Situation awareness method, device and equipment of electrochemical energy storage system and medium

Abstract

The invention discloses a situation awareness method, device and equipment for an electrochemical energy storage system and a medium, and relates to the field of power grid management, and the method comprises the steps: collecting the operation data of a battery in the electrochemical energy storage system in a charging and discharging period, and constructing a battery operation database in combination with the measured aging data of a local laboratory battery; the battery operation database comprises a state evolution data set; extracting first aging feature information of the battery and inconsistency feature information of the battery module based on a battery operation database to determine a feature mapping model from a monomer level to a module level; based on a preset hybrid neural network model, the second aging feature information of the battery module and the equivalent circuit model, determining a battery pack power state estimation model under multiple constraint conditions; and determining a situation awareness result based on the feature mapping model and the battery pack power state estimation model. According to the invention, for a scene that the energy storage system frequently participates in power grid regulation and control, accurate state sensing of the whole life cycle of the energy storage system is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power grid management, and in particular to a situation awareness method, device, equipment and medium of an electrochemical energy storage system. BACKGROUND

[0002] With the deep application of the electrochemical energy storage system in the power grid regulation and control task scenarios such as frequency regulation, peak regulation and black start, the energy storage system faces more complex and severe dynamic operation conditions. Under this background, the battery in the system is long-term in high-frequency and high-rate charging and discharging cycle, which is easy to cause rapid performance degradation and potential safety hazards, resulting in system efficiency decline and even safety accidents.

[0003] However, the traditional solutions rely on historical data modeling, although they can collect basic battery parameters such as voltage, current and temperature in real time, but the generalization ability is limited, and it is difficult to adapt to the dynamic stress environment brought by the frequently changing working conditions (such as power grid frequency regulation and high-speed charging and discharging), resulting in low accuracy and precision, especially in the case of multi-level coupling, inconsistency enhancement and battery aging path diversification of the system. These solutions cannot meet the needs of accurate monitoring and real-time safety management of the whole life cycle of the energy storage system.

[0004] Therefore, how to realize accurate state perception of the whole life cycle of the energy storage system in the scene of frequent participation of the energy storage system in the power grid regulation and control is a problem to be solved at present. SUMMARY

[0005] Therefore, the purpose of the present application is to provide a situation awareness method, device, equipment and medium of an electrochemical energy storage system, which can realize accurate state perception of the whole life cycle of the energy storage system in the scene of frequent participation of the energy storage system in the power grid regulation and control, solve the problem of perception deviation and distortion caused by the cross-level transmission characteristics of the state of the energy storage system, improve the accuracy, precision and reliability of state perception, and thus improve the safety and intelligent management level of the energy storage system in complex regulation scenarios. The specific scheme is as follows:

[0006] In the first aspect, the present application provides a situation awareness method of an electrochemical energy storage system, comprising:

[0007] Collecting the operation data of the battery in the electrochemical energy storage system in the charging and discharging cycle, and combining the local laboratory battery aging measured data to construct a battery operation database; the battery operation database includes an initial state recognition data set and a state evolution data set;

[0008] Based on the battery operation database, feature extraction is performed, and the corresponding first aging feature information of the battery and the inconsistency feature information of the battery module are used to determine the feature mapping model from the single cell level to the module level;

[0009] determine a battery pack power state estimation model under multiple constraint conditions based on the preset hybrid neural network model, the second aging feature information corresponding to the battery module, the inconsistent feature information, and the equivalent circuit model;

[0010] perform multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model, and the topological structure information corresponding to the electrochemical energy storage system to determine a situational awareness result.

[0011] Optionally, the running data of the battery in the electrochemical energy storage system in the charge and discharge cycle is collected, and the local laboratory battery aging measured data is combined to construct a battery running database, including:

[0012] determine the running data of the battery in the electrochemical energy storage system in the charge and discharge cycle based on the sensor;

[0013] obtain the local laboratory battery aging measured data corresponding to the running data;

[0014] perform evolution analysis of battery performance and battery parameters based on the laboratory battery aging measured data and the battery aging data to determine the battery running database; the battery parameters include voltage, current, and capacity.

[0015] Optionally, the feature extraction is performed based on the battery running database, and the feature mapping model from the single cell level to the module level is determined by using the first aging feature information corresponding to the battery and the inconsistent feature information corresponding to the battery module, including:

[0016] determine the single cell charge and discharge curve of the battery based on the battery running database;

[0017] perform feature extraction based on the single cell charge and discharge curve to determine the first aging feature information corresponding to the battery;

[0018] perform feature extraction based on the battery running database to determine the inconsistent feature information corresponding to the battery module; the battery module includes a plurality of batteries, and the inconsistent feature information includes the range of voltage curves of each battery in the module and the distance between the voltage curve and the average voltage curve of all batteries in the module;

[0019] determine the feature mapping model from the single cell level to the module level based on the first aging feature information and the inconsistent feature information.

[0020] Optionally, the battery module corresponding second aging feature information, the inconsistency feature information and the equivalent circuit model based on the preset hybrid neural network model are used to determine a battery pack power state estimation model under multiple constraint conditions, including:

[0021] The second aging feature information corresponding to the battery module is determined based on the battery operation database;

[0022] The preset hybrid neural network model is trained based on the health features in the second aging feature information and the inconsistency feature information, so as to determine a module-level battery data-driven model when the training is completed; the preset hybrid neural network model is a neural network model determined based on a bidirectional long short-term memory network and an attention mechanism;

[0023] The equivalent circuit model corresponding to the battery module is determined based on the average model and the difference model corresponding to the battery module;

[0024] The battery pack power state estimation model under multiple constraint conditions is determined based on the battery data-driven model and the equivalent circuit model.

[0025] Optionally, the equivalent circuit model corresponding to the battery module is determined based on the average model and the difference model corresponding to the battery module, including:

[0026] The average model and the difference model corresponding to the battery module are determined based on the battery parameters corresponding to each battery in the battery module; the average model is used to represent the average state of the battery module, and the difference model is used to represent the deviation between the state of each battery in the battery module and the average state;

[0027] The equivalent circuit model corresponding to the battery module is determined based on the average model, the difference model and an extended Kalman filtering algorithm.

[0028] Optionally, the battery pack power state estimation model under multiple constraint conditions is determined based on the battery data-driven model and the equivalent circuit model, including:

[0029] A preset multiple constraint condition is obtained; the preset multiple constraint condition includes a charge-discharge current constraint condition, a state of charge constraint condition and a state of health constraint condition of the battery module;

[0030] The battery pack power state estimation model is determined by calculation and deduction based on the preset multiple constraint condition, the battery data-driven model and the equivalent circuit model.

[0031] Optionally, the multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model and the corresponding topology structure information of the electrochemical energy storage system comprises:

[0032] The series-parallel topology structure of the battery module and the battery in the electrochemical energy storage system is analyzed through the topology structure information to determine an analysis result;

[0033] A multi-level state perception model is determined based on the feature mapping model and the battery pack power state estimation model;

[0034] A multi-state parameter joint perception of the electrochemical energy storage system is performed based on the analysis result and the multi-level state perception model to determine a situation awareness result; the multi-state parameter comprises a state of charge parameter, a state of health parameter and a state of power parameter.

[0035] In a second aspect, the present application provides a situation awareness device of an electrochemical energy storage system, comprising:

[0036] A database construction module is configured to collect operation data of a battery in a charging and discharging cycle of an electrochemical energy storage system, and combine local laboratory battery aging measured data to construct a battery operation database; the battery operation database comprises an initial state identification data set and a state evolution data set;

[0037] A mapping model construction module is configured to perform feature extraction based on the battery operation database, and determine a feature mapping model from a single battery level to a module level by using corresponding first aging feature information of the battery and inconsistent feature information of the battery module;

[0038] A model determination module is configured to determine a battery pack power state estimation model under multiple constraint conditions based on a preset hybrid neural network model, second aging feature information of the battery module, the inconsistent feature information and an equivalent circuit model;

[0039] A situation awareness module is configured to perform multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model and the corresponding topology structure information of the electrochemical energy storage system to determine a situation awareness result.

[0040] In a third aspect, the present application provides an electronic device, comprising:

[0041] A memory is configured to save a computer program;

[0042] A processor is configured to execute the computer program to implement the steps of the situation awareness method of the electrochemical energy storage system.

[0043] In a fourth aspect, the present application provides a computer readable storage medium for storing a computer program, which, when executed by a processor, implements the steps of the situational awareness method of the electrochemical energy storage system as described above.

[0044] It can be seen that, in the present application, the operation data of the battery in the electrochemical energy storage system in the charge and discharge cycle is collected, and the local laboratory battery aging measured data is combined to construct a battery operation database; the battery operation database includes an initial state identification data set and a state evolution data set; feature extraction is performed based on the battery operation database, and the corresponding first aging feature information of the battery and the inconsistency feature information of the battery module are used to determine the feature mapping model from the single cell level to the module level; based on the preset hybrid neural network model, the second aging feature information of the battery module, the inconsistency feature information and the equivalent circuit model, the battery pack power state estimation model under multiple constraint conditions is determined; based on the feature mapping model, the battery pack power state estimation model and the topological structure information corresponding to the electrochemical energy storage system, multi-state joint estimation is performed to determine the situational awareness result. That is, in the present application, first, based on the local laboratory battery aging measured data and the operation data of the battery in the electrochemical energy storage system in the charge and discharge cycle, a battery operation database is constructed, then feature extraction is performed based on the battery operation database, and the corresponding first aging feature information of the battery and the inconsistency feature information of the battery module are used to determine the feature mapping model from the single cell level to the module level, then based on the preset hybrid neural network model, the second aging feature information of the battery module, the inconsistency feature information and the equivalent circuit model, the battery pack power state estimation model under multiple constraint conditions is determined, then based on the feature mapping model, the battery pack power state estimation model and the topological structure information of the system, the situational awareness result is determined. In this way, for the scenario that the energy storage system frequently participates in grid regulation, the precise state perception of the whole life cycle of the energy storage system can be realized, the problems of perception deviation and distortion caused by the cross-level transmission characteristics of the state of the energy storage system are solved, the accuracy, precision and reliability of the state perception are improved, and the safety and intelligent management level of the energy storage system in the complex regulation scenario are improved. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on the provided drawings.

[0046] Figure 1A situational awareness method flowchart of an electrochemical energy storage system provided for the present application;

[0047] Figure 2 A battery charging and discharging voltage and current change curve schematic diagram provided for the present application;

[0048] Figure 3 A hybrid neural network structure schematic diagram provided for the present application;

[0049] Figure 4 An equivalent circuit topology schematic diagram of a series-parallel battery module provided for the present application;

[0050] Figure 5 A SOH estimation curve schematic diagram of a battery pack constructed by B1 batteries provided for the present application;

[0051] Figure 6 A SOH estimation value and true value comparison curve schematic diagram of an electrochemical energy storage system provided for the present application;

[0052] Figure 7 A SOC estimation curve diagram schematic diagram of a battery pack constructed by B1 batteries provided for the present application;

[0053] Figure 8 A SOC estimation value and true value comparison curve schematic diagram of an electrochemical energy storage system provided for the present application;

[0054] Figure 9 A charging and discharging peak power curve schematic diagram of B3 batteries under different aging degrees provided for the present application;

[0055] Figure 10 A situational awareness device structure schematic diagram of an electrochemical energy storage system provided for the present application;

[0056] Figure 11 An electronic device structure diagram provided for 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, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0058] Traditional solutions rely on historical data modeling, although they can collect basic battery parameters such as voltage, current, and temperature in real time, they have limited generalization ability and are difficult to adapt to dynamic stress environments caused by frequent changes in working conditions (such as power grid frequency modulation and high-speed charging and discharging), resulting in low accuracy and precision, especially in the case of multi-level coupling, inconsistency enhancement, and battery aging path diversification of the system. These solutions cannot meet the demand for precise monitoring and real-time safety management of the entire life cycle of the energy storage system.

[0059] To this end, the present application provides a situational awareness solution for an electrochemical energy storage system, which can realize accurate state perception of the entire life cycle of the energy storage system in the scenario of frequent participation of the energy storage system in power grid regulation, solve the problem of perception deviation and distortion caused by cross-level transmission characteristics of the state of the energy storage system, and improve the accuracy, precision and reliability of state perception.

[0060] Referring to Figure 1 The embodiment of the present application discloses a situational awareness method for an electrochemical energy storage system, comprising:

[0061] Step S11, collect the running data of the battery in the electrochemical energy storage system in the charging and discharging cycle, and combine the local laboratory battery aging measured data to construct a battery running database; the battery running database includes an initial state identification data set and a state evolution data set.

[0062] In this embodiment, first, the local laboratory battery aging measured data is used to construct a battery running database, that is, the running data of the battery in the electrochemical energy storage system in the charging and discharging cycle is determined based on the sensor; the local laboratory battery aging measured data corresponding to the running data is obtained; based on the laboratory battery aging measured data and the battery aging data, the evolution analysis of the battery performance and the battery parameters is performed to determine the battery running database; the battery parameters include voltage, current and capacity.

[0063] Taking a lithium ion battery as an example, the lithium ion battery is a general term for batteries using various lithium ion intercalation compounds as positive electrode materials. It can be understood that in this embodiment, the running data of the lithium ion battery in the charging and discharging cycle is collected, the locally stored battery measured data accumulated by the local laboratory is obtained, and the battery running database is constructed by combining the two kinds of data, which covers the key running information of the battery in the constant current constant voltage charging and constant current discharging process, for example, Figure 2 The lithium ion battery charging and discharging voltage and current change curve shown in FIG. 1. Then, the constructed database is used to analyze the evolution law of the voltage, current, capacity and other battery parameters in the aging cycle, analyze the performance degradation law of the lithium ion battery in the cyclic charging and discharging process, the main aging factors and the cause of the inconsistency of the single cells in the battery pack.

[0064] Specifically, for the process of analyzing the evolution of battery parameters such as voltage, current, capacity, etc. in the aging cycle, the charging stage first uses a 1.5A current for constant current charging until the voltage reaches the cutoff value of 4.2V, and then enters the constant voltage charging stage until the current drops below 20mA. During the constant current charging process, the battery temperature gradually rises and reaches a peak, while in the constant voltage stage it begins to decline. In a specific embodiment, the battery model to be used is set to B1, B2, B3, and local experimental data shows that as the number of charge and discharge cycles increases, the battery capacity as a whole shows a downward trend. It is worth noting that during the standing period after each charge and discharge, the battery may undergo a capacity regeneration phenomenon, i.e. due to the decomposition of accumulated reactants on the electrode surface that slow down the chemical reaction, there is a short-term increase in capacity in the next cycle.

[0065] Regarding the process of analyzing the performance degradation law of lithium-ion batteries in the charging and discharging process of the cycle, the main aging factors, and the causes of inconsistency within the battery pack (i.e. battery module), during the charging process, lithium ions will be deintercalated from the surface of the positive electrode material, enter the electrolyte, and be intercalated into the negative electrode through the separator; during the discharging process, lithium ions will be deintercalated from the negative electrode and return to the positive electrode. The charging and discharging process of lithium batteries is reversible. After experiencing multiple charge and discharge cycles, the battery monomer will undergo a series of irreversible physical and chemical changes, including the formation of solid electrolyte interface film, the loss of lithium ions and active materials, and complex electrochemical reactions caused by operating mode and external working conditions. Specifically, factors such as high temperature, deep charge and discharge, high rate current, and external force impact can all accelerate the performance degradation process of lithium-ion batteries. In addition, in a battery pack, single batteries are combined in series and parallel to achieve higher system voltage and current. From the manufacturing process, assembly and use of the battery to the performance degradation and eventual end of life of the battery, consistency issues run throughout. Specifically, the inconsistency of single batteries within the battery pack is mainly derived from two stages: one is the difference in single batteries during production and storage; the other is the exacerbation of the performance difference of single batteries during the use of the battery pack. These two factors interact with each other and jointly affect the consistency and overall performance of the battery pack.

[0066] After completing the above analysis, the initial state recognition data set and the state evolution data set can be obtained.

[0067] Step S12, based on the battery operation database, feature extraction is performed, and the first aging feature information corresponding to the battery and the inconsistency feature information corresponding to the battery module are used to determine the feature mapping model from the single level to the module level.

[0068] In this embodiment, after obtaining the battery operation database for feature extraction, the database is used to determine the feature mapping model from the single level to the module level, that is, the single charge-discharge curve of the battery is determined based on the battery operation database; feature extraction is performed based on the single charge-discharge curve to determine the first aging feature information corresponding to the battery; feature extraction is performed based on the battery operation database to determine the inconsistency feature information corresponding to the battery module; the battery module includes a plurality of batteries, and the inconsistency feature information includes the range of the voltage curve of each battery in the module, and the distance between the voltage curve and the average voltage curve of all batteries in the module; based on the first aging feature information and the inconsistency feature information, the feature mapping model from the single level to the module level is determined.

[0069] Specifically, the determination process of the cross-level feature mapping model is as follows:

[0070] Because in the operation of frequent participation in grid regulation, the discharge process of the battery shows extremely dynamic characteristics, and presents a piecewise charge-discharge condition, and relatively speaking, the charging process is more stable. Therefore, the first aging feature information is extracted from the charging process in this embodiment. In the constant current charging process, the charging capacity Q of the battery can be calculated by the following formula:

[0071] ;

[0072] In the formula, I represents the size of the charging current, and the unit is A (ampere); t represents time, and the unit is s (second).

[0073] The incremental capacity (IC) curve of the battery is represented by IC:

[0074] ;

[0075] In the formula, is the charging capacity in the corresponding voltage interval, and the unit is Ah (ampere-hour); is the size of the voltage interval, and the unit is V (volt). It is set that = 0.05V, the charging capacity of each interval in each cycle is calculated. As the number of battery cycles increases, the charging capacity of each interval gradually decreases. Therefore, only a few continuous and fixed voltage intervals are selected, and the sum of the charging capacities of these intervals gradually decreases as the number of cycles increases. From the statistical point of view, according to the standard deviation formula, the standard deviation of them also gradually decreases as the number of cycles increases.

[0076] To estimate the health status of any charging segment, it is necessary to extract the health indicators (HI) of all charging segments to train the model. Taking the i-th cycle as an example, given the initial voltage... and cutoff voltage ,according to The constant voltage charging stage is divided into intervals of 0.05V. According to the following formula, the i-th cycle can be divided into n intervals, resulting in a voltage interval sequence. ;

[0077] ;

[0078] During battery charging, the capacity sequence corresponding to the voltage range sequence. If the charging segment length is set to... indivual Then we can obtain the number of charging segments m in the i-th cycle:

[0079] ;

[0080] Based on the above settings, the charging segment sequence is obtained in the i-th iteration: For charging segments Contains capacity sequence: , Contains capacity sequence: And so on. Contains capacity sequence Ultimately, this covers the entire constant current charging stage, with spacing... The charging segment sequence P is 0.05V.

[0081] With charging segments For example, HI1 can be extracted as the sum of the charging capacity within the segment. The formula is as follows:

[0082] ;

[0083] In the formula, Let q be the q-th capacity segment.

[0084] HI2 is the standard deviation of the charging capacity within a segment. The formula is as follows:

[0085] ;

[0086] In the formula, It is the average of all charging capacities in the corresponding segment, in Ah.

[0087] At the same time, in order to distinguish the voltage segment in which the feature is located, the initial voltage corresponding to the voltage segment is... Size is also considered as one of the features, namely feature HI3.

[0088] Before studying the correlation between fragment length and HIs (Health Status) and SOH (State of Health), it is necessary to determine... and For the battery studied in this embodiment, the voltage range for feature extraction is [3.5V, 4.2V]. Generally, the higher the correlation between the input features and output of a data-driven model, the more accurate the model. The Pearson correlation coefficient... It is widely used to quantify the degree of linear correlation between two variables, and its formula is:

[0089] ;

[0090] In the formula, For characteristic sequences, It is its average value; y is the battery capacity. It is its average value.

[0091] Furthermore, to achieve a deep integration of the data-driven model and the equivalent circuit model, the ohmic resistance identified in the equivalent circuit model of a single battery cell is further selected. As one of the health characteristics, it is defined as the health indicator HI4, which is used to reflect the evolution trend of battery internal resistance as it ages.

[0092] Based on the above formula, the correlation between HIs and SOH extracted for different segment lengths is calculated, thereby selecting the appropriate segment length and the optimal voltage sampling interval.

[0093] Based on the extraction of the first aging characteristic information of individual battery cells, the inconsistencies between modules are considered to achieve cross-level migration modeling of features from individual cells to modules. Since inconsistencies within the battery pack not only reduce the overall performance of the battery pack but also affect the accuracy of state perception, this embodiment needs to analyze the differences between individual cells within the battery module and extract the inconsistencies within the group to improve the state perception capability at the module level.

[0094] The inconsistency features extracted in this embodiment include the range of the individual cell voltage curves within the battery pack. Euclidean distance between the voltage curve of a single cell within the group and the average voltage curve of all cells Assume the voltage curves of the battery cells within the battery pack are determined by vector... This is represented by [the vector]. Furthermore, the average voltage curve of all battery cells is represented by [the vector]. The inconsistency characteristic is represented by the following formula.

[0095] ;

[0096] wherein N is the length of the battery voltage sequence, represents the voltage value of the i-th battery at the j-th time point, in units of V; represents the average voltage value of all batteries at the j-th time point, in units of V.

[0097] In step S13, a battery pack power state estimation model under multiple constraint conditions is determined based on the preset hybrid neural network model, the second aging characteristic information corresponding to the battery module, the inconsistency characteristic information, and the equivalent circuit model.

[0098] In this embodiment, the battery pack power state estimation model under multiple constraint conditions is determined using the preset hybrid neural network model, the second aging characteristic information corresponding to the battery module, and the inconsistency characteristic information. That is, the second aging characteristic information corresponding to the battery module is determined based on the battery operation database; the preset hybrid neural network model is trained based on the health characteristics in the second aging characteristic information and the inconsistency characteristic information, so as to determine a battery data-driven model at the module level when the training is completed; the preset hybrid neural network model is a neural network model determined based on a bidirectional long short-term memory network and an attention mechanism; the equivalent circuit model corresponding to the battery module is determined based on the average model and the difference model corresponding to the battery module; and the battery pack power state estimation model under multiple constraint conditions is determined based on the battery data-driven model and the equivalent circuit model.

[0099] Further, regarding the determination of the equivalent circuit model, in this embodiment, the average model and the difference model corresponding to the battery module are first determined based on the battery parameters corresponding to each battery in the battery module; the average model is used to represent the average state of the battery module, and the difference model is used to represent the deviation between the state of each battery in the battery module and the average state; and then the equivalent circuit model corresponding to the battery module is determined based on the average model, the difference model, and an extended Kalman filter algorithm. Regarding the determination of the battery pack power state estimation model, the preset multiple constraint conditions are first obtained; the preset multiple constraint conditions include the charge and discharge current constraint condition, the state of charge constraint condition, and the state of health constraint condition of the battery module; and then the battery pack power state estimation model is determined by calculation and deduction based on the preset multiple constraint conditions, the battery data-driven model, and the equivalent circuit model.

[0100] It should be understood that the specific process of determining the battery pack power state estimation model under multiple constraint conditions is as follows:

[0101] In combination with Figure 3As shown, the embodiment adopts a hybrid neural network model obtained by combining BiLSTM network (Bidirectional Long Short-Term Memory) and attention mechanism, which has the advantages of processing long-term dependencies in time series data in combination with BiLSTM model, and adding attention mechanism to enhance the role of important time steps in the network, solving the problem of ignoring important information of some moments when the input is large data, improving the accuracy and computational efficiency of the network. The model takes the aging and inconsistency features extracted from the voltage and current curves as input, and takes the battery pack capacity as output, divides the training set and test set according to the 7:3 ratio, realizes the high-precision estimation of the battery module SOH. In the embodiment, the health factors in the battery charging voltage curve, charging current curve and charging temperature change curve that can describe the battery degradation trend are selected as the BiLSTM input to construct the time series matrix , which is expressed as follows:

[0102] ;

[0103] In the above formula, is the parameter set of all battery health characteristics at time t, is the data set of T historical time of the characteristic M, and M is the number of parameters in the set. The battery health characteristics at time t are input, and the hidden states are defined as and respectively, and the hidden state at time t output by the BiLSTM layer is calculated as follows:

[0104] ;

[0105] Among them, represents the LSTM network function; represents the hidden state at time t-1; U is the weight matrix of the hidden state; W is the weight matrix of the input; b represents the bias term; and the arrow represents the direction of LSTM transition.

[0106] The attention mechanism can give different weights to different input features to enhance important features and avoid irrelevant information affecting the final result. Specifically, a scoring function is first used, and its expression is:

[0107] ;

[0108] In the formula, is the bias term of the hidden layer; is the weight matrix from the hidden layer to the hidden layer; The weighted information of the sequence; The hidden state fused by the bidirectional LSTM; The sequence weight; The activation function; The weight of Attention; The bias of Attention; v is the attention value; The output of the Attention layer at time t; The weight coefficient.

[0109] Then, an average model based on the average voltage and current of the module is constructed, a difference model is introduced to correct the inconsistency of the single body, compensate for the loss of model accuracy, and further establish an equivalent circuit model at the module level.

[0110] (1) Construction of battery pack average model: the average model represents the average state of the battery pack, and the parameters are the average values of the parameters of each single body, which has uniqueness, so the calculation amount is only equivalent to that of the single body model. In addition, since it is the basis for the calculation of each single body difference model, the model accuracy is particularly important. First, an ohmic resistance and an RC circuit (Resistor-Capacitor Network, a circuit composed of resistance and capacitance) are used to construct the Thevenin equivalent circuit model of the power battery, and its mathematical expression is:

[0111]

[0112] wherein, represents the polarization resistance of the lithium ion battery, with the unit of Ω (Ohm); represents the polarization capacitance, with the unit of pF (picoFarad); the RC network represents the polarization phenomenon of the lithium ion battery, represents the load current, with the unit of A; represents the terminal voltage when the battery is externally connected, with the unit of V; is the state of charge at time t; is the maximum available capacity of the battery pack, with the unit of Ah; represents the start time of current integration, with the unit of s; represents the coulomb efficiency; is the state of charge at time t; is the polarization voltage; is the current flowing through the polarization capacitor; is the current flowing through the polarization resistance; OCV() is the open circuit voltage-state of charge function; is the ohmic resistance. By using Laplace transform and discretization on the equation emphasized above, the following expression can be obtained:

[0113] ;​​

[0114] wherein, is the sampling period, unit s; is the cell polarization time constant; is the state of charge at the kth sampling moment; is the state of charge at the (k-1)th sampling moment; k represents the sampling moment; is the polarization voltage at the kth sampling moment; is the polarization voltage at the (k-1)th sampling moment; is the load current at the kth sampling moment; is the load current at the (k-1)th sampling moment; represents the open-circuit voltage at the kth sampling moment.

[0115] (2) Construction of battery pack difference model: the difference model is used to represent the deviation of the state of each single cell in the battery pack from the average state, so the number of difference models is the same as the number of single cells in series. And this deviation is mainly the ohmic resistance difference caused by the deterioration of the consistency of the battery pack. In order to consider the calculation complexity, Rint model is selected.

[0116] ;

[0117] ;

[0118] wherein, is the port voltage of the reference battery, unit V; represents the port voltage of the non-reference battery i, unit V; is the current SOC state of the reference battery; is the current SOC state of the non-reference battery i; represents the polarization voltage of the reference battery; represents the polarization voltage of the non-reference battery i, unit V; is the ohmic resistance of the reference cell, unit Ω; represents the ohmic resistance of the non-reference battery i, unit Ω; is the SOC difference between the differential battery cell i and the reference battery; represents the voltage difference when the SOC difference of the two batteries is , unit V; represents the load current, unit A. Combining the above equations, the equation is obtained:

[0119] ;

[0120] wherein, is the terminal voltage difference between the differential battery cell i and the reference battery cell, unit V; represents the difference in internal resistance between the reference battery cell and the differential battery cell i, in V. Rintmodel contains an internal open-circuit voltage source that varies with the discharge current of the battery in the positive direction. Solving the above for is:

[0121] ;

[0122] where, represents the current remaining available capacity of the differential battery cell i, in Ah; represents the current remaining available capacity of the reference battery, in Ah; represents the maximum available capacity of the differential battery cell i in its current SOH; represents the maximum available capacity of the reference battery in its current SOH; represents the coulombic efficiency. Thus, the discrete-time approximate recursion can be obtained as follows:

[0123] ;

[0124] where k represents the sampling time instant; represents the difference between the SOC of the individual battery i and the average SOC at time instant k; represents the difference between the open-circuit voltage of the individual battery i and the average open-circuit voltage at time instant k; represents the difference between the open-circuit voltage of the individual battery i and the average ohmic resistance at time instant k.

[0125] (3) Extended Kalman filter algorithm based on equivalent circuit model, based on the above content to obtain the state equation of the battery pack average model and the output observation equation as follows:

[0126] ;

[0127] where the extended Kalman filter is used to estimate the transient quantity x; the system input and output vectors are represented by u and y, respectively; represents the estimation error covariance matrix of the extended Kalman filter used to estimate the model parameters ; represents the estimation error covariance matrix of the extended Kalman filter used to estimate the state vector x; represents the sampling time; k represents the sampling point; L represents the time scale of parameter identification, in s; is the battery state vector at the kth sampling point, the +1th time scale; is the battery state vector at the kth sampling point, the The system input vector at each time scale; This is the model parameter vector at the kth sampling point; For the k-th sampling point, the +1 timescale of state of charge; For the k-th sampling point, the +1 timescale polarization voltage; For the k-th sampling point, the Load current at a time scale; For the k-th sampling point, the Load voltage at a time scale; For k sampling points, the first Polarization voltage at a time scale; For the k-th sampling point, the Open-circuit voltage at a time scale; The ohmic resistance of the battery; For the k-th sampling point, the The state of charge at several time scales.

[0128] ;

[0129] In the formula, For the k-th sampling point, the A battery state vector at each time scale. and Differentiation into:

[0130] ;

[0131] ;

[0132] in, , as well as Represents the system matrix. For the k-1th sampling point, the State transition matrix at -1 time scales; For the k-1th sampling point, the Observation matrix at multiple time scales; For the k-1th sampling point, the The estimated battery state vector at each time scale; For the k-1th sampling point, the The estimated battery state vector at a time scale of -1; This represents the estimated model parameter vector at the k-th sampling point; For the k-1th sampling point, the State of charge at various time scales; The open-circuit voltage is used. In the differential model, current is used as the input parameter, and the voltage difference between the reference battery and the differential battery cell is used as the output. Discrete equations for the voltage difference and the SOC (State of Charge) difference are established, yielding the state equation and observation equation of the differential model:

[0133] ;

[0134] ;

[0135] In the formula, and All use micro-timescale Kalman filtering; For the i-th battery at the k-th sampling point, the... The difference in state of charge at each time scale represents the difference in state of charge with respect to the reference cell. For the i-th battery at the k-th sampling point, the... The resistance difference over a time scale represents the difference in resistance compared to the reference cell; For the k-th sampling point, the +1 battery state vectors at different time scales; For the k-th sampling point, the Battery state vectors at various time scales; For the i-th battery at the k-th sampling point, the... +1 time scale difference in state of charge; For the i-th battery at the k-th sampling point, the... The voltage difference over a time scale represents the voltage difference from the reference cell; Let be the model parameter vector at k sampling points of the i-th battery. By linearizing the state equation and observation equation, the following derivatives can be obtained:

[0136] ;

[0137] ;

[0138] In the formula, For the difference model at the k-1th sampling point of the i-th battery, the... State transition matrix at -1 time scales; This is the prior estimate of the i-th battery parameter at the k-th sampling point of the difference model; This represents the state vector of the i-th battery in the difference model. This is the estimated value of the i-th battery parameter at the k-th sampling point of the difference model; For the k-1th sampling point of the difference model, the... The estimated value of the state of charge difference of the i-th battery at each time scale.

[0139] Figure 4 This section presents the equivalent circuit topology of a series-parallel battery pack, showcasing the topology of the equivalent circuit model under the series-parallel structure. The average model represents the average state of the battery pack, while the differential state equivalent circuit model reflects the differences between individual cells within the battery pack. Furthermore... Figure 4 In For the cell in the Nth column and Mth row; For the Nth column of parallel battery modules; The internal resistance of the battery is ohmic. This is the battery open-circuit voltage; This refers to the battery polarization voltage. Battery polarization resistor; For battery polarization capacitors; This is the battery load current; Let be the resistance difference of the i-th battery; This represents the state-of-charge difference of the i-th battery. This represents the difference in battery load voltage.

[0140] Furthermore, the updated state of charge (SOC) and polarization voltage of the battery pack are substituted into the numerical analysis model of the battery pack. Combined with multiple constraints such as battery pack voltage, current, and SOP (State of Power), the peak power current of the battery pack is calculated. Based on this, and combined with the peak voltage, a numerical model for estimating the battery pack's state of power under multiple constraints is established.

[0141] (1) Maximum charge and discharge current constraint: The maximum discharge current specified by the manufacturer in the design of the power battery. Minimum charging current This serves as a constraint to prevent the power battery from operating beyond the capacity of the energy storage unit.

[0142] ;

[0143] In the formula, This is the peak discharge current of the battery pack calculated at time k; The peak charging current of the battery pack at time k; This represents the internal resistance of the battery pack during the discharge process. This refers to the internal resistance of the battery pack during the charging process. This is the charging cutoff voltage; This is the discharge cutoff voltage; Open-circuit voltage, in volts (V). This represents the maximum available capacity of the battery pack, expressed in Ah.

[0144] (2) State of Charge constraint: when the battery is overcharged and over-discharged, there is a greater security risk, so when the SOC of the battery pack is close to the preset limit condition, the battery current value needs to be limited to avoid damage to the battery due to excessive current. The maximum battery calculation formula in the interval of continuous L sampling times is:

[0145]

[0146] In the formula, SOCk is the SOC at time k; η is the battery charge and discharge efficiency; SOCmax is the maximum limit value of the battery SOC, SOCmin is the minimum limit of the battery SOC, and the calculation of the actual limit peak current based on the battery SOC within the time ∆t can ensure the safety performance of the battery during charging and discharging.

[0147] (3) State of Health constraint: as aging progresses, the maximum available capacity of the power battery gradually decreases, and the charge and discharge capability is weakened, so the maximum available capacity of the battery pack needs to be updated based on the current state of health .

[0148] Based on the above constraints, the multi-constraint peak dynamic current and the peak power of the power battery are calculated, and the peak power of the battery pack at time k in the interval L of the duration is obtained:

[0149]

[0150]

[0151] Among them, Ipeakdischargek is the peak discharge current of the battery pack at time k, Ipeakchargek is the peak charge current of the battery pack at time k, unit A; Pmincharge is the minimum charge power set during the design and application of the battery pack, Pmaxdischarge is the maximum discharge power limit set during the design and application of the battery pack, unit W; Ppeakdischargek is the peak discharge power of the battery pack estimated by the multi-constraint dynamic continuous peak power estimation method at time k, Ppeakchargek is the peak charge power of the battery pack estimated by the multi-constraint dynamic continuous peak power estimation method at time k, unit W; Ipeakdischarge is the maximum discharge current; Ipeakcharge is the minimum charge current; Vcut-offk+L is the cut-off voltage at time k+L.

[0152] ​​​​Step S14, based on the feature mapping model, the battery pack power state estimation model and the corresponding topological structure information of the electrochemical energy storage system, multi-state joint estimation is performed to determine the situational awareness result.

[0153] In this embodiment, the feature mapping model and the battery pack power state estimation model are used to perform multi-state joint estimation on the batteries in the system, that is, the series and parallel topological structure of the battery modules and the batteries in the electrochemical energy storage system is analyzed based on the topological structure information to determine the analysis result; based on the feature mapping model and the battery pack power state estimation model, a multi-level state perception model is determined; based on the analysis result and the multi-level state perception model, the electrochemical energy storage system is jointly perceived in multiple state parameters to determine the situational awareness result; the multiple state parameters include state of charge parameters, state of health parameters and power state parameters.

[0154] It should be understood that in the process of multi-state joint estimation, the topological structure information corresponding to the energy storage system is considered in this embodiment, and the series and parallel topological structure inside the electrochemical energy storage system is analyzed first; the mapping relationship between the topological parameters and the system state perception model is established. For example, the classical topological form 3 and 6 series structure of the battery pack can be selected, based on the physical connection relationship of the battery monomers in the energy storage system, the characteristics of voltage accumulation and capacity consistency under series structure, and the characteristics of capacity accumulation and voltage consistency under parallel structure are determined, and the module-level electrical characteristic mapping model is constructed. By analyzing the connection mode and quantity of the batteries in the module, the theoretical values of the overall voltage, current and capacity are determined, and the calculation logic of the key states such as module-level SOC, SOP and SOH is defined accordingly. Considering that the voltages of the battery monomers remain consistent when connected in parallel, the overall consistency is high; while under series connection condition, due to the difference in voltage of each monomer, it is difficult to realize unified full charge and full discharge, which easily leads to the expansion of performance difference between monomers, and the consistency obviously decreases, so this embodiment sets the consistency of parallel monomers to be the same, but the consistency of series monomers is not required.

[0155] Then, at the modeling level, the multi-state joint estimation model from the monomer level to the module level is constructed by combining the equivalent circuit model and the data-driven method, wherein the monomer level takes the actually collected voltage, current and capacity as input, and outputs the key state indicators; the module level forms dynamic perception of the overall operating state through battery topological structure mapping and feature fusion, and consideration of the inconsistency in the battery pack. This model can realize online prediction and update of parameters such as state of charge, state of health and power state at the module level. Specifically, in one specific embodiment, the result of state perception can be as shown in Figures 5 to 9 , Figure 5 the SOH estimation curve of the battery pack constructed for B1 battery, the first 70% is the training set, and the last 30% is the verification set,Figure 6 The comparison curve of the SOH estimation value of the electrochemical energy storage system and the true value, wherein the SOH estimation error of each battery pack is less than 2%, Figure 7 The SOC estimation curve of the battery pack constructed for the B1 battery, Figure 8 The comparison curve of the SOC estimation value of the electrochemical energy storage system and the true value, wherein the SOC estimation error of each battery pack is less than 1.5%, Figure 9 The charge-discharge peak power curves of the B3 battery under different aging degrees, Figure 9 As can be seen from the above, the more serious the aging is, the smaller the charge-discharge peak power of the battery is.

[0156] In summary, the embodiment provides a safety situation awareness scheme for an electrochemical energy storage system frequently participating in power grid regulation. In view of the problems of aggravated aging, enhanced inconsistency and inaccurate state estimation of the energy storage system in frequent participation in power grid regulation tasks, a state perception framework integrating multi-source data driving and mechanism modeling is constructed. First, the voltage, current and other sensing technologies are used to collect multi-type operation data of lithium ion batteries under different working conditions, and the public battery aging experiment data and laboratory measured data are combined to construct an operation database, which covers initial identification data and state dynamic evolution data. Through systematic analysis of multi-source data, key health characteristics in the cycle process are extracted, and the aging evolution law and dominant factors are determined. Second, based on the charge-discharge characteristics of the battery monomer, a monomer level aging feature model is constructed, and is migrated to the module level, while considering the inconsistency of capacity, internal resistance and other aspects between cells, a multi-level battery pack feature model is formed. At the module level, a data-driven model based on BiLSTM-Attention hybrid neural network is proposed to capture the time sequence health characteristics, and an equivalent circuit model containing aging and inconsistency description is constructed by combining the battery pack average model and the single cell difference model. On this basis, a power state estimation model is constructed, which estimates the dynamic peak power capability (SOP) of the battery pack based on the constraints of SOC, voltage, current and polarization characteristics. Finally, around the actual structure of the system, the series-parallel topology relationship of the battery module is analyzed, a hybrid modeling system integrating equivalent circuit and data driving is constructed at the battery pack level, and the joint estimation and real-time update of multi-state parameters (SOC, SOH, SOP) are realized, which provides accurate perception basis for the system operation situation. The invention realizes the state modeling closed loop from monomer to module to system, has good engineering practicability and expansibility, and can effectively support the safety management and performance guarantee of the energy storage system in complex power grid regulation scenarios.

[0157] It can be seen that, in the present application, first, based on the local laboratory battery aging measured data and the operation data of the battery in the electrochemical energy storage system in the charge and discharge cycle, a battery operation database is constructed, then based on the battery operation database, feature extraction is performed, the corresponding first aging feature information of the battery and the inconsistency feature information corresponding to the battery module are used to determine the feature mapping model from the single body level to the module level, then based on the preset hybrid neural network model, the second aging feature information corresponding to the battery module, the inconsistency feature information and the equivalent circuit model, the battery pack power state estimation model under multiple constraint conditions is determined, and then based on the feature mapping model, the battery pack power state estimation model and the topology structure information of the system, the situation awareness result is determined. In this way, for the scene that the energy storage system frequently participates in the grid regulation, the precise state perception of the whole life cycle of the energy storage system is realized, the problems of perception deviation and distortion caused by the cross-level transmission characteristics of the state of the energy storage system are solved, the accuracy, precision and reliability of the state perception are improved, and the safety and intelligent management level of the energy storage system in the complex regulation scene are improved.

[0158] Referring to Figure 10 The embodiment of the present application also discloses a situation awareness device of an electrochemical energy storage system, which comprises:

[0159] The database construction module 11 is used for collecting the operation data of the battery in the electrochemical energy storage system in the charge and discharge cycle, and combining the local laboratory battery aging measured data to construct a battery operation database; the battery operation database comprises an initial state identification data set and a state evolution data set;

[0160] The mapping model construction module 12 is used for performing feature extraction based on the battery operation database, and using the corresponding first aging feature information of the battery and the inconsistency feature information corresponding to the battery module to determine the feature mapping model from the single body level to the module level;

[0161] The model determination module 13 is used for determining the battery pack power state estimation model under multiple constraint conditions based on the preset hybrid neural network model, the second aging feature information corresponding to the battery module, the inconsistency feature information and the equivalent circuit model;

[0162] The situation awareness module 14 is used for performing multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model and the topology structure information corresponding to the electrochemical energy storage system to determine the situation awareness result.

[0163] In some embodiments, the database construction module 11 can be specifically configured to: determine, based on a sensor, operation data of a battery in a charge-discharge cycle in an electrochemical energy storage system; obtain local laboratory battery aging measured data corresponding to the operation data; perform evolution analysis on battery performance and battery parameters based on the laboratory battery aging measured data and battery aging data to determine a battery operation database; the battery parameters include voltage, current and capacity.

[0164] In some embodiments, the mapping model construction module 12 can be specifically configured to: determine, based on the battery operation database, a single cell charge-discharge curve of the battery; perform feature extraction based on the single cell charge-discharge curve to determine first aging feature information corresponding to the battery; perform feature extraction based on the battery operation database to determine inconsistency feature information corresponding to a battery module; the battery module includes a plurality of the batteries, and the inconsistency feature information includes a range of voltage curves of each of the batteries in the module and a distance between the voltage curves and an average voltage curve of all the batteries in the module; and determine a feature mapping model from a single cell level to a module level based on the first aging feature information and the inconsistency feature information.

[0165] In some embodiments, the model determination module 13 can be specifically configured to: determine, based on the battery operation database, second aging feature information corresponding to the battery module; train a preset hybrid neural network model based on the second aging feature information and health features in the inconsistency feature information to determine a battery data-driven model at a module level when the training is completed; the preset hybrid neural network model is a neural network model determined based on a bidirectional long short-term memory network and an attention mechanism; determine an equivalent circuit model corresponding to the battery module based on an average model and a difference model corresponding to the battery module; and determine a battery pack power state estimation model under multiple constraints based on the battery data-driven model and the equivalent circuit model.

[0166] In some embodiments, the model determination module 13 can be specifically configured to: determine, based on battery parameters corresponding to each of the batteries in the battery module, an average model and a difference model corresponding to the battery module; the average model is used to represent an average state of the battery module, and the difference model is used to represent a deviation between a state of each of the batteries in the battery module and the average state; and determine an equivalent circuit model corresponding to the battery module based on the average model, the difference model and an extended Kalman filtering algorithm.

[0167] In some embodiments, the model determination module 13 can be specifically configured to: obtain preset multiple constraints; the preset multiple constraints include a charge-discharge current constraint, a state of charge constraint and a state of health constraint of the battery module; and perform calculation deduction based on the preset multiple constraints, the battery data-driven model and the equivalent circuit model to determine a battery pack power state estimation model.

[0168] In some embodiments, the situation awareness module 14 can be specifically configured to: analyze the series-parallel connection topology of the battery module and the battery in the electrochemical energy storage system through topology information to determine an analysis result; determine a multi-level state awareness model based on the feature mapping model and the battery pack power state estimation model; and perform joint awareness of multiple state parameters of the electrochemical energy storage system based on the analysis result and the multi-level state awareness model to determine a situation awareness result; the multiple state parameters include a state of charge parameter, a state of health parameter and a power state parameter.

[0169] Further, the embodiment of the present application further discloses an electronic device, Figure 11 is a structural diagram of an electronic device 20 according to an exemplary embodiment, and the contents in the figure cannot be considered as any limitation on the use range of the present application.

[0170] Figure 11 A structural schematic diagram of an electronic device 20 is provided in the embodiment of the present application. The electronic device 20 can specifically include at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input-output interface 25 and a communication bus 26. The memory 22 is used to store a computer program, the computer program is loaded and executed by the processor 21 to realize the related steps in the situation awareness method of the electrochemical energy storage system disclosed in any of the preceding embodiments. In addition, the electronic device 20 in the embodiment can be an electronic computer.

[0171] In the embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solution of the present application, which is not limited specifically herein; the input-output interface 25 is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to the specific application needs, which is not limited specifically herein.

[0172] In addition, the memory 22 can be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc. as a carrier for storing resources, and the resources stored thereon can include an operating system 221, a computer program 222, etc. The storage mode can be temporary storage or permanent storage.

[0173] The operating system 221 is used to manage and control each hardware device on the electronic device 20 and the computer program 222, and can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program capable of completing the situation awareness method of the electrochemical energy storage system executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 can further include a computer program capable of completing other specific work.

[0174] Further, the present application also discloses a computer readable storage medium for storing a computer program; wherein the computer program is executed by a processor to implement the situation awareness method of the electrochemical energy storage system disclosed above. For the specific steps of the method, please refer to the corresponding content disclosed in the foregoing embodiments, which will not be described here.

[0175] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. For the same or similar parts between the embodiments, please refer to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and please refer to the method part for the relevant part.

[0176] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of the two. In order to clearly show the interchangeability of hardware and software, the components and steps of each example have been described in the above description. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0177] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0178] Finally, it needs to be pointed out that in this document, relational terms such as first and second and the like can only be intended to distinguish one entity or operation from another entity or operation without necessarily requiring or implying any actual such relationship or order between such entities or operations. Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus including the stated element.

[0179] The above detailed description of the technical solutions provided by the present application has been provided, and the principles and implementation manners of the present application have been described by applying specific examples. The above description of the examples is only for the purpose of helping to understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description of the content of the specification should not be understood as a limitation of the present application.

Claims

1. A situational awareness method for an electrochemical energy storage system, the method comprising: The method comprises the following steps: Collecting operation data of the battery in the electrochemical energy storage system during the charging and discharging cycle, and combining local laboratory battery aging measured data to construct a battery operation database; The battery operation database includes initial state identification data set and state evolution data set; Based on the battery operation database, feature extraction is performed, and the corresponding first aging feature information of the battery and the inconsistency feature information of the battery module are used to determine the feature mapping model from the single cell level to the module level; Based on the preset hybrid neural network model, the second aging feature information of the battery module, the inconsistency feature information and the equivalent circuit model, a battery pack power state estimation model under multiple constraint conditions is determined; Based on the feature mapping model, the battery pack power state estimation model and the corresponding topological structure information of the electrochemical energy storage system, multi-state joint estimation is performed to determine the situation awareness result.

2. The situational awareness method of an electrochemical energy storage system of claim 1, wherein, The method comprises the following steps: Collecting operation data of the battery in the electrochemical energy storage system during the charging and discharging cycle, and combining local laboratory battery aging measured data to construct a battery operation database, comprising: Based on the sensor, the operation data of the battery in the electrochemical energy storage system during the charging and discharging cycle is determined; Obtaining local laboratory battery aging measured data corresponding to the operation data; 3. The self-aware method of an electrochemical energy storage system of claim 1, wherein, Based on the laboratory battery aging measured data and the battery aging data, the evolution analysis of the battery performance and the battery parameters is performed to determine the battery operation database; the battery parameters include voltage, current and capacity. The method comprises the following steps: Based on the battery operation database, the single charging and discharging curve of the battery is determined; Based on the single charging and discharging curve, feature extraction is performed to determine the first aging feature information corresponding to the battery; Based on the battery operation database, feature extraction is performed to determine the inconsistency feature information of the battery module; the battery module includes a plurality of batteries, and the inconsistency feature information includes the range of voltage curve of each battery in the module, the distance between the voltage curve and the average voltage curve of all batteries in the module; 4. The situational awareness method of an electrochemical energy storage system of claim 1, wherein, Based on the first aging feature information and the inconsistency feature information, the feature mapping model from the single cell level to the module level is determined. The method comprises the following steps: Based on the battery operation database, the second aging feature information of the battery module is determined; Based on the second aging feature information and the health feature in the inconsistency feature information, the preset hybrid neural network model is trained to determine the battery data driven model at the module level when the training is completed; the preset hybrid neural network model is a neural network model determined based on bidirectional long short-term memory network and attention mechanism; determine the equivalent circuit model corresponding to the battery module based on the average model and the difference model corresponding to the battery module; determine the battery pack power state estimation model under multiple constraint conditions based on the battery data-driven model and the equivalent circuit model.

5. The self-aware method of an electrochemical energy storage system of claim 4, wherein, The determination of the equivalent circuit model corresponding to the battery module based on the average model and the difference model corresponding to the battery module comprises: determine the average model and the difference model corresponding to the battery module based on the battery parameters corresponding to each battery in the battery module; the average model is used to represent the average state of the battery module, and the difference model is used to represent the deviation between the state of each battery in the battery module and the average state; determine the equivalent circuit model corresponding to the battery module based on the average model, the difference model and the extended Kalman filtering algorithm.

6. The self-aware method of an electrochemical energy storage system of claim 4, wherein, The determination of the battery pack power state estimation model under multiple constraint conditions based on the battery data-driven model and the equivalent circuit model comprises: obtain a preset multiple constraint condition; the preset multiple constraint condition includes a charge-discharge current constraint condition, a state of charge constraint condition and a state of health constraint condition of the battery module; calculate and deduce based on the preset multiple constraint condition, the battery data-driven model and the equivalent circuit model to determine the battery pack power state estimation model.

7. The self-aware method of an electrochemical energy storage system of claim 1, wherein, The multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model and the topological structure information corresponding to the electrochemical energy storage system comprises: analyze the series-parallel topological structure of the battery module and the battery in the electrochemical energy storage system through the topological structure information to determine an analysis result; determine a multi-level state perception model based on the feature mapping model and the battery pack power state estimation model; jointly perceive multiple state parameters of the electrochemical energy storage system based on the analysis result and the multi-level state perception model to determine a situation awareness result; the multiple state parameters include state of charge parameters, state of health parameters and power state parameters.

8. A situational awareness device for an electrochemical energy storage system, comprising: The database construction module is configured to collect operation data of the battery in the electrochemical energy storage system in a charge-discharge cycle, and construct a battery operation database in combination with local laboratory battery aging measured data; the battery operation database includes an initial state identification data set and a state evolution data set. The mapping model construction module is configured to perform feature extraction based on the battery operation database, and determine a feature mapping model from a single body level to a module level by using corresponding first aging feature information of the battery and inconsistency feature information of the battery module. The model determination module is configured to determine a battery pack power state estimation model under multiple constraint conditions based on a preset hybrid neural network model, second aging feature information of the battery module, the inconsistency feature information and an equivalent circuit model. The situation awareness module is configured to perform multi-state joint estimation based on the feature mapping model, the battery pack power state estimation model and topological structure information corresponding to the electrochemical energy storage system to determine a situation awareness result. ​ 9. An electronic device, comprising: comprising: a memory for holding a computer program; a processor for executing the computer program to implement the situational awareness method of the electrochemical energy storage system of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, a computer program for holding a computer program which, when executed by a processor, implements the situational awareness method of the electrochemical energy storage system of any one of claims 1 to 7.

Images