CN115169580A - Training method and device for voltage difference abnormity detection model of vehicle battery pack - Google Patents
Training method and device for voltage difference abnormity detection model of vehicle battery pack Download PDFInfo
- Publication number
- CN115169580A CN115169580A CN202210777169.2A CN202210777169A CN115169580A CN 115169580 A CN115169580 A CN 115169580A CN 202210777169 A CN202210777169 A CN 202210777169A CN 115169580 A CN115169580 A CN 115169580A
- Authority
- CN
- China
- Prior art keywords
- data
- voltage difference
- battery pack
- module
- vehicle
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/10—Measuring sum, difference or ratio
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Secondary Cells (AREA)
Abstract
The embodiment of the invention relates to a training method and a device for a voltage difference abnormity detection model of a vehicle battery pack, wherein the training method comprises the following steps: obtaining sample historical operating data of a target vehicle; determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data; performing data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the first data matrix; the method can rapidly and accurately identify the voltage difference of the vehicle battery pack by training the voltage difference abnormity detection model of the vehicle battery pack, and complete early identification and positioning of the battery module with the fault.
Description
Technical Field
The embodiment of the invention relates to the field of voltage difference abnormity detection of a vehicle battery pack, in particular to a training method and a device of a voltage difference abnormity detection model of the vehicle battery pack.
Background
The new energy automobile power battery pack is generally formed by connecting a plurality of battery cells in series and parallel, and the inconsistency of the battery cells is increased due to the fact that the production process is inconsistent and the battery cells are used for a long time in different environments, so that the performance of the battery pack is influenced, faults are caused, and even safety accidents are caused.
The cell voltage difference in the battery pack is the most direct and easily calculated index for describing the inconsistency of the battery pack, and a threshold-based method is commonly used in the industry to identify the battery pack with abnormal cell voltage difference.
The existing battery cell pressure difference abnormity detection method usually sets different threshold values aiming at different vehicle types, depends on expert experience, needs to spend a great deal of effort to repeatedly adjust and verify, and is more complicated due to different seasons, geographical positions, driving strength or use habits; and the threshold-based method can only be detected when the cell voltage difference in the battery pack significantly deviates from the normal condition, and can not identify early faults and locate the failed battery module.
Disclosure of Invention
In view of the above, to solve the above technical problems or some technical problems, embodiments of the present invention provide a training method and apparatus for a voltage difference abnormality detection model of a vehicle battery pack.
In a first aspect, an embodiment of the present invention provides a training method for a voltage difference abnormality detection model of a vehicle battery pack, including:
obtaining sample historical operating data of a target vehicle;
determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data;
performing data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window;
extracting data characteristics of the first data matrix;
and training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
In one possible embodiment, the method further comprises:
extracting sample data of the battery pack in a charging state from the sample historical operating data;
determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data;
and taking the difference value of the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
In one possible embodiment, the method further comprises:
extracting a first data characteristic corresponding to the voltage difference of the first electric core of each battery sub-module;
and performing data processing on the first data characteristic based on a preset rule to obtain a second data characteristic after the data processing.
In one possible embodiment, the method further comprises:
extracting a first similarity of the voltage difference between each battery sub-module and the first battery core of other battery sub-modules in each time window, and calculating a third data characteristic of the first similarity;
and extracting a second similarity of the voltage difference of the first electric core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
In one possible embodiment, the method further comprises:
analyzing the time-varying trend of the voltage difference of the first electric core of each battery sub-module, and setting a first data label corresponding to each first data matrix;
and inputting the first data label corresponding to each first data matrix and the first data characteristic, the second data characteristic, the third data characteristic and the fourth data characteristic into a machine learning model for supervised learning training.
In one possible embodiment, the method further comprises:
and when the performance index of the machine learning model reaches a preset threshold value, determining that the machine learning model is trained, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
In a second aspect, an embodiment of the present invention provides a voltage difference abnormality detection method for a vehicle battery pack, including:
acquiring historical operating data of a vehicle to be detected;
determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data;
performing data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window;
extracting data characteristics of the second data matrix;
and inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack, and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
In a third aspect, an embodiment of the present invention provides a training apparatus for a voltage difference abnormality detection model of a vehicle battery pack, including:
the acquisition module is used for acquiring sample historical operating data of the target vehicle;
the determining module is used for determining a first battery cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data;
the processing module is used for carrying out data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix consisting of the first battery cell voltage differences corresponding to each moment in each time window;
the characteristic extraction module is used for extracting the data characteristics of the first data matrix;
and the training module is used for training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
In a fourth aspect, an embodiment of the present invention provides a voltage difference abnormality detection apparatus for a vehicle battery pack, including:
the acquisition module is used for acquiring historical operation data of the vehicle to be detected;
the determining module is used for determining a second battery cell voltage difference of each battery sub-module in the battery pack based on the historical operation data;
the processing module is used for carrying out data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window;
the characteristic extraction module is used for extracting the data characteristics of the second data matrix;
and the detection module is used for inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory, the processor being configured to execute a training program of a voltage difference abnormality detection model of a vehicle battery pack and a voltage difference abnormality detection program of the vehicle battery pack stored in the memory, so as to implement the training method of the voltage difference abnormality detection model of the vehicle battery pack described in the first aspect and the voltage difference abnormality detection method of the vehicle battery pack described in the second aspect.
In a sixth aspect, an embodiment of the present invention provides a storage medium, including: the storage medium stores one or more programs executable by one or more processors to implement the method for training a voltage difference abnormality detection model of a vehicle battery pack described in the first aspect and the method for detecting a voltage difference abnormality of a vehicle battery pack described in the second aspect described above.
According to the training scheme of the voltage difference abnormity detection model of the vehicle battery pack, provided by the embodiment of the invention, the historical operating data of a sample of a target vehicle is obtained; determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data; performing data segmentation processing on the first cell voltage difference based on a preset time window to obtain a first data matrix formed by the first cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the first data matrix; training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack, compared with the prior art that different thresholds are set for different vehicle types, the situation is more complicated due to the fact that a great deal of effort is needed to repeatedly adjust and verify depending on expert experience, and different seasons, geographic positions, driving strengths or use habits are caused; according to the scheme, the voltage difference of the vehicle battery pack can be rapidly and accurately identified by training a voltage difference abnormity detection model of the vehicle battery pack, so that the battery module with the fault can be identified and positioned in the early stage.
According to the scheme for detecting the voltage difference abnormity of the vehicle battery pack, provided by the embodiment of the invention, historical operation data of a vehicle to be detected is obtained; determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data; performing data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the second data matrix; the data characteristics are input into a voltage difference abnormity detection model of the vehicle battery pack, whether the voltage difference of the battery pack of the vehicle to be detected is abnormal or not is detected, and according to the scheme, the voltage difference of the vehicle battery pack can be quickly and accurately identified by inputting the data into the voltage difference abnormity detection model of the vehicle battery pack, so that early identification is completed, and the battery module with a fault is positioned.
Drawings
Fig. 1 is a schematic flowchart of a training method for a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another training method for a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a method for detecting an abnormal voltage difference of a vehicle battery pack according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a training apparatus of a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a voltage difference abnormality detection apparatus for a vehicle battery pack according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
For the convenience of understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.
Fig. 1 is a schematic flowchart of a training method for a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention, and as shown in fig. 1, the method specifically includes:
and S11, obtaining sample historical operating data of the target vehicle.
According to the embodiment of the invention, the voltage difference abnormity detection model of the vehicle battery pack is trained, and the model is trained through the sample data of different vehicle types, so that the model can automatically learn the pressure difference abnormity discrimination rule of each vehicle type, and early warning of the pressure difference abnormity problem of different vehicle types and different use scenes by one model is realized without manually setting a threshold value. For new-market vehicle types, the anomaly recognition model trained by other vehicle type data can also be applied to recognize anomalies of known types (i.e., types already included in the model training data), with broad spectrum.
A vehicle battery pack generally includes a plurality of battery sub-modules, each of which is formed by connecting a plurality of battery cells in series and parallel, and thus a voltage difference exists between the battery cells. The method comprises the steps of obtaining sample historical operating data of a target vehicle, cleaning the data according to a rule, and removing invalid values, wherein the rule can be that a standard data format is set, the obtained data in different formats are uniformly changed into the standard data format, and it needs to be stated that the extracted data needs to comprise pressure difference abnormal data fragments.
And S12, determining the first electric core voltage difference of each battery sub-module in the battery pack based on the sample historical operation data.
Based on the sample historical operation data, calculating a first cell voltage difference (difference between the maximum value and the minimum value of the cell voltage in the battery sub-modules) of each battery sub-module by taking each battery sub-module in the battery pack as a unit.
And S13, carrying out data segmentation processing on the first cell voltage difference based on a preset time window to obtain a first data matrix formed by the first cell voltage differences corresponding to each moment in each time window.
The data segmentation processing is performed on the first battery cell voltage difference based on a preset time window, wherein the time window may be a fixed time period, such as a week or a month, or one or more charging conditions, and may be set according to actual conditions, and a first data matrix of the first battery cell voltage difference corresponding to each moment in the time window is obtained after the data segmentation processing. The cell voltages corresponding to each time in each time window are shown in table 1:
TABLE 1
And S14, extracting the data characteristics of the first data matrix.
And S15, training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
The data characteristics of the first data matrix are extracted, further, a sample set consisting of the data characteristics corresponding to the first data matrix and corresponding labels (normal or abnormal) can be divided into a training set and a testing set according to a proportion, the training set is used as input data of the machine learning model, the machine learning model is tested by the testing set, performance indexes (such as accuracy, recall rate and the like) of the machine learning model in the training set and the testing set are counted, when the performance indexes reach preset threshold values (such as the accuracy and the recall rate on the testing set are both more than 95%), the model training is considered to be finished, and the trained model is used as a voltage difference abnormity detection model of the vehicle battery pack.
It should be noted that, the specific extraction method and the model training method for the data features of the first data matrix are described in the embodiment of fig. 2, and will not be described in detail here.
According to the training method of the voltage difference abnormity detection model of the vehicle battery pack, provided by the embodiment of the invention, the historical operating data of a sample of a target vehicle is obtained; determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data; performing data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the first data matrix; training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack, compared with the prior art that different thresholds are set for different vehicle types, the situation is more complicated due to the fact that a great deal of effort is needed to repeatedly adjust and verify depending on expert experience, and different seasons, geographic positions, driving strengths or use habits are caused; the method based on the threshold value can be used for rapidly and accurately identifying the voltage difference of the vehicle battery pack by training a voltage difference abnormity detection model of the vehicle battery pack so as to complete early identification and positioning of the battery module with the fault.
Fig. 2 is a schematic flow chart of another training method for a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention, as shown in fig. 2, the method specifically includes:
and S21, extracting sample data of the battery pack in the charging state from the sample historical operation data.
According to the embodiment of the invention, the voltage difference abnormity detection model of the vehicle battery pack is trained, and the model is trained through the sample data of different vehicle types, so that the model can automatically learn the pressure difference abnormity discrimination rule of each vehicle type, and early warning of the pressure difference abnormity problem of different vehicle types and different use scenes by one model is realized.
Firstly, obtaining sample historical operating data of a target vehicle, cleaning the data according to a rule to remove invalid values, wherein the rule can be that a standard data format is set, the obtained data in different formats is changed into the standard data format in a unified mode, and it needs to be stated that the extracted data needs to include a pressure difference abnormal data fragment.
Further, sample data of the battery pack in the charging state is extracted from the sample historical operation data, including but not limited to: total battery pack voltage, battery pack current, voltage per cell, etc.
And S22, determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data.
And S23, taking the difference value between the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
And determining the maximum value and the minimum value of the cell voltage in each battery sub-module group based on the acquired sample data of the battery pack in the charging state, and taking the difference value of the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module group.
And S24, carrying out data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window.
The data segmentation processing is performed on the first battery cell voltage difference based on a preset time window, wherein the time window may be a fixed time period, such as a week or a month, or one or more charging conditions, and may be set according to actual conditions, and a first data matrix of the first battery cell voltage difference corresponding to each moment in the time window is obtained after the data segmentation processing.
And S25, extracting a first data characteristic corresponding to the voltage difference of the first electric core of each battery sub-module.
Carry out first data feature extraction to the first electric core voltage difference of every battery submodule group, it is specific, extract the statistics characteristic of the first electric core voltage difference that each battery submodule group corresponds in the time window, regard this statistics characteristic as first data feature, include but not limited to: maximum, minimum, mean, median, standard deviation, skewness, kurtosis, and the like.
And S26, based on a preset rule, performing data processing on the first data characteristic to obtain a second data characteristic after data processing.
For each battery sub-module, respectively calculating first-order and high-order differences of first data characteristics of the first battery cell voltage difference of each battery sub-module in the current time window and the first battery cell voltage differences of the previous time windows, such as the difference with the median of the battery cell voltage differences in the previous time window, and performing the difference again, namely the first-order difference and the second-order difference, to obtain second data characteristics after data processing.
S27, extracting a first similarity of the voltage difference between each battery sub-module in each time window and the first battery core of other battery sub-modules, and calculating a third data characteristic of the first similarity.
Calculating a first similarity between the voltage difference of the first battery core of the local sub-module and the voltage difference of the first battery core of each other sub-module in the same time window of each battery sub-module, extracting statistical characteristics of the first similarity, and obtaining third data characteristics of the first similarity, wherein the statistical characteristics include but are not limited to a maximum value, a minimum value, an average value, a median value, a standard deviation and the like. Wherein, the similarity can be a dynamic-time-wrapping (DTW) distance, pearson correlation, a spearman similarity, etc. The similarity is used for confirming whether the change of the electric core voltage difference of every battery submodule group is close in the same time window, for example, simultaneously grow, diminish simultaneously, and the similarity that calculates out of step change can be lower.
It should be noted that, each row in the first data matrix is the voltage difference of the electric core of one battery sub-module, and the conditions of other battery sub-modules except a certain battery sub-module, that is, assuming 6 battery sub-modules in total, for the No. 1 battery sub-module, the statistical characteristics of the No. 2-6 battery sub-modules (corresponding to the matrixes formed by the rows 2-6 of the matrix) are counted as the characteristics of the No. 1 battery sub-module; for the No. 2 battery sub-module, the statistical characteristics of the No. 1 and No. 3-6 battery sub-modules (corresponding to the matrixes formed by the columns 1 and 3-6) are counted as the characteristics of the No. 2 battery sub-module, and so on.
S28, extracting second similarity of the voltage difference of the first electric core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
And respectively calculating second similarity of the voltage difference of the first electric core in any time window in the same battery sub-module and the voltage difference of the first electric core in the previous time windows, and taking the calculated second similarity as a fourth data characteristic.
S29, analyzing the change trend of the voltage difference of the first battery core of each battery sub-module along with time, and setting a first data label corresponding to each first data matrix.
The trend of the voltage difference of the first battery core along with time is balanced under a normal condition, a sudden change place can be considered as abnormal, and at this time, a first data tag corresponding to each first data matrix can be set, for example, normal or abnormal.
S210, inputting the first data labels corresponding to the first data matrixes, the first data characteristics, the second data characteristics, the third data characteristics and the fourth data characteristics into a machine learning model, and performing supervised learning training.
After extracting data features from each first data matrix and marking the completed data labels, a sample set consisting of the data features corresponding to the first data matrix and the corresponding labels (normal or abnormal) can be proportionally divided into a training set and a test set, the training set is used as input data of a machine learning model, and the machine learning model is tested by the test set. Specifically, the first data label corresponding to the first data matrix and the obtained first data feature, second data feature, third data feature and fourth data feature are input into a machine learning model, and supervised machine learning classification (normal or abnormal) model training is performed, where the classification model may be a model such as logistic regression and lightGBM.
S211, when the performance index of the machine learning model reaches a preset threshold value, the machine learning model is determined to be trained, and the trained machine learning model is used as a voltage difference abnormity detection model of the vehicle battery pack.
And counting the performance indexes (such as accuracy, recall rate and the like) of the machine learning model in the training set and the testing set, and when the performance indexes reach a preset threshold (for example, the accuracy and the recall rate in the testing set are both more than 95%), considering that the model training is finished, and taking the trained model as a voltage difference abnormity detection model of the vehicle battery pack.
The embodiment of the invention provides a training method of a voltage difference abnormity detection model of a vehicle battery pack, which comprises the steps of obtaining historical operation data of a vehicle to be detected; determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data; performing data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the second data matrix; the data characteristics are input into a voltage difference abnormity detection model of the vehicle battery pack, whether the voltage difference of the battery pack of the vehicle to be detected is abnormal or not is detected, and according to the method, the voltage difference of the vehicle battery pack can be rapidly and accurately identified by training the voltage difference abnormity detection model of the vehicle battery pack, so that early identification and positioning of the battery module with the fault are completed.
Fig. 3 is a schematic flow chart of a method for detecting an abnormal voltage difference of a vehicle battery pack according to an embodiment of the present invention, as shown in fig. 3, the method specifically includes:
and S31, acquiring historical operation data of the vehicle to be detected.
In the embodiment of the invention, the voltage difference of the vehicle battery pack can be detected abnormally through the voltage difference abnormity detection model of the vehicle battery pack.
Firstly, historical operating data of a vehicle to be detected is obtained, data cleaning is carried out according to a rule, invalid values are removed, the rule can be a standard data format, and the obtained data are changed into the standard data format.
Further, the data of the battery pack in the charging state is extracted from the historical operation data, including but not limited to: total battery pack voltage, battery pack current, voltage per cell, etc.
And S32, determining the second electric core voltage difference of each battery sub-module in the battery pack based on the historical operation data.
And determining the difference value between the maximum value and the minimum value of the cell voltage in each battery sub-module based on the acquired data of the battery pack in the charging state, and taking the difference value as the second cell voltage difference of each battery sub-module.
And S33, performing data segmentation processing on the second cell voltage difference based on preset time windows to obtain a second data matrix formed by the second cell voltage differences corresponding to each moment in each time window.
And performing data segmentation processing on the second electric core voltage difference based on a preset time window, wherein the time window can be a fixed time period, such as a week or a month, or one or more charging conditions, and can be set according to actual conditions, and a second data matrix of the second electric core voltage difference corresponding to each moment in the time window is obtained after the data segmentation processing.
And S34, extracting the data characteristics of the second data matrix.
And S35, inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack, and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
And extracting data characteristics of the second data matrix, inputting the extracted data characteristics into a trained voltage difference abnormity detection model of the vehicle battery pack, detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal, and outputting a result according to the model to perform corresponding early warning prompt, for example, when the voltage difference of the battery pack of the vehicle to be detected is detected, performing early warning.
According to the voltage difference abnormity detection method of the vehicle battery pack, provided by the embodiment of the invention, historical operation data of a vehicle to be detected is obtained; determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data; performing data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the second data matrix; the data characteristics are input into a voltage difference abnormity detection model of the vehicle battery pack, whether the voltage difference of the battery pack of the vehicle to be detected is abnormal or not is detected, and according to the method, the voltage difference of the vehicle battery pack can be rapidly and accurately identified by inputting the data into the voltage difference abnormity detection model of the vehicle battery pack, so that early identification and positioning of the battery module with the fault are completed.
Fig. 4 is a schematic structural diagram of a training device of a voltage difference abnormality detection model of a vehicle battery pack according to an embodiment of the present invention, as shown in fig. 4, specifically including:
an obtaining module 401, configured to obtain sample historical operating data of a target vehicle;
a determining module 402, configured to determine a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data;
the processing module 403 is configured to perform data segmentation processing on the first cell voltage difference based on a preset time window, so as to obtain a first data matrix formed by the first cell voltage differences corresponding to each time in each time window;
a feature extraction module 404, configured to extract data features of the first data matrix;
and a training module 405, configured to train a machine learning model based on the data features of the first data matrix, and use the trained machine learning model as a voltage difference abnormality detection model of the vehicle battery pack.
In a possible embodiment, the determining module 402 is specifically configured to extract sample data of the battery pack in the charging state from the sample historical operating data; determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data; and taking the difference value of the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
In a possible embodiment, the feature processing module 404 is specifically configured to extract a first data feature corresponding to the first cell voltage difference of each battery sub-module; and based on a preset rule, performing data processing on the first data characteristic to obtain a second data characteristic after data processing.
In a possible implementation manner, the feature processing module 404 is further configured to extract a first similarity between the first cell voltage difference of each battery sub-module and the first cell voltage difference of other battery sub-modules in each time window, and calculate a third data feature of the first similarity; and extracting a second similarity of the voltage difference of the first battery core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
In a possible embodiment, the training module 405 is specifically configured to analyze a trend of a first cell voltage difference of each battery sub-module over time, and set a first data tag corresponding to each first data matrix; and inputting the first data label corresponding to each first data matrix and the first data characteristic, the second data characteristic, the third data characteristic and the fourth data characteristic into a machine learning model for supervised learning training.
In a possible embodiment, the training module 405 is further configured to determine that the training of the machine learning model is completed when the performance index of the machine learning model reaches a preset threshold, and use the trained machine learning model as a voltage difference abnormality detection model of a vehicle battery pack.
The training device for the voltage difference abnormality detection model of the vehicle battery pack provided in this embodiment may be the training device for the voltage difference abnormality detection model of the vehicle battery pack shown in fig. 4, and may perform all steps of the training method for the voltage difference abnormality detection model of the vehicle battery pack shown in fig. 1-2, so as to achieve the technical effect of the training method for the voltage difference abnormality detection model of the vehicle battery pack shown in fig. 1-2, specifically refer to the related description of fig. 1-2, which is for brevity and will not be described herein again.
Fig. 5 is a schematic structural diagram of a voltage difference abnormality detection apparatus for a vehicle battery pack according to an embodiment of the present invention, as shown in fig. 5, specifically including:
the acquiring module 501 is used for acquiring historical operating data of a vehicle to be detected;
a determining module 502, configured to determine, according to the historical operation data, a second cell voltage difference of each battery sub-module in the battery pack;
the processing module 503 is configured to perform data segmentation processing on the second cell voltage difference based on preset time windows to obtain a second data matrix formed by second cell voltage differences corresponding to each time in each time window;
a feature extraction module 504, configured to extract data features of the second data matrix;
and the detecting module 505 is configured to input the data characteristics into a voltage difference abnormality detection model of the vehicle battery pack, and detect whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
The voltage difference abnormality detection device of the vehicle battery pack provided in this embodiment may be the voltage difference abnormality detection device of the vehicle battery pack shown in fig. 5, and may perform all steps of the voltage difference abnormality detection method of the vehicle battery pack shown in fig. 3, so as to achieve the technical effect of the voltage difference abnormality detection method of the vehicle battery pack shown in fig. 3, which is described with reference to fig. 3 for brevity, and is not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 604, and other user interfaces 603. The various components in the electronic device 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable communications among the components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 605 in fig. 6.
The user interface 603 may include, among other things, a display, a keyboard or a pointing device (e.g., a mouse, trackball (trackball), a touch pad or touch screen, etc.
It will be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), double Data Rate Synchronous Dynamic random access memory (ddr Data Rate SDRAM, ddr SDRAM), enhanced Synchronous SDRAM (ESDRAM), synchlronous SDRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 6021 and application programs 6022.
The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application program 6022 includes various application programs such as a Media Player (Media Player), a Browser (Browser), and the like, and is used to implement various application services. A program implementing the method of an embodiment of the invention can be included in the application program 6022.
In the embodiment of the present invention, by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application program 6022, the processor 601 is configured to execute the method steps provided by the method embodiments, for example, including:
obtaining sample historical operating data of a target vehicle; determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data; performing data segmentation processing on the first cell voltage difference based on a preset time window to obtain a first data matrix formed by the first cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the first data matrix; and training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
In one possible implementation mode, sample data of the battery pack in the charging state is extracted from the sample historical operation data; determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data; and taking the difference value of the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
In one possible implementation, extracting a first data feature corresponding to the first cell voltage difference of each battery sub-module; and based on a preset rule, performing data processing on the first data characteristic to obtain a second data characteristic after data processing.
In one possible implementation, extracting a first similarity of a voltage difference between a first battery cell of each battery sub-module and a first battery cell of other battery sub-modules in each time window, and calculating a third data characteristic of the first similarity; and extracting a second similarity of the voltage difference of the first electric core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
In one possible implementation manner, the variation trend of the voltage difference of the first battery cell of each battery sub-module along with time is analyzed, and a first data tag corresponding to each first data matrix is set; and inputting the first data label corresponding to each first data matrix and the first data characteristic, the second data characteristic, the third data characteristic and the fourth data characteristic into a machine learning model for supervised learning training.
In a possible implementation manner, when the performance index of the machine learning model reaches a preset threshold, it is determined that the machine learning model is trained, and the trained machine learning model is used as a voltage difference abnormality detection model of the vehicle battery pack.
Or the like, or a combination thereof,
acquiring historical operation data of a vehicle to be detected; determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data; performing data segmentation processing on the second cell voltage difference based on preset time windows to obtain a second data matrix formed by the second cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the second data matrix; and inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack, and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
The method disclosed by the above-mentioned embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by integrated logic circuits of hardware or instructions in the form of software in the processor 601. The Processor 601 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602, and in combination with the hardware thereof, performs the steps of the method.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The electronic device provided in this embodiment may be the electronic device shown in fig. 6, and may perform all steps of the training method of the voltage difference abnormality detection model of the vehicle battery pack in fig. 1-2 and the voltage difference abnormality detection method of the vehicle battery pack in fig. 3, so as to achieve technical effects of the training method of the voltage difference abnormality detection model of the vehicle battery pack shown in fig. 1-2 and the voltage difference abnormality detection method of the vehicle battery pack in fig. 3, specifically please refer to the relevant descriptions of fig. 1-2 and fig. 3, which are not described herein for brevity.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, storage media may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of the above kinds of memories.
When the one or more programs in the storage medium are executable by the one or more processors, the method for training the voltage difference abnormality detection model of the vehicle battery pack and the method for detecting the voltage difference abnormality of the vehicle battery pack, which are executed on the electronic device side, are implemented.
The processor is configured to execute a training program of a voltage difference abnormality detection model of the vehicle battery pack and a voltage difference abnormality detection program of the vehicle battery pack stored in the memory to implement the following steps of a training method of a voltage difference abnormality detection model of the vehicle battery pack and a voltage difference abnormality detection method of the vehicle battery pack, executed on the electronic device side:
obtaining sample historical operating data of a target vehicle; determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data; performing data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the first data matrix; and training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
In one possible implementation mode, sample data of the battery pack in the charging state is extracted from the sample historical operation data; determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data; and taking the difference value between the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
In one possible implementation, extracting a first data feature corresponding to the first cell voltage difference of each battery sub-module; and based on a preset rule, performing data processing on the first data characteristic to obtain a second data characteristic after data processing.
In one possible implementation manner, extracting a first similarity of the voltage difference between the first battery cell of each battery sub-module and the first battery cell of other battery sub-modules in each time window, and calculating a third data characteristic of the first similarity; and extracting a second similarity of the voltage difference of the first electric core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
In one possible implementation manner, the variation trend of the first cell voltage difference of each battery sub-module along with time is analyzed, and a first data tag corresponding to each first data matrix is set; and inputting the first data label corresponding to each first data matrix and the first data characteristic, the second data characteristic, the third data characteristic and the fourth data characteristic into a machine learning model for supervised learning training.
In one possible implementation manner, when the performance index of the machine learning model reaches a preset threshold, it is determined that the machine learning model is trained, and the trained machine learning model is used as a voltage difference abnormality detection model of the vehicle battery pack.
Or the like, or, alternatively,
acquiring historical operation data of a vehicle to be detected; determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data; performing data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window; extracting data characteristics of the second data matrix; and inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack, and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A training method of a voltage difference abnormality detection model of a vehicle battery pack, characterized by comprising:
obtaining sample historical operating data of a target vehicle;
determining a first cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data;
performing data segmentation processing on the first cell voltage difference based on a preset time window to obtain a first data matrix formed by the first cell voltage differences corresponding to each moment in each time window;
extracting data characteristics of the first data matrix;
and training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
2. The method of claim 1, wherein determining the first cell voltage difference for each battery sub-module in the battery pack based on the sample historical operating data comprises:
extracting sample data of the battery pack in a charging state from the sample historical operating data;
determining the maximum value and the minimum value of the cell voltage in each battery sub-module based on the sample data;
and taking the difference value between the maximum value and the minimum value of the cell voltage as the first cell voltage difference of each battery sub-module.
3. The method of claim 2, wherein said extracting data features of said first data matrix comprises:
extracting a first data characteristic corresponding to the voltage difference of the first electric core of each battery sub-module;
and based on a preset rule, performing data processing on the first data characteristic to obtain a second data characteristic after data processing.
4. The method of claim 2, wherein the extracting the data feature of the first data matrix comprises:
extracting a first similarity of the voltage difference between the first battery core of each battery sub-module and the first battery core of other battery sub-modules in each time window, and calculating a third data characteristic of the first similarity;
and extracting a second similarity of the voltage difference of the first electric core in different time windows corresponding to each battery sub-module, and taking the second similarity as a fourth data characteristic.
5. The method of claim 3 or 4, wherein training a machine learning model based on the data features of the first data matrix comprises:
analyzing the time-varying trend of the voltage difference of the first electric core of each battery sub-module, and setting a first data label corresponding to each first data matrix;
and inputting the first data label corresponding to each first data matrix and the first data characteristic, the second data characteristic, the third data characteristic and the fourth data characteristic into a machine learning model for supervised learning training.
6. The method of claim 5, further comprising:
and when the performance index of the machine learning model reaches a preset threshold value, determining that the machine learning model is trained, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
7. A method for detecting an abnormality in voltage difference of a vehicle battery pack, comprising:
acquiring historical operation data of a vehicle to be detected;
determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data;
performing data segmentation processing on the second cell voltage difference based on preset time windows to obtain a second data matrix formed by the second cell voltage differences corresponding to each moment in each time window;
extracting data characteristics of the second data matrix;
inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack established by the method of any one of claims 1-6, and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
8. A training apparatus of a voltage difference abnormality detection model of a vehicle battery pack, characterized by comprising:
the acquisition module is used for acquiring sample historical operating data of the target vehicle;
the determining module is used for determining a first battery cell voltage difference of each battery sub-module in the battery pack based on the sample historical operation data;
the processing module is used for carrying out data segmentation processing on the first battery cell voltage difference based on a preset time window to obtain a first data matrix formed by the first battery cell voltage differences corresponding to each moment in each time window;
the characteristic extraction module is used for extracting the data characteristics of the first data matrix;
and the training module is used for training a machine learning model based on the data characteristics of the first data matrix, and taking the trained machine learning model as a voltage difference abnormity detection model of the vehicle battery pack.
9. A voltage difference abnormality detection device for a vehicle battery pack, characterized by comprising:
the acquisition module is used for acquiring historical operating data of the vehicle to be detected;
the determining module is used for determining a second cell voltage difference of each battery sub-module in the battery pack based on the historical operation data;
the processing module is used for carrying out data segmentation processing on the second battery cell voltage difference based on a preset time window to obtain a second data matrix formed by the second battery cell voltage differences corresponding to each moment in each time window;
the characteristic extraction module is used for extracting the data characteristics of the second data matrix;
and the detection module is used for inputting the data characteristics into a voltage difference abnormity detection model of the vehicle battery pack and detecting whether the voltage difference of the battery pack of the vehicle to be detected is abnormal.
10. An electronic device, comprising: a processor and a memory, the processor being configured to execute a training of a voltage difference abnormality detection model of a vehicle battery pack stored in the memory and a voltage difference abnormality detection program of the vehicle battery pack to implement the training method of the voltage difference abnormality detection model of the vehicle battery pack according to any one of claims 1 to 6 and the voltage difference abnormality detection method of the vehicle battery pack according to claim 7.
11. A storage medium characterized in that the storage medium stores one or more programs executable by one or more processors to implement the training method of the voltage difference abnormality detection model of the vehicle battery pack according to any one of claims 1 to 6 and the voltage difference abnormality detection method of the vehicle battery pack according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210777169.2A CN115169580A (en) | 2022-06-30 | 2022-06-30 | Training method and device for voltage difference abnormity detection model of vehicle battery pack |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210777169.2A CN115169580A (en) | 2022-06-30 | 2022-06-30 | Training method and device for voltage difference abnormity detection model of vehicle battery pack |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115169580A true CN115169580A (en) | 2022-10-11 |
Family
ID=83490990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210777169.2A Pending CN115169580A (en) | 2022-06-30 | 2022-06-30 | Training method and device for voltage difference abnormity detection model of vehicle battery pack |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169580A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115825755A (en) * | 2022-12-30 | 2023-03-21 | 哈尔滨光宇新能源有限公司 | Method for evaluating voltage consistency of battery core of energy storage battery |
| CN115877222A (en) * | 2023-02-14 | 2023-03-31 | 国网浙江省电力有限公司宁波供电公司 | Energy storage power station fault detection method and device, medium and energy storage power station |
| CN116381514A (en) * | 2023-06-07 | 2023-07-04 | 广汽埃安新能源汽车股份有限公司 | Cell differential pressure early warning method, device, storage medium and equipment |
| CN116400126A (en) * | 2023-06-08 | 2023-07-07 | 广东佰林电气设备厂有限公司 | Low-voltage power box with data processing system |
| CN116958130A (en) * | 2023-09-18 | 2023-10-27 | 深圳市赛特新能科技有限公司 | Vehicle detection system and method based on machine learning |
-
2022
- 2022-06-30 CN CN202210777169.2A patent/CN115169580A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115825755A (en) * | 2022-12-30 | 2023-03-21 | 哈尔滨光宇新能源有限公司 | Method for evaluating voltage consistency of battery core of energy storage battery |
| CN115825755B (en) * | 2022-12-30 | 2023-09-19 | 哈尔滨昆宇新能源有限公司 | Method for evaluating consistency of voltages of battery cells of energy storage battery |
| CN115877222A (en) * | 2023-02-14 | 2023-03-31 | 国网浙江省电力有限公司宁波供电公司 | Energy storage power station fault detection method and device, medium and energy storage power station |
| CN116381514A (en) * | 2023-06-07 | 2023-07-04 | 广汽埃安新能源汽车股份有限公司 | Cell differential pressure early warning method, device, storage medium and equipment |
| CN116381514B (en) * | 2023-06-07 | 2023-08-08 | 广汽埃安新能源汽车股份有限公司 | Cell differential pressure early warning method, device, storage medium and equipment |
| CN116400126A (en) * | 2023-06-08 | 2023-07-07 | 广东佰林电气设备厂有限公司 | Low-voltage power box with data processing system |
| CN116400126B (en) * | 2023-06-08 | 2023-08-01 | 广东佰林电气设备厂有限公司 | Low-voltage power box with data processing system |
| CN116958130A (en) * | 2023-09-18 | 2023-10-27 | 深圳市赛特新能科技有限公司 | Vehicle detection system and method based on machine learning |
| CN116958130B (en) * | 2023-09-18 | 2024-01-05 | 深圳市赛特新能科技有限公司 | Vehicle detection system and method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115169580A (en) | Training method and device for voltage difference abnormity detection model of vehicle battery pack | |
| CN107798047B (en) | Repeated work order detection method, device, server and medium | |
| CN111931868A (en) | Time series data abnormity detection method and device | |
| CN113688042A (en) | Method and device for determining test scene, electronic equipment and readable storage medium | |
| CN111177655B (en) | Data processing method and device and electronic equipment | |
| CN110275878B (en) | Service data detection method and device, computer equipment and storage medium | |
| CN112733884A (en) | Welding defect recognition model training method and device and computer terminal | |
| CN116148656B (en) | Portable analog breaker fault detection method | |
| CN111967535A (en) | Fault diagnosis method and device for temperature sensor in grain storage management scene | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN111427928A (en) | Data quality detection method and device | |
| CN114492764A (en) | Artificial intelligence model testing method and device, electronic equipment and storage medium | |
| WO2015035750A1 (en) | Method and apparatus for detecting magnetic signal of paper money | |
| CN110852860A (en) | Vehicle maintenance reimbursement behavior abnormity detection method, equipment and storage medium | |
| CN111143191A (en) | Website testing method and device, computer equipment and storage medium | |
| CN110990575A (en) | Test case failure reason analysis method and device and electronic equipment | |
| CN114548280A (en) | Fault diagnosis model training method, fault diagnosis method and electronic equipment | |
| CN112199295B (en) | Spectrum-based deep neural network defect positioning method and system | |
| CN113822336A (en) | Cloud hard disk fault prediction method, device and system and readable storage medium | |
| CN105653455A (en) | Program vulnerability detection method and detection system | |
| CN113033639A (en) | Training method of abnormal data detection model, electronic device and storage medium | |
| CN111309584B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN115494431A (en) | Transformer fault warning method, terminal equipment and computer readable storage medium | |
| CN115358348A (en) | Vehicle straight-through rate influence characteristic determination method, device, equipment and medium | |
| CN115345241A (en) | Battery abnormality detection method, battery abnormality detection device, electronic apparatus, and computer 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 |