CN117665604A - Battery sampling abnormality identification method and device, storage medium and electronic equipment - Google Patents
Battery sampling abnormality identification method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117665604A CN117665604A CN202311373647.4A CN202311373647A CN117665604A CN 117665604 A CN117665604 A CN 117665604A CN 202311373647 A CN202311373647 A CN 202311373647A CN 117665604 A CN117665604 A CN 117665604A
- Authority
- CN
- China
- Prior art keywords
- sampling
- battery
- target
- voltage
- target battery
- 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
- 238000005070 sampling Methods 0.000 title claims abstract description 175
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000005856 abnormality Effects 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 114
- 239000000178 monomer Substances 0.000 claims abstract description 53
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 51
- 230000008859 change Effects 0.000 claims description 36
- 238000012423 maintenance Methods 0.000 claims description 16
- 238000002372 labelling Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 9
- 210000004027 cell Anatomy 0.000 description 117
- 238000007726 management method Methods 0.000 description 54
- 238000010586 diagram Methods 0.000 description 12
- 238000011176 pooling Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000012795 verification Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013024 troubleshooting Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a battery sampling abnormality identification method, a device, a storage medium and electronic equipment. Wherein the method comprises the following steps: sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the plurality of target battery cells respectively; identifying measured voltage data corresponding to a plurality of target battery monomers respectively by adopting a target neural network model, and determining an abnormal identification result of a target battery pack; determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal; based on the voltage time sequence trend corresponding to the plurality of target battery cells, the abnormal event of positioning and sampling occurs in the battery management system and/or the target battery pack. The invention solves the technical problems of insufficient sampling abnormality identification and positioning capability in the related technology.
Description
Technical Field
The present invention relates to the field of battery technologies, and in particular, to a method and apparatus for identifying battery sampling anomalies, a storage medium, and an electronic device.
Background
The power battery is an indispensable core component of a new energy automobile (electric automobile), and is directly related to the performance and safety of the whole automobile, so that the importance is self-evident. The state parameters (voltage, current, temperature and the like) of the battery pack of the electric automobile are collected, monitored, analyzed and early-warned in real time in the use process, so that the health and normal use of the battery pack are ensured. However, due to reasons such as manufacturing process, poor contact of acquisition lines, battery pack faults and the like, abnormal acquisition of adjacent single voltages can occur, which can influence management strategies of a Battery Management System (BMS), early warning strategies of cloud monitoring algorithms and analysis algorithms of battery health states, and problems such as analysis errors, fault false alarms, fault detection failures and the like can occur. Therefore, fault location and troubleshooting are required, and the locating capability of the location of the abnormality after the presence of the sampling abnormality is not provided in the related art, and great inconvenience is brought to the troubleshooting due to the difficulty in disassembling the battery pack.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the invention provides a battery sampling abnormality identification method, a device, a storage medium and electronic equipment, which are used for at least solving the technical problems of insufficient sampling abnormality identification and positioning capability in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a battery sampling abnormality identification method including: sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the target battery cells respectively; identifying measured voltage data corresponding to each of the plurality of target battery cells by adopting a target neural network model, and determining an abnormal identification result of the target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to each of a plurality of reference battery packs, and the plurality of reference battery packs are in different states; determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal; and positioning and sampling abnormal events to occur to the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to the target battery cells.
Optionally, the method further comprises: acquiring voltage characteristic data of any battery pack in the plurality of reference battery packs; expanding the voltage characteristic data of any battery pack to obtain an expansion sample corresponding to the any battery pack; taking the plurality of reference battery packs as the arbitrary battery packs respectively to obtain expansion samples corresponding to the plurality of reference battery packs respectively; and carrying out sample labeling on the extended samples respectively corresponding to the plurality of reference battery packs to obtain the training set.
Optionally, the expanding the voltage characteristic data of the arbitrary battery pack to obtain an expanded sample corresponding to the arbitrary battery pack includes: based on a preset sliding step length and a preset window time sequence length, carrying out multiple interception on the voltage characteristic data of any battery pack by adopting a sliding window to obtain a plurality of groups of window data with overlapping; and under the condition that the time sequence length of any group of data in the plurality of groups of window data is smaller than the time sequence length of the preset window, splicing the any group of data so that the time sequence length of any group of data is equal to the time sequence length of the preset window.
Optionally, the positioning and sampling abnormal event occurs in the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, including: and when the voltage time sequence trend of one of the two adjacent battery cells is higher than the average change trend, the sampling abnormal event is positioned to occur in the target battery pack, wherein the average change trend is the average voltage trend of other cells except the two adjacent cells in the plurality of target battery cells.
Optionally, the positioning and sampling abnormal event occurs in the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, including: three adjacent battery monomers exist in the plurality of target battery monomers, namely a first monomer, a second monomer and a third monomer in sequence, the voltage time sequence trend corresponding to the first monomer and the voltage time sequence trend corresponding to the third monomer are the same and higher than the average change trend, and the abnormal sampling event is located to occur in the battery management system under the condition that the voltage time sequence trend of the second monomer is lower than the average change trend, wherein the average change trend is the average voltage trend of other monomers except the three adjacent monomers in the plurality of target battery monomers.
Optionally, the positioning and sampling abnormal event occurs in the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, including: and under the condition that two adjacent battery cells exist in the plurality of target battery cells, and the voltage time sequence trend corresponding to the two adjacent battery cells is higher or lower than the average change trend at the same time, positioning that the sampling abnormal event occurs in the target battery pack and the battery management system, wherein the average change trend is the average voltage trend of other cells except the two adjacent battery cells in the plurality of target battery cells.
Optionally, after the positioning and sampling abnormal event occurs in the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, the method further includes: determining a plurality of maintenance battery packs matched with the target battery pack type and sampling abnormal positioning data corresponding to the plurality of maintenance data packs respectively, wherein the plurality of maintenance battery packs are battery packs in which the sampling abnormal event is positioned in a preset historical period; determining abnormal probability of the sampling abnormal event occurring in the battery management system and/or the target battery pack based on the sampling abnormal positioning data respectively corresponding to the plurality of maintenance data packs; and generating combined prompt information based on the positioning result of the sampling abnormal event and the abnormal probability.
According to another aspect of the embodiment of the present invention, there is provided a battery sampling abnormality identification apparatus including: the sampling module is used for sampling a plurality of target battery monomers included in the target battery pack by adopting the battery management system to obtain measured voltage data corresponding to the plurality of target battery monomers respectively; the identification module is used for identifying measured voltage data corresponding to the plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of the target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to the plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states; the trend determining module is used for determining voltage time sequence trends corresponding to the target battery cells based on measured voltage data corresponding to the target battery cells respectively when the abnormality identification result indicates that sampling voltage abnormality exists; and the positioning module is used for positioning and sampling abnormal events to occur to the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to the target battery cells.
According to another aspect of an embodiment of the present invention, there is provided a nonvolatile storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform any one of the battery sampling abnormality identification methods.
According to another aspect of an embodiment of the present invention, there is provided an electronic apparatus including: the battery sampling anomaly identification device comprises one or more processors and a memory, wherein the memory is used for storing one or more programs, and the one or more processors are caused to realize any battery sampling anomaly identification method when the one or more programs are executed by the one or more processors.
In the embodiment of the invention, a battery management system is adopted to sample a plurality of target battery cells included in a target battery pack, so as to obtain measured voltage data corresponding to the target battery cells respectively; identifying measured voltage data corresponding to each of the plurality of target battery cells by adopting a target neural network model, and determining an abnormal identification result of the target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to each of a plurality of reference battery packs, and the plurality of reference battery packs are in different states; determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal; and positioning and sampling abnormal events to occur to the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to the target battery cells. The method achieves the aim of reducing the workload of abnormal sampling examination, achieves the technical effect of positioning the position where the abnormal sampling occurs, and further solves the technical problems of abnormal sampling identification and insufficient positioning capability in the related technology.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of an alternative battery sampling anomaly identification method provided in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of a battery sampling anomaly identification method according to an embodiment of the present invention;
FIG. 3 is an algorithm block diagram of an alternative battery sampling anomaly identification method provided in accordance with an embodiment of the present invention;
FIG. 4 is a schematic view of a sliding window of an alternative method for identifying battery sampling anomalies according to an embodiment of the present invention;
FIG. 5 is a schematic view of a method for identifying an abnormality in battery sampling according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of sampling anomalies for an alternative method of identifying battery sampling anomalies according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of sampling anomalies according to another alternative method of identifying battery sampling anomalies provided by an embodiment of the present invention;
FIG. 8 is a schematic illustration of sampling anomalies according to yet another alternative method of identifying battery sampling anomalies provided in accordance with an embodiment of the present invention;
Fig. 9 is a schematic diagram of an alternative battery sampling anomaly identification device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The battery is the only source of the power of the pure electric vehicle, and the overall performance of the electric vehicle, including endurance, dynamic performance and the like, is directly influenced by the quality of the battery technology, so that the safety problem of the battery cannot be ignored. In the use process of the vehicle, in order to ensure the healthy use of the battery, the power storage battery management system can monitor the voltage of the battery monomer in real time, so that the overcharge and overdischarge of the battery are avoided. According to the control strategy of battery management, the battery cell sampling is lost or abnormal (such as too low voltage and too high voltage) occurs in the whole vehicle running or charging process, and certain fault treatment measures such as limiting the output power of a battery pack or stopping charging are adopted. A battery cell sampling module of a battery pack relates to a battery cell, a module, a sampling chip, a wire harness, a plug-in unit and the like, and failure of any module can lead to failure of a sampling functional module.
The power battery pack is formed by connecting a plurality of single batteries in series and parallel, in the using process of the power battery, BMS needs to monitor the voltage information of each single battery in real time for SOC calculation, safety monitoring, fault diagnosis and the like, when the single voltage sampling function is lost, such as the situation that the collected voltage is 0, the collected voltage is higher or lower than the actual voltage and the like and is inconsistent with the actual single voltage, the state of losing the specified function is generally called as failure or fault, and abnormal positioning and detection are needed after functional abnormality is generated so as to ensure the normal use of the power battery pack.
The power battery is waterproof, dustproof and protected, disassembly and abnormal investigation after the battery is packaged into a group can possibly result in physical damage to the battery, such as damage to a battery shell, electrolyte leakage, breakage of a connecting row and the like, so that the battery cannot work normally or becomes unsafe. If the connection between the anode and the cathode of the battery is carelessly shorted during maintenance and inspection, the battery may be shorted, a large amount of current is generated, and serious safety problems are caused. In general, disassembly and inspection of the assembled battery packs are not performed as much as possible if not necessary.
Because connect through the sampling line between Battery Management System (BMS) and the battery body in the battery package, battery management system sets up in the control unit under many circumstances, compares the investigation degree of difficulty that the battery package was disassembled lower, if can fix a position the sampling anomaly and come from battery management system, can avoid a large amount of work load of disassembling. In the related art, only the abnormal sampling can be determined, but the specific abnormal sampling position cannot be identified, so that the whole disassembly is required, the repair workload is large, and the battery pack is difficult to rebuilt.
In view of the foregoing, embodiments of the present invention provide a method embodiment for identifying battery sampling anomalies, it should be noted that the steps illustrated in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, while a logical sequence is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in a different order than that illustrated herein.
Fig. 1 is a flowchart of a battery sampling abnormality recognition method according to an embodiment of the present invention, as shown in fig. 1, including the steps of:
step S102, sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the plurality of target battery cells respectively;
it can be appreciated that the battery management system (BMS, battery Management System) is configured to detect parameters such as voltage, current, temperature, etc. of all the target battery cells in the target battery pack, and can know the operating state of the target battery pack, including the battery capacity, the remaining power, etc. in real time. By sampling a plurality of target battery cells, the battery management system can protect the target battery pack from overcharge, overdischarge, overcurrent, overtemperature and the like, so as to prevent the battery from being damaged or accidents. If the sampling function is abnormal instead of the battery itself, the battery management system can generate erroneous judgment based on measured voltage data, for example, if the battery unit with lower voltage caused by abnormal sampling function is judged to have over-discharge of the battery, the battery management system can cut off the electric energy output to the target battery pack, and the problem of power loss is caused.
Step S104, identifying measured voltage data corresponding to a plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of a target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states;
it can be understood that the trained target neural network model is adopted to identify the measured voltage data corresponding to the plurality of target battery cells respectively, so that an abnormal identification result can be obtained. The training set of the target neural network model is obtained according to voltage characteristic data of a plurality of reference battery packs. The abnormal types are various due to the sampling function, the voltage expression forms of the different types of sampling abnormalities are different, so that the target neural network model has better sampling abnormality recognition capability, the reference battery packs in the normal state and different abnormal states are selected, the training set is richer, the recognition capability of the target neural network model is stronger, and the obtained abnormality recognition result is more accurate.
Alternatively, as shown in fig. 2, the target neural model may include stacking a plurality of convolution kernels, which are filters for extracting local features in the voltage feature data, and pooling layers, and adding a plurality of full-connection layers to the back end of the network, and extracting features by sliding on the input data and performing convolution operations. The pooling layer is an operation for reducing the size of the feature map and reducing the number of computations and parameters.
The specific model structure can be various, as shown in fig. 3, which is a preferable model setting, the model setting sequentially passes through 16 convolution kernels with the size of 3*d, 32 pooling windows with the size of 2 rows and 1 column of pooling layers, 64 convolution kernels with the size of 3*1, repeatedly passes through the pooling layers with the size of 2 rows and 1 column of the 32 pooling windows, and 64 convolution kernels with the size of 3*1, and then outputs an abnormal recognition result after passing through 2 layers of full connection layers. Where, for 16 convolution kernels of size 3*d, 3 represents the size of each convolution kernel over the width and height of the input data, d represents the depth or number of channels of the input data, and 64 convolution kernels of size 3*1 are the same. The pooling layer of 2*1 represents that the size of each pooling window is 2 rows and 1 column, i.e. each pooling operation will take the maximum or average of 2 rows as output, 31 pooling layers of 2*1 represent 31 such pooling layers in the model, and the input of each pooling layer is the profile of the previous layer. Each neuron in the fully connected layer is connected to all neurons in the upper layer, each connection having a corresponding weight. Thus, the fully connected layer can connect each feature of the input data with each neuron of the next layer and adjust the degree of influence of the input data by the weight. Through superposition of a plurality of fully connected layers, the neural network can learn more complex and abstract feature representations, and perform tasks such as classification, regression and the like through the features.
In an alternative embodiment, the method further comprises: acquiring voltage characteristic data of any battery pack in the plurality of reference battery packs; expanding the voltage characteristic data of any battery pack to obtain an expansion sample corresponding to any battery pack; taking the multiple reference battery packs as any battery pack respectively to obtain expansion samples corresponding to the multiple reference battery packs respectively; and carrying out sample labeling on the extended samples respectively corresponding to the plurality of reference battery packs to obtain a training set.
It will be appreciated that due to the event characteristics of the sampling anomaly, such as poor contact, anomalies may be recovered due to vibration or jolt, and thus the amount of data collected is not large. The voltage characteristic data in the normal state is taken as a positive sample, the voltage characteristic data in different abnormal states is taken as a negative sample, and the data of the positive and negative samples are excessively different for a machine learning model, so that the problem of insufficient recognition capability for sampling abnormality is caused. Therefore, any battery pack in the plurality of reference battery packs is expanded, an expanded sample can be obtained, and after the expanded sample is subjected to sample standard, a training set for training the target neural network model can be obtained.
Optionally, sample labeling is performed on the extended samples corresponding to the plurality of reference battery packs, the extended samples containing sampling anomalies are labeled as 1, the samples without sampling anomalies are labeled as 0, and all the extended samples are divided into a training set, a verification set and a test set according to 60%, 20% and 20%. The training set is used for training the target neural network model, and the model is repeatedly iterated to learn and optimize by utilizing the training set data so that the model can be better fitted with the training data. The verification set is used for adjusting the model hyper-parameters and selecting the model, and in the training process, whether the model is over-fitted or under-fitted can be judged by evaluating the performance of the model on the verification set, and corresponding adjustment is performed. For example, the optimal super-parameter configuration can be selected by changing super-parameters such as the layer number, the node number, the learning rate and the like of the model, and then evaluating the performance of the model on the verification set. The test set is used to evaluate the final model performance, and the test set is used after the training and verification stage to simulate the behavior of the model in practical applications. By evaluating on the test set, the generalization capability of the model, i.e. the processing capability of the model to unseen data, can be checked, and the advantages and disadvantages of different models or the model can be evaluated and improved.
Optionally, the voltage characteristic data corresponding to any battery pack in the plurality of reference battery packs can be obtained by adopting a data cleaning and characteristic extraction mode. For example, the unprocessed data of any battery pack is taken as initial voltage data, the sampling interval of the initial voltage data is between 10 and 30 seconds, and the packet loss condition in the data transmission is cleaned, including dividing the fragments according to a time sequence (dividing the fragments when no data exceeds t minutes, taking 5 minutes for t generally), removing noise and filling a small amount of missing values. And extracting key characteristics such as the average value, variance and adjacent monomer voltages of the battery packs, and generating the voltage characteristic data of any battery pack.
In an alternative embodiment, the expanding the voltage characteristic data of any battery pack to obtain an expanded sample corresponding to any battery pack includes: based on a preset sliding step length and a preset window time sequence length, intercepting voltage characteristic data of any battery pack for multiple times by adopting a sliding window to obtain a plurality of groups of window data with overlapping; and under the condition that the time sequence length of any one group of data in the plurality of groups of window data is smaller than the time sequence length of the preset window, splicing any one group of data so that the time sequence length of any one group of data is equal to the time sequence length of the preset window.
It can be understood that the voltage characteristic data of any battery pack can be intercepted for multiple times in a sliding window mode, and multiple groups of window data can be obtained in a intercepting mode that partial overlapping exists among windows. In order to ensure that the sample lengths of the samples are consistent, when any one set of data in the plurality of sets of window data is shorter than the predetermined window time sequence length, the data end portion is generally used for splicing the any one set of data, so that the time sequence length of the any one set of data is equal to the predetermined window time sequence length.
Optionally, as shown in fig. 4, the predetermined sliding step length is s, the predetermined window time sequence length is n, and it is known that part of the windows cover sampling anomalies of adjacent battery cells, which may be labeled 1, and other windows may or may not include sampling anomalies, so that a plurality of positive and negative samples can be obtained in this way. As shown in fig. 5, when the window is not completely cut, if one partial window is cut to be k and the other partial window is cut to be n-k, the two windows may be spliced so that the sample length is a predetermined window time sequence length n.
Step S106, determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality recognition result indicates that the sampling voltage is abnormal;
It can be understood that the target neural network is adopted to perform abnormality recognition, and under the condition that the abnormality of the sampling voltage exists, the state of the battery pack side is normally received due to sampling, the state of the battery management system side is influenced, after the abnormality of the sampling voltage is recognized, the positioning of the sampling abnormality is also required, and the voltage time sequence trend corresponding to each of the plurality of target battery monomers is determined based on the actually measured voltage data corresponding to each of the plurality of target battery monomers.
Step S108, based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, the abnormal event of positioning and sampling occurs in the battery management system and/or the target battery pack.
It will be appreciated that the battery management system samples a plurality of target battery cells in real time, each of which has a cell voltage variation trend that varies with time, i.e., a corresponding voltage time series trend. According to the voltage time sequence trend corresponding to the multiple target battery cells, the position of the sampling abnormal event can be positioned in the battery management system and/or the target battery pack.
In an alternative embodiment, locating sampling anomalies occurring in a battery management system and/or a target battery pack based on voltage timing trends corresponding to a plurality of target battery cells, respectively, includes: two adjacent battery cells exist in the plurality of target battery cells, the voltage time sequence trends corresponding to the two adjacent battery cells are symmetrically distributed about the mean change trend, and under the condition that the voltage time sequence trend of one of the two adjacent battery cells is higher than the mean change trend and the voltage time sequence trend of the other battery cell is lower than the mean change trend, the positioning and sampling abnormal event occurs in the target battery pack, wherein the mean change trend is the average voltage trend of other battery cells except the two adjacent battery cells in the plurality of target battery cells.
It can be appreciated that the voltages of all the target battery cells in the battery pack are relatively balanced under normal conditions, and the voltage time sequence trend of each battery cell tends to be consistent. In the event of a battery sampling anomaly, the sampling anomaly results in a voltage timing trend that is identifiable as a specific trend, as compared to the cell itself anomaly (e.g., cell overdischarge). Two adjacent battery cells exist in the plurality of target battery cells, the voltage time sequence trends corresponding to the two adjacent battery cells are symmetrically distributed about the mean change trend, and the voltage time sequence trend of one of the two adjacent battery cells is higher than the mean change trend, and the voltage time sequence trend of the other one of the two adjacent battery cells is lower than the mean change trend, namely the two adjacent battery cells are one high and one low, and are symmetrically distributed about the mean change trend, so that the abnormal sampling event can be positioned and generated in the target battery pack.
Alternatively, in the above case, the sampling abnormality event may be various, as shown in fig. 6, a common sampling line between two adjacent cells at one side of the battery pack, a harness terminal having dust or an abnormal connection of the collection harness, resulting in an increase in contact resistance. The welding failure or missing welding of the connecting row can also exist between two adjacent monomers, so that the series connection is unstable, a high voltage and a low voltage exist between the two adjacent monomers, and the reason that the two adjacent monomers are distributed symmetrically along the average value is that the voltage of the monomer with higher voltage is the difference between V2 and V1 acquired by the sampling line, the voltage of the other adjacent monomer U2 is lower due to the fact that the voltage of the sampling line is abnormal or the series connection is unstable, the contact resistance is abnormally increased, the voltage of the U1 is increased, the V2 is larger, a common line exists between the two adjacent monomers, and the acquisition voltage of the U2 is obtained due to the difference between the sampling lines V3 and V2.
In an alternative embodiment, locating sampling anomalies occurring in a battery management system and/or a target battery pack based on voltage timing trends corresponding to a plurality of target battery cells, respectively, includes: and under the condition that the voltage time sequence trend of the first monomer and the voltage time sequence trend of the third monomer are the same and higher than the mean change trend, and the voltage time sequence trend of the second monomer is lower than the mean change trend, positioning and sampling abnormal events occur in a battery management system, wherein the mean change trend is the average voltage trend of other monomers except for the three adjacent monomers in the plurality of target battery monomers.
It can be understood that three adjacent battery cells exist in the plurality of target battery cells, and the voltage time sequence trend change characteristics of the three adjacent battery cells are that the voltage time sequence trend corresponding to the first cell and the third cell is the same and higher than the mean change trend, and the voltage time sequence trend of the second cell is lower than the mean change trend, so that the abnormal event of sampling can be positioned and occurred in the battery management system according to the characteristics.
In the above-mentioned case, as shown in fig. 7, the abnormal sampling event may be that the leakage current of the zener diode of the second unit in the battery management system is too large, and the zener diode may also limit the maximum output current of the battery unit, so as to prevent overload or short circuit of the battery and protect the safety of the battery unit and the whole system. Once the leakage current of the zener diode of the second monomer is too large, the voltage division on the shared collecting line between the first monomer and the second monomer is increased, and the voltage division on the shared collecting line between the third monomer and the second monomer is increased, so that the voltage time sequence trend corresponding to the first monomer and the third monomer is the same and higher than the mean change trend, and the time sequence trend of the second monomer is lower than the mean change trend. Further, the first and third cells are greater than the first differential pressure value of the mean change trend and are less than twice the second differential pressure value of the mean change trend.
In an alternative embodiment, locating sampling anomalies occurring in a battery management system and/or a target battery pack based on voltage timing trends corresponding to a plurality of target battery cells, respectively, includes: under the condition that two adjacent battery cells exist in the plurality of target battery cells, and the voltage time sequence trend corresponding to the two adjacent battery cells is higher or lower than the average value change trend at the same time, the positioning and sampling abnormal event occurs in the target battery pack and the battery management system, wherein the average value change trend is the average voltage trend of other cells except the two adjacent battery cells in the plurality of target battery cells.
It can be understood that under the condition that multiple sampling abnormal events exist and multiple abnormal events coexist, the voltage time sequence trend characteristics are two adjacent battery units, the voltage time sequence trend corresponding to the two adjacent battery units is higher or lower than the mean value change trend at the same time, and the sampling abnormal events can be positioned to occur in the target battery pack and the battery management system.
In the above case, as shown in fig. 8, in the case where there is an abnormality on both the battery management system side and the battery pack side, it is possible that the adjacent cell voltages are higher or lower due to the superposition of various abnormalities, and may be located at the upper or lower positions of the voltage average, instead of being symmetrical.
In an alternative embodiment, after locating the sampling anomaly event to occur in the battery management system and/or the target battery pack based on the voltage timing trends corresponding to the plurality of target battery cells, respectively, the method further comprises: determining a plurality of maintenance battery packs matched with the type of the target battery pack and sampling abnormal positioning data respectively corresponding to the plurality of maintenance data packs, wherein the plurality of maintenance battery packs are battery packs for positioning sampling abnormal events in a preset historical period; determining abnormal probability of the sampling abnormal event occurring in the battery management system and/or the target battery pack based on the sampling abnormal positioning data respectively corresponding to the plurality of maintenance data packs; based on the positioning result of the sampling abnormal event and the abnormal probability, generating combined prompt information.
It can be understood that, in order to further improve accuracy of the prompt information, based on the sampling abnormality positioning data corresponding to each of the plurality of maintenance battery packs with matched types, positions where sampling abnormality of the battery packs appears once can be prompted, so as to obtain abnormality probability of the battery management system or the target battery pack, after the positioning result is combined with the abnormality probability, combined prompt information is obtained, and positioning adopting abnormal events is performed to suggest maintenance for relevant technicians, so that troubleshooting of fault positions is facilitated, and unnecessary battery unpacking is avoided.
Through the step S102, a battery management system is adopted to sample a plurality of target battery cells included in a target battery pack, so as to obtain measured voltage data corresponding to the plurality of target battery cells respectively; step S104, identifying measured voltage data corresponding to a plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of a target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states; step S106, determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality recognition result indicates that the sampling voltage is abnormal; step S108, based on the voltage time sequence trend corresponding to each of the plurality of target battery cells, the abnormal event of positioning and sampling occurs in the battery management system and/or the target battery pack. The method can realize the purpose of reducing the workload of abnormal sampling examination, realize the technical effect of positioning the position where the abnormal sampling occurs, and further solve the technical problems of abnormal sampling identification and insufficient positioning capability in the related technology.
Based on the above embodiment and the optional embodiment, the present invention provides an optional embodiment, which is applied to an electric vehicle with a lithium ion battery, and a battery management system in a control unit in the vehicle is connected with a power battery pack through a communication line and a sampling line to collect battery cells in real time, so as to obtain measured voltage data.
In order to identify sampling abnormality, a target neural network model needs to be obtained first, and the model generation mode is that initial voltage data of different normal or abnormal reference battery packs are obtained, data emotion and feature extraction are carried out, and voltage feature data are generated. In order to make the normal and abnormal states respectively correspond to the positive and negative samples to be relatively balanced, a sliding window mode is adopted for sample expansion, and an expanded sample is obtained. After the extended samples are subjected to sample labeling, training sets, verification sets and test sets are divided by 60%, 20% and 20%. Training the target neural network model by using a training set, adjusting model parameters in the training process by using a verification set, and finally verifying the model performance by using a test set to obtain the target neural network model.
And inputting the measured voltage data into a target neural network model for recognition, so that an abnormal recognition result of the battery pack can be obtained. Under the condition that the battery pack is determined to have the abnormal sampling voltage, on the basis of measured voltage data, all the battery cells can be determined to correspond to voltage time sequence trend respectively, and by determining the trend characteristics, for example, the situation that one high-low voltage exists between two adjacent battery cells and the sampling voltage is symmetrical along the average voltage trend is determined, the sampling abnormal situation can be located in the battery pack. For example, three adjacent battery cells have high and low trends, and the abnormal trends of the first cell and the third cell are the same, so that the sampling abnormality can be positioned and occurred in the battery management system.
According to the mode, the positioning result of the sampling abnormal event in the battery pack can be obtained, the abnormal probability of the occurrence position of the sampling abnormal event in the battery pack can be determined by combining the type-matched maintenance battery pack, and the combined prompt information can be obtained to prompt related technicians to assist in the detection of the sampling abnormal event. The identification capability of the sampling abnormality can be effectively improved, and the workload of battery disassembly caused by the abnormal battery sampling is reduced.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment also provides a device for identifying abnormal battery sampling, which is used for implementing the above embodiment and the preferred implementation, and is not described in detail. As used below, the terms "module," "apparatus" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
According to an embodiment of the present invention, there is further provided an apparatus embodiment for implementing a method for identifying a battery sampling abnormality, and fig. 9 is a schematic diagram of an apparatus for identifying a battery sampling abnormality according to an embodiment of the present invention, as shown in fig. 9, including: the sampling module 902, the identification module 904, the gesture determination module 906, the positioning module 908, the apparatus is described below.
The sampling module 902 is configured to sample a plurality of target battery cells included in a target battery pack by using a battery management system, so as to obtain measured voltage data corresponding to the plurality of target battery cells respectively;
the identifying module 904 is connected with the sampling module 902, and is configured to identify measured voltage data corresponding to a plurality of target battery cells respectively by using a target neural network model, and determine an abnormal identification result of a target battery pack, where the target neural network model is obtained by training using a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states;
the trend determining module 906 is connected with the identifying module 904, and is configured to determine voltage time sequence trends corresponding to the multiple target battery cells respectively based on measured voltage data corresponding to the multiple target battery cells respectively when the abnormal identification result indicates that there is a sampling voltage abnormality;
The positioning module 908 is connected to the trend determining module 906, and is configured to position the abnormal event of sampling to occur in the battery management system and/or the target battery pack based on the voltage time sequence trends corresponding to the target battery cells.
In the device for identifying abnormal sampling of a battery provided by the embodiment of the invention, a sampling module 902 is used for sampling a plurality of target battery monomers included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the plurality of target battery monomers respectively; the identifying module 904 is connected with the sampling module 902, and is configured to identify measured voltage data corresponding to a plurality of target battery cells respectively by using a target neural network model, and determine an abnormal identification result of a target battery pack, where the target neural network model is obtained by training using a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states; the trend determining module 906 is connected with the identifying module 904, and is configured to determine voltage time sequence trends corresponding to the multiple target battery cells respectively based on measured voltage data corresponding to the multiple target battery cells respectively when the abnormal identification result indicates that there is a sampling voltage abnormality; the positioning module 908 is connected to the trend determining module 906, and is configured to position the abnormal event of sampling to occur in the battery management system and/or the target battery pack based on the voltage time sequence trends corresponding to the target battery cells. The method achieves the aim of reducing the workload of abnormal sampling examination, achieves the technical effect of positioning the position where the abnormal sampling occurs, and further solves the technical problems of abnormal sampling identification and insufficient positioning capability in the related technology.
It should be noted that each of the above modules may be implemented by software or hardware, for example, in the latter case, it may be implemented by: the above modules may be located in the same processor; alternatively, the various modules described above may be located in different processors in any combination.
It should be noted that the sampling module 902, the identifying module 904, the gesture determining module 906, and the positioning module 908 correspond to steps S102 to S108 in the embodiment, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the embodiment. It should be noted that the above modules may be run in a computer terminal as part of the apparatus.
It should be noted that, the optional or preferred implementation manner of this embodiment may be referred to the related description in the embodiment, and will not be repeated herein.
The battery sampling abnormality recognition device may further include a processor and a memory, the sampling module 902, the recognition module 904, the trend determination module 906, the positioning module 908, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel may be provided with one or more. The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the invention provides a nonvolatile storage medium, and a program is stored on the nonvolatile storage medium, and the program realizes a battery sampling abnormality identification method when being executed by a processor.
The embodiment of the invention provides an electronic device, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the following steps are realized when the processor executes the program: sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the plurality of target battery cells respectively; identifying measured voltage data corresponding to a plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of a target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states; determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal; based on the voltage time sequence trend corresponding to the plurality of target battery cells, the abnormal event of positioning and sampling occurs in the battery management system and/or the target battery pack. The device herein may be a server, a PC, etc.
The invention also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the plurality of target battery cells respectively; identifying measured voltage data corresponding to a plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of a target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to a plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states; determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal; based on the voltage time sequence trend corresponding to the plurality of target battery cells, the abnormal event of positioning and sampling occurs in the battery management system and/or the target battery pack.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.
Claims (10)
1. A battery sampling abnormality identification method, characterized by comprising:
sampling a plurality of target battery cells included in a target battery pack by adopting a battery management system to obtain measured voltage data corresponding to the target battery cells respectively;
identifying measured voltage data corresponding to each of the plurality of target battery cells by adopting a target neural network model, and determining an abnormal identification result of the target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to each of a plurality of reference battery packs, and the plurality of reference battery packs are in different states;
determining voltage time sequence trend corresponding to each of the plurality of target battery cells based on measured voltage data corresponding to each of the plurality of target battery cells when the abnormality identification result indicates that the sampling voltage is abnormal;
and positioning and sampling abnormal events to occur to the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to the target battery cells.
2. The method according to claim 1, wherein the method further comprises:
Acquiring voltage characteristic data of any battery pack in the plurality of reference battery packs;
expanding the voltage characteristic data of any battery pack to obtain an expansion sample corresponding to the any battery pack;
taking the plurality of reference battery packs as the arbitrary battery packs respectively to obtain expansion samples corresponding to the plurality of reference battery packs respectively;
and carrying out sample labeling on the extended samples respectively corresponding to the plurality of reference battery packs to obtain the training set.
3. The method according to claim 2, wherein the expanding the voltage characteristic data of the arbitrary battery pack to obtain the expanded sample corresponding to the arbitrary battery pack includes:
based on a preset sliding step length and a preset window time sequence length, carrying out multiple interception on the voltage characteristic data of any battery pack by adopting a sliding window to obtain a plurality of groups of window data with overlapping;
and under the condition that the time sequence length of any group of data in the plurality of groups of window data is smaller than the time sequence length of the preset window, splicing the any group of data so that the time sequence length of any group of data is equal to the time sequence length of the preset window.
4. The method of claim 1, wherein locating sampling anomalies occurring at the battery management system and/or the target battery pack based on the respective corresponding voltage timing trends of the plurality of target battery cells comprises:
and when the voltage time sequence trend of one of the two adjacent battery cells is higher than the average change trend, the sampling abnormal event is positioned to occur in the target battery pack, wherein the average change trend is the average voltage trend of other cells except the two adjacent cells in the plurality of target battery cells.
5. The method of claim 1, wherein locating sampling anomalies occurring at the battery management system and/or the target battery pack based on the respective corresponding voltage timing trends of the plurality of target battery cells comprises:
Three adjacent battery monomers exist in the plurality of target battery monomers, namely a first monomer, a second monomer and a third monomer in sequence, the voltage time sequence trend corresponding to the first monomer and the voltage time sequence trend corresponding to the third monomer are the same and higher than the average change trend, and the abnormal sampling event is located to occur in the battery management system under the condition that the voltage time sequence trend of the second monomer is lower than the average change trend, wherein the average change trend is the average voltage trend of other monomers except the three adjacent monomers in the plurality of target battery monomers.
6. The method of claim 1, wherein locating sampling anomalies occurring at the battery management system and/or the target battery pack based on the respective corresponding voltage timing trends of the plurality of target battery cells comprises:
and under the condition that two adjacent battery cells exist in the plurality of target battery cells, and the voltage time sequence trend corresponding to the two adjacent battery cells is higher or lower than the average change trend at the same time, positioning that the sampling abnormal event occurs in the target battery pack and the battery management system, wherein the average change trend is the average voltage trend of other cells except the two adjacent battery cells in the plurality of target battery cells.
7. The method according to any one of claims 1 to 6, wherein after the positioning sampling abnormal event occurs to the battery management system and/or the target battery pack based on the voltage timing trend corresponding to the plurality of target battery cells, respectively, the method further comprises:
determining a plurality of maintenance battery packs matched with the target battery pack type and sampling abnormal positioning data corresponding to the plurality of maintenance data packs respectively, wherein the plurality of maintenance battery packs are battery packs in which the sampling abnormal event is positioned in a preset historical period;
determining abnormal probability of the sampling abnormal event occurring in the battery management system and/or the target battery pack based on the sampling abnormal positioning data respectively corresponding to the plurality of maintenance data packs;
and generating combined prompt information based on the positioning result of the sampling abnormal event and the abnormal probability.
8. A battery sampling abnormality recognition device, characterized by comprising:
the sampling module is used for sampling a plurality of target battery monomers included in the target battery pack by adopting the battery management system to obtain measured voltage data corresponding to the plurality of target battery monomers respectively;
The identification module is used for identifying measured voltage data corresponding to the plurality of target battery cells respectively by adopting a target neural network model, and determining an abnormal identification result of the target battery pack, wherein the target neural network model is obtained by training by adopting a training set, the training set is generated based on voltage characteristic data corresponding to the plurality of reference battery packs respectively, and the plurality of reference battery packs are in different states;
the trend determining module is used for determining voltage time sequence trends corresponding to the target battery cells based on measured voltage data corresponding to the target battery cells respectively when the abnormality identification result indicates that sampling voltage abnormality exists;
and the positioning module is used for positioning and sampling abnormal events to occur to the battery management system and/or the target battery pack based on the voltage time sequence trend corresponding to the target battery cells.
9. A non-volatile storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the battery sampling anomaly identification method of any one of claims 1 to 7.
10. An electronic device, comprising: one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the battery sample anomaly identification method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373647.4A CN117665604A (en) | 2023-10-20 | 2023-10-20 | Battery sampling abnormality identification method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373647.4A CN117665604A (en) | 2023-10-20 | 2023-10-20 | Battery sampling abnormality identification method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117665604A true CN117665604A (en) | 2024-03-08 |
Family
ID=90063018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311373647.4A Pending CN117665604A (en) | 2023-10-20 | 2023-10-20 | Battery sampling abnormality identification method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117665604A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118151020A (en) * | 2024-05-11 | 2024-06-07 | 广汽埃安新能源汽车股份有限公司 | Method and system for detecting safety performance of battery |
-
2023
- 2023-10-20 CN CN202311373647.4A patent/CN117665604A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118151020A (en) * | 2024-05-11 | 2024-06-07 | 广汽埃安新能源汽车股份有限公司 | Method and system for detecting safety performance of battery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Voltage fault diagnosis and prognosis of battery systems based on entropy and Z-score for electric vehicles | |
| CN112098850B (en) | Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm | |
| CN115902646B (en) | Energy storage battery fault identification method and system | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| CN117665604A (en) | Battery sampling abnormality identification method and device, storage medium and electronic equipment | |
| CN110146817A (en) | The diagnostic method of lithium battery failure | |
| CN115267557B (en) | Lithium battery electrolyte leakage fault diagnosis method and device and electronic equipment | |
| CN111257755A (en) | Method for preventive detection and diagnosis of battery pack | |
| CN113255764A (en) | Method, system and device for detecting electrochemical energy storage system fault by using machine learning | |
| CN113866641A (en) | Fault detection method and device for lithium ion battery | |
| Sohn et al. | Two-stage deep learning for online prediction of knee-point in Li-ion battery capacity degradation | |
| He et al. | Voltage abnormality-based fault diagnosis for batteries in electric buses with a self-adapting update model | |
| CN116973782A (en) | New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning | |
| Jeng et al. | Evaluation of cell inconsistency in lithium-ion battery pack using the autoencoder network model | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| CN114325433A (en) | Lithium ion battery fault detection method and system based on electrochemical impedance spectrum test | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN112540301B (en) | Battery detection method, device and storage medium | |
| Shete et al. | Fault diagnosis of electric vehicle’s battery by deploying neural network | |
| CN115128468A (en) | Chemical energy storage battery PHM undervoltage fault prediction method | |
| CN115447439A (en) | Charging safety early warning method, system, equipment and medium based on battery temperature | |
| CN115608653A (en) | Method and device for screening abnormal battery units in battery system | |
| CN113391228A (en) | Battery internal resistance and health state monitoring method and electronic device | |
| Ren et al. | Multi-fault diagnosis strategy based on a non-redundant interleaved measurement circuit and improved fuzzy entropy for the battery system | |
| CN117648612B (en) | Parallel battery pack fault detection method, device, electronic equipment and storage medium |
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 |