CN107422266A - A kind of method for diagnosing faults and device of high capacity cell energy-storage system - Google Patents
A kind of method for diagnosing faults and device of high capacity cell energy-storage system Download PDFInfo
- Publication number
- CN107422266A CN107422266A CN201710153380.6A CN201710153380A CN107422266A CN 107422266 A CN107422266 A CN 107422266A CN 201710153380 A CN201710153380 A CN 201710153380A CN 107422266 A CN107422266 A CN 107422266A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- msubsup
- battery
- neural network
- 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
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims abstract description 39
- 238000003062 neural network model Methods 0.000 claims abstract description 31
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 34
- 238000013528 artificial neural network Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 18
- 230000002068 genetic effect Effects 0.000 claims description 12
- 239000000178 monomer Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 230000035772 mutation Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010792 warming Methods 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]
- G01R31/3644—Constructional arrangements
- G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The present invention relates to a kind of method for diagnosing faults and device of high capacity cell energy-storage system, including obtain the diagnostic data of battery energy storage system；Fault diagnosis is carried out using the diagnostic data as the BP neural network model that test sample input is built in advance, exports fault diagnosis result.The it is proposed of this programme solve thes problems, such as high capacity cell energy-storage system fault diagnosis difficulty so that fault diagnosis has higher accuracy.
Description
Technical Field
The invention belongs to the technical field of energy storage, and particularly relates to a fault diagnosis method and device for a high-capacity battery energy storage system.
Background
The problems of energy crisis, global warming and the like have led renewable energy sources such as wind energy, solar energy and the like to enter various fields of human life. In order to support the development of green technology, high-capacity battery energy storage systems have been developed. The high-capacity battery energy storage system is generally formed by connecting thousands of battery monomers in series and parallel, and due to the fact that the number of the battery monomers is large, whether the battery monomers break down or not is difficult to detect accurately in time, the faults of the battery monomers often endanger the whole energy storage system, and the safety and stability of the energy storage system directly influence the safety and stability of electric equipment and even the whole electric system, so that the high-capacity battery energy storage system has great significance in the research of fault diagnosis of the high-capacity battery energy storage system.
Disclosure of Invention
In order to make up for the technical blank, the invention provides a fault diagnosis method and a fault diagnosis device for a high-capacity battery energy storage system according to the characteristics of the high-capacity battery energy storage system, and a genetic algorithm is combined to optimize a BP neural network, so that a new direction is provided for fault diagnosis of the high-capacity battery energy storage system.
The purpose of the invention is realized by adopting the following technical scheme:
a fault diagnosis method for a high capacity battery energy storage system, the method comprising:
acquiring data to be diagnosed of the battery energy storage system;
inputting the data to be diagnosed as a test sample into a pre-constructed BP neural network model for fault diagnosis, and outputting a fault diagnosis result;
wherein the pre-constructed BP neural network model is terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiExtracting the ohmic internal resistance of the battery monomerSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fkntiObtained by training as a training sample.
Preferably, the construction process of the BP neural network model is as follows:
collecting terminal voltage signals of battery monomers through collection cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
Extracting a characteristic vector of the collected signals, and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
Inputting the normalized feature vector into an initial BP neural network, and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and training the optimized BP neural network to obtain a final BP neural network model.
Further, the sample entropy of the ohmic internal resistance of the battery cell is determined by the following formula:
in the formula,for the terminal voltage of the kth cell at the ith sampling point,for the ohmic internal resistance of the kth cell at the ith sampling point,is composed ofN is the number of sample points, H (R)k) The entropy of the k-th cell ohmic internal resistance.
Further, the penalty factor Ad of the battery pack is determined by the following formulai：
In the formula IiAnd UiThe current value and the voltage value of the ith sampling point of the battery energy storage system are respectively.
Further, the degree of membership of the amount of change in terminal voltage of the battery cell is determined by the following formula:
in the formula (f)staAs a function of the state of the battery energy storage system, fchaThe method comprises the following steps of taking an external characteristic function of the battery energy storage system, wherein n is the number of sampling points, C is a relative coefficient of a certain degree of the external characteristic of the battery energy storage system, and m is the number of single batteries; f. ofkntiIndicating voltage variation of ith sampling point of kth batteryDegree of membership.
Further, the normalizing the feature vector includes:
let the feature vector T ═ H (R)k),Adi,fknti]And the normalized feature vector T' is [ H (R) ]k)/Ek,Adi/Ek,fknti/Ek]，
Wherein T' is the normalized feature vector,fkntivoltage variation of ith sampling point for kth cellDegree of membership of H (R)k) Ohmic internal resistance of kth battery cellEntropy of (1), AdiIs a penalty factor for the battery.
Preferably, the output F of the BP neural network model is [ F1, F2, F3, F4], where F1 indicates no fault in the battery cell, F2 indicates an increase in internal resistance of the battery cell, F3 indicates a decrease in capacity of the battery cell, F4 indicates a short circuit in the battery cell, values of F1, F2, F3, and F4 are 0 or 1, 1 indicates the existence of the fault, and 0 indicates the absence of the fault.
Further, the optimizing the weight of the initial BP neural network by using a genetic algorithm includes:
determining a fitness function f (x) of each individual in the current population, and selecting m individuals with the highest or lowest fitness functions; the initial population comprises an initial weight value and a threshold value code in the BP neural network model;
and carrying out inheritance, crossover and mutation operations on the m individuals until a preset termination condition is met, and defining the individuals meeting the termination condition at present as an optimal weight threshold.
Further, the fitness function of each individual in the population is f (x) ═ P' -P2Wherein, f (x) represents a fitness function, P' is a predicted value of the test sample set, and P is a true value of the test sample set;
the preset termination condition is as follows: f, less than or equal to (x); wherein preset crossover and mutation probabilities are represented.
A fault diagnosis apparatus of a large capacity battery energy storage system, the apparatus comprising:
a model building module for pre-aligning the terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiTraining an input training sample to obtain a BP neural network model;
the acquisition module is used for acquiring data to be diagnosed of the battery energy storage system;
and the diagnosis module is used for inputting the data to be diagnosed as a test sample into the pre-constructed BP neural network model for fault diagnosis and outputting a fault diagnosis result.
Preferably, the model building module includes:
a collecting unit for collecting terminal voltage signals of the battery cells via a collecting cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
The processing unit is used for extracting the characteristic vector of the collected signal and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
The optimization unit is used for inputting the normalized feature vector into an initial BP neural network and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and the training unit is used for training the optimized BP neural network to obtain a final BP neural network model.
Compared with the closest prior art, the invention has the following beneficial effects:
according to the characteristics of the battery energy storage system, the sample entropy of ohmic internal resistance of a battery monomer, punishment factors of a battery pack and membership degree of voltage variation of the battery monomer are used as the input of an initial BP neural network after normalization processing, and a Genetic Algorithm (GA) is used for optimizing the weight of the initial BP neural network, so that the method and the device for diagnosing the faults of the high-capacity battery energy storage system are an important research direction for solving the problem of diagnosing the faults of the high-capacity battery energy storage system.
Secondly, training the optimized BP neural network to finally obtain a BP neural network model; the BP neural network model has the capability of diagnosing various faults simultaneously, can realize the fault diagnosis by taking the characteristic quantity for judging the faults of the battery energy storage system as a test sample, and outputs an accurate diagnosis result. The method provides an important technical support for fault diagnosis of the high-capacity battery energy storage system; therefore, the problem that the fault diagnosis of the high-capacity battery energy storage system is difficult is solved, and the fault diagnosis has higher accuracy.
Drawings
Fig. 1 is a flowchart of a fault diagnosis method for a high-capacity battery energy storage system provided in an embodiment of the present invention;
FIG. 2 is a flowchart of a method for optimizing weights of an initial BP neural network by using a genetic algorithm according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a BP neural network model provided in an embodiment of the present invention.
The specific implementation mode is as follows:
a fault diagnosis method for a high-capacity battery energy storage system, as shown in fig. 1, the method comprising:
acquiring data to be diagnosed of the battery energy storage system;
and inputting the data to be diagnosed as a test sample into a pre-constructed BP neural network model for fault diagnosis, and outputting a fault diagnosis result.
The construction process of the BP neural network model (I) is as follows:
1. collecting terminal voltage signals of battery monomers through collection cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
2. Extracting a characteristic vector of the collected signals, and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
Determining the sample entropy of the ohmic internal resistance of the battery cell by the following formula:
in the formula,for the terminal voltage of the kth cell at the ith sampling point,for the ohmic internal resistance of the kth cell at the ith sampling point,is composed ofN is the number of sample points, H (R)k) The entropy of the k-th cell ohmic internal resistance.
The penalty factor Ad of the battery is determined by the following formulai：
In the formula IiAnd UiThe current value and the voltage value of the ith sampling point of the battery energy storage system are respectively.
Determining a membership of the variation of the terminal voltage of the battery cell by:
in the formula (f)staAs a function of the state of the battery energy storage system, fchaThe method comprises the following steps of taking an external characteristic function of the battery energy storage system, wherein n is the number of sampling points, C is a relative coefficient of a certain degree of the external characteristic of the battery energy storage system, and m is the number of single batteries; f. ofkntiIndicating voltage variation of ith sampling point of kth batteryDegree of membership.
3. Inputting the normalized feature vector into an initial BP neural network, and optimizing the weight of the initial BP neural network by using a genetic algorithm;
let the feature vector T ═ H (R)k),Adi,fknti]And the normalized feature vector T' is [ H (R) ]k)/Ek,Adi/Ek,fknti/Ek]，
Wherein T' is the normalized feature vector,fkntivoltage variation of ith sampling point for kth cellDegree of membership of H (R)k) Ohmic internal resistance of kth battery cellEntropy of (1), AdiIs a penalty factor for the battery.
As shown in fig. 2, optimizing the weights of the initial BP neural network by using a genetic algorithm includes:
determining a fitness function f (x) of each individual in the current population, and selecting m individuals with the highest or lowest fitness functions; the initial population comprises an initial weight value and a threshold value code in the BP neural network model;
and carrying out inheritance, crossover and mutation operations on the m individuals until a preset termination condition is met, and defining the individuals meeting the termination condition at present as an optimal weight threshold.
The fitness function for each individual in the population is f (x) ═ P' -P2Wherein, f (x) represents a fitness function, P' is a predicted value of the test sample set, and P is a true value of the test sample set;
the preset termination condition is as follows: f (x) is less than or equal to 0.05; wherein preset crossover and mutation probabilities are represented.
4. Training the optimized BP neural network to obtain a final BP neural network model, as shown in FIG. 3. Wherein, the constructed BP neural network model is used for terminal voltage signals of the battery cellsTerminal voltage signal U of battery energy storage systemiAnd a current signal IiExtracting the ohmic internal resistance of the battery monomerSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fkntiObtained by training as a training sample.
And (II) finally performing fault diagnosis by using the BP neural network model, and outputting a fault diagnosis result F ═ F1, F2, F3 and F4], wherein F1 indicates that the battery cell has no fault, F2 indicates that the internal resistance of the battery cell is increased, F3 indicates that the capacity of the battery cell is reduced, F4 indicates that the battery cell is short-circuited, F1, F2, F3 and F4 take values of 0 or 1, 1 indicates that the fault exists, and 0 indicates that the fault does not exist.
Based on the same inventive concept, the invention also provides a fault diagnosis device of the high-capacity battery energy storage system, which comprises:
a model building module for pre-aligning the terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiTraining an input training sample to obtain a BP neural network model;
the acquisition module is used for acquiring data to be diagnosed of the battery energy storage system;
and the diagnosis module is used for inputting the data to be diagnosed as a test sample into the pre-constructed BP neural network model for fault diagnosis and outputting a fault diagnosis result.
Wherein, the model building module comprises:
a collecting unit for collecting terminal voltage signals of the battery cells via a collecting cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
The processing unit is used for extracting the characteristic vector of the collected signal and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
The optimization unit is used for inputting the normalized feature vector into an initial BP neural network and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and the training unit is used for training the optimized BP neural network to obtain a final BP neural network model.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting the protection scope thereof, and although the present application is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: numerous variations, modifications, and equivalents will occur to those skilled in the art upon reading the present application and are within the scope of the claims appended hereto.
Claims (11)
1. A fault diagnosis method for a high-capacity battery energy storage system is characterized by comprising the following steps:
acquiring data to be diagnosed of the battery energy storage system;
inputting the data to be diagnosed as a test sample into a pre-constructed BP neural network model for fault diagnosis, and outputting a fault diagnosis result;
wherein the pre-constructed BP neural network model is terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiExtracting the ohmic internal resistance of the battery monomerSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fkntiObtained by training as a training sample.
2. The method of claim 1, wherein the BP neural network model is constructed by:
collecting terminal voltage signals of battery monomers through collection cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
Extracting a characteristic vector of the collected signals, and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
Inputting the normalized feature vector into an initial BP neural network, and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and training the optimized BP neural network to obtain a final BP neural network model.
3. The method of claim 2, wherein the sample entropy of the ohmic internal resistance of the cell is determined by:
<mrow> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>=</mo> <mfrac> <msubsup> <mi>U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <msub> <mi>I</mi> <mi>i</mi> </msub> </mfrac> </mrow>
<mrow> <mi>H</mi> <mrow> <mo>(</mo> <msup> <mi>R</mi> <mi>k</mi> </msup> <mo>)</mo> </mrow> <mo>=</mo> <mo>-</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <mi>p</mi> <mrow> <mo>(</mo> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> <mi>log</mi> <mi> </mi> <mi>p</mi> <mrow> <mo>(</mo> <msubsup> <mi>R</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> </mrow>
in the formula,for the terminal voltage of the kth cell at the ith sampling point,for the ohmic internal resistance of the kth cell at the ith sampling point,is composed ofN is the number of sample points, H (R)k) The entropy of the k-th cell ohmic internal resistance.
4. The method of claim 2, wherein the penalty factor Ad for a battery is determined by the following equationi：
<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Ad</mi> <mi>i</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>U</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <mrow> <mo>(</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>U</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>|</mo> <mi>tanh</mi> <mrow> <mo>(</mo> <msub> <mi>&Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>|</mo> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>tanh</mi> <mrow> <mo>(</mo> <msub> <mi>&Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mrow> <mi>sinh</mi> <mrow> <mo>(</mo> <msub> <mi>&Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>cosh</mi> <mrow> <mo>(</mo> <msub> <mi>&Delta;I</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> </mfrac> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&Delta;I</mi> <mi>i</mi> </msub> <mo>=</mo> <msub> <mi>I</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced>
In the formula IiAnd UiThe current value and the voltage value of the ith sampling point of the battery energy storage system are respectively.
5. The method of claim 2, wherein the degree of membership of the amount of change in terminal voltage of the battery cell is determined by:
<mrow> <msub> <mi>f</mi> <mrow> <mi>k</mi> <mi>n</mi> <mi>t</mi> <mi>i</mi> </mrow> </msub> <mo>=</mo> <msub> <mi>f</mi> <mrow> <mi>s</mi> <mi>t</mi> <mi>a</mi> </mrow> </msub> <mo>*</mo> <msub> <mi>f</mi> <mrow> <mi>c</mi> <mi>h</mi> <mi>a</mi> </mrow> </msub> <mrow> <mo>(</mo> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> </mrow>1
<mrow> <msub> <mi>f</mi> <mrow> <mi>c</mi> <mi>h</mi> <mi>a</mi> </mrow> </msub> <mrow> <mo>(</mo> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>n</mi> <mo>*</mo> <mfrac> <mrow> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mrow> <mi>C</mi> <munderover> <mi>&Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> </mfrac> <mn>...</mn> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>&le;</mo> <mfrac> <mrow> <mi>C</mi> <munderover> <mi>&Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mi>n</mi> </mfrac> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>1...</mn> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> <mo>></mo> <mfrac> <mrow> <mi>C</mi> <munderover> <mi>&Sigma;</mi> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msubsup> <mi>&Delta;U</mi> <mi>i</mi> <mi>k</mi> </msubsup> </mrow> <mi>n</mi> </mfrac> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
in the formula (f)staAs a function of the state of the battery energy storage system, fchaThe method comprises the following steps of taking an external characteristic function of the battery energy storage system, wherein n is the number of sampling points, C is a relative coefficient of a certain degree of the external characteristic of the battery energy storage system, and m is the number of single batteries; f. ofkntiIndicating voltage variation of ith sampling point of kth batteryDegree of membership.
6. The method of claim 2, wherein the normalizing the feature vectors comprises:
let the feature vector T ═ H (R)k),Adi,fknti]And the normalized feature vector T' is [ H (R) ]k)/Ek,Adi/Ek,fknti/Ek]，
Wherein,fkntivoltage variation of ith sampling point for kth cellDegree of membership of H (R)k) Ohmic internal resistance of kth battery cellEntropy of (1), AdiIs a penalty factor for the battery.
7. The method of claim 1, wherein an output F of the BP neural network model is [ F1, F2, F3, F4], F1 indicates no fault in the battery cell, F2 indicates an increase in internal resistance of the battery cell, F3 indicates a decrease in capacity of the battery cell, F4 indicates a short circuit in the battery cell, F1, F2, F3, F4 take a value of 0 or 1, 1 indicates the existence of the fault, and 0 indicates the absence of the fault.
8. The method of claim 2, wherein the optimizing the weights of the initial BP neural network using a genetic algorithm comprises:
determining a fitness function f (x) of each individual in the current population, and selecting m individuals with the highest or lowest fitness functions; the initial population comprises an initial weight value and a threshold value code in the BP neural network model;
and carrying out inheritance, crossover and mutation operations on the m individuals until a preset termination condition is met, and defining the individuals meeting the termination condition at present as an optimal weight threshold.
9. The method of claim 8, wherein the fitness function for each individual in the population is f (x) ═ P' -P2Wherein, f (x) represents a fitness function, P' is a predicted value of the test sample set, and P is a true value of the test sample set;
the preset termination condition is as follows: f, less than or equal to (x); wherein preset crossover and mutation probabilities are represented.
10. A fault diagnosis device for a high capacity battery energy storage system, the device comprising:
a model building module for pre-aligning the terminal voltage signal of the battery cellTerminal voltage signal U of battery energy storage systemiAnd a current signal IiTraining an input training sample to obtain a BP neural network model;
the acquisition module is used for acquiring data to be diagnosed of the battery energy storage system;
and the diagnosis module is used for inputting the data to be diagnosed as a test sample into the pre-constructed BP neural network model for fault diagnosis and outputting a fault diagnosis result.
11. The apparatus of claim 10, wherein the model building module comprises:
a collecting unit for collecting terminal voltage signals of the battery cells via a collecting cardTerminal voltage signal U of battery energy storage systemiAnd a current signal Ii；
The processing unit is used for extracting the characteristic vector of the collected signal and normalizing the characteristic vector; the characteristic vector comprises the ohmic internal resistance of the battery cellSample entropy of (1), penalty factor Ad of battery packiAnd cell terminal voltage variationDegree of membership fknti；
The optimization unit is used for inputting the normalized feature vector into an initial BP neural network and optimizing the weight of the initial BP neural network by using a genetic algorithm;
and the training unit is used for training the optimized BP neural network to obtain a final BP neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710153380.6A CN107422266B (en) | 2017-03-15 | 2017-03-15 | Fault diagnosis method and device for high-capacity battery energy storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710153380.6A CN107422266B (en) | 2017-03-15 | 2017-03-15 | Fault diagnosis method and device for high-capacity battery energy storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107422266A true CN107422266A (en) | 2017-12-01 |
| CN107422266B CN107422266B (en) | 2021-04-16 |
Family
ID=60423468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710153380.6A Active CN107422266B (en) | 2017-03-15 | 2017-03-15 | Fault diagnosis method and device for high-capacity battery energy storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107422266B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363016A (en) * | 2018-02-22 | 2018-08-03 | 上海理工大学 | Battery micro-short circuit quantitative Diagnosis method based on artificial neural network |
| CN109061495A (en) * | 2018-08-07 | 2018-12-21 | 中国电建集团福建省电力勘测设计院有限公司 | A kind of hybrid energy-storing battery failure diagnostic method |
| CN109085507A (en) * | 2018-07-31 | 2018-12-25 | 中国电力科学研究院有限公司 | A kind of method and system for assessing energy-storage battery health status |
| CN109283469A (en) * | 2018-09-21 | 2019-01-29 | 四川长虹电器股份有限公司 | Battery management system failure prediction method, device and readable storage medium storing program for executing |
| CN109375116A (en) * | 2018-08-09 | 2019-02-22 | 上海国际汽车城（集团）有限公司 | A kind of battery system exception battery discriminating method based on self-encoding encoder |
| CN109840593A (en) * | 2019-01-28 | 2019-06-04 | 华中科技大学鄂州工业技术研究院 | Diagnose the method and apparatus of solid oxide fuel battery system failure |
| CN109991556A (en) * | 2019-04-08 | 2019-07-09 | 洛阳理工学院 | A kind of diagnostic method for the short-term failure failure of lithium iron phosphate dynamic battery |
| CN110286333A (en) * | 2019-06-18 | 2019-09-27 | 哈尔滨理工大学 | A kind of lithium dynamical battery diagnosis method for system fault |
| CN110703109A (en) * | 2019-10-25 | 2020-01-17 | 山东大学 | Battery string multi-fault diagnosis method and system based on correction sample entropy |
| CN112858917A (en) * | 2021-01-15 | 2021-05-28 | 哈尔滨工业大学（威海） | Battery system multi-fault diagnosis method based on genetic algorithm optimization neural network |
| CN113325317A (en) * | 2021-07-08 | 2021-08-31 | 山东大学 | Power battery fault diagnosis method and system based on improved RBF neural network |
| CN113376534A (en) * | 2021-05-12 | 2021-09-10 | 山东大学 | Phase plane diagnosis method for early fault of power battery and advanced early warning system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090112395A1 (en) * | 2007-10-31 | 2009-04-30 | Toyota Motor Engineering & Manufacturing North America, Inc.. | System for detecting a battery malfunction and performing battery mitigation for an hev |
| CN105223510A (en) * | 2015-09-01 | 2016-01-06 | 国家电网公司 | A kind of battery pack based on internal resistance Information Entropy falls behind cell method of discrimination |
| CN106226700A (en) * | 2016-07-17 | 2016-12-14 | 安徽卓越电气有限公司 | Lithium battery detection platform system and method for testing |
| CN106482938A (en) * | 2016-10-14 | 2017-03-08 | 温州大学 | Brake fluid system multi-source fusion fault predicting method based on GA BP network |
-
2017
- 2017-03-15 CN CN201710153380.6A patent/CN107422266B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090112395A1 (en) * | 2007-10-31 | 2009-04-30 | Toyota Motor Engineering & Manufacturing North America, Inc.. | System for detecting a battery malfunction and performing battery mitigation for an hev |
| CN105223510A (en) * | 2015-09-01 | 2016-01-06 | 国家电网公司 | A kind of battery pack based on internal resistance Information Entropy falls behind cell method of discrimination |
| CN106226700A (en) * | 2016-07-17 | 2016-12-14 | 安徽卓越电气有限公司 | Lithium battery detection platform system and method for testing |
| CN106482938A (en) * | 2016-10-14 | 2017-03-08 | 温州大学 | Brake fluid system multi-source fusion fault predicting method based on GA BP network |
Non-Patent Citations (1)
| Title |
|---|
| ZUCHANG GAO等: "Genetic Algorithm based Back-Propagation Neural Network approach for fault diagnosis in lithium-ion battery system", 《2015 6TH INTERNATIONAL CONFERENCE ON POWER ELECTRONICS SYSTEMS AND APPLICATIONS》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363016A (en) * | 2018-02-22 | 2018-08-03 | 上海理工大学 | Battery micro-short circuit quantitative Diagnosis method based on artificial neural network |
| CN109085507A (en) * | 2018-07-31 | 2018-12-25 | 中国电力科学研究院有限公司 | A kind of method and system for assessing energy-storage battery health status |
| CN109085507B (en) * | 2018-07-31 | 2022-04-15 | 中国电力科学研究院有限公司 | Method and system for evaluating health state of energy storage battery |
| CN109061495A (en) * | 2018-08-07 | 2018-12-21 | 中国电建集团福建省电力勘测设计院有限公司 | A kind of hybrid energy-storing battery failure diagnostic method |
| CN109375116B (en) * | 2018-08-09 | 2021-12-14 | 上海国际汽车城（集团）有限公司 | Battery system abnormal battery identification method based on self-encoder |
| CN109375116A (en) * | 2018-08-09 | 2019-02-22 | 上海国际汽车城（集团）有限公司 | A kind of battery system exception battery discriminating method based on self-encoding encoder |
| CN109283469A (en) * | 2018-09-21 | 2019-01-29 | 四川长虹电器股份有限公司 | Battery management system failure prediction method, device and readable storage medium storing program for executing |
| CN109840593A (en) * | 2019-01-28 | 2019-06-04 | 华中科技大学鄂州工业技术研究院 | Diagnose the method and apparatus of solid oxide fuel battery system failure |
| CN109840593B (en) * | 2019-01-28 | 2023-09-05 | 华中科技大学鄂州工业技术研究院 | Method and apparatus for diagnosing solid oxide fuel cell system failure |
| CN109991556B (en) * | 2019-04-08 | 2021-03-19 | 洛阳理工学院 | Diagnosis method for short-term failure fault of lithium iron phosphate power battery |
| CN109991556A (en) * | 2019-04-08 | 2019-07-09 | 洛阳理工学院 | A kind of diagnostic method for the short-term failure failure of lithium iron phosphate dynamic battery |
| CN110286333B (en) * | 2019-06-18 | 2021-09-24 | 哈尔滨理工大学 | Fault diagnosis method for lithium power battery system |
| CN110286333A (en) * | 2019-06-18 | 2019-09-27 | 哈尔滨理工大学 | A kind of lithium dynamical battery diagnosis method for system fault |
| CN110703109A (en) * | 2019-10-25 | 2020-01-17 | 山东大学 | Battery string multi-fault diagnosis method and system based on correction sample entropy |
| CN110703109B (en) * | 2019-10-25 | 2020-07-07 | 山东大学 | Battery string multi-fault diagnosis method and system based on correction sample entropy |
| US11959973B2 (en) | 2019-10-25 | 2024-04-16 | Shandong University | Multi-fault diagnosis method and system for battery packs based on corrected sample entropy |
| CN112858917A (en) * | 2021-01-15 | 2021-05-28 | 哈尔滨工业大学（威海） | Battery system multi-fault diagnosis method based on genetic algorithm optimization neural network |
| CN113376534A (en) * | 2021-05-12 | 2021-09-10 | 山东大学 | Phase plane diagnosis method for early fault of power battery and advanced early warning system |
| CN113376534B (en) * | 2021-05-12 | 2022-04-05 | 山东大学 | Phase plane diagnosis method for early fault of power battery and advanced early warning system |
| CN113325317A (en) * | 2021-07-08 | 2021-08-31 | 山东大学 | Power battery fault diagnosis method and system based on improved RBF neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107422266B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107422266B (en) | Fault diagnosis method and device for high-capacity battery energy storage system | |
| CN112858919B (en) | Battery system online fault diagnosis method and system based on cluster analysis | |
| CN110752410B (en) | Method for rapidly sorting and recombining retired lithium battery | |
| CN109031145B (en) | Series-parallel battery pack model considering inconsistency and implementation method | |
| CN111007417A (en) | Battery pack SOH and RUL prediction method and system based on inconsistency evaluation | |
| CN109165687A (en) | Vehicle lithium battery method for diagnosing faults based on multi-category support vector machines algorithm | |
| CN106026260A (en) | SOC estimation method for series-wound battery pack having equalization circuit | |
| CN107192953B (en) | A kind of energy-storage battery soft fault diagnosis method based on GA-Elman | |
| CN108872869B (en) | Lithium ion battery degradation classification method based on BP neural network | |
| CN102937704A (en) | Method for identifying RC (resistor-capacitor) equivalent model of power battery | |
| CN113866642A (en) | Lithium ion battery fault diagnosis method based on gradient lifting tree | |
| CN104502844A (en) | Power lithium battery deterioration degree diagnosis method based on AC impedance | |
| CN105242212A (en) | Lithium iron phosphate battery health state characteristic parameter extraction method for battery gradient utilization | |
| CN114818831B (en) | Bidirectional lithium ion battery fault detection method and system based on multi-source perception | |
| CN115327403A (en) | Power battery safety evaluation method and device based on new energy automobile big data | |
| CN109613446A (en) | A kind of aging of lithium battery detection method based on time series analysis | |
| CN111208436A (en) | Energy storage battery overcharge diagnosis method based on IMF energy moment and genetic algorithm optimization SVM | |
| CN110866366A (en) | XGboost algorithm-based island detection method for photovoltaic microgrid containing PHEV | |
| CN113406520A (en) | Battery health state estimation method for real new energy automobile | |
| CN112686380A (en) | Neural network-based echelon power cell consistency evaluation method and system | |
| CN111983464A (en) | Lithium battery lithium separation testing method based on pure electric vehicle | |
| CN115389955A (en) | Differential pressure prediction method and device for total pressure test inside and outside battery | |
| CN115980588A (en) | Lithium ion battery health state estimation method based on self-encoder extraction features | |
| CN112595918A (en) | Low-voltage meter reading fault detection method and device | |
| CN117110925A (en) | Method and system for evaluating health state of battery pack |
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 |