CN112542621B - Battery temperature vector generation method and related equipment thereof - Google Patents
Battery temperature vector generation method and related equipment thereof Download PDFInfo
- Publication number
- CN112542621B CN112542621B CN202011337703.5A CN202011337703A CN112542621B CN 112542621 B CN112542621 B CN 112542621B CN 202011337703 A CN202011337703 A CN 202011337703A CN 112542621 B CN112542621 B CN 112542621B
- Authority
- CN
- China
- Prior art keywords
- battery
- data
- processed
- temperature
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Secondary Cells (AREA)
Abstract
The application discloses a battery temperature vector generation method and related equipment thereof, wherein the method comprises the following steps: firstly, acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period; and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period. The temperature vector is determined based on the temperature data and the state data of the battery to be processed in the first time period, so that the temperature vector can more accurately represent the actual temperature of the battery to be processed in the first time period, and the representation accuracy of the actual temperature of the battery is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a battery temperature vector generation method and related devices.
Background
The battery temperature may be indicative of whether a powered device (e.g., an electric vehicle, a hybrid vehicle, etc.) is operating properly. Currently, the temperature of the battery is generally collected by a temperature sensor (e.g., a probe) installed inside the battery.
However, since the temperature collected by the temperature sensor cannot accurately represent the actual temperature of the battery, how to accurately represent the actual temperature of the battery becomes an urgent technical problem to be solved.
Disclosure of Invention
In order to solve the technical problems in the prior art, the application provides a battery temperature vector generation method and related equipment thereof, which can accurately determine a battery temperature vector so that the battery temperature vector can more accurately and comprehensively represent the actual temperature of a battery.
In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:
the embodiment of the application provides a battery temperature vector generation method, which comprises the following steps:
acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
In a possible implementation manner, the generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period includes:
and inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model.
In one possible implementation, the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
when the temperature data in the first time period includes temperature data at N sampling time points, and the state data in the first time period includes state data at N sampling time points, the inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model, and obtaining the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model, including:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
In one possible embodiment, the data fusion layer includes at least one layer of graph convolutional neural network.
In a possible implementation, the data coding layer includes a long and short memory network; or, the data coding layer comprises a long and short memory network and an attention layer.
In one possible implementation, the training process of the battery temperature vector generation model includes:
acquiring at least one training data; the training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period;
inputting the at least one piece of training data into the battery temperature vector generation model to obtain a temperature vector of the at least one piece of training data output by the battery temperature vector generation model;
and updating the battery temperature vector generation model according to the at least one training data, the temperature vector of the at least one training data and a preset loss function, and continuing to execute the steps of inputting the at least one training data into the battery temperature vector generation model and the subsequent steps until a preset stop condition is reached.
In one possible embodiment, the temperature data includes at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery;
and/or the presence of a gas in the gas,
the state data includes at least one of a voltage, a current, an internal resistance, a battery capacity, a battery health, and a battery remaining capacity.
The embodiment of the present application further provides a battery temperature vector generating device, the device includes:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
and the generating unit is used for generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
An embodiment of the present application further provides an apparatus, where the apparatus includes a processor and a memory:
the memory is used for storing a computer program;
the processor is configured to execute any implementation of the battery temperature vector generation method provided by the embodiment of the application according to the computer program.
The embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, and the computer program is used to execute any implementation manner of the battery temperature vector generation method provided in the embodiment of the present application.
Compared with the prior art, the embodiment of the application has at least the following advantages:
in the battery temperature vector generation method provided by the embodiment of the application, after the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period are acquired, the temperature vector of the battery to be processed in the first time period can be generated according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period. The temperature vector is determined based on the temperature data and the state data of the battery to be processed in the first time period, so that the temperature vector can more accurately represent the actual temperature of the battery to be processed in the first time period, and the representation accuracy of the actual temperature of the battery is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for generating a battery temperature vector according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a battery temperature vector generation model according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a battery temperature vector generation apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus according to an embodiment of the present application.
Detailed Description
The inventor finds that, in the study of the battery temperature, the temperature collected by the temperature sensor installed inside the battery is not only influenced by the actual temperature of the battery, but also influenced by the factors such as the heat dissipation of the temperature sensor itself, the heat dissipation of the wires distributed inside the battery, the ambient temperature, the voltage, the current, the internal resistance, the equipment working condition (for example, the vehicle working condition) and the like, so that the temperature collected by the temperature sensor cannot accurately represent the actual temperature of the battery.
Based on the above findings, an embodiment of the present application provides a method for generating a battery temperature vector, including: firstly, acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period; and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
The temperature vector is determined based on the temperature data and the state data of the battery to be processed in the first time period, so that the temperature vector can more accurately represent the actual temperature of the battery to be processed in the first time period, and the representation accuracy of the actual temperature of the battery is improved.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Method embodiment
Referring to fig. 1, the figure is a flowchart of a battery temperature vector generation method according to an embodiment of the present application.
The battery temperature vector generation method provided by the embodiment of the application comprises the following steps of S1-S2:
s1: temperature data of the battery to be processed in a first time period and state data of the battery to be processed in the first time period are obtained.
The battery to be processed refers to a battery of which the battery temperature vector needs to be determined. In addition, the embodiment of the application is not limited to the battery to be processed. For example, the battery to be treated may be a vehicle battery.
The first time period is the time period during which the temperature indication is required. In addition, the first period is not limited in the embodiments of the present application.
The temperature data refers to data related to the temperature of the battery, and the embodiment of the present application does not limit the temperature data. For example, the temperature data may include at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery.
In addition, the embodiment of the present application also does not limit the temperature data in the first period of time. For example, the temperature data over the first time period may include temperature data at N sampling time points. Wherein, the j sampling time point is earlier than the j +1 sampling time point; j is a positive integer, j +1 is not more than N, and N is a positive integer. The sampling time point refers to a time point at which the temperature data and the state data are collected.
The state data is used for describing the operation state of the battery, and the embodiment of the present application does not limit the state data. For example, the state data may include at least one of voltage, current, internal resistance, battery capacity, battery health, and remaining battery capacity.
Based on the above-mentioned related content of S1, when the first time period includes N sampling time points, the temperature data and the state data of the battery to be processed at the 1 st sampling time point, the temperature data and the state data of the battery to be processed at the 2 nd sampling time point, … … (analogy), the temperature data and the state data of the battery to be processed at the nth sampling time point may be obtained, so that a temperature vector may be generated based on the temperature data and the state data of the battery to be processed at the N sampling time points, so that the temperature vector may accurately represent the actual temperature of the battery to be processed in the first time period.
S2: and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
Wherein the temperature vector is used to characterize the actual temperature of the battery to be treated, and the temperature vector is a time series. In addition, the embodiment of the present application does not limit the generation manner of the temperature vector, for example, in a possible implementation, S2 may specifically be: and inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model.
The battery temperature vector generation model is used for generating a battery temperature vector according to the battery temperature data and the battery state data.
In addition, the battery temperature vector generation model is not limited in the embodiments of the present application, and for example, the battery temperature vector generation model may be a neural network model.
In addition, the structure of the battery temperature vector generation model is not limited in the embodiments of the present application, for example, in one possible implementation, as shown in fig. 2, the battery temperature vector generation model may include a data fusion layer, a data aggregation layer, and a data encoding layer. The output data of the data fusion layer is input data of the data aggregation layer, and the output data of the data aggregation layer is input data of the data coding layer.
For the convenience of understanding the battery temperature vector generation model shown in fig. 2, the following description is made with reference to an example.
As an example, when the temperature data in the first period of time includes temperature data at N sampling time points and the state data in the first period of time includes state data at N sampling time points, the operation process of the battery temperature vector generation model shown in fig. 2 may include steps 11 to 13:
step 11: fusing temperature data of the battery to be processed at the ith sampling time point and state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer.
The data fusion layer is used for fusing the input data of the data fusion layer. In addition, the data fusion layer is not limited in the embodiments of the present application, for example, the data fusion layer may include at least one layer of a graph convolution neural network.
Based on the above-mentioned related content of step 11, when the temperature data and the state data of the battery to be processed at the ith sampling time point are input into the data fusion layer, the data fusion layer fuses the temperature data and the state data of the battery to be processed at the ith sampling time point, so as to obtain and output the fused data of the battery to be processed at the ith sampling time point. Wherein i is a positive integer, i is not more than N, and N is a positive integer.
Step 12: and aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period.
The data aggregation layer is used for aggregating the input data of the data aggregation layer. It should be noted that the embodiment of the present application is not limited to the data aggregation layer, and may be implemented by using any existing or future network capable of implementing the aggregation function.
The aggregate data refers to a set of fused data of the battery to be processed at the 1 st sampling time point to fused data of the battery to be processed at the Nth sampling time point.
Based on the related content of step 12, after the fused data of the to-be-processed battery at the 1 st sampling time point is input to the fused data of the to-be-processed battery at the nth sampling time point, the data aggregation layer aggregates the fused data of the to-be-processed battery at the 1 st sampling time point to the fused data of the to-be-processed battery at the nth sampling time point, so as to obtain and output the aggregated data of the to-be-processed battery in the first time period.
Step 13: and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
The data coding layer is used for coding input data of the data coding layer. In addition, the data encoding layer is not limited in the embodiments of the present application, for example, the data encoding layer may include a long and short memory network. As another example, the data encoding layer may include a long and short memory network and an attention layer.
Based on the above-mentioned relevant content from step 11 to step 13, when the battery temperature vector generation model includes the data fusion layer, the data aggregation layer and the data coding layer, the battery temperature vector generation model may sequentially perform fusion processing, aggregation data and coding data on the temperature data and the state data of the battery to be processed in the first time period, so as to obtain and output the temperature vector of the battery to be processed in the first time period, so that the temperature vector can accurately represent the actual temperature of the battery to be processed in the first time period.
In addition, the embodiment of the present application also does not limit the training process of the battery temperature vector generation model, for example, in a possible implementation manner, the training process of the battery temperature vector generation model may specifically include steps 21 to 24:
step 21: at least one training data is acquired.
The training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period.
The battery to be trained refers to a battery capable of providing historical temperature data and historical state data for the acquisition process of training data.
The second time period refers to a historical time period in which temperature representation is required. In addition, the second period is not limited in the embodiments of the present application.
In addition, the embodiment of the present application does not limit the acquisition manner of the training data, for example, the acquisition process of the training data may specifically be: firstly, according to historical temperature data and historical state data of a battery to be trained, determining temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period; and determining the temperature data of the battery to be trained in the second time period and the state data of the battery to be trained in the second time period as training data.
Step 22: and inputting the at least one piece of training data into the battery temperature vector generation model to obtain the temperature vector of the at least one piece of training data output by the battery temperature vector generation model.
Step 23: judging whether a preset stopping condition is reached, if so, finishing the training process of the battery temperature vector generation model; if not, go to step 24.
The preset stop condition may be preset. In addition, the preset stop condition is not limited in the embodiment of the present application, for example, the preset stop condition may be that a loss value of the battery temperature vector generation model reaches a first threshold, that a change rate of the temperature vector of at least one piece of training data is lower than a second threshold, and that the number of times of updating the battery temperature vector generation model reaches a third threshold.
Based on the relevant content in the step 23, judging whether the current battery temperature vector generation model reaches the preset stop condition, if so, indicating that the vectorization performance of the current battery temperature vector generation model is better, so that the training process of the battery temperature vector generation model can be directly ended, and the battery temperature vector generation model is stored or used; if not, the vectorization performance of the current battery temperature vector generation model is poor, so that the battery temperature vector generation model can be updated by using at least one training data, the temperature vector of at least one training data and a preset loss function, so that the updated battery temperature vector generation model has better vectorization performance.
Step 24: and updating the battery temperature vector generation model according to the at least one training data, the at least one temperature vector of the training data and the preset loss function, and returning to execute the step 22.
The preset loss function is used for calculating the vectorization performance of the battery temperature vector generation model; moreover, the embodiment of the present application does not limit the preset loss function. For example, the predetermined loss function may be predetermined.
In some cases, the battery temperature vector generation model may be trained in an unsupervised learning manner, such that the battery temperature vector generation model may be learned according to the following learning objectives: if the similarity degree between any two training data is larger, the similarity degree between the temperature vectors of the two training data is larger; if the similarity between any two training data is smaller, the similarity between the temperature vectors of the two training data is smaller. Based on this, in some cases, the preset loss function may be set based on the above learning target.
Based on the above-mentioned related contents of step 21 to step 24, in the embodiment of the present application, the battery temperature vector generation model may be trained by using the temperature data and the state data of some batteries in the historical time period, so that the trained battery temperature vector generation model can accurately determine the battery temperature vector.
Based on the above-mentioned related content of S2, after the temperature data and the state data of the battery to be processed in the first time period are obtained, the temperature data and the state data of the battery to be processed in the first time period may be vectorized by using a pre-trained battery temperature vector generation model, so as to obtain the temperature vector of the battery to be processed in the first time period, so that the temperature vector can accurately represent the time series of the actual temperature of the battery to be processed in the first time period.
Based on the above-mentioned related contents of S1 to S2, in the method for generating a battery temperature vector provided in the embodiment of the present application, after the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period are acquired, the temperature vector of the battery to be processed in the first time period may be generated according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period. The temperature vector is determined based on the temperature data and the state data of the battery to be processed in the first time period, so that the temperature vector can more accurately represent the actual temperature of the battery to be processed in the first time period, and the representation accuracy of the actual temperature of the battery is improved.
Based on the method for generating the battery temperature vector provided by the above method embodiment, the embodiment of the present application further provides a device for generating the battery temperature vector, which is explained and explained below with reference to the accompanying drawings.
Device embodiment
Please refer to the above method embodiment for the technical details of the battery temperature vector generation apparatus provided in the apparatus embodiment.
Referring to fig. 3, the diagram is a schematic structural diagram of a battery temperature vector generation apparatus according to an embodiment of the present application.
The battery temperature vector generation apparatus 300 provided in the embodiment of the present application includes:
an obtaining unit 301, configured to obtain temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
a generating unit 302, configured to generate a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
In a possible implementation, the generating unit 302 includes:
and inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model.
In one possible embodiment, the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
when the temperature data in the first time period includes temperature data at N sampling time points, and the state data in the first time period includes state data at N sampling time points, the inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model, and obtaining the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model, including:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
In one possible embodiment, the data fusion layer includes at least one layer of graph convolutional neural network.
In one possible embodiment, the data coding layer includes a long and short memory network; or, the data coding layer comprises a long and short memory network and an attention layer.
In one possible embodiment, the training process of the battery temperature vector generation model includes:
acquiring at least one training data; the training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period;
inputting the at least one piece of training data into the battery temperature vector generation model to obtain a temperature vector of the at least one piece of training data output by the battery temperature vector generation model;
and updating the battery temperature vector generation model according to the at least one training data, the temperature vector of the at least one training data and a preset loss function, and continuing to execute the steps of inputting the at least one training data into the battery temperature vector generation model and the subsequent steps until a preset stop condition is reached.
In one possible embodiment, the temperature data includes at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery;
and/or the presence of a gas in the gas,
the state data includes at least one of a voltage, a current, an internal resistance, a battery capacity, a battery health, and a battery remaining capacity.
Based on the related content of the battery temperature vector generation apparatus 300 provided in the above apparatus embodiment, for the battery temperature vector generation apparatus 300, after the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period are acquired, the temperature vector of the battery to be processed in the first time period may be generated according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period. The temperature vector is determined based on the temperature data and the state data of the battery to be processed in the first time period, so that the temperature vector can more accurately represent the actual temperature of the battery to be processed in the first time period, and the representation accuracy of the actual temperature of the battery is improved.
Based on the method for generating the battery temperature vector provided by the above method embodiment, the embodiment of the present application further provides a device, which is explained and explained below with reference to the accompanying drawings.
Apparatus embodiment
Please refer to the above method embodiment for the device technical details provided by the device embodiment.
Referring to fig. 4, the figure is a schematic structural diagram of an apparatus provided in an embodiment of the present application.
The apparatus 400 provided in the embodiment of the present application includes: a processor 401 and a memory 402;
the memory 402 is used for storing computer programs;
the processor 401 is configured to execute any implementation of the method for generating a battery temperature vector provided by the above method embodiments according to the computer program. That is, the processor 401 is configured to perform the following steps:
acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
In a possible embodiment, the generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period includes:
and inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model.
In one possible embodiment, the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
when the temperature data in the first time period includes temperature data at N sampling time points, and the state data in the first time period includes state data at N sampling time points, the inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model, and obtaining the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model, including:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
In one possible embodiment, the data fusion layer includes at least one layer of graph convolutional neural network.
In one possible embodiment, the data coding layer includes a long and short memory network; or, the data coding layer comprises a long and short memory network and an attention layer.
In one possible embodiment, the training process of the battery temperature vector generation model includes:
acquiring at least one training data; the training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period;
inputting the at least one piece of training data into the battery temperature vector generation model to obtain a temperature vector of the at least one piece of training data output by the battery temperature vector generation model;
and updating the battery temperature vector generation model according to the at least one training data, the temperature vector of the at least one training data and a preset loss function, and continuing to execute the steps of inputting the at least one training data into the battery temperature vector generation model and the subsequent steps until a preset stop condition is reached.
In one possible embodiment, the temperature data includes at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery;
and/or the presence of a gas in the gas,
the state data includes at least one of a voltage, a current, an internal resistance, a battery capacity, a battery health, and a battery remaining capacity.
The above is related to the apparatus 400 provided in the embodiment of the present application.
Based on the method for generating the battery temperature vector provided by the method embodiment, the embodiment of the application also provides a computer-readable storage medium.
Media embodiments
Media embodiments provide technical details of computer-readable storage media, please refer to method embodiments.
The embodiment of the application provides a computer-readable storage medium for storing a computer program, wherein the computer program is used for executing any implementation mode of the battery temperature vector generation method provided by the method embodiment. That is, the computer program is for performing the steps of:
acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
and generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period.
In a possible embodiment, the generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period includes:
and inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model.
In one possible embodiment, the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
when the temperature data in the first time period includes temperature data at N sampling time points, and the state data in the first time period includes state data at N sampling time points, the inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model, and obtaining the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model, including:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
In one possible embodiment, the data fusion layer includes at least one layer of graph convolutional neural network.
In one possible embodiment, the data coding layer includes a long and short memory network; or, the data coding layer comprises a long and short memory network and an attention layer.
In one possible embodiment, the training process of the battery temperature vector generation model includes:
acquiring at least one training data; the training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period;
inputting the at least one piece of training data into the battery temperature vector generation model to obtain a temperature vector of the at least one piece of training data output by the battery temperature vector generation model;
and updating the battery temperature vector generation model according to the at least one training data, the temperature vector of the at least one training data and a preset loss function, and continuing to execute the steps of inputting the at least one training data into the battery temperature vector generation model and the subsequent steps until a preset stop condition is reached.
In one possible embodiment, the temperature data includes at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery;
and/or the presence of a gas in the gas,
the state data includes at least one of a voltage, a current, an internal resistance, a battery capacity, a battery health, and a battery remaining capacity.
The above is related to the computer-readable storage medium provided in the embodiments of the present application.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (8)
1. A method for generating a battery temperature vector, the method comprising:
acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
generating a temperature vector of the battery to be processed in a first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period;
the generating a temperature vector of the battery to be processed in the first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period includes:
inputting the temperature data of the battery to be processed in a first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model; the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
when the temperature data in the first time period includes temperature data at N sampling time points and the state data in the first time period includes state data at N sampling time points, the inputting the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model to obtain the temperature vector of the battery to be processed in the first time period output by the battery temperature vector generation model, including:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
2. The method of claim 1, wherein the data fusion layer comprises at least one layer of graph convolutional neural network.
3. The method of claim 1, wherein the data encoding layer comprises a long and short memory network; or, the data coding layer comprises a long and short memory network and an attention layer.
4. The method of claim 1, wherein the training process of the battery temperature vector generation model comprises:
acquiring at least one training data; the training data comprises temperature data of the battery to be trained in a second time period and state data of the battery to be trained in the second time period;
inputting the at least one piece of training data into the battery temperature vector generation model to obtain a temperature vector of the at least one piece of training data output by the battery temperature vector generation model;
and updating the battery temperature vector generation model according to the at least one training data, the temperature vector of the at least one training data and a preset loss function, and continuing to execute the steps of inputting the at least one training data into the battery temperature vector generation model and the subsequent steps until a preset stop condition is reached.
5. The method of any one of claims 1 to 4, wherein the temperature data comprises at least one of an ambient temperature, a maximum temperature within the battery, a minimum temperature within the battery, and a probe temperature within the battery;
and/or the presence of a gas in the gas,
the state data includes at least one of a voltage, a current, an internal resistance, a battery capacity, a battery health, and a battery remaining capacity.
6. A battery temperature vector generation apparatus, characterized in that the apparatus comprises:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring temperature data of a battery to be processed in a first time period and state data of the battery to be processed in the first time period;
the generating unit is used for generating a temperature vector of the battery to be processed in a first time period according to the temperature data of the battery to be processed in the first time period and the state data of the battery to be processed in the first time period;
the generating unit is specifically configured to input temperature data of the battery to be processed in a first time period and state data of the battery to be processed in the first time period into a pre-trained battery temperature vector generation model, so as to obtain a temperature vector of the battery to be processed in the first time period, which is output by the battery temperature vector generation model; the battery temperature vector generation model comprises a data fusion layer, a data aggregation layer and a data coding layer;
wherein, when the temperature data in the first period of time includes temperature data at N sampling time points, and the state data in the first period of time includes state data at N sampling time points, the generating unit is specifically configured to:
fusing the temperature data of the battery to be processed at the ith sampling time point and the state data of the battery to be processed at the ith sampling time point by using the data fusion layer to obtain fused data of the battery to be processed at the ith sampling time point; wherein i is a positive integer, i is not more than N, and N is a positive integer;
aggregating the fusion data of the battery to be processed at the 1 st sampling time point to the fusion data of the battery to be processed at the Nth sampling time point by using the data aggregation layer to obtain the aggregation data of the battery to be processed in the first time period;
and encoding the aggregated data of the battery to be processed in the first time period by using the data encoding layer to obtain the temperature vector of the battery to be processed in the first time period.
7. An apparatus to generate a battery temperature vector, the apparatus comprising a processor and a memory:
the memory is used for storing a computer program;
the processor is configured to perform the method of any of claims 1-5 in accordance with the computer program.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program for performing the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337703.5A CN112542621B (en) | 2020-11-25 | 2020-11-25 | Battery temperature vector generation method and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337703.5A CN112542621B (en) | 2020-11-25 | 2020-11-25 | Battery temperature vector generation method and related equipment thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112542621A CN112542621A (en) | 2021-03-23 |
| CN112542621B true CN112542621B (en) | 2022-04-01 |
Family
ID=75015135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011337703.5A Active CN112542621B (en) | 2020-11-25 | 2020-11-25 | Battery temperature vector generation method and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112542621B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108983103A (en) * | 2018-06-29 | 2018-12-11 | 上海科列新能源技术有限公司 | A kind of data processing method and device of power battery |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103579708B (en) * | 2012-07-24 | 2016-04-27 | 联想(北京)有限公司 | A kind of battery temperature monitoring method and device, battery |
| US9063018B1 (en) * | 2012-10-22 | 2015-06-23 | Qnovo Inc. | Method and circuitry to determine temperature and/or state of health of a battery/cell |
| JP6806602B2 (en) * | 2017-03-17 | 2021-01-06 | 株式会社東芝 | Temperature control device |
| US11300624B2 (en) * | 2017-07-28 | 2022-04-12 | Northstar Battery Company, Llc | System for utilizing battery operating data |
| JP6806002B2 (en) * | 2017-08-24 | 2020-12-23 | トヨタ自動車株式会社 | Temperature estimation device |
| CN108226693B (en) * | 2017-12-18 | 2020-02-07 | 清华大学 | Method and apparatus for detecting short circuit in battery in real time, and computer-readable storage medium |
| US11846678B2 (en) * | 2018-06-07 | 2023-12-19 | Samsung Sdi Co., Ltd. | Method and system for validating a temperature sensor in a battery cell |
| CN110118617A (en) * | 2019-05-30 | 2019-08-13 | 上海元城汽车技术有限公司 | The internal temperature of battery modules determines method, apparatus and intelligent terminal |
| CN110598300A (en) * | 2019-09-05 | 2019-12-20 | 东软睿驰汽车技术（沈阳）有限公司 | Battery SOH prediction method and device |
| CN110816366B (en) * | 2019-10-31 | 2022-12-09 | 上海交通大学 | Temperature estimation method, system, medium and device suitable for inside of single battery |
| CN111595485B (en) * | 2020-05-07 | 2022-03-04 | 广东工业大学 | Lithium ion battery online temperature distribution observer design method based on reduced order model |
-
2020
- 2020-11-25 CN CN202011337703.5A patent/CN112542621B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108983103A (en) * | 2018-06-29 | 2018-12-11 | 上海科列新能源技术有限公司 | A kind of data processing method and device of power battery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112542621A (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| Yuan et al. | Design and performance analysis of deterministic learning of sampled-data nonlinear systems | |
| JP6944208B2 (en) | Charger | |
| JP6842212B1 (en) | Battery performance evaluation method and battery performance evaluation device | |
| CN110751385A (en) | Non-invasive load identification method, terminal device and storage medium | |
| JP2023139227A (en) | Battery health state prediction method, device, and electronic instrument and readable storage medium | |
| CN112444748A (en) | Battery abnormality detection method, battery abnormality detection device, electronic apparatus, and storage medium | |
| CN116559667A (en) | Model training method and device, battery detection method and device, equipment and medium | |
| Savargaonkar et al. | Uncorrelated sparse autoencoder with long short-term memory for state-of-charge estimations in lithium-ion battery cells | |
| WO2022144542A1 (en) | Method for predicting condition parameter degradation of a cell | |
| CN116992311B (en) | Energy storage power supply state analysis method based on machine learning | |
| CN112542621B (en) | Battery temperature vector generation method and related equipment thereof | |
| CN113295399B (en) | Converter valve element state evaluation method, device, electronic equipment and storage medium | |
| CN113689039A (en) | Lithium ion battery RUL time sequence prediction method | |
| CN116154914B (en) | Battery charging management method and device | |
| CN116842447A (en) | Post-processing method, device and system for classified data and electronic device | |
| WO2022239391A1 (en) | Battery performance evaluation device and battery performance evaluation method | |
| CN113459897B (en) | Electric vehicle charging big data-based state of charge correction and prediction method | |
| WO2021149482A1 (en) | Battery performance evaluation device, electronic apparatus, charger, and battery performance evaluation method | |
| US11860235B2 (en) | Battery state estimation apparatus | |
| CN116976530B (en) | Cable equipment state prediction method, device and storage medium | |
| CN112787386B (en) | Intelligent charging control method, system, charging equipment and computer storage medium | |
| JP7242109B2 (en) | BATTERY PERFORMANCE EVALUATION DEVICE AND BATTERY PERFORMANCE EVALUATION METHOD | |
| Lei et al. | Pruning LS-SVM Based Battery Model for Electric Vehicles | |
| Wei et al. | Health State Estimation of Lithium Battery Based on Wavelet Packet Transform and Transformer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |