining the first performance indicator of the sodium ion battery output by the graph neural network model.
[0067] In this embodiment, by determining one or more graph neural network layers, learning the connection relationship between each node and the nodes in the adjacency graph structure, and outputting the first performance indicator, the prediction accuracy of the sodium ion battery performance is improved, so that suitable electrode materials and electrolytes at a specific ambient temperature can be screened to maintain stability and high performance, reducing the experimental and testing costs of electrode material and electrolyte research and development, and thereby reducing the cost of sodium ion batteries to adapt to ambient temperature.
[0068] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 3 In this embodiment, the method for determining the performance of a sodium ion battery further includes steps S11 to S31:
[0069] Step S11, obtaining performance data of the sodium ion battery in the charge and discharge cycle at different ambient temperatures, wherein the performance data includes the ambient temperature and the charge and discharge parameters of the battery.
[0070] It should be noted that ambient temperature refers to the external environment temperature of the battery; the charge and discharge cycle is the repeated charging and discharging process of the sodium-ion battery, and the charge and discharge parameters include the various performance index data of the sodium-ion battery in the charge and discharge process under specific conditions, such as discharge capacity, charging efficiency, cycle stability, energy density, internal resistance, number of cycles, etc.
[0071] In addition, it should be noted that the ambient temperature has a significant impact on the charge and discharge parameters of sodium ion batteries. Too high or too low a temperature may affect the chemical reaction rate, energy efficiency and life of the battery. For example, at low temperatures, the capacity of sodium ion batteries is usually reduced because low temperatures reduce the ionic conductivity of the electrolyte inside the sodium ion battery, thereby affecting the movement of sodium ions, while at high temperatures, the aging of sodium ion battery materials is accelerated, resulting in a shortened cycle life.
[0072] Optionally, the sodium ion battery is placed in a temperature-controlled environment, and the battery is charged and discharged at different ambient temperatures, and performance data such as voltage, current, capacity, discharge depth, internal resistance, and number of cycles of the sodium ion battery are recorded.
[0073] Exemplarily, a sodium ion battery sample in a stable state is prepared and placed in a thermostat that can simulate different ambient temperatures. The thermostat will be set at a series of temperature points, including -40°C, -20°C, 0°C, 20°C, 40°C and 60°C. A series of charge and discharge cycle tests are performed on the sodium ion battery under these specific temperature conditions, and its performance data at each temperature point is recorded in detail to determine the performance of the sodium ion battery at different ambient temperatures.
[0074] Optionally, the battery is installed in a preset device and connected to a data acquisition device to be tested in different actual application scenarios.
[0075] Exemplarily, a sodium-ion battery is installed in an electric vehicle, and data acquisition equipment such as sensors and battery management systems are installed to detect the performance data of the sodium-ion battery in real time. The electric vehicle is placed at a standard temperature such as 25°C, and a standard charge and discharge cycle test is performed on the electric vehicle, and the performance data of each cycle is recorded. The vehicle is then placed in a high temperature environment such as 50°C and a low temperature environment such as -20°C, and the above tests are repeated, and the corresponding performance data is recorded to determine the performance of the sodium-ion battery under different temperature conditions in actual applications.
[0076] It should be noted that the specific ambient temperature setting can be customized according to the selected sodium-ion battery or the actual application scenario, and this application does not impose any restrictions on the temperature value.
[0077] Step S21, inputting the performance data into a preset temperature performance prediction model to predict a second performance indicator of the sodium ion battery.
[0078] Optionally, the temperature performance prediction model includes a long short-term memory network model, which can predict the performance data of the battery at a specific temperature based on the input performance data. These predicted performance data constitute a second performance indicator for evaluating the performance of the sodium-ion battery under various temperature conditions, including the charging and discharging parameters under each temperature condition.
[0079] Step S31, determining a performance state of the sodium ion battery based on the first performance indicator and the second performance indicator.
[0080] It should be noted that the performance status of the sodium-ion battery shows whether the battery is in the best working state, whether there is performance degradation, whether it is suitable for a specific application environment, etc., including the temperature of the sodium-ion battery, the charging level, etc. Combining the first performance indicator and the second performance indicator, the comprehensive performance status of the sodium-ion battery can be evaluated.
[0081] Exemplarily, it is assumed that the first performance indicator obtained is the specific capacity of the sodium ion battery electrode, that is, the amount of charge that can be stored per unit mass of the electrode material of the battery, and the second performance indicator obtained is the battery charge and discharge efficiency, that is, the efficiency of energy conversion of the battery during the charge and discharge process. If the specific capacity is higher than 80% of the standard value of the electrode material and the charge and discharge efficiency exceeds 90%, it indicates that the battery is in the best working state. If the specific capacity is lower than 80% of the standard value of the electrode material or the charge and discharge efficiency is lower than 90%, it indicates that the battery has performance degradation.
[0082] In this embodiment, by collecting the charge and discharge cycle performance data of the sodium ion battery and inputting these data into a preset temperature performance prediction model, the second performance index of the battery can be predicted. Combined with the first performance index, the performance state of the sodium ion battery is comprehensively evaluated and determined, thereby accurately predicting and evaluating the performance of the battery under different temperature conditions.
[0083] Based on the above embodiment, in the third embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction, and will not be described in detail later. Figure 4 , before step S21, it also includes steps B211 to B212:
[0084] Step B211, obtaining training data, wherein the training data includes performance reference data and performance reference indicators;
[0085] It should be noted that training data is a set of data containing battery performance parameters used to train machine learning models. These data can be laboratory test results, simulation data, or field measured data. Select training data that fully represents the various situations and conditions that the battery may encounter in actual use to ensure that the machine learning model has good generalization capabilities and can accurately predict new, unseen data. Performance reference indicators are quantitative indicators corresponding to performance reference data and used to evaluate battery performance, including charge and discharge parameters under various temperature conditions and performance data of electrode materials and electrolytes at different ambient temperatures.
[0086] Step B212, using the performance reference data as input data and the performance reference index as output data, training the preset long short-term memory network model to obtain the temperature performance prediction model.
[0087] It should be noted that the long short-term memory network model is a special recurrent neural network that can process and predict time series data, taking performance reference data as input data and performance reference indicators as output data. The long short-term memory network model can learn how to predict performance indicators based on input data.
[0088] Optionally, the structure of the long short-term memory network model is designed, including determining the number of network layers, the number of neurons, activation functions, etc., and the model parameters are continuously adjusted during the training process to minimize the prediction error.
[0089] For example, assuming that the capacity attenuation of sodium-ion batteries at different ambient temperatures is to be predicted, the long short-term memory network model can be designed as three hidden layers, each hidden layer contains 100 neurons, and the ReLU (Rectified Linear Unit) activation function is used. The training data is divided into a training set and a validation set. The long short-term memory network model is trained with the training set, and the prediction ability of the long short-term memory network model is verified with the validation set. The prediction error of the long short-term memory network model is calculated by the cross entropy loss function, and the structure of the long short-term memory network model is adjusted according to the error, such as increasing or decreasing the number of hidden layers, adjusting the number of neurons, or trying different activation functions. After the training is completed, the temperature performance prediction model is obtained.
[0090] In this implementation, training data is obtained and used to train a preset long short-term memory network model to obtain a model that can predict the performance of sodium-ion batteries at a specific temperature, thereby predicting the performance of batteries at different temperatures based on historical data, reducing dependence on physical experiments and reducing prediction costs.
[0091] Based on the above embodiments, in the fourth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , after step S31, further comprising S41:
[0092] Step S41, determining a control strategy of the sodium ion battery according to the current performance state of the sodium ion battery, wherein different performance states correspond to different control strategies, and the control strategy includes a charge and discharge strategy and / or a temperature control strategy.
[0093] Optionally, one or more control strategies may be set for the same performance state.
[0094] For example, when the battery temperature is too high, a charge and discharge strategy may be applied, such as reducing the charge rate to avoid overheating. A charge and discharge strategy and a temperature control strategy may also be applied simultaneously, such as reducing the charge rate and starting the refrigeration system to lower the battery temperature, or stopping charge and discharge.
[0095] Based on the above embodiment, in the fifth embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction, and will not be repeated in the following. On this basis, referring to FIG. 6, step S41 also includes steps C411 to C413:
[0096] Step C411, determining the reward functions of multiple control strategies to be determined corresponding to the current performance state.
[0097] It should be noted that the reward function is a function used to evaluate the benefits obtained by an agent after taking a certain action in a specific environment. It is used in reinforcement learning algorithms such as Q-learning, Policy Gradient, and DQN (Deep Q-Network), in which the agent learns the best strategy by interacting with the environment and maximizes the cumulative reward by constantly adjusting its behavior to achieve a specific goal. In this application, the execution subject is used as the agent.
[0098] Optionally, rewards can be action-based, i.e., rewards that the agent receives immediately after taking an action, or cumulative rewards, i.e., rewards that the agent receives after taking a series of actions.
[0099] Optionally, the reward can be positive, i.e., encouraging the agent to take a certain action, or negative, i.e., punishing the agent for taking a certain action, so that the agent can distinguish the pros and cons of different actions.
[0100] It should be noted that the setting of rewards depends on the impact of the behavior on long-term goals, and this application does not impose any restrictions on this.
[0101] Step C412: evaluating the expected reward values that can be obtained by the multiple control strategies to be determined according to the reward function.
[0102] It should be noted that the expected return value refers to the expected value of the long-term cumulative reward that the agent can obtain by adopting the corresponding control strategy to be determined under a given performance state.
[0103] Optionally, determine the control strategy to be determined corresponding to the current performance state, that is, the action taken by the agent, and calculate the immediate reward that the agent can obtain after taking the current action according to the reward function. Consider the probability of the new state that the agent may transfer to after taking the current action, and convert the reward that can only be obtained after a period of time after taking the action to the current time point, and combine it to calculate the expected return value that can be obtained by taking the current control strategy to be determined.
[0104] For example, according to the current performance state of the sodium-ion battery, if the battery temperature remains within a safe range, a positive reward is given to the agent. If the battery temperature is too high, the charging rate is adjusted to lower the temperature, and a positive reward is given to the agent. Among them, adjusting the charging rate may cause the battery temperature to rise or fall, thereby entering different states, and the probability of occurrence of these two situations is calculated; if the agent attaches great importance to long-term battery life, the reward obtained after a period of time after adjusting the charging rate will be relatively low when converted to the current time point. Conversely, if the agent attaches more importance to short-term work efficiency, the reward converted to the current time point will be relatively high. The immediate reward, the probability of occurrence of the two situations, and the reward converted to the current time point are combined to calculate the expected return value that can be obtained by adjusting the charging rate.
[0105] Step C413, determining the control strategy of the sodium ion battery according to the expected return value.
[0106] It should be noted that the higher the expected return value obtained by adopting a certain control strategy to be determined, the better the control strategy is, and the control strategy to be determined with the highest expected return value is selected as the control strategy for the sodium-ion battery.
[0107] Exemplarily, the Q function is used as the reward function, where the Q function Q(s, a) represents the expected value of the cumulative reward that can be obtained by adopting the adaptive strategy a in state s. The reinforcement learning algorithm continuously updates the value of the Q function in an iterative manner. In each iteration, the agent executes the control strategy to be determined and observes its results. Then, the value of the Q function is updated according to the reward and the new performance state. By iteratively updating the Q value, it is possible to learn which control strategies to be determined can bring the best long-term results under the current performance state, and finally select the control strategy to be determined with the highest Q function value as the control strategy for the sodium-ion battery.
[0108] In this embodiment, the control strategy of the sodium ion battery is selected according to the reward function and the expected return value to help the sodium ion battery better adapt to different ambient temperatures and reduce unnecessary energy consumption and maintenance costs of the sodium ion battery in temperature adaptation.
[0109] Based on the above embodiment, in the sixth embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction, and will not be described in detail later. Figure 7 , step S41 also includes steps D411 to D412:
[0110] Step D411, when the current performance state of the sodium ion battery includes temperature abnormality, determining a temperature control strategy for the sodium ion battery.
[0111] Optionally, when the temperature data of the sodium ion battery exceeds a preset safety range, it is determined that the current performance state of the sodium ion battery includes temperature abnormality. Exemplarily, when the battery operating temperature exceeds the normal operating temperature range specified by the manufacturer, or the operating temperature does not exceed the specified range but remains in a high temperature state for more than a preset time, it is determined that the current performance state of the sodium ion battery includes temperature abnormality.
[0112] Exemplarily, assuming that a sodium-ion battery is used in an electric vehicle and the normal operating temperature range of the battery is between 20°C and 40°C, when the intelligent sodium-ion battery management and material optimization system detects that the temperature of the battery has risen to 50°C, the current performance state of the sodium-ion battery includes temperature abnormality. At this time, the temperature control strategy of the sodium-ion battery is determined according to the method described in the fourth embodiment.
[0113] Step D412: When the current performance state of the sodium ion battery includes abnormal charge and discharge speed, determine the charge and discharge strategy of the sodium ion battery.
[0114] Optionally, when the current change rate of the sodium ion battery during charging or discharging exceeds a preset safety range, it is determined that the current performance state of the sodium ion battery includes abnormal charging and discharging speed. Exemplarily, when the charging and discharging time of the battery exceeds or is shorter than a preset time range, it is determined that the current performance state of the sodium ion battery includes abnormal charging and discharging speed.
[0115] For example, in daily use of an electric bicycle battery, the intelligent sodium-ion battery management and material optimization system detects abnormal charging and discharging speeds of the battery and finds that the battery takes 50% longer to charge than usual under a standard charger. At this time, the charging and discharging strategy of the sodium-ion battery is determined according to the method described in the fourth embodiment.
[0116] In this embodiment, when the sodium ion battery has abnormal temperature or abnormal charge and discharge speed, the corresponding temperature control strategy and charge and discharge strategy are determined to ensure that the battery operates at a normal operating temperature and charge and discharge rate to maintain the stability and reliability of its performance.
[0117] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining the performance of the sodium ion battery of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0118] The present application provides a sodium ion battery performance determination device, the sodium ion battery performance determination device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sodium ion battery performance determination method in the above-mentioned embodiment 1.
[0119] Reference below Figure 8 , which shows a schematic diagram of a structure of a sodium ion battery performance determination device suitable for implementing an embodiment of the present application. The sodium ion battery performance determination device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The sodium ion battery performance determination device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0120] like Figure 8 As shown, the performance determination device of the sodium ion battery may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the performance determination device of the sodium ion battery are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the performance determination device of the sodium ion battery to communicate wirelessly or wired with other devices to exchange data. Although the performance determination device of the sodium ion battery with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.
[0121] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0122] The performance determination device of the sodium ion battery provided in the present application adopts the performance determination method of the sodium ion battery in the above embodiment, which can solve the technical problem of low accuracy in predicting the performance of the sodium ion battery. Compared with the prior art, the beneficial effects of the performance determination device of the sodium ion battery provided in the present application are the same as the beneficial effects of the performance determination method of the sodium ion battery provided in the above embodiment, and the other technical features in the performance determination device of the sodium ion battery are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0123] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0125] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for determining the performance of a sodium-ion battery in the above-mentioned embodiment.
[0126] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0127] The computer-readable storage medium may be included in the sodium-ion battery performance determination device; or may exist independently without being assembled into the sodium-ion battery performance determination device.
[0128] The computer-readable storage medium carries one or more programs, and when the one or more programs are executed by the sodium-ion battery performance determination device, the sodium-ion battery performance determination device can be written in one or more programming languages or a combination thereof to perform computer program codes for the operation of the present application, and the programming languages include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0129] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0130] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0131] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned sodium ion battery performance determination method, and can solve the technical problem of low accuracy in sodium ion battery performance prediction. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the sodium ion battery performance determination method provided in the above-mentioned embodiment, and will not be repeated here.
[0132] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for determining the performance of a sodium ion battery as described above.
[0133] The computer program product provided in this application can solve the technical problem of low accuracy in predicting the performance of sodium ion batteries. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the method for determining the performance of sodium ion batteries provided in the above embodiment, and will not be described in detail here.
[0134] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for determining the performance of a sodium ion battery, characterized in that: The method includes: Obtaining structural information of electrode materials and electrolytes of sodium ion batteries, wherein the structural information includes atomic information and chemical bond information; generating an adjacency graph according to the structural information, wherein the nodes of the adjacency graph are the atomic information, and the connecting edges of the adjacency graph are the chemical bond information; The first performance indicator of the sodium ion battery is determined according to the connection relationship between each node and the nodes in the adjacency graph.
2. The method according to claim 1, characterized in that The method further comprises: Acquiring performance data of a sodium ion battery in a charge and discharge cycle at different ambient temperatures, wherein the performance data includes ambient temperature and charge and discharge parameters of the battery; Inputting the performance data into a preset temperature performance prediction model to predict a second performance indicator of the sodium ion battery; Based on the first performance indicator and the second performance indicator, a performance state of the sodium ion battery is determined.
3. The method according to claim 2, characterized in that Before the step of inputting the performance data into a preset temperature performance prediction model to predict the second performance index of the sodium ion battery, the method further includes: Acquiring training data, wherein the training data includes performance reference data and performance reference indicators; The performance reference data is used as input data, and the performance reference index is used as output data, and a preset long short-term memory network model is trained to obtain the temperature performance prediction model.
4. The method according to claim 1, characterized in that The step of determining the first performance indicator of the sodium ion battery according to the connection relationship between each node and the nodes in the adjacency graph comprises: Inputting the adjacency graph into a graph neural network model, wherein the graph neural network model is used to determine a first performance indicator of the sodium ion battery according to a connection relationship between each node and nodes in the adjacency graph; Obtain a first performance indicator of the sodium ion battery output by the graph neural network model.
5. The method according to claim 2, characterized in that After the step of determining the performance state of the sodium ion battery based on the first performance indicator and the second performance indicator, the method further includes: A control strategy of the sodium ion battery is determined according to the current performance state of the sodium ion battery, wherein different performance states correspond to different control strategies, and the control strategy includes a charge and discharge strategy and / or a temperature control strategy.
6. The method according to claim 5, characterized in that The step of determining the control strategy of the sodium ion battery according to the current performance state of the sodium ion battery comprises: Determine a reward function of a plurality of control strategies to be determined corresponding to a current performance state; According to the reward function, evaluating the expected reward values that can be obtained by the multiple control strategies to be determined; The control strategy of the sodium ion battery is determined according to the expected reward value.
7. The method according to claim 5, characterized in that The step of determining the control strategy of the sodium ion battery according to the current performance state of the sodium ion battery comprises: When the current performance state of the sodium ion battery includes temperature abnormality, determining a temperature control strategy for the sodium ion battery; When the current performance state of the sodium ion battery includes abnormal charging and discharging speed, a charging and discharging strategy of the sodium ion battery is determined.
8. A sodium ion battery performance determination device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for determining the performance of a sodium ion battery according to any one of claims 1 to 7.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for determining the performance of a sodium ion battery according to any one of claims 1 to 7 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the method for determining the performance of a sodium ion battery according to any one of claims 1 to 7.
Citation Information
Cited By
Electrolyte formula property prediction method and device based on graph neural network
CN119296679A
Battery time capacity relationship determination method and device, equipment and medium
CN120908688A
