CN113608140A - Battery fault diagnosis method and system - Google Patents
Battery fault diagnosis method and system Download PDFInfo
- Publication number
- CN113608140A CN113608140A CN202110713083.9A CN202110713083A CN113608140A CN 113608140 A CN113608140 A CN 113608140A CN 202110713083 A CN202110713083 A CN 202110713083A CN 113608140 A CN113608140 A CN 113608140A
- Authority
- CN
- China
- Prior art keywords
- battery
- fault
- current
- voltage
- temperature information
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 39
- 238000012423 maintenance Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000011176 pooling Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 208000032953 Device battery issue Diseases 0.000 claims description 6
- 230000032683 aging Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000013021 overheating Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 230000004927 fusion Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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
- G01R31/005—Testing of electric installations on transport means
- G01R31/006—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks
- G01R31/007—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks using microprocessors or computers
-
- 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]
- G01R31/385—Arrangements for measuring battery or accumulator 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]
- G01R31/389—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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/54—Testing for continuity
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Secondary Cells (AREA)
Abstract
The present disclosure provides a battery fault diagnosis method, which collects voltage, current and temperature information of a battery in real time; preprocessing the acquired voltage, current and temperature information of the battery and then inputting the preprocessed voltage, current and temperature information into a trained convolutional neural network model to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery; sending the battery fault diagnosis result to a power distribution network master control center, and giving an alarm to operation and maintenance personnel; the influence of the voltage, current and temperature information of the battery on the battery fault diagnosis result is comprehensively considered, and the convolutional neural network is used for diagnosis, so that the accuracy of battery fault diagnosis can be effectively improved.
Description
Technical Field
The disclosure relates to the technical field of battery fault diagnosis, in particular to a battery fault diagnosis method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The current development situation at home and abroad is as follows: according to the requirements of the battery management system standard established by the International Electrotechnical Commission (IEC) in 1995, the battery management system for the electric vehicle must have certain battery diagnosis functions including early warning of an unhealthy battery and providing battery aging information. In more than 10 years, various foreign companies have conducted intensive research on the situation and add certain battery diagnosis function to the battery management system used for operation.
The large-scale battery energy storage is large in application scale on electric power, a backup power supply and an electric automobile, and is usually used by connecting hundreds of batteries in series. Over the years of development, some batteries are in service and some are in or have been retired. No matter the battery is in service or returned, the battery is idle and lacks effective management.
However, the inventors have found that the current diagnostic method for a battery cannot meet the demand for battery failure diagnosis accuracy because only a single battery parameter is used for failure diagnosis.
Disclosure of Invention
The present disclosure is directed to solve the above problems, and provides a battery fault diagnosis method and system, in which a convolutional neural network is used to diagnose a battery fault, and the common influence of multiple parameters is considered, so that the accuracy of battery fault diagnosis can be effectively improved.
In order to achieve the above object, in a first aspect, the present disclosure provides a battery fault diagnosis method:
collecting voltage, current and temperature information of a battery in real time;
preprocessing the acquired voltage, current and temperature information of the battery and then inputting the preprocessed voltage, current and temperature information into a trained convolutional neural network model to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
and sending the battery fault diagnosis result to a power distribution network master control center, and giving an alarm to operation and maintenance personnel.
In a second aspect, the present disclosure provides a battery fault diagnosis system;
the battery data acquisition module is configured to acquire voltage, current and temperature information of the battery in real time;
the battery fault diagnosis module is configured to input the acquired voltage, current and temperature information of the battery into a trained convolutional neural network model after data preprocessing so as to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
and the battery fault diagnosis result output module is configured to send the battery fault diagnosis result to the power distribution network main control center and give an alarm to operation and maintenance personnel.
In a third aspect, the present disclosure also provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method of the first aspect.
In a fourth aspect, the present disclosure also provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of the first aspect.
The beneficial effect of this disclosure:
1. the method comprehensively considers the influence of the voltage, the current and the temperature information of the battery on the battery fault diagnosis result, utilizes the convolutional neural network to diagnose, and can effectively improve the precision of the battery fault diagnosis.
2. According to the convolutional neural network recognition method and device, the connecting layer is added in front of the full connecting layer, the features of different layers are fused in the connecting layer, the overfitting phenomenon caused by the features of only deep layers is reduced, and therefore the training efficiency and recognition accuracy of the convolutional neural network are further improved.
Drawings
Fig. 1 is a schematic flowchart of a battery fault diagnosis method according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a battery fault diagnosis system according to a second embodiment of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it is to be understood that when "comprising" and/or "includes" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
The present disclosure is further described with reference to the following drawings and examples.
Example one
As shown in fig. 1, the present embodiment provides a battery fault diagnosis method including:
s1: collecting voltage, current and temperature information of a battery in real time;
s2: preprocessing the acquired voltage, current and temperature information of the battery and then inputting the preprocessed voltage, current and temperature information into a trained convolutional neural network model to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
s3: and sending the battery fault diagnosis result to a power distribution network master control center, and giving an alarm to operation and maintenance personnel.
In the embodiment, the convolutional neural network is adopted to identify the fault type of the battery, the convolutional structure of the convolutional neural network can optimize the parameter structure of the deep network, the artificial neural network technology and the deep learning method are combined conveniently, the multi-layer filter network structure of the sub-deep learning and the global training algorithm combining the filter and the classifier are realized, the identification result can be obtained directly, effectively, quickly and accurately, the detected unstructured data is prevented from being converted into structured data, and the high efficiency and robustness of identification can be ensured.
The process of training the convolutional neural network model specifically comprises the following steps:
collecting voltage, current and temperature information of batteries corresponding to various battery fault types;
according to the collected voltage, current and temperature information of the battery and the corresponding battery fault type, constructing a map data training set of the voltage, current and temperature information of the battery;
constructing a convolutional neural network structure model, designing a corresponding convolutional neural network structure according to the fault type of the battery to be tested, and calculating the initialization parameters of the convolutional neural network;
and training the convolutional neural network by using a training set, inputting the voltage of the battery and the atlas data training set of the temperature information into the convolutional neural network for training, and correcting various parameters of the convolutional neural network.
A Convolutional Neural Network (CNN) is a typical deep learning algorithm and is widely used in the field of image recognition. Compared with the traditional shallow layer network, the convolutional neural network has stronger characteristic extraction capability and high operation speed, and avoids the problem that training is easy to trap human local extremum. In recent years, scholars at home and abroad apply the convolutional neural network to fault diagnosis and obtain good research results, wherein a feedback mechanism is added on the basis of the traditional CNN network to improve the accuracy of insulator state detection by adjusting the number and size of convolutional kernels. Or generating a time-frequency spectrogram of a bearing vibration signal by using short-time Fourier transform, establishing a CNN diagnosis model, and verifying robustness by adding data of corresponding environment; in order to further improve the accuracy of the convolutional neural network in battery fault diagnosis, a connection layer is added into the convolutional neural network, and the structure of the convolutional neural network specifically comprises the following steps:
the system comprises an input layer, a hidden layer, a link layer, a full connection layer and an output layer; the hidden layer is formed by alternately stacking a plurality of convolution layers and pooling layers; the different hierarchical features of the pooling layer and the convolutional layer are fused simultaneously in the connection layer.
A method for adding a connection layer before a full connection layer and simultaneously fusing different hierarchical features in the connection layer is provided. When the classifier classifies, the overfitting caused by only deep-level features is reduced by taking the mutually complementary fusion features as the standard. The operation process of the connecting layer is
Xc=fc(xc-1,xm) (1)
In the formula: xcIs a fused feature; f. ofc(. a) feature fusion operation; x is the number ofc-1The characteristic vector of the previous layer of the connection layer; x is the number ofmIs the feature vector to be fused at the mth layer.
If the last layer of features and the low-layer features which are not pooled are selected during the fusion of the connection layers, the occupation ratio of the high-layer features is small, and the precision of fault diagnosis is influenced. Therefore, the connection layer fuses the shallow features after the first layer of pooling with the high-level features extracted from the last layer of convolutional layer. And connecting the fusion results in the connection layer into a one-dimensional vector in the full connection layer. Because the one-dimensional data is used as the feature vector in the method, the size of the feature data does not need to be considered in the feature fusion, and the problem of structural limitation or feature data loss in the traditional CNN feature fusion is avoided.
And (3) carrying out convolution operation on the 1 x 18-dimensional feature data of the input human layer and 3 1 x 3-dimensional convolution kernels in the convolution layer to form 3 1 x 16-dimensional feature vectors, continuing the pooling and convolution operation, fusing different hierarchical features in the pooling layer and the C2 convolution layer at the connection layer, connecting the different hierarchical features into one-dimensional vectors at the full connection layer, and finally finishing diagnosis output through a classifier.
The convolution layer is mainly used for convolving an input image with a convolution filter thereof, each local filter can repeatedly act on the whole receptive field, convolution operation is carried out on input data, weight sharing is achieved, and network parameters are reduced. Finally, the convolution value generates a plurality of feature maps of the input data through an activation function, the feature maps contain effective features of the image data, and a calculation formula for performing convolution on the input image data by using a convolution filter can be as follows:
wherein the content of the first and second substances,j-th feature map representing the l-th layer, M being a set of input feature maps, representing a convolution operation,is the convolution kernel matrix of the l-th layer,is the characteristic bias of the convolution kernel, and f (×) is the activation function, which is effectively a non-linear excitation function.
In the embodiment, the use of the ReLU activation function enables the network to introduce sparsity by itself, which is equivalent to pre-training of unsupervised learning.
The activation function expression may be:
f(x)=max(0,x) (3)
the convolution operation is the filter weight ω, ω ∈ RNAnd cumulative expression xi:i+N-1Multiplication operation between xi:i+N-1Refers to the cumulative representation of the N sequence points connected to the filter. After the original image data with the input length of D is subjected to filter convolution operation, a feature map expression is obtained as follows:
wherein, the characteristic dimension is D-N +1, and j represents the jth filter.
And the pooling layer completes the pooling step and performs local averaging and secondary extraction on the feature map obtained by the input convolutional layer. The secondary extraction of features may be performed using maximum pooling. The method is applied to the pooling layer, the pooling layer sub-samples the image characteristics, the data processing amount can be reduced, and the previous layer is subjected toIn order to reduce the resolution of the characteristic diagram, the operation can reduce the data volume, simultaneously reserve useful key information to the maximum extent, eliminate offset and image distortion, reduce the calculation time and reduce the sensitivity of network output to displacement and deformation. The secondary extraction comprises maximum pooling and average pooling, the maximum pooling has a better effect on image texture extraction, the maximum pooling mode is selected in the embodiment, and the jth feature map of the ith pooling layerCan be obtained from the following formula:
down () is a down-sampling function,is a characteristic diagramIs generated by the first and second linear phase-shift,is a convolution signatureIs uniquely additive.
For the multi-classification problem, a Softmax classifier can be chosen, which can be derived from the binary class by logistic regression, wide to multi-classification, and for a given input x, we need to compute the probability value p (y ═ j | x) that it belongs to each class j, so in Softmax regression, we assume that the function h isθ(x) A k-dimensional vector will be output to represent the probability that the input belongs to each class.
The output layer outputs a real number vector, the number of nodes of the real number vector is consistent with the classified number, the number of the output nodes in the embodiment is the number of the partial discharge defect types, the output value of each node represents the probability that the sample belongs to the corresponding type, the result of the final output layer is the identification probability of each type, and the identification result can be judged through the size relationship, so that the identification result can be output.
In a specific embodiment, the battery is composed of a plurality of battery cells, and the voltage, current and temperature information of the battery includes voltage, current and temperature data of each battery cell.
The method for acquiring the battery fault type comprises the following steps:
acquiring historical voltage, current and temperature information data of the battery;
and judging the battery fault type corresponding to the historical voltage, current and temperature information data of the battery according to the priori knowledge.
Specific battery failure types include:
an overheat fault, an overcooling fault, an overcharge fault, an overdischarge fault, a short circuit fault, an open circuit fault, an aging fault, and an internal resistance over-small fault.
In a specific embodiment, the determination conditions of the battery failure type are:
when the temperature of the single battery is greater than the maximum threshold value of the temperature of the single battery, determining that the battery has an overheating fault;
when the temperature of the single battery is smaller than the minimum threshold value of the temperature of the single battery, determining that the battery has an overcooling fault;
when the voltage of the single battery is larger than the maximum threshold value of the voltage of the single battery, determining that the battery has an overcharge fault;
when the voltage of the single battery is smaller than the minimum threshold value of the voltage of the single battery, determining that the over-discharge fault occurs to the battery;
when the current of the single battery is larger than the maximum threshold value of the current of the single battery, determining that the short-circuit fault occurs in the battery;
when the current of the single battery is smaller than the minimum threshold value of the current of the single battery, determining that the open circuit fault occurs in the battery;
when the internal resistance of the battery is larger than the maximum threshold value of the internal resistance of the battery, determining that the battery has an aging fault;
and when the internal resistance of the battery is smaller than the minimum threshold value of the internal resistance of the battery, determining that the internal resistance of the battery is too small.
Example two
The present embodiment provides a battery failure diagnosis system, including:
the battery data acquisition module is configured to acquire voltage, current and temperature information of the battery in real time;
the battery fault diagnosis module is configured to input the acquired voltage, current and temperature information of the battery into a trained convolutional neural network model after data preprocessing so as to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
and the battery fault diagnosis result output module is configured to send the battery fault diagnosis result to the power distribution network main control center and give an alarm to operation and maintenance personnel.
In a specific embodiment, the battery fault output module is in wired communication connection with the power distribution network main control center, and a battery fault diagnosis result is sent to the power distribution network main control center, so that operation and maintenance personnel can check the battery fault diagnosis result conveniently.
EXAMPLE III
The present embodiment provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, the computer instructions, when executed by the processor, performing the steps of the method of the first embodiment.
Example four
The present embodiment provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of the first embodiment.
Those skilled in the art will appreciate that the modules or steps of the present disclosure described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code executable by computing means, whereby the modules or steps may be stored in memory means for execution by the computing means, or separately fabricated into individual integrated circuit modules, or multiple modules or steps thereof may be fabricated into a single integrated circuit module. The present disclosure is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. A battery fault diagnosis method is characterized by comprising the following steps:
collecting voltage, current and temperature information of a battery in real time;
preprocessing the acquired voltage, current and temperature information of the battery and then inputting the preprocessed voltage, current and temperature information into a trained convolutional neural network model to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
and sending the battery fault diagnosis result to a power distribution network master control center, and giving an alarm to operation and maintenance personnel.
2. The method according to claim 1, wherein the battery is composed of a plurality of battery cells, and the voltage, current and temperature information of the battery includes voltage, current and temperature data of each battery cell.
3. The battery fault diagnosis method according to claim 1, wherein the process of training the convolutional neural network model specifically comprises:
collecting voltage, current and temperature information of batteries corresponding to various battery fault types;
according to the collected voltage, current and temperature information of the battery and the corresponding battery fault type, constructing a map data training set of the voltage, current and temperature information of the battery;
constructing a convolutional neural network structure model, designing a corresponding convolutional neural network structure according to the fault type of the battery to be tested, and calculating the initialization parameters of the convolutional neural network;
and training the convolutional neural network by using a training set, inputting the voltage of the battery and the atlas data training set of the temperature information into the convolutional neural network for training, and correcting various parameters of the convolutional neural network.
4. The battery fault diagnosis method according to claim 3, wherein the method for acquiring the type of the battery fault comprises:
acquiring historical voltage, current and temperature information data of the battery;
and judging the battery fault type corresponding to the historical voltage, current and temperature information data of the battery according to the priori knowledge.
5. The battery fault diagnosis method according to claim 4, wherein the battery fault types include:
an overheat fault, an overcooling fault, an overcharge fault, an overdischarge fault, a short circuit fault, an open circuit fault, an aging fault, and an internal resistance over-small fault.
6. The battery failure diagnosis method according to claim 5, wherein the determination condition of the type of the battery failure is:
when the temperature of the single battery is greater than the maximum threshold value of the temperature of the single battery, determining that the battery has an overheating fault;
when the temperature of the single battery is smaller than the minimum threshold value of the temperature of the single battery, determining that the battery has an overcooling fault;
when the voltage of the single battery is larger than the maximum threshold value of the voltage of the single battery, determining that the battery has an overcharge fault;
when the voltage of the single battery is smaller than the minimum threshold value of the voltage of the single battery, determining that the over-discharge fault occurs to the battery;
when the current of the single battery is larger than the maximum threshold value of the current of the single battery, determining that the short-circuit fault occurs in the battery;
when the current of the single battery is smaller than the minimum threshold value of the current of the single battery, determining that the open circuit fault occurs in the battery;
when the internal resistance of the battery is larger than the maximum threshold value of the internal resistance of the battery, determining that the battery has an aging fault;
and when the internal resistance of the battery is smaller than the minimum threshold value of the internal resistance of the battery, determining that the internal resistance of the battery is too small.
7. The battery fault diagnosis method according to claim 1, wherein the convolutional neural network structure comprises an input layer, a hidden layer, a link layer, a full-link layer and an output layer; the hidden layer is formed by alternately stacking a plurality of convolution layers and pooling layers;
and different hierarchical features of the pooling layer and the convolutional layer are fused in the connecting layer at the same time.
8. A battery fault diagnosis system, comprising:
the battery data acquisition module is configured to acquire voltage, current and temperature information of the battery in real time;
the battery fault diagnosis module is configured to input the acquired voltage, current and temperature information of the battery into a trained convolutional neural network model after data preprocessing so as to generate and output a battery fault diagnosis result of the acquired voltage, current and temperature information of the battery;
and the battery fault diagnosis result output module is configured to send the battery fault diagnosis result to the power distribution network main control center and give an alarm to operation and maintenance personnel.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executable on the processor, the computer instructions when executed by the processor performing the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110713083.9A CN113608140A (en) | 2021-06-25 | 2021-06-25 | Battery fault diagnosis method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110713083.9A CN113608140A (en) | 2021-06-25 | 2021-06-25 | Battery fault diagnosis method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113608140A true CN113608140A (en) | 2021-11-05 |
Family
ID=78303748
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110713083.9A Pending CN113608140A (en) | 2021-06-25 | 2021-06-25 | Battery fault diagnosis method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113608140A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114646880A (en) * | 2022-04-13 | 2022-06-21 | 中国铁塔股份有限公司江西省分公司 | Intelligent diagnosis method and system for lead-acid battery |
CN114742297A (en) * | 2022-04-11 | 2022-07-12 | 中国第一汽车股份有限公司 | Power battery treatment method |
CN114781551A (en) * | 2022-06-16 | 2022-07-22 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
CN116879761A (en) * | 2023-09-06 | 2023-10-13 | 杭州宇谷科技股份有限公司 | Multi-mode-based battery internal short circuit detection method, system, device and medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409431A (en) * | 2018-10-29 | 2019-03-01 | 吉林大学 | Multisensor attitude data fusion method and system neural network based |
CN109583507A (en) * | 2018-12-07 | 2019-04-05 | 浙江工商大学 | A kind of pig body recognition methods based on depth convolutional neural networks |
CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
CN110308397A (en) * | 2019-07-30 | 2019-10-08 | 重庆邮电大学 | A kind of lithium battery multiclass fault diagnosis modeling method of mixing convolutional neural networks driving |
CN110309795A (en) * | 2019-07-04 | 2019-10-08 | 腾讯科技(深圳)有限公司 | Video detecting method, device, electronic equipment and storage medium |
CN110426637A (en) * | 2019-07-04 | 2019-11-08 | 佛山科学技术学院 | A kind of battery failures diagnostic method neural network based and device |
CN111652348A (en) * | 2020-02-29 | 2020-09-11 | 上海电力大学 | Power battery pack fault fusion diagnosis method and system based on improved CNN |
CN111865702A (en) * | 2020-08-04 | 2020-10-30 | 北京航空航天大学 | Network fault diagnosis method and device based on convolutional neural network |
CN112215197A (en) * | 2020-10-27 | 2021-01-12 | 华能国际电力股份有限公司上海石洞口第一电厂 | Underground cable fault early warning method and system based on artificial intelligence |
CN112666480A (en) * | 2020-12-02 | 2021-04-16 | 西安交通大学 | Battery life prediction method based on charging process characteristic attention |
US20210119576A1 (en) * | 2019-10-16 | 2021-04-22 | Tata Consultancy Services Limited | Methods and systems for fault detection, diagnosis and localization in solar panel network |
CN112946497A (en) * | 2020-12-04 | 2021-06-11 | 广东电网有限责任公司 | Storage battery fault diagnosis method and device based on fault injection deep learning |
CN112986830A (en) * | 2021-04-22 | 2021-06-18 | 湖北工业大学 | Lithium battery capacity estimation method based on convolution time memory neural network |
-
2021
- 2021-06-25 CN CN202110713083.9A patent/CN113608140A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109409431A (en) * | 2018-10-29 | 2019-03-01 | 吉林大学 | Multisensor attitude data fusion method and system neural network based |
CN109583507A (en) * | 2018-12-07 | 2019-04-05 | 浙江工商大学 | A kind of pig body recognition methods based on depth convolutional neural networks |
CN110018425A (en) * | 2019-04-10 | 2019-07-16 | 北京理工大学 | A kind of power battery fault diagnosis method and system |
CN110309795A (en) * | 2019-07-04 | 2019-10-08 | 腾讯科技(深圳)有限公司 | Video detecting method, device, electronic equipment and storage medium |
CN110426637A (en) * | 2019-07-04 | 2019-11-08 | 佛山科学技术学院 | A kind of battery failures diagnostic method neural network based and device |
CN110308397A (en) * | 2019-07-30 | 2019-10-08 | 重庆邮电大学 | A kind of lithium battery multiclass fault diagnosis modeling method of mixing convolutional neural networks driving |
US20210119576A1 (en) * | 2019-10-16 | 2021-04-22 | Tata Consultancy Services Limited | Methods and systems for fault detection, diagnosis and localization in solar panel network |
CN111652348A (en) * | 2020-02-29 | 2020-09-11 | 上海电力大学 | Power battery pack fault fusion diagnosis method and system based on improved CNN |
CN111865702A (en) * | 2020-08-04 | 2020-10-30 | 北京航空航天大学 | Network fault diagnosis method and device based on convolutional neural network |
CN112215197A (en) * | 2020-10-27 | 2021-01-12 | 华能国际电力股份有限公司上海石洞口第一电厂 | Underground cable fault early warning method and system based on artificial intelligence |
CN112666480A (en) * | 2020-12-02 | 2021-04-16 | 西安交通大学 | Battery life prediction method based on charging process characteristic attention |
CN112946497A (en) * | 2020-12-04 | 2021-06-11 | 广东电网有限责任公司 | Storage battery fault diagnosis method and device based on fault injection deep learning |
CN112986830A (en) * | 2021-04-22 | 2021-06-18 | 湖北工业大学 | Lithium battery capacity estimation method based on convolution time memory neural network |
Non-Patent Citations (1)
Title |
---|
彭运赛 等: "基于改进CNN和信息融合的动力电池组故障诊断方法", 《汽车工程》, vol. 42, no. 11, pages 1529 - 1536 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114742297A (en) * | 2022-04-11 | 2022-07-12 | 中国第一汽车股份有限公司 | Power battery treatment method |
CN114742297B (en) * | 2022-04-11 | 2024-05-24 | 中国第一汽车股份有限公司 | Method for processing power battery |
CN114646880A (en) * | 2022-04-13 | 2022-06-21 | 中国铁塔股份有限公司江西省分公司 | Intelligent diagnosis method and system for lead-acid battery |
CN114781551A (en) * | 2022-06-16 | 2022-07-22 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
CN114781551B (en) * | 2022-06-16 | 2022-11-29 | 北京理工大学 | Battery multi-fault intelligent classification and identification method based on big data |
CN116879761A (en) * | 2023-09-06 | 2023-10-13 | 杭州宇谷科技股份有限公司 | Multi-mode-based battery internal short circuit detection method, system, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113608140A (en) | Battery fault diagnosis method and system | |
CN109947086B (en) | Mechanical fault migration diagnosis method and system based on counterstudy | |
Hong et al. | Vehicle energy system active defense: a health assessment of lithium‐ion batteries | |
Kim et al. | Data-driven state of health estimation of li-ion batteries with RPT-reduced experimental data | |
CN110879377B (en) | Metering device fault tracing method based on deep belief network | |
Zhang et al. | Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network | |
CN114791993B (en) | Power battery pack SOH prediction method and system | |
Su et al. | Prediction of remaining useful life for lithium-ion battery with multiple health indicators | |
CN114355240A (en) | Power distribution network ground fault diagnosis method and device | |
CN116842459B (en) | Electric energy metering fault diagnosis method and diagnosis terminal based on small sample learning | |
CN111257753A (en) | Battery system fault diagnosis method | |
CN114048468A (en) | Intrusion detection method, intrusion detection model training method, device and medium | |
CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
CN115980560A (en) | CNN-GRU-based high-voltage circuit breaker mechanical fault diagnosis system, method and equipment | |
Kim et al. | Outlier mining-based fault diagnosis for multiceli lithium-ion batteries using a low-priced microcontroller | |
CN116819328A (en) | Electric automobile power battery fault diagnosis method, system, equipment and medium | |
Yao et al. | An intelligent fault diagnosis method for lithium-ion battery pack based on empirical mode decomposition and convolutional neural network | |
CN113825165B (en) | 5G slice network congestion early warning method and device based on time diagram network | |
CN117743971A (en) | Method, device, equipment and medium for detecting direct current series arc faults of electric automobile | |
Song et al. | Capacity estimation method of lithium-ion batteries based on deep convolution neural network | |
Wang et al. | An inconsistency fault diagnosis method for lithium-ion cells in the battery pack based on piecewise dimensionality reduction and outlier identification | |
CN116028893A (en) | Intelligent data monitoring method, system and electronic equipment | |
CN114636933B (en) | Composite neural network-based retired power battery capacity detection method and system | |
CN113884903B (en) | Battery fault diagnosis method based on multi-layer perceptron neural network | |
CN116359738A (en) | Method, device, equipment and storage medium for monitoring health state of battery |
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 |