A digital-twin energy storage management method and system

Abstract

The application relates to a digital twin energy storage management method and system, which comprises the following steps: firstly, obtaining battery unit historical operation data and working environment data, analyzing the correlation of key features of the data, and determining the influence weight of the data on the battery unit efficiency; then, constructing a correlation model of the battery unit operation state and the efficiency based on the key features, and obtaining a prediction formula of the battery unit efficiency; at the same time, establishing a mathematical model of the internal electrochemical reaction process of the battery unit, and simulating the efficiency change trend under different strategies; in addition, establishing a mapping relationship between the electrochemical reaction and the working environment, and quantifying the influence of the working environment on the performance of the battery unit; based on this, optimizing the control strategy of the battery unit management system, and determining the charge-discharge strategy combination under different conditions; finally, applying the optimized strategy to the actual system, dynamically adjusting the charge-discharge 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 the efficient management of the energy storage system.

Description

TECHNICAL FIELD

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

[0002] Electricity has become the core of modern life, and energy storage technology plays a crucial role in power grid operation. Whether it is household electricity or outdoor electricity scene, it puts forward higher demand for large-capacity, long-endurance energy storage battery units. However, the performance of energy storage lithium-ion battery units is easily affected by temperature fluctuations, and high or low temperature will not only reduce its efficiency, but also significantly shorten the battery unit life. Limited by traditional technology, the existing energy storage battery units are difficult to achieve efficient, safe and stable operation, and there are also deficiencies in battery unit state analysis and fine control, resulting in low overall operation efficiency, hindering the promotion of green electric energy.

[0003] The patent application No. 202310976868.4 discloses an energy storage management method based on digital twin, which realizes real-time monitoring of energy storage battery units, data correlation analysis based on monitoring data and corresponding battery unit operating state, further constructs an energy storage model based on digital twin, real-time acquisition of monitoring data to be analyzed and import into the energy storage model for battery unit energy storage evaluation, generation of energy storage battery unit optimization control scheme and operation and maintenance plan based on evaluation data, and sending of the energy storage battery unit optimization control scheme and operation and maintenance plan to a preset terminal device for display. Through the present application, information management and analysis of energy storage battery units can be realized, and the management efficiency and safety of energy storage battery units can be further improved.

[0004] However, in the actual energy storage management process, although the energy storage model based on digital twin is constructed by historical operating environment and charge-discharge data, and real-time monitoring and simulation analysis of the battery pack are realized, the method still has certain limitations: first, the historical operation data and working environment data of the battery unit are not deeply mined, and the influence weight of the key features on the efficiency of the battery unit is not clear; second, the mathematical model of the internal electrochemical reaction of the battery unit is not established, and the performance of the battery unit and the parameter change under different charge-discharge strategies cannot be accurately simulated; in addition, the mapping relationship between the internal electrochemical reaction of the battery unit and the external parameters is not established, so that the influence degree of the external parameters on the performance of the battery unit cannot be quantified. SUMMARY

[0005] The present application provides a digital twin energy storage management method to solve the technical problems in the prior art, which realizes more accurate and efficient energy storage management by extracting key features, constructing a battery unit efficiency prediction model, establishing an electrochemical model, optimizing control strategies and dynamically adjusting charge-discharge strategies.

[0006] The technical solution of the present application to solve the above technical problems is as follows:

[0007] S1, obtaining battery cell historical operation data and battery cell working environment data;

[0008] S2, analyzing the correlation between the key features of the data to determine the influence weight of the key features on the battery cell efficiency;

[0009] S3, constructing a correlation model of the battery cell operation state and efficiency based on the key features to obtain a prediction formula of the battery cell efficiency;

[0010] S4, establishing a mathematical model of the internal electrochemical reaction process of the battery cell to simulate the efficiency change trend of the battery cell under different strategies;

[0011] S5, establishing a mapping relationship between the internal electrochemical reaction of the battery cell and the working environment to quantify the influence degree of the working environment on the performance of the battery cell;

[0012] S6, optimizing the control strategy of the battery cell management system based on all the models and mapping relationships to determine the combination of charging and discharging strategies under different working environment conditions;

[0013] S7, applying the optimized control strategy to the actual system to dynamically adjust the charging and discharging strategies.

[0014] Preferably, the S2, analyzing the correlation between the key features of the data, comprises:

[0015] 2A, performing descriptive statistical analysis on the time series data, visualizing the analyzed results using charts, and extracting the patterns, trends and outliers in the visualized charts as key features;

[0016] 2B, quantifying the correlation between the extracted key features, and preliminarily screening out features strongly correlated with the battery cell efficiency.

[0017] Preferably, the S2, determining the influence weight of the key features on the battery cell efficiency, comprises:

[0018] 2C, using the features preliminarily screened out as the features strongly correlated with the battery cell efficiency to train a random forest model to predict the battery cell efficiency;

[0019] 2D, calculating the importance value of each feature through the random forest model to evaluate its influence on the battery cell efficiency;

[0020] 2E, evaluating the stability of the model by using a cross-validation method, adjusting the model parameters according to the evaluation results, and recalculating the feature importance;

[0021] 2F, screening key features according to feature importance values and normalizing calculation of weights thereof.

[0022] Preferably, the S6, the battery cell management system, comprises:

[0023] S61, layering the battery cell management system and establishing information interaction mechanism between layers;

[0024] S62, real-time acquisition of battery cell data by sensors and state evaluation;

[0025] S63, based on the battery cell state evaluation results, matching the best working point to generate a preliminary energy distribution scheme;

[0026] S64, based on the battery cell electrochemical reaction and state evaluation results, using machine learning model to predict battery cell performance degradation trend and best working point;

[0027] S65, according to the prediction results, adjust the charge and discharge task, determine the final energy distribution scheme.

[0028] Preferably, the S63, the best working point, comprises: the best working point refers to the voltage and current that the battery cell can work most efficiently under certain conditions. For each battery cell, there is a specific efficiency curve indicating the efficiency under different working conditions.

[0029] Preferably, the S63 comprises:

[0030] S63a, real-time monitoring of battery cell state, real-time dynamic adjustment of best working point according to current state of battery cell;

[0031] S63b, designing the optimal transition curve of the best working point, predicting the transient response characteristics of the battery cell in the switching process;

[0032] S63c, calculating the switching coefficient according to the optimal transition curve and the transient response characteristics;

[0033] S63d, when the state of the battery cell changes, triggering the switching of the best working point, calculating the switching path of the best working point according to the current state and the target state, and gradually adjusting the actual running state of the battery cell.

[0034] Preferably, the optimal transition curve can be expressed as: , is the optimal transition curve, is 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 as follows: , V(t) is the battery cell terminal voltage, I(t) is the battery cell terminal current, T(t) is the battery cell terminal temperature; the switching coefficient calculation formula is: , and is a weight coefficient; the switching path calculation formula of the optimal working point is: , is a new optimal working point, is a current optimal working point, is a state change amount, is a switching coefficient, and the dynamic correction term is to compensate the influence of transient response characteristics on the switching path.

[0035] Preferably, the S63d comprises:

[0036] d1, record the optimal working point of each battery cell and the corresponding working environment data;

[0037] d2, combine a plurality of battery cells into a battery pack, and calculate the optimal working point of the battery pack according to the connection mode of the battery pack;

[0038] d3, simulate inputting data of different working environments to the battery pack, and adjust the optimal working point of the battery pack according to the data;

[0039] d4, when the state of the battery pack changes and triggers the switching of the optimal working point, calculate and record the overall transition time of the battery pack;

[0040] d5, according to the overall transition time of the battery pack and the preset standard, judge whether the switching path of the battery pack needs to be optimized.

[0041] Preferably, assuming that the battery pack is composed of n battery cells, the optimal working point of each battery cell is (wherein i=1, 2,..., n), and the optimal working point of the battery pack can be expressed as: , represents the optimal working point of the i-th battery cell, represents a function or calculation method for calculating the optimal working point of each battery cell , and the optimal working point of the battery pack , represents the number of battery cells in the battery pack; the adjustment formula is: , is data of different working environments, is the final optimal working point.

[0042] The application also provides a digital twin energy storage management system, which comprises:

[0043] a data acquisition module configured to acquire historical operation data and working environment data of the battery unit;

[0044] a data analysis module configured to analyze the correlation between key features and determine the influence weight of the key features on the efficiency of the battery unit;

[0045] a correlation model construction module configured to construct a correlation model between the operation state and the efficiency of the battery unit based on the key features, and obtain a prediction formula of the efficiency of the battery unit;

[0046] a model establishment module configured to establish a mathematical model of the internal electrochemical reaction process of the battery unit, and simulate the efficiency variation trend of the battery unit under different strategies;

[0047] a mapping relationship establishment module configured to establish a mapping relationship between the internal electrochemical reaction and the working environment of the battery unit, and quantify the influence degree of the working environment on the performance of the battery unit;

[0048] a control strategy optimization module configured to optimize the control strategy of the battery unit management system based on all the models and the mapping relationship, and determine the combination of the charging and discharging strategies under different working environment conditions;

[0049] a strategy application module configured to apply the optimized control strategy to an actual system and dynamically adjust the charging and discharging strategies.

[0050] The present application has the following advantages:

[0051] By acquiring the historical operation data and the working environment data of the battery unit, analyzing the correlation between the key features, constructing the correlation model between the operation state and the efficiency of the battery unit, and establishing the mapping relationship between the internal electrochemical reaction and the working environment of the battery unit, the control strategy of the battery unit management system is optimized. The performance of the battery unit can be accurately predicted, the influence of the working environment on the efficiency of the battery unit can be quantified, and the charging and discharging strategies can be dynamically adjusted, thereby improving the operation efficiency of the battery unit, prolonging the service life of the battery unit, enhancing the safety, and providing a scientific basis and technical support for the efficient management of the energy storage system.

[0052] By managing the battery unit system in layers and establishing the information interaction mechanism between the layers, the real-time monitoring and evaluation of the state of the battery unit are realized. Meanwhile, by combining the electrochemical reaction of the battery unit and the state evaluation result, the performance degradation trend and the optimal working point are predicted by using a machine learning model, and the charging and discharging tasks are allocated accordingly to determine the final energy distribution scheme. The scheme improves the energy utilization efficiency, prolongs the service life of the battery unit, and can adapt to the state change of the battery unit in real time, and has significant technical effects and advantages.

[0053] By monitoring the battery cell state in real time, the optimal operating point is dynamically adjusted. Genetic algorithm is used to design the optimal transition curve, considering 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 switching, including the changes of battery cell terminal voltage, current and temperature. According to the optimal transition curve and the transient response characteristics, the switching coefficient is calculated, the switching of the optimal operating point is triggered when the battery cell state changes, and the switching path is calculated according to the current state, target state and state change. This technical scheme improves the flexibility and efficiency of battery cell management, optimizes the battery cell performance and prolongs the battery cell life.

[0054] This scheme provides a basis for the optimal management of the battery pack by accurately recording the optimal operating point of each battery cell and the corresponding working environment data. Secondly, according to the connection mode of the battery pack, this scheme can scientifically calculate the optimal operating point of the battery pack, and accurate results can be obtained whether the connection is in series, parallel or mixed. In addition, this scheme can dynamically adjust the optimal operating point of the battery pack according to different working environment data simulated by input, improving the adaptability and stability of the battery pack. Finally, by calculating and recording the overall transition time of the battery pack, strong support is provided for the performance evaluation and optimization of the battery pack. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 A flowchart of a digital twin energy storage management method according to an embodiment of the present application;

[0056] Figure 2 A structural diagram of a digital twin energy storage management system according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] In the description of the present application, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0059] In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration." Any embodiment described as "for example" in this application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present application. It will be apparent, however, to one skilled in the art that the present application can be practiced without using these specific details. In other instances, well-known structures and processes are not elaborated upon in order to avoid unnecessary detail, which can obscure the description of the present application. Thus, the present application is not intended to be limited by the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0060] Embodiment 1: Figure 1 is a flowchart of a digital twin energy storage management method according to an embodiment of the present application, comprising the following steps:

[0061] S1, obtaining battery cell historical operation data and battery cell working environment data.

[0062] Specifically, the battery cell historical operation data is collected from the battery cell management system (BMS), and is matched and stored with the battery cell working environment data collected in real time through the sensor.

[0063] Among them, the battery cell historical operation data is collected from the battery cell management system, including current, voltage, power and state of charge (SOC) during charging and discharging process. The working environment data is collected in real time through the sensor, including environmental temperature, humidity and current.

[0064] S2, analyze the correlation between the key features of the data, and determine the influence weight of the key features on the battery cell efficiency.

[0065] Among them, the battery cell historical operation data and working environment data collected from the BMS are cleaned and arranged, and are converted into time series data.

[0066] Specifically, the correlation between the key features of the data is analyzed, including:

[0067] 2A, descriptive statistical analysis is performed on the time series data, the results after analysis are visualized using charts, and the patterns, trends and outliers in the visualized charts are extracted as key features.

[0068] Among them, the descriptive statistical analysis includes calculating the mean, standard deviation, maximum value, minimum value, median and the like, in order to understand the basic distribution and characteristics of the data.

[0069] 2B, quantify the correlation between the extracted key features, and preliminarily screen out the features strongly related to the battery cell efficiency.

[0070] 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. Scatter plots are used to show the relationship between two features, and the correlation is determined by observing the distribution and trend of data points. Heat maps are used to display the correlation coefficient matrix, and the color depth represents the value of the correlation coefficient. The calculated correlation coefficients are subjected to significance test (t-test) 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 strong correlation), the features strongly related to the battery cell efficiency are judged and screened out.

[0071] Specifically, the influence weight of key features on battery cell efficiency is determined, including:

[0072] 2C, use the features preliminarily screened out to train a random forest model to predict the battery cell efficiency.

[0073] 2D, calculate the importance value of each feature through the random forest model to evaluate its influence on the battery cell efficiency.

[0074] 2E, adopt cross-validation method to evaluate the stability of the model, adjust the model parameters according to the evaluation results, and recalculate the feature importance.

[0075] Among them, the feature importance formula:

[0076]

[0077] 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, the greater the influence of the feature on the battery cell efficiency.

[0078] 2F, screen out key features according to the feature importance value and normalize the calculation of their weights.

[0079] For example, suppose the battery cell data includes the following features: current, voltage, temperature, SOC (state of charge), and charge-discharge times. Calculate the Pearson correlation coefficient of current, voltage, temperature, SOC and battery cell efficiency. It is found that the correlation coefficient between temperature and battery cell efficiency is , indicating that temperature rise will significantly reduce the battery cell efficiency. Using the random forest model, the feature importance value of temperature is 0.6, SOC is 0.3, and current is 0.1. The feature importance value is normalized to get 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. Therefore, temperature is the most important feature affecting the efficiency of the battery cell.

[0080] S3, based on the key features, a correlation model between the operating state of the battery cell and the efficiency is constructed, and a prediction formula of the battery cell efficiency is obtained.

[0081] Specifically, the key features extracted in step S2 are used as input variables, and the battery cell efficiency is used as output variable to construct a prediction model. The data set is divided into training set and test set, and linear regression model, support vector regression or neural network model is selected according to the characteristics of the data. The key feature data of the training set is input into the model, and the model parameters are fitted. The key feature data of the test set is input into the trained model, and the predicted value of the battery cell efficiency is calculated. According to the verification result, the model parameters are adjusted, the model is retrained with the adjusted parameters, and the model performance is verified. The model with the best performance is selected as the final model, and the real-time collected key feature data is input into the prediction formula to calculate the predicted value of the battery cell efficiency.

[0082] For example, assuming that the key features are temperature (x1), SOC (x2), and current (x3), and 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 weight, x2 is the SOC weight, and x3 is the current weight.

[0083] S4, a mathematical model of the internal electrochemical reaction process of the battery cell is established to simulate the efficiency variation trend of the battery cell under different strategies.

[0084] Before performing step S4, the type of battery cell (such as lithium battery cell, lead-acid battery cell, etc.) and its electrochemical characteristics (electrode material, electrolyte composition and reaction mechanism) need to be determined to determine the model to simulate the efficiency variation trend of the battery cell under different charging and discharging strategies.

[0085] Specifically, after clarifying the type and basic electrochemical characteristics of the battery cells to be simulated, an equivalent circuit model is selected. Key parameters such as internal resistance, open-circuit voltage, and polarization voltage are defined in the model. Battery cell data under different charge and discharge strategies are input into the mathematical model, which is then used to simulate the performance (voltage, current, and temperature changes) and parameter changes (internal resistance and capacity decay) of the battery cells under different strategies. Based on the simulation results, the efficiency change trend of the battery cells under different strategies is calculated (e.g., using the equivalent circuit model to simulate the constant current charging process, it is found that the battery cell terminal voltage gradually increases with charging time, and the internal resistance increases with increasing temperature).

[0086] The different discharge strategies include constant current charging, constant voltage charging, constant current-constant voltage charging, pulse charging, trickle charging, segmented charging, and smart charging.

[0087] S5 establishes the mapping relationship between the internal electrochemical reactions of the battery cell and the working environment, and quantifies the degree of influence of the working environment on the performance of the battery cell.

[0088] Specifically, the efficiency variation trend data of the battery cells under different charge and discharge strategies obtained in step S4 are integrated with the mathematical model simulation results of the electrochemical reactions inside the battery cells. The variation trend of the internal reaction parameters (internal resistance, polarization voltage) of the battery cells with the working environment is analyzed. A mapping relationship is established using a neural network (e.g., for every 10°C increase in temperature, the internal resistance increases by 20%). The battery cell working environment data is used as the input variable, and the internal reaction parameters of the battery cells are used as the output variable. The influence of the working environment on the battery cell performance is quantified through the mapping relationship.

[0089] For example, establishing the internal resistance of a battery cell With the temperature in the working environment Based on the relationship between the changes, calculate the internal resistance of the battery cell at a certain operating temperature:

[0090]

[0091] This represents the internal resistance of the battery cell at temperature T. Indicates reference temperature The internal resistance of the battery cell below, The temperature coefficient represents the sensitivity of internal resistance to temperature changes, where T represents the current temperature. Reference temperature (usually room temperature, such as 25°C). Assuming a reference temperature. =Reference temperature 25°C, internal resistance at reference temperature Temperature coefficient The current temperature is T = 35°C. Calculate the internal resistance at the current temperature. (35°C): .

[0092] S6, optimize the battery cell management system control strategy based on all the models and mapping relationships, and determine the charge and discharge strategy combination under different working environmental conditions.

[0093] Specifically, the correlation 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. The influence of different working environments and charge and discharge strategies on the performance of the battery cell is analyzed. According to the application requirements, the optimization target (maximizing the charging efficiency, prolonging the battery cell life, and improving the safety) is determined, the optimization algorithm (genetic algorithm) is used to optimize the charge and discharge strategy, the optimization variables (such as the charging current, the charging voltage, and the discharge cutoff voltage) are defined, and the charge and discharge strategy combination under different working environmental conditions (for example, small current charging is adopted in high temperature environment to avoid overheating, preheating strategy is adopted in low temperature environment to improve the charging efficiency, and the charging voltage is adjusted in high humidity environment to reduce the polarization effect) is determined according to the optimization results.

[0094] S7, apply the optimized control strategy to the actual system to dynamically adjust the charge and discharge strategy.

[0095] Specifically, the optimized charge and discharge strategy is deployed to the battery cell management system, the internal electrochemical reaction process of the battery cell and the working environmental parameters are monitored in real time through the sensor, and the charge and discharge strategy is dynamically adjusted (for example, when the temperature of the battery cell exceeds the threshold, the charging current is automatically reduced; when the SOC approaches the upper limit, the constant voltage charging mode is switched) according to the real-time monitoring data, so as to ensure the efficient and safe operation of the battery cell.

[0096] The technical solutions in the embodiments of the application have at least the following technical effects or advantages:

[0097] By obtaining the historical operation data and working environmental data of the battery cell, analyzing the correlation between the key features, constructing the correlation model of the operation state and efficiency of the battery cell, and establishing the mapping relationship between the internal electrochemical reaction of the battery cell and the working environment, the battery cell management system control strategy is optimized. The performance of the battery cell can be accurately predicted, the influence of the working environment on the efficiency of the battery cell can be quantified, and the charge and discharge strategy can be dynamically adjusted, so as to improve the operation efficiency of the battery cell, prolong the life of the battery cell, enhance the safety, and provide scientific basis and technical support for the efficient management of the energy storage system.

[0098] Embodiment 2

[0099] In embodiment 1, by obtaining battery cell historical operation data and working environment data, analyzing the correlation between key features, constructing the correlation model of battery cell operation state and efficiency, and establishing the mapping relationship between the internal electrochemical reaction of 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 embodiment one 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 balancing control. In the face of state differences of different battery cells (such as SOC, temperature, health status), using a unified management strategy will inevitably have optimization errors and weak generalization ability. Since the electrochemical reaction parameters and performance degradation trends of different battery cells differ, the indicators required for energy distribution and balancing control must differ. In order to further refine the control strategy of the battery cell management system and obtain a more accurate energy distribution scheme, the state evaluation results, electrochemical reaction parameters and performance degradation trends of the battery cell need to be considered for further optimization and improvement. Therefore, embodiment two further refines the energy distribution and balancing control by dividing the battery cell management system into layers and establishing an information interaction mechanism between the layers.

[0100] In some embodiments, the step S6 of optimizing the control strategy of the battery cell management system further comprises:

[0101] S61, the battery cell management system is divided into layers, and an information interaction mechanism between the layers is established.

[0102] Among them, the battery cell management system is divided into three layers: the top layer is the system level management layer, responsible for overall energy scheduling and strategy formulation, receiving data from the middle layer and the bottom layer, and generating a global energy distribution scheme; the middle layer is the battery pack level management layer, responsible for energy distribution and balancing control of the battery pack, receiving data from the bottom layer, and generating an energy distribution scheme for the battery pack; the bottom layer is the battery cell level management layer, responsible for monitoring and controlling individual battery cells, and obtaining real-time state of charge (SOC), temperature, voltage and other data of the battery cell through sensors.

[0103] The information interaction mechanism between the layers is established, the real-time data of the battery cell is uploaded to the middle layer, the energy distribution scheme of the battery pack is uploaded to the top layer, and the global energy distribution scheme is issued to the middle layer and the bottom layer by the top layer. The middle layer adjusts the energy distribution of the battery pack according to the instructions of the top layer, and the bottom layer adjusts the charging and discharging strategy of individual battery cells according to the instructions of the middle layer.

[0104] S62, real-time battery cell data is obtained through sensors and state evaluation is performed.

[0105] Specifically, through the sensors installed on the battery cells, real-time data such as SOC, temperature, voltage, etc. of the battery cells are collected. The collected raw data is cleaned to remove outliers, noise and other interference, and the data of different dimensions is normalized. According to the characteristics of the battery cells and the evaluation requirements, a neural network algorithm model is selected for state evaluation. The historical data is used to train the model, and the preprocessed real-time data is input into the trained state evaluation model. The model calculates the current state indicators of the battery cells, such as state of health (SOH), remaining useful life (RUL), etc. based on the input data.

[0106] S63, based on the battery cell state evaluation results, the best working point is matched to generate a preliminary energy distribution scheme.

[0107] Among them, the best working point refers to the voltage and current at which the battery cell can work most efficiently under certain conditions. For each battery cell, there is a specific efficiency curve that represents the efficiency under different working 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 best working point, the constraints of the battery cell, such as the maximum charging / discharging current, the highest / lowest working temperature, etc. also need to be considered. Define the objective function to comprehensively measure the efficiency, life, safety and other performance of the battery cell under certain working conditions. Use optimization algorithms to find the working point that maximizes the objective function under the constraints. Optimization algorithms can traverse the solution space to find the working point closest to the optimal solution.

[0108] Experimental tests are conducted on actual battery cells to verify whether the working point found by the optimization algorithm is the best working point. Experimental tests include charge / discharge cycles, temperature cycles, etc. to simulate actual use scenarios. Based on the experimental test results, the optimization algorithm and the state evaluation model are adjusted and optimized to continuously improve the accuracy and reliability of finding the best working point.

[0109] S64, based on the electrochemical reaction of the battery cell and the state evaluation results, use a machine learning model to predict the performance degradation trend and the best working point of the battery cell.

[0110] Specifically, based on the electrochemical reaction of the battery cell and the state evaluation results, training data is prepared. A neural network machine learning model is used to model the performance degradation trend of the battery cell. The established performance degradation model is used to predict the future best working point of each battery cell.

[0111] S65, according to the prediction results, adjust the charge and discharge tasks, and determine the final energy distribution scheme.

[0112] Specifically, the charging and discharging tasks are allocated according to the predicted optimal working point and the current system demand. The battery cells are ensured to operate near the optimal working point to improve the energy utilization efficiency and prolong the battery cell life. The final energy allocation scheme is determined by comprehensively considering the prediction results, the system demand and the battery cell state.

[0113] The technical solutions in the embodiments of the application have at least the following technical effects or advantages:

[0114] By hierarchically managing the battery cell system and establishing the information interaction mechanism between the layers, real-time monitoring and evaluation of the battery cell state are realized. Meanwhile, by combining the electrochemical reaction of the battery cell and the state evaluation results, a machine learning model is used to predict the performance degradation trend and the optimal working point, and the charging and discharging tasks are allocated accordingly to determine the final energy allocation scheme. This scheme improves the energy utilization efficiency, prolongs the battery cell life, and can adapt to the changes in the battery cell state in real time, thus having significant technical effects and advantages.

[0115] Embodiment 3

[0116] In embodiment 2, the fine monitoring and control of the battery cell have been realized by the hierarchical management of the battery cell management system and the information interaction mechanism, and the energy allocation scheme is generated based on the state evaluation results and the matching optimal working point. 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. Moreover, the transition characteristics of different battery cells differ when the state is switched, 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 allocation scheme, embodiment three introduces optimal transition curve design while considering the current state of the battery cell, monitors the state of the battery cell in real time and dynamically adjusts the optimal working point. At the same time, the switching coefficient is calculated according to the smoothness of the transition curve, the energy loss, the battery cell life loss and the transient response characteristics, so as to more finely control the switching path of the working point.

[0117] In some embodiments, step S63 further includes:

[0118] S63a, the state of the battery cell is monitored in real time, and the optimal working point is dynamically adjusted in real time according to the current state of the battery cell.

[0119] S63b, an optimal transition curve of the optimal working point is designed, and the transient response characteristics of the battery cell in the switching process are predicted.

[0120] wherein the optimal transition curve is designed, the genetic algorithm is used to design the optimal transition curve, a population is initialized, a group of transition curves is randomly generated, the fitness (i.e. the objective function value) of each transition curve is calculated, a new generation of population is generated through selection, crossover and mutation operations, the above process is repeated until the optimal transition curve is found. The optimal transition curve can be expressed as:

[0121]

[0122] for the optimal transition curve, for all possible transition curves, T, E and L are the switching time, energy loss and battery cell life loss respectively, the switching time T is calculated as: , and are the start and end times 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 cell. For detailed methods of designing the optimal transition curve, please refer to the prior art, which will not be described herein.

[0123] The equivalent circuit model is used to predict the transient response characteristics of the battery cell during the switching process, according to the current change during the switching process, the battery cell terminal voltage is calculated as: , is the battery cell terminal voltage, is the internal resistance, is the polarization voltage, is the open-circuit voltage. The polarization voltage can be expressed as: , is the initial polarization voltage, is the time constant, is the steady-state polarization voltage, denotes the time from the time when the polarization condition is applied. According to the current and the internal resistance , the battery cell temperature change is calculated, C is the battery cell heat capacity, is the ambient temperature, is the thermal resistance. The battery cell terminal voltage , the current , and the temperature vary with time.

[0124] The transient response characteristics are quantified as a comprehensive index as follows:

[0125]

[0126] S63c, calculate the switching coefficient according to the optimal transition curve and the transient response characteristic.

[0127] wherein the switching coefficient calculation formula is:

[0128]

[0129] and is a weight coefficient, used to balance the importance of different factors.

[0130] S63d, when the battery unit state changes, trigger the switching of the optimal working point, calculate the switching path of the optimal working point according to the current state and the target state, and gradually adjust the actual running state of the battery unit.

[0131] wherein the trigger condition for triggering the switching of the optimal working point is:

[0132]

[0133] The above threshold is set according to the application scenario and the historical battery unit data.

[0134] The switching path calculation formula of the optimal working point is:

[0135]

[0136] is the new optimal working point, is the current optimal working point, is the state change amount (such as the SOC change amount, the temperature change amount), is the switching coefficient, and the dynamic correction term is used to compensate the influence of the transient response characteristic on the switching path.

[0137] The technical solutions in the embodiments of the present application have at least the following technical effects or advantages:

[0138] By monitoring the battery cell state in real time, the optimal operating point is dynamically adjusted. Genetic algorithm is used to design the optimal transition curve, considering 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 the changes of battery cell terminal voltage, current and temperature. According to the optimal transition curve and the transient response characteristics, the switching coefficient is calculated, and when the battery cell state changes, the switching of the optimal operating point is triggered, and the switching path is calculated according to the current state, target state and state change. This technical scheme improves the flexibility and efficiency of battery cell management, optimizes the battery cell performance, and prolongs the battery cell life.

[0139] Embodiment 4

[0140] In embodiment 3, fine monitoring and control of battery cells have been realized, and an energy distribution scheme 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, so a unified transition strategy cannot guarantee the optimality of the battery pack performance. In order to further optimize the switching process of the battery pack operating point and improve the efficiency and reliability of energy management, embodiment 4 introduces a calculation method for the battery pack optimal operating point while considering the optimal operating point of individual battery cells. By recording the optimal operating point of each battery cell and the corresponding environmental data, the optimal operating point of the battery pack is calculated according to the connection mode of the battery pack, and adjustments are made according to different working environment data. At the same time, the overall transition time is monitored when the state of the battery pack changes, and it is judged whether the switching path needs to be optimized, so as to more finely control the switching process of the operating point of the battery pack.

[0141] In some embodiments, step S63d further comprises:

[0142] d1, recording the optimal operating point of each battery cell and the corresponding working environment data.

[0143] d2, combining multiple battery cells into a battery pack, and calculating the optimal operating point of the battery pack according to the connection mode of the battery pack.

[0144] Wherein, assuming that the battery pack is composed of n battery cells, the optimal operating point of each battery cell is (where i=1, 2,..., n), and the optimal operating point of the battery pack is which can be expressed as: , wherein, represents the optimal operating point of the i-th battery cell, represents a function or calculation method for calculating the optimal operating point of each battery cell Comprehensively, the optimal operating point of the battery pack is calculated as n represents the number of battery cells in the battery pack. The specific formula is different according to the connection mode of the battery pack:

[0145] The formula for calculating the optimal working point of the battery pack connected in series is: , , is the optimal voltage of the i-th battery unit, is the optimal current of the i-th battery unit, is the optimal total voltage of the battery pack, is the optimal total current of the battery pack.

[0146] The formula for calculating the optimal working point of the battery pack connected in parallel is: , , is the optimal voltage of the i-th battery unit, is the optimal current of the i-th battery unit, is the optimal total voltage of the battery pack, is the optimal total current of the battery pack. For a battery pack connected in hybrid, assuming the battery pack is composed of m series modules, each module contains k parallel battery units, the formula for calculating the optimal working point of the battery pack is: , , is the optimal voltage of each module, is the optimal current of each module, is the optimal total voltage of the battery pack, is the optimal total current of the battery pack.

[0147] d3, simulate different working environment data to the battery pack, and adjust the optimal working point of the battery pack according to these data.

[0148] wherein the adjustment formula is:

[0149]

[0150] is the optimal working point of the battery pack, is the data of different working environments, is the final optimal working point.

[0151] d4, when the state of the battery pack changes and triggers the switching of the optimal working point, calculate and record the overall transition duration of the battery pack.

[0152] wherein the overall transition duration refers to the total time for the battery pack to switch from the current working point to the new working point.

[0153] d5, according to the overall transition duration of the battery pack and the preset standard, judge whether the switching path of the battery pack needs to be optimized.

[0154] The preset standard threshold of the overall transition duration of the battery pack is determined according to the type, scale and application scenario of the battery pack.

[0155] The technical solutions in the embodiments of the application have at least the following technical effects or advantages:

[0156] The scheme provides a basis for the optimized management of the battery pack by accurately recording the optimal working point of each battery unit and the corresponding working environment data. Secondly, according to the connection mode of the battery pack, the scheme can scientifically calculate the optimal working point of the battery pack, and accurate results can be obtained regardless of series connection, parallel connection or hybrid connection. In addition, the scheme can dynamically adjust the optimal working point of the battery pack according to different simulated working environment data, thereby improving the adaptability and stability of the battery pack. Finally, by calculating and recording the overall transition duration of the battery pack, the scheme provides strong support for the performance evaluation and optimization of the battery pack.

[0157] Further, the embodiment of the application also provides a digital-twin energy storage management system.

[0158] Figure 2 is a structural schematic diagram of the digital-twin energy storage management system of the embodiment of the application.

[0159] As shown in Figure 2 , a digital-twin energy storage management system comprises 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.

[0160] The data acquisition module is configured to acquire historical operation data of the battery unit and working environment data of the battery unit.

[0161] The data analysis module is configured to analyze the correlation between key features of the data and determine the influence weight of the key features on the efficiency of the battery unit.

[0162] The association model construction module is configured to construct an association model of the operation state and the efficiency of the battery unit based on the key features, to obtain a prediction formula of the efficiency of the battery unit.

[0163] The model establishment module is configured to establish a mathematical model of the internal electrochemical reaction process of the battery unit, to simulate the efficiency variation trend of the battery unit under different strategies.

[0164] The mapping relationship establishment module is configured to establish a mapping relationship between the internal electrochemical reaction of the battery unit and the working environment, to quantify the influence degree of the working environment on the performance of the battery unit.

[0165] A control strategy optimization module is configured to optimize the battery cell management system control strategy based on all the models and mapping relationships, and determine the charge-discharge strategy combination under different working environmental conditions.

[0166] A strategy application module is configured to apply the optimized control strategy to the actual system, and dynamically adjust the charge-discharge strategy.

[0167] It should be noted that other specific implementation contents of the digital twin energy storage management system in the embodiments of the present application can refer to the above-mentioned digital twin energy storage management method.

[0168] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0169] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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.

[0170] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams 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 devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 An apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams. Figure 1 An apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams.

[0171] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatuses that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 An apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams. Figure 1 An apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams.

[0172] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0173] Although preferred embodiments of the application have been described herein, it will be apparent to those skilled in the art that various modifications can be made within the scope of the application and it is intended that the application should cover any and all modifications and variations of the preferred embodiments.

[0174] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A digital twin-based energy storage management method, characterized in that, The method includes: S1, acquire historical operating data of the battery cell and operating environment data of the battery cell; S2, Analyze the correlation between key features of the data and determine the weight of the key features on the efficiency of the battery cell. S3. Based on key features, construct a correlation model between the operating state and efficiency of the battery cell to obtain 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, establish the mapping relationship between the internal electrochemical reaction of the battery cell and the working environment, and quantify the degree of influence of the working environment on the performance of the battery cell; S6 optimizes the control strategy of the battery cell management system based on all models and mapping relationships, and determines the combination of charging and discharging strategies under different working environment conditions; S61, The battery cell management system is layered and an information interaction mechanism between layers is established; S62, Battery cell data is acquired in real time through sensors and its status is evaluated; S63, Based on the battery cell status evaluation results, the optimal operating point is matched to generate a preliminary energy allocation scheme. S63a: Monitor the battery cell status in real time and dynamically adjust the optimal operating point based on the current status of the battery cell; S63b: Design the optimal transition curve for the optimal operating point and predict the transient response characteristics of the battery cell during the switching process; S63c: Calculate the switching coefficient based on the optimal transition curve and transient response characteristics; S63d: When the battery cell status changes, trigger the switching of the optimal operating point, calculate the switching path of the optimal operating point based on the current state and the target state, and gradually adjust the actual operating state of the battery cell. S64, Based on the electrochemical reaction and state assessment results of the battery cells, use a machine learning model to predict the performance degradation trend and optimal operating point of the battery cells; S65, Based on the prediction results, allocate charging and discharging tasks to determine the final energy allocation scheme. S7 applies the optimized control strategy to the actual system and dynamically adjusts the charging and discharging strategy.

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

3. The energy storage management method based on digital twins according to claim 1, characterized in that, S2, determining the influence weights of key features on battery cell efficiency, includes: 2C: Use features that are strongly correlated with battery cell efficiency to train a random forest model to predict battery cell efficiency. In 2D, the importance value of each feature is calculated using a random forest model to evaluate its impact on battery cell efficiency. 2E, cross-validation is used to evaluate model stability, the model parameters are adjusted based on the evaluation results, and the feature importance is recalculated; 2F: Select key features based on feature importance values ​​and normalize their weights.

4. The energy storage management method of digital twin according to claim 1, characterized in that, S63, the 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.

5. The energy storage management method of digital twin according to claim 1, characterized in that, include: The optimal transition curve can be expressed as: This is the optimal transition curve. For all possible transition curves, T, E, and L represent switching time, energy loss, and battery cell life loss, respectively; the transient response characteristics are quantified into a comprehensive index as follows: Where 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 is calculated using the following formula: , and These are weighting coefficients; Formula for calculating the switching path to the optimal operating point: , For the new best working location, The current best working point For state changes, The switching coefficient is used, and the dynamic correction term compensates for the impact of transient response characteristics on the switching path.

6. The energy storage management method of digital twin according to claim 1, characterized in that, The S63d includes: d1 records the optimal operating point and corresponding operating environment data for each battery cell; d2 combines multiple battery cells into a battery pack and calculates the optimal operating point of the battery pack based on the connection method of the battery pack. d3 simulates inputting data from different working environments into the battery pack and adjusts the optimal operating point of the battery pack based on this data; d4, When the battery pack state changes and triggers the switching of the optimal operating point, calculate and record the overall transition time of the battery pack; d5 determines whether the battery pack switching path and switching coefficient need to be optimized based on the overall transition time of the battery pack and the preset standard.

7. The energy storage management method of digital twin according to claim 6, characterized in that, include: Assuming 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 represented as: , The optimal operating point of the i-th battery cell, f represents a function or calculation method to calculate the optimal operating point of each battery cell. In summary, the optimal operating point of the battery pack is calculated. , where n represents the number of battery cells in the battery pack; the adjustment formula is: , Data from different work environments It is the ultimate optimal working point.

8. A digital twin energy storage management system, applied to a digital twin energy storage management method as described in any one of claims 1 to 7, characterized in that, The system includes: The data acquisition module is used to acquire historical operating data of the battery cell and operating environment data of the battery cell; The data analysis module is used to analyze the correlation between key features of the data and determine the weight of the impact of key features on battery cell efficiency. The correlation model building module is used to build a correlation model between the operating state and efficiency of battery cells based on key features, and obtain a prediction formula for battery cell efficiency. The model building module is 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. The mapping relationship establishment module is used to establish the mapping relationship between the internal electrochemical reactions of the battery cell and the working environment, and to quantify the degree of 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 cell management system based on all models and mapping relationships, and to 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