Thermal runaway warning method and system for charging cable of battery swapping station

Abstract

The present invention discloses a method and system for thermal runaway warning of a charging cable in a battery swapping station. Among them, the thermal runaway warning method includes: obtaining temperature data of temperature measurement points on the charging cable; extracting at least two temperature characteristics of the temperature measurement points from the temperature data; based on at least two temperature characteristics of the temperature measurement points, determining whether the temperature of the temperature measurement points is abnormal, so as to give a thermal runaway warning when the temperature of the temperature measurement points is abnormal. Since the abnormal temperature of the temperature measurement point can indicate the abnormal temperature of the local position corresponding to the temperature measurement point on the charging cable, and the abnormal temperature of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, the present invention can give a warning of the thermal runaway of the charging cable, thereby providing guidance such as the thermal runaway position for the timely maintenance and fault troubleshooting of the charging cable, being able to reduce the thermal runaway events occurring in the charging cables of the battery swapping station, and being able to achieve the balance between the performance and economic benefits of the battery swapping station.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method and system for thermal runaway warning of charging cables in a battery swapping station. Background Art

[0002] The charging cable in a battery swapping station is a medium for single - unit energy transmission of the station's cables and is an important infrastructure of the battery swapping station. The cable is composed of a core conductor, insulating material, and a protective layer. Due to the long - term current - carrying heat generation of the core conductor in the cable and the influence of factors such as electricity, machinery, and moisture, it is easy to cause the aging of the insulating material, resulting in the loss or reduction of its insulation performance and mechanical performance. Therefore, it is easy to cause breakdown and fire, and even combustion and fire occur in many places along the entire length of the cable, and even explosion accidents, thus bringing huge safety hazards and economic losses to the battery swapping station. However, currently, how to select reasonable indicators for safety monitoring of the charging cables in a battery swapping station is still a technical difficulty. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the defect in the prior art that it is difficult to select reasonable indicators for safety monitoring of the charging cables in a battery swapping station, and to provide a method and system for thermal runaway warning of the charging cables in a battery swapping station.

[0004] The present invention solves the above - mentioned technical problem through the following technical solutions:

[0005] A method for thermal runaway warning of a charging cable in a battery swapping station, the thermal runaway warning method comprising:

[0006] Obtaining temperature data of temperature measurement points on the charging cable;

[0007] Extracting at least two temperature characteristics of the temperature measurement points from the temperature data;

[0008] Based on at least two temperature characteristics of the temperature measurement points, determining whether the temperature of the temperature measurement points is abnormal, so as to give a thermal runaway warning when the temperature of the temperature measurement points is abnormal.

[0009] In this solution, at least two temperature characteristics of the temperature measurement points on the charging cable are selected as indicators for safety monitoring of the charging cable. Specifically, when it is determined that the temperature of the temperature measurement point is abnormal according to at least two temperature characteristics of the temperature measurement points on the charging cable, it can indicate that the temperature of the local position corresponding to the temperature measurement point on the charging cable is abnormal, and the temperature abnormality of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, this solution can give a warning of the thermal runaway of the charging cable, thereby providing guidance such as the location of thermal runaway for timely maintenance and fault troubleshooting of the charging cable, being able to reduce the thermal runaway events occurring in the charging cables of the battery swapping station, and being able to achieve a balance between the performance and economic benefits of the battery swapping station.

[0010] Preferably, the temperature data is real-time streaming temperature data, and extracting at least two temperature characteristic data of the temperature measurement point from the temperature data includes:

[0011] Extracting the temperature value characteristic, temperature rise characteristic, and temperature difference characteristic of the temperature measurement point from the real-time streaming temperature data.

[0012] In this solution, it is preferable to extract characteristic data such as temperature value characteristics, temperature rise characteristics, and temperature difference characteristics from the temperature data of the temperature measurement point for temperature anomaly identification. In this way, it is possible to judge whether the corresponding temperature measurement point has a temperature anomaly from multiple perspectives and levels of effective information such as the absolute value, absolute change value, and relative change value of the temperature at the temperature measurement point, which can improve the accuracy and effectiveness of temperature anomaly identification.

[0013] Preferably, the temperature value characteristic is the temperature value T of the temperature measurement point at the temperature acquisition moment t i ; i ;

[0014] The temperature rise characteristics include cumulative temperature rise characteristics and relative temperature rise change characteristics, where:

[0015] The cumulative temperature rise characteristic is the temperature rise amount T of the temperature value during the temperature acquisition time period t i -t j ; i -T j ;

[0016] The relative temperature rise change characteristic is:

[0017]

[0018] Wherein, when |T i-1 -T i-2 | < 1, let |T i-1 -T i-2 | = 1;

[0019] The temperature difference characteristic is Wherein, represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i ;

[0020] In this solution, the definitions of the temperature value characteristic, temperature rise characteristic, and temperature difference characteristic of the temperature measurement point are clarified, and among them, the temperature rise characteristic further includes cumulative temperature rise characteristics and relative temperature rise change characteristics, so that more effective information is extracted from the limited temperature data, thereby enabling more accurate judgment of whether the corresponding temperature measurement point has a temperature anomaly, and further enabling more accurate implementation of thermal runaway warning for the charging cable.

[0021] Preferably, judging whether the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement point to give a thermal runaway warning when the temperature of the temperature measurement point is abnormal, includes:

[0022] Judging whether the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement point and in combination with at least two anomaly detection models;

[0023] When the temperature of the temperature measurement point is abnormal, give a thermal runaway warning.

[0024] In this solution, it is preferable to combine at least two anomaly detection models to judge whether the temperature of the temperature measurement point is abnormal, avoiding the errors that may be brought by the identification of a single anomaly detection model and improving the accuracy of temperature anomaly identification.

[0025] Preferably, the number of the anomaly detection models is three and includes a one-class support vector machine (One-class SVM, non-Gaussian distribution); judging whether the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement point and in combination with at least two anomaly detection models, includes:

[0026] Taking at least two temperature characteristics of the temperature measurement point as a whole and inputting them into the three anomaly detection models respectively to obtain the anomaly recognition results output by each anomaly detection model;

[0027] When there are at least two anomaly recognition results indicating temperature abnormality and one of the anomaly recognition results indicating temperature abnormality is output from the one-class support vector machine, it is determined that the temperature of the temperature measurement point is abnormal.

[0028] In this solution, since experimental data shows that the one-class support vector machine is superior in judging whether the temperature of the temperature measurement point is abnormal, when selecting three anomaly detection models for judging whether the temperature of the temperature measurement point is abnormal, it is preferably to include the one-class support vector machine. In this way, when the majority of the three anomaly recognition results output by the three anomaly detection models indicate temperature abnormality and the anomaly recognition result output by the one-class support vector machine indicates temperature abnormality, it is determined that the temperature of the temperature measurement point is abnormal, which can more accurately judge whether the temperature of the temperature measurement point is abnormal, and thus can more accurately realize the thermal runaway warning of the charging cable.

[0029] Preferably, the giving a thermal runaway warning when the temperature of the temperature measurement point is abnormal, includes:

[0030] When the temperature of the temperature measurement point is abnormal, determining the abnormal type of the temperature measurement point according to the anomaly detection model based on which it is determined that the temperature of the temperature measurement point is abnormal;

[0031] Determining the warning type of the charging cable according to the abnormal type of the temperature measurement point and giving a warning.

[0032] In this solution, when it is determined that the temperature at the temperature measurement point is abnormal, the abnormal type of the temperature measurement point can be further determined to determine the alarm type of the charging cable, so that different handling measures can be adopted according to different alarm types, which is conducive to improving the handling efficiency of the thermal runaway of the charging cable. Among them, the abnormal type of the temperature measurement point is determined according to the abnormal detection model that determines the temperature abnormality of the temperature measurement point.

[0033] Preferably, the thermal runaway early warning method further includes:

[0034] Obtain the detection threshold corresponding to each of the temperature characteristics; the detection threshold is obtained according to the historical temperature data of the temperature measurement points on the charging cable;

[0035] After determining that the temperature at the temperature measurement point is abnormal based on the abnormal detection model, use the detection threshold to re-determine whether the temperature measurement point with abnormal temperature is actually abnormal;

[0036] When it is determined that the temperature at the temperature measurement point is abnormal using the detection threshold, it is determined that the temperature at the temperature measurement point is abnormal.

[0037] In this solution, when determining that the temperature at the temperature measurement point is abnormal based on the abnormal detection model, it is also possible to further determine whether the corresponding temperature characteristics are abnormal based on a preset detection threshold, so as to achieve a secondary judgment on whether the temperature at the temperature measurement point is abnormal, thereby being able to more accurately determine whether the temperature at the temperature measurement point is abnormal, and further being able to more accurately achieve the thermal runaway early warning of the charging cable.

[0038] A thermal runaway early warning system for a charging cable in a swapping station, the thermal runaway early warning system includes:

[0039] An acquisition module, configured to acquire the temperature data of the temperature measurement points on the charging cable;

[0040] An extraction module, configured to extract at least two temperature characteristics of the temperature measurement points from the temperature data;

[0041] An early warning module, configured to determine whether the temperature at the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement point, so as to perform thermal runaway early warning when the temperature at the temperature measurement point is abnormal.

[0042] In this solution, at least two temperature characteristics of the temperature measurement points on the charging cable are selected as the indicators for the safety monitoring of the charging cable. Specifically, when it is determined that the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement points on the charging cable, it can indicate that the temperature of the local position corresponding to the temperature measurement point on the charging cable is abnormal, and the temperature abnormality of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, this solution can give an early warning of the thermal runaway of the charging cable, thereby providing guidance such as the location of the thermal runaway for the timely maintenance and fault troubleshooting of the charging cable, reducing the thermal runaway events of the charging cables in the swapping station, and achieving the balance between the performance and economic benefits of the swapping station.

[0043] Preferably, the temperature data is real-time streaming temperature data, and the extraction module is specifically configured to extract the temperature value characteristic, the temperature rise characteristic, and the temperature difference characteristic of the temperature measurement point from the real-time streaming temperature data.

[0044] In this solution, it is preferable to extract characteristic data such as the temperature value characteristic, the temperature rise characteristic, and the temperature difference characteristic from the temperature data of the temperature measurement points for temperature abnormality identification. In this way, it is possible to judge whether the corresponding temperature measurement point is abnormally hot from multiple perspectives and levels of effective information such as the absolute value, the absolute change value, and the relative change value of the temperature of the temperature measurement point, which can improve the accuracy and effectiveness of temperature abnormality identification.

[0045] Preferably, the temperature value characteristic is the temperature value T of the temperature measurement point at the temperature acquisition moment t i ; i ;

[0046] The temperature rise characteristics include the cumulative temperature rise characteristic and the relative change characteristic of the temperature rise, where:

[0047] The cumulative temperature rise characteristic is the temperature rise amount T of the temperature value during the temperature acquisition time period t i -t j ; i -T j ;

[0048] The relative change characteristic of the temperature rise is:

[0049]

[0050] where, when |T i-1 -T i-2 | < 1, let |T i-1 -T i-2 | = 1;

[0051] The temperature difference characteristic is where, represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i .

[0052] In this solution, the definitions of the temperature value characteristics, temperature rise characteristics, and temperature difference characteristics of the temperature measurement points are clarified. Among them, the temperature rise characteristics further include the cumulative temperature rise characteristics and the relative change characteristics of the temperature rise, so that more effective information is extracted from the limited temperature data, enabling more accurate judgment of whether the corresponding temperature measurement point has abnormal temperature, and further enabling more accurate realization of the thermal runaway warning for the charging cable.

[0053] Preferably, the warning module includes:

[0054] A judgment unit, configured to judge whether the temperature measurement point has abnormal temperature based on at least two temperature characteristics of the temperature measurement point and in combination with at least two anomaly detection models;

[0055] A warning unit, configured to perform a thermal runaway warning when the temperature of the temperature measurement point is abnormal.

[0056] In this solution, it is preferably to combine at least two anomaly detection models to judge whether the temperature measurement point has abnormal temperature, avoiding the errors that may be brought by the identification of a single anomaly detection model and improving the accuracy of temperature anomaly identification.

[0057] Preferably, the number of the anomaly detection models is three and includes a one-class support vector machine; the judgment unit is specifically configured to:

[0058] Take at least two temperature characteristics of the temperature measurement point as a whole and input them into the three anomaly detection models respectively, and obtain the anomaly identification results output by each of the anomaly detection models;

[0059] When there are at least two anomaly identification results indicating abnormal temperature and one of the anomaly identification results indicating abnormal temperature is output from the one-class support vector machine, it is determined that the temperature of the temperature measurement point is abnormal.

[0060] In this solution, since experimental data shows that the one-class support vector machine performs better in judging whether the temperature measurement point has abnormal temperature, when selecting three anomaly detection models for judging whether the temperature measurement point has abnormal temperature, it is preferably to include the one-class support vector machine. In this way, when the majority of the three anomaly identification results output by the three anomaly detection models indicate abnormal temperature and the anomaly identification result output by the one-class support vector machine indicates abnormal temperature, it is determined that the temperature of the temperature measurement point is abnormal, and the thermal runaway warning for the charging cable can be realized more accurately.

[0061] Preferably, the warning unit is specifically configured to:

[0062] When the temperature of the temperature measurement point is abnormal, determine the abnormal type of the temperature measurement point according to the anomaly detection model based on which it is determined that the temperature of the temperature measurement point is abnormal;

[0063] Determine the alarm type of the charging cable according to the abnormal type of the temperature measurement point and give an alarm.

[0064] In this solution, when it is determined that the temperature of the temperature measurement point is abnormal, the abnormal type of the temperature measurement point can be further determined to determine the alarm type of the charging cable, so that different processing measures can be adopted according to different alarm types, which is beneficial to improving the processing efficiency of the thermal runaway of the charging cable. Among them, the abnormal type of the temperature measurement point is determined according to the abnormal detection model that determines the temperature abnormality of the temperature measurement point.

[0065] Preferably, the judging unit is specifically further configured to:

[0066] Obtain the detection threshold corresponding to each temperature feature; the detection threshold is obtained according to the historical temperature data of the temperature measurement points on the charging cable;

[0067] After it is determined based on the abnormal detection model that the temperature of the temperature measurement point is abnormal, use the detection threshold to secondarily determine whether the temperature measurement point with abnormal temperature is actually abnormal;

[0068] When it is determined using the detection threshold that the temperature of the temperature measurement point is abnormal, determine that the temperature of the temperature measurement point is abnormal.

[0069] In this solution, when it is determined based on the abnormal detection model that the temperature of the temperature measurement point is abnormal, it is also possible to further determine whether the corresponding temperature feature is abnormal based on a preset detection threshold to implement a secondary determination of whether the temperature measurement point is abnormal, so as to be able to more accurately determine whether the temperature measurement point is abnormal, and further be able to more accurately achieve the thermal runaway warning of the charging cable.

[0070] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements any one of the above thermal runaway warning methods for the charging cable of the swapping station.

[0071] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, it implements the steps of any one of the above thermal runaway warning methods for the charging cable of the swapping station.

[0072] The positive and progressive effects of the present invention are as follows: In the present invention, at least two temperature characteristics of the temperature measurement points on the charging cable are selected as the indicators for the safety monitoring of the charging cable. Specifically, when it is determined that the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement points on the charging cable, it can indicate that the temperature of the local position corresponding to the temperature measurement point on the charging cable is abnormal, and the temperature abnormality of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, the present invention can give an early warning of the thermal runaway of the charging cable, thereby providing guidance such as the location of the thermal runaway for the timely maintenance and fault troubleshooting of the charging cable, being able to reduce the thermal runaway events occurring in the charging cables of the battery swapping station, and being able to achieve the balance between the performance and economic benefits of the battery swapping station. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 FIG. is a flowchart of a method for early warning of thermal runaway of a charging cable of a battery swapping station according to Embodiment 1 of the present invention.

[0074] Figure 2 FIG. is a flowchart of step S3 in the method for early warning of thermal runaway of a charging cable of a battery swapping station according to Embodiment 1 of the present invention.

[0075] Figure 3 FIG. is a schematic diagram of modules of a system for early warning of thermal runaway of a charging cable of a battery swapping station according to Embodiment 2 of the present invention.

[0076] Figure 4 FIG. is a schematic structural diagram of an electronic device according to Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0077] The present invention will be further described below by way of embodiments, but the present invention is not limited to the scope of the described embodiments.

[0078] Embodiment 1

[0079] This embodiment provides a method for early warning of thermal runaway of a charging cable of a battery swapping station. Referring to Figure 1 , the method for early warning of thermal runaway in this embodiment includes:

[0080] S1. Obtain the temperature data of the temperature measurement points on the charging cable;

[0081] S2. Extract at least two temperature characteristics of the temperature measurement points from the temperature data;

[0082] S3. Based on at least two temperature characteristics of the temperature measurement points, determine whether the temperature of the temperature measurement point is abnormal to give an early warning of thermal runaway when the temperature of the temperature measurement point is abnormal.

[0083] In this embodiment, the temperature data of the temperature measurement points on the charging cable can be collected by using optical fibers arranged on the surface of the charging cable, and the temperature data is preferably real-time streaming temperature data based on a time series.

[0084] In a specific embodiment, the temperature data is shown in the following table and includes collection time, station number, temperature measurement point location, temperature information, etc. Among them, the specific values in Table 1 are for illustrative purposes only and do not constitute a limitation.

[0085] Table 1:

[0086]

[0087] In this embodiment, it is preferred to first perform data cleaning on the collected temperature data, and then extract at least two temperature characteristics of the temperature measurement points from the temperature data after data cleaning. Among them, the rules for data cleaning may include, for example, deleting error data outside the fiber optic collection range to convert temperature data that may have quality defects into temperature data that meets quality requirements.

[0088] In one embodiment, there may be a large number of temperature measurement points on the charging cable. When it is determined that the temperature of a single temperature measurement point is abnormal, a thermal runaway warning can be issued. In other embodiments, a thermal runaway warning may also be issued when it is determined that the temperatures of multiple temperature measurement points are all abnormal.

[0089] In this embodiment, at least two temperature characteristics of the temperature measurement points on the charging cable are selected as indicators for safety monitoring of the charging cable. Specifically, when it is determined that the temperature of a temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement points on the charging cable, it can indicate that the temperature of the local position corresponding to the temperature measurement point on the charging cable is abnormal, and the temperature abnormality of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, this embodiment can issue a warning for the thermal runaway of the charging cable, thereby providing guidance such as the thermal runaway location for the timely maintenance and fault troubleshooting of the charging cable, being able to reduce the thermal runaway events occurring in the charging cables of the battery swapping station, and being able to achieve a balance between the performance and economic benefits of the battery swapping station.

[0090] In this embodiment, it is preferable to extract feature data such as temperature value features, temperature rise features, and temperature difference features from real-time streaming data, and preferably use the extracted temperature value features, temperature rise features, and temperature difference features and other feature data for temperature anomaly recognition. In this way, it is possible to judge whether the corresponding temperature measurement point has a temperature anomaly from multiple perspectives and levels of effective information such as the absolute value, absolute change value, and relative change value of the temperature at the temperature measurement point, which can improve the accuracy and effectiveness of temperature anomaly recognition. That is, in this embodiment, it is preferable to use the three complementary temperature features of the temperature value feature, temperature rise feature, and temperature difference feature of the temperature measurement point on the charging cable as indicators for safety monitoring of the charging cable, so as to more comprehensively cover all scenarios of temperature change before thermal runaway of the charging cable, and further improve the accuracy of thermal runaway warning for the charging cable. Based on this, step S2 in this embodiment preferably includes the steps of extracting the temperature value feature, temperature rise feature, and temperature difference feature of the temperature measurement point from the real-time streaming temperature data.

[0091] Specifically, in this embodiment, the temperature value feature is the temperature value T of the temperature measurement point at the temperature acquisition moment t i . i .

[0092] Specifically, in this embodiment, the temperature rise feature preferably includes an accumulated temperature rise feature and a relative change feature of the temperature rise. Among them, the accumulated temperature rise feature is the temperature rise amount T of the temperature value during the temperature acquisition time period t i -t j , and the relative change feature of the temperature rise is: i -T j , where when |T

[0093]

[0094] -T i-1 -T i-2 |<1, let |T i-1 -T i-2 | = 1.

[0095] Specifically, in this embodiment, the temperature difference feature is preferably set as , where represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i .

[0096] In this embodiment, the definitions of the temperature value feature, temperature rise feature, and temperature difference feature of the temperature measurement point are clarified, and among them, the temperature rise feature further includes an accumulated temperature rise feature and a relative change feature of the temperature rise, so that more effective information is extracted from the limited temperature data, thereby enabling more accurate judgment of whether the corresponding temperature measurement point has a temperature anomaly, and further enabling more accurate realization of thermal runaway warning for the charging cable.

[0097] Refer toFigure 2 , in this embodiment, step S3 may further include:

[0098] S31. Based on at least two temperature characteristics of the temperature measurement point and in combination with at least two anomaly detection models, determine whether the temperature of the temperature measurement point is abnormal;

[0099] S32. When the temperature of the temperature measurement point is abnormal, give a thermal runaway warning.

[0100] In this embodiment, it is preferred to combine at least two anomaly detection models to determine whether the temperature of the temperature measurement point is abnormal, so as to avoid the errors that may be brought by the identification of a single anomaly detection model and improve the accuracy of temperature anomaly identification. Specifically, at least two temperature characteristics of the temperature measurement point are taken as a whole and input into at least two trained anomaly detection models respectively, and the anomaly identification results output by each anomaly detection model are obtained. Furthermore, it is possible to determine whether the temperature of the temperature measurement point is abnormal according to the anomaly identification results corresponding to the at least two anomaly detection models output. Compared with relying only on a single anomaly detection model, it is possible to more accurately determine whether the corresponding temperature measurement point is abnormal, and thus it is possible to more accurately achieve the thermal runaway warning of the charging cable. In addition, in this embodiment, it is preferred to set that only one thermal runaway warning is given within a preset time period to avoid the repetition and interference caused by frequent warnings.

[0101] In one embodiment, in the scenario of combining at least two anomaly detection models to determine whether the temperature of a single temperature measurement point is abnormal, it is determined that the temperature of the temperature measurement point is abnormal only when at least more than half of the anomaly detection models output anomaly identification results. In another embodiment, it is also determined that the temperature of the temperature measurement point is abnormal only when a specified anomaly detection model outputs an anomaly identification result.

[0102] Specifically, in one implementation, since experimental data shows that a one-class support vector machine has an advantage in determining whether the temperature of a temperature measurement point is abnormal, when selecting three anomaly detection models for determining whether the temperature of a temperature measurement point is abnormal, it is preferred to include a one-class support vector machine. The other two anomaly detection models can be selected, for example, EllipticEnvelope (anomaly point detection based on Gaussian probability density) and isolationForest (anomaly point detection based on ensemble learning method). Step S31 preferably includes the step of taking at least two temperature characteristics of the temperature measurement point as a whole and inputting them into the three anomaly detection models respectively to obtain the anomaly identification results output by each anomaly detection model, and the step of determining that the temperature of the temperature measurement point is abnormal when at least two anomaly identification results indicating temperature abnormality exist and one of the anomaly identification results indicating temperature abnormality is output from the one-class support vector machine.

[0103] In this embodiment, the experimental data show that a classification vector machine outperforms the other two anomaly detection models in determining whether the temperature at the temperature measurement point is abnormal. That is, in this embodiment, at least two anomaly detection models are not necessarily in exactly the same position, but can be in an incompletely equal position according to their respective detection effects. Therefore, this solution can more accurately determine whether the temperature at the temperature measurement point is abnormal, and thus can more accurately achieve the thermal runaway warning of the charging cable. However, it should be understood that this embodiment is not intended to limit the number of anomaly detection models to three, and is also not intended to limit the anomaly detection models to the above three types.

[0104] In this embodiment, the anomaly detection model is constructed using the historical temperature data of the temperature measurement points on the charging cable. Specifically, at least two temperature features extracted from the historical temperature data are used as a whole to construct at least two anomaly detection models. And because the actually occurring thermal runaway events are extremely rare compared to normal samples, that is, there may be one abnormal data among hundreds of millions of normal data, it is necessary to optimize and iterate the anomaly detection model by comparing the anomaly recognition results of the anomaly detection model with the actual situation.

[0105] In this embodiment, step S32 preferably includes the steps of determining the anomaly type of the temperature measurement point according to the anomaly detection model based on which the temperature of the temperature measurement point is determined to be abnormal when the temperature of the temperature measurement point is abnormal, and determining the alarm type of the charging cable according to the anomaly type of the temperature measurement point and giving an alarm.

[0106] In this embodiment, when it is determined that the temperature of the temperature measurement point is abnormal, the anomaly type of the temperature measurement point can be further determined to determine the alarm type of the charging cable, so that different processing measures can be adopted according to different alarm types, which is beneficial to improving the processing efficiency of the thermal runaway of the charging cable. Among them, the anomaly type of the temperature measurement point is determined corresponding to the anomaly detection model that determines that the temperature of the temperature measurement point is abnormal. For example, the anomaly type can be determined by referring to the numerical values of the decision function of each anomaly detection model. Among them, the higher the negative value of the numerical value, the higher the corresponding anomaly level.

[0107] In this embodiment, the thermal runaway warning method may further include the following steps:

[0108] Obtain the detection thresholds corresponding to each temperature feature; the detection thresholds are obtained from the historical temperature data of the temperature measurement points on the charging cable;

[0109] After determining that the temperature of the temperature measurement point is abnormal based on the anomaly detection model, use the detection threshold to re-determine whether the temperature measurement point with abnormal temperature is actually abnormal;

[0110] When it is determined that the temperature of the temperature measurement point is abnormal using the detection threshold, determine that the temperature of the temperature measurement point is abnormal.

[0111] In this embodiment, the 3sigma principle can be used to determine the detection thresholds corresponding to each temperature characteristic of the charging cable in the normal state. Similarly, since the actually occurring thermal runaway events are extremely rare compared to normal samples, that is, there may be one abnormal data among hundreds of millions of normal data, it is necessary to optimize and iterate the detection thresholds by comparing the results obtained by using the detection thresholds with the actual situation.

[0112] Thus, when it is determined based on the anomaly detection model that the temperature of the temperature measurement point is abnormal in this embodiment, it is also possible to further determine whether the corresponding temperature characteristic is abnormal based on the preset detection threshold, so as to implement a secondary determination of whether the temperature of the temperature measurement point is abnormal, thereby being able to more accurately determine whether the temperature of the temperature measurement point is abnormal, and further being able to more accurately achieve the thermal runaway warning of the charging cable.

[0113] Embodiment 2

[0114] This embodiment provides a thermal runaway warning system for the charging cable of a battery swapping station. Referring to Figure 3 , the thermal runaway warning system of this embodiment includes:

[0115] An acquisition module 1, configured to acquire the temperature data of the temperature measurement points on the charging cable;

[0116] An extraction module 2, configured to extract at least two temperature characteristics of the temperature measurement points from the temperature data;

[0117] A warning module 3, configured to determine whether the temperature of the temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement point, so as to give a thermal runaway warning when the temperature of the temperature measurement point is abnormal.

[0118] In this embodiment, the optical fiber arranged on the surface of the charging cable can be used to collect the temperature data of the temperature measurement points on the charging cable, and the temperature data is preferably real-time streaming temperature data based on time series.

[0119] In a specific embodiment, the temperature data includes collection time, station number, temperature measurement point position, temperature information, etc. as shown in the following table. Among them, the specific values in Table 1 are for illustrative purposes and do not constitute a limitation.

[0120] Table 1:

[0121]

[0122]

[0123] In this embodiment, it is preferably to first perform data cleaning on the collected temperature data, and then extract at least two temperature characteristics of the temperature measurement points from the temperature data after data cleaning. Among them, the rules for data cleaning may include, for example, deleting error data outside the fiber optic acquisition range, so as to convert temperature data that may have quality defects into temperature data that meets quality requirements.

[0124] In one embodiment, there may be a large number of temperature measurement points on the charging cable. When it is determined that the temperature of a single temperature measurement point is abnormal, a thermal runaway warning can be issued. In other embodiments, a thermal runaway warning may also be issued when it is determined that the temperatures of multiple temperature measurement points are all abnormal.

[0125] In this embodiment, at least two temperature characteristics of the temperature measurement points on the charging cable are selected as indicators for safety monitoring of the charging cable. Specifically, when it is determined that the temperature of a temperature measurement point is abnormal based on at least two temperature characteristics of the temperature measurement points on the charging cable, it can indicate that the temperature of the local position corresponding to the temperature measurement point on the charging cable is abnormal, and the temperature abnormality of the local position on the charging cable often leads to the thermal runaway of the entire charging cable. Therefore, this embodiment can give a warning of the thermal runaway of the charging cable, thereby providing guidance such as the thermal runaway position for the timely maintenance and fault troubleshooting of the charging cable, being able to reduce the thermal runaway events of the charging cables in the swapping station, and being able to achieve the balance between the performance and economic benefits of the swapping station.

[0126] In this embodiment, it is preferably to extract characteristic data such as temperature value characteristics, temperature rise characteristics, and temperature difference characteristics from real-time streaming data, and preferably use the extracted temperature value characteristics, temperature rise characteristics, and temperature difference characteristics for temperature anomaly identification. In this way, it is possible to judge whether the corresponding temperature measurement point is abnormally hot from multiple angles and levels of effective information such as the absolute value, absolute change value, and relative change value of the temperature of the temperature measurement point, which can improve the accuracy and effectiveness of temperature anomaly identification. That is, this embodiment preferably selects the three mutually complementary temperature characteristics of the temperature value characteristic, temperature rise characteristic, and temperature difference characteristic of the temperature measurement points on the charging cable as indicators for safety monitoring of the charging cable, so as to more comprehensively cover all scenarios of temperature changes before the thermal runaway of the charging cable, and then improve the accuracy of the thermal runaway warning for the charging cable. Based on this, the extraction module 2 in this embodiment is preferably specifically configured to extract the temperature value characteristic, temperature rise characteristic, and temperature difference characteristic of the temperature measurement point from the real-time streaming temperature data.

[0127] Specifically, in this embodiment, the temperature value characteristic is the temperature value T of the temperature measurement point at the temperature acquisition moment t i i

[0128] Specifically, in this embodiment, the temperature rise characteristics preferably include cumulative temperature rise characteristics and relative change characteristics of temperature rise. Among them, the cumulative temperature rise characteristic is the temperature acquisition time period t​​i -t j Temperature increase amount T of i -T j , the relative change characteristic of temperature rise is:

[0129]

[0130] Among them, when |T i-1 -T i-2 | < 1, let |T i-1 -T i-2 | = 1.

[0131] Specifically, in this embodiment, the temperature difference characteristic is preferably set as Among them, represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i .

[0132] In this embodiment, the definitions of the temperature value characteristic, temperature rise characteristic, and temperature difference characteristic of the temperature measurement point are clarified. Among them, the temperature rise characteristic further includes the cumulative temperature rise characteristic and the relative change characteristic of temperature rise, so that more effective information is extracted from the limited temperature data, thereby enabling more accurate judgment of whether the corresponding temperature measurement point has abnormal temperature, and further enabling more accurate realization of the thermal runaway warning of the charging cable.

[0133] Referring to Figure 3 , in this embodiment, the warning module 3 may further include:

[0134] A judgment unit 31, configured to judge whether the temperature measurement point has abnormal temperature based on at least two temperature characteristics of the temperature measurement point and in combination with at least two anomaly detection models;

[0135] A warning unit 32, configured to perform a thermal runaway warning when the temperature of the temperature measurement point is abnormal.

[0136] In this embodiment, it is preferred to combine at least two anomaly detection models to judge whether the temperature measurement point has abnormal temperature, avoiding the errors that may be brought by the identification of a single anomaly detection model and improving the accuracy of temperature anomaly identification. Specifically, at least two temperature characteristics of the temperature measurement point are used as a whole and respectively input into at least two trained anomaly detection models to obtain the anomaly identification results output by each anomaly detection model. Furthermore, it is possible to judge whether the temperature measurement point has abnormal temperature according to the anomaly identification results corresponding to the at least two anomaly detection models. Compared with relying only on a single anomaly detection model, it is possible to more accurately judge whether the corresponding temperature measurement point has abnormal temperature, and thus more accurately realize the thermal runaway warning of the charging cable. In addition, in this embodiment, it is preferably set that only one thermal runaway warning is performed within a preset time period to avoid the repetition and interference caused by frequent warnings.

[0137] In one embodiment, in a scenario where at least two anomaly detection models are combined to determine whether the temperature of a single temperature measurement point is abnormal, it is determined that the temperature of the temperature measurement point is abnormal only when more than half of the anomaly detection models output abnormal recognition results. In another embodiment, it is also necessary for a specified anomaly detection model to output an abnormal recognition result before it is determined that the temperature of the temperature measurement point is abnormal.

[0138] Specifically, in one implementation, since experimental data shows that a one-class support vector machine has an advantage in determining whether the temperature of a temperature measurement point is abnormal, when selecting three anomaly detection models for determining whether the temperature of a temperature measurement point is abnormal, it is preferably to include a one-class support vector machine. The other two anomaly detection models can be, for example, EllipticEnvelope (anomaly point detection based on Gaussian probability density) and isolationForest (anomaly point detection based on ensemble learning methods). The determination unit 31 is preferably specifically configured to input at least two temperature features of the temperature measurement point as a whole into the three anomaly detection models respectively, obtain the abnormal recognition results output by each anomaly detection model, and determine that the temperature of the temperature measurement point is abnormal when at least two abnormal recognition results indicating temperature abnormality exist and one of the abnormal recognition results indicating temperature abnormality is output from the one-class support vector machine.

[0139] In this embodiment, experimental data shows that a one-class support vector machine has an advantage over the other two anomaly detection models in determining whether the temperature of a temperature measurement point is abnormal. That is, in this embodiment, at least two anomaly detection models are not necessarily in exactly the same position, but can be in an unequal position according to their respective detection effects. Therefore, this solution can more accurately determine whether the temperature of the temperature measurement point is abnormal, and thus can more accurately achieve the thermal runaway warning of the charging cable. However, it should be understood that this embodiment is not intended to limit the number of anomaly detection models to three, and is also not intended to limit the anomaly detection models to the above three types.

[0140] In this embodiment, the anomaly detection model is constructed using the historical temperature data of the temperature measurement points on the charging cable. Specifically, at least two temperature features extracted from the historical temperature data are used as a whole to construct at least two anomaly detection models. And because the actually occurring thermal runaway events are extremely rare compared to normal samples, that is, there may be one abnormal data among hundreds of millions of normal data, it is necessary to optimize and iterate the anomaly detection model by comparing the abnormal recognition results of the anomaly detection model with the actual situation.

[0141] In this embodiment, the warning unit 32 is preferably specifically configured to, when the temperature of the temperature measurement point is abnormal, determine the abnormal type of the temperature measurement point according to the anomaly detection model based on which the determination of the abnormal temperature of the temperature measurement point is made, and determine the warning type of the charging cable according to the abnormal type of the temperature measurement point and issue a warning.

[0142] In this embodiment, when it is determined that the temperature at the temperature measurement point is abnormal, the abnormal type of the temperature measurement point can be further determined to determine the alarm type of the charging cable, so that different processing measures can be adopted according to different alarm types, which is beneficial to improving the processing efficiency of the thermal runaway of the charging cable. Among them, the abnormal type of the temperature measurement point is determined according to the abnormal detection model that determines the temperature abnormality of the temperature measurement point. For example, the abnormal type can be determined by referring to the numerical values of the decision function of each abnormal detection model. Among them, the higher the abnormal level corresponding to the more negative numerical value.

[0143] In this embodiment, the judging unit 31 is specifically further configured to:

[0144] Obtain the detection thresholds corresponding to each temperature feature; the detection thresholds are obtained according to the historical temperature data of the temperature measurement points on the charging cable;

[0145] After it is determined based on the abnormal detection model that the temperature at the temperature measurement point is abnormal, use the detection threshold to re-determine whether the temperature measurement point with abnormal temperature is actually abnormal;

[0146] When it is determined by using the detection threshold that the temperature at the temperature measurement point is abnormal, it is determined that the temperature at the temperature measurement point is abnormal.

[0147] In this embodiment, the 3sigma principle can be used to determine the detection thresholds corresponding to each temperature feature of the charging cable in the normal state. Similarly, since the actually occurring thermal runaway events are extremely rare compared to the normal samples, that is, there may be one abnormal data among hundreds of millions of normal data, it is necessary to optimize and iterate the detection threshold by comparing the result obtained by using the detection threshold with the actual situation.

[0148] Thus, when it is determined in this embodiment based on the abnormal detection model that the temperature at the temperature measurement point is abnormal, it can further be determined whether the corresponding temperature feature is abnormal based on the preset detection threshold, so as to implement a secondary judgment on whether the temperature at the temperature measurement point is abnormal, thereby being able to more accurately determine whether the temperature at the temperature measurement point is abnormal, and further being able to more accurately achieve the thermal runaway warning of the charging cable.

[0149] Embodiment 3

[0150] This embodiment provides an electronic device, which can be presented in the form of a computing device (for example, it can be a server device), including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the thermal runaway warning method of the charging cable of the swapping station provided in Embodiment 1 can be implemented.

[0151] Figure 4 The hardware structure diagram of this embodiment is shown, as Figure 4As shown, the electronic device 9 specifically includes:

[0152] At least one processor 91, at least one memory 92, and a bus 93 for connecting different system components (including the processor 91 and the memory 92), where:

[0153] The bus 93 includes a data bus, an address bus, and a control bus.

[0154] The memory 92 includes volatile memory, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0155] The memory 92 further includes a program / utility 925 having a set (at least one) of program modules 924. Such program modules 924 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0156] The processor 91 executes various functional applications and data processing by running computer programs stored in the memory 92, such as the method for thermal runaway warning of the charging cable of the battery swapping station provided in Embodiment 1 of the present invention.

[0157] The electronic device 9 can further communicate with one or more external devices 94 (such as a keyboard, a pointing device, etc.). Such communication can be carried out through an input / output (I / O) interface 95. And, the electronic device 9 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 96. The network adapter 96 communicates with other modules of the electronic device 9 through the bus 93. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 9, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0158] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into being embodied by multiple units / modules.

[0159] Embodiment 4

[0160] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the steps of the method for predicting thermal runaway of the charging cable of the battery swapping station provided in Embodiment 1.

[0161] Among them, the readable storage medium can more specifically include, but is not limited to: portable disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0162] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps of implementing the method for predicting thermal runaway of the charging cable of the battery swapping station described in Embodiment 1.

[0163] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, executed as an independent software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0164] Although the specific implementation manners of the present invention have been described above, those skilled in the art should understand that this is only an example. The protection scope of the present invention is defined by the appended claims. Without departing from the principles and essence of the present invention, those skilled in the art can make various changes or modifications to these implementation manners, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for predicting thermal runaway of a charging cable in a battery swapping station, characterized in that, The thermal runaway warning method includes: Obtaining temperature data of the temperature measurement points on the charging cable; wherein, the temperature data is real-time streaming temperature data; Extracting the temperature value feature, temperature rise feature, and temperature difference feature of the temperature measurement points from the real-time streaming temperature data; The temperature value feature is the temperature value T of the temperature measurement point at the temperature acquisition moment t i i ;​ The temperature rise feature includes an accumulated temperature rise feature and a relative temperature rise change feature, where: The cumulative temperature rise characteristic is the temperature rise amount T i -t j of the temperature value in the temperature acquisition time period t i -T j ; The relative temperature rise change feature is: Wherein, when |T i-1 -T i-2 | < 1, let |T i-1 -T i-2 | = 1; The temperature difference feature is wherein represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i ; Based on at least two temperature features of the temperature measurement points and in combination with at least two anomaly detection models, determining whether the temperature of the temperature measurement points is abnormal, so as to give a thermal runaway warning when the temperature of the temperature measurement points is abnormal.

2. The thermal runaway warning method for the charging cable of the battery swapping station according to claim 1, characterized in that, The number of the anomaly detection models is three and includes a one-class support vector machine; the determining whether the temperature of the temperature measurement points is abnormal based on at least two temperature features of the temperature measurement points and in combination with at least two anomaly detection models includes: Taking at least two temperature features of the temperature measurement points as a whole and inputting them into the three anomaly detection models respectively to obtain the anomaly recognition results output by each of the anomaly detection models; When there are at least two anomaly recognition results indicating temperature abnormality and one of the anomaly recognition results indicating temperature abnormality is output from the one-class support vector machine, it is determined that the temperature of the temperature measurement points is abnormal.

3. The method for thermal runaway warning of the charging cable of the battery swapping station according to claim 2, wherein, The giving a thermal runaway warning when the temperature of the temperature measurement points is abnormal includes: When the temperature of the temperature measurement points is abnormal, determining the abnormal type of the temperature measurement points according to the anomaly detection model based on which it is determined that the temperature of the temperature measurement points is abnormal; Determining the alarm type of the charging cable according to the abnormal type of the temperature measurement points and giving an alarm.

4. The method for predicting thermal runaway of the charging cable of the battery swapping station according to claim 2, wherein, The thermal runaway warning method further includes: Obtaining the detection thresholds corresponding to the respective temperature features; the detection thresholds are obtained according to the historical temperature data of the temperature measurement points on the charging cable; After determining that the temperature of the temperature measurement points is abnormal based on the anomaly detection model, using the detection thresholds to re-determine whether the temperature measurement points with abnormal temperature are abnormal; When it is determined that the temperature of the temperature measurement points is abnormal by using the detection thresholds, it is determined that the temperature of the temperature measurement points is abnormal.

5. A thermal runaway early warning system for a charging cable of a battery swapping station, characterized in that, The thermal runaway warning system includes: An acquisition module for acquiring temperature data of the temperature measurement points on the charging cable; wherein, the temperature data is real-time streaming temperature data; an extraction module for extracting the temperature value feature, temperature rise feature, and temperature difference feature of the temperature measurement points from the real-time streaming temperature data; The temperature value feature is the temperature value T of the temperature measurement point at the temperature acquisition moment t i ; i ; The temperature rise feature includes an accumulated temperature rise feature and a relative temperature rise change feature, where: The cumulative temperature rise feature is the temperature rise amount T i -t j -T i -T j ; The relative temperature rise change feature is: Where, when |T i-1 -T i-2 | < 1, let |T i-1 -T i-2 | = 1; The temperature difference feature is wherein represents the average temperature of other temperature measurement points within a preset range near the temperature measurement point at the temperature acquisition moment t i ; A warning module for determining whether the temperature of the temperature measurement points is abnormal based on at least two temperature features of the temperature measurement points and in combination with at least two anomaly detection models, so as to give a thermal runaway warning when the temperature of the temperature measurement points is abnormal.

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the thermal runaway warning method for the charging cable of the battery swapping station according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the thermal runaway warning method for the charging cable of the battery swapping station according to any one of claims 1 to 4.

Images