Battery temperature abnormality detection method and medium

Abstract

The application discloses a battery temperature anomaly detection method and medium. The method can include: acquiring real-time temperature sensing data of a vehicle power battery and extracting abnormal temperature sensing data; setting an abnormal temperature sensing warning level and determining the corresponding warning level according to the abnormal temperature sensing data; and extracting abnormal temperature sensing detailed data, including the abnormal temperature sensing data and the corresponding warning level. The application is based on historical data of the power battery, efficiently calculates the temperature rise rate, the temperature drop rate and the temperature difference at the same time of the battery in batches on a big data platform, sets a threshold, detects vehicles and corresponding battery modules with abnormalities in advance, reduces maintenance costs, safety accidents and improves customer experience.

Description

Technical Field

[0001] This invention relates to the automotive field, and more specifically, to a method and medium for detecting abnormal battery temperature. Background Technology

[0002] In today's era, the number of new energy vehicles is rapidly increasing, and the frequency of fire accidents involving new energy vehicles is also increasing year by year, seriously endangering the lives and property of drivers. The power battery, as the "heart" of a new energy vehicle, is the root cause of most safety accidents. Persistent abnormal temperatures will affect the safety, lifespan, function, and performance of the power battery. Excessively high or low temperatures can lead to thermal runaway, severe lifespan degradation, and limited charge / discharge capabilities.

[0003] Therefore, it is necessary to develop a method and medium for detecting abnormal battery temperatures.

[0004] The information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] This invention proposes a method and medium for detecting abnormal battery temperatures. Based on historical data of power batteries, it efficiently calculates the rate of temperature rise, rate of temperature fall, and temperature difference at the same time on a big data platform. By setting a threshold, it can detect abnormal vehicles and corresponding battery modules in advance, thereby reducing maintenance costs, safety accidents, and improving customer experience.

[0006] In a first aspect, embodiments of this disclosure provide a method for detecting abnormal battery temperature, including: Acquire real-time temperature sensing data of the vehicle's power battery and extract abnormal temperature sensing data; Set abnormal temperature sensing warning levels and determine the corresponding warning levels based on abnormal temperature sensing data; Extract detailed data on abnormal temperature sensing, including abnormal temperature sensing data and corresponding warning levels.

[0007] Preferably, extracting abnormal temperature sensing data includes extracting abnormal temperature sensing data from module temperature sensing anomalies, extracting abnormal temperature sensing data from module temperature sensing change rate anomalies, and extracting individual abnormal temperature sensing data.

[0008] Preferably, extracting abnormal temperature sensing data from module temperature sensing anomalies includes: Extract abnormal temperature sensing modules; Extract abnormal temperature sensing data from the abnormal temperature sensing module.

[0009] Preferably, the abnormal temperature sensing module includes: In a single frame of data, the temperature difference is calculated for each temperature sensor within each module to obtain the temperature difference value for each module. :

[0010] in, Number the module; Number the temperature sensors; Set threshold ,when > This module is an abnormal temperature sensing module.

[0011] Preferably, extracting abnormal temperature sensing data from the abnormal temperature sensing module includes: Calculate the average temperature sensing data of the abnormal temperature sensing module:

[0012] in : The sum of all temperature sensing data at any given moment. : Time of the first The temperature of a temperature sensing point : The sum of invalid values ​​at any given time, where n is the number of temperature sensors and m is the number of invalid values; When | |>| |and| |>| Then determine This indicates an abnormal temperature sensation.

[0013] Preferably, determining the corresponding warning level based on abnormal temperature sensing data includes: Set threshold , , ; remember , ,when and Then the outlier trait is higher. and If so, the outlier characteristic is low; When the outlier trait is high and Then the first The risk level for temperature-related sensitivities is low. and Then the first The risk level for temperature-related sensitivities is high. When the outlier trait is low and Then the first The risk level for temperature-related sensitivities is low. and Then the first The temperature-sensitive risk level is high.

[0014] Preferably, extracting abnormal temperature sensing data from abnormal module temperature sensing rate of change includes: Calculate the rate of change of the j-th temperature sensor in two consecutive frames of data:

[0015] in, for Time of the first Data on temperature sensitivity, For a moment, Let j be the rate of change of the temperature sensor over two consecutive frames of data. Set a threshold for the rate of change; Within a module, when > Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. If j+1 is an abnormal temperature sensing signal, then j+1 is an abnormal temperature sensing signal.

[0016] Within a module, when Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. This indicates an abnormal temperature reading; conversely, This is an abnormal temperature sensing signal.

[0017] Preferably, extracting a single temperature anomaly data point includes: Calculate the mean value after removing invalid temperature sensing values ​​at time j:

[0018] Calculate the average of the temperature sensor values ​​at time j after removing invalid temperature sensor values ​​and the current temperature sensor value:

[0019] in, The sum of all temperature sensing data. The temperature at the current point. : Sum of invalid values, n: Number of temperature sensors, m: Number of invalid values Let be the mean value after removing invalid temperature sensing values ​​at time j. This is the average of the temperature sensing values ​​at time j after removing invalid temperature sensing values ​​and the current temperature sensing value; when < and |>= If the duration is continuously set, then Tj is determined to be abnormal temperature data, and j is considered abnormal temperature data. and The threshold is set based on the vehicle's condition.

[0020] Preferably, determining the corresponding warning level based on abnormal temperature sensing data includes: All extracted abnormal temperature data were set to high risk.

[0021] Secondly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the battery temperature anomaly detection method.

[0022] Its beneficial effects are as follows: 1. This invention reduces false alarms by removing invalid values ​​from a frame of data and averaging the current module's temperature sensing values; 2. This invention determines temperature sensing anomalies by judging whether two frames of data simultaneously meet the conditions, thereby reducing false alarms; 3. This invention enables batch calculations through a big data platform.

[0023] The methods and apparatus of the present invention have other features and advantages that will be apparent from or will be set forth in detail in the accompanying drawings and following detailed description, which together serve to explain the particular principles of the invention. Attached Figure Description

[0024] The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of exemplary embodiments of the invention in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same parts.

[0025] Figure 1 A flowchart illustrating the steps of a battery temperature anomaly detection method according to an embodiment of the present invention is shown. Detailed Implementation

[0026] Preferred embodiments of the invention will now be described in more detail. While preferred embodiments of the invention are described below, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0027] To facilitate understanding of the solutions and effects of the embodiments of the present invention, two specific application examples are given below. Those skilled in the art should understand that these examples are merely for the purpose of understanding the present invention, and any specific details therein are not intended to limit the present invention in any way.

[0028] Example 1

[0029] Figure 1 A flowchart illustrating the steps of a battery temperature anomaly detection method according to an embodiment of the present invention is shown.

[0030] like Figure 1 As shown, the battery temperature anomaly detection method includes: Step 101: Obtain real-time temperature sensing data of the vehicle's power battery and extract abnormal temperature sensing data; Step 102: Set the abnormal temperature sensing warning level and determine the corresponding warning level based on the abnormal temperature sensing data; Step 103: Extract detailed data on abnormal temperature sensing, including abnormal temperature sensing data and corresponding warning levels.

[0031] In one example, extracting abnormal temperature sensing data includes extracting abnormal temperature sensing data from module temperature sensing anomalies, extracting abnormal temperature sensing data from module temperature sensing rate of change anomalies, and extracting individual temperature sensing anomaly data.

[0032] In one example, extracting abnormal temperature sensing data in the event of module temperature sensing anomalies includes: Extract abnormal temperature sensing modules; Extract abnormal temperature sensing data from the abnormal temperature sensing module.

[0033] In one example, extracting abnormal temperature sensing modules includes: In a single frame of data, the temperature difference is calculated for each temperature sensor within each module to obtain the temperature difference value for each module. :

[0034] in, Number the module; Number the temperature sensors; Set threshold ,when > This module is an abnormal temperature sensing module.

[0035] In one example, extracting abnormal temperature sensing data from the abnormal temperature sensing module includes: Calculate the average temperature sensing data of the abnormal temperature sensing module:

[0036] in : The sum of all temperature sensing data at any given moment. : Time of the first The temperature of a temperature sensing point : The sum of invalid values ​​at any given time, where n is the number of temperature sensors and m is the number of invalid values; When | |>| |and| |>| Then determine This indicates an abnormal temperature sensation.

[0037] In one example, determining the corresponding warning level based on abnormal temperature sensing data includes: Set threshold , , ; remember , ,when and Then the outlier trait is higher. and If so, the outlier characteristic is low; When the outlier trait is high and Then the first The risk level for temperature-related sensitivities is low. and Then the first The risk level for temperature-related sensitivities is high. When the outlier trait is low and Then the first The risk level for temperature-related sensitivities is low. and Then the first The temperature-sensitive risk level is high.

[0038] In one example, extracting abnormal temperature sensing data from anomalies in the module's temperature sensing rate of change includes: Calculate the rate of change of the j-th temperature sensor in two consecutive frames of data:

[0039] in, for Time of the first Data on temperature sensitivity, For a moment, Let j be the rate of change of the temperature sensor over two consecutive frames of data. Set a threshold for the rate of change; Within a module, when > Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. If j+1 is an abnormal temperature sensing signal, then j+1 is an abnormal temperature sensing signal.

[0040] Within a module, when Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. This indicates an abnormal temperature reading; conversely, This is an abnormal temperature sensing signal.

[0041] In one example, extracting a single temperature anomaly data point includes: Calculate the mean value after removing invalid temperature sensing values ​​at time j:

[0042] Calculate the average of the temperature sensor values ​​at time j after removing invalid temperature sensor values ​​and the current temperature sensor value:

[0043] in, The sum of all temperature sensing data. The temperature at the current point. : Sum of invalid values, n: Number of temperature sensors, m: Number of invalid values Let be the mean value after removing invalid temperature sensing values ​​at time j. This is the average of the temperature sensing values ​​at time j after removing invalid temperature sensing values ​​and the current temperature sensing value; when < and |>= If the duration is continuously set, then Tj is determined to be abnormal temperature data, and j is considered abnormal temperature data. and The threshold is set based on the vehicle's condition.

[0044] In one example, determining the corresponding warning level based on abnormal temperature sensing data includes: All extracted abnormal temperature data were set to high risk.

[0045] Specifically, acquire the temperature sensing data of each power battery for each frame within a period T (the specific value depends on the application, T can be 1 week, 2 weeks, or 1 month, etc.). 'j' represents the temperature sensor number. In each frame of data, the number of null values ​​and invalid data exceeding a certain threshold is considered. When a threshold is given based on the vehicle's status, this frame of data is not included in the calculation to reduce false alarms; data from certain specific operating states of the vehicle are also not included in the calculation to reduce false alarms.

[0046] Extracting abnormal temperature sensing data includes extracting abnormal temperature sensing data from module temperature sensing anomalies, extracting abnormal temperature sensing data from module temperature sensing rate of change anomalies, and extracting individual abnormal temperature sensing data. 1. Extract abnormal temperature sensing data from abnormal module temperature sensing. In a single frame of data, the temperature differences between the individual temperature sensors in the first module are calculated, the differences between the individual temperature sensors in the second module are calculated, the differences between the individual temperature sensors in the third module are calculated, and so on, to obtain the temperature difference values ​​for each module. :

[0047] in Which module is it? Which temperature sensor?

[0048] Set threshold ,when > The module was found to have an abnormal temperature.

[0049] Calculate the average temperature sensor value of the frame corresponding to the abnormal module (sum all temperature sensor data, remove invalid values ​​and the current module's temperature).

[0050] in : The sum of all temperature sensing data at any given moment. : Time of the first The temperature of a temperature sensing point : The sum of invalid values ​​at any given time, where n is the number of temperature sensors and m is the number of invalid values.

[0051] When | |>| |and| |>| Then determine This is an abnormal temperature sensing signal.

[0052] 2. Extract abnormal temperature sensing data from abnormal module temperature sensing rate of change.

[0053] Calculate the rate of change of the j-th temperature sensor in two consecutive frames of data:

[0054] in for Time of the first Data on temperature sensitivity, For a moment, Let j be the rate of change of the temperature sensor over two consecutive frames of data. Set a threshold for the rate of change.

[0055] Within a module, when > ℃ / s or report an invalid value and continue for a set duration, while If the value is ℃ / s and no invalid values ​​are reported, and the set duration is maintained, then it is determined that... This is abnormal temperature sensing data. If j+1 is an abnormal temperature sensing signal, then j+1 is an abnormal temperature sensing signal.

[0056] Within a module, when ℃ / s or report an invalid value and continue for a set duration, while If the value is ℃ / s and no invalid values ​​are reported, and the set duration is maintained, then it is determined that... This is abnormal temperature sensing data. This indicates an abnormal temperature reading; conversely, This is an abnormal temperature sensing signal.

[0057] 3. Extract individual temperature anomaly data

[0058] Calculate the mean value after removing invalid temperature sensing values ​​at time j:

[0059] Calculate the average of the temperature sensor values ​​at time j after removing invalid temperature sensor values ​​and the current temperature sensor value:

[0060] in The sum of all temperature sensing data. The temperature at the current point. : Sum of invalid values, n: Number of temperature sensors, m: Number of invalid values Let be the mean value after removing invalid temperature sensing values ​​at time j. This is the average of the temperature sensing values ​​at time j after removing invalid temperature sensing values ​​and the current temperature sensing value.

[0061] when < and |>= Furthermore, if the duration is continuously set, Tj is determined to be abnormal temperature data, and j is considered abnormal temperature data. and The threshold is set based on the vehicle's condition.

[0062] For abnormal temperature sensing data extracted from abnormal temperature sensing in the module, a threshold is set. , , ,remember , ,when and The outlier trait is then higher. and If the outlier trait is high, then the outlier trait is low. If the outlier trait is high, then... and Then the first The risk level for temperature-related sensitivities is low. and Then the first The individual's temperature sensitivity risk level is high; when the outlier characteristic is low... and Then the first The risk level for temperature-related sensitivities is low. and Then the first The temperature-sensitive risk level is high.

[0063] For both the abnormal temperature sensing data extracted from the abnormal temperature sensing rate of the module and the extracted single abnormal temperature sensing data, all extracted abnormal temperature sensing data are set as high risk.

[0064] Extract data before and after the occurrence of abnormal temperature readings, mark the risk level and the calculated average at the time of the abnormality, and display them on the early warning data display page.

[0065] This detection method utilizes Hive SQL and offline data warehouse technology to perform batch calculations on multiple vehicle models. The specific implementation is as follows: Step 1: Write Hive SQL, configure the scheduling, and set the task execution time, execution frequency, and alarm personnel information.

[0066] Step 2: First, set the amount of data to be checked. If the amount is less than the specified amount, the program will terminate directly and the alarm personnel will be notified simultaneously. The program will be rerun once the amount of data is normal. If the amount of data is normal, but there is abnormal data > 0, the alarm personnel will be notified to check the vehicle. If there is no abnormal data, there will be no alarm.

[0067] Example 2

[0068] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the battery temperature anomaly detection method.

[0069] A computer-readable storage medium according to embodiments of the present disclosure stores non-transitory computer-readable instructions. When these non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the methods described in the foregoing embodiments of the present disclosure are performed.

[0070] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0071] Those skilled in the art should understand that the above description of the embodiments of the present invention is only intended to illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any of the examples given.

[0072] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for detecting abnormal battery temperature, characterized in that, include: Acquire real-time temperature sensing data of the vehicle's power battery and extract abnormal temperature sensing data; Set abnormal temperature sensing warning levels and determine the corresponding warning levels based on abnormal temperature sensing data; Extract detailed data on abnormal temperature sensing, including abnormal temperature sensing data and corresponding warning levels.

2. The battery temperature anomaly detection method according to claim 1, wherein, Extracting abnormal temperature sensing data includes extracting abnormal temperature sensing data from module temperature sensing anomalies, extracting abnormal temperature sensing data from module temperature sensing change rate anomalies, and extracting individual abnormal temperature sensing data.

3. The battery temperature anomaly detection method according to claim 2, wherein, Extracting abnormal temperature sensing data from module temperature sensing anomalies includes: Extract abnormal temperature sensing modules; Extract abnormal temperature sensing data from the abnormal temperature sensing module.

4. The battery temperature anomaly detection method according to claim 3, wherein, The abnormal temperature sensing module includes: In a single frame of data, the temperature difference is calculated for each temperature sensor within each module to obtain the temperature difference value for each module. : in, Number the module; Number the temperature sensors; Set threshold ,when > This module is an abnormal temperature sensing module.

5. The battery temperature anomaly detection method according to claim 3, wherein, Extracting abnormal temperature sensing data from the abnormal temperature sensing module includes: Calculate the average temperature sensing data of the abnormal temperature sensing module: in : The sum of all temperature sensing data at any given moment. : Time of the first The temperature of a temperature sensing point : The sum of invalid values ​​at any given time, where n is the number of temperature sensors and m is the number of invalid values; When | |>| |and| |>| Then determine This indicates an abnormal temperature sensation.

6. The battery temperature anomaly detection method according to claim 5, wherein, The corresponding warning levels are determined based on abnormal temperature sensing data, including: Set threshold , , ; remember , ,when and Then the outlier trait is higher. and If so, the outlier characteristic is low; When the outlier trait is high and Then the first The risk level for temperature-related sensitivities is low. and Then the first The risk level for temperature-related sensitivities is high. When the outlier trait is low and Then the first The risk level for temperature-related sensitivities is low. and Then the first The temperature-sensitive risk level is high.

7. The battery temperature anomaly detection method according to claim 2, wherein, Abnormal temperature sensing data extracted from abnormal module temperature sensing rate of change includes: Calculate the rate of change of the j-th temperature sensor in two consecutive frames of data: in, for Time of the first The data of temperature sensing, For a moment, Let j be the rate of change of the temperature sensor over two consecutive frames of data. Set a threshold for the rate of change; Within a module, when > Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. If j+1 is an abnormal temperature sensing signal, then j+1 is an abnormal temperature sensing signal. Within a module, when Alternatively, report invalid values ​​and continue for a set duration. If invalid values ​​are not reported and the set duration is maintained, then a judgment is made. This is abnormal temperature sensing data. This indicates an abnormal temperature reading; conversely, This is an abnormal temperature sensing signal.

8. The battery temperature anomaly detection method according to claim 2, wherein, Extracting individual temperature anomaly data includes: Calculate the mean value after removing invalid temperature sensing values ​​at time j: Calculate the average of the temperature sensor values ​​at time j after removing invalid temperature sensor values ​​and the current temperature sensor value: in, The sum of all temperature sensing data. The temperature at the current point. : Sum of invalid values, n: Number of temperature sensors, m: Number of invalid values Let be the mean value after removing invalid temperature sensing values ​​at time j. This is the average of the temperature sensing values ​​at time j after removing invalid temperature sensing values ​​and the current temperature sensing value; when < and |>= If the duration is continuously set, then Tj is determined to be abnormal temperature data, and j is considered abnormal temperature data. and The threshold is set based on the vehicle's condition.

9. The battery temperature anomaly detection method according to claim 7 or 8, wherein, The corresponding warning levels are determined based on abnormal temperature sensing data, including: All extracted abnormal temperature data were set to high risk.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the battery temperature anomaly detection method according to any one of claims 1-9.

Images