CN113094989A - Unmanned aerial vehicle battery life prediction method based on random configuration network - Google Patents

Unmanned aerial vehicle battery life prediction method based on random configuration network Download PDF

Info

Publication number
CN113094989A
CN113094989A CN202110371138.2A CN202110371138A CN113094989A CN 113094989 A CN113094989 A CN 113094989A CN 202110371138 A CN202110371138 A CN 202110371138A CN 113094989 A CN113094989 A CN 113094989A
Authority
CN
China
Prior art keywords
representing
network
layer node
hidden
error
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.)
Granted
Application number
CN202110371138.2A
Other languages
Chinese (zh)
Other versions
CN113094989B (en
Inventor
李少波
廖子豪
周鹏
张安思
李传江
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.)
Guizhou University
Original Assignee
Guizhou 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 Guizhou University filed Critical Guizhou University
Priority to CN202110371138.2A priority Critical patent/CN113094989B/en
Publication of CN113094989A publication Critical patent/CN113094989A/en
Application granted granted Critical
Publication of CN113094989B publication Critical patent/CN113094989B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Secondary Cells (AREA)
  • Tests Of Electric Status Of Batteries (AREA)

Abstract

The invention discloses a method for predicting the service life of an unmanned aerial vehicle battery based on a random configuration network, which comprises the following steps: the capacity of a lithium ion battery for the unmanned aerial vehicle is used as a direct health factor, the discharge voltage of the battery is used as an indirect health factor, model training and parameter debugging are carried out by adopting a random configuration network, and a service life prediction model of the lithium ion battery is obtained for prediction. The problems of low precision, large training data requirement and the like in the existing data-driven prediction method are effectively avoided, the characteristics of strong SCN autonomy, high convergence speed, low network cost and the like are fully exerted, compared with other neural networks, the RMSE value of the SCN is minimum, the training loss is lower, the network fitting effect is better, and the method is an effective RUL prediction algorithm for the lithium battery.

Description

Unmanned aerial vehicle battery life prediction method based on random configuration network
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle battery health management, and relates to an unmanned aerial vehicle battery life prediction method based on a random configuration network.
Background
The lithium ion battery generates current by depending on the flow of internal lithium ions, and has the advantages of high power density, wide working temperature range, long service life and the like. Although improvement and optimization are performed for many years, performance degradation of the lithium ion battery still occurs after long-term use of the lithium ion battery, so that the service Life and the use safety of the lithium ion battery are affected, and even serious property, personnel and other losses are caused, so that it is very necessary to predict the Remaining service Life (Remaining Useful Life, RUL) of the lithium ion battery, so as to realize health management, avoid various operations which damage the battery Life, and reasonably manage and use the lithium ion battery safely and effectively.
The lithium ion Battery internal system is a dynamic system which changes along with time, and the development of the RUL of the Battery is systematically summarized by Hu Xiaoson, Xu Le, Lin Xiao ke, et al Battery Life software sciences [ J ]. Cross ref (2): 310-. The RUL prediction method of the battery based on the model is to establish a battery life degradation mathematical model, such as a physical model or an electrochemical equation of the internal structure of the battery, by using professional related knowledge and experience, and to deeply discuss the mathematical mechanism and the degradation rule in the internal structure of the battery, so that the RUL prediction method has the advantages of stable performance, high prediction precision and the like, but has the defects that the RUL prediction method needs to know the accurate electrochemical and battery physical action equations and is not suitable for off-line detection. The battery RUL prediction method based on data is characterized in that relevant failure data of battery life degradation are collected, potential relation between implicit data information and data is mined by utilizing an algorithm, an approximation model of battery life degradation is built under the support of technologies such as statistical analysis and the like, and the model is extrapolated so as to realize prediction of the battery RUL. The fusion-based battery RUL prediction method fully exerts the advantages of various methods, develops the advantages of various methods, better extracts and uses information and data characteristics in data by fusing and integrating models and algorithms, algorithms and algorithms to obtain more excellent network model robustness and prediction accuracy, but the fusion-based method has the problems of high consumption, large data demand and the like and limits the application range and generalization capability of the fusion-based battery RUL prediction method.
The biggest advantage of the data-driven prediction algorithm is that the prediction algorithm can be completed only by a certain amount of degradation data without knowing an accurate model of the battery, so that the data-driven prediction method of the battery RUL is more popular and widely applied, and is slowly the mainstream method for predicting the service life of the battery. The data-driven battery RUL prediction method mainly comprises an artificial neural network, a support vector machine, support vector regression, particle filtering and the like, wherein the artificial neural network aims at simulating the operation of a human brain nervous system, and is greatly different in the battery life prediction problem due to the advantages of strong nonlinear processing capability, self-adaptability, self-learning capability and the like, but the problems of slow training, excessive resource consumption, weak generalization and the like caused by the artificial neural network are slowly shown in the use process, so that the problems become a difficulty which hinders the development of the artificial neural network in the lithium ion battery life prediction direction, and the problems are gradually solved when incremental learning appears.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the unmanned aerial vehicle battery life prediction method based on the random configuration network is provided to solve the technical problems in the prior art.
The technical scheme adopted by the invention is as follows: a unmanned aerial vehicle battery life prediction method based on a random configuration network comprises the following steps: the capacity of a lithium ion battery for the unmanned aerial vehicle is used as a direct health factor, the discharge voltage of the battery is used as an indirect health factor, a random configuration network is adopted to carry out model training and parameter debugging, and a life prediction model of the lithium ion battery is obtained for prediction.
The random configuration network algorithm comprises the following specific steps:
(1) for a given objective function
Figure BDA0003009346830000031
Suppose that a congestion has been establishedA single layer feedforward network with L-1 hidden nodes is shown in (1).
Figure BDA0003009346830000032
Wherein f isL-1(x) Represents a hypothetical single-layer feedforward network with L-1 hidden nodes, betajRepresenting hidden layer output weights, gjIt is shown that the activation function is,
Figure BDA0003009346830000033
input weights representing hidden layers, bjAn input bias representing a hidden layer;
error is shown as (2)
eL-1＝f-fL-1＝[eL-1,1,…,eL-1,m] (2)
Wherein eL-1Representing the current error, f represents the network value currently having L nodes, fL-1Network values representing L-1 nodes of the last stage of swimming, eL-1,1Indicating the error of the L-1 hidden layer node to the first output layer node, …, eL-1,mThe error of the L-1 hidden layer node to the mth output layer node;
if the error eL-1If the preset error limit is not reached, the algorithm aims to add beta by an incremental learning methodL,gL(wherein g isLHas a weight of wLOffset is bL) Update fL＝fL-1+βLgLUp to an error eL-1Reaching a given error limit;
(2) suppose for
Figure BDA0003009346830000034
Are all 0 < | g | < bgGiven 0 < r < 1 and a sequence of non-negative real numbers [ mu ]LIn which μLSatisfy the requirement of
Figure BDA0003009346830000035
And muLLess than or equal to (1-r). Hidden nodeL ═ 1,2,. denotes:
Figure BDA0003009346830000036
wherein deltaLRepresents the value of node L, δL,qA value representing the q output layer node corresponding to the L hidden layer node, r is a self-set numerical value, muLIs a sequence of non-negative real numbers, eL-1,qRepresenting the error of the qth output layer node corresponding to the L-1 hidden layer node, | | | | | represents the norm calculation;
if the generated random basis function gL satisfies the formula (4)
Figure BDA0003009346830000041
Wherein eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting random basis functions, bgRepresenting the bias, δ, of the random basis functionL,qA value representing that the lth hidden layer node corresponds to the qth output layer node;
and the output weight is represented by formula (5)
Figure BDA0003009346830000042
Wherein beta isL,qRepresenting the output weight, eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
if the calculation is obtained, the conclusion can be drawn
Figure BDA0003009346830000043
Wherein:
Figure BDA0003009346830000044
thereby deriving an approximator with strong generalization.
Unlike other methods of maximizing the objective function, the supervision mechanism in equation (4) works by computing the optimal weight wLAnd bias bLObtaining a suitable new node, thereby further achieving the mathematical condition satisfying the formula (7):
<eL-1,gL>2/||gL||2 (7)
wherein eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
obvious type (8)
βL＝[βL,1,...,βL,m]T (8)
Wherein beta isLRepresenting the output weight, betaL,1Output weights …, β representing the Lth hidden layer node corresponding to the 1 st output layer nodeL,mRepresenting the output weight of the Lth hidden layer node corresponding to the mth output layer node;
analysis by the formula (9)
Figure BDA0003009346830000051
Wherein beta isL,qRepresenting output weights representing the q-th output layer node corresponding to the L-th hidden layer node, eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
the formula (9) is analyzed and evaluated, and is kept constant in the network for adding further nodes. However, this approach may result in slow convergence of the construction process. Therefore, the calculation scheme of the output weight is reconsidered, i.e. g is calculated according to (4)j(j ═ 1, 2.. times, L), β is calculated by minimizing the global residual1,β2,...,βLThe value of (c).
The establishment of the random configuration network algorithm is divided into two steps: 1) configuration of hidden node parameters: randomly assigning input weights and deviations to satisfy equation (4); then generating a new hidden node and adding the new hidden node into the current learner model; 2) calculating an output weight: the system of linear equations is solved by using a least squares method or a regularized version thereof.
The random configuration network algorithm adopts a sigmoid function as a hidden node activation function, wherein the parameter Y is { lambda ═ lambda1:Δλ:λmaxFor the self-adaptive determination of the range of random parameters w and b, selecting a desired error margin epsilon or a preset maximum number L of hidden nodesmaxTo terminate the algorithm, the maximum number of hidden nodes LmaxDetermined using single variable experiments.
The randomly configured network takes the time-varying value of r, in which case r needs to be set very close to 1 (where the value of r is 0 < r < 1, r is an uncertain value, and needs to be adjusted in real time according to the use condition of the algorithm, and the meaning of very close to 1 is similar to the values of 0.99999, 0.99999999 and 0.9999999999999), so that the formula (10) approaches zero, and xi is made as much as possibleL≥0：
Figure BDA0003009346830000052
When r is set to be close to 1, the ratio of e to the equation (11) becomes largerL-1 2Much smaller:
δL＝(1-r-μL)eL-1 2。 (11)
the unmanned aerial vehicle battery life prediction method based on the random configuration network further comprises a reliability analysis method for selecting health factors, wherein the reliability analysis method for selecting the health factors adopts grey correlation degree analysis, and the specific method comprises the following steps: the method comprises the following steps of setting n influencing elements in a gray system, setting an important element X, knowing that other n-1 elements have influence on X in different degrees, calculating the influence degree of the other n-1 elements on X by using multi-element statistical analysis, calculating a GRA value between two data elements by using the following formula, wherein the higher the tightness degree of the two elements is, the higher the GRA value is:
Figure BDA0003009346830000061
xi in the formula (12)i(k) The calculated gray correlation coefficient of the kth influence element sequence is y (k), and the calculated gray correlation coefficient is a reference element sequence, namely a battery capacity sequence X; x is the number ofi(k) Comparing element sequences, namely n-1 discharge voltage sequences; rho is a self-defined resolution coefficient (generally 0.6); and finally, calculating the average value of the discharge voltage sequence according to a formula (13) to obtain a grey correlation value of the discharge voltage to the battery capacity:
Figure BDA0003009346830000062
wherein gamma isiRepresenting grey correlation value, ξi(k) Representing the correlation coefficient of element k of the total n elements.
The random configuration network training data uses the root mean square error value as the performance evaluation label of the random configuration network, the calculation of the root mean square error value is as the formula (14), wherein
Figure BDA0003009346830000063
And yiPredicted capacity and real capacity, respectively:
Figure BDA0003009346830000064
training data requires removing the first M cycles and the last N cycles of data, and training the randomly configured network with the middle L cycles of data.
The invention has the beneficial effects that: compared with the prior art, the method can effectively solve the problems of low precision, large training data requirement and the like in the conventional data-driven prediction method, fully exerts the characteristics of strong SCN autonomy, high convergence speed, low network cost and the like, has the minimum RMSE value of SCN compared with other neural networks, has lower training loss and better network fitting effect, and is an effective RUL prediction algorithm for the lithium battery.
Drawings
FIG. 1 is a graph of battery voltage versus capacity fade images;
FIG. 2 is a graph of a 100 cycle data fit to a training set;
FIG. 3 is a graph of a 168 cycle data fit to a training set;
FIG. 4 is a graph of a comparison of network test fit images for a training set of 100 and 168 cycles;
fig. 5 is a comparative experimental plot of single variables of γ;
FIG. 6 is a fitting graph of SCN-based battery life prediction;
FIG. 7 is a graph of training RMSE attenuation
FIG. 8 is a training fit graph
FIG. 9 is a graph of a control experiment of SCN and various artificial neural networks.
Detailed Description
The invention is further described with reference to the accompanying drawings and specific embodiments.
The Stochastic Configuration Networks (SCN) is a neural network adopting an incremental learning mode, and hidden nodes are added incrementally and inequalities are used to constrain parameters and weights of the Stochastic Configuration nodes, so that compared with neural networks such as CNN and ANN, the neural network has the advantages of strong network generalization, simple structure, strong real-time performance, fast training and the like. Therefore, aiming at the problems of the neural network in the battery life prediction, the invention takes the battery capacity as a direct health factor and the battery discharge voltage as an indirect health factor, and carries out model training and parameter debugging on SCN by using an NASA lithium ion battery data set to carry out a life prediction experiment of the lithium ion battery; finally, various neural networks such as FNN, CNN, LSTM and the like are compared with the method for verification, the usability and the superiority of the method are proved, scientific basis is provided for the accurate application and popularization of a random configuration algorithm in the battery life prediction, and scientific guarantee is provided for the safety application of the lithium ion battery in various fields such as aerospace, electronic equipment, automobiles and the like.
Example 1: a unmanned aerial vehicle battery life prediction method based on a random configuration network comprises the following steps: the capacity of a lithium ion battery for the unmanned aerial vehicle is used as a direct health factor, the discharge voltage of the battery is used as an indirect health factor, and a random configuration network is adopted to carry out model training and parameter debugging, so that the service life of the lithium ion battery is predicted.
The random configuration network algorithm comprises the following specific steps:
(1) for a given objective function
Figure BDA0003009346830000081
Assume that a single-layer feedforward network with L-1 hidden nodes has been established, as shown in (1).
Figure BDA0003009346830000082
Error is shown as (2)
eL-1＝f-fL-1＝[eL-1,1,…,eL-1,m] (2)
If the error eL-1If the preset error limit is not reached, the algorithm aims to add beta by an incremental learning methodL,gL(wherein g isLHas a weight of wLOffset is bL) Update fL＝fL-1+βLgLUp to an error eL-1Reaching a given error limit;
(2) suppose for
Figure BDA0003009346830000083
Are all 0 < | g | < bgGiven 0 < r < 1 and a sequence of non-negative real numbers [ mu ]LIn which μLSatisfy the requirement of
Figure BDA0003009346830000084
And muLLess than or equal to (1-r). Hidden node L ═ 1,2,. is denoted as:
Figure BDA0003009346830000085
if the generated random basis function gL satisfies the formula (4)
Figure BDA0003009346830000086
And the output weight is represented by formula (5)
Figure BDA0003009346830000091
If the calculation is obtained, the conclusion can be drawn
Figure BDA0003009346830000092
Wherein:
Figure BDA0003009346830000093
thereby deriving an approximator with strong generalization.
Unlike other methods of maximizing the objective function, the supervision mechanism in equation (4) works by computing the optimal weight wLAnd bias bLObtaining a suitable new node, thereby further achieving the mathematical condition satisfying the formula (7):
<eL-1,gL〉2/||gL||2 (7)
obvious type (8)
βL＝[βL,1,...,βL,m]T (8)
By passing
Figure BDA0003009346830000094
The formula (9) is analyzed and evaluated, and is kept constant in the network for adding further nodes. However, this approach may result in slow convergence of the construction process. Thus, make a new examinationCalculation scheme taking into account output weight, i.e. calculating g according to (4)j(j ═ 1, 2.. times, L), β is calculated by minimizing the global residual1,β2,...,βLThe value of (c).
The establishment of the random configuration network algorithm is divided into two steps: 1) configuration of hidden node parameters: randomly assigning input weights and deviations to satisfy equation (4); then generating a new hidden node and adding the new hidden node into the current learner model; 2) calculating an output weight: the system of linear equations is solved by using a least squares method or a regularized version thereof.
The random configuration network algorithm adopts a sigmoid function as a hidden node activation function, wherein the parameter Y is { lambda ═ lambda1:Δλ:λmaxFor the self-adaptive determination of the range of random parameters w and b, selecting a desired error margin epsilon or a preset maximum number L of hidden nodesmaxTo terminate the algorithm, the maximum number of hidden nodes LmaxDetermined using single variable experiments.
The randomly configured network takes a time-varying value of r, in which case r needs to be set very close to 1 to get equation (10) to approach zero, so that ξ is made as much as possibleL≥0：
Figure BDA0003009346830000101
When r is set to be close to 1, the ratio of e to the equation (11) becomes largerL-1 2Much smaller:
δL＝(1-r-μL)eL-1 2。 (11)
the unmanned aerial vehicle battery life prediction method based on the random configuration network further comprises a reliability analysis method for selecting health factors, wherein the reliability analysis method for selecting the health factors adopts grey correlation degree analysis, and the specific method comprises the following steps: the method comprises the following steps of setting n influencing elements in a gray system, setting an important element X, knowing that other n-1 elements have influence on X in different degrees, calculating the influence degree of the other n-1 elements on X by using multi-element statistical analysis, calculating a GRA value between two data elements by using the following formula, wherein the higher the tightness degree of the two elements is, the higher the GRA value is:
Figure BDA0003009346830000102
xi in the formula (12)i(k) The calculated gray correlation coefficient of the kth influence element sequence is y (k), and the calculated gray correlation coefficient is a reference element sequence, namely a battery capacity sequence X; x is the number ofi(k) Comparing element sequences, namely n-1 discharge voltage sequences; rho is a self-defined resolution coefficient (generally 0.6); and finally, calculating the average value of the discharge voltage sequence according to a formula (13) to obtain a grey correlation value of the discharge voltage to the battery capacity:
Figure BDA0003009346830000103
the random configuration network training data uses the root mean square error value as the performance evaluation label of the random configuration network, the calculation of the root mean square error value is as the formula (14), wherein
Figure BDA0003009346830000104
And yiPredicted capacity and real capacity, respectively:
Figure BDA0003009346830000111
training data requires removing the first M cycles and the last N cycles of data, and training the randomly configured network with the middle L cycles of data.
The method takes the battery capacity as a direct health factor and the battery discharge voltage as an indirect health factor, distributes random parameters through inequality constraint, adaptively selects the range of the random parameters, and establishes a prediction model of the residual life of the lithium battery; the prediction model was trained using the NASA battery dataset.
To illustrate the effects of the present invention, the following simulations were performed:
selecting an experimental data set: data of three batteries B0005, B0006 and B0007 in a NASA battery data set PCoE databases are used as input data of the SCN to carry out a cross validation experiment, a discharge voltage data sequence and a battery capacity data sequence of one battery are used for training the SCN, and discharge voltage data of the other two batteries are respectively used for predicting the self capacity, so that the residual effective life of the lithium ion battery is predicted. The PCoE data set carries out charging and discharging treatment on the battery at different temperatures, records data such as charging and discharging voltage, current, temperature, impedance and the like of the battery, is a good data set for a data driving algorithm, and the specific information of NASA battery data is listed in Table 1.
TABLE 1 NASA Battery data
Figure BDA0003009346830000112
The selection of the network parameters comprises the selection of health factors, training data and training parameters:
(1) health factors: the battery discharge voltage is selected as an indirect health factor, the battery capacity is used as a health factor, the battery discharge voltage is used as network input data, a data-driven battery capacity prediction model is established, and then the battery capacity is predicted and the health state of the lithium ion battery is evaluated. And Grey correlation Analysis (GRA) was used to prove the reliability of the health factor selection. The grey relevance analysis is used for calculating the influence degree of other elements in the system on a certain element. Assuming that there are n influencing elements in a gray system and an important element X, knowing that other n-1 elements all have different degrees of influence on X, the degree of influence of other n-1 elements on X can be calculated by using multi-element statistical analysis. The GRA value between two data elements can be calculated using equation (12), with the higher the closeness of the two elements, the higher the GRA value that is calculated. Xi in equation (12)i(k) For the calculated grey correlation coefficient of the kth influencing element sequence, y (k) is the reference element sequence, i.e. the above mentioned element sequence X of interest, in the present invention the battery capacity sequence; x is the number ofi(k) For comparison of the element sequences, i.e. the N-1 other element sequences mentioned above, in the present case the discharge voltage sequences; ρ is the custom resolution coefficient (typically 0.6). And finally, calculating the average value of the discharge voltage sequence according to a formula (13) to obtain a grey correlation value of the discharge voltage to the battery capacity.
Fig. 1 is a voltage vol and capacity cap fade contrast image of battery B0007 after pretreatment. The relevance of the two system elements can be more intuitively observed according to the discharge voltage and the attenuation image of the battery capacity.
(2) Training data: Root-Mean-Square Error (RMSE) values were chosen as performance evaluation markers for the SCNs used, each RMSE value being the Mean of 20 experiments. The RMSE is calculated as shown in formula (14), wherein
Figure BDA0003009346830000121
And yiPredicted capacity and real capacity, respectively; considering the unstable voltage condition of the lithium ion battery caused by chemical reaction at the beginning and the end of charging and discharging, comparing 168 times of cycle data of the battery, we remove the first 30 cycles and the end 38 cycles of the data, and train the SCN with the middle 100 times of cycle data. The following are the resulting network training RMSE, training set fitted images and test set fitted image comparisons, where the network experiment used a combination of B0005 cells as the training set and B0007 cells as the test set.
TABLE 2 network RMSE values
Number of data cycles RMSE
100 times (twice) 0.0192
168 times (one hour) 0.0495
Comparing the 100-time cycle data with the 168-time cycle data to respectively make a test fitting image of a network training data set, and the RMSE mean value in table 2, it can be seen that removing the first 30-time cycle and the last 38-time cycle of the voltage data can effectively reduce the influence of unstable voltage data on network training, thereby enhancing the network training effect, and therefore, the 100-time cycle data of the battery discharge voltage, which removes the first 30-time cycle and the last 38-time cycle, is finally adopted as the training input data of the SCN.
(3) Training parameters: after the training set data volume is determined, next, a battery B0005 is used as a training collector battery B0007 as a test set, and a single variable experiment is used for finding out the optimal LmaxI.e. the maximum number of nodes of the hidden layer. As can be seen from Table 3, the network training effect is enhanced with the increase of the maximum node number of the hidden layer, where the maximum node number is LmaxThe network training RMSE is 0.0192 at 100, and the network fitting effect is the best at this moment. The article also sets the node number to 200, 500 and 1000 respectively to carry out comparison experiments, and the experimental result is that the network training is all at LmaxWhen the number is less than or equal to 100, the training is automatically cut off, and the maximum node number L of the hidden layer is shownmaxThe value of (c) is chosen to be 100 for best network training.
TABLE 3 network LmaxNumber and corresponding RMSE
LmaxNumber of RMSE
5 0.0270
10 0.0261
50 0.0243
100 0.0192
In SCN, γ is an important parameter. Y is a series of positive scalars used to randomly configure the network weights ω and offsets b. From 0.5, upsizing to 10000 was carried out, and a single variable experiment was carried out by using a combination of battery B0005 as a training set and battery B0007 as a test set, and it was found that upsizing of upsizing also resulted in a strong and humanized overfitting condition of good performance of the training set and the test set, as shown in fig. 5. Considering the results of multiple experiments, the γ was finally set to a maximum value of 200 and a minimum value of 0.5.
Simulation result and comparative analysis:
the final parameter settings for SCN are shown in table 4 after several comparative experiments.
TABLE 4 SCN parameter settings
Maximum number of hidden nodes 100
Margin of error 0.00
Number of random configurations 100
Υ Maximum 200, minimum 0.5
r Increasing by 0.9-0.99999
batchsize 1
Fig. 6 is a battery life prediction fit image of SCN, where the black curve is the true decay value of battery life and the red curve is the predicted value of SCN. It is obvious that the SCN fitting curve fluctuates slightly only in the early stage of the network, but because the nodes are fewer at the beginning of the network construction, the curve fitting condition becomes better gradually as the network nodes increase.
Fig. 7 is a battery training RMSE attenuation image with the battery data of B0005, B0006, B0007 as the training data sets, respectively.
Fig. 8 is a training fit image of three pieces of battery data, where the solid line is the true capacity fade image of the battery and the dashed line is the model predicted fade image.
And selecting a plurality of commonly used battery RUL prediction algorithms and a battery RUL prediction algorithm based on SCN to carry out a comparison experiment so as to verify the usability and effectiveness of the random configuration network for predicting the residual life of the battery. A comparison experiment is carried out on two Feedforward Neural Networks (FNN) with different network structures, two Convolutional Neural Networks (CNN) with different network structures and a long-time memory network LSTM; data set B0005 data was used as training set B0007 data as a combination of test sets. The first full-connection layer of the FNN1 adopts an output dimension 10 and normal distribution initialization weight, the activation layer adopts a Leaky ReLU activation function, the second full-connection layer adopts an output dimension 1 and the activation function adopts a linear activation function, the network optimizer adopts an Adam optimizer, and a Dropout layer is not arranged; the first full-connection layer of FNN2 adopts output dimension 40 and normal distribution initialization weight, the activation layer adopts Leaky ReLU activation function, the second full-connection layer adopts output dimension 1 and linear activation function, the network optimizer adopts Adam optimizer, and a Dropout layer is arranged between the two full-connection layers; CNN1 adopts a small convolution kernel and a Leaky ReLU activation function, CNN2 adopts a large convolution kernel and a Leaky ReLU activation function, and Dropout layers are respectively added between the first layer of convolution and the second layer of convolution and between the second layer of convolution and the full connection layer. The LSTM network also employs the leakage ReLU activation function and adds a Dropout layer.
From table 5 comparing RMSE mean values of SCN algorithm and other algorithms, it can be seen that the training rms error of SCN is minimal. The test set fits most well on SCN. Compared with other artificial neural networks, the training RMSE value of SCN is the smallest, with a value of 0.0192, 43% for FNN1, 41% for FNN2, 42% for CNN1, and 34% for CNN2, respectively.
TABLE 5 network RMSE value comparison table
Training algorithm RMSE mean value
FNN1 0.0445
FNN2 0.0462
CNN1 0.0460
CNN2 0.0553
LSTM 0.0254
SCN 0.0186
Figure 9 is a control experiment fitting image of SCN with various neural networks, where black bold lines are true values and red bold lines are SCN fitting values. It can be obviously seen that the overall fitting condition of the SCN is better than that of other networks, and the fitting effect of the network stability is slightly worse than that of the LSTM network due to less hidden nodes in the early prediction stage, and is similar to that of the CNN 1; after 50 cycles, the fitting effect of SCN is significantly better than the rest of the network, almost overlapping with the real life decay image. Therefore, the lithium ion battery service life prediction method based on the random configuration network has practicability, and the accuracy is superior to that of various existing neural network methods.
And (4) simulation conclusion: the invention provides a lithium ion battery RUL prediction method based on a random configuration network. The battery RUL prediction experiment is carried out by utilizing an incremental random neural network SCN, firstly, training set data of the SCN is determined, the data set adopts a NASA PCoE battery data set, firstly, 100 cycles of stable data are intercepted to serve as training data of the SCN, secondly, comparison experiments are carried out to successively determine network parameter values, and finally, two FNN networks, two CNN networks, an LSTM network and the SCN are used for carrying out comparison experiments.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present invention, and therefore, the scope of the present invention should be determined by the scope of the claims.

Claims (8)

1. A method for predicting the service life of an unmanned aerial vehicle battery based on a random configuration network is characterized by comprising the following steps: the method comprises the following steps: the capacity of a lithium ion battery for the unmanned aerial vehicle is used as a direct health factor, the discharge voltage of the battery is used as an indirect health factor, model training and parameter debugging are carried out by adopting a random configuration network, and a service life prediction model of the lithium ion battery is obtained for prediction.
2. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 1, wherein: the random configuration network algorithm comprises the following specific steps:
(1) for a given objective function f:
Figure FDA0003009346820000011
suppose a single-layer feedforward network with L-1 hidden nodes has been established, as shown in equation (1).
Figure FDA0003009346820000012
Wherein f isL-1(x) Represents a hypothetical single-layer feedforward network with L-1 hidden nodes, betajRepresenting hidden layer output weights, gjIt is shown that the activation function is,
Figure FDA0003009346820000013
input weights representing hidden layers, bjAn input bias representing a hidden layer;
error is expressed as formula (2)
eL-1＝f-fL-1＝[eL-1,1,...,eL-1,m] (2)
Wherein eL-1Representing the current error, f represents the network value currently having L nodes, fL-1Network values representing L-1 nodes of the last stage of swimming, eL-1,1Indicating the error of the L-1 hidden layer node to the first output layer node, …, eL-1,mThe error of the L-1 hidden layer node to the mth output layer node;
if the error eL-1If the preset error limit is not reached, adding beta by using an incremental learning methodL,gLWherein g isLHas a weight of wLOffset is bLUpdate fL＝fL-1+βLgLUp to an error eL-1Reaching a given error limit;
(2) suppose for
Figure FDA0003009346820000014
Are all 0 < | g | < bgGiven 0 < r < 1 and a sequence of non-negative real numbers [ mu ]LIn which μLSatisfy the requirement of
Figure FDA0003009346820000015
And muL≦ (1-r), hidden node L ═ 1, 2.. is expressed as:
Figure FDA0003009346820000021
wherein deltaLRepresents the value of node L, δL,qA value representing the q output layer node corresponding to the L hidden layer node, r is a self-set numerical value, muLIs a sequence of non-negative real numbers, eL-1,qRepresenting the error of the qth output layer node corresponding to the L-1 hidden layer node, | | | | | represents the norm calculation;
if the random basis function g is generatedLSatisfaction formula (4)
Figure FDA0003009346820000022
Wherein eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting random basis functions, bgRepresenting the bias, δ, of the random basis functionL,qA value representing that the lth hidden layer node corresponds to the qth output layer node;
and the output weight is represented by formula (5)
Figure FDA0003009346820000023
Wherein beta isL,qRepresenting the output weight, eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
if the calculation is obtained, the conclusion is reached
Figure FDA0003009346820000024
Wherein:
Figure FDA0003009346820000025
the supervision mechanism in equation (4) calculates the optimal weight wLAnd bias bLObtaining a proper newly added node to meet the mathematical condition of the formula (7):
<eL-1,gL>2/||gL||2 (7)
wherein eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
obvious type (8)
βL＝[βL,1,...,βL,m]T (8)
Wherein beta isLRepresenting the output weight, betaL,1Output weights …, β representing the Lth hidden layer node corresponding to the 1 st output layer nodeL,mRepresenting the output weight of the Lth hidden layer node corresponding to the mth output layer node;
analysis by formula (9):
Figure FDA0003009346820000031
wherein beta isL,qRepresenting output weights representing the q-th output layer node corresponding to the L-th hidden layer node, eL-1,qRepresenting the error of the q-th output layer node corresponding to the L-1 th hidden layer node, gLRepresenting a random basis function, | | | | | initiative norm calculation;
the formula (9) is analyzed and evaluated, and g is obtained by calculating the calculation scheme of the output weight according to the formula (4)j(j ═ 1, 2.. times, L), β is calculated by minimizing the global residual1,β2,...,βLThe value of (c).
3. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 2, wherein: the establishment of the random configuration network algorithm is divided into two steps: 1) configuration of hidden node parameters: randomly assigning input weights and deviations to satisfy equation (4); then generating a new hidden node and adding the new hidden node into the current learner model; 2) calculating an output weight: the system of linear equations is solved by using a least squares method or a regularized version thereof.
4. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 3, wherein: the random configuration network algorithm adopts a sigmoid function as a hidden node activation function, wherein the parameter Y is { lambda ═ lambda1:Δλ:λmaxFor the self-adaptive determination of the range of random parameters w and b, selecting a desired error margin epsilon or a preset maximum number L of hidden nodesmaxTo terminate the algorithm.
5. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 2, wherein: the randomly configured network takes a time-varying value of r, in which case r needs to be set very close to 1 to get equation (10) to approach zero, making ξL≥0：
Figure FDA0003009346820000032
When r is set to be close to 1, the ratio of e to the equation (11) becomes largerL-1 2Small:
δL＝(1-r-μL)eL-1 2。 (11)
6. the unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 1, wherein: the method also comprises a reliability analysis method for selecting the health factors, wherein the reliability analysis method for selecting the health factors adopts grey correlation degree analysis, and the specific method comprises the following steps: setting n influencing elements in a gray system, setting an important element X, knowing that other n-1 elements have influence on X in different degrees, calculating the influence degree of the other n-1 elements on X by using multi-element statistical analysis, and calculating the GRA value between two data elements by using the following formula:
Figure FDA0003009346820000041
xi in the formula (12)i(k) The calculated gray correlation coefficient of the kth influence element sequence is y (k), and the calculated gray correlation coefficient is a reference element sequence, namely a battery capacity sequence X; x is the number ofi(k) Comparing element sequences, namely n-1 discharge voltage sequences; rho is a self-defined resolution coefficient; and finally, calculating the average value of the discharge voltage sequence according to a formula (13) to obtain a grey correlation value of the discharge voltage to the battery capacity:
Figure FDA0003009346820000042
wherein gamma isiRepresenting grey correlation value, ξi(k) Representing the correlation coefficient of element k of the total n elements.
7. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 1, wherein: random machineThe network training data is set with the performance evaluation label of the random configuration network by using the root mean square error value, the calculation of the root mean square error value is as the formula (14), wherein
Figure FDA0003009346820000043
And yiPredicted capacity and real capacity, respectively:
Figure FDA0003009346820000044
wherein
Figure FDA0003009346820000045
yiRespectively representing a predicted value and a true value;
training data requires removing the first M cycles and the last N cycles of data, and training the randomly configured network with the middle L cycles of data.
8. The unmanned aerial vehicle battery life prediction method based on the random configuration network as claimed in claim 4, wherein: number of large hidden nodes LmaxDetermined using single variable experiments.
CN202110371138.2A 2021-04-07 2021-04-07 Unmanned aerial vehicle battery life prediction method based on random configuration network Active CN113094989B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110371138.2A CN113094989B (en) 2021-04-07 2021-04-07 Unmanned aerial vehicle battery life prediction method based on random configuration network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110371138.2A CN113094989B (en) 2021-04-07 2021-04-07 Unmanned aerial vehicle battery life prediction method based on random configuration network

Publications (2)

Publication Number Publication Date
CN113094989A true CN113094989A (en) 2021-07-09
CN113094989B CN113094989B (en) 2022-12-09

Family

ID=76674324

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110371138.2A Active CN113094989B (en) 2021-04-07 2021-04-07 Unmanned aerial vehicle battery life prediction method based on random configuration network

Country Status (1)

Country Link
CN (1) CN113094989B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113777496A (en) * 2021-09-06 2021-12-10 北京化工大学 Lithium ion battery residual life prediction method based on time convolution neural network

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5815134B2 (en) * 2013-08-28 2015-11-17 株式会社日立製作所 Li-ion battery life prediction method and system
CN108549036A (en) * 2018-05-03 2018-09-18 太原理工大学 Ferric phosphate lithium cell life-span prediction method based on MIV and SVM models
CN109061504A (en) * 2018-08-28 2018-12-21 中北大学 Same type difference lithium ion battery remaining life prediction technique and system
CN110568374A (en) * 2019-09-02 2019-12-13 东北电力大学 Lithium ion battery residual service life prediction method based on consideration of internal and external characteristics
CN111443294A (en) * 2020-04-10 2020-07-24 华东理工大学 Method and device for indirectly predicting remaining life of lithium ion battery

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5815134B2 (en) * 2013-08-28 2015-11-17 株式会社日立製作所 Li-ion battery life prediction method and system
US20160239586A1 (en) * 2013-08-28 2016-08-18 Hitachi, Ltd. Lifetime prediction method and system of lithium-ion battery
CN108549036A (en) * 2018-05-03 2018-09-18 太原理工大学 Ferric phosphate lithium cell life-span prediction method based on MIV and SVM models
CN109061504A (en) * 2018-08-28 2018-12-21 中北大学 Same type difference lithium ion battery remaining life prediction technique and system
CN110568374A (en) * 2019-09-02 2019-12-13 东北电力大学 Lithium ion battery residual service life prediction method based on consideration of internal and external characteristics
CN111443294A (en) * 2020-04-10 2020-07-24 华东理工大学 Method and device for indirectly predicting remaining life of lithium ion battery

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
XUEJIAO ZHAO ET AL.: "Reliable Life Prediction and Evaluation Analysis of Lithium-ion Battery Based on Long-Short Term Memory Model", 《2019 IEEE 19TH INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY COMPANION (QRS-C)》 *
苗建国 等: "无人机故障诊断技术研究进展概述", 《仪器仪表学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113777496A (en) * 2021-09-06 2021-12-10 北京化工大学 Lithium ion battery residual life prediction method based on time convolution neural network
CN113777496B (en) * 2021-09-06 2023-10-24 北京化工大学 Lithium ion battery residual life prediction method based on time convolution neural network

Also Published As

Publication number Publication date
CN113094989B (en) 2022-12-09

Similar Documents

Publication Publication Date Title
CN109991542B (en) Lithium ion battery residual life prediction method based on WDE optimization LSTM network
CN109659933B (en) Electric energy quality prediction method for power distribution network with distributed power supply based on deep learning model
CN112241608B (en) Lithium battery life prediction method based on LSTM network and transfer learning
CN111539515B (en) Complex equipment maintenance decision method based on fault prediction
CN110119854B (en) Voltage stabilizer water level prediction method based on cost-sensitive LSTM (least squares) cyclic neural network
US20190265768A1 (en) Method, system and storage medium for predicting power load probability density based on deep learning
CN111736084B (en) Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network
Wang et al. Rapid ultracapacitor life prediction with a convolutional neural network
CN111680786B (en) Time sequence prediction method based on improved weight gating unit
CN112734002B (en) Service life prediction method based on data layer and model layer joint transfer learning
CN113094981B (en) Lithium ion battery reliability evaluation method based on grey neural network model and self-service method
CN112381320A (en) Community personnel flow prediction method, system, storage medium and equipment
CN113361692A (en) Lithium battery residual life combined prediction method
CN116703464A (en) Electric automobile charging demand modeling method and device, electronic equipment and storage medium
CN115759336A (en) Prediction method and storage medium for short-term power load prediction
CN113094989B (en) Unmanned aerial vehicle battery life prediction method based on random configuration network
CN116523001A (en) Method, device and computer equipment for constructing weak line identification model of power grid
CN113884936B (en) ISSA coupling DELM-based lithium ion battery health state prediction method
CN111337833A (en) Lithium battery capacity integrated prediction method based on dynamic time-varying weight
CN115221731A (en) Transformer life evaluation method based on data fusion and Wiener model
CN115453871A (en) Non-linear system modeling method based on IDE extended multidimensional Taylor network
CN115600495A (en) Hybrid prediction method and system for performance degradation of solid oxide fuel cell
CN113270867A (en) Weak power grid power flow non-solution automatic adjustment method
CN113723660A (en) Specific behavior type prediction method and system based on DNN-LSTM fusion model
CN112329995A (en) Optimal scheduling method and device for distributed energy storage cluster and computer equipment

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
GR01 Patent grant
GR01 Patent grant