CN117517971A - Battery electric quantity prediction method and device, electronic equipment and storage medium - Google Patents
Battery electric quantity prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117517971A CN117517971A CN202311475578.8A CN202311475578A CN117517971A CN 117517971 A CN117517971 A CN 117517971A CN 202311475578 A CN202311475578 A CN 202311475578A CN 117517971 A CN117517971 A CN 117517971A
- Authority
- CN
- China
- Prior art keywords
- electric quantity
- battery
- prediction
- predicted
- terminal voltage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001914 filtration Methods 0.000 claims abstract description 104
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 16
- 238000009792 diffusion process Methods 0.000 claims description 8
- 230000010287 polarization Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 238000012549 training Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003446 memory effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a battery electric quantity prediction method, a device, electronic equipment and a storage medium; the method comprises the following steps: acquiring initial electric quantity and prediction time of a battery to be estimated; based on the initial electric quantity and the prediction time, carrying out electric quantity prediction from a macro scale and a micro scale through a Kalman filtering algorithm, and determining a first predicted electric quantity, a terminal voltage true value of a battery, a Kalman filtering gain and a filtering estimation terminal voltage error; inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity; the electric quantity of the battery to be estimated is determined based on the first predicted electric quantity and the second predicted electric quantity, the problem that the predicted result of the electric quantity of the battery is inaccurate is solved, the electric quantity is predicted from data of different dimensions, and the result is more accurate.
Description
Technical Field
The present invention relates to the field of battery management technologies, and in particular, to a method and an apparatus for predicting an electric quantity of a battery, an electronic device, and a storage medium.
Background
The battery is a key component of the electric automobile, and is widely applied to the fields of electronics, military industry, aviation and the like due to the advantages of high energy density, open circuit voltage, output power, no memory effect and the like. In the early development stage of the battery, the method is mainly applied to some basic devices, and the estimation requirement on the state of charge (SOC) of the battery is low, but with the continuous change of the application environment and the user requirement, the accuracy of the estimation on the SOC of the battery is also continuously improved. The existing SOC estimation algorithm has the defect that the accuracy of electric quantity estimation is low.
Disclosure of Invention
The invention provides a battery electric quantity prediction method, a device, electronic equipment and a storage medium, which are used for solving the problem of low estimation accuracy in the battery electric quantity estimation process.
According to an aspect of the present invention, there is provided a method of predicting an electric power of a battery, including:
acquiring initial electric quantity and prediction time of a battery to be estimated;
based on the initial electric quantity and the prediction time, carrying out electric quantity prediction from a macro scale and a micro scale through a Kalman filtering algorithm, and determining a first predicted electric quantity, a terminal voltage true value of a battery, a Kalman filtering gain and a filtering estimation terminal voltage error;
Inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity;
and determining the electric quantity of the battery to be estimated based on the first predicted electric quantity and the second predicted electric quantity.
According to another aspect of the present invention, there is provided a power prediction apparatus of a battery, including:
the data acquisition module is used for acquiring the initial electric quantity and the prediction time of the battery to be estimated;
the first prediction module is used for predicting the electric quantity from a macroscopic scale and a microscopic scale through a Kalman filtering algorithm based on the initial electric quantity and the prediction time, and determining a first predicted electric quantity, a terminal voltage true value of the battery, a Kalman filtering gain and a filtering estimation terminal voltage error;
the second prediction module is used for inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity;
and the electric quantity determining module is used for determining the electric quantity of the battery to be estimated based on the first predicted electric quantity and the second predicted electric quantity.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of predicting the charge of a battery according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for predicting the charge of a battery according to any embodiment of the present invention.
According to the technical scheme, the initial electric quantity and the prediction time of the battery to be estimated are obtained; based on the initial electric quantity and the prediction time, carrying out electric quantity prediction from a macro scale and a micro scale through a Kalman filtering algorithm, and determining a first predicted electric quantity, a terminal voltage true value of a battery, a Kalman filtering gain and a filtering estimation terminal voltage error; inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity; the electric quantity of the battery to be estimated is determined based on the first predicted electric quantity and the second predicted electric quantity, the problem that the battery electric quantity prediction result is inaccurate is solved, the initial electric quantity and the prediction time of the battery to be estimated are processed through a Kalman filtering algorithm, electric quantity prediction is achieved, the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error are obtained, the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error are further predicted through a target neural network model, the second predicted electric quantity is obtained, and the problem that the accuracy of the prediction result is lower through the combination of the Kalman filtering algorithm and the target neural network model is avoided; the electric quantity is predicted through the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error, so that the electric quantity is predicted according to data of different dimensions, and the result is more accurate; and the electric quantity of the battery to be estimated is determined by combining the first predicted electric quantity and the second predicted electric quantity, the prediction results of multiple angles are comprehensively considered, and the electric quantity prediction accuracy is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for predicting the electric power of a battery according to a first embodiment of the present invention;
fig. 2 is a flowchart of a method for predicting the electric quantity of a battery according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of an equivalent circuit model according to a second embodiment of the present invention;
fig. 4 is a flowchart illustrating an example of determining the electric quantity of a battery to be estimated according to the second embodiment of the present invention;
fig. 5 is a schematic structural diagram of a battery power prediction device according to a third embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device implementing a battery charge prediction method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a battery power prediction method according to an embodiment of the present invention, where the method may be performed by a battery power prediction device, the battery power prediction device may be implemented in hardware and/or software, and the battery power prediction device may be configured in an electronic device. As shown in fig. 1, the method includes:
s101, acquiring initial electric quantity and prediction time of a battery to be estimated.
In this embodiment, the battery to be estimated may be specifically understood as a battery having a power estimation requirement, and the battery to be estimated may be a storage battery, a lithium ion battery, or the like. The initial electric quantity can be specifically understood as the electric quantity of the electric quantity to be estimated when the work is started; the prediction time can be specifically understood as a time, and the method for predicting the electric quantity of the battery provided by the embodiment of the application can predict the electric quantity at the time.
The initial electric quantity can be determined in advance according to the actual electric quantity of the battery to be estimated, namely, the electric quantity of the battery to be estimated can change along with the use of the battery to be estimated. In the power supply process of the battery to be estimated, the electric quantity is gradually reduced, when the electric quantity is predicted, the initial electric quantity of the battery to be estimated is firstly obtained, the prediction time can be specified according to requirements, for example, the prediction time is 20h, because the electric quantity is determined in a periodical iteration mode when the electric quantity is predicted by a Kalman filtering method, the sampling period and the unit of the prediction time can be different, the sampling period is usually s, the unit of the prediction time and the unit of the sampling period are required to be unified, conversion is not required if the obtained prediction time and the unit of the sampling period are unified, the prediction time is converted, and the electric quantity is predicted by adopting the converted prediction time.
S102, based on the initial electric quantity and the prediction time, electric quantity prediction is carried out from a macroscopic scale and a microscopic scale through a Kalman filtering algorithm, and a first predicted electric quantity, a terminal voltage true value of a battery, a Kalman filtering gain and a filtering estimation terminal voltage error are determined.
In this embodiment, the first predicted electric quantity may be specifically understood as an electric quantity predicted by a kalman filtering method; the terminal voltage true value of the battery can be understood as a numerical value of terminal voltages at both ends of the battery; the filter estimation terminal voltage error can be understood as an error when the terminal voltage is predicted by a kalman filter algorithm.
Taking the initial electric quantity as an initial value calculated by a Kalman filtering algorithm, and carrying out electric quantity prediction from a macroscopic scale and a microscopic scale based on the Kalman filtering algorithm to realize electric quantity prediction of multiple time scales; according to the embodiment of the application, the operation code of the Kalman filtering algorithm can be called when the electric quantity prediction is carried out based on the Kalman filtering algorithm, the data is calculated through the code, the data is calculated by taking the data into different formulas, and the calculation result is taken into other different formulas again for calculation. When the electric quantity is predicted based on the initial electric quantity, cyclic prediction is sequentially performed according to the k moment and the k+1 moment … of the initial electric quantity, so that a first predicted electric quantity corresponding to the prediction time is obtained, and the terminal voltage true value, the Kalman filtering gain and the filtering estimation terminal voltage error of the battery are obtained.
And S103, inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity.
In this embodiment, the target neural network model may be specifically understood as a pre-trained neural network model, and the target neural network model may be a multi-layer feedforward neural network BP, a cyclic neural network RNN, or the like. The second predicted electrical quantity may be understood as an electrical quantity predicted by the target neural network model.
The method comprises the steps of training a target neural network model in advance, obtaining a training sample, training the model based on the training sample, continuously adjusting parameters of the model according to a loss function in the training process, and finally obtaining a model meeting the requirements as the target neural network model, wherein the training sample comprises four parameters including electric quantity, a terminal voltage true value of a battery, kalman filtering gain and a filtering estimation terminal voltage error. The trained target neural network model can be used to predict the amount of power. And inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a trained target neural network model, and predicting the target neural network model according to experience and parameters learned in the training process to obtain and output a second predicted electric quantity.
And S104, determining the electric quantity of the battery to be estimated based on the first predicted electric quantity and the second predicted electric quantity.
Performing comprehensive operation based on the first predicted electric quantity and the second predicted electric quantity, for example, taking a maximum value, a minimum value, an average value, a weighted sum value and the like, or presetting an electric quantity calculation formula, and taking the first predicted electric quantity and the second predicted electric quantity as parameters of the electric quantity calculation formula into the electric quantity calculation formula to calculate; and taking the result obtained by the comprehensive operation as the electric quantity of the battery to be estimated.
In this embodiment, the second predicted electric quantity may also be an error compensation of an electric quantity prediction error, and the first predicted electric quantity is subjected to the error compensation by the second predicted electric quantity to obtain an electric quantity of the battery to be estimated, for example, the first predicted electric quantity plus the second predicted electric quantity is equal to the electric quantity of the battery to be estimated.
The battery electric quantity prediction method provided by the embodiment of the invention solves the problem of inaccurate battery electric quantity prediction results, processes the initial electric quantity and the prediction time of the battery to be estimated through a Kalman filtering algorithm, realizes electric quantity prediction, obtains the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filter estimated terminal voltage error, further predicts the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filter estimated terminal voltage error through a target neural network model, obtains the second predicted electric quantity, predicts through a combined Kalman filtering algorithm and the target neural network model, and avoids the problem of lower accuracy of the prediction result through a single algorithm; the electric quantity is predicted through the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error, so that the electric quantity is predicted according to data of different dimensions, and the result is more accurate; and the electric quantity of the battery to be estimated is determined by combining the first predicted electric quantity and the second predicted electric quantity, the prediction results of multiple angles are comprehensively considered, and the electric quantity prediction accuracy is improved.
Example two
Fig. 2 is a flowchart of a battery power prediction method according to a second embodiment of the present invention, where the present embodiment is refined based on the foregoing embodiment. As shown in fig. 2, the method includes:
s201, acquiring initial electric quantity and prediction time of a battery to be estimated.
S202, obtaining model parameters and an electric quantity estimation period of an equivalent circuit model of the battery.
In this embodiment, the equivalent circuit model is a circuit model obtained by performing equivalent on the battery; model parameters can be understood in particular as parameters in the equivalent circuit model, such as resistance, capacitance, etc.; the charge estimation period may be understood as a sampling period during which the charge estimation is performed.
The method comprises the steps of presetting an electric quantity estimation period, carrying out periodic estimation on the electric quantity according to the electric quantity estimation period, namely, a process that an electric quantity prediction process is a periodic iteration process, carrying out iterative calculation on the electric quantity of a second period according to a value of the first period, carrying out iterative calculation on the electric quantity of a third period according to a value of the second period, and the like until the electric quantity corresponding to the prediction time is obtained. Therefore, in order to facilitate the power prediction by the kalman filter algorithm, a power estimation period, for example, ts=1s, may be set in advance. The equivalent circuit model is constructed in advance according to the characteristics of the battery, the same equivalent circuit model can be adopted for the battery of the same type, and the equivalent circuit model and the identity or type of the battery can be correspondingly stored after the equivalent circuit model of the battery is constructed. After the battery to be estimated is determined, a prestored equivalent circuit model can be queried, if the corresponding equivalent circuit model exists, the equivalent circuit model is directly obtained, and if the corresponding equivalent circuit model does not exist, the equivalent circuit model is constructed according to the characteristics of the battery.
Optionally, the model parameters include: polarization resistance, diffusion resistance, polarization capacitance, diffusion capacitance, open circuit voltage of the battery, load current, ohmic internal resistance of the battery, battery capacity, coulombic efficiency.
Exemplary, FIG. 3 provides a schematic diagram of an equivalent circuit model, namely a Thevenin second order RC circuit model, U OC Open circuit voltage of a battery, typically varies non-linearly with SOC; r is R 0 Is the ohmic internal resistance of the battery; r is R 1 、C 1 Respectively a polarization resistor and a polarization capacitor; r is R 2 、C 2 Respectively a diffusion resistor and a diffusion capacitor; i (t) is the load electricity flowing throughFlow, which can be measured by a current sensor; u (U) 1 、U 2 R is respectively 1 、R 2 Voltage of U 0 Is the terminal voltage.
After the second-order RC equivalent circuit model is built, a state equation and an observation equation of the battery can be deduced.
Let z=soc, derive the state equation of the battery:
observation equation of battery:
U o ＝g (z) -R 0 I(t)-U 1 -U 2
wherein eta is coulombic efficiency, T S For sampling period (T S ＝1s)，Q n G (z) is the battery capacity.
S203, calculating an analytical solution of a battery state equation of the equivalent circuit model based on the electric quantity estimation period and the model parameters, and determining the time of the microscale.
In this embodiment, the time of the macro scale is the time point corresponding to different acquisition periods such as k, k+1, etc., the predicted time is the time of the macro scale, and the time of the micro scale refers to the time between k and k+1. And determining a state equation of the battery based on the equivalent circuit model, introducing the electric quantity estimation period and the model parameters into a calculation formula of an analytic solution, and obtaining the analytic solution aiming at the characteristics of slow change of the battery parameters and fast change of the battery state to obtain the time of microscopic scale.
Exemplary, the embodiment of the application provides a calculation formula of an analytic solution:
where l is the time on a microscopic scale.
Multi-time scale discretization is performed from macroscopic and microscopic angles, respectively:
further, a discretized state equation on a multi-time scale is obtained:
and (3) observing an equation:
s33: the formula is further generalized:
X k,l+1 ＝F(X k,l ,u k,l ,θ k )+ω k,l θ k+1 ＝θ k +r k
y k,l ＝G(X k,l ,u k,l ,θ k )+v k,l
wherein omega is k,l 、v k,l R is the system process noise and the observation noise k Process noise, which is a model parameter.
S204, carrying out macro-scale prediction based on the initial electric quantity to obtain a filter parameter estimated value.
In this embodiment, the filter parameter estimation value may be specifically understood as a parameter value predicted when the electric quantity is predicted by a kalman filter algorithm. And carrying the initial electric quantity into a corresponding calculation formula to predict, and obtaining a filter parameter estimated value.
Exemplary, the embodiment of the application provides a calculation formula of a filter parameter estimation value:
initializing parameters:
wherein θ 0 For the initial filter parameter estimate,is the covariance of state parameters, X 0,0 For the initial charge,/->Is the state parameter error covariance.
Performing scale conversion to obtain a filter parameter estimated value under a macro scale
The filter parameter estimated value obtained in the step is the filter parameter estimated value at the moment k.
And S205, performing microscale prediction based on the microscale time and the filter parameter estimation value to obtain an electric quantity estimation value, a predicted terminal voltage value, a predicted filter gain and a predicted voltage error.
In this embodiment, the estimated electric quantity value may be specifically understood as an estimated electric quantity value in the current period; the predicted terminal voltage value may be specifically understood as a terminal voltage value of the battery predicted in the current period; the prediction filtering gain can be understood as specifically being the kalman filtering gain predicted in the current period; the predicted voltage error can be understood as an error value of the terminal voltage predicted in the current period.
And carrying the time of the microscale and the estimated value of the filtering parameter into a related calculation formula of microscale prediction for calculation to obtain an estimated value of electric quantity, a predicted terminal voltage value, a predicted filtering gain and a predicted voltage error.
Exemplary, the embodiment of the present application provides a calculation formula of an estimated value of electric quantity, a predicted terminal voltage value, a predicted filtering gain and a predicted voltage error:
wherein the predicted terminal voltage value is Y k The prediction filtering gain is K k The predicted voltage error isElectric quantity estimation valueThe parameters are data predicted from a macro scale k; w (W) (i) The compensation error for the ith neuron is predetermined.
And selecting a proper X point prediction state value under the microscopic scale, and then calculating a state variable to realize electric quantity prediction under the microscopic scale.
S206, judging whether the iteration stop condition is met according to the prediction time, if so, executing S207; otherwise, S208 is performed.
In this embodiment, the iteration stop condition may be specifically understood as a condition for determining whether to stop iteration when periodically iteratively predicting the electric quantity, for example, the current predicted electric quantity is an electric quantity corresponding to the prediction time. Presetting an iteration stop condition, analyzing according to the predicted time, determining whether the predicted electric quantity is the electric quantity corresponding to the predicted time at the moment, if so, determining that the iteration stop condition is met, and executing S207; if not, it is determined that the iteration stop condition is not satisfied, and step S208 is executed.
S207, determining an estimated electric quantity value as a first predicted electric quantity, determining a predicted terminal voltage value as a terminal voltage true value of a battery, determining a prediction filtering gain as a Kalman filtering gain, and determining a predicted voltage error as a filtering estimated terminal voltage error.
S208, taking the electric quantity estimated value as a new initial electric quantity, and returning to S204.
And when the iteration stop condition is not met, taking the electric quantity estimated value as a new initial electric quantity, and updating the electric quantity at different moments.
S209, inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity.
Optionally, the target neural network model is a multi-layer feedforward neural network.
In this embodiment, the target neural network model preferably adopts a multi-layer feedforward neural network BP, takes the first predicted electric quantity, the terminal voltage true value of the battery, the kalman filter gain and the filter estimation terminal voltage error as the input of the target neural network model, and predicts the electric quantity through the target neural network model to obtain the second predicted electric quantity.
The multi-time scale Kalman UKF filtering output data is beneficial to training the BP network, and the dependence of the BP network on the training data quantity is reduced; the UKF filter output is enabled to reflect battery characteristics more accurately by utilizing multi-time scale theoretical modeling, and the generalization capability of an algorithm is effectively improved; BP network input is reasonably selected, error compensation effect is improved, high-precision estimation on the initial value calibration deviation of the electric quantity SOC is realized, and the overall generalization capability and the robustness are excellent.
S210, multiplying the first predicted electric quantity by a first weighting coefficient to obtain a first weighted electric quantity.
In this embodiment, the first weighting coefficient may be specifically understood as a coefficient for weighting the first predicted electric quantity; the first weighted power may be specifically understood as a power value obtained by weighting the first predicted power. And presetting a first weighting coefficient, wherein the first weighting coefficient is set according to the accuracy of Kalman filtering, and multiplying the first predicted electric quantity by the first weighting coefficient to obtain a product which is the first weighting electric quantity.
S211, multiplying the second predicted electric quantity by a second weighting coefficient to obtain a second weighted electric quantity.
In the present embodiment, the second weighting coefficient may be understood as a coefficient for weighting the second predicted electric quantity in particular; the second weighted power may be specifically understood as a power value obtained by weighting the second predicted power. And presetting a second weighting coefficient, wherein the second weighting coefficient is set according to the accuracy of Kalman filtering, and multiplying the second predicted electric quantity by the second weighting coefficient to obtain a product which is the second weighted electric quantity.
S212, taking the sum of the first weighted electric quantity and the second weighted electric quantity as the electric quantity of the battery to be estimated.
And adding the first weighted electric quantity and the second weighted electric quantity to obtain a sum, namely the electric quantity of the battery to be estimated.
For example, fig. 4 provides an exemplary flowchart for determining the electric quantity of the battery to be estimated, taking the target neural network model as the BP model as an example. Electric quantity prediction is respectively carried out from a macro scale and a micro scale based on a Kalman filtering algorithm, and the filtering parameter estimation value is obtained by continuously updating and iterating the time kUpdate based on->And->Determining a filter parameter estimate +.>Wherein (1)>Is the prior value of the electric quantity; determining a first predicted electrical quantity by updating at a macro-scale and a micro-scale, respectively>And simultaneously, inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error determined by the Kalman filtering algorithm into a BP model, and performing error compensation on the second predicted electric quantity output by the BP model and the first predicted electric quantity to obtain the electric quantity at the moment k.
It should be noted that the electric quantity described in the embodiments of the present application may be the remaining electric quantity percentage SOC, or may be other parameters that may indicate the electric quantity.
As an optional embodiment of the present embodiment, the optional embodiment further optimizes the power including obtaining power at different prediction times; and generating a power curve graph according to each predicted time and power.
In this embodiment, the electric quantity graph may be specifically understood as a graph formed by electric quantities of the battery to be estimated at different times, where the abscissa of the electric quantity graph is time and the ordinate is electric quantity.
Different prediction times are preset, for each prediction time, the electric quantity is predicted by the electric quantity prediction method of the battery provided by the embodiment of the application, the corresponding electric quantity is predicted, a rectangular coordinate system is established, corresponding points in the coordinate system are determined according to each prediction time and the corresponding electric quantity, and each point is connected in sequence to form an electric quantity graph.
According to the embodiment of the application, different types of algorithms can be selected for electric quantity prediction, corresponding electric quantity graphs are formed, and by comparing the electric quantity graphs, the electric quantity graph corresponding to which algorithm is judged to be more fit with the electric quantity change of an actual battery, so that the accuracy of each algorithm is determined.
The battery electric quantity prediction method provided by the embodiment of the invention solves the problem of inaccurate battery electric quantity prediction results, predicts through combining a Kalman filtering algorithm and a target neural network model, and avoids the problem of lower accuracy of the prediction results by using a single algorithm; the electric quantity is predicted through the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error, so that the electric quantity is predicted according to data of different dimensions, and the result is more accurate; and the electric quantity of the battery to be estimated is determined by combining the first predicted electric quantity and the second predicted electric quantity, the prediction results of multiple angles are comprehensively considered, and the electric quantity prediction accuracy is improved. The multi-layer feedforward neural network is selected as a target neural network model, and the BP network is trained based on the multi-time scale Kalman UKF filtering output data, so that the dependence of the BP network on the training data quantity is reduced; the UKF filter output is enabled to reflect battery characteristics more accurately by utilizing multi-time scale theoretical modeling, and the generalization capability of an algorithm is effectively improved; BP network input is reasonably selected, error compensation effect is improved, high-precision estimation on the initial value calibration deviation of the electric quantity SOC is realized, and the overall generalization capability and the robustness are excellent.
Example III
Fig. 5 is a schematic structural diagram of a battery power prediction device according to a third embodiment of the present invention. As shown in fig. 5, the apparatus includes: a data acquisition module 31, a first prediction module 32, a second prediction module 33, and a power determination module 34.
The data acquisition module 31 is configured to acquire an initial electric quantity and a predicted time of a battery to be estimated;
a first prediction module 32, configured to predict, based on the initial power and the prediction time, the power from the macro scale and the micro scale by using a kalman filter algorithm, and determine a first predicted power, a terminal voltage true value of the battery, a kalman filter gain, and a filter estimated terminal voltage error;
the second prediction module 33 is configured to input the first predicted electric quantity, the terminal voltage true value of the battery, the kalman filter gain, and the filter estimated terminal voltage error into a predetermined target neural network model, so as to obtain a second predicted electric quantity;
the power determining module 34 is configured to determine the power of the battery to be estimated based on the first predicted power and the second predicted power.
The battery electric quantity prediction device provided by the embodiment of the invention solves the problem of inaccurate battery electric quantity prediction results, processes the initial electric quantity and the prediction time of the battery to be estimated through a Kalman filtering algorithm, realizes electric quantity prediction, obtains the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filter estimated terminal voltage error, further predicts the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filter estimated terminal voltage error through a target neural network model, obtains the second predicted electric quantity, predicts through a combined Kalman filtering algorithm and the target neural network model, and avoids the problem of lower accuracy of the prediction result through a single algorithm; the electric quantity is predicted through the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error, so that the electric quantity is predicted according to data of different dimensions, and the result is more accurate; and the electric quantity of the battery to be estimated is determined by combining the first predicted electric quantity and the second predicted electric quantity, the prediction results of multiple angles are comprehensively considered, and the electric quantity prediction accuracy is improved.
Optionally, the first prediction module 32 includes:
the model parameter acquisition unit is used for acquiring model parameters and an electric quantity estimation period of an equivalent circuit model of the battery;
the microcosmic time determining unit is used for calculating an analytic solution of a battery state equation of the equivalent circuit model based on the electric quantity estimation period and the model parameters, and determining microcosmic scale time;
the macro prediction unit is used for carrying out macro scale prediction based on the initial electric quantity to obtain a filter parameter estimated value;
the micro prediction unit is used for performing micro-scale prediction based on the micro-scale time and the filter parameter estimation value to obtain an electric quantity estimation value, a prediction terminal voltage value, a prediction filter gain and a prediction voltage error;
the judging unit is used for judging whether iteration stopping conditions are met or not according to the prediction time, if so, determining the electric quantity estimation value as a first prediction electric quantity, determining the prediction terminal voltage value as a terminal voltage true value of a battery, determining the prediction filtering gain as a Kalman filtering gain, and determining the prediction voltage error as a filtering estimation terminal voltage error; otherwise, taking the electric quantity estimated value as a new initial electric quantity, and returning to execute the step of carrying out macro-scale prediction based on the initial electric quantity to obtain a filtering parameter estimated value.
Optionally, the model parameters include: polarization resistance, diffusion resistance, polarization capacitance, diffusion capacitance, open circuit voltage of the battery, load current, ohmic internal resistance of the battery, battery capacity, coulombic efficiency.
Optionally, the power determination module 34 includes:
the first weighting unit is used for multiplying the first predicted electric quantity by a first weighting coefficient to obtain a first weighted electric quantity;
the second weighting unit is used for multiplying the second predicted electric quantity by a second weighting coefficient to obtain a second weighted electric quantity;
and the electric quantity determining unit is used for taking the sum of the first weighted electric quantity and the second weighted electric quantity as the electric quantity of the battery to be estimated.
Optionally, the target neural network model is a multi-layer feedforward neural network.
Optionally, the apparatus further comprises:
the electric quantity acquisition module is used for acquiring electric quantities of different prediction times;
and the electric quantity diagram generating module is used for generating an electric quantity diagram according to each predicted time and the electric quantity.
The battery power prediction device provided by the embodiment of the invention can execute the battery power prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 6 shows a schematic diagram of an electronic device 40 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a Read Only Memory (ROM) 42, a Random Access Memory (RAM) 43, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 41 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 42 or the computer program loaded from the storage unit 48 into the Random Access Memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 may also be stored. The processor 41, the ROM 42 and the RAM 43 are connected to each other via a bus 44. An input/output (I/O) interface 45 is also connected to bus 44.
Various components in electronic device 40 are connected to I/O interface 45, including: an input unit 46 such as a keyboard, a mouse, etc.; an output unit 47 such as various types of displays, speakers, and the like; a storage unit 48 such as a magnetic disk, an optical disk, or the like; and a communication unit 49 such as a network card, modem, wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 41 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 41 performs the respective methods and processes described above, such as a battery charge prediction method.
In some embodiments, the battery charge prediction method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 40 via the ROM 42 and/or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the battery charge prediction method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the battery charge prediction method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for predicting the charge of a battery, comprising:
acquiring initial electric quantity and prediction time of a battery to be estimated;
based on the initial electric quantity and the prediction time, carrying out electric quantity prediction from a macro scale and a micro scale through a Kalman filtering algorithm, and determining a first predicted electric quantity, a terminal voltage true value of a battery, a Kalman filtering gain and a filtering estimation terminal voltage error;
inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity;
And determining the electric quantity of the battery to be estimated based on the first predicted electric quantity and the second predicted electric quantity.
2. The method of claim 1, wherein the determining the first predicted power, the terminal voltage true value of the battery, the kalman filter gain, and the filter estimated terminal voltage error based on the initial power and the prediction time by performing power prediction from a macro scale and a micro scale by a kalman filter algorithm comprises:
obtaining model parameters and an electric quantity estimation period of an equivalent circuit model of the battery;
calculating an analytical solution of a battery state equation of the equivalent circuit model based on the electric quantity estimation period and the model parameters, and determining microscopic-scale time;
performing macro-scale prediction based on the initial electric quantity to obtain a filter parameter estimation value;
performing microscale prediction based on the microscale time and the filtering parameter estimation value to obtain an electric quantity estimation value, a predicted terminal voltage value, a predicted filtering gain and a predicted voltage error;
judging whether iteration stopping conditions are met according to the prediction time, if so, determining the electric quantity estimation value as a first prediction electric quantity, determining the prediction terminal voltage value as a terminal voltage true value of a battery, determining the prediction filtering gain as a Kalman filtering gain, and determining the prediction voltage error as a filtering estimation terminal voltage error;
Otherwise, taking the electric quantity estimated value as a new initial electric quantity, and returning to execute the step of carrying out macro-scale prediction based on the initial electric quantity to obtain a filtering parameter estimated value.
3. The method of claim 2, wherein the model parameters comprise: polarization resistance, diffusion resistance, polarization capacitance, diffusion capacitance, open circuit voltage of the battery, load current, ohmic internal resistance of the battery, battery capacity, coulombic efficiency.
4. The method of claim 1, wherein the determining the charge of the battery to be estimated based on the first and second predicted charge amounts comprises:
multiplying the first predicted electric quantity by a first weighting coefficient to obtain a first weighted electric quantity;
multiplying the second predicted electric quantity by a second weighting coefficient to obtain a second weighted electric quantity;
and taking the sum of the first weighted electric quantity and the second weighted electric quantity as the electric quantity of the battery to be estimated.
5. The method of claim 1, wherein the target neural network model is a multi-layer feedforward neural network.
6. The method of any one of claims 1-5, further comprising:
Acquiring electric quantity of different prediction time;
and generating a power curve graph according to each predicted time and power.
7. A power predicting apparatus for a battery, comprising:
the data acquisition module is used for acquiring the initial electric quantity and the prediction time of the battery to be estimated;
the first prediction module is used for predicting the electric quantity from a macroscopic scale and a microscopic scale through a Kalman filtering algorithm based on the initial electric quantity and the prediction time, and determining a first predicted electric quantity, a terminal voltage true value of the battery, a Kalman filtering gain and a filtering estimation terminal voltage error;
the second prediction module is used for inputting the first predicted electric quantity, the terminal voltage true value of the battery, the Kalman filtering gain and the filtering estimation terminal voltage error into a predetermined target neural network model to obtain a second predicted electric quantity;
and the electric quantity determining module is used for determining the electric quantity of the battery to be estimated based on the first predicted electric quantity and the second predicted electric quantity.
8. The apparatus of claim 7, wherein the first prediction module comprises:
the model parameter acquisition unit is used for acquiring model parameters and an electric quantity estimation period of an equivalent circuit model of the battery;
The microcosmic time determining unit is used for calculating an analytic solution of a battery state equation of the equivalent circuit model based on the electric quantity estimation period and the model parameters, and determining microcosmic scale time;
the macro prediction unit is used for carrying out macro scale prediction based on the initial electric quantity to obtain a filter parameter estimated value;
the micro prediction unit is used for performing micro-scale prediction based on the micro-scale time and the filter parameter estimation value to obtain an electric quantity estimation value, a prediction terminal voltage value, a prediction filter gain and a prediction voltage error;
the judging unit is used for judging whether iteration stopping conditions are met or not according to the prediction time, if so, determining the electric quantity estimation value as a first prediction electric quantity, determining the prediction terminal voltage value as a terminal voltage true value of a battery, determining the prediction filtering gain as a Kalman filtering gain, and determining the prediction voltage error as a filtering estimation terminal voltage error; otherwise, taking the electric quantity estimated value as a new initial electric quantity, and returning to execute the step of carrying out macro-scale prediction based on the initial electric quantity to obtain a filtering parameter estimated value.
9. An electronic device, the electronic device comprising:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the battery charge prediction method of any one of claims 1-6.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of predicting the charge of a battery according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311475578.8A CN117517971A (en) | 2023-11-07 | 2023-11-07 | Battery electric quantity prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311475578.8A CN117517971A (en) | 2023-11-07 | 2023-11-07 | Battery electric quantity prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117517971A true CN117517971A (en) | 2024-02-06 |
Family
ID=89752389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311475578.8A Pending CN117517971A (en) | 2023-11-07 | 2023-11-07 | Battery electric quantity prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117517971A (en) |
-
2023
- 2023-11-07 CN CN202311475578.8A patent/CN117517971A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230152380A1 (en) | Method and apparatus for determining state of charge and battery management system | |
| JP5058814B2 (en) | Battery state and parameter estimation system and method | |
| WO2019114240A1 (en) | Method and system for predicting state of charge of battery | |
| Alfi et al. | Hybrid state of charge estimation for lithium‐ion batteries: design and implementation | |
| WO2018112818A1 (en) | Rapid prediction method for cycle life of battery and rapid prediction device therefor | |
| CN115932586A (en) | Method, device, equipment and medium for estimating state of charge of battery on line | |
| CN112816879A (en) | Online estimation method for power battery SoE for variable-working-condition vehicle | |
| CN115221795A (en) | Training method, prediction method, device, equipment and medium of capacity prediction model | |
| CN117517971A (en) | Battery electric quantity prediction method and device, electronic equipment and storage medium | |
| CN116859255A (en) | Method, device, equipment and medium for predicting state of health of energy storage battery | |
| CN115754772A (en) | Battery capacity attenuation processing method, device, equipment and storage medium | |
| Tang et al. | Data-physics-driven estimation of battery state of charge and capacity based on Gaussian distribution fusion | |
| Wang et al. | Improved Long Short-Term Memory: Statistical Regression Model for High Precision SOC Estimation of Lithium-Ion Batteries Adaptive to Complex Current Variation Conditions | |
| CN117318021A (en) | Electric power system dynamic state estimation method and system based on long-term and short-term memory network | |
| CN117907872A (en) | Battery life prediction method and device, electronic equipment and storage medium | |
| CN114563045B (en) | Detection method and device for hospital logistics system, electronic equipment and medium | |
| CN116224087B (en) | Battery energy storage system and SOC estimation method and device thereof | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN117665597B (en) | Lithium battery OCV estimation method, system, electronic equipment and medium | |
| Li et al. | An improved adaptive weights correction-particle swarm optimization-unscented particle filter method for high-precision online state of charge estimation of lithium-ion batteries | |
| CN118033461A (en) | Method and device for evaluating battery health state and electronic equipment | |
| Vepa et al. | Batteries: Modeling and state of charge estimation | |
| CN116840588A (en) | Aging detection method, device and equipment for lightning arrester and storage medium | |
| CN117872156A (en) | Method, device, equipment and storage medium for predicting residual life of battery | |
| Xu et al. | State of Charge Estimation of Li-Ion Batteries Based on Sage-Husa High-Degree Cubature Kalman Filter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |