Digital twin energy storage management method and system

Abstract

The invention relates to a digital twinning energy storage management method and system, and the method comprises the steps: firstly obtaining the historical operation data and working environment data of a battery unit, analyzing the key feature correlation of the data, and determining the influence weight of the data on the efficiency of the battery unit; a correlation model of the operation state and efficiency of the battery unit is constructed based on the key features, and a prediction formula of the efficiency of the battery unit is obtained; meanwhile, a mathematical model of the electrochemical reaction process in the battery unit is established, and the efficiency change trend under different strategies is simulated; in addition, a mapping relation between electrochemical reaction and a working environment is established, and the influence of the working environment on the performance of the battery unit is quantified; on the basis, a control strategy of the battery unit management system is optimized, and a charging and discharging strategy combination under different conditions is determined; and finally, applying the optimization strategy to an actual system, and dynamically adjusting a charging and discharging strategy so as to improve the operation efficiency of the battery unit, prolong the service life of the battery unit, enhance the safety and provide a scientific basis for efficient management of an energy storage system.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage management, and in particular to a digital twin energy storage management method and system. Background Art

[0002] Electricity has become the core of modern life, and energy storage technology plays a vital role in the operation of the power grid. Whether it is household electricity or outdoor electricity use, higher requirements are placed on large-capacity and long-lasting energy storage battery cells. However, the performance of energy storage lithium-ion battery cells is easily affected by temperature fluctuations. Too high or too low temperature will not only reduce its efficiency, but may also significantly shorten the life of the battery cell. Limited by traditional technology, existing energy storage battery cells are difficult to achieve efficient, safe and stable operation. At the same time, there are also deficiencies in battery cell status analysis and refined regulation, resulting in low overall operating efficiency and hindering the promotion of green electricity.

[0003] The invention patent with patent application number 202310976868.4 discloses a method for energy storage management based on digital twins. Through real-time monitoring of energy storage battery cells, data correlation analysis is performed based on monitoring data and the operating status of corresponding battery cells, and an energy storage model based on digital twins is further constructed. The monitoring data to be analyzed is obtained in real time and imported into the energy storage model to evaluate the energy storage of battery cells. The energy storage battery cell optimization control scheme and operation and maintenance plan are generated based on the evaluation data, and the energy storage battery cell optimization control scheme and operation and maintenance plan are sent to the preset terminal device for display. The present invention can perform information management and analysis on energy storage battery cells, further improving the management efficiency and safety of energy storage battery cells.

[0004] However, in the actual energy storage management process, although a digital twin-based energy storage model was constructed through historical operating environment and charging and discharging data, and real-time monitoring and simulation analysis of the battery pack was realized, this method still has certain limitations: First, there is a lack of in-depth mining of the historical operating data and working environment data of the battery unit, and the influence weight of key characteristics on the efficiency of the battery unit is not clear; second, a mathematical model of the electrochemical reaction inside the battery unit has not been established, and the battery unit performance and parameter changes under different charging and discharging strategies cannot be accurately simulated; in addition, the mapping relationship between the electrochemical reaction inside the battery unit and the external parameters cannot be established, resulting in the inability to quantify the influence of external parameters on the performance of the battery unit. Summary of the invention

[0005] In response to the technical problems existing in the prior art, the present invention provides a digital twin energy storage management method, which achieves more accurate and efficient energy storage management by extracting key features, constructing a battery cell efficiency prediction model, establishing an electrochemical model, optimizing the control strategy and dynamically adjusting the charging and discharging strategy.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: S1, obtaining historical operation data of the battery unit and working environment data of the battery unit; S2, analyzing the correlation between key features of the data and determining the weight of the key features on the efficiency of the battery cell; S3, constructing a correlation model between the operating state and efficiency of the battery cell based on the key features, and obtaining a prediction formula for the battery cell efficiency; S4, establish a mathematical model of the electrochemical reaction process inside the battery cell to simulate the efficiency change trend of the battery cell under different strategies; S5, establishing a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and quantifying the influence of the working environment on the performance of the battery cell; S6, optimizing the control strategy of the battery unit management system based on all models and mapping relationships, and determining the combination of charging and discharging strategies under different working environment conditions; S7, applies the optimized control strategy to the actual system and dynamically adjusts the charging and discharging strategy.

[0007] Preferably, the S2, analyzing the correlation between key features of the data, includes: 2A, perform descriptive statistical analysis on time series data, use charts to visualize the results of the analysis, and extract key features from the patterns, trends, and outliers in the visualized charts; 2B, quantify the correlation between the extracted key features, and preliminarily screen out the features that are strongly correlated with the battery cell efficiency.

[0008] Preferably, the step S2, determining the weight of the impact of the key features on the battery cell efficiency, includes: 2C, using the features that are initially screened out and strongly correlated with battery cell efficiency to train a random forest model to predict battery cell efficiency; 2D, the importance value of each feature is calculated through the random forest model to evaluate its impact on the battery cell efficiency; 2E, use cross-validation method to evaluate model stability, adjust model parameters according to the evaluation results, and recalculate feature importance; 2F, filter key features according to feature importance values ​​and normalize and calculate their weights.

[0009] Preferably, the S6, battery unit management system, includes: S61, stratify the battery unit management system and establish an information interaction mechanism between the layers; S62, obtaining battery cell data in real time through sensors and performing status evaluation; S63, based on the battery cell status evaluation result, matching the optimal working point to generate a preliminary energy allocation plan; S64, based on the electrochemical reaction and status evaluation results of the battery cell, a machine learning model is used to predict the battery cell performance degradation trend and the optimal operating point; S65, allocating charging and discharging tasks according to the prediction results and determining the final energy allocation plan.

[0010] Preferably, the S63, optimal operating point, includes: the optimal operating point refers to the voltage and current at which the battery cell can operate most efficiently under specific conditions. For each battery cell, there is a specific efficiency curve, which represents the efficiency under different operating conditions.

[0011] Preferably, the S63 includes: S63a, real-time monitoring of the battery cell status, and real-time dynamic adjustment of the optimal operating point according to the current status of the battery cell; S63b, designing an optimal transition curve for an optimal operating point and predicting transient response characteristics of the battery cell during the switching process; S63c, calculating a switching coefficient according to an optimal transition curve and transient response characteristics; S63d, when the state of the battery cell changes, the switching of the optimal operating point is triggered, and the switching path of the optimal operating point is calculated according to the current state and the target state, and the actual operating state of the battery cell is gradually adjusted.

[0012] Preferably, the optimal transition curve can be expressed as: , is the optimal transition curve, For all possible transition curves, T, E and L are switching time, energy loss and battery cell life loss respectively; the transient response characteristics are quantified as a comprehensive index: , the battery cell terminal V(t) is the battery cell terminal voltage, I(t) is the battery cell terminal current, and T(t) is the battery cell terminal temperature; the switching coefficient calculation formula is: , and is the weight coefficient; the switching path calculation formula for the optimal working point is: , is the new optimal working point, is the current optimal working point, is the state change, is the switching coefficient, and the dynamic correction term is used to compensate for the impact of transient response characteristics on the switching path.

[0013] Preferably, the S63d comprises: d1, record the optimal working point of each battery unit and the corresponding working environment data; d2, combining multiple battery cells into a battery pack, and calculating the optimal operating point of the battery pack according to the connection method of the battery pack; d3, inputting data of different working environments into the battery pack simulation, and adjusting the optimal working point of the battery pack according to these data; d4, when the battery pack state changes and triggers the switching of the optimal working point, the overall transition time of the battery pack is calculated and recorded; d5, judging whether the battery pack switching path needs to optimize the switching path and switching coefficient according to the overall transition time of the battery pack and the preset standard.

[0014] Preferably, assuming that the battery pack consists of n battery cells, the optimal operating point of each battery cell is (where i=1,2,...,n), the optimal operating point of the battery pack It can be expressed as: , represents the optimal operating point of the ith battery cell, Represents a function or calculation method for converting the optimal operating point of each battery cell to Taken together, the optimal operating point of the battery pack is calculated , Indicates the number of battery cells in the battery pack; the adjustment formula is: , It is data of different working environments. It is the ultimate optimal working point.

[0015] The present application also provides a digital twin energy storage management system, the system comprising: A data acquisition module, used to acquire historical operation data of the battery unit and working environment data of the battery unit; A data analysis module is used to analyze the correlation between key features of the data and determine the weight of the key features on the efficiency of the battery cell; A correlation model building module is used to build a correlation model between the battery cell operating state and efficiency based on key features to obtain a prediction formula for the battery cell efficiency; Model building module, used to build a mathematical model of the electrochemical reaction process inside the battery cell and simulate the efficiency change trend of the battery cell under different strategies; A mapping relationship establishment module is used to establish a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and to quantify the influence of the working environment on the performance of the battery cell; The control strategy optimization module is used to optimize the control strategy of the battery unit management system based on all models and mapping relationships, and determine the combination of charging and discharging strategies under different working environment conditions; The strategy application module is used to apply the optimized control strategy to the actual system and dynamically adjust the charging and discharging strategy.

[0016] The beneficial effects of the present invention are: By acquiring the historical operation data and working environment data of the battery cell, analyzing the correlation between key features, building a correlation model between the operating status and efficiency of the battery cell, and establishing a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, the control strategy of the battery cell management system is optimized. It can accurately predict the performance of the battery cell, quantify the impact of the working environment on the efficiency of the battery cell, and dynamically adjust the charging and discharging strategy, thereby improving the operating efficiency of the battery cell, extending the life of the battery cell, and enhancing safety, providing a scientific basis and technical support for the efficient management of the energy storage system.

[0017] By managing the battery cell system in layers and establishing an information exchange mechanism between layers, real-time monitoring and evaluation of the battery cell status is achieved. At the same time, combined with the electrochemical reaction and status evaluation results of the battery cell, the machine learning model is used to predict the performance degradation trend and the optimal operating point, and the charging and discharging tasks are allocated accordingly to determine the final energy allocation plan. This solution improves energy utilization efficiency, extends the life of the battery cell, and can adapt to changes in the battery cell status in real time, with significant technical effects and advantages.

[0018] The optimal operating point can be adjusted dynamically by real-time monitoring of the battery cell status. The optimal transition curve is designed using a genetic algorithm, taking into account the switching time, energy loss, and battery cell life loss. The equivalent circuit model is used to predict the transient response characteristics of the battery cell during the switching process, including changes in the battery cell terminal voltage, current, and temperature. The switching coefficient is calculated based on the optimal transition curve and transient response characteristics. When the battery cell state changes, the switching of the optimal operating point is triggered, and the switching path is calculated based on the current state, target state, and state change. This technical solution improves the flexibility and efficiency of battery cell management, optimizes battery cell performance, and extends battery cell life.

[0019] This solution provides a basis for the optimized management of battery packs by accurately recording the optimal operating point of each battery cell and the corresponding working environment data. Secondly, based on the connection method of the battery pack, the solution can scientifically calculate the optimal operating point of the battery pack, and obtain accurate results regardless of series, parallel or mixed connection. In addition, the solution can dynamically adjust the optimal operating point of the battery pack based on the different working environment data of the simulated input, thereby improving the adaptability and stability of the battery pack. Finally, by calculating and recording the overall transition time of the battery pack, it provides strong support for the performance evaluation and optimization of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1A schematic diagram of a flow chart of a digital twin energy storage management method according to an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a digital twin energy storage management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0022] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0024] Embodiment 1: Figure 1 1 is a flow chart of a digital twin energy storage management method according to the first embodiment of the present invention, comprising the following steps: S1, obtaining the historical operation data of the battery unit and the working environment data of the battery unit.

[0025] Specifically, the historical operation data of the battery cells is collected from the battery cell management system (BMS) and matched and stored with the working environment data of the battery cells collected in real time by sensors.

[0026] The battery cell historical operation data is collected from the battery cell management system, including the current, voltage, power and state of charge (SOC) during the charging and discharging process. The working environment data is collected in real time through sensors, including the ambient temperature, humidity and current.

[0027] S2, analyzing the correlation between key features of the data and determining the weight of the key features on the efficiency of the battery cell.

[0028] Among them, the historical operation data and working environment data of the battery cells collected from the BMS are cleaned and sorted, and converted into time series data.

[0029] Specifically, the correlation between key features of the data is analyzed, including: 2A, perform descriptive statistical analysis on time series data, use charts to visualize the analysis results, and extract key features from the patterns, trends, and outliers in the visualized charts.

[0030] Among them, descriptive statistical analysis includes calculating the mean, standard deviation, maximum value, minimum value, median, etc. to understand the basic distribution and characteristics of the data.

[0031] 2B, quantify the correlation between the extracted key features, and preliminarily screen out the features that are strongly correlated with the battery cell efficiency.

[0032] Among them, the Pearson correlation coefficient is used to evaluate the linear relationship (positive correlation, negative correlation, nonlinearity) or monotonic relationship between key features, and the correlation coefficient matrix is ​​calculated. A scatter plot is used to show the relationship between two features, and the correlation is judged by observing the distribution and trend of data points. A heat map is used to show the correlation coefficient matrix, and the value of the correlation coefficient is represented by the depth of color. A significance test (t-test) is performed on the calculated correlation coefficient to determine the statistical significance of the correlation. According to the significance level (p value <0.05) and the absolute value of the correlation coefficient (|r|>0.7 indicates a strong correlation), the features that are strongly correlated with the battery cell efficiency are judged and screened.

[0033] Specifically, determine the weight of key characteristics on battery cell efficiency, including: 2C, use the features that are initially screened out and strongly correlated with battery cell efficiency to train a random forest model to predict battery cell efficiency.

[0034] 2D, the importance value of each feature is calculated by the random forest model to evaluate its impact on the battery cell efficiency.

[0035] 2E, the cross-validation method is used to evaluate the model stability, the model parameters are adjusted according to the evaluation results, and the feature importance is recalculated.

[0036] Among them, the feature importance formula is:

[0037] f is the feature, T is the number of decision trees, Gain(f,t) is the information gain of feature f in tree t, and the larger the feature importance value is, the greater the impact of the feature on the battery cell efficiency is.

[0038] 2F, filter key features according to feature importance values ​​and normalize and calculate their weights.

[0039] For example, assume that the battery cell data includes the following features: current, voltage, temperature, SOC (state of charge), and charge and discharge times. Calculate the Pearson correlation coefficient between current, voltage, temperature, SOC, and battery cell efficiency. It is found that the correlation coefficient between temperature and battery cell efficiency is , indicating that rising temperature will significantly reduce the efficiency of the battery cell. Using the random forest model, it is found that the feature importance value of temperature is 0.6, SOC is 0.3, and current is 0.1. The feature importance values ​​are normalized to obtain the weight of each feature. The temperature weight is 0.6 / (0.6+0.3+0.1)=0.6, the SOC weight is 0.3 / (0.6+0.3+0.1)=0.3, and the current weight is 0.1 / (0.6+0.3+0.1)=0.1, so temperature is the feature that has the greatest impact on battery cell efficiency.

[0040] S3, constructing a correlation model between the battery cell operating status and efficiency based on the key features, and obtaining a prediction formula for the battery cell efficiency.

[0041] Specifically, the key features extracted in step S2 are used as input variables, and the battery cell efficiency is used as the output variable to build a prediction model. The data set is divided into a training set and a test set, and a linear regression model, a support vector regression model, or a neural network model is selected according to the data characteristics. The key feature data of the training set is input into the model to fit the model parameters. The key feature data of the test set is input into the trained model to calculate the predicted value of the battery cell efficiency. The model parameters are adjusted according to the verification results, the model is retrained using the adjusted parameters, and the model performance is verified. The model with the best performance is selected as the final model, the key feature data collected in real time is input into the prediction formula, and the predicted value of the battery cell efficiency is calculated.

[0042] For example, assuming that the key features are temperature (x1), SOC (x2), and current (x3), the final model is a linear regression model: y=0.8+0.5x1+0.3x2+0.1x3; where y is the battery cell efficiency, x1 is the temperature with a weight of 0.5, x2 is the SOC with a weight of 0.3, and x3 is the current with a weight of 0.1.

[0043] S4, establishes a mathematical model of the electrochemical reaction process inside the battery cell and simulates the efficiency change trend of the battery cell under different strategies.

[0044] Among them, before executing step S4, it is necessary to clarify the battery cell type (such as lithium battery cell, lead-acid battery cell, etc.) and its electrochemical characteristics (electrode material, electrolyte composition and reaction mechanism) to determine whether the model simulates the efficiency change trend of the battery cell under different charging and discharging strategies.

[0045] Specifically, after clarifying the type of battery cell to be simulated and its basic electrochemical characteristics, select the equivalent circuit model, define the key parameters such as internal resistance, open circuit voltage, polarization voltage, etc. in the model, input the battery cell data under different charging and discharging strategies into the mathematical model, and use the mathematical model to simulate the performance (voltage, current, temperature changes) and parameter changes (internal resistance, capacity attenuation) of the battery cell under different strategies. Based on the simulation results, calculate the efficiency change trend of the battery cell under different strategies (for example: using the equivalent circuit model to simulate the constant current charging process, it is found that the battery cell terminal voltage gradually increases with the charging time, and the internal resistance increases with the temperature).

[0046] Among them, different discharge strategies include constant current charging, constant voltage charging, constant current-constant voltage charging, pulse charging, trickle charging, segmented charging and intelligent charging.

[0047] S5, establishing a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and quantifying the influence of the working environment on the performance of the battery cell.

[0048] Specifically, the efficiency change trend data of the battery cell under different charge and discharge strategies obtained in step S4 are integrated with the simulation results of the mathematical model of the electrochemical reaction inside the battery cell. The change trend of the internal reaction parameters (internal resistance, polarization voltage) of the battery cell with the working environment is analyzed. A mapping relationship is established using a neural network (for example, for every 10°C increase in temperature, the internal resistance increases by 20%), the working environment data of the battery cell is used as the input variable, and the internal reaction parameters of the battery cell are used as the output variable, and the degree of influence of the working environment on the performance of the battery cell is quantified through the mapping relationship.

[0049] For example, to establish a battery cell internal resistance With the working environment temperature The internal resistance of the battery cell at a certain working environment temperature is calculated based on the change relationship of

[0050] Represents the internal resistance of the battery cell at temperature T, Indicates reference temperature The internal resistance of the battery cell under The temperature coefficient represents the sensitivity of the internal resistance to temperature changes. T represents the current temperature. Reference temperature (usually room temperature, such as 25°C). Assume the reference temperature = Internal resistance at reference temperature 25°C , temperature coefficient , the current temperature T = 35°C. Calculate the internal resistance at the current temperature (35°C): .

[0051] S6, optimizes the battery cell management system control strategy based on all models and mapping relationships, and determines the combination of charging and discharging strategies under different working environment conditions.

[0052] Specifically, the association model of step S3, the electrochemical simulation results of step S4, and the mapping relationship of step S5 are integrated to form a complete battery cell performance model. Analyze the impact of different working environments and charging and discharging strategies on battery cell performance. Determine the optimization goals (maximize charging efficiency, extend battery cell life, and improve safety) according to application requirements, use optimization algorithms (genetic algorithms) to optimize charging and discharging strategies, define optimization variables (such as charging current, charging voltage, and discharge cut-off voltage), and determine the combination of charging and discharging strategies under different working environment conditions based on the optimization results (for example: use small current charging in high temperature environments to avoid overheating, use preheating strategies in low temperature environments to improve charging efficiency, and adjust charging voltage in high humidity environments to reduce polarization effects).

[0053] S7, applies the optimized control strategy to the actual system and dynamically adjusts the charging and discharging strategy.

[0054] Specifically, the optimized charging and discharging strategy is deployed to the battery cell management system, and sensors are used to monitor the electrochemical reaction process and working environment parameters inside the battery cell in real time. Based on the real-time monitoring data, the charging and discharging strategy is dynamically adjusted (for example, when the battery cell temperature exceeds the threshold, the charging current is automatically reduced; when the SOC approaches the upper limit, it switches to constant voltage charging mode) to ensure efficient and safe operation of the battery cell.

[0055] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By acquiring the historical operation data and working environment data of the battery cell, analyzing the correlation between key features, building a correlation model between the operating status and efficiency of the battery cell, and establishing a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, the control strategy of the battery cell management system is optimized. It can accurately predict the performance of the battery cell, quantify the impact of the working environment on the efficiency of the battery cell, and dynamically adjust the charging and discharging strategy, thereby improving the operating efficiency of the battery cell, extending the life of the battery cell, and enhancing safety, providing a scientific basis and technical support for the efficient management of the energy storage system.

[0056] Example 2 In Example 1, by acquiring the historical operation data and working environment data of the battery cell, analyzing the correlation between the key features, constructing the correlation model between the operating state and efficiency of the battery cell, and establishing the mapping relationship between the electrochemical reaction inside the battery cell and the working environment, the control strategy of the battery cell management system is optimized. However, the battery cell management system in Example 1 adopts a single-level management architecture, which fails to fully consider the differences between the battery pack and the battery cell, resulting in insufficient refinement of energy distribution and balanced control. In the face of state differences (such as SOC, temperature, and health status) of different battery cells, the use of a unified management strategy will inevitably result in optimization errors and weak generalization capabilities. Due to the differences in electrochemical reaction parameters and performance decay trends of different battery cells, there must be differences in the judgment requirements for energy distribution and balanced control. In order to further refine and distinguish the control strategy of the battery cell management system and obtain a more accurate energy distribution plan, it is necessary to simultaneously consider the state evaluation results, electrochemical reaction parameters, and performance decay trends of the battery cell, and make further optimization improvements. Therefore, on the basis of Example 1, Example 2 divides the battery cell management system into layers, and establishes an information interaction mechanism between the layers to achieve more refined energy distribution and balanced control.

[0057] In some embodiments, the control strategy of the battery unit management system is optimized, and step S6 further includes: S61, the battery unit management system is layered and an information interaction mechanism between the layers is established.

[0058] Among them, the battery cell management system is divided into three layers: the top layer is the system-level management layer, which is responsible for overall energy scheduling and strategy formulation, receives data from the middle and bottom layers, and generates a global energy allocation plan; the middle layer is the battery pack-level management layer, which is responsible for the energy distribution and balancing control of the battery pack, receives bottom-layer data, and generates an energy allocation plan for the battery pack; the bottom layer is the battery cell-level management layer, which is responsible for the monitoring and control of a single battery cell, and obtains the real-time charge state, temperature, voltage and other data of the battery cell through sensors.

[0059] An information exchange mechanism is established between the layers. The bottom layer uploads the real-time data of the battery unit to the middle layer. The middle layer uploads the energy allocation plan of the battery pack to the top layer. The top layer sends the global energy allocation plan to the middle and bottom layers. The middle layer adjusts the energy allocation of the battery pack according to the instructions of the top layer, and the bottom layer adjusts the charge and discharge strategy of a single battery unit according to the instructions of the middle layer.

[0060] S62, obtaining battery cell data in real time through sensors and performing status assessment.

[0061] Specifically, the sensors installed on the battery cells collect the SOC, temperature, voltage and other data of the battery cells in real time. The collected raw data is cleaned to remove outliers, noise and other interference, and the data of different dimensions are normalized. According to the characteristics and evaluation requirements of the battery cells, a neural network algorithm model is selected for state evaluation. The model is trained using historical data, and the preprocessed real-time data is input into the trained state evaluation model. The model calculates the current state indicators of the battery cell based on the input data, such as the state of health (SOH), remaining life (RUL), etc.

[0062] S63, based on the battery cell status evaluation result, matching the optimal working point to generate a preliminary energy allocation plan.

[0063] Among them, the optimal operating point refers to the voltage and current at which the battery cell can work most efficiently under specific conditions. For each battery cell, there is a specific efficiency curve that represents the efficiency under different operating conditions. Through experiments or simulations, these efficiency curves are obtained, and the voltage and current at the highest efficiency point are found. When looking for the optimal operating point, the constraints of the battery cell, such as the maximum charge / discharge current, the highest / lowest operating temperature, etc., must also be considered. Define the objective function to comprehensively measure the efficiency, life, safety and other performance of the battery cell under specific operating conditions. Use the optimization algorithm to find the operating point that maximizes the objective function under the constraints. The optimization algorithm can traverse the solution space and find the operating point closest to the optimal solution.

[0064] Experimental tests are conducted on actual battery cells to verify whether the operating point found by the optimization algorithm is the optimal operating point. The experimental tests include charge and discharge cycles, temperature cycles, etc. to simulate actual usage scenarios. Based on the experimental test results, the optimization algorithm and state assessment model are adjusted and optimized to continuously improve the accuracy and reliability of finding the optimal operating point.

[0065] S64, based on the electrochemical reaction and status evaluation results of the battery cell, uses a machine learning model to predict the battery cell performance degradation trend and optimal operating point.

[0066] Specifically, training data is prepared based on the electrochemical reaction and state assessment results of the battery cells. The performance degradation trend of the battery cells is modeled using a neural network machine learning model. The established performance degradation model is used to predict the optimal operating point of each battery cell in the future.

[0067] S65, allocating charging and discharging tasks according to the prediction results and determining the final energy allocation plan.

[0068] Specifically, the charging and discharging tasks are allocated based on the predicted optimal operating point and the current system requirements. The battery cells are ensured to operate near the optimal operating point to improve energy efficiency and extend the battery cell life. The final energy allocation plan is determined by comprehensively considering the prediction results, system requirements, and battery cell status.

[0069] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By managing the battery cell system in layers and establishing an information exchange mechanism between layers, real-time monitoring and evaluation of the battery cell status is achieved. At the same time, combined with the electrochemical reaction and status evaluation results of the battery cell, the machine learning model is used to predict the performance degradation trend and the optimal operating point, and the charging and discharging tasks are allocated accordingly to determine the final energy allocation plan. This solution improves energy utilization efficiency, extends the life of the battery cell, and can adapt to changes in the battery cell status in real time, with significant technical effects and advantages.

[0070] Example 3 In Example 2, refined monitoring and control of battery cells have been achieved through the battery cell management system hierarchical and information interaction mechanism, and an energy distribution plan is generated by matching the optimal working point based on the state evaluation results. However, when the state of the battery cell changes, directly switching to a new optimal working point may cause transient response problems, affecting the performance and life of the battery cell. In addition, there are differences in the transition characteristics of different battery cells when switching states, and it is difficult to ensure optimality using a unified transition strategy. In order to further optimize the switching process of the battery cell working point and improve the accuracy and reliability of the energy distribution plan, Example 3 introduces the optimal transition curve design while considering the current state of the battery cell, monitors the battery cell state in real time, and dynamically adjusts the optimal working point. At the same time, the switching coefficient is calculated based on the smoothness of the transition curve, energy loss, battery cell life loss, and transient response characteristics to more finely control the switching path of the working point.

[0071] In some embodiments, step S63 further includes: S63a, monitor the battery cell status in real time, and dynamically adjust the optimal working point in real time according to the current status of the battery cell.

[0072] S63b, designing an optimal transition curve for an optimal working point, and predicting transient response characteristics of the battery cell during the switching process.

[0073] The optimal transition curve is designed by using a genetic algorithm to design the optimal transition curve, initialize the population, randomly generate a set of transition curves, calculate the fitness of each transition curve (i.e., the objective function value), generate a new generation of populations through selection, crossover, and mutation operations, and repeat the above process until the optimal transition curve is found. The optimal transition curve can be expressed as:

[0074] is the optimal transition curve, For all possible transition curves, T, E and L are switching time, energy loss and battery cell life loss respectively. The switching time T is calculated as: , and are the start and end time of the switching process respectively. The energy loss E is calculated as: , is the current, is the internal resistance. The battery cell life loss L is calculated as: , is the capacity of the battery unit. For detailed methods of designing the optimal transition curve, please refer to the prior art, which will not be described in detail in this article.

[0075] The equivalent circuit model is used to predict the transient response characteristics of the battery cell during the switching process. , calculate the battery cell terminal voltage , , is the battery cell terminal voltage, is the internal resistance, is the polarization voltage, is the open circuit voltage. It can be expressed as: , is the initial polarization voltage, is the time constant, is the steady-state polarization voltage, The indicated time is the time elapsed from the moment the polarization condition is applied. and internal resistance , calculate the battery cell temperature change , C is the heat capacity of the battery cell, is the ambient temperature, is the thermal resistance. Output battery cell terminal voltage , Current ,temperature Changes over time.

[0076] The transient response characteristics are quantified as a comprehensive index:

[0077] S63c, calculating the switching coefficient according to the optimal transition curve and transient response characteristics.

[0078] The calculation formula of the switching coefficient is:

[0079] and is the weight coefficient used to balance the importance of different factors.

[0080] S63d, when the state of the battery cell changes, the switching of the optimal operating point is triggered, and the switching path of the optimal operating point is calculated according to the current state and the target state, and the actual operating state of the battery cell is gradually adjusted.

[0081] Among them, the triggering condition for switching the optimal working point is:

[0082] The above thresholds are set according to the application scenario and historical battery cell data.

[0083] The calculation formula of the switching path of the optimal working point is:

[0084] is the new optimal working point, is the current optimal working point, is the state change (such as SOC change, temperature change), is the switching coefficient, and the dynamic correction term is used to compensate for the impact of transient response characteristics on the switching path.

[0085] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: The optimal operating point can be adjusted dynamically by real-time monitoring of the battery cell status. The optimal transition curve is designed using a genetic algorithm, taking into account the switching time, energy loss, and battery cell life loss. The equivalent circuit model is used to predict the transient response characteristics of the battery cell during the switching process, including changes in the battery cell terminal voltage, current, and temperature. The switching coefficient is calculated based on the optimal transition curve and transient response characteristics. When the battery cell state changes, the switching of the optimal operating point is triggered, and the switching path is calculated based on the current state, target state, and state change. This technical solution improves the flexibility and efficiency of battery cell management, optimizes battery cell performance, and extends battery cell life.

[0086] Example 4 In Example 3, refined monitoring and control of battery cells have been achieved, and an energy allocation plan has been generated based on state evaluation. However, the battery pack is composed of multiple battery cells, and the state switching process is complex and significantly different. It is difficult for a unified transition strategy to ensure the optimal performance of the battery pack. In order to further optimize the switching process of the battery pack operating point and improve the efficiency and reliability of energy management, Example 4 introduces a method for calculating the optimal operating point of the battery pack while considering the optimal operating point of a single battery cell. By recording the optimal operating point and corresponding environmental data of each battery cell, the optimal operating point of the battery pack is calculated according to the connection method of the battery pack, and different working environment data are simulated for adjustment. At the same time, the overall transition time when the battery pack state changes is monitored to determine whether the switching path needs to be optimized, so as to more finely control the operating point switching process of the battery pack.

[0087] In some embodiments, step S63d further includes: d1, record the optimal working point of each battery cell and the corresponding working environment data.

[0088] d2, combine multiple battery cells into a battery pack, and calculate the optimal operating point of the battery pack according to the connection method of the battery pack.

[0089] Assume that the battery pack consists of n battery cells, and the optimal operating point of each battery cell is (where i=1,2,...,n), the optimal operating point of the battery pack It can be expressed as: , represents the optimal operating point of the ith battery cell, Represents a function or calculation method for converting the optimal operating point of each battery cell to Taken together, the optimal operating point of the battery pack is calculated , n represents the number of battery cells in the battery pack. The specific formula varies depending on how the battery pack is connected: The formula for calculating the optimal operating point of a battery pack connected in series is: , , is the optimal voltage of the ith battery cell, is the optimal current of the ith battery cell, is the optimal total voltage of the battery pack, is the optimum total current of the battery pack.

[0090] The formula for calculating the optimal operating point of the battery pack connected in parallel is: , , is the optimal voltage of the ith battery cell, is the optimal current of the ith battery cell, is the optimal total voltage of the battery pack, is the optimal total current of the battery pack. For a hybrid connected battery pack, assuming that the battery pack consists of m series modules, each module contains k parallel battery cells, the optimal operating point calculation formula of the battery pack is: , , is the optimum voltage for each module, is the optimum current for each module, is the optimal total voltage of the battery pack, is the optimum total current of the battery pack.

[0091] d3, input data of different working environments into the battery pack simulation, and adjust the optimal working point of the battery pack according to these data.

[0092] The adjustment formula is:

[0093] It is the best working point of the battery pack. It is data of different working environments. It is the ultimate optimal working point.

[0094] d4: When the battery pack state changes and triggers the switching of the optimal working point, the overall transition time of the battery pack is calculated and recorded.

[0095] The overall transition time refers to the total time it takes for the battery pack to switch from the current operating point to the new operating point.

[0096] d5, judging whether the battery pack switching path needs to optimize the switching path and switching coefficient according to the overall transition time of the battery pack and the preset standard.

[0097] Among them, the preset standard threshold of the overall transition time of the battery pack is specifically determined according to the type, scale and application scenario of the battery pack.

[0098] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: This solution provides a basis for the optimized management of battery packs by accurately recording the optimal operating point of each battery cell and the corresponding working environment data. Secondly, based on the connection method of the battery pack, the solution can scientifically calculate the optimal operating point of the battery pack, and obtain accurate results regardless of series, parallel or mixed connection. In addition, the solution can dynamically adjust the optimal operating point of the battery pack based on the different working environment data of the simulated input, thereby improving the adaptability and stability of the battery pack. Finally, by calculating and recording the overall transition time of the battery pack, it provides strong support for the performance evaluation and optimization of the battery pack.

[0099] Furthermore, an embodiment of the present invention also provides a digital twin energy storage management system.

[0100] Figure 2 It is a structural schematic diagram of a digital twin energy storage management system according to an embodiment of the present invention.

[0101] like Figure 2 As shown, a digital twin energy storage management system includes: a data acquisition module, a data analysis module, an association model construction module, a model establishment module, a mapping relationship establishment module, a control strategy optimization module and a strategy application module.

[0102] A data acquisition module, used to acquire historical operation data of the battery unit and working environment data of the battery unit; A data analysis module is used to analyze the correlation between key features of the data and determine the weight of the key features on the efficiency of the battery cell; A correlation model building module is used to build a correlation model between the battery cell operating state and efficiency based on key features to obtain a prediction formula for the battery cell efficiency; Model building module, used to build a mathematical model of the electrochemical reaction process inside the battery cell and simulate the efficiency change trend of the battery cell under different strategies; A mapping relationship establishment module is used to establish a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and to quantify the influence of the working environment on the performance of the battery cell; The control strategy optimization module is used to optimize the control strategy of the battery unit management system based on all models and mapping relationships, and determine the combination of charging and discharging strategies under different working environment conditions; The strategy application module is used to apply the optimized control strategy to the actual system and dynamically adjust the charging and discharging strategy.

[0103] It should be noted that other specific implementation contents of the digital twin energy storage management system of the embodiment of the present invention can refer to the above-mentioned digital twin energy storage management method.

[0104] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0110] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A digital twin energy storage management method, characterized in that: The method comprises: S1, obtaining historical operation data of the battery unit and working environment data of the battery unit; S2, analyzing the correlation between key features of the data and determining the weight of the key features on the efficiency of the battery cell; S3, constructing a correlation model between the operating state and efficiency of the battery cell based on the key features, and obtaining a prediction formula for the battery cell efficiency; S4, establish a mathematical model of the electrochemical reaction process inside the battery cell to simulate the efficiency change trend of the battery cell under different strategies; S5, establishing a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and quantifying the influence of the working environment on the performance of the battery cell; S6, optimizing the control strategy of the battery unit management system based on all models and mapping relationships, and determining the combination of charging and discharging strategies under different working environment conditions; S7, applies the optimized control strategy to the actual system and dynamically adjusts the charging and discharging strategy.

2. The digital twin energy storage management method according to claim 1, characterized in that: S2, analyzing the correlation between key features of the data, includes: 2A, perform descriptive statistical analysis on time series data, use charts to visualize the results of the analysis, and extract key features from the patterns, trends, and outliers in the visualized charts; 2B, quantify the correlation between the extracted key features, and preliminarily screen out the features that are strongly correlated with the battery cell efficiency.

3. The digital twin energy storage management method according to claim 1, characterized in that: S2, determining the weight of the key features on the battery cell efficiency, includes: 2C, using the features that are initially screened out and strongly correlated with battery cell efficiency to train a random forest model to predict battery cell efficiency; 2D, the importance value of each feature is calculated through the random forest model to evaluate its impact on the battery cell efficiency; 2E, use cross-validation method to evaluate model stability, adjust model parameters according to the evaluation results, and recalculate feature importance; 2F, filter key features according to feature importance values ​​and normalize and calculate their weights.

4. The digital twin energy storage management method according to claim 1, characterized in that: The S6, battery cell management system, comprises: S61, stratify the battery unit management system and establish an information interaction mechanism between the layers; S62, obtaining battery cell data in real time through sensors and performing status evaluation; S63, based on the battery cell status evaluation result, matching the optimal working point to generate a preliminary energy allocation plan; S64, based on the electrochemical reaction and status evaluation results of the battery cell, a machine learning model is used to predict the battery cell performance degradation trend and the optimal operating point; S65, allocating charging and discharging tasks according to the prediction results and determining the final energy allocation plan.

5. The digital twin energy storage management method according to claim 4, characterized in that: The S63, optimal operating point, includes: the optimal operating point refers to the voltage and current at which the battery cell can operate most efficiently under specific conditions. For each battery cell, there is a specific efficiency curve, which represents the efficiency under different operating conditions.

6. The digital twin energy storage management method according to claim 4, characterized in that: The S63 includes: S63a, real-time monitoring of the battery cell status, and real-time dynamic adjustment of the optimal operating point according to the current status of the battery cell; S63b, designing an optimal transition curve for an optimal operating point and predicting transient response characteristics of the battery cell during the switching process; S63c, calculating a switching coefficient according to an optimal transition curve and transient response characteristics; S63d, when the state of the battery cell changes, the switching of the optimal operating point is triggered, and the switching path of the optimal operating point is calculated according to the current state and the target state, and the actual operating state of the battery cell is gradually adjusted.

7. The digital twin energy storage management method according to claim 6, characterized in that: include: The optimal transition curve can be expressed as: is the optimal transition curve, For all possible transition curves, T, E and L are switching time, energy loss and battery cell life loss respectively; the transient response characteristics are quantified as a comprehensive indicator: , the battery cell terminal V(t) is the battery cell terminal voltage, I(t) is the battery cell terminal current, and T(t) is the battery cell terminal temperature; the switching coefficient calculation formula is: , and is the weight coefficient; The switching path calculation formula for the optimal working point is: , is the new optimal working point, is the current optimal working point, is the state change, is the switching coefficient, and the dynamic correction term is used to compensate for the impact of transient response characteristics on the switching path.

8. The digital twin energy storage management method according to claim 6, characterized in that: The S63d comprises: d1, record the optimal working point of each battery unit and the corresponding working environment data; d2, combining multiple battery cells into a battery pack, and calculating the optimal operating point of the battery pack according to the connection method of the battery pack; d3, inputting data of different working environments into the battery pack simulation, and adjusting the optimal working point of the battery pack according to these data; d4, when the battery pack state changes and triggers the switching of the optimal working point, the overall transition time of the battery pack is calculated and recorded; d5, judging whether the battery pack switching path needs to optimize the switching path and switching coefficient according to the overall transition time of the battery pack and the preset standard.

9. The digital twin energy storage management method according to claim 8, characterized in that: include: Assume that the battery pack consists of n battery cells, and the optimal operating point of each battery cell is , where i=1,2,...,n, the optimal operating point of the battery pack It can be expressed as: , represents the optimal operating point of the ith battery cell, and f represents a function or calculation method for converting the optimal operating point of each battery cell into Taken together, the optimal operating point of the battery pack is calculated , n represents the number of battery cells in the battery pack; the adjustment formula is: , It is data of different working environments. It is the ultimate optimal working point.

10. A digital twin energy storage management system, applied to a digital twin energy storage management method as claimed in any one of claims 1 to 9, characterized in that: The system comprises: A data acquisition module, used to acquire historical operation data of the battery unit and working environment data of the battery unit; A data analysis module is used to analyze the correlation between key features of the data and determine the weight of the key features on the efficiency of the battery cell; A correlation model building module is used to build a correlation model between the battery cell operating state and efficiency based on key features to obtain a prediction formula for the battery cell efficiency; Model building module, used to build a mathematical model of the electrochemical reaction process inside the battery cell and simulate the efficiency change trend of the battery cell under different strategies; A mapping relationship establishment module is used to establish a mapping relationship between the electrochemical reaction inside the battery cell and the working environment, and to quantify the influence of the working environment on the performance of the battery cell; The control strategy optimization module is used to optimize the control strategy of the battery unit management system based on all models and mapping relationships, and determine the combination of charging and discharging strategies under different working environment conditions; The strategy application module is used to apply the optimized control strategy to the actual system and dynamically adjust the charging and discharging strategy.

Images