CN110794319A  Method and device for predicting parameters of lithium battery impedance model and readable storage medium  Google Patents
Method and device for predicting parameters of lithium battery impedance model and readable storage medium Download PDFInfo
 Publication number
 CN110794319A CN110794319A CN201911101543.1A CN201911101543A CN110794319A CN 110794319 A CN110794319 A CN 110794319A CN 201911101543 A CN201911101543 A CN 201911101543A CN 110794319 A CN110794319 A CN 110794319A
 Authority
 CN
 China
 Prior art keywords
 lithium battery
 parameters
 support vector
 vector machine
 impedance
 Prior art date
 Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
 Pending
Links
 WHXSMMKQMYFTQSUHFFFAOYSAN lithium Chemical compound data:image/svg+xml;base64,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 data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0nMS4wJyBlbmNvZGluZz0naXNvLTg4NTktMSc/Pgo8c3ZnIHZlcnNpb249JzEuMScgYmFzZVByb2ZpbGU9J2Z1bGwnCiAgICAgICAgICAgICAgeG1sbnM9J2h0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnJwogICAgICAgICAgICAgICAgICAgICAgeG1sbnM6cmRraXQ9J2h0dHA6Ly93d3cucmRraXQub3JnL3htbCcKICAgICAgICAgICAgICAgICAgICAgIHhtbG5zOnhsaW5rPSdodHRwOi8vd3d3LnczLm9yZy8xOTk5L3hsaW5rJwogICAgICAgICAgICAgICAgICB4bWw6c3BhY2U9J3ByZXNlcnZlJwp3aWR0aD0nODVweCcgaGVpZ2h0PSc4NXB4JyB2aWV3Qm94PScwIDAgODUgODUnPgo8IS0tIEVORCBPRiBIRUFERVIgLS0+CjxyZWN0IHN0eWxlPSdvcGFjaXR5OjEuMDtmaWxsOiNGRkZGRkY7c3Ryb2tlOm5vbmUnIHdpZHRoPSc4NScgaGVpZ2h0PSc4NScgeD0nMCcgeT0nMCc+IDwvcmVjdD4KPHRleHQgeD0nMzUuMDQ1NScgeT0nNTMuNTkwOScgY2xhc3M9J2F0b20tMCcgc3R5bGU9J2ZvbnQtc2l6ZToyM3B4O2ZvbnQtc3R5bGU6bm9ybWFsO2ZvbnQtd2VpZ2h0Om5vcm1hbDtmaWxsLW9wYWNpdHk6MTtzdHJva2U6bm9uZTtmb250LWZhbWlseTpzYW5zLXNlcmlmO3RleHQtYW5jaG9yOnN0YXJ0O2ZpbGw6IzNCNDE0MycgPkw8L3RleHQ+Cjx0ZXh0IHg9JzUxLjA0MDknIHk9JzUzLjU5MDknIGNsYXNzPSdhdG9tLTAnIHN0eWxlPSdmb250LXNpemU6MjNweDtmb250LXN0eWxlOm5vcm1hbDtmb250LXdlaWdodDpub3JtYWw7ZmlsbC1vcGFjaXR5OjE7c3Ryb2tlOm5vbmU7Zm9udC1mYW1pbHk6c2Fucy1zZXJpZjt0ZXh0LWFuY2hvcjpzdGFydDtmaWxsOiMzQjQxNDMnID5pPC90ZXh0Pgo8cGF0aCBkPSdNIDYxLjIzMDksNDIgTCA2MS4yMjY2LDQxLjkwMDQgTCA2MS4yMTM4LDQxLjgwMTUgTCA2MS4xOTI1LDQxLjcwNCBMIDYxLjE2MjksNDEuNjA4OCBMIDYxLjEyNTIsNDEuNTE2NCBMIDYxLjA3OTcsNDEuNDI3NyBMIDYxLjAyNjgsNDEuMzQzMSBMIDYwLjk2NjgsNDEuMjYzNSBMIDYwLjkwMDIsNDEuMTg5MyBMIDYwLjgyNzQsNDEuMTIxMSBMIDYwLjc0OTEsNDEuMDU5NCBMIDYwLjY2NTcsNDEuMDA0NiBMIDYwLjU3NzksNDAuOTU3MiBMIDYwLjQ4NjQsNDAuOTE3NiBMIDYwLjM5MTgsNDAuODg2IEwgNjAuMjk0OSw0MC44NjI2IEwgNjAuMTk2Myw0MC44NDc2IEwgNjAuMDk2OCw0MC44NDEyIEwgNTkuOTk3LDQwLjg0MzMgTCA1OS44OTc5LDQwLjg1NCBMIDU5LjgsNDAuODczMiBMIDU5LjcwNDIsNDAuOTAwOCBMIDU5LjYxMSw0MC45MzY0IEwgNTkuNTIxMyw0MC45OCBMIDU5LjQzNTcsNDEuMDMxMSBMIDU5LjM1NDcsNDEuMDg5NCBMIDU5LjI3OTEsNDEuMTU0NCBMIDU5LjIwOTMsNDEuMjI1NyBMIDU5LjE0Niw0MS4zMDI3IEwgNTkuMDg5NCw0MS4zODQ4IEwgNTkuMDQwMiw0MS40NzE2IEwgNTguOTk4Niw0MS41NjIyIEwgNTguOTY0OSw0MS42NTYxIEwgNTguOTM5NSw0MS43NTI1IEwgNTguOTIyNCw0MS44NTA4IEwgNTguOTEzOCw0MS45NTAxIEwgNTguOTEzOCw0Mi4wNDk5IEwgNTguOTIyNCw0Mi4xNDkyIEwgNTguOTM5NSw0Mi4yNDc1IEwgNTguOTY0OSw0Mi4zNDM5IEwgNTguOTk4Niw0Mi40Mzc4IEwgNTkuMDQwMiw0Mi41Mjg0IEwgNTkuMDg5NCw0Mi42MTUyIEwgNTkuMTQ2LDQyLjY5NzMgTCA1OS4yMDkzLDQyLjc3NDMgTCA1OS4yNzkxLDQyLjg0NTYgTCA1OS4zNTQ3LDQyLjkxMDYgTCA1OS40MzU3LDQyLjk2ODkgTCA1OS41MjEzLDQzLjAyIEwgNTkuNjExLDQzLjA2MzYgTCA1OS43MDQyLDQzLjA5OTIgTCA1OS44LDQzLjEyNjggTCA1OS44OTc5LDQzLjE0NiBMIDU5Ljk5Nyw0My4xNTY3IEwgNjAuMDk2OCw0My4xNTg4IEwgNjAuMTk2Myw0My4xNTI0IEwgNjAuMjk0OSw0My4xMzc0IEwgNjAuMzkxOCw0My4xMTQgTCA2MC40ODY0LDQzLjA4MjQgTCA2MC41Nzc5LDQzLjA0MjggTCA2MC42NjU3LDQyLjk5NTQgTCA2MC43NDkxLDQyLjk0MDYgTCA2MC44Mjc0LDQyLjg3ODkgTCA2MC45MDAyLDQyLjgxMDcgTCA2MC45NjY4LDQyLjczNjUgTCA2MS4wMjY4LDQyLjY1NjkgTCA2MS4wNzk3LDQyLjU3MjMgTCA2MS4xMjUyLDQyLjQ4MzYgTCA2MS4xNjI5LDQyLjM5MTIgTCA2MS4xOTI1LDQyLjI5NiBMIDYxLjIxMzgsNDIuMTk4NSBMIDYxLjIyNjYsNDIuMDk5NiBMIDYxLjIzMDksNDIgTCA2MC4wNzE4LDQyIFonIHN0eWxlPSdmaWxsOiMwMDAwMDA7ZmlsbC1ydWxlOmV2ZW5vZGQ7ZmlsbC1vcGFjaXR5OjE7c3Ryb2tlOiMwMDAwMDA7c3Ryb2tlLXdpZHRoOjBweDtzdHJva2UtbGluZWNhcDpidXR0O3N0cm9rZS1saW5lam9pbjptaXRlcjtzdHJva2Utb3BhY2l0eToxOycgLz4KPC9zdmc+Cg== [Li] WHXSMMKQMYFTQSUHFFFAOYSAN 0.000 title claims abstract description 152
 229910052744 lithium Inorganic materials 0.000 title claims abstract description 152
 230000004044 response Effects 0.000 claims abstract description 88
 239000003990 capacitor Substances 0.000 claims description 14
 238000004590 computer program Methods 0.000 claims description 13
 238000004422 calculation algorithm Methods 0.000 claims description 7
 230000000875 corresponding Effects 0.000 claims description 7
 230000002068 genetic Effects 0.000 claims description 7
 238000000137 annealing Methods 0.000 claims description 6
 230000001537 neural Effects 0.000 abstract description 7
 238000005259 measurement Methods 0.000 description 7
 238000001514 detection method Methods 0.000 description 6
 1 nickelcadmium Chemical compound 0.000 description 5
 238000004364 calculation method Methods 0.000 description 4
 238000010586 diagram Methods 0.000 description 4
 238000000034 method Methods 0.000 description 4
 229910052739 hydrogen Inorganic materials 0.000 description 3
 239000001257 hydrogen Substances 0.000 description 3
 238000001453 impedance spectrum Methods 0.000 description 3
 210000004556 Brain Anatomy 0.000 description 2
 238000007599 discharging Methods 0.000 description 2
 238000011156 evaluation Methods 0.000 description 2
 238000010606 normalization Methods 0.000 description 2
 238000005070 sampling Methods 0.000 description 2
 238000002922 simulated annealing Methods 0.000 description 2
 238000006467 substitution reaction Methods 0.000 description 2
 239000002253 acid Substances 0.000 description 1
 238000004891 communication Methods 0.000 description 1
 238000011161 development Methods 0.000 description 1
 230000000694 effects Effects 0.000 description 1
 238000004134 energy conservation Methods 0.000 description 1
 230000005284 excitation Effects 0.000 description 1
 230000004048 modification Effects 0.000 description 1
 238000006011 modification reaction Methods 0.000 description 1
 210000000653 nervous system Anatomy 0.000 description 1
 235000001968 nicotinic acid Nutrition 0.000 description 1
 230000003287 optical Effects 0.000 description 1
 238000005457 optimization Methods 0.000 description 1
 230000000750 progressive Effects 0.000 description 1
Classifications

 G—PHYSICS
 G01—MEASURING; TESTING
 G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
 G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
 G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
 G01R31/389—Measuring internal impedance, internal conductance or related variables

 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 lookup 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]
 G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

 G—PHYSICS
 G06—COMPUTING; CALCULATING; COUNTING
 G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
 G06N20/00—Machine learning
 G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]

 G—PHYSICS
 G06—COMPUTING; CALCULATING; COUNTING
 G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
 G06N3/00—Computer systems based on biological models
 G06N3/12—Computer systems based on biological models using genetic models
 G06N3/126—Genetic algorithms, i.e. information processing using digital simulations of the genetic system
Abstract
The invention discloses a method for predicting parameters of a lithium battery impedance model, which comprises the following steps: establishing a least square support vector machine model for predicting target parameters; acquiring a voltage response value of a lithium battery to be tested; the method comprises the steps of obtaining a target parameter of a lithium battery to be tested according to a least square support vector machine model and a voltage response value, obtaining the target parameter of the lithium battery to be tested according to the least square support vector machine model and the voltage response value, obtaining the target parameter according to the preestablished least square support vector machine model and the obtained voltage response value, avoiding the use of an artificial neural network to predict the parameter of an impedance model of the lithium battery, reducing the upper bound of the generalization error of the model while minimizing the error of a sample point when the least square support vector machine is applied to predicting problems by adopting a structural risk minimization principle, and improving the generalization capability of the model, so that the parameter of the impedance model of the battery can be.
Description
Technical Field
The invention relates to the technical field of lithium batteries, in particular to a method and a device for predicting parameters of an impedance model of a lithium battery and a readable storage medium.
Background
With the continuous development of society, China has rapidly developed new energy and energy conservation and emission reduction, and lithium batteries have started to replace traditional leadacid, nickelhydrogen and nickelcadmium batteries due to higher energy and more environmental protection. When the lithium battery is applied to an electric automobile, the working voltage of the lithium battery which needs to be loaded on the electric automobile is 12V or 24V, but the working voltage of the single lithium battery is 3.7V, so that the plurality of batteries need to be connected in series to improve the voltage, however, the batteries are difficult to be charged and discharged in a completely balanced manner, the consistency of the batteries is difficult to ensure, the situations of insufficient charging and overdischarging can occur, the performance of the batteries is directly and rapidly deteriorated, and the cycle life and the reliability of the batteries are greatly reduced. It is particularly important to improve the uniformity of the battery. Through a large amount of researches, parameters in an impedance model of the lithium battery are the basis for evaluating the dynamic performance consistency of the battery.
In the prior art, parameters of a lithium battery impedance model are predicted by adopting an artificial neural network method. The artificial neural network simulates the nervous system of the human brain from the bionics angle so as to realize the functions of perception, learning, reasoning and the like of the human brain, and the artificial neural network is introduced into the lithium battery impedance model parameter prediction so as to realize the purpose of rapidly predicting the battery impedance model parameter. Although the artificial neural network has achieved a certain success, the artificial neural network follows the principle of minimizing empirical risk, the modeling process needs a large amount of sample data, the generalization capability is poor, local optimization is prone to occur, and the like.
Therefore, how to predict the parameters of the lithium battery impedance model more accurately is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
Embodiments of the present invention provide a method, an apparatus, and a readable storage medium for predicting parameters of an impedance model of a lithium battery, so as to solve the above problems.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for predicting parameters of a lithium battery impedance model comprises the following steps:
s10: establishing a least square support vector machine model for predicting target parameters;
s20: acquiring a voltage response value of a lithium battery to be tested;
s30: and obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
In one alternative: the establishing of the least square support vector machine model of the predicted target parameters comprises the following steps:
obtaining sample voltage response values of a plurality of sample lithium batteries;
obtaining reference parameters of the multiple sample lithium battery impedance models;
and establishing the least square support vector machine model according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter.
In one alternative: the kernel function of the support vector machine is a radial basis kernel function.
In one alternative: the step of establishing the least squares support vector machine model according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter comprises the following steps:
and determining the least square support vector machine model by adopting a genetic annealing algorithm according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter.
In one alternative: the step of obtaining the reference parameters of the multiple sample lithium battery impedance models comprises the following steps:
and measuring the reference parameters of the impedance models of the plurality of sample lithium batteries by adopting an electrochemical workstation.
In one alternative: the step of obtaining the voltage response value of the lithium battery to be tested comprises the following steps:
and obtaining voltage response values respectively corresponding to the lithium battery to be tested when the lithium battery to be tested discharges for 10s, 20s, 40s, 50s and 100s respectively at the current of 1C.
In one alternative: the target parameters include: the capacitancetype capacitor comprises an inductance value, a first resistance value, a second resistance value, a third resistance value, a fourth resistance value, a first capacitance value, a second capacitance value, a third capacitance value and a fourth capacitance value.
An apparatus for predicting parameters of an impedance model of a lithium battery, comprising:
the first model establishing unit is used for establishing a least square support vector machine model for predicting target parameters;
the first acquisition unit is used for acquiring a voltage response value of the lithium battery;
the calculation unit is used for obtaining the parameters according to the least square support vector machine model and the voltage response value;
an apparatus for predicting parameters of an impedance model of a lithium battery, comprising a processor for implementing the steps of any one of the above methods for predicting parameters of an impedance model of a lithium battery when executing a program stored in a memory.
A computerreadable storage medium having a computer program stored thereon, the computer program being executable by a processor to perform the steps of:
establishing a least square support vector machine model for predicting target parameters;
acquiring a voltage response value of a lithium battery to be tested;
and obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
the method comprises the steps of establishing a least square support vector machine model for predicting target parameters; acquiring a voltage response value of a lithium battery to be tested; obtaining target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value; therefore, the target parameters can be obtained according to the preestablished least square support vector machine model and the obtained voltage response value. The method avoids the situation that the parameters of the impedance model of the lithium battery are predicted by using an artificial neural network, and the least square support vector machine adopts the structure risk minimization principle, so that when the method is applied to the prediction of problems, the upper bound of the model generalization error is reduced while the sample point error is minimized, and the generalization capability of the model is improved, so that the parameters of the impedance model of the battery can be predicted more accurately.
Drawings
Fig. 1 is a flowchart of a method for predicting parameters of an impedance model of a lithium battery according to a first embodiment of the present invention;
fig. 2 is a flowchart of another method for predicting parameters of an impedance model of a lithium battery according to a second embodiment of the present invention;
FIG. 3 is a diagram of a lithium battery impedance model according to a third embodiment of the present invention;
fig. 4 is a block diagram of an apparatus for predicting parameters of an impedance model of a lithium battery according to a fourth embodiment of the present invention;
fig. 5 is a block diagram of another apparatus for predicting parameters of an impedance model of a lithium battery according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to the following embodiments, wherein like or similar elements are designated by like reference numerals throughout the several views, and wherein the shape, thickness or height of the various elements may be expanded or reduced in practice. The examples are given solely for the purpose of illustration and are not intended to limit the scope of the invention. Any obvious modifications or variations can be made to the present invention without departing from the spirit or scope of the present invention.
Example 1
Referring to fig. 1, in an embodiment of the present invention, a method for predicting parameters of an impedance model of a lithium battery includes the following steps:
s10: establishing a least square support vector machine model for predicting target parameters;
the target parameters can be parameters or parameter values to be obtained finally, and the number and the types of the target parameters can be selected in advance according to needs;
firstly, establishing a least square support vector machine model for predicting target parameters, wherein the least square support vector machine model can be a specific calculation formula obtained specifically or not directly embodied in the manner of the calculation formula, and is realized by a computer program;
specifically, a certain sample data may be acquired in advance, and a least square support vector machine model may be established according to the sample data.
S11: acquiring a voltage response value of a lithium battery to be tested;
the voltage response value can be one quantity or a plurality of quantities, a certain battery performance detection instrument can be selected to obtain the voltage response value, specifically, a ZM7510 series battery performance detector can be used for obtaining the voltage response value, the detector can be used for detecting the performance of various batteries such as nickelhydrogen batteries, nickelcadmium batteries, nickelzinc batteries, lithium batteries and the like, the detector has high measurement precision and high detection speed, can be monitored and operated in real time in the measurement process, can store and display an operation curve and complete measurement data, and can export the data to formats such as EXCEL, WORD, TXT and the like so as to be convenient for archiving and analysis.
S12: obtaining target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value;
parameters of the lithium battery impedance model can be calculated and obtained according to the least squares support vector machine model established in step S10 and the voltage response value acquired in step S11. Specifically, the obtained voltage response value may be input into a least squares support vector machine model, and the output of the least squares support vector machine model may be a target parameter, and the parameter is calculated and obtained;
optionally, after the voltage response value is obtained, the voltage response value may be normalized and then input into the least squares support vector machine, and the output of the least squares support vector machine is further subjected to inverse normalization to obtain the reference parameter. So as to eliminate the difference between dimensions and predict the result more accurately;
establishing a least square support vector machine model for predicting a target parameter, obtaining a voltage response value of the lithium battery to be tested, and obtaining the target parameter according to the least square support vector machine model and the voltage response value. Therefore, the target parameters can be obtained according to the preestablished least square support vector machine model and the obtained voltage response value. The least square support vector machine adopts a structure risk minimization principle, when the least square support vector machine is used for predicting problems, the upper bound of a model generalization error is reduced while a sample point error is minimized, and the generalization capability of the model is improved, so that parameters of a battery impedance model can be predicted more accurately.
Example 2
Referring to fig. 2, the difference between the present embodiment and embodiment 1 is that the method for establishing the least squares support vector machine model of the predicted target parameter in step S10 is as follows:
s20: obtaining sample voltage response values of a plurality of sample lithium batteries;
a plurality of lithium batteries can be selected as samples for obtaining sample data for training the least square support vector machine model, theoretically, the number of the lithium batteries in the samples is increased, the obtained sample data is increased, the least square support vector machine model obtained through training is more accurate, and a large amount of time may be consumed for obtaining excessive samples, so that the comprehensive consideration of the actual engineering condition is required. For example, the number of the sample lithium batteries may be 10, and certainly, in order to obtain more sample data, the number of the sample lithium batteries may also be 50. The voltage response value may include only one physical quantity or a plurality of physical quantities.
Can design certain main control circuit and battery charge and discharge control circuit and acquire the voltage response value of lithium cell automatically, optionally, can use the MSP430 singlechip as control chip, carry out the charge and discharge operation to the lithium cell through control battery charge and discharge control circuit, can measure the voltage signal who acquires the battery and input to the singlechip through certain detecting instrument, the singlechip can pass through ethernet module and host computer and carry out the communication to host computer control charge and discharge circuit's work and convey the voltage sampling value to the host computer in real time.
And measuring voltage response values of a plurality of lithium batteries. A certain battery performance detection instrument can be selected to obtain the voltage response value. Specifically, a ZM7510 series battery performance detector may be employed as the charge and discharge control circuit, and the voltage response value may be acquired. The detector can be used for detecting the performance of various batteries such as nickelhydrogen batteries, nickelcadmium batteries, nickelzinc batteries, lithium batteries and the like, has high accuracy and high detection speed in the aspect of measurement, can perform realtime monitoring and operation in the measurement process, can store and display an operating curve and complete measurement data, and can export the data to formats such as EXCEL, WORD, TXT and the like so as to be convenient for archiving and analysis. Optionally, the lithium battery samples may be connected to the detection instrument, and each time one lithium battery is connected, the two ends of each lithium battery may be successively excited by the step pulse current to obtain a voltage sampling value, and then the next lithium battery is replaced, and the steps are sequentially performed until the sample voltage response value of each lithium battery sample is obtained.
S21: and obtaining reference parameters of the lithium battery impedance models of the multiple samples.
The reference parameter may be considered to be a more accurate parameter value of the standard. The reference parameters of the lithium battery impedance model can be obtained by adopting a certain measuring instrument. And sequentially measuring the reference parameters of the lithium battery impedance model of each sample.
S22: and establishing a least square support vector machine model according to the sample voltage response values and the reference parameters of the plurality of sample lithium batteries.
The least squares support vector machine model can be expressed as:
wherein K (x, x)_{i}) The method comprises the following steps that a kernel function is adopted, n is the number of sample lithium batteries, the type of the kernel function can be selected according to requirements, when a least square support vector machine is used for predicting an impedance model of the lithium batteries, x is input and can be a voltage response value of the lithium batteries to be tested, f (x) is a parameter of the impedance model of the lithium batteries to be tested, and x is_{i}For the ith sample voltage response value, the process of establishing and training the least square support vector machine model can be to determine the parameters a and a in the kernel function in the expression by the sample voltage response value and the reference parameter_{i}And b. In this way, the calculation formula of the parameters of the impedance model can be determined.
Specifically, buildingWhen the least square support vector machine model is established, the sample voltage response value can be used as the input of the least square support vector machine, the reference parameter is used as the expected output of the least square support vector machine model, the least square support vector machine model is trained, the difference between the actual output and the expected output can be calculated in each training, and when the difference value reaches a preset range, the currently selected parameter is considered to meet the requirement, so that the parameter a in the kernel function is determined_{i}And b. Preferably, the sample voltage response value, the reference parameter and the expected output may be normalized respectively, and then used as the input and the expected output of the least squares support vector machine, and correspondingly, the actual output of the least squares support vector machine is transformed by inverse normalization. Therefore, the difference between dimensions can be eliminated, and the established model of the least square support vector machine is more accurate.
The method comprises the steps of obtaining sample voltage response values of a plurality of sample lithium batteries, obtaining reference parameters of impedance models of the plurality of sample lithium batteries, establishing a least square support vector machine model according to the sample voltage response values and the reference parameters of the plurality of sample lithium batteries, obtaining voltage response values of lithium batteries to be tested, and obtaining target parameters according to the least square support vector machine model and the voltage response values. Therefore, the target parameters can be obtained according to the preestablished least square support vector machine model and the obtained voltage response value. Parameters of the battery impedance model can be predicted more accurately;
in order to determine the parameters in the least squares support vector machine model more quickly and accurately, as a preferred embodiment, establishing the least squares support vector machine model according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameters comprises: determining a least square support vector machine model by adopting a genetic annealing algorithm according to the sample voltage response values and the reference parameters of the plurality of sample lithium batteries;
in building a least squares support vector machine model, parameter values in the model need to be determined. For example, if the kernel function in the least squares support vector machine is a radial basis kernel function, the expression of the least squares support vector machine model is:
the parameters to be determined include sigma and a_{i}And b, if a manual trial and error method is adopted to determine the final parameter value, the efficiency is extremely low. Therefore, computer algorithms are often employed to determine parameter values. Such as a genetic annealing algorithm. Specific steps of the genetic annealing algorithm may include: first, encoding work is carried out to generate an initial population. The initial population can be a parameter to be solved in a least square support vector machine model; and designing an individual fitness evaluation method to evaluate the population fitness. Alternatively, the error of the output value may be used as the fitness, and the error of the output value may be an error between the value of the parameter of the output impedance model and a reference parameter of the impedance model; designing a conventional genetic operator; selecting a next generation population, reserving a part of excellent individuals, and performing crossover and variation to generate crossover offspring and variant offspring; and performing simulated annealing operation on the cross progeny and the variant progeny individuals generated in the last step to generate new individuals, forming a new population together with the reserved excellent individuals, then continuously designing an individual fitness evaluation method, evaluating the population fitness until the fitness meets the requirement, and setting parameters of the population as parameters of a least square support vector machine model. For example, when the fitness represents an error, that is, the error satisfies a final required value;
in order to more conveniently, quickly and accurately measure the target parameters of the lithium battery impedance model to be measured, as a preferred embodiment, the obtaining of the reference parameters of the multiple sample lithium battery impedance models includes: measuring reference parameters of a plurality of sample lithium battery impedance models by adopting an electrochemical workstation;
optionally, an impedance spectrum of the lithium battery can be measured by using an electrochemical workstation, and then fitting analysis can be performed on experimental data by using electrochemical impedance software Zsimp Win, wherein the software can manually designate a specific battery impedance model before measurement;
for example, when measuring by an electrochemical workstation, the positive electrode of the lithium battery can be connected to the measuring pens of the working electrode and the sensing electrode of the electrochemical workstation, and the negative electrode of the lithium battery can be connected to the two pens of the auxiliary electrode and the reference electrode;
illustratively, when the measured impedance spectrum is fitted by using the software ZSimp Win, the measured impedance spectrum can be stored and converted into a data file, then the data is imported into the ZSimp Win software to be fitted, and an impedance model circuit to be fitted is selected, so that a fitting result can be obtained, and parameters of the lithium battery impedance model can be obtained;
in order to more accurately establish a model of a least squares support vector machine, as a preferred embodiment, obtaining voltage response values of the lithium battery to be tested may include obtaining voltage values respectively corresponding to the lithium battery to be tested discharging for 10s, 20s, 40s, 50s and 100s at a current of 1C;
in general, as the current multiplying power increases, the difference of the chargedischarge response of the lithium battery also increases, and in order to make the difference between different single batteries more obvious, the size of the discharge excitation current is selected as the maximum working current 1C of the battery;
regarding obtaining the voltage response value of the lithium battery to be tested, a specific example is described as follows: the lithium battery can be connected to a sorting device, and is charged at a constant current at a charging rate of 0.5C, with a cutoff voltage of 4.2V, and then is charged at a constant voltage with a cutoff current of 50mA while the voltage is maintained at 4.2V. Then, the discharge is carried out for 10s, 20s, 40s, 50s and 100s respectively at the current with the size of 1C, and the discharge can be paused for 5min after each pulse discharge with different periods. Finally, the data can be exported to the EXCEL format by using detection equipment for archiving;
in order to be able to predict the parameters of the lithium battery impedance model more accurately, as a preferred embodiment, the target parameters of the lithium battery impedance model to be tested include: the capacitance value comprises an inductance value, a first resistance value, a second resistance value, a third resistance value, a fourth resistance value, a first capacitance value, a second capacitance value, a third capacitance value and a fourth capacitance value;
example 3
Referring to fig. 3, in an embodiment of the present invention, an impedance model diagram of a lithium battery is shown, and optionally, the impedance model of the battery may be as shown in fig. 3, and includes an inductor L, a first resistor RL, a second resistor R1, a third resistor RS, a fourth resistor R2, a first electric doublelayer capacitor Q1, and a second electric doublelayer capacitor Q2. The first end and the second end of the inductor L are respectively connected with the first end and the second end of the first resistor RL, the second end of the first resistor RL is simultaneously connected with the first ends of the first electric doublelayer capacitor Q1 and the second resistor R1, the second end of the second resistor R1 is connected with the second end of the first electric doublelayer capacitor Q1 and the first end of the third resistor RS, the second end of the third resistor RS is simultaneously connected with the first end of the second electric doublelayer capacitor Q2 and the first end of the fourth resistor R2, the second end of the second electric doublelayer capacitor Q2 is connected with the second end of the fourth resistor R2, and the model can be used as an effective basis for screening the consistency of batteries. The first electric doublelayer capacitor Q1 and the second electric doublelayer capacitor Q2 both include two parameters, the two parameters of the first electric doublelayer capacitor Q1 are a first capacitance value and a second capacitance value, and the two parameter values of the second electric doublelayer capacitor Q2 are a third capacitance value and a fourth capacitance value. Correspondingly, the parameters of the battery impedance model may be an inductance of the inductor L, a first resistance of the first resistor RL, a second resistance of the second resistor R1, a third resistance of the third resistor RS, a fourth resistance of the fourth resistor R2, a first capacitance value and a second capacitance value of the first electric doublelayer capacitor Q1, and a third capacitance value and a fourth capacitance value of the second electric doublelayer capacitor Q2;
the embodiment of the method for predicting the impedance model of the lithium battery is described in detail above, and based on the method for predicting the parameters of the impedance model of the lithium battery described in the above embodiment, the embodiment of the present invention provides a device for predicting the impedance model of the lithium battery corresponding to the method. Since the embodiment of the apparatus portion and the embodiment of the method portion correspond to each other, the embodiment of the apparatus portion is described with reference to the embodiment of the method portion, and is not described in detail here.
Example 4
Referring to fig. 4, an embodiment of a method for predicting an impedance model of a lithium battery is described in detail above, and based on the method for predicting an impedance model of a lithium battery described in the above embodiment, an embodiment of the present invention provides a device for predicting an impedance model of a lithium battery corresponding to the method. Since the embodiment of the apparatus portion and the embodiment of the method portion correspond to each other, the embodiment of the apparatus portion is described with reference to the embodiment of the method portion, and is not described in detail here.
A device for predicting parameters of a lithium battery impedance model comprises a first model establishing unit 40, a first obtaining unit 41 and a calculating unit 42;
a first model establishing unit 40 for establishing a least squares support vector machine model of the predicted target parameter;
the first obtaining unit 41 is configured to obtain a voltage response value of the lithium battery to be tested;
the first acquiring unit 41 may specifically be an acquiring device or an acquiring instrument;
and the calculating unit 42 is used for obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
The first model establishing unit establishes a least square support vector machine model for predicting target parameters, the first obtaining unit obtains a voltage response value of the lithium battery to be tested, and the calculating unit obtains the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value. Therefore, the target parameters can be obtained according to the preestablished least square support vector machine model and the obtained voltage response value. The least square support vector machine adopts a structure risk minimization principle, when the least square support vector machine is applied to a prediction problem, the upper bound of a model generalization error is reduced while a sample point error is minimized, and the generalization capability of the model is improved, so that the parameters of the battery impedance model can be predicted more accurately.
The first model building unit 40 includes a second obtaining unit, a third obtaining unit, and a second model building unit. The second obtaining unit may be configured to obtain sample voltage response values of a plurality of sample lithium batteries; the third obtaining unit can be used for obtaining reference parameters of the impedance models of the multiple sample lithium batteries; the second model establishing unit is used for establishing a least square support vector machine model according to the sample voltage response values and the reference parameters of the multiple lithium batteries;
the kernel function of the least squares support vector machine model established by the first model establishing unit may be a radial basis kernel function;
the second model establishing unit can be specifically used for determining a least square support vector machine model by adopting a simulated annealing algorithm according to the sample voltage response values and the reference parameters of the multiple sample lithium batteries;
the third obtaining unit can be specifically used for measuring reference parameters of the impedance models of the multiple sample lithium batteries by adopting the electrochemical workstation;
the first obtaining unit may be specifically configured to obtain voltage values corresponding to the lithium battery to be tested which discharges for 10s, 20s, 40s, 50s, and 100s at a current of 1C;
example 5
Referring to fig. 5, an apparatus for predicting parameters of an impedance model of a lithium battery includes:
a memory 50 and a processor 51;
a memory 50 for storing a computer program;
the processor 51, when executing the computer program stored in the memory 50, may implement the following steps:
establishing a least square support vector machine model for predicting target parameters;
acquiring a voltage response value of a lithium battery to be tested;
and obtaining target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
In some embodiments of the present invention, the processor 51 may be further configured to execute the computer program in the memory 50 to implement the following steps:
obtaining sample voltage response values of a plurality of sample lithium batteries;
obtaining reference parameters of a plurality of sample lithium battery impedance models;
and establishing a least square support vector machine model according to the sample voltage response values and the reference parameters of the plurality of sample lithium batteries.
The processor 51 may be further configured to execute the computer program in the memory 50 to implement the following steps:
and determining a least square support vector machine model by adopting a genetic annealing algorithm according to the sample voltage response values and the reference parameters of the multiple sample lithium batteries.
The processor 51 may be further configured to execute the computer program in the memory 50 to implement the following steps:
and obtaining voltage response values respectively corresponding to the lithium battery to be tested when the lithium battery to be tested discharges for 10s, 20s, 40s, 50s and 100s respectively at the current of 1C.
In the apparatus for predicting an impedance model of a lithium battery provided in this embodiment, when the processor executes a computer program in the memory, the processor establishes a least square support vector machine model for predicting a target parameter, obtains a voltage response value of the lithium battery to be measured, and obtains the target parameter according to the least square support vector machine model and the voltage response value. Therefore, the target parameters can be obtained according to the preestablished least square support vector machine model and the obtained voltage response value. The least square support vector machine adopts a structure risk minimization principle, when the least square support vector machine is applied to a prediction problem, the upper bound of a model generalization error is reduced while a sample point error is minimized, and the generalization capability of the model is improved, so that the parameters of the battery impedance model can be predicted more accurately.
Example 6
The embodiment of the computerreadable storage medium portion corresponds to the embodiment of the method portion, so that the embodiment of the computerreadable storage medium portion is described with reference to the embodiment of the method portion and is not described in detail herein;
a computerreadable storage medium having stored thereon a computer program for execution by a processor to perform the steps of:
establishing a least square support vector machine model for predicting target parameters;
acquiring a voltage response value of a lithium battery to be tested;
and obtaining target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
It should be noted that the computerreadable storage medium in the present invention may be a medium such as a usb disk or an optical disk, and is not particularly limited;
when the computer program in the computer readable storage medium provided by the invention is executed by the processor, a least square support vector machine model for predicting parameters is established, a voltage response value of the lithium battery is obtained, and the parameters are obtained according to the least square support vector machine model and the voltage response value. Therefore, parameters can be obtained according to a preestablished least square support vector machine model and the obtained voltage response value. The least square support vector machine adopts a structure risk minimization principle, when the least square support vector machine is applied to a prediction problem, the upper bound of a model generalization error is reduced while a sample point error is minimized, and the generalization capability of the model is improved, so that the parameters of the battery impedance model can be predicted more accurately;
the method, the device and the computer readable storage medium for predicting the parameters of the lithium battery impedance model provided by the invention are described in detail above. The embodiments are described in a progressive mode in the specification, the emphasis of each embodiment is different from that of other embodiments, and the same and similar parts among the embodiments are referred to each other.
The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present disclosure, and all the changes or substitutions should be covered within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A method for predicting parameters of a lithium battery impedance model is characterized by comprising the following steps:
s10: establishing a least square support vector machine model for predicting target parameters;
s20: acquiring a voltage response value of a lithium battery to be tested;
s30: and obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
2. The method of predicting parameters of an impedance model for a lithium battery as claimed in claim 1 wherein the step of establishing a least squares support vector machine model of the predicted target parameters comprises:
obtaining sample voltage response values of a plurality of sample lithium batteries;
obtaining reference parameters of the multiple sample lithium battery impedance models;
and establishing the least square support vector machine model according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter.
3. The method of predicting parameters of a lithium battery impedance model of claim 2, wherein the kernel function of the least squares support vector machine model is a radial basis kernel function.
4. The method of predicting the parameters of the impedance model of the lithium battery as set forth in claim 2, wherein the step of establishing the leastsquares support vector machine model based on the sample voltage response values of the plurality of sample lithium batteries and the reference parameters comprises:
and determining the least square support vector machine model by adopting a genetic annealing algorithm according to the sample voltage response values of the plurality of sample lithium batteries and the reference parameter.
5. The method of predicting parameters of a lithium battery impedance model as recited in claim 2, wherein the step of obtaining reference parameters of the plurality of sample lithium battery impedance models comprises:
and measuring the reference parameters of the impedance models of the plurality of sample lithium batteries by adopting an electrochemical workstation.
6. The method for predicting the parameters of the impedance model of the lithium battery as claimed in claim 2, wherein the obtaining the voltage response value of the lithium battery to be tested comprises:
and obtaining voltage response values respectively corresponding to the lithium battery to be tested when the lithium battery to be tested discharges for 10s, 20s, 40s, 50s and 100s respectively at the current of 1C.
7. The method of predicting parameters of a lithium battery impedance model of claim 2, wherein the target parameters comprise: the capacitancetype capacitor comprises an inductance value, a first resistance value, a second resistance value, a third resistance value, a fourth resistance value, a first capacitance value, a second capacitance value, a third capacitance value and a fourth capacitance value.
8. An apparatus for predicting parameters of an impedance model of a lithium battery, comprising:
the first model establishing unit is used for establishing a least square support vector machine model for predicting target parameters;
the first acquisition unit is used for acquiring a voltage response value of the lithium battery to be detected;
and the calculating unit is used for obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
9. An apparatus for predicting parameters of an impedance model of a lithium battery, comprising a processor for implementing the steps of the method for predicting parameters of an impedance model of a lithium battery as claimed in any one of claims 1 to 7 when executing a program stored in a memory.
10. A computerreadable storage medium, having a computer program stored thereon, the computer program being executable by a processor to perform the steps of:
establishing a least square support vector machine model for predicting target parameters;
acquiring a voltage response value of a lithium battery to be tested;
and obtaining the target parameters of the lithium battery to be tested according to the least square support vector machine model and the voltage response value.
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN201911101543.1A CN110794319A (en)  20191112  20191112  Method and device for predicting parameters of lithium battery impedance model and readable storage medium 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN201911101543.1A CN110794319A (en)  20191112  20191112  Method and device for predicting parameters of lithium battery impedance model and readable storage medium 
Publications (1)
Publication Number  Publication Date 

CN110794319A true CN110794319A (en)  20200214 
Family
ID=69444029
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN201911101543.1A Pending CN110794319A (en)  20191112  20191112  Method and device for predicting parameters of lithium battery impedance model and readable storage medium 
Country Status (1)
Country  Link 

CN (1)  CN110794319A (en) 
Cited By (1)
Publication number  Priority date  Publication date  Assignee  Title 

CN113049973A (en) *  20210602  20210629  河南工学院  Power battery detection device 
Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

CN105116343A (en) *  20150824  20151202  桂林电子科技大学  LSSVM power cell SOC estimation method and system 
CN105444923A (en) *  20151118  20160330  浙江工业大学  Mechanical temperature instrument error prediction method based on geneticalgorithm optimized least square support vector machine 
CN105574231A (en) *  20151127  20160511  上海交通大学  Storage battery surplus capacity detection method 
CN106646253A (en) *  20161207  20170510  华南农业大学  Online identification method for intrinsic parameters of battery 
CN109709483A (en) *  20181226  20190503  天津瑞源电气有限公司  A kind of variablepitch system of wind turbine generator method for diagnosing faults 
CN109917298A (en) *  20171213  20190621  北京创昱科技有限公司  A kind of cell charge state prediction method and system 

2019
 20191112 CN CN201911101543.1A patent/CN110794319A/en active Pending
Patent Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

CN105116343A (en) *  20150824  20151202  桂林电子科技大学  LSSVM power cell SOC estimation method and system 
CN105444923A (en) *  20151118  20160330  浙江工业大学  Mechanical temperature instrument error prediction method based on geneticalgorithm optimized least square support vector machine 
CN105574231A (en) *  20151127  20160511  上海交通大学  Storage battery surplus capacity detection method 
CN106646253A (en) *  20161207  20170510  华南农业大学  Online identification method for intrinsic parameters of battery 
CN109917298A (en) *  20171213  20190621  北京创昱科技有限公司  A kind of cell charge state prediction method and system 
CN109709483A (en) *  20181226  20190503  天津瑞源电气有限公司  A kind of variablepitch system of wind turbine generator method for diagnosing faults 
NonPatent Citations (3)
Title 

李刚 等: "基于遗传算法最小二乘支持向量机蓄电池SOC估测", 《电源技术》 * 
解冰: "基于支持向量机的锂离子电池寿命预测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * 
陈严君: "锂电池阻抗模型参数的BP神经网络预测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * 
Cited By (2)
Publication number  Priority date  Publication date  Assignee  Title 

CN113049973A (en) *  20210602  20210629  河南工学院  Power battery detection device 
CN113049973B (en) *  20210602  20210813  河南工学院  Power battery detection device 
Similar Documents
Publication  Publication Date  Title 

JP5203394B2 (en)  Expert diagnostic method for analyzing storage battery performance.  
CN105589040B (en)  Battery based on aging adjustment battery operation section regulates and controls method  
CN101359036B (en)  Method for measuring state of charge of battery  
JP5936711B2 (en)  Storage device life prediction apparatus and storage device life prediction method  
CN101535827A (en)  Apparatus and method for determination of the stateofcharge of a battery when the battery is not in equilibrium  
CN108254696A (en)  The health state evaluation method and system of battery  
CN104577242B (en)  A kind of batteries management system and method  
JP6234946B2 (en)  Battery state estimation device  
CN106055775B (en)  A kind of service life of secondary cell prediction technique that particle filter is combined with mechanism model  
CN103412264A (en)  Method for evaluating consistency of single cells in storage battery pack  
CN107037375B (en)  Method and device for measuring direct current internal resistance of battery  
CN204030697U (en)  Based on the battery management system of dynamic SOC estimating system  
CN110794319A (en)  Method and device for predicting parameters of lithium battery impedance model and readable storage medium  
CN106033114A (en)  Health state evaluation method of energy storage battery  
Manwell et al.  Improvements to the Hybrid2 battery model  
CN110208702B (en)  Neural networkbased lithium battery ultrasonic information characteristic extraction method  
CN111142025A (en)  Battery SOC estimation method and device, storage medium and electric vehicle  
CN109613440A (en)  Stage division, device, equipment and the storage medium of battery  
CN109991545A (en)  A kind of battery pack detection method of quantity of electricity, device and terminal device  
TWI395963B (en)  Stateofhealth estimation method for leadacid batteries  
CN108120932A (en)  The method and apparatus estimated the cell health state of rechargeable battery  
KR20200023672A (en)  Diagnosis method of battery using Deep Learning  
CN109490790B (en)  Method and device for testing power characteristics of lithium power battery by adopting compensation pulse method  
CN110673037A (en)  Battery SOC estimation method and system based on improved simulated annealing algorithm  
TWI597510B (en)  Battery Life Cycle Prediction System and Method 
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 