CN117289026A - Battery gluing detection method and device, electronic equipment and storage medium - Google Patents
Battery gluing detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117289026A CN117289026A CN202210688456.6A CN202210688456A CN117289026A CN 117289026 A CN117289026 A CN 117289026A CN 202210688456 A CN202210688456 A CN 202210688456A CN 117289026 A CN117289026 A CN 117289026A
- Authority
- CN
- China
- Prior art keywords
- battery pack
- adhesive
- classification
- parameter
- detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 146
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000004026 adhesive bonding Methods 0.000 title abstract description 6
- 239000000853 adhesive Substances 0.000 claims abstract description 91
- 230000001070 adhesive effect Effects 0.000 claims abstract description 91
- 230000000694 effects Effects 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000013145 classification model Methods 0.000 claims description 38
- 239000003292 glue Substances 0.000 claims description 36
- 230000007547 defect Effects 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 239000012790 adhesive layer Substances 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 239000000110 cooling liquid Substances 0.000 description 2
- 238000003475 lamination Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- SMZOUWXMTYCWNB-UHFFFAOYSA-N 2-(2-methoxy-5-methylphenyl)ethanamine Chemical compound COC1=CC=C(C)C=C1CCN SMZOUWXMTYCWNB-UHFFFAOYSA-N 0.000 description 1
- NIXOWILDQLNWCW-UHFFFAOYSA-N 2-Propenoic acid Natural products OC(=O)C=C NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 239000002390 adhesive tape Substances 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 239000004814 polyurethane Substances 0.000 description 1
- 229920002635 polyurethane Polymers 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R27/00—Arrangements for measuring resistance, reactance, impedance, or electric characteristics derived therefrom
- G01R27/02—Measuring real or complex resistance, reactance, impedance, or other two-pole characteristics derived therefrom, e.g. time constant
- G01R27/08—Measuring resistance by measuring both voltage and current
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R27/00—Arrangements for measuring resistance, reactance, impedance, or electric characteristics derived therefrom
- G01R27/02—Measuring real or complex resistance, reactance, impedance, or other two-pole characteristics derived therefrom, e.g. time constant
- G01R27/26—Measuring inductance or capacitance; Measuring quality factor, e.g. by using the resonance method; Measuring loss factor; Measuring dielectric constants ; Measuring impedance or related variables
- G01R27/2605—Measuring capacitance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Battery Mounting, Suspending (AREA)
Abstract
The disclosure provides a battery gluing detection method and device, electronic equipment and a storage medium, and belongs to the technical field of battery detection. The battery gluing detection method comprises the following steps: acquiring a first RC parameter of a battery pack; and carrying out classification recognition on the adhesive in the battery pack based on the first RC parameter to generate a classification recognition result of the adhesive, wherein the classification recognition result is used for indicating the filling effect of the adhesive. According to the method and the device, the filling effect of the adhesive in the battery pack is identified according to the RC parameters of the battery pack, the filling effect of the pressed adhesive can be detected, the detection efficiency is improved, and the detection cost is saved.
Description
Technical Field
The disclosure relates to the technical field of battery detection, and in particular relates to a battery gluing detection method, a device, electronic equipment and a storage medium.
Background
In the process of manufacturing the battery pack of the vehicle, an adhesive is generally used for adhering the battery cells of the battery with the water-cooling plate/box bottom plate to form the battery pack, wherein the adhesive has the function of fixing the battery cells on one hand and can improve the heat transfer efficiency on the other hand.
The filling effect of the adhesive is extremely important to the structural reliability and the thermal management effect of the battery pack, so that the filling effect of the adhesive in the battery pack needs to be detected to ensure the quality of the battery pack.
In the related art, the visual detection scheme judges the filling effect of the adhesive by identifying parameters such as a gluing track before lamination, the size of the adhesive tape and the like, but the filling effect of the adhesive after lamination cannot be detected in actual production, and in addition, the detection method using X rays and the like has higher cost, lower efficiency and cannot be put into mass production.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
To this end, an object of the present disclosure is to propose a battery glue detection method.
A second object of the present disclosure is to provide a battery glue detecting device.
A third object of the present disclosure is to propose an electronic device.
A fourth object of the present disclosure is to propose a non-transitory computer readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present disclosure provides a battery glue detection method, including: acquiring a first RC parameter of a battery pack; and based on the first RC parameters, classifying and identifying the adhesive in the battery pack to generate a classifying and identifying result of the adhesive, wherein the classifying and identifying result is used for indicating the filling effect of the adhesive.
In the embodiment of the disclosure, a first RC parameter of a battery pack is obtained, and based on the first RC parameter, the adhesive in the battery pack is classified and identified, so that a classification and identification result of the adhesive is generated. In the embodiment of the disclosure, the filling effect of the adhesive in the battery pack is identified according to the RC parameter of the battery pack, so that the filling effect of the pressed adhesive can be detected, the detection efficiency is improved, and the detection cost is saved.
An embodiment of a second aspect of the present disclosure provides a battery glue detection device, including: the first acquisition module is used for acquiring a first RC parameter of the battery pack; and the classification and identification module is used for carrying out classification and identification on the adhesive in the battery pack based on the first RC parameter to generate a classification and identification result of the adhesive, wherein the classification and identification result is used for indicating the filling effect of the adhesive.
To achieve the above object, an embodiment of a third aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to implement the battery glue detection method according to the embodiment of the first aspect of the present disclosure.
To achieve the above object, a fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for implementing the battery glue detection method according to the foregoing first aspect embodiment.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flow chart of a battery glue detection method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of the detection principle of a battery pack;
fig. 3 is a flow chart of a battery glue detection method according to another embodiment of the present disclosure;
fig. 4 is a flow chart of a battery glue detection method according to another embodiment of the present disclosure;
fig. 5 is a flow chart of a battery glue detection method according to another embodiment of the present disclosure;
fig. 6 is a flow chart of a battery glue detection method according to another embodiment of the present disclosure;
fig. 7 is a flow chart of a battery glue detection method according to another embodiment of the present disclosure;
fig. 8 is a schematic diagram of a practical application flow of a battery glue detection method;
fig. 9 is a schematic structural view of a battery glue detection device according to an embodiment of the present disclosure;
fig. 10 is a schematic structural view of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
The battery glue detecting method, device, electronic equipment and storage medium according to the embodiments of the present disclosure are described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a battery glue detection method according to an embodiment of the disclosure, as shown in fig. 1, the method includes the following steps:
s101, acquiring a first RC parameter of the battery pack.
The first RC parameter includes a capacitance parameter and a resistance parameter for characterizing capacitive and impedance characteristics of the battery.
In this embodiment of the disclosure, referring to fig. 2, the battery pack includes a cell and a bottom plate of the battery, where the bottom plate may be a water-cooled plate or a box bottom plate, the cell includes an aluminum metal shell, the shell is insulated, and the bottom of the shell is adhered to the bottom plate by an adhesive. In the process of producing the battery pack, the adhesive smeared between the bottom of the battery cell shell and the bottom plate is pressed to form the battery pack. The battery cell may be a rectangular battery cell, and the shape of the battery cell is not limited herein.
The water cooling plate is a sub-part of a battery thermal management system, is usually an aluminum element with a cooling liquid flow channel, can exchange heat with the battery core, and realizes the cooling/heating function through the circulation of cooling liquid.
The case is a sub-part of the battery structural system for housing and carrying the cells and other components.
The adhesive is a substance with an adhesive function, can connect two or more object surfaces, can play roles of fixing constraint and improving heat transfer efficiency, and refers to structural adhesive or heat-conducting adhesive in the battery pack, and the chemical components of the adhesive can be polyurethane, epoxy resin, acrylic acid and the like.
In some implementations, a voltage may be applied across the battery pack, a current of the battery pack at the voltage is measured, and a first RC parameter of the battery pack is obtained based on the current and the voltage.
S102, based on the first RC parameters, classifying and identifying the adhesives in the battery pack, and generating a classifying and identifying result of the adhesives.
The classification recognition result is used for indicating the filling effect of the adhesive.
The adhesives with different filling effects have different capacitive reactance characteristics and impedance characteristics, namely different first RC parameters, so that a certain mapping relation exists between the first RC parameters and the filling effects of the adhesives in the battery pack, the mapping relation between the first RC parameters and the filling of the adhesives can be determined, the adhesives in the battery pack are classified and identified according to the mapping relation between the first RC parameters and the filling of the adhesives, and the filling effects of the adhesives, such as over-thick adhesive layer, over-thin adhesive layer, insufficient filling, excessive adhesive overflow, no defects and the like, are determined.
For example, assume that the mapping between the first RC parameter and the adhesive fill is: and when the filling defect of the adhesive corresponding to the first RC parameter A is a defect a, the filling defect of the adhesive corresponding to the first RC parameter B is a defect B, and the filling defect of the adhesive corresponding to the first RC parameter C is a defect C and … …, determining that the filling defect of the adhesive in the battery pack is a defect B.
After the classification and identification of the adhesive in the battery pack are performed to generate a classification and identification result of the adhesive, the battery pack with the filling defect of the adhesive can be screened out based on the classification and identification result so as to ensure the quality of the battery pack.
In the embodiment of the disclosure, a first RC parameter of a battery pack is obtained, and based on the first RC parameter, the adhesive in the battery pack is classified and identified, so that a classification and identification result of the adhesive is generated. In the embodiment of the disclosure, the filling effect of the adhesive in the battery pack is identified according to the RC parameter of the battery pack, so that the filling effect of the pressed adhesive can be detected, the detection efficiency is improved, and the detection cost is saved.
Fig. 3 is a flowchart of a battery glue detection method according to an embodiment of the present disclosure, and further with reference to fig. 3, a process of obtaining a first RC parameter of a battery pack is explained based on the above embodiment, and the process includes the following steps:
s301, acquiring a first detection current of the battery pack in a first detection loop.
The first detection loop is formed by connecting a battery pack and a detection device in series, and the detection device is used for detecting current in the loop.
In the embodiment of the disclosure, the detection device comprises an oscilloscope, a universal meter and the like, and can provide detection voltages for two ends of the battery pack and measure first detection currents of the battery pack in the first detection loop at different detection moments under the detection voltages.
The first detection current curve may be generated based on the first detection current of the battery pack in the first detection loop at different detection times at the detection voltage, and the first detection current curve represents the relationship between the first detection current and the detection time at the detection voltage provided by the detection device.
The detection device is taken as an oscilloscope for explanation: referring to fig. 2, an input end and an output end of the oscilloscope are respectively connected with two ends of the battery pack to form a first detection loop. The oscilloscope applies high voltage excitation at two ends of the battery pack and detects the response (namely first detection current) of the battery pack to generate a corresponding first detection current curve.
S302, determining a target RC equivalent circuit model, and carrying out parameter identification based on the first detection current and the target RC equivalent circuit model to generate a first RC parameter of the battery pack.
The RC equivalent circuit model is an equivalent theoretical circuit model of an actual circuit, and the target RC equivalent circuit model may be a first-order equivalent RC equivalent circuit model, a second-order equivalent circuit RC model, a third-order RC equivalent circuit model, or the like, which is not limited herein.
When the filling effect of the adhesive in the battery pack is identified, the standard battery pack without filling defects can be used as a reference for identification so as to identify the filling defects of the battery pack.
Optionally, determining an RC equivalent circuit model corresponding to a second detection loop where the standard battery pack without filling defects is located as a target RC equivalent circuit model, wherein the second detection loop is formed by connecting the standard battery pack and a detection device in series.
The parameter identification is a method for combining a theoretical model and experimental data for prediction, and the parameter of an unknown system model can be inverted according to the known system model and the known system model parameters.
The battery pack can be equivalently a parallel plate capacitor (usually at nF level), and the adhesive has a certain dielectric constant and an equivalent resistor (usually at gΩ level), and since the filling effect of the adhesive in the battery pack affects the capacitive reactance characteristic and the impedance characteristic of the battery pack, the battery pack can be equivalently used as a capacitor and a resistor to obtain a target RC equivalent circuit model corresponding to the first detection loop, and the first RC parameter of the battery pack is generated by performing parameter identification based on the first detection current and the target RC equivalent circuit.
In the embodiment of the disclosure, a first detection current of a battery pack in a first detection loop is obtained, parameter identification is performed based on the first detection current and a target RC equivalent circuit model corresponding to the first detection loop, and a first RC parameter of the battery pack is generated. According to the embodiment of the disclosure, the RC parameters of the battery pack are obtained through the parameter identification method, so that the accuracy of the RC parameters of the battery pack is improved.
Fig. 4 is a flowchart of a battery glue detecting method according to an embodiment of the present disclosure, and further with reference to fig. 4, a process of generating a first RC parameter of a battery pack by performing parameter identification based on a first detected current and a target RC equivalent circuit model is explained based on the above embodiment, and includes the following steps:
s401, generating an identification equation based on the target RC equivalent circuit model.
Wherein the identification equation is a mathematical equation generated with respect to the first RC parameter based on the target RC equivalent circuit model.
In some implementations, the recognition equation of the target RC equivalent circuit model may be established according to the method of the dyvenin theorem, kirchhoff current law, kirchhoff voltage law, or the like.
S402, calculating a first RC parameter of the battery pack based on the first detection current and the identification equation.
In the embodiment of the disclosure, the detection device may provide a detection voltage for the battery pack, so as to detect the first detection current at different detection moments under the detection voltage, and obtain a current curve of the first detection current.
In some implementations, discretizing an identification equation to obtain a Laplacian equation of a target RC equivalent circuit model, establishing a differential equation of input and output of the target RC equivalent circuit model according to the Laplacian equation, and establishing a parameter equation of a first RC parameter according to the differential equation by a least square method, a recursive augmented square method, a recursive least square method with forgetting factors or the like, and substituting first detection currents of the battery pack at different detection moments under detection voltages into the parameter equation of the first RC parameter to calculate to obtain the first RC parameter of the battery pack.
In an embodiment of the disclosure, an identification equation is generated based on a target RC equivalent circuit model, and a first RC parameter of the battery pack is calculated based on a first detection current and the identification equation. According to the embodiment of the disclosure, the first RC parameter of the battery pack is calculated, accurate identification data is provided for the classification and identification of the filling effect of the adhesive in the battery pack, and the accuracy of classification and identification is improved.
Fig. 5 is a flow chart of a battery glue detection method according to an embodiment of the disclosure, as shown in fig. 5, the battery glue detection method further includes the following steps:
s501, a first RC parameter of the battery pack is acquired.
The description of step S501 may be referred to the description of the above embodiments, and will not be repeated here.
S502, inputting the first RC parameters into the target classification model to obtain a classification recognition result.
The classification model comprises a support vector machine (Support Vector Machines, SVM), logistic regression (Logistic Regression, LR), K nearest neighbor (K-Nearest Neighbors, KNN), decision tree, naive Bayes and the like. The target classification model is a trained classification model, and comprises a mapping relation between a first RC parameter and a classification recognition result.
The first RC parameters can be input into a trained target classification model, and the target classification model carries out classification recognition processing on the first RC parameters to generate classification recognition results, namely the filling effect of the adhesive.
In the embodiment of the disclosure, a first RC parameter of a battery pack is acquired, and the first RC parameter is input into a target classification model to obtain a classification recognition result. According to the embodiment of the disclosure, the filling effect of the adhesive is identified through the trained classification model, and the accuracy and the efficiency of identification are improved.
Fig. 6 is a schematic flow chart of a battery glue detection method according to an embodiment of the present disclosure, and further explaining a training process of a classification model with reference to fig. 6 based on the above embodiment, including the following steps:
s601, acquiring sample RC parameters of the sample battery pack and classification labels of adhesives in the sample battery pack.
The sample RC parameter is the RC parameter of a sample battery pack including a standard battery pack without fill defects and a plurality of battery packs with different fill defects.
The class labels are the filling effect of the adhesive in the sample battery, e.g., no defects, defect a, defect b, defect c, etc.
In some implementations, the filling effect of the adhesive in the sample battery pack can be detected using a detection tool such as a gauge, X-ray, or the like to obtain a classification label for the adhesive in the sample battery pack.
In the embodiment of the disclosure, the RC parameter of the prefabricated sample battery pack can be obtained as a sample RC parameter, and the filling effect of the adhesive in the sample battery is detected and used as a classification label.
In some implementations, sample battery packs with different filling effects can be manufactured by adjusting the manufacturing process of the battery pack so as to simulate filling defects possibly occurring in the actual production process of the battery pack to achieve a better identification effect, or, the actually produced battery pack is selected as the sample battery pack, which is not limited in any way.
As a possible scenario, the sample RC parameter and the classification label of the adhesive in the sample battery pack corresponding to the sample RC parameter may be collected from a sample database, where the sample database may be pre-established.
S602, inputting the sample RC parameters into the initial classification model to obtain a prediction classification result.
The initial classification model is a classification model to be trained.
S603, adjusting model parameters of the initial classification model based on the prediction classification result and the classification label to obtain a target classification model.
Inputting the sample RC parameters into an initial classification model, classifying and identifying the sample RC parameters by the initial classification model, generating a prediction classification result, generating a loss value based on the prediction classification result and a classification label, adjusting the model parameters of the initial model based on the loss value, and performing next training in the mode after adjustment until the model training ending condition is met, for example, the model converges, or the model achieves the expected effect, or the training times reach the preset training times, and the like, ending the training of the initial classification model, and obtaining the trained target classification model.
In the embodiment of the disclosure, a sample RC parameter of a sample battery pack and a classification label of an adhesive in the sample battery pack are obtained, the sample RC parameter is input into an initial classification model to obtain a prediction classification result, and model parameters of the initial classification model are adjusted based on the prediction classification result and the classification label to obtain a target classification model. According to the embodiment of the disclosure, the classification model is trained through the sample RC parameters and the classification labels, so that the trained classification model has a mapping relation between the RC parameters and the filling effect of the battery pack, the classification recognition can be carried out on the filling effect of the adhesive in the battery pack according to the RC parameters through the trained classification model, and the accuracy of the classification recognition is improved.
Fig. 7 is a flowchart of a battery glue detection method according to an embodiment of the present disclosure, and further illustrates a process of obtaining a sample RC parameter with reference to fig. 7 based on the above embodiment, including the following steps:
s701, acquiring a second detection current of the sample battery pack in a third detection loop.
The third detection loop is formed by connecting a sample battery pack and a detection device in series.
The detection device provides detection voltage for the sample battery pack in the third detection loop and measures third detection currents of the sample battery pack in the third detection loop at different detection moments under the detection voltage. The second detection current curve can be generated based on the second detection current of the battery pack in the third detection loop at different detection moments under the detection voltage, and the second detection current curve represents the relation between the second detection current and the detection moments under the detection voltage provided by the detection device.
It should be noted that, the detection voltages provided by the detection device in the first detection loop and the third detection loop are consistent, so as to ensure the applicability of the RC parameter of the sample.
In an actual application scene, a small number of sample battery packs can be selected to obtain sample RC parameters, so that the cost is saved.
S702, carrying out parameter identification based on the second detection current and the target RC equivalent circuit model, and generating sample RC parameters of the battery pack.
The description of step S702 may be referred to the description of the above embodiments, and will not be repeated here.
In the embodiment of the disclosure, a second detection current of the sample battery pack in a third detection loop is obtained, parameter identification is performed based on the second detection current and a target RC equivalent circuit model, and sample RC parameters of the battery pack are generated. According to the embodiment of the disclosure, the sample RC parameters are obtained, high-quality training data are provided for training of the classification model, and the training effect of the classification model is improved.
In order to enable those skilled in the art to more clearly understand the battery glue spreading method according to the embodiments of the present disclosure, fig. 8 is a schematic flow chart of the battery glue spreading detection method in practical application, as shown in fig. 8, and the model training phase is as follows: manufacturing a sample battery pack through an adjustment process, standing until the adhesive is completely solidified, detecting the filling effect of the adhesive in the sample battery pack by using detection tools such as measuring tools and X rays to generate a classification label of the sample battery pack, then externally applying step voltage excitation to the sample battery pack, testing and recording a current curve (namely a second detection current curve) in a loop, carrying out parameter identification based on the current curve and a target RC equivalent circuit model to generate sample RC parameters, training an initial model based on the sample RC parameters and the classification label of the sample battery pack corresponding to the sample RC parameters, and obtaining the target classification model. And (3) detection: after the battery pack in actual production is stood until the adhesive is completely solidified, step voltage excitation is applied to the battery pack, a current curve in a loop is tested and recorded, a first RC parameter of the battery pack is generated based on the current curve (namely a first detection current curve) and a target RC equivalent circuit model, the first RC parameter is input into a target classification model obtained in a model training stage, classification and identification are carried out, and the filling effect of the adhesive in the battery pack is identified.
Fig. 9 is a schematic structural diagram of a battery glue detection device according to an embodiment of the present disclosure, and as shown in fig. 9, a battery glue detection device 900 includes:
a first obtaining module 910, configured to obtain a first RC parameter of the battery pack;
the classification and identification module 920 is configured to perform classification and identification on the adhesive in the battery pack based on the first RC parameter, and generate a classification and identification result of the adhesive, where the classification and identification result is used to indicate a filling effect of the adhesive.
In the embodiment of the disclosure, a first RC parameter of a battery pack is obtained, and based on the first RC parameter, the adhesive in the battery pack is classified and identified, so that a classification and identification result of the adhesive is generated. In the embodiment of the disclosure, the filling effect of the adhesive in the battery pack is identified according to the RC parameter of the battery pack, so that the filling effect of the pressed adhesive can be detected, the detection efficiency is improved, and the detection cost is saved.
In one embodiment of the disclosure, the first obtaining module 910 is further configured to obtain a first detection current of the battery pack in a first detection loop, where the first detection loop is formed by connecting the battery pack and a detection device in series, and the detection device is configured to detect the current in the loop; and determining a target RC equivalent circuit model, and carrying out parameter identification based on the first detection current and the target RC equivalent circuit model to generate a first RC parameter of the battery pack.
In one embodiment of the present disclosure, the classification recognition model 920 is also used to: and inputting the first RC parameters into a target classification model to obtain a classification recognition result, wherein the target classification model comprises a mapping relation between the first RC parameters and the classification recognition result.
In one embodiment of the present disclosure, the battery glue detection device 900 further includes:
a second obtaining module 930, configured to obtain a sample RC parameter of the sample battery pack and a classification label of the adhesive in the sample battery pack;
the prediction module 940 is configured to input the sample RC parameter into the initial classification model, to obtain a predicted classification result;
the adjustment module 950 is configured to adjust model parameters of the initial classification model based on the prediction classification result and the classification label, so as to obtain a target classification model.
In one embodiment of the present disclosure, the first obtaining module 910 is further configured to determine, as the target RC equivalent circuit model, an RC equivalent circuit model corresponding to a second detection loop where the standard battery pack without the filling defect is located, where the second detection loop is formed by connecting the standard battery pack and the detection device in series.
In one embodiment of the present disclosure, the first obtaining module 910 is further configured to generate an identification equation based on the target RC equivalent circuit model; a first RC parameter of the battery pack is calculated based on the first sensed current and the identification equation.
In one embodiment of the present disclosure, the battery glue detection device 900 further includes:
and a screening module 960, configured to perform classification and identification on the adhesive in the battery pack, and screen the battery pack with the adhesive filling defect based on the classification and identification result after the classification and identification result of the adhesive is generated.
It should be noted that, for details not disclosed in the battery glue detecting device in the embodiment of the disclosure, please refer to details disclosed in the battery glue detecting method in the embodiment of the disclosure, and details are not described here again.
In order to implement the above-mentioned embodiments, as shown in fig. 10, the disclosure further proposes an electronic device 1000, including a memory 1010, a processor 1020, and a computer program stored on the memory 1010 and executable on the processor 1020, where the processor 1020 executes the program to implement the battery glue detection method according to the above-mentioned embodiments of the disclosure.
To achieve the above-described embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the battery glue detection method proposed by the foregoing embodiments of the present disclosure.
In the description of this specification, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.
Claims (10)
1. A battery glue detection method, the method comprising:
acquiring a first RC parameter of a battery pack;
and based on the first RC parameters, classifying and identifying the adhesive in the battery pack to generate a classifying and identifying result of the adhesive, wherein the classifying and identifying result is used for indicating the filling effect of the adhesive.
2. The method of claim 1, wherein the obtaining a first RC parameter of the battery pack comprises:
acquiring a first detection current of the battery pack in a first detection loop, wherein the first detection loop is formed by connecting the battery pack and a detection device in series, and the detection device is used for detecting the current in the loop;
and determining a target RC equivalent circuit model, and carrying out parameter identification based on the first detection current and the target RC equivalent circuit model to generate a first RC parameter of the battery pack.
3. The method of claim 1, wherein the classifying and identifying the adhesive in the battery pack based on the first RC parameter to generate a classification and identification result of the adhesive comprises:
and inputting the first RC parameters into a target classification model to obtain the classification recognition result, wherein the target classification model comprises a mapping relation between the first RC parameters and the classification recognition result.
4. A method according to claim 3, characterized in that the method further comprises:
acquiring a sample RC parameter of a sample battery pack and a classification label of an adhesive in the sample battery pack;
inputting the sample RC parameters into an initial classification model to obtain a prediction classification result;
and adjusting model parameters of the initial classification model based on the prediction classification result and the classification label to obtain the target classification model.
5. The method of claim 2, wherein the determining the target RC equivalent circuit model comprises:
and determining an RC equivalent circuit model corresponding to a second detection loop of the standard battery pack without filling defects as the target RC equivalent circuit model, wherein the second detection loop is formed by connecting the standard battery pack and the detection device in series.
6. The method of claim 2, wherein the generating the first RC parameter of the battery pack based on the first detected current and the target RC equivalent circuit model for parameter identification comprises:
generating an identification equation based on the target RC equivalent circuit model;
a first RC parameter of the battery pack is calculated based on the first detected current and the identification equation.
7. The method of claim 1, wherein the classifying and identifying the adhesive in the battery pack, after generating the classifying and identifying result of the adhesive, comprises:
and screening out the battery pack with the adhesive filling defect based on the classification and identification result.
8. A battery glue detection device, the device comprising:
the first acquisition module is used for acquiring a first RC parameter of the battery pack;
and the classification and identification module is used for carrying out classification and identification on the adhesive in the battery pack based on the first RC parameter to generate a classification and identification result of the adhesive, wherein the classification and identification result is used for indicating the filling effect of the adhesive.
9. An electronic device, comprising a memory and a processor;
wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for implementing the battery glue detection method according to any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements a battery glue detection method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210688456.6A CN117289026A (en) | 2022-06-17 | 2022-06-17 | Battery gluing detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210688456.6A CN117289026A (en) | 2022-06-17 | 2022-06-17 | Battery gluing detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117289026A true CN117289026A (en) | 2023-12-26 |
Family
ID=89246825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210688456.6A Pending CN117289026A (en) | 2022-06-17 | 2022-06-17 | Battery gluing detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117289026A (en) |
-
2022
- 2022-06-17 CN CN202210688456.6A patent/CN117289026A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210072321A1 (en) | System and method for sensing battery capacity | |
| Xie et al. | Experimental and analytical study on heat generation characteristics of a lithium-ion power battery | |
| KR102106775B1 (en) | Diagnosis method of battery using Deep Learning | |
| CN108169679B (en) | Battery specific heat capacity detection method and system | |
| JP7020273B2 (en) | Battery information processing system, assembled battery, battery module capacity calculation method, and assembled battery manufacturing method | |
| CN111352034B (en) | Battery capacity estimating method and battery capacity estimating device | |
| CN111707957B (en) | Method and device for estimating residual value of battery of electric vehicle | |
| CN104184182A (en) | Battery management system and method of driving the same | |
| WO2021189146A1 (en) | Apparatus and methods for testing electrochemical systems | |
| CN107037375B (en) | Method and device for measuring direct current internal resistance of battery | |
| CN109541479A (en) | A kind of predictor method and device of battery remaining power | |
| KR20190092767A (en) | Method and apparatus for evaluating safety of secondary battery | |
| CN113590482B (en) | Test method and test system for battery management system BMS | |
| CN113933734B (en) | Method for extracting parameters of single body in retired battery pack | |
| KR20160108963A (en) | Apparatus and method for diagnosing status of battery using high frequency and impedance, and computer-readable recording medium with program therefor | |
| CN114729967A (en) | Method for estimating the state of an energy store | |
| Ranieri et al. | Electronic module for the thermal monitoring of a Li-ion battery cell through the electrochemical impedance estimation | |
| Balasingam et al. | Performance analysis results of a battery fuel gauge algorithm at multiple temperatures | |
| CN117289026A (en) | Battery gluing detection method and device, electronic equipment and storage medium | |
| KR102280292B1 (en) | Method of evaluating impedance spectroscopy for used battery module, recording medium and apparatus for performing the method | |
| CN115144037B (en) | Safety monitoring method and system for explosion-proof performance of lithium battery | |
| CN113587972B (en) | Sensor parameter correction processing method, device and system | |
| CN112285585B (en) | Method and device for calculating battery energy state by considering temperature and multiplying power | |
| CN113109722A (en) | Charging rate-fused multi-factor battery charging internal resistance modeling method | |
| CN113156314A (en) | Method for measuring and calculating service life attenuation of whole-vehicle-level power battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |