CN117686921B - Method and system for detecting short circuit in battery and computing device - Google Patents
Method and system for detecting short circuit in battery and computing device Download PDFInfo
- Publication number
- CN117686921B CN117686921B CN202410148151.5A CN202410148151A CN117686921B CN 117686921 B CN117686921 B CN 117686921B CN 202410148151 A CN202410148151 A CN 202410148151A CN 117686921 B CN117686921 B CN 117686921B
- Authority
- CN
- China
- Prior art keywords
- battery
- voltage data
- image
- short circuit
- network model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000003062 neural network model Methods 0.000 claims abstract description 49
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000005070 sampling Methods 0.000 claims abstract description 15
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 6
- 230000015654 memory Effects 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 230000000306 recurrent effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 230000007787 long-term memory Effects 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims 4
- 238000010586 diagram Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The invention provides a method and a system for detecting short circuit in a battery and computing equipment, wherein the method comprises the following steps: acquiring initial sequence voltage data of a battery; predicting to obtain first sequence voltage data by using the initial sequence voltage data and a pre-trained first neural network model; acquiring second sequence voltage data corresponding to the first sequence voltage data; converting the first sequence of voltage data and the second sequence of voltage data into a first image and a second image; synthesizing the first image and the second image into a third image, and superposing the first image and the second image according to a sampling time point to obtain the third image; and inputting the third image into a pre-trained second neural network model to obtain a detection result of the short circuit in the battery. According to the technical scheme of the invention, the internal short circuit of the battery can be rapidly identified.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for detecting short circuits in a battery and computing equipment.
Background
The development background of the battery internal short circuit detection technology is closely related to the wide application of batteries in consumer electronics, electric automobiles and energy storage systems. With the continuous increase of battery energy density, safety problems become increasingly prominent, wherein internal short circuits are one of the main causes of serious safety accidents such as battery performance deterioration, thermal runaway, even explosion and fire.
For this reason, a technical solution is required that can rapidly identify the internal short circuit of the battery.
Disclosure of Invention
The invention aims to provide a method and a system for detecting an internal short circuit of a battery and computing equipment, which can quickly identify the internal short circuit of the battery.
According to an aspect of the present invention, there is provided a method of detecting an internal short circuit of a battery, the method comprising:
acquiring initial sequence voltage data of a battery;
Predicting to obtain first sequence voltage data by using the initial sequence voltage data and a pre-trained first neural network model;
Acquiring second sequence voltage data corresponding to the first sequence voltage data;
Converting the first sequence of voltage data and the second sequence of voltage data into a first image and a second image;
Synthesizing the first image and the second image into a third image;
and inputting the third image into a pre-trained second neural network model to obtain a detection result of the short circuit in the battery.
According to some embodiments, the first neural network model comprises a time-series neural network model.
According to some embodiments, the first neural network model comprises a long-short term memory network model.
According to some embodiments, the first neural network model comprises a recurrent neural network model.
According to some embodiments, the second neural network model comprises a convolutional neural network model.
According to some embodiments, the initial sequence of voltage data, the first sequence of voltage data, and the second sequence of voltage data comprise voltage sampling data based on a same sampling time point.
According to some embodiments, acquiring second sequence voltage data corresponding to the first sequence voltage data comprises: and acquiring actual detection voltage data of the battery at a sampling time point corresponding to the first sequence voltage data.
According to some embodiments, synthesizing the first image and the second image into a third image comprises:
and superposing the first image and the second image according to the sampling time point to obtain a third image.
According to another aspect of the present invention, there is provided a system for detecting an internal short circuit of a battery, the system comprising:
the initial data acquisition module is used for acquiring initial sequence voltage data of the battery;
the prediction module is used for predicting the first sequence voltage data by utilizing the initial sequence voltage data and the pre-trained first neural network model;
a second data acquisition module, configured to acquire second sequence voltage data corresponding to the first sequence voltage data;
the image conversion module is used for converting the first sequence voltage data and the second sequence voltage data into a first image and a second image;
an image synthesis module for synthesizing the first image and the second image into a third image;
And the detection module is used for inputting the third image into a pre-trained second neural network model to obtain a detection result of the short circuit in the battery.
According to another aspect of the present invention, there is provided a computing device comprising:
A processor; and
A memory storing a computer program which, when executed by the processor, causes the processor to perform the method of any one of the preceding claims.
According to another aspect of the invention there is provided a non-transitory computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor, cause the processor to perform the method of any of the above.
According to the embodiment of the invention, based on the artificial intelligence technology, the internal short circuit of the battery is judged by adopting the technology based on the big data AI, so that the internal short circuit fault of the battery can be effectively avoided. And predicting and obtaining first sequence voltage data through initial sequence voltage data of the battery and a pre-trained neural network model, obtaining second sequence voltage data corresponding to the first sequence voltage data, converting the voltage data into images, combining the images into an image, and obtaining a short circuit detection result in the battery by utilizing the neural network model. The intelligent recognition and detection of the internal short circuit of the battery can timely early warn fire hazards of the battery, and can quickly capture fluctuation of a charging curve by adopting a short circuit recognition algorithm, so that the system accurately recognizes the internal short circuit and then quickly alarms.
According to some embodiments, the invention can realize safety precaution, and potential safety hazards of the battery can be found in advance through internal short circuit detection, so that safety accidents such as thermal runaway, fire and explosion caused by short circuit are prevented.
According to some embodiments, by detecting the data fed back by the technology, the scientific researchers can optimize the battery materials, the structural design and the production process, so that the short-circuit resistance and the overall safety of the battery are improved. For the end user in the battery application field, the effective internal short circuit detection means higher safety guarantee, reduces the occurrence of accidents and ensures the life and property safety of the user.
According to some embodiments, performing internal short circuit testing during the battery production phase is a critical step to ensure battery product quality, ensuring that each battery shipped meets safety standards, and avoiding failures due to manufacturing defects. By monitoring the internal state of the battery, the health condition and the life expectancy of the battery can be estimated, the battery with short circuit risk can be maintained or replaced in time, and the stability and the reliability of the whole battery pack are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the description of the embodiments will be briefly described below.
Fig. 1 shows a flowchart of a method of detecting an internal short circuit of a battery according to an example embodiment.
Fig. 2 shows a schematic diagram of normal voltages within a burst-type battery according to an example embodiment.
Fig. 3 shows a schematic diagram of a burst intra-battery short circuit voltage according to an example embodiment.
Fig. 4 shows a schematic diagram of burst in-battery short circuit detection according to an example embodiment.
Fig. 5 shows a schematic diagram of the normal voltage within a derivative battery according to an example embodiment.
Fig. 6 shows a schematic diagram of a derivative in-cell short circuit voltage according to an example embodiment.
Fig. 7 shows a schematic diagram of derivative in-cell short circuit detection according to an example embodiment.
Fig. 8 shows a system schematic diagram for detecting an intra-battery short circuit according to an example embodiment.
FIG. 9 illustrates a block diagram of a computing device in accordance with an exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another element. Accordingly, a first component discussed below could be termed a second component without departing from the teachings of the present inventive concept. As used herein, the term "and/or" includes any one of the associated listed items and all combinations of one or more.
The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present invention are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of related data is required to comply with the relevant laws and regulations and standards of the relevant country and region, and is provided with corresponding operation entries for the user to select authorization or rejection.
Those skilled in the art will appreciate that the drawings are schematic representations of example embodiments and that the modules or flows in the drawings are not necessarily required to practice the invention and therefore should not be taken to limit the scope of the invention.
Currently, there are knowledge-based methods and data-driven based methods for the intra-battery short circuit recognition method. The knowledge-based method relies on long-term knowledge experience accumulation, and the method utilizes the knowledge and observation information of the battery system to diagnose without using fault trees, graph theory, fuzzy logic, expert systems and other methods to build a model. But it is very difficult to acquire knowledge and establish rules. The method based on data driving is difficult to acquire the characteristic data, an accurate battery analysis model is not required to be established, and the potential mode of fault occurrence is learned from a large number of battery training samples so as to diagnose the battery fault, but the method is less applied to the aspect of battery fault diagnosis at present because a large number of battery fault data are difficult to acquire.
Therefore, the invention provides a method for detecting the short circuit in the battery, which is characterized in that first sequence voltage data is obtained through the prediction of initial sequence voltage data and a pre-trained neural network model of the battery, second sequence voltage data corresponding to the first sequence voltage data is obtained, the voltage data is converted into images and combined into an image, and a neural network model is utilized to obtain a detection result of the short circuit in the battery. The intelligent recognition and detection of the internal short circuit of the battery can timely early warn fire hazards of the battery, rapidly capture fluctuation of a charging curve, and accurately recognize the internal short circuit and rapidly alarm.
Before describing embodiments of the present invention, some terms or concepts related to the embodiments of the present invention are explained.
Time-series neural network model: the time series neural network model is a deep learning architecture dedicated to processing and predicting data with time dependence. Such models capture trends, periodicity and auto-correlation characteristics in time series data and thus find wide application in fields such as financial predictions (e.g., stock price predictions), weather predictions, power load predictions, traffic flow predictions, sales predictions, hydrologic predictions, and various industrial control and health monitoring.
Long-term memory network model: the English abbreviation LSTM, long-term memory network model is a variant of a special floor cabinet neural network model, solves the problem of long-term dependence by introducing a gate mechanism, and can better capture modes in a long time range.
Recurrent neural network model: the acronym RNN, the recurrent neural network model can retain past information through its internal state and update this state based on the current input, which is well suited to process data that is sequential or time dependent.
Convolutional neural network model: when the English abbreviation CNN and the one-dimensional convolutional neural network (1D CNN) are applied to the time sequence, a filter (or a convolution kernel) can be utilized to extract local features, and the sequence is subjected to dimension reduction and abstract representation through a pooling layer, so that the method is suitable for finding the local features in the sequence and the change rule thereof.
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings.
FIG. 1 shows a flow chart of a method for model training according to an example embodiment.
Referring to fig. 1, initial sequence voltage data of a battery is acquired at S101.
According to some embodiments, the initial sequence voltage data of the battery refers to the voltage of the newly assembled, non-charged or discharged battery cell in a stationary state.
According to some embodiments, specific initial sequence voltage data is obtained by consulting specifications for a particular battery model or by experimental measurements. For the battery pack, the initial voltage is the sum of the initial open circuit voltages of the individual cells, but in practical applications, the battery pack may include an equalization circuit, so that the initial voltage of the entire battery pack also includes the influence of the management system on the balance of the individual cell voltages.
According to some embodiments, the initial sequence voltage data is open circuit voltage data recorded for each cell or the entire battery system at the beginning of a test, monitoring or diagnosis of the battery pack or battery module. This data is of great importance for evaluating the performance of the battery in its initial state, state of health and during subsequent charge and discharge.
For example, in a battery management system, voltage information for each battery cell is collected and recorded in real time to facilitate monitoring of battery consistency, prevention of overcharge and overdischarge, prediction of battery life, and the like. The initial sequence voltage data can be used as a datum reference value to be compared and analyzed with the data at each subsequent moment, so that accurate judgment and effective management of the battery state are realized.
And S103, predicting to obtain first sequence voltage data by using the initial sequence voltage data and the pre-trained first neural network model.
According to some embodiments, the first neural network model includes, but is not limited to, a time series neural network model, a long and short term memory network model, a recurrent neural network model.
The long-term and short-term memory network model is a special type of circulating neural network, and is designed for initially solving the problems of gradient disappearance and gradient explosion of the traditional circulating neural network when the long-term dependence problem is treated. Structurally, the long-and-short-term memory network model has a unique gating mechanism and mainly comprises three core gating components, namely a forgetting gate, an input gate and an output gate. The forgetting gate decides which information in the memory cells of the previous time step needs to be discarded, a weight value between 0 and 1 is calculated through an activation function, a value close to 1 indicates that the information is reserved, and a value close to 0 indicates forgetting. The input gate has two functions, one is to determine which of the newly received information is to be written into the memory cell, and the other is to calculate new candidate memory contents. The output gate decides which information in the memory cell at the current time should be output as hidden state to the next time step or for final prediction.
A recurrent neural network model is a deep learning model capable of processing data having a tree or a recurrent structure, which captures hierarchical information in input data by recursively making a structure. The model introduces recursive operation in a network structure, and is particularly suitable for tasks such as natural language processing, image analysis in computer vision, semantic analysis and the like, wherein data usually show internal hierarchical relations in the form of trees or graphs.
According to some embodiments, the initial sequence voltage data of the battery is utilized, and the battery voltage change under different conditions or using stages can be predicted by combining the pre-trained first neural network model, so as to obtain the first sequence voltage data. It is first ensured that the initial sequence voltage and other relevant parameters of the battery under various conditions are acquired, and the initial sequence voltage and other influencing factors are converted into characteristic vectors suitable for the input neural network.
And loading a pre-training model, preparing for prediction, and transmitting the processed initial sequence voltage and other characteristics as input to the pre-trained neural network model, wherein the model can be calculated and inferred according to the learned rule.
At S105, second sequence voltage data corresponding to the first sequence voltage data is acquired.
According to some embodiments, acquiring second sequence of voltage data corresponding to the first sequence of voltage data includes acquiring actual detected voltage data of the battery at a sampling time point corresponding to the first sequence of voltage data.
According to some embodiments, the first sequence voltage data and the second sequence voltage data are voltage changes of the battery unit before and after charging, the first sequence voltage data are predicted voltage values in a normal operation state, and the second sequence voltage data are voltage values measured after a short circuit may occur in the battery after charging for a period of time.
At S107, the first sequence voltage data and the second sequence voltage data are converted into a first image and a second image.
According to some embodiments, the initial sequence of voltage data, the first sequence of voltage data, and the second sequence of voltage data comprise voltage sampling data based on a same sampling time point.
According to some embodiments, the first sequence of voltage data and the second sequence of voltage data are converted into a first image and a second image. For example, fig. 2 shows the normal voltage in a burst-type battery, and fig. 5 shows the normal voltage in a derivative-type battery, wherein the horizontal axis represents time and the vertical axis represents voltage in the image, and the graph shows the change in the battery voltage under normal conditions.
Fig. 3 shows a voltage change of a short circuit in a burst-type battery, and fig. 6 shows a voltage change of a short circuit in a derivative-type battery, wherein a curve represents a change of a battery voltage in a case where a short circuit occurs in the battery.
At S109, the first image and the second image are combined into a third image.
According to some embodiments, the first image and the second image are superimposed according to a sampling time point to obtain a third image.
According to some embodiments, after obtaining the first image and the second image, the first image and the second image are combined into a third image. For example, fig. 4 shows a comparison of burst-type battery normal voltage variation and occurrence of intra-battery short-circuit voltage detection, and fig. 7 shows a schematic diagram of derivative-type battery normal voltage variation and occurrence of intra-battery short-circuit detection.
And in S111, inputting the third image into a pre-trained second neural network model to obtain an intra-battery short circuit detection result.
According to some embodiments, the second neural network model comprises a convolutional neural network model. Convolutional neural network models are a type of deep learning model that is specific to image recognition, computer vision, and many other data related to mesh. The design inspiration of the convolutional neural network model is derived from the structure of a biological vision system, and the convolutional neural network model has excellent capability in an image analysis task and can automatically extract high-level features from original pixel data.
The main components of the convolutional neural network include a convolutional layer, an activation function, a pooling layer, a fully-connected layer and an output layer. The convolution layer is the core of the model, it performs sliding window operation on the input data through a set of learnable filters, and calculates the multiplication and addition results between elements. Each filter will produce a feature map over the entire input that emphasizes a particular pattern or feature in the input, and different types of features, such as edges, colors, textures, etc., can be extracted by multiple filters. The activation function is used to increase nonlinearity, helping the network to capture more complex decision boundaries. The pooling layer is used for reducing the space dimension of the data, reducing the calculation amount and simultaneously keeping important characteristic information. After the rolling and pooling layers, the full connection layers are usually connected with a plurality of full connection layers, and all nodes are directly connected to all nodes of the next layer by the layers, so that global feature fusion is realized and classification or regression tasks are completed. The output layer is used to calculate the probability distribution for each category.
According to some embodiments, voltage image data is first acquired, and the collected image is subjected to necessary preprocessing, including graying, normalization, cropping, enhancement, etc., to facilitate better recognition of the features by the model.
A second neural network model, a convolutional neural network, is selected and pre-trained. The pre-trained model is applied to a battery internal short circuit detection task, a new output layer is required to be added to the last layer or part of middle layers of the model according to the characteristics of the voltage image, and fine adjustment is carried out on image data. And comparing the first sequence voltage with the second sequence voltage to judge whether the battery has an internal short circuit risk.
For example, referring to fig. 4, fig. 4 is a combination of fig. 2 and 3. Referring to fig. 2 and 3, it can be seen from fig. 2 that the voltage of the battery decreases with time, and fig. 3 shows that the voltage of the battery is severely dithered at the moment of sudden and severe short-circuiting of the battery, and the charge-discharge curve of the battery cell fluctuates instantaneously. The voltage contrast change can be seen at the position of the circle in fig. 4, and the instant fluctuation of the voltage when the battery is short-circuited can be identified through the reasoning calculation of the second neural network model, so that the short circuit in the battery is detected.
Referring to fig. 7, fig. 7 is a combination of fig. 5 and 6. Referring to fig. 5, fig. 5 shows that the voltage value of the derivative battery under normal conditions varies in a stable cycle. Fig. 6 shows that the voltage is shifted when the derivative battery is short-circuited, and the cell charge-discharge curve fluctuates. The voltage contrast change can be seen at the position of the circle in fig. 7, and the deviation of the cyclic fluctuation of the voltage during the battery short circuit can be identified through the reasoning calculation of the second neural network model, so that the short circuit in the battery is detected.
Fig. 8 shows a system schematic diagram for detecting an intra-battery short circuit according to an example embodiment.
Referring to fig. 8, there is shown a system for detecting an internal short circuit of a battery, comprising: an initial data acquisition module 801, a prediction module 803, a second data acquisition module 805, an image conversion module 807, an image synthesis module 809, and a detection module 811.
The initial data acquisition module 801 is configured to acquire initial sequence voltage data of the battery. The prediction module 803 is configured to predict the first sequence voltage data by using the initial sequence voltage data and a pre-trained first neural network model. The second data acquisition module 805 is configured to acquire second sequence voltage data corresponding to the first sequence voltage data. The image conversion module 807 is configured to convert the first sequence of voltage data and the second sequence of voltage data into a first image and a second image. The image synthesis module 809 is configured to synthesize the first image and the second image into a third image. The detection module 811 is configured to input the third image into a pre-trained second neural network model, so as to obtain an intra-battery short circuit detection result.
FIG. 9 illustrates a block diagram of a computing device in accordance with an exemplary embodiment.
As shown in fig. 9, computing device 30 includes processor 12 and memory 14. Computing device 30 may also include a bus 22, a network interface 16, and an I/O interface 18. The processor 12, memory 14, network interface 16, and I/O interface 18 may communicate with each other via a bus 22.
The processor 12 may include one or more general purpose CPUs (Central Processing Unit, processors), microprocessors, or application specific integrated circuits, etc. for executing associated program instructions. According to some embodiments, computing device 30 may also include a high performance display adapter (GPU) 20 that accelerates processor 12.
Memory 14 may include machine-system-readable media in the form of volatile memory, such as Random Access Memory (RAM), read Only Memory (ROM), and/or cache memory. Memory 14 is used to store one or more programs including instructions as well as data. The processor 12 may read instructions stored in the memory 14 to perform the methods according to embodiments of the invention described above.
Computing device 30 may also communicate with one or more networks through network interface 16. The network interface 16 may be a wireless network interface.
Bus 22 may be a bus including an address bus, a data bus, a control bus, etc. Bus 22 provides a path for exchanging information between the components.
It should be noted that, in the implementation, the computing device 30 may further include other components necessary to achieve normal operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method. The computer readable storage medium may include, but is not limited to, any type of disk including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROM, RAM, EPROM, EEPROM, DRAM, VRAM, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), network storage devices, cloud storage devices, or any type of media or device suitable for storing instructions and/or data.
Embodiments of the present invention also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform part or all of the steps of any one of the methods described in the method embodiments above.
It will be clear to a person skilled in the art that the solution according to the invention can be implemented by means of software and/or hardware. "Unit" and "module" in this specification refer to software and/or hardware capable of performing a specific function, either alone or in combination with other components, where the hardware may be, for example, a field programmable gate array, an integrated circuit, or the like.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present invention.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
The exemplary embodiments of the present invention have been particularly shown and described above. It is to be understood that this invention is not limited to the precise arrangements, instrumentalities and instrumentalities described herein; on the contrary, the invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (8)
1. A method of detecting a short circuit in a battery, comprising:
Acquiring initial sequence voltage data of a battery, wherein the initial sequence voltage data is the voltage of a newly assembled battery unit which is not subjected to a charging or discharging process in a standing state;
Predicting the first sequence voltage data by using the initial sequence voltage data and a pre-trained first neural network model to obtain first sequence voltage data as a predicted voltage value in a normal running state;
Acquiring actual detection voltage data of the battery at a sampling time point corresponding to the first sequence voltage data as second sequence voltage data, wherein the second sequence voltage data is a voltage value which is obtained by measuring after a short circuit possibly occurs in the battery after the battery is charged for a period of time;
Converting the first sequence of voltage data and the second sequence of voltage data into a first image and a second image;
superposing and synthesizing the first image and the second image into a third image according to a sampling time point;
inputting the third image into a pre-trained second neural network model to obtain a detection result of the short circuit in the battery, wherein,
For burst battery short circuit, when the battery bursts to violent short circuit, the second neural network model recognizes that the voltage of the battery is violently dithered, and the charging and discharging curve of the battery core is instantaneously fluctuated, so that the short circuit in the battery is detected;
For derivative battery short circuit, deviation fluctuation occurs in the battery cell charge-discharge curve, and the second neural network model recognizes that the circulation voltage is deviated, so that the battery internal short circuit is detected.
2. The method of claim 1, wherein the first neural network model comprises a time-series neural network model.
3. The method of claim 2, wherein the first neural network model comprises a long-term memory network model.
4. The method of claim 1, wherein the first neural network model comprises a recurrent neural network model.
5. The method of claim 1, wherein the second neural network model comprises a convolutional neural network model.
6. The method of claim 1, wherein the initial sequence of voltage data, the first sequence of voltage data, and the second sequence of voltage data comprise voltage sampling data based on a same sampling time point.
7. A system for detecting a short circuit in a battery, comprising:
The initial data acquisition module is used for acquiring initial sequence voltage data of the battery, wherein the initial sequence voltage data is the voltage of a newly assembled battery unit which is not subjected to a charging or discharging process in a standing state;
The prediction module is used for predicting the first sequence voltage data by using the initial sequence voltage data and the pre-trained first neural network model to obtain a predicted voltage value in a normal running state;
The second data acquisition module is used for acquiring actual detection voltage data of the battery at a sampling time point corresponding to the first sequence voltage data as second sequence voltage data, wherein the second sequence voltage data is a voltage value which is measured after a short circuit possibly occurs in the battery after the battery is charged for a period of time;
the image conversion module is used for converting the first sequence voltage data and the second sequence voltage data into a first image and a second image;
The image synthesis module is used for superposing and synthesizing the first image and the second image into a third image according to a sampling time point;
The detection module is used for inputting the third image into a pre-trained second neural network model to obtain a detection result of the short circuit in the battery, wherein,
For burst battery short circuit, when the battery bursts to violent short circuit, the second neural network model recognizes that the voltage of the battery is violently dithered, and the charging and discharging curve of the battery core is instantaneously fluctuated, so that the short circuit in the battery is detected;
For derivative battery short circuit, deviation fluctuation occurs in the battery cell charge-discharge curve, and the second neural network model recognizes that the circulation voltage is deviated, so that the battery internal short circuit is detected.
8. A computing device, comprising:
A processor; and
A memory storing a computer program which, when executed by the processor, causes the processor to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410148151.5A CN117686921B (en) | 2024-02-02 | 2024-02-02 | Method and system for detecting short circuit in battery and computing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410148151.5A CN117686921B (en) | 2024-02-02 | 2024-02-02 | Method and system for detecting short circuit in battery and computing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117686921A CN117686921A (en) | 2024-03-12 |
| CN117686921B true CN117686921B (en) | 2024-05-31 |
Family
ID=90135666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410148151.5A Active CN117686921B (en) | 2024-02-02 | 2024-02-02 | Method and system for detecting short circuit in battery and computing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117686921B (en) |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104614630A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Identification method for micro short circuit of battery |
| CN106154172A (en) * | 2016-06-17 | 2016-11-23 | 清华大学 | The quantitative estimation method of lithium-ion-power cell internal short-circuit degree |
| WO2018083802A1 (en) * | 2016-11-07 | 2018-05-11 | 日産自動車株式会社 | Short circuit detection device |
| CN111007364A (en) * | 2019-11-07 | 2020-04-14 | 长沙理工大学 | Method for identifying early self-recovery fault of cable |
| CN111190113A (en) * | 2020-04-15 | 2020-05-22 | 中国人民解放军国防科技大学 | Spacecraft storage battery performance degradation abnormity detection method |
| CN111413629A (en) * | 2020-02-24 | 2020-07-14 | 上海蔚来汽车有限公司 | Short circuit monitoring method, system and device for single batteries in power battery |
| CN111551860A (en) * | 2020-05-26 | 2020-08-18 | 同济大学 | Battery internal short circuit diagnosis method based on relaxation voltage characteristics |
| CN112946522A (en) * | 2021-02-05 | 2021-06-11 | 四川大学 | On-line monitoring method for short-circuit fault in battery energy storage system caused by low-temperature working condition |
| CN113359047A (en) * | 2021-04-22 | 2021-09-07 | 万向一二三股份公司 | Method for evaluating influence of internal short circuit measurement on performance of lithium ion battery |
| CN215180728U (en) * | 2021-04-20 | 2021-12-14 | 苏州天富利新能源科技有限公司 | BMS-based safety monitoring and protecting system |
| CN113848495A (en) * | 2021-10-11 | 2021-12-28 | 江苏省特种设备安全监督检验研究院 | Internal micro short circuit fault diagnosis method based on charging curve |
| CN113884890A (en) * | 2021-11-02 | 2022-01-04 | 轻橙时代(深圳)科技有限责任公司 | Power battery internal short circuit detection method |
| CN114740359A (en) * | 2022-03-31 | 2022-07-12 | 同济大学 | Method and device for diagnosing short circuit in battery based on electric quantity estimation and storage medium |
| CN115079007A (en) * | 2022-06-24 | 2022-09-20 | 上海玫克生储能科技有限公司 | Lithium ion battery micro short circuit identification method, lithium ion battery micro short circuit identification system and battery management system |
| EP4137347A1 (en) * | 2021-08-20 | 2023-02-22 | Nio Technology (Anhui) Co., Ltd | Short circuit detection method for starting battery |
| CN115718260A (en) * | 2022-09-30 | 2023-02-28 | 山东工商学院 | Battery fault prediction method and system based on combination of CNN-LSTM and correlation coefficient |
| CN116154900A (en) * | 2023-01-05 | 2023-05-23 | 北京西清能源科技有限公司 | Active safety three-stage prevention and control system and method for battery energy storage power station |
| WO2023115988A1 (en) * | 2021-12-22 | 2023-06-29 | 北京国家新能源汽车技术创新中心有限公司 | Method for detecting internal short-circuit of traction battery |
| 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 |
| CN116951328A (en) * | 2023-07-21 | 2023-10-27 | 浙江华创设计有限公司 | Intelligent drainage pipeline operation monitoring system based on big data |
| CN116973788A (en) * | 2023-08-04 | 2023-10-31 | 嘉庚创新实验室 | Internal short circuit fault detection method, device, computer equipment and storage medium |
| CN117252112A (en) * | 2023-11-16 | 2023-12-19 | 江苏林洋亿纬储能科技有限公司 | Method for training driving data model and method for estimating remaining life of battery |
| CN117289142A (en) * | 2023-11-24 | 2023-12-26 | 国网天津市电力公司电力科学研究院 | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery |
| CN117320461A (en) * | 2023-09-08 | 2023-12-29 | 广东工业大学 | Application of pyrenyl aniline derivatives in organic electronic device |
-
2024
- 2024-02-02 CN CN202410148151.5A patent/CN117686921B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104614630A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Identification method for micro short circuit of battery |
| CN106154172A (en) * | 2016-06-17 | 2016-11-23 | 清华大学 | The quantitative estimation method of lithium-ion-power cell internal short-circuit degree |
| WO2018083802A1 (en) * | 2016-11-07 | 2018-05-11 | 日産自動車株式会社 | Short circuit detection device |
| CN111007364A (en) * | 2019-11-07 | 2020-04-14 | 长沙理工大学 | Method for identifying early self-recovery fault of cable |
| WO2021169487A1 (en) * | 2020-02-24 | 2021-09-02 | 上海蔚来汽车有限公司 | Short-circuit monitoring method, system and device for cells in power battery |
| CN111413629A (en) * | 2020-02-24 | 2020-07-14 | 上海蔚来汽车有限公司 | Short circuit monitoring method, system and device for single batteries in power battery |
| CN111190113A (en) * | 2020-04-15 | 2020-05-22 | 中国人民解放军国防科技大学 | Spacecraft storage battery performance degradation abnormity detection method |
| CN111551860A (en) * | 2020-05-26 | 2020-08-18 | 同济大学 | Battery internal short circuit diagnosis method based on relaxation voltage characteristics |
| CN112946522A (en) * | 2021-02-05 | 2021-06-11 | 四川大学 | On-line monitoring method for short-circuit fault in battery energy storage system caused by low-temperature working condition |
| CN215180728U (en) * | 2021-04-20 | 2021-12-14 | 苏州天富利新能源科技有限公司 | BMS-based safety monitoring and protecting system |
| CN113359047A (en) * | 2021-04-22 | 2021-09-07 | 万向一二三股份公司 | Method for evaluating influence of internal short circuit measurement on performance of lithium ion battery |
| EP4137347A1 (en) * | 2021-08-20 | 2023-02-22 | Nio Technology (Anhui) Co., Ltd | Short circuit detection method for starting battery |
| CN113848495A (en) * | 2021-10-11 | 2021-12-28 | 江苏省特种设备安全监督检验研究院 | Internal micro short circuit fault diagnosis method based on charging curve |
| CN113884890A (en) * | 2021-11-02 | 2022-01-04 | 轻橙时代(深圳)科技有限责任公司 | Power battery internal short circuit detection method |
| WO2023115988A1 (en) * | 2021-12-22 | 2023-06-29 | 北京国家新能源汽车技术创新中心有限公司 | Method for detecting internal short-circuit of traction battery |
| CN114740359A (en) * | 2022-03-31 | 2022-07-12 | 同济大学 | Method and device for diagnosing short circuit in battery based on electric quantity estimation and storage medium |
| CN115079007A (en) * | 2022-06-24 | 2022-09-20 | 上海玫克生储能科技有限公司 | Lithium ion battery micro short circuit identification method, lithium ion battery micro short circuit identification system and battery management system |
| CN115718260A (en) * | 2022-09-30 | 2023-02-28 | 山东工商学院 | Battery fault prediction method and system based on combination of CNN-LSTM and correlation coefficient |
| CN116154900A (en) * | 2023-01-05 | 2023-05-23 | 北京西清能源科技有限公司 | Active safety three-stage prevention and control system and method for battery energy storage power station |
| CN116951328A (en) * | 2023-07-21 | 2023-10-27 | 浙江华创设计有限公司 | Intelligent drainage pipeline operation monitoring system based on big data |
| CN116973788A (en) * | 2023-08-04 | 2023-10-31 | 嘉庚创新实验室 | Internal short circuit fault detection method, device, computer equipment and storage medium |
| 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 |
| CN117320461A (en) * | 2023-09-08 | 2023-12-29 | 广东工业大学 | Application of pyrenyl aniline derivatives in organic electronic device |
| CN117252112A (en) * | 2023-11-16 | 2023-12-19 | 江苏林洋亿纬储能科技有限公司 | Method for training driving data model and method for estimating remaining life of battery |
| CN117289142A (en) * | 2023-11-24 | 2023-12-26 | 国网天津市电力公司电力科学研究院 | Method and device for detecting internal short circuit fault of lithium ion energy storage power station battery |
Non-Patent Citations (1)
| Title |
|---|
| 锂离子电池内短路机理与检测研究进展;刘力硕;张明轩;卢兰光;欧阳明高;冯旭宁;郑岳久;韩雪冰;潘岳;;储能科学与技术;20181022(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117686921A (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khan et al. | Batteries state of health estimation via efficient neural networks with multiple channel charging profiles | |
| Xu et al. | An improved CNN-LSTM model-based state-of-health estimation approach for lithium-ion batteries | |
| Wang et al. | Online remaining useful life prediction of lithium-ion batteries using bidirectional long short-term memory with attention mechanism | |
| Ren et al. | A review of machine learning state-of-charge and state-of-health estimation algorithms for lithium-ion batteries | |
| Rouhi Ardeshiri et al. | Multivariate gated recurrent unit for battery remaining useful life prediction: A deep learning approach | |
| Song et al. | Remaining life prediction of lithium-ion batteries based on health management: A review | |
| Semeraro et al. | Battery monitoring and prognostics optimization techniques: challenges and opportunities | |
| Liu et al. | State of health estimation of power batteries based on multi-feature fusion models using stacking algorithm | |
| Zhou et al. | Battery health prognosis using improved temporal convolutional network modeling | |
| Kong et al. | State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization | |
| Zhang et al. | Cost-effective Lebesgue sampling long short-term memory networks for lithium-ion batteries diagnosis and prognosis | |
| Niu et al. | Lebesgue sampling based deep belief network for lithium-ion battery diagnosis and prognosis | |
| CN111856287A (en) | Lithium battery health state detection method based on stacked residual causal convolutional neural network | |
| Jiang et al. | A fault diagnosis method for electric vehicle power lithium battery based on wavelet packet decomposition | |
| CN111983474A (en) | Lithium ion battery life prediction method and system based on capacity decline model | |
| Wang et al. | A remaining useful life prediction model based on hybrid long-short sequences for engines | |
| Wang et al. | A multi-scale fusion prediction method for lithium-ion battery capacity based on ensemble empirical mode decomposition and nonlinear autoregressive neural networks | |
| Li et al. | An optimal stacking ensemble for remaining useful life estimation of systems under multi-operating conditions | |
| Bao et al. | Hybrid deep neural network with dimension attention for state-of-health estimation of lithium-ion batteries | |
| Wu et al. | Remaining useful life prediction of lithium-ion batteries based on data preprocessing and improved ELM | |
| Zhu et al. | Attention-based CNN-BiLSTM for SOH and RUL estimation of lithium-ion batteries | |
| Duan et al. | Serial transfer learning (STL) theory for processing data insufficiency: Fault diagnosis of transformer windings | |
| Gao et al. | A hybrid cnn-bilstm approach for remaining useful life prediction of evs lithium-ion battery | |
| Gou et al. | Remaining useful life prediction for lithium-ion battery using ensemble learning method | |
| Wang et al. | Assessing the Performance Degradation of Lithium‐Ion Batteries Using an Approach Based on Fusion of Multiple Feature Parameters |
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 | ||
| CP03 | Change of name, title or address |
Address after: Floor 17, Building 1, No. 2 Mudanjiang Street, Jianye District, Nanjing City, Jiangsu Province, 210019 Patentee after: Jiangsu Linyang Energy Storage Technology Co.,Ltd. Country or region after: China Address before: Floor 17, Building D1, No. 2 Mudanjiang Street, Jianye District, Nanjing City, Jiangsu Province, 210019 Patentee before: Jiangsu Linyang Yiwei Energy Storage Technology Co.,Ltd. Country or region before: China |