Resonant inductor temperature early warning method and related device
By monitoring the relative temperature of the resonant inductor and the inlet temperature of the traction converter coolant and identifying anomalies, and using quantile regression and linear regression models, the problems of false alarms and missed alarms in the resonant inductor temperature monitoring were solved, and efficient and accurate temperature early warning was achieved.
Patent Information
- Application Number
- CN202511787208.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-03-03
AI Technical Summary
In existing technologies, temperature monitoring of the resonant inductor of high-speed trains relies on a fixed threshold, which leads to frequent false alarms and missed alarms, failing to meet the requirements of train operation safety and being unable to adapt to the influence of external temperature changes.
By performing consistency discrimination and aggregation processing on the temperature of the resonant inductor and the inlet temperature of the coolant on the four quadrant side of the traction converter, abnormal data points are identified. Quantile regression and linear regression models are used to determine the severity and duration of the anomalies, and corresponding thresholds are set for accurate early warning.
It enables precise monitoring of the temperature of the resonant inductor, reduces the influence of subjective human factors, lowers the risk of false alarms and missed alarms caused by changes in external temperature, and improves detection efficiency and accuracy.
Smart Images
Figure CN121600673A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of temperature monitoring technology, and in particular to a method and device for early warning of temperature using a resonant inductor. Background Technology
[0002] Resonant inductors in high-speed trains are inductive components used in the train's power system to achieve resonance in conjunction with capacitors. They are primarily used in voltage conversion, filtering, and energy regulation, with their core function being to optimize circuit performance through resonance. For example, in the traction converter of a high-speed train, the resonant inductor, together with the supporting capacitor, forms an LC resonant circuit. Its core function is to filter out the 100Hz harmonics generated in the single-phase rectification stage, thereby purifying the grid-side current and stabilizing the intermediate DC voltage. Currently, abnormal temperature monitoring is performed using fixed thresholds. This method relies on human perception and experience. While simple to implement and relatively stable, it is limited by human perception; the threshold judgment depends on subjective human assessment and cannot cover true anomalies. This significantly increases the likelihood of false alarms and missed alarms due to threshold influence, failing to meet the safety requirements of high-speed train operation. Summary of the Invention
[0003] In view of the above problems, this application provides a method and related device for early warning of resonant inductor temperature, so as to improve detection efficiency and accuracy. The specific solution is as follows:
[0004] The first aspect of this application provides a method for early warning of resonant inductor temperature, comprising:
[0005] Based on the reference temperature, the temperature of each resonant inductor during the train's operation is determined and aggregated to obtain a first aggregation time period and a second aggregation time period. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time period indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time period indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature.
[0006] According to the anomaly identification strategy, the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period are processed respectively to obtain first anomaly data and second anomaly data, as well as a first anomaly parameter value characterizing the severity and duration of the first anomaly data, and a second anomaly parameter value characterizing the severity and duration of the second anomaly data. The first anomaly data includes the temperature anomaly resonant inductor in the first aggregation time period, and the second anomaly data includes the temperature anomaly resonant inductor in the second aggregation time period.
[0007] Based on the first reference threshold and the second reference threshold, the first abnormal parameter value and the second abnormal parameter value are compared and processed respectively to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductors. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
[0008] In one possible implementation, the step of performing temperature consistency discrimination and aggregation processing on the temperatures of each resonant inductor during the train's movement based on a reference temperature to obtain a first aggregation time period and a second aggregation time period includes:
[0009] At each temperature acquisition time, the temperature of each resonant inductor is subtracted from the corresponding reference temperature to obtain the temperature rise value of each resonant inductor.
[0010] Based on the temperature rise value of each resonant inductor and the number of each resonant inductor, the temperature rise characteristic value of each resonant inductor is determined.
[0011] Based on the temperature rise characteristic value and characteristic threshold, each of the resonant inductors is aggregated to obtain the first aggregation time period and the second aggregation time period.
[0012] In one possible implementation, determining the temperature rise characteristic value of each of the resonant inductors based on the temperature rise value of each of the resonant inductors and the number of each of the resonant inductors includes:
[0013] For each of the resonant inductors, the temperature rise value is subtracted from the average value to obtain the temperature rise characteristic value. The average value is the quotient of the sum of temperature rise values and the target quantity. The sum of temperature rise values is the sum of the temperature rise values of the other resonant inductors besides the resonant inductor. The target quantity is the number of the other resonant inductors.
[0014] In one possible implementation, the step of processing the reference temperature and the temperature of each of the resonant inductors during the first aggregation time period according to the anomaly identification strategy to obtain first anomaly data and a first anomaly parameter value characterizing the severity and duration of the anomaly in the first anomaly data includes:
[0015] For each time window in the first aggregation time period, a second two-dimensional data point is determined based on each first two-dimensional data point and the number of each resonant inductor. Each first two-dimensional data point includes: a first average value and a second average value. The first average value is the average temperature of each resonant inductor in the time window, and the second average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0016] For each of the obtained second two-dimensional data points, the first outlier two-dimensional data points are determined based on the quantile regression model;
[0017] Based on the linear regression results and the first outlier two-dimensional data points, a first deviation value is determined. The linear regression results are the temperature values of the resonant inductor obtained by processing each of the second two-dimensional data points based on the linear regression model.
[0018] The first cumulative outlier duration is obtained by statistically analyzing each outlier two-dimensional data point within the statistical duration, and the first outlier mean value is determined based on the first deviation degree and the first cumulative outlier duration. The first deviation degree is obtained by summing each first deviation cumulative value, and each first deviation cumulative value is the product of the first deviation degree value and the collection interval duration.
[0019] In one possible implementation, the step of comparing the first abnormal parameter value according to a first reference threshold to determine whether the first abnormal point data is a temperature-abnormal resonant inductor includes:
[0020] If the first cumulative anomaly duration is greater than the first cumulative anomaly duration threshold, and the first outlier mean is greater than the first outlier mean threshold, then it is determined to be the temperature anomaly resonant inductor.
[0021] In one possible implementation, the step of processing the reference temperature and the temperature of each of the resonant inductors during the second aggregation time period according to the anomaly identification strategy to obtain second anomaly data and a second anomaly parameter value characterizing the severity and duration of the anomaly in the second anomaly data includes:
[0022] For each time window in the second aggregation period, a third two-dimensional data point is obtained based on the third average value and the fourth average value. The third average value is the average temperature of each resonant inductor in the time window, and the fourth average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0023] For each of the obtained third two-dimensional data points, the second outlier two-dimensional data points are determined based on the quantile regression model;
[0024] Based on the linear regression results and the second outlier two-dimensional data points, a second deviation value is determined. The linear regression results are the temperature values of the resonant inductor obtained by processing each of the third two-dimensional data points based on the linear regression model.
[0025] The second cumulative outlier duration is obtained by statistically analyzing each of the second outlier two-dimensional data points within the statistical duration. The second outlier mean is determined based on the second deviation degree and the second cumulative outlier duration. The second deviation degree is obtained by summing each second deviation cumulative value. Each second deviation cumulative value is the product of the second deviation degree value and the collection interval duration.
[0026] In one possible implementation, the step of comparing the second abnormal parameter value according to a second reference threshold to determine whether the second abnormal point data is a temperature-abnormal resonant inductor includes:
[0027] If the second cumulative anomaly duration is greater than the second cumulative anomaly duration threshold, and the second outlier mean is greater than the second outlier mean threshold, then it is determined to be the temperature anomaly resonant inductor.
[0028] A second aspect of this application provides a resonant inductor temperature warning device, comprising:
[0029] The time-segment aggregation module is used to perform temperature consistency judgment and aggregation processing on the temperature of each resonant inductor during the train's operation based on a reference temperature, to obtain a first aggregation time segment and a second aggregation time segment. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time segment indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time segment indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature.
[0030] An anomaly identification module is used to process the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period respectively, according to an anomaly identification strategy, to obtain first anomaly data and second anomaly data, as well as a first anomaly parameter value characterizing the severity and duration of the first anomaly data, and a second anomaly parameter value characterizing the severity and duration of the second anomaly data. The first anomaly data includes temperature-abnormal resonant inductors in the first aggregation time period, and the second anomaly data includes temperature-abnormal resonant inductors in the second aggregation time period; and...
[0031] An abnormal resonant inductance determination module is used to compare and process the first abnormal parameter value and the second abnormal parameter value according to a first reference threshold and a second reference threshold, respectively, to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductances. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
[0032] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the resonant inductor temperature warning method described in the first aspect or any implementation thereof.
[0033] A fourth aspect of this application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:
[0034] The memory is used to store computer programs;
[0035] The processor is used to execute the computer program so that the electronic device can implement the resonant inductor temperature warning method described in the first aspect or any implementation thereof.
[0036] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the resonant inductor temperature warning method described in the first aspect or any implementation thereof.
[0037] By employing the above technical solution, the resonant inductor temperature early warning method provided in this application can perform temperature consistency judgment and aggregation processing on the temperature of each resonant inductor during the train's operation based on a reference temperature, obtaining a first aggregation time period and a second aggregation time period. Then, according to an anomaly point identification strategy, the reference temperature and the temperature of each resonant inductor in the first and second aggregation time periods are processed respectively to obtain first and second anomaly point data. Finally, based on a first and second reference thresholds, the first and second anomaly parameter values are compared and processed to determine whether the first and second anomaly point data represent a temperature-abnormal resonant inductor, wherein the first reference threshold corresponds to the first anomaly parameter value, and the second reference threshold corresponds to the second anomaly parameter value. By using the relative temperature between the resonant inductor temperature and the traction converter's four-quadrant side coolant inlet temperature instead of the conventional absolute temperature value, and subsequently using this relative temperature for statistical analysis, the influence of subjective human factors is reduced, eliminating the need for threshold adjustments based on seasons and lowering the risk of false alarms and missed alarms caused by external temperature. Attached Figure Description
[0038] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.
[0039] Figure 1This application provides an architecture diagram of a resonant inductor temperature warning system.
[0040] Figure 2 A flowchart of a resonant inductor temperature early warning method provided in this application;
[0041] Figure 3 A diagram illustrating the process of determining abnormal temperature points provided in this application;
[0042] Figure 4 The temperature rise equivalent relationship diagram provided for this application;
[0043] Figure 5 The outlier deviation diagram provided for this application;
[0044] Figure 6 Another flowchart of a resonant inductor temperature early warning method provided in this application;
[0045] Figure 7 A structural diagram of a resonant inductor temperature warning device provided in this application;
[0046] Figure 8 This is a structural diagram of an electronic device provided in this application. Detailed Implementation
[0047] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.
[0048] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.
[0049] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.
[0050] See Figure 1 , Figure 1A schematic diagram of the architecture of a resonant inductor temperature warning system is shown. The system may include a temperature sensor 100 and a server 200.
[0051] Server 200 includes a bus, a processor, a communication interface, and memory. The processor, memory, and communication interface communicate with each other via the bus.
[0052] The memory can be used to store software code related to the resonant inductor temperature warning method, and the processor can execute the steps of the chip's resonant inductor temperature warning method, or schedule other units to achieve the corresponding functions.
[0053] Most current high-speed train anomaly monitoring models are fixed threshold models, which can be summarized as "under xxx conditions, when xxx value lasts for xxx minutes, it is an anomaly." These threshold models rely on human cognition and experience. These models only require a few minutes or even real-time data as input to determine if an anomaly exists. The triggering of these model thresholds is not necessarily related to anomalies in the resonant inductor itself: an increase in the temperature of the resonant inductor, besides being due to anomalies in itself (or its traction system), can also be caused by severe weather (freezing rain, etc.), which is the main focus of existing models.
[0054] Furthermore, the fixed threshold of existing resonant inductor anomaly monitoring models cannot fully characterize the seasonal variation of resonant inductor temperature. In other words, the resonant inductor temperature also fluctuates due to the influence of external temperature: as the external temperature rises, the temperature naturally increases in summer, making it easier to reach the threshold temperature and generate false alarms; in winter, due to the lower external temperature, the temperature is at a lower level and far from the fixed threshold, which may lead to missed alarms when there are real anomalies.
[0055] To address the aforementioned problems, this application provides a method for early warning of resonant inductor temperature. The method for early warning of resonant inductor temperature according to this application will be described in detail below with reference to the accompanying drawings.
[0056] Reference Figure 2 , Figure 2 This is a flowchart illustrating a resonant inductor temperature warning method provided in an embodiment of this application, as shown below. Figure 2 As shown in the embodiment of this application, a resonant inductor temperature warning method may include steps S201 to S203, which are described in detail below.
[0057] S201. Based on the reference temperature, the temperature of each resonant inductor during the train's operation is determined and aggregated to obtain a first aggregation time period and a second aggregation time period. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time period indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time period indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature.
[0058] Specifically, the reference temperature can be selected as either the outside temperature or the coolant inlet temperature on the four-quadrant side of the traction converter. In practical applications, using the outside temperature as the reference temperature results in significantly lower accuracy compared to using the coolant inlet temperature on the four-quadrant side of the traction converter. Furthermore, the coolant inlet temperature not only reflects the outside temperature but also indicates the operating status of the traction converter, potentially providing more comprehensive information about the train's operating conditions compared to the outside temperature.
[0059] Normally, resonant inductors are cooled by coolant and cooling fans, and their temperature should not exceed the coolant temperature by much. Conversely, if the temperature rise is too high, it may indicate a cooling system malfunction or abnormal heating of the resonant inductor itself, both of which fall within the scope of early warning. Furthermore, fault diagnosis of train components typically relies on comparing the mean and variance statistics of an individual component with the overall values of all components at a given time. This involves analyzing the difference between the maximum and mean values to determine if an anomaly has occurred. However, resonant inductors are only located within the traction converter of the train, and their number is relatively small compared to other train components. Directly comparing the temperature of an individual resonant inductor with the mean and other statistical values of all inductors at a given time is not statistically significant. On the other hand, the traction system is greatly affected by the train's operating conditions. For example, traction may be cut off during train operations, meaning some trains do not provide traction. In this case, the temperature of the resonant inductor in that train will not rise. Using statistical values in such situations may introduce significant errors. Therefore, fault diagnosis strategies for other components are not applicable to resonant inductors.
[0060] Because the relationship between the resonant inductor temperature and the reference temperature is inconsistent when the train is running and stopped, the latter being more complex (as it's difficult to determine whether the train is stopping at a station or has been idle for an extended period, increasing the model's complexity), combining both scenarios would be equivalent to superimposing multiple data points with different distributions, resulting in a rather disordered final result, which is detrimental to model construction. Therefore, data with speeds at least 1 km / h can be selected for subsequent analysis, i.e., the reference temperature and the temperatures of each resonant inductor can be collected during the train's movement.
[0061] Under normal circumstances, during the operation of a high-speed train, the temperatures of the resonant inductors are highly synchronized, trending in the same direction, and the degree of temperature rise should be roughly the same. However, by observing actual data, temperature rise differences exist between individual resonant inductors. Therefore, it is necessary to determine whether such differences exist between these individuals, classifying each moment into two categories: consistent and inconsistent temperature rises.
[0062] S202. According to the anomaly identification strategy, the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period are processed respectively to obtain the first anomaly data and the second anomaly data, as well as the first anomaly parameter value characterizing the severity and duration of the anomaly of the first anomaly data and the second anomaly parameter value characterizing the severity and duration of the anomaly of the second anomaly data. The first anomaly data includes the temperature anomaly resonant inductor in the first aggregation time period, and the second anomaly data includes the temperature anomaly resonant inductor in the second aggregation time period.
[0063] Specifically, after obtaining the aforementioned time periods of consistent and inconsistent temperature rises, considering the different data distributions for these cases (the latter being more prone to anomalies), separate models need to be constructed. Different anomaly identification strategies can be used to process the reference temperature and the temperature of each resonant inductor in the first and second aggregation time periods, respectively.
[0064] Finding the moments with higher temperature rises is equivalent to finding data points that are relatively high on the resonant inductor temperature y(t) - reference temperature x(t) plane. (Refer to...) Figure 3 As shown, from top to bottom, the first graph represents the resonant inductor temperature, the second is the reference temperature graph, the difference between the two is shown in the third graph, and the comparison between the two at the corresponding acquisition times is shown in the fourth graph (i.e., without considering the time dimension, only considering the two temperature pairs). It can be seen that the data points with larger vertical axis (difference) values in the difference graph correspond to the upper positions in the fourth graph. After conversion, the reference... Figure 4 As shown, data points with higher temperature rise correspond to Figure 4 Points that are in the upper middle and far from the data point cluster.
[0065] Each outlier and anomaly can be characterized by the degree of deviation, and its inherent attributes include the length of the corresponding time interval. This can be achieved by aggregating the initial screening anomalies for each natural day. For cases of consistent temperature rise, each train's situation per day is represented by a single data point: its time is the time of each initial screening anomaly, and its temperature deviation is the weighted average of the temperatures of each initial screening anomaly point according to the corresponding time. For cases of inconsistent temperature rise, the situation for each day and each resonant inductor can be represented by independent single data points, with a total of n data points per train, where n is the number of traction converters (resonant inductors). See details for further information. Figure 5 As shown, outlier severity and cumulative duration can be used as measures.
[0066] S203. Based on the first reference threshold and the second reference threshold, the first abnormal parameter value and the second abnormal parameter value are compared and processed respectively to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductors. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
[0067] Specifically, based on actual data anomalies, dual thresholds are set for temperature deviation and corresponding time. Both temperature (degree of outlier) and time (accumulated anomaly time) are considered together to obtain the final anomaly diagnosis. Specifically, data anomalies with consistent temperature rise indicate that all resonant inductors are synchronously abnormally temperature-rising within the corresponding time period; data anomalies with inconsistent temperature rise indicate that the traction converter of the corresponding carriage is malfunctioning during this period. The reason for setting the time accumulation threshold is mainly to filter out anomalies caused by factors other than the resonant inductors themselves, such as short-term temperature spikes. If, after averaging over a longer period, the temperature deviation threshold is still met, it indicates the existence of a trend-based (long-lasting) anomaly.
[0068] This resonant inductor temperature early warning method uses statistical data to determine abnormal temperature rises. The entire process relies entirely on objective temperature data, effectively reducing the influence of subjective human factors. It eliminates the need for frequent threshold adjustments based on the season, lowering the risk of false alarms and missed alarms caused by changes in external temperature.
[0069] In one embodiment, the above-mentioned temperature consistency determination and aggregation processing of the temperatures of each resonant inductor during the train's movement based on a reference temperature to obtain a first aggregation time period and a second aggregation time period may specifically include the following processing steps:
[0070] Step 11: At each temperature acquisition time, calculate the difference between the temperature of each resonant inductor and the corresponding reference temperature to obtain the temperature rise value of each resonant inductor.
[0071] Step 12: Determine the temperature rise characteristic value of each resonant inductor based on the temperature rise value of each resonant inductor and the number of each resonant inductor.
[0072] Step 13: Aggregate each resonant inductor according to each temperature rise characteristic value and characteristic threshold to obtain the first aggregation time period and the second aggregation time period.
[0073] Specifically, based on the temperature rise value of each resonant inductor and the number of resonant inductors, the temperature rise characteristic value of each resonant inductor is determined, which may include:
[0074] For each resonant inductor, the temperature rise value is subtracted from the average value to obtain the temperature rise characteristic value. The average value is the quotient of the sum of temperature rise values and the target quantity. The sum of temperature rise values is the sum of the temperature rise values of the other resonant inductors except the resonant inductor. The target quantity is the number of other resonant inductors.
[0075] Specifically, for each moment and the temperature of each resonant inductor and reference temperature (i.e., the temperature of the coolant inlet on the four-quadrant side of the traction converter). Calculate the temperature rise value ,in Numbering the resonant inductors, totaling indivual.
[0076] To quantitatively describe the similarity in temperature rise among different carriages, the characteristic value of each carriage's temperature rise can be defined as the difference between its temperature rise and the average temperature rise of the remaining carriages. Assume the... Temperature rise in the carriage The characteristic value is obtained by calculating the difference between the resonant inductor temperature and the coolant inlet temperature. ,in This represents the total number of resonant inductors. The eigenvalues corresponding to time points with consistent temperature rise are smaller, and vice versa. The eigenvalues for all train sets and all time points are sorted, and the eigenvalue at the 98th percentile is selected as the consistency threshold. The operating data is divided into two categories: consistent temperature rise (i.e., the maximum characteristic value at any given moment does not exceed this threshold) and inconsistent temperature rise. The characteristic values of each resonant inductor at each moment are used. :like The largest eigenvalue at time t Not exceeding the consistency threshold This means assuming that the temperature rise is uniform at any given moment. Each moment with uniform temperature rise is extracted and aggregated into a time period. Conversely, the remaining unaggregated moments are aggregated into time periods with inconsistent temperature rises.
[0077] It is understood that those skilled in the art can adjust the above-mentioned judgment thresholds as needed, and will not elaborate further here.
[0078] Accordingly, in some embodiments, under the condition of consistent temperature rise, the above-mentioned processing of the reference temperature and the temperature of each resonant inductor during the first aggregation time period according to the anomaly identification strategy to obtain first anomaly data and first anomaly parameter values characterizing the severity and duration of the anomaly of the first anomaly data may specifically include:
[0079] Step 21: For each time window in the first aggregation time period, determine the second two-dimensional data point based on the number of each first two-dimensional data point and each resonant inductor. Each first two-dimensional data point includes: a first average value and a second average value. The first average value is the average temperature of each resonant inductor in the time window, and the second average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0080] Step 22: For each of the obtained second two-dimensional data points, determine the first outlier two-dimensional data points based on the quantile regression model.
[0081] Step 23: Based on the linear regression results and the first outlier two-dimensional data points, determine the first deviation value. The linear regression result is the temperature value of the resonant inductor obtained by processing each second two-dimensional data point based on the linear regression model.
[0082] Step 24: Statistically analyze each outlier two-dimensional data point within the statistical time period to obtain the first cumulative outlier time period, and determine the first outlier mean value based on the first deviation degree and the first cumulative outlier time period. The first deviation degree is obtained by summing each first deviation cumulative value. Each first deviation cumulative value is the product of the first deviation degree value and the collection interval time.
[0083] Specifically, for time periods with uniform temperature rise, a fixed-length time window of W minutes is selected, and each time period is further refined. Time windows shorter than W are also counted as one. The reason for not using all data points in the time window selection is twofold: too many data points would significantly increase the time and space complexity of model construction; too few data points (e.g., directly averaging the entire time period) might bury potential anomalies. Therefore, a balance needs to be found between these two aspects, hence the fixed length. For example, for a 25-minute time period, if the time window length is 10 minutes, it will be divided into two 10-minute time windows and one 5-minute time window.
[0084] For the first aggregation time period (i.e., the time period with consistent temperature as described above), assuming that after the aggregation within the aforementioned window, there is a short time period of length 𝑊, which includes the temperature of the resonant inductor. and reference temperature If there are a total of n resonant inductors (where n = 1, 2, ..., n above), then the calculations are performed sequentially:
[0085] (1) Average inductor temperature:
[0086]
[0087] (2) Average reference temperature:
[0088]
[0089] (3) The average value of the 𝑛 resonant inductors is obtained:
[0090]
[0091] That is, the second two-dimensional data point.
[0092] It is understood that those skilled in the art can adjust and select the length of the above time window as needed, which will not be elaborated here.
[0093] Within each time window, the average temperature of each resonant inductor and the average temperature of the coolant in all four quadrants are taken. Then, the average value is calculated across all traction converters to obtain a two-dimensional data point. The plane containing this two-dimensional data point is composed of the resonant inductor temperature and the coolant inlet temperature.
[0094] Two models are introduced on a two-dimensional plane composed of "resonant inductor temperature - coolant inlet temperature": a quantile regression model and a linear regression model. The quantile regression model, corresponding to the aforementioned temperature rise conversion relationship, is used to filter out high-level outlier data points. This facilitates the accumulation of outlier durations in the subsequent daily accumulation step and better aligns with the initial goal of identifying excessively high resonant inductor temperature rises. The linear regression model measures the extent of the temperature rise, i.e., the degree of anomaly in the resonant inductor temperature. In other words, assuming the four-quadrant coolant inlet temperature is... The resonant inductor temperature is Then linear regression can be performed: .
[0095] A quantile regression model is used to separate the data points with the highest resonant inductor temperature; that is, data points with resonant inductor temperatures higher than the quantile regression results are considered as initial outliers. During prediction, the two-dimensional data points obtained within each time window are calculated. The temperature of the resonant inductor in the middle Has the coolant inlet temperature been exceeded? If the corresponding quantile regression result exceeds the threshold, it is initially identified as an outlier, and subsequent outlier aggregation is performed.
[0096] Based on the above preliminary screening results, for the first... In spatial terms, this point represents the degree of deviation of the temperature from the regression value. (i.e., the true value) Compared to regression values (difference); its own attributes include the length of the corresponding small time segment. These two pieces of information correspond precisely to the two factors that the model needs to consider: the degree of deviation. and cumulative duration .
[0097] On each natural day, the "initial screening anomalies" are aggregated. For cases with consistent temperature rise, the cumulative anomaly time for each vehicle group and each day is recorded. and degree of isolation After aggregation, for cases with consistent temperature rise, each train's situation each day is represented by a single data point: the time represents the time of each initial screening anomaly point, and the temperature deviation value is the weighted average of the temperatures of each initial screening anomaly point according to their corresponding time. Daily cumulative data can be found by referring to... Figure 5 As shown, the corresponding anomaly point is located in the upper right corner.
[0098] Finally, based on the data distribution, quantiles are calculated for the cumulative anomaly time and outlier degree. Combining this with the actual data anomaly situation, dual thresholds are set for temperature deviation and corresponding time. By considering both temperature (outlier degree) and time (anomaly cumulative time), the final anomaly diagnosis result is obtained. Specifically, data anomalies with consistent temperature rise indicate that all resonant inductors experience synchronous temperature rise anomalies within the time corresponding to this data. Specifically, if the first cumulative anomaly duration is greater than the first cumulative anomaly duration threshold, and the first outlier degree mean is greater than the first outlier degree mean threshold, then it is determined to be a temperature-abnormal resonant inductor.
[0099] Similarly, for cases of inconsistent temperature rise, the above-mentioned anomaly identification strategy is used to process the reference temperature and the temperature of each resonant inductor during the second aggregation time period to obtain second anomaly data, as well as second anomaly parameter values characterizing the severity and duration of the anomalies in the second anomaly data, including:
[0100] Step 31: For each time window in the second aggregation period, obtain each third two-dimensional data point based on the third average value and the fourth average value. The third average value is the average temperature of each resonant inductor in the time window, and the fourth average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0101] Step 32: For each of the obtained third two-dimensional data points, determine the second outlier two-dimensional data points based on the quantile regression model.
[0102] Step 33: Based on the linear regression results and the second outlier two-dimensional data points, determine the second deviation value. The linear regression results are the temperature values of the resonant inductor obtained by processing each third two-dimensional data point based on the linear regression model.
[0103] Step 34: Statistically analyze each second outlier two-dimensional data point within the statistical time period to obtain the second cumulative outlier time, and determine the second outlier mean value based on the second deviation degree and the second cumulative outlier time. The second deviation degree is obtained by summing each second deviation cumulative value. Each second deviation cumulative value is the product of the second deviation degree value and the collection interval time.
[0104] Specifically, unlike the case of consistent temperature rise, when the temperature rise is inconsistent, the average value of the resonant inductor temperature and the average value of the four-quadrant coolant temperature are taken within each time window, and each resonant inductor is considered independently to obtain n two-dimensional data points, where n is the number of traction converters (resonant inductors).
[0105] Accordingly, when aggregating data within each natural day, the situation of each day and each resonant inductor can be represented by an independent single data point. Each train corresponds to n data points, where n is the number of traction converters (resonant inductors). Finally, based on the data distribution, quantiles are calculated for the cumulative anomaly time and outlier degree, and dual thresholds for temperature deviation and corresponding time are set based on the actual data anomalies. During comparison, if the second cumulative anomaly duration is greater than the second cumulative anomaly duration threshold, and the second outlier degree mean is greater than the second outlier degree mean threshold, then it is identified as a temperature-abnormal resonant inductor. This indicates that the resonant inductor is abnormal during that period.
[0106] As a specific implementation of the above-mentioned resonant inductor temperature warning method, refer to Figure 6 As shown, the specific processing steps may include the following:
[0107] The vehicle's operating parameters were collected.
[0108] The train set is in operation based on the operating parameters;
[0109] Step S201 is executed to determine the consistency of temperature rise;
[0110] For periods of consistent temperature rise, the mean values are calculated within the time window and along the resonant inductance dimension. Then, quantile regression and linear regression models are used to identify outliers. The degree of anomaly (degree of deviation and duration) of outliers is accumulated daily, and an alert is issued when the accumulated result exceeds a threshold.
[0111] For cases of inconsistent temperature rise, for each resonant inductor, the mean values of the resonant inductance and reference temperature are calculated over a time window. Then, quantile regression and linear regression models are used to identify outliers. The degree of anomaly (degree of deviation and duration) of outliers is accumulated daily, and an alert is issued when the accumulated result exceeds a threshold.
[0112] The above describes a resonant inductor temperature warning method provided by the embodiments of this application. The following will describe the apparatus for performing the above-described resonant inductor temperature warning method.
[0113] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a resonant inductor temperature warning device provided in an embodiment of this application. Figure 7 As shown, the resonant inductor temperature warning device includes:
[0114] The time period aggregation module 701 is used to perform temperature consistency judgment and aggregation processing on the temperature of each resonant inductor during the train's operation based on the reference temperature, to obtain a first aggregation time period and a second aggregation time period. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time period indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time period indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature.
[0115] Anomaly identification module 702 is used to process the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period respectively, according to anomaly identification strategy, to obtain first anomaly data and second anomaly data, as well as a first anomaly parameter value characterizing the severity and duration of the anomaly in the first anomaly data, and a second anomaly parameter value characterizing the severity and duration of the anomaly in the second anomaly data. The first anomaly data includes temperature-abnormal resonant inductors in the first aggregation time period, and the second anomaly data includes temperature-abnormal resonant inductors in the second aggregation time period.
[0116] The abnormal resonant inductance determination module 703 is used to compare and process the first abnormal parameter value and the second abnormal parameter value according to the first reference threshold and the second reference threshold, respectively, to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductance. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
[0117] In one possible implementation, the time-segment aggregation module 701 performs temperature consistency determination and aggregation processing on the temperatures of each resonant inductor during the train's movement based on a reference temperature to obtain a first aggregated time segment and a second aggregated time segment, including:
[0118] At each temperature acquisition moment, the temperature of each resonant inductor is subtracted from the corresponding reference temperature to obtain the temperature rise value of each resonant inductor.
[0119] Based on the temperature rise value of each resonant inductor and the number of each resonant inductor, the temperature rise characteristic value of each resonant inductor is determined.
[0120] Based on each temperature rise characteristic value and characteristic threshold, each resonant inductor is aggregated to obtain the first aggregation time period and the second aggregation time period.
[0121] In one possible implementation, the process by which the time-segment aggregation module 701 determines the temperature rise characteristic value of each resonant inductor based on the temperature rise value of each resonant inductor and the number of each resonant inductor includes:
[0122] For each resonant inductor, the temperature rise value is subtracted from the average value to obtain the temperature rise characteristic value. The average value is the quotient of the sum of temperature rise values and the target quantity. The sum of temperature rise values is the sum of the temperature rise values of the other resonant inductors except the resonant inductor. The target quantity is the number of other resonant inductors.
[0123] In one possible implementation, the anomaly identification module 702 processes the reference temperature and the temperature of each resonant inductor during the first aggregation time period according to an anomaly identification strategy to obtain first anomaly data and a first anomaly parameter value characterizing the severity and duration of the anomaly in the first anomaly data, including:
[0124] For each time window in the first aggregation period, a second two-dimensional data point is determined based on the number of each first two-dimensional data point and each resonant inductor. Each first two-dimensional data point includes: a first average value and a second average value. The first average value is the average temperature of each resonant inductor in the time window, and the second average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0125] For each of the obtained second two-dimensional data points, the first outlier two-dimensional data points are determined based on the quantile regression model;
[0126] Based on the linear regression results and the first outlier two-dimensional data points, the first deviation value is determined. The linear regression result is the temperature value of the resonant inductor obtained by processing each second two-dimensional data point based on the linear regression model.
[0127] The first cumulative outlier duration is obtained by statistically analyzing each outlier two-dimensional data point within the statistical duration. The first outlier mean is determined based on the first deviation degree and the first cumulative outlier duration. The first deviation degree is obtained by summing each first deviation cumulative value. Each first deviation cumulative value is the product of the first deviation degree value and the collection interval duration.
[0128] In one possible implementation, the abnormal resonant inductance determination module 703 compares the first abnormal parameter value with a first reference threshold to determine whether the first abnormal point data is a temperature-abnormal resonant inductance, including:
[0129] If the first cumulative anomaly duration is greater than the first cumulative anomaly duration threshold, and the first outlier mean is greater than the first outlier mean threshold, then it is determined to be a temperature-abnormal resonant inductor.
[0130] In one possible implementation, the anomaly identification module 702 processes the reference temperature of the second aggregation time period and the temperature of each resonant inductor according to an anomaly identification strategy to obtain second anomaly data, and a second anomaly parameter value characterizing the severity and duration of the anomaly in the second anomaly data, including:
[0131] For each time window in the second aggregation period, the third two-dimensional data points are obtained based on the third average value and the fourth average value. The third average value is the average temperature of each resonant inductor in the time window, and the fourth average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window.
[0132] For each of the obtained third two-dimensional data points, the second outlier two-dimensional data points are determined based on the quantile regression model;
[0133] Based on the linear regression results and the second outlier two-dimensional data points, the second deviation value is determined. The linear regression result is the temperature value of the resonant inductor obtained by processing each third two-dimensional data point based on the linear regression model.
[0134] The second cumulative outlier duration is obtained by statistically analyzing each second outlier two-dimensional data point within the statistical time period. The second outlier mean value is determined based on the second deviation degree and the second cumulative outlier duration. The second deviation degree is obtained by summing each second deviation cumulative value. Each second deviation cumulative value is the product of the second deviation degree value and the collection interval duration.
[0135] In one possible implementation, the abnormal resonant inductance determination module 703 compares the second abnormal parameter value with a second reference threshold to determine whether the second abnormal point data is a temperature-abnormal resonant inductance, including:
[0136] If the second cumulative anomaly duration is greater than the second cumulative anomaly duration threshold, and the second outlier mean is greater than the second outlier mean threshold, then it is determined to be a temperature-abnormal resonant inductor.
[0137] This application also provides an electronic device in its embodiments. (See reference...) Figure 8The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0138] like Figure 8 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. When the electronic device is powered on, the RAM 803 also stores various programs and data required for the operation of the electronic device. The processing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0139] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, memory cards, hard drives, etc.; and communication devices 809. Communication device 809 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.
[0140] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the resonant inductor temperature warning methods provided in this application.
[0141] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the resonant inductor temperature warning methods provided in this application.
[0142] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.
[0143] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0144] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.
[0145] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).
Claims
1. A method for early warning of resonant inductor temperature, characterized in that, include: Based on the reference temperature, the temperature of each resonant inductor during the train's operation is determined and aggregated to obtain a first aggregation time period and a second aggregation time period. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time period indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time period indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature. According to the anomaly identification strategy, the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period are processed respectively to obtain first anomaly data and second anomaly data, as well as a first anomaly parameter value characterizing the severity and duration of the first anomaly data, and a second anomaly parameter value characterizing the severity and duration of the second anomaly data. The first anomaly data includes the temperature anomaly resonant inductor in the first aggregation time period, and the second anomaly data includes the temperature anomaly resonant inductor in the second aggregation time period. Based on the first reference threshold and the second reference threshold, the first abnormal parameter value and the second abnormal parameter value are compared and processed respectively to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductors. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
2. The resonant inductor temperature early warning method according to claim 1, characterized in that, The temperature consistency determination and aggregation processing of the temperatures of each resonant inductor during the train's movement, based on a reference temperature, yields a first aggregation time period and a second aggregation time period, including: At each temperature acquisition time, the temperature of each resonant inductor is subtracted from the corresponding reference temperature to obtain the temperature rise value of each resonant inductor. Based on the temperature rise value of each resonant inductor and the number of each resonant inductor, the temperature rise characteristic value of each resonant inductor is determined. Based on the temperature rise characteristic value and characteristic threshold, each of the resonant inductors is aggregated to obtain the first aggregation time period and the second aggregation time period.
3. The resonant inductor temperature early warning method according to claim 2, characterized in that, The step of determining the temperature rise characteristic value of each resonant inductor based on its temperature rise value and the number of resonant inductors includes: For each of the resonant inductors, the temperature rise value is subtracted from the average value to obtain the temperature rise characteristic value. The average value is the quotient of the sum of temperature rise values and the target quantity. The sum of temperature rise values is the sum of the temperature rise values of the other resonant inductors besides the resonant inductor. The target quantity is the number of the other resonant inductors.
4. The resonant inductor temperature early warning method according to claim 1, characterized in that, The step of processing the reference temperature and the temperature of each resonant inductor during the first aggregation time period according to the anomaly identification strategy to obtain first anomaly data and a first anomaly parameter value characterizing the severity and duration of the anomaly in the first anomaly data includes: For each time window in the first aggregation time period, a second two-dimensional data point is determined based on each first two-dimensional data point and the number of each resonant inductor. Each first two-dimensional data point includes: a first average value and a second average value. The first average value is the average temperature of each resonant inductor in the time window, and the second average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window. For each of the obtained second two-dimensional data points, the first outlier two-dimensional data points are determined based on the quantile regression model; Based on the linear regression results and the first outlier two-dimensional data points, a first deviation value is determined. The linear regression results are the temperature values of the resonant inductor obtained by processing each of the second two-dimensional data points based on the linear regression model. The first cumulative outlier duration is obtained by statistically analyzing each outlier two-dimensional data point within the statistical duration, and the first outlier mean value is determined based on the first deviation degree and the first cumulative outlier duration. The first deviation degree is obtained by summing each first deviation cumulative value, and each first deviation cumulative value is the product of the first deviation degree value and the collection interval duration.
5. The resonant inductor temperature early warning method according to claim 4, characterized in that, The step of comparing the first abnormal parameter value according to a first reference threshold to determine whether the first abnormal point data is a temperature-abnormal resonant inductor includes: If the first cumulative anomaly duration is greater than the first cumulative anomaly duration threshold, and the first outlier mean is greater than the first outlier mean threshold, then it is determined to be the temperature anomaly resonant inductor.
6. The resonant inductor temperature early warning method according to claim 1, characterized in that, The step of processing the reference temperature and the temperature of each resonant inductor during the second aggregation time period according to the anomaly identification strategy to obtain second anomaly data and second anomaly parameter values characterizing the severity and duration of the anomalies in the second anomaly data includes: For each time window in the second aggregation period, a third two-dimensional data point is obtained based on the third average value and the fourth average value. The third average value is the average temperature of each resonant inductor in the time window, and the fourth average value is the average temperature of the coolant inlet on the four quadrant side of each traction converter in the time window. For each of the obtained third two-dimensional data points, the second outlier two-dimensional data points are determined based on the quantile regression model; Based on the linear regression results and the second outlier two-dimensional data points, a second deviation value is determined. The linear regression results are the temperature values of the resonant inductor obtained by processing each of the third two-dimensional data points based on the linear regression model. The second cumulative outlier duration is obtained by statistically analyzing each of the second outlier two-dimensional data points within the statistical duration. The second outlier mean is determined based on the second deviation degree and the second cumulative outlier duration. The second deviation degree is obtained by summing each second deviation cumulative value. Each second deviation cumulative value is the product of the second deviation degree value and the collection interval duration.
7. The resonant inductor temperature early warning method according to claim 6, characterized in that, The step of comparing the second abnormal parameter value according to the second reference threshold to determine whether the second abnormal point data is a temperature-abnormal resonant inductor includes: If the second cumulative anomaly duration is greater than the second cumulative anomaly duration threshold, and the second outlier mean is greater than the second outlier mean threshold, then it is determined to be the temperature anomaly resonant inductor.
8. A resonant inductor temperature warning device, characterized in that, include: The time-segment aggregation module is used to perform temperature consistency judgment and aggregation processing on the temperature of each resonant inductor during the train's operation based on a reference temperature, to obtain a first aggregation time segment and a second aggregation time segment. The reference temperature includes at least the temperature of the coolant inlet on the four-quadrant side of the traction converter. The first aggregation time segment indicates that the temperature change of each resonant inductor is consistent with the trend of the reference temperature, while the second aggregation time segment indicates that the temperature change of each resonant inductor is not consistent with the trend of the reference temperature. An anomaly identification module is used to process the reference temperature and the temperature of each resonant inductor in the first aggregation time period and the second aggregation time period respectively, according to an anomaly identification strategy, to obtain first anomaly data and second anomaly data, as well as a first anomaly parameter value characterizing the severity and duration of the first anomaly data, and a second anomaly parameter value characterizing the severity and duration of the second anomaly data. The first anomaly data includes temperature-abnormal resonant inductors in the first aggregation time period, and the second anomaly data includes temperature-abnormal resonant inductors in the second aggregation time period; and... An abnormal resonant inductance determination module is used to compare and process the first abnormal parameter value and the second abnormal parameter value according to a first reference threshold and a second reference threshold, respectively, to determine whether the first abnormal point data and the second abnormal point data are temperature abnormal resonant inductances. The first reference threshold corresponds to the first abnormal parameter value, and the second reference threshold corresponds to the second abnormal parameter value.
9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the resonant inductor temperature warning method as described in any one of claims 1 to 7.
10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the resonant inductor temperature warning method as described in any one of claims 1 to 7.