[go: up one dir, main page]

CN113406503A - Lithium battery SOH online estimation method based on deep neural network - Google Patents

Lithium battery SOH online estimation method based on deep neural network Download PDF

Info

Publication number
CN113406503A
CN113406503A CN202110607933.7A CN202110607933A CN113406503A CN 113406503 A CN113406503 A CN 113406503A CN 202110607933 A CN202110607933 A CN 202110607933A CN 113406503 A CN113406503 A CN 113406503A
Authority
CN
China
Prior art keywords
lithium battery
neural network
estimation
deep neural
battery soh
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
Application number
CN202110607933.7A
Other languages
Chinese (zh)
Inventor
杨知方
李中浩
余娟
杨燕
王博石
杜思君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University
Original Assignee
Chongqing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University filed Critical Chongqing University
Priority to CN202110607933.7A priority Critical patent/CN113406503A/en
Publication of CN113406503A publication Critical patent/CN113406503A/en
Pending legal-status Critical Current

Links

Images

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]
    • G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
    • 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]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

本发明公开基于深度神经网络的锂电池SOH在线估算方法，步骤为：1)建立基于深度神经网络的锂电池SOH估算模型；2)对所述基于深度神经网络的锂电池SOH估算模型进行训练，得到锂电池SOH估算优化模型；3)获取待评估锂电池的近全充电过程的锂电池充电片段数据，并输入到锂电池SOH估算优化模型中，完成锂电池SOH估算。本发明提出了基于深度神经网络的SOH在线估算方法，通过随机抽样、标准化等数据预处理方式对输入输出数据进行处理，并通过训练得到最终的SOH估算模型，代入验证集输入，即可得到所对应的SOH值，实现锂电池SOH在线估算，且其估算精度较基于模型的方法提高约10％，满足车企实际应用所需达到的估算精度。

Figure 202110607933

The invention discloses an online estimation method for lithium battery SOH based on a deep neural network. The steps are: 1) establishing a lithium battery SOH estimation model based on a deep neural network; 2) training the lithium battery SOH estimation model based on a deep neural network, Obtain the lithium battery SOH estimation optimization model; 3) obtain the lithium battery charging segment data of the nearly full charging process of the lithium battery to be evaluated, and input it into the lithium battery SOH estimation optimization model to complete the lithium battery SOH estimation. The invention proposes an online SOH estimation method based on a deep neural network. The input and output data are processed by data preprocessing methods such as random sampling and standardization, and the final SOH estimation model is obtained through training, which is substituted into the input of the verification set, and the result is obtained. The corresponding SOH value can realize the online estimation of lithium battery SOH, and its estimation accuracy is about 10% higher than that of the model-based method, which meets the estimation accuracy required by the actual application of car companies.

Figure 202110607933

Description

Lithium battery SOH online estimation method based on deep neural network
Technical Field
The invention relates to the field of new energy automobile battery management, in particular to a lithium battery SOH online estimation method based on a deep neural network.
Background
Automobiles become an indispensable transportation tool in people's daily life, but with the vigorous development of the automobile industry, the problems of large consumption of petroleum resources, increasingly severe environmental pollution and the like follow. In the face of the serious problems of resource shortage and environmental pollution, new energy technology is becoming the focus of the industry. Under the strong support of national policies, the development of the pure electric vehicle is particularly rapid, however, the battery still has many technical problems to be solved as a core component of the pure electric vehicle, and technical bottlenecks still exist on accurate estimation of battery state of health (SOH), battery state of charge (SOC), and the like. In recent years, the quantity of electric vehicles increases year by year, and a large number of retired lithium ion batteries need to be treated correspondingly in the future. In order to respond to the relevant policy of the national lithium ion battery echelon utilization and enable the lithium ion battery to still play a role in other aspects after the electric automobile is retired, the high-precision estimation of the SOH value of the battery needs to be realized. In addition, the online estimation of the service life of the battery can also discover the potential safety hazard of the battery in time. Therefore, the task of breaking the technical barrier of the high-precision estimation of the SOH is not easy.
Currently, the methods commonly used for estimating the SOH of a lithium battery are roughly classified into the following three methods: 1. a constant current discharge method; 2. a model-based approach; 3. a data-driven based method. The method 1 is to fully charge the battery under laboratory conditions to accurately measure and calculate the actual capacity of the battery, and although the method has high precision and high cost, the SOH estimation is usually performed by adopting a model-based or data-driven mode.
Disclosure of Invention
The invention aims to provide an SOH (state of health) online estimation method for a lithium battery based on a deep neural network, which comprises the following steps of:
1) and establishing a lithium battery SOH estimation model based on a deep neural network.
The lithium battery SOH estimation model based on the deep neural network comprises an input layer, a plurality of hidden layers and an output layer.
The output y of the hidden layer is as follows:
Figure BDA0003094312390000011
in the formula, WjRepresenting the weight matrix from layer j-1 to layer j. bjRepresenting the bias vectors for layer j-1 through layer j. SigmajRepresenting the activation function of the j-th layer.
The output Y of the output layer is as follows:
Figure BDA0003094312390000021
in the formula, the upper label～Indicating transposition.
The activation function of the hidden layer is as follows:
σj(x)＝max(x,0) (3)
the activation function of the output layer is as follows:
σh+1(x)＝x (4)
2) and training the lithium battery SOH estimation model based on the deep neural network to obtain a lithium battery SOH estimation optimization model.
The step of training the lithium battery SOH estimation model based on the deep neural network comprises the following steps:
and 2.1) acquiring lithium battery charging fragment data and corresponding lithium battery SOH in the nearly full charging process in the T period, and respectively writing the lithium battery charging fragment data and the corresponding lithium battery SOH into a training set and a verification set.
2.2) inputting the training set into a lithium battery SOH estimation model based on a deep neural network to obtain a current weight matrix W and a bias vector b.
2.3) setting an iteration parameter thetat＝{Wt，bt}. And t is the iteration number. the initial value of t is 0.
2.4) updating the iteration times t ═ t +1, and calculating the objective function ft(θt-1) For the iteration parameter thetat-1Gradient g oftNamely:
Figure BDA0003094312390000022
wherein the objective function f is as follows:
Figure BDA0003094312390000023
in the formula, MSE (Y, Y') represents a mean square error loss function. Y is the actual value. Y' is an estimated value. n is the number of training samples.
2.5) calculating the gradient g separatelytFirst and second order moments of (a), i.e.:
mt←β1·mt-1+(1-β1)·gt (8)
Figure BDA0003094312390000024
in the formula, mtIs the first moment of the gradient. v. oftIs a gradient second moment.
Figure BDA0003094312390000025
Is the square of the gradient. Beta is a1Is the first moment attenuation coefficient. Beta is a2The second moment attenuation coefficient.
2.6) first moment m of gradienttAnd the second moment v of the gradienttAnd (3) correcting to obtain:
Figure BDA0003094312390000026
Figure BDA0003094312390000031
in the formula (I), the compound is shown in the specification,
Figure BDA0003094312390000032
respectively, the bias correction of the first moment of gradient and the second moment of gradient.
2.7) updating the iteration parameter θtAnd returns to step 2.2).
Wherein the iteration parameter thetatThe update is as follows:
Figure BDA0003094312390000033
where α is a learning rate for controlling the stride. ε is a constant.
2.8) judging the current iteration parameter thetatWhether convergence is achieved, if yes, based on the current iteration parameter thetatAnd (4) establishing a lithium battery SOH estimation optimization model, and skipping to the step 2.9), or else, entering the step 2.3).
2.9) inputting the verification set into a lithium battery SOH estimation optimization model, and verifying whether the accuracy of the output result of the lithium battery SOH estimation optimization model is greater than an accuracy threshold value PmaxIf yes, training is finished, otherwise, the step 2.1) is returned.
Judging the current iteration parameter thetatThe convergence method comprises the following steps: judging the difference value delta theta of the two adjacent iteration parameters to be thetat-θt-1≤ΔθmaxAnd if so, converging, and otherwise, not converging. Delta thetamaxIs the difference threshold.
3) And acquiring data of a nearly full-charge segment of the lithium battery to be evaluated, preprocessing the data, and inputting the data into a lithium battery SOH estimation optimization model to finish the estimation of the SOH of the lithium battery.
The lithium battery charging fragment data X in the nearly full-charging process is the lithium battery secondary battery capacity I1Charging to electric quantity I2Charging segment data of (1). (I)2-I1)/Imax100% is greater than the specific gravity threshold p. I ismaxThe maximum electric quantity of the lithium battery.
The lithium battery charging segment data comprises battery charge state, monomer voltage, total current, temperature and charging duration.
The lithium battery charging fragment data in the nearly full-charging process is standardized data with consistent dimensions.
It is worth explaining that the method firstly utilizes the characteristic that the deep neural network has strong nonlinear q-type fitting capability to establish a lithium battery SOH estimation model based on the deep neural network; and then, an improved training method based on the adaptive learning rate is introduced to train the model so as to solve the optimal weight matrix and offset vector value. By the method, the data-driven SOH model is trained, and the SOH of the lithium battery can be estimated with high precision. And finally, using the near-full charge segment which does not participate in training as a verification set, obtaining a corresponding SOH value through model estimation, and comparing the SOH value with a true value to obtain a series of errors so as to verify the effectiveness of the model.
The technical effects of the present invention are undoubted, and the present invention has the following effects:
1) the invention provides an SOH estimation model and a training method based on a deep neural network, which introduces a deep learning algorithm based on an adaptive learning rate to update network parameters, avoids the problem that the learning rate is set artificially, and sets different adaptive learning rates for different parameters; the data is preprocessed in a standardized way; and introduces a mean square error loss function as the objective function.
2) The invention provides an SOH on-line estimation method based on a deep neural network, which is characterized in that input and output data are processed in data preprocessing modes such as random sampling and standardization, a final SOH estimation model is obtained through training, and the final SOH estimation model is substituted into a verification set for input, so that a corresponding SOH value can be obtained, the SOH on-line estimation of a lithium battery is realized, the estimation precision is improved by about 10% compared with that of a model-based method, and the estimation precision required by the practical application of a vehicle enterprise is met.
3) The invention has strong industrial application potential. Because the SOH influence factors of the lithium battery are more and the mechanism is more complex, the estimation of the SOH from the mechanical angle is relatively difficult, so the method is considered to be used, the SOH of the lithium battery can be estimated with high precision by directly mapping through a neural network without considering the internal mechanism of the battery.
Drawings
FIG. 1 is a diagram of a SOH estimation model of a deep neural network;
FIG. 2 is a verification set verification effect.
Detailed Description
The present invention is further illustrated by the following examples, but it should not be construed that the scope of the above-described subject matter is limited to the following examples. Various substitutions and alterations can be made without departing from the technical idea of the invention and the scope of the invention is covered by the present invention according to the common technical knowledge and the conventional means in the field.
Example 1:
referring to fig. 1, the lithium battery SOH online estimation method based on the deep neural network includes the following steps:
1) and establishing a lithium battery SOH estimation model based on a deep neural network.
The lithium battery SOH estimation model based on the deep neural network comprises an input layer, a plurality of hidden layers and an output layer.
The output y of the hidden layer is as follows:
Figure BDA0003094312390000041
in the formula, WjRepresenting the weight matrix from layer j-1 to layer j. bjRepresenting the bias vectors for layer j-1 through layer j. SigmajRepresenting the activation function of the j-th layer.
The output Y of the output layer is as follows:
Figure BDA0003094312390000042
in the formula, the upper label～Indicating transposition.
The activation function of the hidden layer is as follows:
σj(x)＝max(x,0) (3)
the activation function of the output layer is as follows:
σh+1(x)＝x (4)
2) and training the lithium battery SOH estimation model based on the deep neural network to obtain a lithium battery SOH estimation optimization model.
The step of training the lithium battery SOH estimation model based on the deep neural network comprises the following steps:
and 2.1) acquiring lithium battery charging fragment data and corresponding lithium battery SOH in the nearly full charging process in the T period, and respectively writing the lithium battery charging fragment data and the corresponding lithium battery SOH into a training set and a verification set.
2.2) inputting the training set into a lithium battery SOH estimation model based on a deep neural network to obtain a current weight matrix W and a bias vector b.
2.3) setting an iteration parameter thetat＝{Wt，bt}. And t is the iteration number. the initial value of t is 0.
2.4) updating the iteration times t ═ t +1, and calculating the objective function ft(θt-1) For the iteration parameter thetat-1Gradient g oftNamely:
Figure BDA0003094312390000051
wherein the objective function f is as follows:
Figure BDA0003094312390000052
in the formula, MSE (Y, Y') represents a mean square error loss function. Y is the actual value. Y' is an estimated value. n is
2.5) calculating the gradient g separatelytFirst and second order moments of (a), i.e.:
mt←β1·mt-1+(1-β1)·gt (8)
Figure BDA0003094312390000053
in the formula, mtIs the first moment of the gradient. v. oftIs a gradient second moment.
Figure BDA0003094312390000054
Is the square of the gradient. Beta is a1Is the first moment attenuation coefficient. Beta is a2The second moment attenuation coefficient. And ← represents the updating of the left symbol with the right expression.
2.6) first moment m of gradienttAnd the second moment v of the gradienttAnd (3) correcting to obtain:
Figure BDA0003094312390000055
Figure BDA0003094312390000056
in the formula (I), the compound is shown in the specification,
Figure BDA0003094312390000061
respectively, the bias correction of the first moment of gradient and the second moment of gradient.
2.7) updating the iteration parameter θtAnd returns to step 2.2).
Wherein the iteration parameter thetatThe update is as follows:
Figure BDA0003094312390000062
where α is a learning rate for controlling the stride. ε is a constant.
2.8) judging the current iteration parameter thetatWhether convergence is achieved, if yes, based on the current iteration parameter thetatAnd (4) establishing a lithium battery SOH estimation optimization model, and skipping to the step 2.9), or else, entering the step 2.3).
2.9) inputting the verification set into the lithium battery SOH estimation optimization model to verify the lithium battery SOH estimation optimization modelWhether the accuracy of the output result is greater than the accuracy threshold PmaxIf yes, training is finished, otherwise, the step 2.1) is returned.
Judging the current iteration parameter thetatThe convergence method comprises the following steps: judging the difference value delta theta of the two adjacent iteration parameters to be thetat-θt-1≤ΔθmaxAnd if so, converging, and otherwise, not converging. Delta thetamaxIs the difference threshold.
3) And acquiring lithium battery charging fragment data of the lithium battery to be evaluated in the nearly full charging process, and inputting the lithium battery charging fragment data into a lithium battery SOH estimation optimization model to complete estimation of the SOH (state of health) of the lithium battery.
The lithium battery charging fragment data X in the nearly full-charging process is the lithium battery secondary battery capacity I1Charging to electric quantity I2Charging segment data of (1). (I)2-I1)/Imax100% is greater than the specific gravity threshold p. In this example, p is 80%. I ismaxThe maximum electric quantity of the lithium battery.
The lithium battery charging segment data comprises battery charge state, monomer voltage, total current, temperature and charging duration.
The lithium battery charging fragment data in the nearly full-charging process is standardized data with consistent dimensions.
Example 2:
the lithium battery SOH online estimation method based on the deep neural network comprises the following steps:
1) acquisition of a full charge fragment sample: selecting data of a near-full-charge segment with an SOC value from below 10 to above 90 as sample input X, wherein the characteristics comprise SOC, monomer voltage, total current, temperature and charging time; the SOH value at the corresponding fully charged segment is taken as the sample output Y.
2) Data preprocessing: firstly, unifying the data line number of all full-charge segments by adopting a random sampling method to ensure that the input dimensionality is consistent; converting all data of SOC, monomer voltage, total current, temperature and charging time length in each full charging process into one line of data; this data is then normalized.
3) Training a deep neural network SOH estimation model: firstly, randomly dividing all sample data into a training set and a verification set according to a certain proportion; secondly, constructing a mean square error loss function; and finally, iteratively solving all optimal weight matrixes and bias vector values theta of the model by introducing parameter updating modes (5) - (12) based on the adaptive learning rate.
4) Solving an online SOH value: and inputting the verification sample divided in the third step into the trained model, and calculating the SOH value corresponding to each full charging section on line.
5) Index statistics: the input of the calculation verification set is the average relative error, the maximum relative error, the average absolute error and the maximum absolute error between the output calculated by the model and the true value.
Example 3:
the lithium battery SOH online estimation method based on the deep neural network comprises the following steps:
1) lithium battery SOH estimation model based on deep neural network
The SOH estimation model based on the deep neural network is built by utilizing the advantage that the deep neural network has stronger fitting capability to the complex nonlinear function, and the model structure is shown in figure 1 in detail. The model takes the battery data X of the nearly fully charged segment after corresponding preprocessing as input, and obtains output Y which is the SOH value of the battery after model operation. The calculation process is as follows:
firstly, taking the processed charging data as input X, calculating by formula (1) to obtain output Y of X after passing through two hidden layers, and secondly, taking Y as the input of an output layer, obtaining output Y of the output layer by formula (2), namely the SOH value of the lithium battery at the moment.
Figure BDA0003094312390000071
Figure BDA0003094312390000072
Wherein, W1、b1、W2、b2、W3、b3Respectively indicating a weight matrix and a bias vector from an input layer to a first layer hidden layer, a weight matrix and a bias vector from the first layer hidden layer to a second layer hidden layer, and a weight matrix and a bias vector from the second layer hidden layer to an output layer; sigma1、σ2、σ3Respectively, the activation functions of two hidden layers and an output layer. Sigma1、σ2The expression (c) is shown in formula (3), σ3Expression of (4)
σ1(x)，σ2(x)＝max(x,0) (3)
σ3(x)＝x (4)
By the method, the model is built, then the model is trained by an improved training method, and the optimal weight matrix and the optimal bias vector value are obtained.
2) Training method for SOH estimation model of deep neural network lithium battery
The invention adopts adaptive motion estimation (Adam) based on an improved training algorithm of adaptive learning rate, the method replaces the traditional random gradient descent method, the traditional random gradient descent only keeps single learning rate to update the weight matrix in the training process, and Adam selects different adaptive learning rates for different parameters by calculating the first moment and the second moment of the gradient, and the Adam has high calculation efficiency and small memory requirement.
Therefore, the method is adopted as an optimization algorithm, and the specific implementation steps are as follows:
when the parameter thetatWhen the convergence is not reached, the step number is updated by the formula (5), and then the gradient of the original objective function f (theta) to the parameter theta is calculated by the formula (6).
t←t+1 (5)
Figure BDA0003094312390000081
Figure BDA0003094312390000082
Where t is the number of updated steps, the initial value is 0, θtFor the parameters to be solved, f (theta) is the objective function with the parameter theta, i.e. g, with the least mean square error loss function (7)tThe resulting gradient is derived from θ for the objective function f (θ). Y is the true value and Y' is the estimated value.
After the gradient value is obtained, the first moment of the gradient, namely the average value of the past gradient and the current gradient, is obtained through the calculation of the formula (8), so that the gradient can be smoothly and stably transited. Furthermore, in order to be able to set different adaptive learning rates for different parameters, the second moment of the gradient, i.e. the average of the square of the past gradient and the square of the current gradient, is introduced by equation (9).
mt←β1·mt-1+(1-β1)·gt (8)
Figure BDA0003094312390000083
Wherein m istIs the first moment of the gradient with an initial value of 0, vtIs a gradient second moment, the initial value is 0,
Figure BDA0003094312390000088
is the square of the gradient, beta1A first-order moment attenuation coefficient of 0.9, beta2The second-order moment attenuation coefficient is 0.999 by default.
However, because
Figure BDA0003094312390000084
Since the initial value is 0, the gradient is biased toward 0, and therefore, it is necessary to correct the first order moment and the second order moment of the gradient by equations (10) and (11), respectively, to reduce the influence of the bias.
Figure BDA0003094312390000085
Figure BDA0003094312390000086
Wherein
Figure BDA0003094312390000087
The first order moment and the second order moment are respectively used for offset correction.
Finally, the parameters are updated using equation (12). Iterating the steps until the parameter thetatAnd (6) converging.
Figure BDA0003094312390000091
Where α is the learning rate to control stride, default is 0.01, and ε is default is 10-8。
3) And acquiring lithium battery charging fragment data of the lithium battery to be evaluated in the nearly full charging process, and inputting the lithium battery charging fragment data into a lithium battery SOH estimation optimization model to complete lithium battery SOH estimation.
Example 4:
the verification experiment of the lithium battery SOH on-line estimation method based on the deep neural network comprises the following steps:
1) sample acquisition
The battery data used in this embodiment is from a certain car-enterprise company.
Firstly, writing a corresponding algorithm aiming at data in the service period of a battery and intercepting charging segment data which is approximately in a full charging process, namely battery data with SOC from below 10 to above 90 is taken as input, and the specific characteristics comprise: SOC, monomer voltage v, total current i, temperature T and charging time T. Subsequently, the SOH value at the charged segment is obtained as an output by the ampere-hour integration method (1) to (3).
Figure BDA0003094312390000092
ocv→soc (2)
SOH＝(S/(Δsoc·C0×0.01))×100 (3)
Wherein k isThe number of rows of sub-charge data; i.e. ik、tkRespectively representing the current at the k-th row and the time for which the current lasts, and the units are ampere (A) and hour (h); ocv is the cell voltage value at the resting point; Δ soc is the difference between soc at the rest point after charging (i.e. the point where the first current is 0 half an hour after the end of charging) and soc at the rest point before charging (i.e. the point where the first current is 0 before the start of charging), wherein the soc value is obtained by the cell voltage ocv through the ocv → soc curve table; c0The nominal capacity of the battery is expressed in ampere-hours (A.h).
2) Data pre-processing
Firstly, because input samples are data in the whole process of single full charge and the number of data lines in each charge is inconsistent, the number of data lines of all the input samples is required to be the same by a random sampling method to ensure the consistency of input dimensions, after the number of lines of all full charge data fragments is counted, the number of lines is determined to be uniformly divided into 300 lines according to the counting result; secondly, deforming the data structure, and changing two-dimensional matrix input into one-dimensional vector input; and finally, standardizing the input data.
3) Deep neural network SOH estimation model training
After data preprocessing, a deep neural network SOH estimation model is set up, wherein 50 neurons of an input layer, 100 neurons of a first hidden layer, 100 neurons of a second hidden layer and 1 neuron of an output layer are input. The training set and the validation set were then randomly divided in a 4:1 ratio for all sample inputs and sample outputs (2000 groups of data in total). And after the division is finished, training the built model, and iteratively solving all optimal weight matrixes and bias vector parameters of the model by using a parameter updating mode of the self-adaptive learning rate to finish the training of the model.
4) Online SOH value solution
And (4) inputting the verification set divided in the step (3) into the trained model in the step (3), and estimating the SOH value on line through model calculation.
5 index statistics
And (4) calculating the average relative error A, the maximum relative error B, the average absolute error C and the maximum absolute error D of the verification set, wherein the formulas are shown in (4) - (7), and the specific numerical values are detailed in table 1. Figure 2 shows the effect graph of the verification set
Figure BDA0003094312390000101
Figure BDA0003094312390000102
Figure BDA0003094312390000103
Figure BDA0003094312390000104
Wherein y isiIn the true value, the value of,
Figure BDA0003094312390000105
is the model estimate.
Table 1 shows the indexes
Average relative error Maximum relative error Mean absolute error Maximum absolute error
1.67％ 8.89％ 1.49 7.35
The invention discloses a lithium battery SOH online estimation method based on a deep neural network, which updates model parameters by introducing a deep learning algorithm based on a self-adaptive learning rate so as to realize SOH online estimation. Finally, the validity and correctness of the obtained model are tested through the verification set. The method does not need to consider the internal mechanism of the battery, can directly map the corresponding SOH value according to the trained neural network, and has high speed and high precision.

Claims (9)

1.基于深度神经网络的锂电池SOH在线估算方法，其特征在于，包括以下步骤：1. The lithium battery SOH online estimation method based on deep neural network is characterized in that, comprises the following steps: 1)建立所述基于深度神经网络的锂电池SOH估算模型。1) Establish the lithium battery SOH estimation model based on the deep neural network. 2)对所述基于深度神经网络的锂电池SOH估算模型进行训练，得到锂电池SOH估算优化模型；2) training the lithium battery SOH estimation model based on the deep neural network to obtain a lithium battery SOH estimation optimization model; 3)获取待评估锂电池的近全充电片段的数据，经预处理后输入到锂电池SOH估算优化模型中，完成锂电池SOH估算。3) Obtain the data of the nearly fully charged segment of the lithium battery to be evaluated, and input it into the lithium battery SOH estimation optimization model after preprocessing to complete the lithium battery SOH estimation. 2.根据权利要求1所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于：近全充电过程的锂电池充电片段数据X为锂电池从电量I1充电至电量I2的充电片段数据；(I2-I1)/Imax*100％大于比重阈值p；Imax为锂电池最大电量。2. the lithium battery SOH online estimation method based on deep neural network according to claim 1, it is characterized in that: the lithium battery charging segment data X of the near full charging process is the charging of the lithium battery from the electric power I 1 to the electric power I 2 Fragment data; (I 2 -I 1 )/I max *100% is greater than the specific gravity threshold p; I max is the maximum power of the lithium battery. 3.根据权利要求1所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于：锂电池充电片段数据包括电池荷电状态、单体电压、总电流、温度、充电时长。3. The method for online estimation of lithium battery SOH based on a deep neural network according to claim 1, wherein the lithium battery charging segment data includes battery state of charge, cell voltage, total current, temperature, and charging duration. 4.根据权利要求1所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，所述基于深度神经网络的锂电池SOH估算模型包括输入层、若干隐藏层和输出层。4 . The method for online estimation of lithium battery SOH based on deep neural network according to claim 1 , wherein the lithium battery SOH estimation model based on deep neural network comprises an input layer, several hidden layers and an output layer. 5 . 5.根据权利要求4所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，所述隐藏层的输出y如下所示：5. the lithium battery SOH online estimation method based on deep neural network according to claim 4, is characterized in that, the output y of described hidden layer is as follows:
Figure FDA0003094312380000011
Figure FDA0003094312380000011
 式中，Wj表示第j-1层到第j层的权值矩阵；bj表示第j-1层到第j层的偏置向量；σj表示第j层的激活函数；上标～表示转置；In the formula, W j represents the weight matrix from layer j-1 to layer j; b j represents the bias vector from layer j-1 to layer j; σ j represents the activation function of layer j; the superscript ~ means transpose; 所述输出层的输出Y如下所示：The output Y of the output layer is as follows:
Figure FDA0003094312380000012
Figure FDA0003094312380000012
 式中，上标～表示转置。In the formula, the superscript ~ represents transposition. 6.根据权利要求4所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，隐藏层的激活函数如下所示：6. the lithium battery SOH online estimation method based on deep neural network according to claim 4, is characterized in that, the activation function of hidden layer is as follows: σj(x)＝max(x,0) (3)σ j (x)=max(x,0) (3) 输出层的激活函数如下所示：The activation function of the output layer is as follows: σh+1(x)＝x (4)σ h+1 (x)=x (4) 7.根据权利要求1所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，对所述基于深度神经网络的锂电池SOH估算模型进行训练的步骤包括：7. The lithium battery SOH online estimation method based on a deep neural network according to claim 1, wherein the step of training the lithium battery SOH estimation model based on the deep neural network comprises: 1)获取T时段的近全充电过程的锂电池充电片段数据和对应的锂电池SOH，并分别写入训练集和验证集中；1) Obtain the lithium battery charging segment data and the corresponding lithium battery SOH of the nearly full charging process in the T period, and write them into the training set and the verification set respectively; 2)将训练集输入到基于深度神经网络的锂电池SOH估算模型中，得到当前权值矩阵W和偏置向量b；2) Input the training set into the lithium battery SOH estimation model based on the deep neural network, and obtain the current weight matrix W and bias vector b; 3)设定迭代参数θt＝{Wt，bt}；t为迭代次数；t初始值为0；3) Set the iteration parameter θ t ={W t , b t }; t is the number of iterations; the initial value of t is 0; 4)更新迭代次数t＝t+1，并计算目标函数ft(θt-1)对迭代参数θt-1的梯度gt，即：4) Update the number of iterations t=t+1, and calculate the gradient g t of the objective function f t (θ t-1 ) to the iteration parameter θ t-1 , namely:
Figure FDA0003094312380000021
Figure FDA0003094312380000021
 其中，目标函数f如下所示：Among them, the objective function f is as follows:
Figure FDA0003094312380000022
Figure FDA0003094312380000022
 式中，MSE(Y,Y')表示均方误差损失函数；Y为实际值；Y'为估算值；n为训练样本个数；In the formula, MSE(Y, Y') represents the mean square error loss function; Y is the actual value; Y' is the estimated value; n is the number of training samples; 5)分别计算梯度gt的一阶矩和二阶矩，即：5) Calculate the first-order moment and second-order moment of the gradient g t respectively, namely: mt←β1·mt-1+(1-β1)·gt (8)m t ←β 1 ·m t-1 +(1-β 1 )·g t (8)
Figure FDA0003094312380000023
Figure FDA0003094312380000023
 式中，mt为梯度一阶矩；vt为梯度二阶矩；
Figure FDA0003094312380000024
为梯度的平方；β1为一阶矩衰减系数；β2为二阶矩衰减系数；In the formula, m t is the first-order moment of the gradient; v t is the second-order moment of the gradient;
Figure FDA0003094312380000024
is the square of the gradient; β 1 is the first-order moment attenuation coefficient; β 2 is the second-order moment attenuation coefficient; 6)对梯度一阶矩mt和梯度二阶矩vt进行校正，得到：6) Correct the first-order moment m t of the gradient and the second-order moment v t of the gradient to obtain:
Figure FDA0003094312380000025
Figure FDA0003094312380000025
Figure FDA0003094312380000026
Figure FDA0003094312380000026
 式中，
Figure FDA0003094312380000027
分别表示梯度一阶矩、梯度二阶矩的偏置校正；In the formula,
Figure FDA0003094312380000027
respectively represent the bias correction of the first-order moment of gradient and the second-order moment of gradient; 7)更新迭代参数θt；7) Update the iteration parameter θ t ; 其中，迭代参数θt更新如下：Among them, the iteration parameter θ t is updated as follows:
Figure FDA0003094312380000028
Figure FDA0003094312380000028
 式中，α为用以控制步幅的学习率；ε为常数。In the formula, α is the learning rate used to control the stride; ε is a constant. 8)判断当前迭代参数θt是否收敛，若是，则基于当前迭代参数θt建立锂电池SOH估算优化模型，并跳转至步骤9)，否则进入步骤3)；8) Judging whether the current iteration parameter θ t converges, if so, establish an optimization model for lithium battery SOH estimation based on the current iteration parameter θ t , and jump to step 9), otherwise enter step 3); 9)将验证集输入到锂电池SOH估算优化模型中，验证锂电池SOH估算优化模型的输出结果准确率是否大于准确率阈值Pmax，若是，则完成训练，否则，返回步骤1)。9) Input the verification set into the lithium battery SOH estimation optimization model, and verify whether the output result accuracy of the lithium battery SOH estimation optimization model is greater than the accuracy threshold P max , if so, complete the training, otherwise, return to step 1). 8.根据权利要求7所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，判断当前迭代参数θt是否收敛的方法为：判断相邻两次迭代参数的差值Δθ＝θt-θt-1≤Δθmax是否成立，若是，则收敛，反之，不收敛；Δθmax为差值阈值。8. The method for on-line estimation of lithium battery SOH based on deep neural network according to claim 7, wherein the method for judging whether the current iteration parameter θ t converges is: judging the difference Δθ=θ between two adjacent iteration parameters Whether t -θ t-1 ≤Δθ max is established, if so, it converges, otherwise, it does not converge; Δθ max is the difference threshold. 9.根据权利要求1或7所述的基于深度神经网络的锂电池SOH在线估算方法，其特征在于，近全充电过程的锂电池充电片段数据为维度一致的标准化数据。9 . The online method for estimating lithium battery SOH based on a deep neural network according to claim 1 or 7 , wherein the charging segment data of the lithium battery in the nearly full charging process is standardized data with consistent dimensions. 10 .
CN202110607933.7A 2021-06-01 2021-06-01 Lithium battery SOH online estimation method based on deep neural network Pending CN113406503A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110607933.7A CN113406503A (en) 2021-06-01 2021-06-01 Lithium battery SOH online estimation method based on deep neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110607933.7A CN113406503A (en) 2021-06-01 2021-06-01 Lithium battery SOH online estimation method based on deep neural network

Publications (1)

Publication Number Publication Date
CN113406503A true CN113406503A (en) 2021-09-17

Family

ID=77675666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110607933.7A Pending CN113406503A (en) 2021-06-01 2021-06-01 Lithium battery SOH online estimation method based on deep neural network

Country Status (1)

Country Link
CN (1) CN113406503A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113721151A (en) * 2021-11-03 2021-11-30 杭州宇谷科技有限公司 Battery capacity estimation model and method based on double-tower deep learning network
CN114925829A (en) * 2022-07-18 2022-08-19 山东海量信息技术研究院 Neural network training method and device, electronic equipment and storage medium
DE102021214154A1 (en) 2021-12-10 2023-06-15 Robert Bosch Gesellschaft mit beschränkter Haftung Computer-implemented method for providing an aging state model for determining a current and predicted aging state of an electrical energy storage device using machine learning methods
CN119249913A (en) * 2024-12-04 2025-01-03 福州福光电子有限公司 A lithium battery SOH estimation model and its construction system and application method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109143105A (en) * 2018-09-05 2019-01-04 上海海事大学 A kind of state-of-charge calculation method of lithium ion battery of electric automobile
CN110194172A (en) * 2019-06-28 2019-09-03 重庆大学 Based on enhanced neural network plug-in hybrid passenger car energy management method
CN110659722A (en) * 2019-08-30 2020-01-07 江苏大学 AdaBoost-CBP neural network-based electric vehicle lithium ion battery health state estimation method
CN110850298A (en) * 2019-10-29 2020-02-28 上海交通大学 Data-driven SOH estimation method and system for lithium batteries
CN112067998A (en) * 2020-09-10 2020-12-11 昆明理工大学 Lithium ion battery state of charge estimation method based on deep neural network
CN112379274A (en) * 2020-11-16 2021-02-19 河南科技大学 Method for predicting residual life of power battery

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109143105A (en) * 2018-09-05 2019-01-04 上海海事大学 A kind of state-of-charge calculation method of lithium ion battery of electric automobile
CN110194172A (en) * 2019-06-28 2019-09-03 重庆大学 Based on enhanced neural network plug-in hybrid passenger car energy management method
CN110659722A (en) * 2019-08-30 2020-01-07 江苏大学 AdaBoost-CBP neural network-based electric vehicle lithium ion battery health state estimation method
CN110850298A (en) * 2019-10-29 2020-02-28 上海交通大学 Data-driven SOH estimation method and system for lithium batteries
CN112067998A (en) * 2020-09-10 2020-12-11 昆明理工大学 Lithium ion battery state of charge estimation method based on deep neural network
CN112379274A (en) * 2020-11-16 2021-02-19 河南科技大学 Method for predicting residual life of power battery

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘志明: "基于LSTM-RNN的动力电池SOH估计算法研究", 中国优秀硕士学位论文全文数据库 (基础科学辑), 30 April 2021 (2021-04-30), pages 042 - 544 *
李超然 等: "基于卷积神经网络的锂离子电池SOH估算", 电工技术学报, vol. 35, no. 19, 30 October 2020 (2020-10-30), pages 4106 - 4119 *
胡晨 等: "基于深度学习的铅酸电池健康状态估计", 电池, vol. 51, no. 1, 26 February 2021 (2021-02-26), pages 63 - 67 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113721151A (en) * 2021-11-03 2021-11-30 杭州宇谷科技有限公司 Battery capacity estimation model and method based on double-tower deep learning network
DE102021214154A1 (en) 2021-12-10 2023-06-15 Robert Bosch Gesellschaft mit beschränkter Haftung Computer-implemented method for providing an aging state model for determining a current and predicted aging state of an electrical energy storage device using machine learning methods
CN114925829A (en) * 2022-07-18 2022-08-19 山东海量信息技术研究院 Neural network training method and device, electronic equipment and storage medium
CN119249913A (en) * 2024-12-04 2025-01-03 福州福光电子有限公司 A lithium battery SOH estimation model and its construction system and application method

Similar Documents

Publication Publication Date Title
Shu et al. Stage of charge estimation of lithium-ion battery packs based on improved cubature Kalman filter with long short-term memory model
Duong et al. Heuristic Kalman optimized particle filter for remaining useful life prediction of lithium-ion battery
CN113740736B (en) A deep network adaptive SOH estimation method for electric vehicle lithium batteries
Hannan et al. Neural network approach for estimating state of charge of lithium-ion battery using backtracking search algorithm
CN110888059B (en) Charge state estimation algorithm based on improved random forest combined volume Kalman
CN113406503A (en) Lithium battery SOH online estimation method based on deep neural network
CN106055775B (en) A kind of service life of secondary cell prediction technique that particle filter is combined with mechanism model
CN108732508B (en) A real-time estimation method of lithium-ion battery capacity
US20230349977A1 (en) Method and apparatus for estimating state of health of battery
Wang et al. Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile
CN114487890B (en) A lithium battery health state estimation method based on improved long short-term memory neural network
CN114814592B (en) Lithium battery health state estimation and residual service life prediction method and equipment
CN112630659A (en) Lithium battery SOC estimation method based on improved BP-EKF algorithm
CN103018673A (en) Method for predicating life of aerospace Ni-Cd storage battery based on improved dynamic wavelet neural network
CN101894185A (en) A Lifetime Prediction Method for Small Sample Data Objects Based on Dynamic Bipolar MPNN
CN115856678A (en) A method for estimating state of health of lithium ion battery
CN117129898A (en) Health status estimation method and system based on impedance spectrum data and R-GPR
CN112163372A (en) SOC estimation method of power battery
CN113702836B (en) A method for estimating the state of charge of lithium-ion batteries based on EMD-GRU
Lin et al. Algorithm of BPNN‐UKF based on a fusion model for SOC estimation in lithium‐ion batteries
CN118465591A (en) A method for estimating the health status of lithium-ion batteries based on parallel hybrid neural networks
CN115146723A (en) Electrochemical model parameter identification method based on deep learning and heuristic algorithm
Bak et al. Accurate estimation of battery SOH and RUL based on a progressive lstm with a time compensated entropy index
Liu et al. Online state of charge estimation for lithium‐ion battery by combining incremental autoregressive and moving average modeling with adaptive H‐infinity filter
Xu et al. State-of-Charge Estimation of Lithium-Ion Batteries Based on EKF Integrated With PSO-LSTM for Electric Vehicles

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