New energy automobile power battery thermal runaway monitoring method and system

Abstract

The invention provides a new energy automobile power battery thermal runaway monitoring method and system, the system comprises a vehicle-mounted terminal and a cloud, and the method comprises the steps that the vehicle-mounted terminal obtains data of a plurality of evaluation parameters in real time and uploads the data to the cloud; the cloud predicts whether the power battery has a fire trend through a digital twinning technology; if the fire trend is predicted, the vehicle-mounted terminal controls the output of a power battery; if the fire trend is not predicted, judging whether the data of each evaluation parameter is in a normal interval range or not; if the data of any evaluation parameter is not in the normal interval range, the vehicle-mounted terminal controls the output of the power battery; if the data of each evaluation parameter is within the normal interval range, the cloud sends a processing instruction to the vehicle-mounted terminal; and the vehicle-mounted terminal performs linkage analysis on the data of the evaluation parameters and the historical data, and when the analysis result is abnormal, the output of the power battery is controlled. Potential safety hazards of the battery can be effectively monitored, and the service life of the battery is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of power batteries, and in particular to a method and system for monitoring thermal runaway of a power battery for a new energy vehicle. Background Art

[0002] Electric vehicles are a means of transportation that can reduce exhaust emissions and lower operating costs. With the reduction of dependence on traditional fossil fuels and the increase in environmental awareness, the demand for electric vehicles is growing rapidly.

[0003] However, with the increasing number of electric vehicles, the safety issues of power batteries have gradually become prominent. Among them, power batteries are prone to thermal runaway under conditions such as overcharging, over-discharging, physical damage or internal failure, and in just a few seconds, they can cause electric vehicles to catch fire or explode. Due to the very short reaction time, the escape of drivers and passengers is greatly restricted, resulting in property damage and casualties. If the abnormal state of the power battery can be detected before thermal runaway, and timely and effective measures can be taken to intervene, the occurrence of power battery fires can be avoided. At present, the risk of thermal runaway of power batteries in electric vehicles has not been completely resolved. Therefore, it is particularly important to identify and predict thermal runaway of power batteries in a timely manner. Summary of the invention

[0004] In view of the above situation, it is necessary to provide a new energy vehicle power battery thermal runaway monitoring method and system to address the problem of how to timely identify and predict power battery thermal runaway problems.

[0005] A method for monitoring thermal runaway of a power battery of a new energy vehicle is applied to a thermal runaway monitoring system of a power battery of a new energy vehicle. The monitoring system includes an on-board terminal and a cloud currently wirelessly connected to the on-board terminal. The method includes:

[0006] The vehicle terminal obtains data of multiple evaluation parameters in real time, performs filtering, and uploads the data to the cloud. The multiple evaluation parameters include the battery voltage, operating current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle.

[0007] The cloud predicts whether the power battery has a tendency to catch fire through digital twin technology;

[0008] If a fire tendency is predicted, a control instruction is sent to the vehicle-mounted terminal so that the vehicle-mounted terminal controls the output of the power battery;

[0009] If no fire trend is predicted, the cloud detects whether the data of each evaluation parameter is within a normal range;

[0010] If the data of any of the evaluation parameters is not within the normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery;

[0011] If the data of each of the evaluation parameters are within the normal range, the cloud sends a processing instruction to the vehicle terminal;

[0012] When the vehicle-mounted terminal receives the processing instruction, the data of the evaluation parameter is linked to the historical data for analysis, and when the analysis result is abnormal, the output of the power battery is controlled.

[0013] Furthermore, in the above-mentioned method for monitoring thermal runaway of power batteries for new energy vehicles, the step of predicting whether the power battery has a fire tendency by using digital twin technology in the cloud includes:

[0014] The cloud estimates the next evaluation parameter data by using the Lagrange interpolation method according to the currently acquired evaluation parameter data and the last acquired evaluation parameter data;

[0015] The difference between the estimated evaluation parameter data and the standard data is calculated, and when the difference exceeds a threshold, it is determined that the power battery has a fire tendency.

[0016] Furthermore, in the above-mentioned method for monitoring thermal runaway of a power battery of a new energy vehicle, the step of linking and analyzing the data of the evaluation parameters with historical data comprises:

[0017] Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data;

[0018] If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged;

[0019] If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged;

[0020] The data values ​​of the evaluation parameters are standardized, and the standardization formula is:

[0021] S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively;

[0022] Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score;

[0023] An analysis result is determined according to the status score.

[0024] Furthermore, the above-mentioned method for monitoring thermal runaway of a power battery of a new energy vehicle further comprises:

[0025] When the cloud predicts a fire trend, or detects that the data of any of the evaluation parameters is not within a normal range, the cloud sends an early warning to the user terminal;

[0026] Or when the analysis result is abnormal, the vehicle-mounted terminal sends an early warning to the user terminal.

[0027] Furthermore, in the above-mentioned method for monitoring thermal runaway of a power battery of a new energy vehicle, the step of filtering the data of the evaluation parameters by the vehicle terminal comprises:

[0028] After the battery voltage is subjected to RC low-pass filtering, it is subjected to code average filtering;

[0029] The working current, ambient temperature, ambient smoke concentration, and battery pack pressure are subjected to mean filtering.

[0030] The present invention also discloses a new energy vehicle power battery thermal runaway monitoring system, the monitoring system comprising a vehicle-mounted terminal and a cloud currently wirelessly connected to the vehicle-mounted terminal.

[0031] The vehicle terminal is used to obtain data of multiple evaluation parameters in real time, and upload them to the cloud after filtering. The multiple evaluation parameters include the battery voltage, operating current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle;

[0032] The cloud is used to predict whether the power battery has a fire tendency through the digital twin technology. If a fire tendency is predicted, a control instruction is sent to the vehicle terminal so that the vehicle terminal controls the output of the power battery. If a fire tendency is not predicted, the cloud detects whether the data of each evaluation parameter is within a normal range; if the data of any evaluation parameter is not within a normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery; if the data of each evaluation parameter is within a normal range, the cloud sends a processing instruction to the vehicle terminal;

[0033] The vehicle-mounted terminal is used to perform linkage analysis on the data of the evaluation parameters and historical data when receiving the processing instruction, and to control the output of the power battery when the analysis result is abnormal.

[0034] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the step of predicting whether the power battery has a fire tendency by using the digital twin technology in the cloud includes:

[0035] The cloud estimates the next evaluation parameter data by using the Lagrange interpolation method according to the currently acquired evaluation parameter data and the last acquired evaluation parameter data;

[0036] The difference between the estimated evaluation parameter data and the standard data is calculated, and when the difference exceeds a threshold, it is determined that the power battery has a fire tendency.

[0037] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the cloud is also used to send an early warning to the user terminal when a fire trend is predicted or the data of any of the evaluation parameters is detected to be out of a normal range;

[0038] The vehicle-mounted terminal is also used to send an early warning to the user terminal when the analysis result is abnormal.

[0039] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the step of linking the data of the evaluation parameters with the historical data for analysis comprises:

[0040] Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data;

[0041] If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged;

[0042] If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged;

[0043] The data values ​​of the evaluation parameters are standardized, and the standardization formula is:

[0044] S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively;

[0045] Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score;

[0046] An analysis result is determined according to the status score.

[0047] The present invention collects, integrates, analyzes and mines data of all electric vehicles connected to the cloud, and provides functions such as real-time monitoring, data analysis, safety warning, data storage, rescue guidance, maintenance plan formulation, and battery tracking. By performing digital twins and data comparison in the cloud and data processing locally, the battery status is predicted and the current status is judged, and timely preventive measures are taken to reduce the probability of system failure to adapt to various situations. The invention can effectively monitor potential safety hazards of batteries, extend battery life, and increase the chance of safe escape, showing a high degree of practicality and credibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a method for monitoring thermal runaway of a power battery for a new energy vehicle provided by the first embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of RC filtering;

[0050] Figure 3 This is a structural block diagram of a new energy vehicle power battery thermal runaway monitoring system provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0051] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0052] These and other aspects of the embodiments of the present invention will become clear with reference to the following description and drawings. In these descriptions and drawings, some specific implementations of the embodiments of the present invention are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present invention, but it should be understood that the scope of the embodiments of the present invention is not limited thereto. On the contrary, the embodiments of the present invention include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0053] See also Figure 1 , is a new energy vehicle power battery thermal runaway monitoring method in an embodiment of the present invention, which is applied to a new energy vehicle power battery thermal runaway monitoring system, the monitoring system comprising a vehicle-mounted terminal and a cloud currently wirelessly connected to the vehicle-mounted terminal. The method comprises steps S11 to S17.

[0054] In step S11, the vehicle terminal obtains data of multiple evaluation parameters in real time, performs filtering, and uploads the data to the cloud. The multiple evaluation parameters include the battery voltage, operating current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle.

[0055] Specifically, the vehicle is equipped with multiple sensors, such as voltage sensors, current sensors, temperature sensors, smoke sensors, pressure sensors, etc., which are all electrically connected to the vehicle terminal in a wireless or wired manner. The vehicle terminal obtains data of each evaluation parameter in real time and performs filtering processing.

[0056] In order to obtain accurate battery voltage, an RC low-pass filter is used in vehicle hardware design to filter the voltage signal. Figure 2 As shown, the VCCBAT of the positive electrode of the battery passes through the resistor R1, flows out from the resistor R1 and then flows out in parallel with the capacitor C1. The voltage flowing out at this time is VOUT. In order to enable it to be collected by the sensor, a voltage divider resistor R2 is added between R1 and VOUT, and it is connected in parallel with C1. At this time, VOUT is connected to the microcontroller, and the real voltage collected at the sensor end is Vreal. In order to obtain more accurate voltage parameters, a microcontroller with an adc acquisition accuracy of 12 bits is selected, and the voltage conversion formula is Vreal=VOUT×3.35×64.4+4096.0, where 3.35 and 64.4 are proportional parameters obtained by testing, and 4096 is a parameter determined according to the acquisition accuracy. After the battery voltage data is filtered by RC low-pass filtering, the peaks in the data can be well filtered out.

[0057] Perform mean filtering on the battery voltage data after RC low-pass filtering, as well as the operating current, ambient temperature, ambient smoke concentration, and battery pack pressure. Set the queue length to 5, that is, collect each data five times, and then divide it by 5 to return the value. At this time, the names of the returned data are set as follows:

[0058] dvoltage returns voltage;

[0059] dcurrent returns current;

[0060] dthermal returns temperature;

[0061] dpressure returns the pressure;

[0062] dfumes returns the smoke density;

[0063] Set the data collection value to: data.

[0064] By changing the evaluation parameters of the function in the code, different data values ​​can be collected. The working logic is:

[0065] Define the acquisition function. The function is implemented by collecting and accumulating data five times, averaging them, and returning the averaged value.

[0066] Set the variable name of each acquisition parameter;

[0067] Input the corresponding acquisition pins of the corresponding variables into the function;

[0068] Get the corresponding value and pass it to the corresponding variable.

[0069] In step S12, the cloud predicts whether the power battery has a tendency to catch fire through digital twin technology.

[0070] Step S13: If a fire tendency is predicted, a control instruction is sent to the vehicle-mounted terminal so that the vehicle-mounted terminal controls the output of the power battery.

[0071] Deploy a client on the cloud server that synchronizes and updates data with the local vehicle terminal, assign the local data of the vehicle terminal to the server, and deploy code on the cloud to realize the judgment of future trends. Select the data of the previous two times to predict the next trend. Specifically, the cloud uses the Lagrange interpolation method to estimate the next evaluation parameter data based on the current evaluation parameter data and the evaluation parameter data obtained last time. The formula is:

[0072]

[0073] b = y1-x1·k;

[0074] y3=k·x1+b;

[0075] Among them, k is the slope, b is the intercept, y1 is the data of the evaluation parameter obtained last time, x1 is the time of the evaluation parameter obtained last time, y2 is the data value of the current evaluation parameter, x2 is the current time, and y3 is the data of the evaluation parameter to be estimated next time.

[0076] By calculating, y3 is obtained as the data value for the next prediction, and it is compared with the standard data. If the data exceeds the normal threshold, the output of the battery is controlled, and a warning can be sent to the user terminal, and the location is reported, and finally the data is stored. It can be understood that controlling the battery output can be to convert the DC power of the power battery into a lower AC power, thereby limiting the motor output, or directly outputting the voltage and current to 0, that is, turning off the power supply.

[0077] Step S14: If no fire trend is predicted, the cloud detects whether the data of each evaluation parameter is within a normal range.

[0078] Step S15: If the data of any of the evaluation parameters is not within a normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery.

[0079] Step S16: If the data of each of the evaluation parameters are within the normal range, the cloud sends a processing instruction to the vehicle terminal.

[0080] The cloud first deploys the normal range of each evaluation parameter data of the battery. When receiving the filtered data from the vehicle terminal, it compares whether each parameter is within the normal range. If the data is not within the normal range, a warning is sent and the battery output is controlled; if it is within the normal range, the next data is compared and a processing instruction is sent to the vehicle terminal.

[0081] Step S17, when the vehicle-mounted terminal receives the processing instruction, the data of the evaluation parameter is linked to the historical data for analysis, and when the analysis result is abnormal, the output of the power battery is controlled.

[0082] Specifically, in one implementation of the present invention, the step of linking the evaluation parameter data with the historical data includes:

[0083] Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data;

[0084] If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged;

[0085] If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged;

[0086] The data values ​​of the evaluation parameters are standardized, and the standardization formula is:

[0087] S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively;

[0088] Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score;

[0089] An analysis result is determined according to the status score.

[0090] In this embodiment, the maximum and minimum values ​​of the historical data of each evaluation parameter are first refreshed. This process is to compare the current data value of the evaluation parameter with the historical maximum and minimum values. If the current data value is less than the historical minimum value of the evaluation parameter, the minimum value of the historical data of the evaluation parameter is replaced with the current data value. If the current data value is greater than the historical maximum value, the maximum value of the historical data of the evaluation parameter is replaced with the current data value. The formula expression is:

[0091] if data<datamin,datamin=data,

[0092] if data>datamax, datamax=data.

[0093] Each evaluation parameter has a different impact on the battery status, so a weight needs to be assigned to each evaluation parameter. Based on expert experience, the following weights are determined:

[0094] The weight k of the battery voltage voltage =0.25; working current weight k current =0.20; weight of ambient temperature k thermal =0.15; weight of ambient smoke concentration k fumes =0.20; battery pack pressure k pressure =0.20.

[0095] The weight is multiplied by the standardized data of the corresponding evaluation parameter and then added to obtain the status score. The analysis result is determined according to the status score. For example, if the status score is > 0.8, it means that the battery status is abnormal.

[0096] The thermal runaway monitoring method for power batteries of new energy vehicles of this embodiment first collects five factors of the vehicle's battery voltage, working current, ambient temperature, ambient smoke concentration, and battery pack pressure in real time. Then, the battery voltage is subjected to hardware RC filtering and code average filtering respectively, and the four factors of working current, ambient temperature, ambient smoke concentration, and battery pack pressure are subjected to code average filtering, and then the local data is uploaded to the cloud. Then, early warning processing is performed, wherein the early warning processing has three levels of execution steps: the first level of execution step is digital twin, which predicts whether there is a fire trend in the future through digital twin, and if so, sends a signal to the vehicle terminal to control the output of the power battery. If it is predicted that there is no fire trend in the future, proceed to the second level of execution step. The second level of execution step is data comparison in the cloud. If the cloud determines that the data of each evaluation parameter is not within the normal range, a signal is sent to the vehicle terminal to control the output of the power battery. If the cloud determines that the data of each evaluation parameter is within the normal range, the third level of execution step is performed. The third level of execution step is local data processing, which links the data of the evaluation parameter with the historical data for analysis, and when the analysis result is abnormal, the output of the power battery is controlled. This strategy can effectively monitor potential safety hazards of batteries, extend battery life, and increase the chance of safe escape, demonstrating high practicality and credibility.

[0097] See also Figure 3 , is a new energy vehicle power battery thermal runaway monitoring system in the second embodiment of the present invention, the monitoring system includes a vehicle terminal 21, and a cloud 22 currently wirelessly connected to the vehicle terminal 21,

[0098] The vehicle terminal 21 is used to obtain data of multiple evaluation parameters in real time, and upload them to the cloud after filtering. The multiple evaluation parameters include the battery voltage, working current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle;

[0099] The cloud 22 is used to predict whether the power battery has a fire tendency through the digital twin technology. If a fire tendency is predicted, a control instruction is sent to the vehicle terminal so that the vehicle terminal controls the output of the power battery. If a fire tendency is not predicted, the cloud detects whether the data of each evaluation parameter is within a normal range; if the data of any evaluation parameter is not within a normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery; if the data of each evaluation parameter is within a normal range, the cloud sends a processing instruction to the vehicle terminal;

[0100] The vehicle-mounted terminal 21 is used to perform linkage analysis on the data of the evaluation parameters and historical data when receiving the processing instruction, and control the output of the power battery when the analysis result is abnormal.

[0101] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the step of predicting whether the power battery has a fire tendency by using the digital twin technology in the cloud includes:

[0102] The cloud estimates the next evaluation parameter data by using the Lagrange interpolation method according to the currently acquired evaluation parameter data and the last acquired evaluation parameter data;

[0103] The difference between the estimated evaluation parameter data and the standard data is calculated, and when the difference exceeds a threshold, it is determined that the power battery has a fire tendency.

[0104] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the cloud is also used to send an early warning to the user terminal when a fire trend is predicted or the data of any of the evaluation parameters is detected to be out of a normal range;

[0105] The vehicle-mounted terminal is also used to send an early warning to the user terminal when the analysis result is abnormal.

[0106] Furthermore, in the above-mentioned new energy vehicle power battery thermal runaway monitoring system, the step of linking the data of the evaluation parameters with the historical data for analysis comprises:

[0107] Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data;

[0108] If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged;

[0109] If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged;

[0110] The data values ​​of the evaluation parameters are standardized, and the standardization formula is:

[0111] S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively;

[0112] Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score;

[0113] An analysis result is determined according to the status score.

[0114] The new energy vehicle power battery thermal runaway monitoring system provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0115] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system or device (such as a computer-based system, a system including a processor, or other system that can obtain instructions from an instruction execution system or device and execute instructions), or in conjunction with such instruction execution systems or devices. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system or device, or in conjunction with such instruction execution systems or devices.

[0116] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0117] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0118] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0119] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for monitoring thermal runaway of a power battery of a new energy vehicle, applied to a thermal runaway monitoring system of a power battery of a new energy vehicle, wherein the monitoring system comprises an on-board terminal and a cloud currently wirelessly connected to the on-board terminal, characterized in that: The method comprises: The vehicle terminal obtains data of multiple evaluation parameters in real time, performs filtering, and uploads the data to the cloud. The multiple evaluation parameters include the battery voltage, operating current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle. The cloud predicts whether the power battery has a tendency to catch fire through digital twin technology; If a fire tendency is predicted, a control instruction is sent to the vehicle-mounted terminal so that the vehicle-mounted terminal controls the output of the power battery; If no fire trend is predicted, the cloud detects whether the data of each evaluation parameter is within a normal range; If the data of any of the evaluation parameters is not within the normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery; If the data of each of the evaluation parameters are within the normal range, the cloud sends a processing instruction to the vehicle terminal; When the vehicle-mounted terminal receives the processing instruction, the data of the evaluation parameter is linked to the historical data for analysis, and when the analysis result is abnormal, the output of the power battery is controlled.

2. The method for monitoring thermal runaway of a power battery for a new energy vehicle according to claim 1, characterized in that: The steps of predicting whether the power battery has a fire tendency by using the digital twin technology in the cloud include: The cloud estimates the next evaluation parameter data by using the Lagrange interpolation method according to the currently acquired evaluation parameter data and the last acquired evaluation parameter data; The difference between the estimated evaluation parameter data and the standard data is calculated, and when the difference exceeds a threshold, it is determined that the power battery has a fire tendency.

3. The method for monitoring thermal runaway of a power battery for a new energy vehicle according to claim 1, characterized in that: The step of linking the evaluation parameter data with the historical data for analysis comprises: Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data; If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged; If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged; The data values ​​of the evaluation parameters are standardized, and the standardization formula is: S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively; Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score; An analysis result is determined according to the status score.

4. The method for monitoring thermal runaway of a power battery of a new energy vehicle according to claim 1, characterized in that: The method further comprises: When the cloud predicts a fire trend, or detects that the data of any of the evaluation parameters is not within a normal range, the cloud sends an early warning to the user terminal; Or when the analysis result is abnormal, the vehicle-mounted terminal sends an early warning to the user terminal.

5. The method for monitoring thermal runaway of a power battery for a new energy vehicle according to claim 1, characterized in that: The steps of filtering the data of the evaluation parameters by the vehicle terminal include: After the battery voltage is subjected to RC low-pass filtering, it is subjected to code average filtering; The working current, ambient temperature, ambient smoke concentration, and battery pack pressure are subjected to mean filtering.

6. A new energy vehicle power battery thermal runaway monitoring system, the monitoring system comprising a vehicle-mounted terminal and a cloud currently wirelessly connected to the vehicle-mounted terminal, characterized in that: The vehicle terminal is used to obtain data of multiple evaluation parameters in real time, and upload them to the cloud after filtering. The multiple evaluation parameters include the battery voltage, operating current, ambient temperature, ambient smoke concentration, and battery pack pressure of the vehicle; The cloud is used to predict whether the power battery has a fire tendency through the digital twin technology. If a fire tendency is predicted, a control instruction is sent to the vehicle terminal so that the vehicle terminal controls the output of the power battery. If a fire tendency is not predicted, the cloud detects whether the data of each evaluation parameter is within a normal range; if the data of any evaluation parameter is not within a normal range, the cloud sends a control instruction to the vehicle terminal so that the vehicle terminal controls the output of the power battery; if the data of each evaluation parameter is within a normal range, the cloud sends a processing instruction to the vehicle terminal; The vehicle-mounted terminal is used to perform linkage analysis on the data of the evaluation parameters and historical data when receiving the processing instruction, and to control the output of the power battery when the analysis result is abnormal.

7. The new energy vehicle power battery thermal runaway monitoring system according to claim 6, characterized in that: The steps of predicting whether the power battery has a fire tendency by using the digital twin technology in the cloud include: The cloud estimates the next evaluation parameter data by using the Lagrange interpolation method according to the currently acquired evaluation parameter data and the last acquired evaluation parameter data; The difference between the estimated evaluation parameter data and the standard data is calculated, and when the difference exceeds a threshold, it is determined that the power battery has a fire tendency.

8. The new energy vehicle power battery thermal runaway monitoring system according to claim 6, characterized in that: The cloud is also used to send an early warning to the user terminal when a fire trend is predicted or when it is detected that the data of any evaluation parameter is not within a normal range; The vehicle-mounted terminal is also used to send an early warning to the user terminal when the analysis result is abnormal.

9. The new energy vehicle power battery thermal runaway monitoring system according to claim 6, characterized in that: The step of linking the evaluation parameter data with the historical data for analysis comprises: Comparing the current data value of the evaluation parameter with the maximum and minimum values ​​of the historical data; If the current data value is smaller than the minimum value of the historical data, the current data value is assigned to the minimum value of the historical data, otherwise the minimum value of the historical data remains unchanged; If the current data value is greater than the maximum value of the historical data, the current data value is assigned to the maximum value of the historical data, otherwise the maximum value of the historical data remains unchanged; The data values ​​of the evaluation parameters are standardized, and the standardization formula is: S i is the standardized value, X i is the current data value of the evaluation parameter, min(X) and max(X) are the minimum and maximum values ​​of the historical data of the evaluation parameter respectively; Assign a weight to each of the evaluation parameters, and perform a weighted sum calculation on the weight and the corresponding standardized data value to obtain a status score; An analysis result is determined according to the status score.

Images