Charging port charging abnormality warning method and vehicle

Abstract

This application provides a charging port charging anomaly early warning method and vehicle, applied in the field of charging port detection technology. The charging port connects to both a battery and a charging pile. The charging port charging anomaly early warning method includes: acquiring a sequence of thermal characteristic parameters during the charging process of the charging pile through the charging port; wherein the thermal characteristic parameter sequence includes parameters characterizing the temperature state of the charging port; acquiring a predicted temperature curve of the charging port based on the thermal characteristic parameter sequence, and determining whether the charging state of the charging port is abnormal based on the predicted temperature curve; if the charging state of the charging port is determined to be abnormal based on the predicted temperature curve, then classifying the anomaly and outputting an early warning signal characterizing the presence of a charging anomaly. Based on the above, by using thermal characteristic parameters related to the charging port temperature to predict future temperatures, charging anomalies can be detected, classified, and warned earlier, solving the problems of delayed warnings and the inability to identify and predict charging anomalies early, significantly improving safety.

Description

Technical Field

[0001] This application relates to the field of charging port detection technology, specifically to a charging port charging abnormality early warning method and vehicle. Background Technology

[0002] In the field of charging port detection technology, abnormal temperature rise at the connection between the charging port and the charging gun is one of the main causes of malfunctions and even safety accidents. To ensure the reliability and safety of the charging process, it is generally necessary to effectively monitor the status of the charging port.

[0003] To meet this need, related technologies monitor the charging port temperature in real time, triggering alarms or taking protective measures when the monitored temperature exceeds a preset safety threshold. These solutions are based on real-time temperature and static thresholds, focusing on reacting to and controlling abnormal temperature rise events that have occurred or are occurring at the charging port. However, they cannot predict abnormal temperature trends, making it difficult to detect potential faults in the charging port or charging gun in a timely manner, potentially leading to irreversible physical damage to the devices. In short, these charging port detection solutions suffer from problems such as delayed warnings, inability to identify and predict charging anomalies early, and inability to perform preventative maintenance. Summary of the Invention

[0004] In view of this, this application aims to provide a charging port charging anomaly early warning method and vehicle to solve the problems of delayed early warning in related technologies and the inability to identify and predict abnormal temperature rise trends in the early stage.

[0005] In a first aspect, this application provides a charging port abnormality early warning method, wherein the charging port is connected to a battery and a charging pile respectively, and the method includes: Obtain the thermal characteristic parameter sequence during the charging process of the charging pile through the charging port; wherein, the thermal characteristic parameter sequence includes parameters used to characterize the temperature state of the charging port; The predicted temperature curve of the charging port is obtained based on the thermal characteristic parameter sequence, and the charging status of the charging port is judged based on the predicted temperature curve. If the charging port is determined to be abnormal based on the predicted temperature curve, the abnormality is classified and an early warning signal is output to characterize the existence of a charging abnormality in the charging port. The warning signals include the types of abnormalities corresponding to charging abnormalities, such as poor contact, overcurrent, line fault, and heat dissipation blockage.

[0006] Optionally, the predicted temperature curve of the charging port is obtained based on the thermal characteristic parameter sequence, including: Input the thermal characteristic parameter sequence into the temperature prediction model to predict the temperature change within N time windows in the future, where N≥1; Output the predicted temperature curve for the next T seconds based on the prediction results, where T≥1.

[0007] Optionally, determining whether the charging state of the charging port is abnormal based on the predicted temperature curve includes: The remaining time for the charging port temperature to reach the warning temperature is determined based on the predicted temperature curve. If the remaining time is less than the first preset value, the charging port is determined to be in an abnormal charging state; wherein the first preset value is determined based on the time required for the charging port to reach the warning temperature under normal charging conditions.

[0008] Optionally, after outputting a warning signal to indicate a charging abnormality at the charging port, the method further includes: The anomaly type and the probability corresponding to the anomaly type are determined based on the thermal characteristic parameter sequence and the predicted temperature curve.

[0009] Optionally, the anomaly type and the probability corresponding to the anomaly type are determined based on the thermal characteristic parameter sequence and the predicted temperature curve, including: The thermal feature parameter sequence and the predicted temperature curve are input into the anomaly classification model to extract anomaly features; Classify anomalies based on their characteristics; Based on the classification results, output the anomaly type and the probability corresponding to the anomaly type.

[0010] Optionally, after obtaining the anomaly type and the probability corresponding to the anomaly type based on the thermal feature parameter sequence and the predicted temperature curve, the method further includes: The warning level for anomalies is determined based on the predicted temperature curve and the probability corresponding to the anomaly type.

[0011] Optionally, the warning level corresponding to the anomaly can be divided according to the probability of the predicted temperature curve and the anomaly type, including: The predicted temperature of the charging port within a preset time is obtained based on the predicted temperature curve. When the predicted temperature reaches the first threshold, the anomaly is classified as Level 1. When the predicted temperature reaches the second threshold, the anomaly is classified as level two. When the probability corresponding to the anomaly type is greater than the second preset value, but the predicted temperature is less than the third threshold, the anomaly level is classified as the third level. Among them, the first threshold is greater than the second threshold, the second threshold is greater than the third threshold, and the degree of danger represented by the first level, the second level and the third level decreases step by step.

[0012] Optionally, after outputting a warning signal to indicate a charging abnormality at the charging port, the method further includes: The charging strategy is dynamically adjusted based on the early warning signal; wherein the dynamic adjustment charging strategy includes at least one of reducing the charging current of the battery during the charging process and shutting off the charging process. The warning signals, anomalies, anomaly types, and the corresponding probabilities of anomaly types are uploaded to the cloud server to establish a health record for the charging port.

[0013] Optionally, the sequence of thermal characteristic parameters of the charging port during the battery charging process is obtained, including: The charging current of the battery during the charging process, the stage identifier of the charging port during the charging process, and the temperature sequence are obtained; wherein, the stage identifier indicates that the charging port is at least in one of the constant current charging stage and the trickle charging stage, and the temperature sequence includes multiple temperature values ​​of the charging port collected at a fixed frequency during the charging process. The temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity at the charging port are calculated based on the temperature sequence. The charging current, stage identifier, temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity are fused together to obtain a sequence of thermal characteristic parameters.

[0014] Secondly, this application provides a vehicle, including: Charging port; Power battery, connected to charging port; A charging controller, connected to a power battery, is configured to execute the charging port charging abnormality early warning method described in the first aspect above.

[0015] Based on the above, the charging port charging anomaly early warning method provided in this application includes obtaining a predicted temperature curve of the charging port based on the thermal characteristic parameter sequence during the charging process of the charging pile through the charging port. When the charging port's charging state is determined to be abnormal based on the predicted temperature curve, the anomaly is classified and an early warning signal is output. Therefore, by using thermal characteristic parameters related to the charging port temperature to predict future temperatures, charging anomalies can be detected, classified, and warned of earlier, solving the problems of delayed warnings and the inability to identify and predict charging anomalies early, thus significantly improving safety. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the charging system provided in the embodiments of this application.

[0018] Figure 2 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this application embodiment.

[0019] Figure 3 This is provided by the embodiments of this disclosure. Figure 2 A flowchart of step S21.

[0020] Figure 4 This is provided by the embodiments of this disclosure. Figure 2 A flowchart illustrating step S22.

[0021] Figure 5 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this embodiment.

[0022] Figure 6 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this embodiment.

[0023] Figure 7 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this embodiment.

[0024] Figure 8 This is a schematic diagram of a vehicle provided in an embodiment of this disclosure. Detailed Implementation

[0025] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0026] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0027] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0029] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0030] Currently, to ensure the safety of electric vehicle charging, the commonly used technical solution is to monitor the charging port temperature in real time and compare it with a safety threshold to trigger safety controls. This involves deploying a temperature sensor on the charging port or charging gun to collect temperature data at a fixed frequency and compare it with one or more static thresholds. The comparison result triggers control commands, such as reducing the charging current or completely shutting down the charging process. However, this type of solution cannot predict abnormal trends in temperature changes, making it difficult to detect potential faults in the charging port or charging gun in a timely manner, which can easily lead to irreversible physical damage to the devices.

[0031] For example, in the case of progressive faults caused by contact point oxidation or foreign object intrusion leading to decreased heat dissipation efficiency, the charging port temperature may not exceed the safety threshold for a considerable period, but its temperature rise rate and pattern have deviated from the normal state. Related technologies cannot identify this early deviation; an alarm is only triggered when the fault accumulates to the point where the temperature eventually exceeds the threshold. At this point, the charging port or connector may have already suffered irreversible physical damage, and the user can only passively accept replacement.

[0032] The embodiments provided in this application introduce an analysis method based on artificial intelligence models to dynamically model and predictively analyze the thermal characteristic parameter sequences continuously collected during the charging process. This effectively enables early identification and risk warning of potential abnormalities in the charging port without affecting its ability to provide immediate protection against deterministic over-temperature events, thereby solving the problem that related technologies cannot detect charging abnormalities before the temperature reaches the dangerous threshold.

[0033] First, let's describe a typical implementation environment. Figure 1 This is a schematic diagram of a charging system to which the charging port charging abnormality early warning method provided in this application embodiment is applied. The charging system 100 includes: a charging port 110, a battery management system 120, a battery 130, a controller 140, and a communication module 150.

[0034] The charging port 110 is connected to the charging gun 160 and installed on the electric vehicle. It includes terminals that correspond one-to-one with the terminals of the charging gun 160 (such as DC+ and DC-), and a temperature sensor (not shown) is arranged at or near the terminal. The battery management system 120 is connected to the battery 130 and the charging port 110 and is used to manage the charging process of the battery 130. The controller 140 is connected to the controller of the charging pile 170, the battery management system 120 and each temperature sensor via a communication bus. It is used to receive data and perform analysis, decision-making and control logic. The communication module 150 is used to establish a data connection with the cloud server 190.

[0035] The charging gun 160 integrates multiple terminals (such as DC+ and DC-) for electrical connection at its end (gun head), and a temperature sensor (not shown) is arranged at or near the terminal. The charging pile 170 includes a power conversion unit 171 (not shown) and a communication control unit 172 (not shown). The input end of the charging pile 170 is electrically connected to the power grid 180 to provide AC or DC power. The output end of the charging pile 170 is connected to the charging gun 160 to convert the AC power from the power grid 180 into DC power to supply the battery 130.

[0036] Figure 2 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this application embodiment. The charging port charging anomaly early warning method provided in this application embodiment can be applied to... Figure 1 The charging system 100 has a charging port 110 that connects to the battery 130 and the charging pile 170, respectively. The method includes: Step S21: Obtain the sequence of thermal characteristic parameters during the charging process of the charging pile through the charging port.

[0037] The thermal characteristic parameter sequence includes parameters used to characterize the temperature state of the charging port 110.

[0038] In one embodiment, the thermal characteristic parameter sequence refers to a set of parameters that can characterize the temperature change of the charging port 110 over time, and is used to reflect the thermal behavior pattern during the charging process. For example, it may include, but is not limited to: the original temperature time series composed of timestamps and temperature values, the derived parameter sequence obtained by mathematical transformation (such as calculating difference, integration, fitting) of the original sequence, such as the temperature rise rate sequence, the temperature rise acceleration sequence, etc., or a combination of these parameters. The sequence must have continuity or quasi-continuity in the time dimension to reflect the process characteristics of thermal behavior.

[0039] In one implementation, the thermal characteristic parameter sequence can be obtained by converting the analog signal from the temperature sensor into digital values ​​using an analog-to-digital converter (ADC), followed by filtering and calculations of features such as temperature rise rate and acceleration performed by a digital signal processor (DSP) or controller 140. In another implementation, the filtering and calculation functions are entirely implemented by the firmware running on controller 140 through mathematical operation functions. The two methods can be used independently or in combination; for example, digitization can be performed by an ADC, and feature fusion can be performed by controller 140 through software.

[0040] Figure 3 This is provided by the embodiments of this disclosure. Figure 2 A flowchart of step S21 is shown in a preferred embodiment. Figure 3 Step S21 includes: Step S211: Obtain the charging current of the battery during the charging process, the stage identifier of the charging port during the charging process, and the temperature sequence.

[0041] The stage identifier indicates that the charging port 110 is at least in one of the constant current charging stage or the trickle charging stage, and the temperature sequence includes multiple temperature values ​​collected by the charging port 110 at a fixed frequency during the charging process.

[0042] In one embodiment, the charging current is acquired at a high sampling rate, for example, it can be set to sample once every 100 milliseconds or once every 10 milliseconds. By setting the high sampling rate, transient changes in current caused by sudden changes in contact state, load switching or power fluctuations during the charging process can be captured.

[0043] In one embodiment, the charging current is obtained in ways including but not limited to: obtaining it through the high-voltage sampling circuit of the battery management system 120, obtaining it through the power module output terminal of the controller of the charging pile 170, obtaining it through a current sensor connected in series in the charging circuit, or any combination of the above methods. For example, current data can be obtained simultaneously from both the battery management system 120 and the charging pile 170, and the difference between the two can be compared by cross-validation. If the difference is less than a preset tolerance, the average value is taken as the final value.

[0044] In one embodiment, the temperature sequence generally refers to a set of discrete temperature measurements collected from the charging port 110 at fixed time intervals and arranged in chronological order. For example, it can be a time sequence of temperature values ​​collected by one or more temperature sensors (e.g., installed at the DC+ and DC- terminals of the charging port 110, respectively) at a fixed sampling frequency (e.g., once every 100 milliseconds or once per second).

[0045] In one embodiment, the stage identifier generally refers to a data tag used to characterize the state or control stage of the charging process at the current moment. It is typically generated by the battery management system 120 based on a comprehensive judgment of the charging protocol, battery voltage, current, and temperature, and includes, but is not limited to, constant current charging stage, constant voltage charging stage, and trickle charging stage. Because the current magnitude, voltage level, and heat dissipation conditions differ significantly under different charging stages, their corresponding normal thermal behavior models also exhibit different dynamic characteristics. For example, in the constant current charging stage, the current remains constant, and the temperature rise rate of the charging port 110 is mainly affected by contact resistance and heat dissipation conditions, with the temperature showing an approximately linear upward trend; while in the trickle charging stage, the current decreases significantly, heat generation decreases, and the temperature of the charging port 110 may tend to stabilize or decrease slowly.

[0046] Step S212: Calculate the temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity at the charging port based on the temperature sequence.

[0047] In one embodiment, the system calculates derived features based on the temperature sequence, including but not limited to: the rate of temperature rise reflecting the speed of temperature change, the acceleration of temperature rise reflecting the drastic change in the rate of temperature rise, the total temperature rise reflecting the total temperature rise value from the start of charging to the current moment, and the temperature rise per unit of electricity reflecting the temperature rise contribution value of the charging port 110 when charging a unit of electrical energy (e.g., 1 kWh) into the battery 130.

[0048] Step S213: The charging current, stage identifier, temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity are fused to obtain a thermal characteristic parameter sequence.

[0049] In one embodiment, fusion processing generally refers to the calculation process of generating a unified, high-information-density thermal feature parameter sequence by taking multiple heterogeneous raw or primary processing parameters related to the temperature state of the charging port 110 through a series of structured data integration and transformation steps.

[0050] In some embodiments, the system performs time-stamp alignment, filtering, normalization, and other fusion processing on the above-mentioned multidimensional heterogeneous data, namely charging current, stage identifier, temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity, to form a unified multidimensional thermal characteristic parameter sequence that can be synchronized in time.

[0051] Based on the above method, multiple dimensions of information reflecting the thermal characteristics of the charging port 110 can be comprehensively reflected, thereby more comprehensively reflecting the real-time thermal state of the charging port 110 under complex working conditions. This enables subsequent steps to more accurately separate abnormal modes caused by different reasons such as poor contact and heat dissipation blockage from normal thermal behavior, significantly improving the accuracy and robustness of early warning.

[0052] Step S22: Obtain the predicted temperature curve of the charging port based on the thermal characteristic parameter sequence, and determine whether the charging state of the charging port is abnormal based on the predicted temperature curve.

[0053] In one embodiment, the predicted temperature curve generally refers to a function curve or discrete point set generated by predicting the temperature change trend of the charging port 110 over a future period based on a sequence of thermal characteristic parameters from the past and present. For example, the curve can be a list of temperature values ​​predicted at fixed time intervals within the next T seconds. The predicted temperature curve not only includes predictions of the absolute values ​​of future temperatures but also includes dynamic trend information about temperature changes over time, such as the rate of temperature rise at future time points and the remaining time required to reach a specific temperature threshold.

[0054] Figure 4 This is provided by the embodiments of this disclosure. Figure 2 A flowchart of step S22 is shown in a preferred embodiment. Figure 4 Step S22 includes: Step S221: Input the thermal characteristic parameter sequence into the temperature prediction model to predict the temperature change within N time windows in the future, where N≥1.

[0055] In one embodiment, the temperature prediction model generally refers to an algorithm or structure that can predict the future temperature trend of the charging port 110 based on a sequence of historical thermal characteristic parameters. For example, it may include, but is not limited to: time series prediction models based on recurrent neural networks or long short-term memory networks, statistical prediction models based on autoregressive moving average models, or ensemble learning models based on gradient boosting decision trees.

[0056] Specifically, the temperature prediction model is trained to learn the dynamic change patterns of the input historical thermal feature parameter sequence, and based on this pattern, predicts the temperature changes within N future time windows. The N time windows can refer to several discrete points in the future (e.g., the temperature values ​​at the 1st, 2nd, ..., 10th second in the future), or they can refer to the temperature change curve within a continuous time interval in the future.

[0057] Step S222: Output the predicted temperature curve for the next T seconds based on the prediction results, where T≥1.

[0058] In one embodiment, the predicted temperature curve generally refers to the curve data output by the temperature prediction model that describes the temperature change trend of the charging port 110 over a future period of time.

[0059] Specifically, based on the prediction results of the temperature prediction model, the system can output the predicted temperature curve within the next T seconds. This curve can be a list containing future time points and corresponding predicted temperature values, or it can be a continuous function expression (such as fitting through spline interpolation). T can refer to any predefined time window length such as 5 seconds, 10 seconds, 30 seconds, or 60 seconds.

[0060] Step S223: Determine the remaining time for the charging port temperature to reach the warning temperature based on the predicted temperature curve.

[0061] In one embodiment, the warning temperature can be a fixed value or a value that is dynamically adjusted based on the type of battery 130, ambient temperature, and charging stage. The remaining time is a dynamic indicator that integrates the current rate of temperature rise, the acceleration of temperature rise, and the trend of temperature change.

[0062] Step S224: If the remaining time is less than the first preset value, determine that the charging port is in an abnormal charging state.

[0063] The first preset value is determined based on the time required for the charging port 110 to reach the warning temperature under normal charging conditions.

[0064] In one embodiment, the first preset value is determined based on the time required for the charging port 110 to reach the warning temperature under normal, fault-free charging conditions. For example, under standard conditions, a healthy charging port 110 may need 600 seconds to reach 80°C when charging at the maximum allowable current. The system can use this time as a benchmark to set the first preset value. If the currently predicted remaining time (e.g., only 120 seconds) is significantly less than the first preset value (e.g., set to 500 seconds), it indicates that the current temperature rise rate is abnormally high, and it can be determined that the charging state of the charging port 110 is abnormal.

[0065] Based on the above method, the thermal characteristic parameter sequence of charging port 110 can be dynamically analyzed and pattern recognized by the temperature prediction model, an artificial intelligence model, which can realize early and accurate detection of charging abnormalities of charging port 110.

[0066] Step S23: If the charging state of the charging port is determined to be abnormal based on the predicted temperature curve, the abnormality is classified and an early warning signal is output to characterize the existence of a charging abnormality in the charging port.

[0067] The warning signals include the types of abnormalities corresponding to charging abnormalities, such as poor contact, overcurrent, line fault, and heat dissipation blockage.

[0068] In one embodiment, abnormal charging status generally refers to a situation where the charging status of the charging port 110 deviates from the normal charging behavior pattern. This deviation can be identified through the analysis of thermal characteristic parameter sequences or the characteristics of the predicted temperature curve. For example, it may include, but is not limited to: the predicted temperature curve showing a significantly shortened remaining time to reach the warning temperature, or the anomaly classification model identifying a specific anomaly type, or the predicted remaining time being less than the first preset value.

[0069] In one embodiment, a warning signal generally refers to a perceptible or processable signal used to communicate to internal system modules, users, or external devices that there may be an abnormality in the charging status and the type of abnormality.

[0070] In some embodiments, the warning signal may be a structured data packet containing information such as the type of anomaly, severity level, and predicted remaining time; or it may be a text, sound, or visual alarm sent directly to the vehicle dashboard or the user's mobile phone.

[0071] In some embodiments, the warning signal can be sent to the vehicle's human-machine interface (such as the dashboard) to remind the driver in the form of text or icons; it can also be sent to the controller of the charging pile 170 to perform active current reduction or shutdown operations; or it can be uploaded to the cloud server 190 to notify operation and maintenance personnel or to perform big data analysis.

[0072] In one implementation, once an anomaly is detected, the system immediately generates a warning signal containing a message indicating poor contact at the charging port 110 and suggesting maintenance. This message is then sent to the central control display screen via the vehicle communication network, and the event is recorded in the local log.

[0073] Optionally, classifying anomalies includes: The anomaly type and the probability corresponding to the anomaly type are determined based on the thermal characteristic parameter sequence and the predicted temperature curve.

[0074] In one embodiment, the thermal characteristic parameter sequence characterizing past and current thermal behavior and the predicted temperature curve characterizing future thermal behavior trends are combined and analyzed comprehensively from the time domain, frequency domain and trend domain to determine the type of anomaly and the probability corresponding to the anomaly type.

[0075] In one implementation, the system can simultaneously analyze whether the current temperature rise rate is abnormally high and whether the predicted temperature curve shows an accelerating upward trend. If both are true, the system can infer that the anomaly type is likely to be a poor contact type and infer the probability that the current anomaly matches this anomaly type.

[0076] Specifically, different types of anomalies (such as poor contact or heat dissipation blockage) have different physical causes and corresponding solutions. For example, poor contact requires checking terminal fit, heat dissipation blockage requires clearing the ventilation path, and sensor failure requires hardware replacement. By determining the anomaly type and its corresponding probability, the system can provide maintenance personnel with targeted diagnostic guidance.

[0077] Based on the above method, the future temperature of the charging port 110 is predicted by using thermal characteristic parameters related to temperature. The abnormal charging behavior can be detected and warned in advance based on the prediction results. This solves the problems of delayed warning and inability to identify and predict abnormal temperature rise trends in related technologies, and significantly improves safety.

[0078] Figure 5 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this disclosure. In a preferred embodiment, see [link to flowchart]. Figure 5 Based on the thermal characteristic parameter sequence and the predicted temperature curve, the anomaly type and the probability corresponding to the anomaly type are determined, including: Step S51: Input the thermal feature parameter sequence and the predicted temperature curve into the anomaly classification model to extract anomaly features.

[0079] In one embodiment, the anomaly classification model generally refers to an algorithm or structure that can identify whether the current thermal feature parameter sequence deviates from the normal charging thermal behavior pattern and determine its anomaly type. For example, it may include, but is not limited to: classification models based on convolutional neural networks or fully connected networks, classifiers based on support vector machines, or classifiers based on gradient boosting decision trees.

[0080] Specifically, the anomaly classification model is trained to analyze which type of anomaly the current abnormal thermal behavior belongs to (such as poor contact, heat dissipation blockage, etc.) and the corresponding probability distribution.

[0081] In one embodiment, the abnormal features are the features that the anomaly classification model learns autonomously and that are most capable of distinguishing different abnormal modes. Broadly speaking, they refer to the key discriminative information extracted by the anomaly classification model from the current input data that characterizes deviations in thermal behavior from normal patterns. These abnormal features essentially reflect the unique changes in the thermal characteristic parameter sequences caused by different physical faults. For example, when a persistently high and drastically fluctuating rate of temperature rise is detected, and the temperature rise no longer maintains an approximately linear proportional relationship with the square of the current, the anomaly classification model can infer, based on these abnormal features, that the current anomaly is highly likely to be a poor contact type anomaly.

[0082] Step S52: Classify anomalies based on their characteristics.

[0083] In one embodiment, different anomalies will exhibit distinctive anomaly features. The anomaly classification model learns the mapping relationship between these features and anomaly types to achieve accurate classification of the current anomaly.

[0084] In some embodiments, when the extracted abnormal features are characterized by a persistently high and highly volatile temperature rise rate, and the temperature rise is not proportional to the square of the current (for example, under constant current, the temperature rise rate abnormally reaches more than 150% of the normal value, accompanied by random fluctuations of more than ±0.1°C / s), the corresponding abnormal type may be poor contact.

[0085] In some embodiments, when the abnormal characteristic is that the rate of temperature rise is proportional to the square of the current, but its absolute value exceeds the normal empirical range under the same operating conditions (for example, at a current of 100A, the measured rate of temperature rise is 30% higher than the historical normal model prediction value), the corresponding abnormal type may be overcurrent.

[0086] In some embodiments, when the abnormal characteristic is that the rate of temperature drop is significantly lower than the normal value after charging stops (for example, the temperature drops by only 10% 5 minutes after charging ends, while it should drop by more than 50% under normal operating conditions), the corresponding abnormal type may be heat dissipation blockage type abnormality.

[0087] In some embodiments, when the abnormal feature manifests as a sudden change or jump in temperature data, or an inconsistency between the sensor data of the same charging port 110 and historical data (for example, the DC+ terminal temperature jumps by 10°C instantaneously, while the DC- terminal temperature changes gradually), the corresponding abnormality type may be a sensor or circuit failure.

[0088] Step S53: Output the anomaly type and the probability corresponding to the anomaly type based on the classification results.

[0089] In one embodiment, the anomaly classification model classifies the current anomaly based on the extracted anomaly features. The classification result can be a probability distribution. For example, the probability of outputting a poor contact anomaly is 85%, the probability of a heat dissipation blockage anomaly is 10%, and the probability of a sensor failure is 5%. Based on the classification result, the system outputs each anomaly type and its corresponding probability value so that the operator can perform relevant safety operations, such as testing or replacing devices.

[0090] Based on the above method, charging anomaly warnings are transformed into clear fault types and their probability of occurrence, which facilitates targeted maintenance, effectively improves the confidence of early warnings, and provides core decision-making basis for implementing differentiated graded response strategies, thereby improving the continuity and efficiency of charging.

[0091] Optionally, the method further includes: establishing and optimizing the temperature prediction model and the anomaly classification model based on offline training and validation. Specifically, this includes: constructing a training dataset and a validation dataset; training the temperature prediction model and the anomaly classification model based on the training dataset; and validating the temperature prediction model and the anomaly classification model based on the validation dataset.

[0092] The training and validation datasets include sequences of thermal characteristic parameters from historical normal charging processes and labeled anomaly types.

[0093] Specifically, training the temperature prediction model and the anomaly classification model based on the training dataset includes: the temperature prediction model learns to predict future temperature changes from historical thermal feature parameter sequences based on the training dataset, and optimizes the parameters by minimizing the prediction error; the anomaly classification model learns to distinguish between normal thermal behavior patterns and various anomaly types based on the training dataset.

[0094] Optionally, after obtaining the anomaly type and the probability corresponding to the anomaly type based on the thermal feature parameter sequence and the predicted temperature curve, the method further includes: The warning level for anomalies is determined based on the predicted temperature curve and the probability corresponding to the anomaly type.

[0095] In one embodiment, the warning level refers to different degrees of severity or risk level of the anomaly, thereby triggering different levels of response measures.

[0096] For example, for an event with a predicted high temperature that is about to trigger a dangerous threshold, a high-level warning should be given regardless of its classification probability; while for an event with a high classification probability but a predicted low temperature (indicating that the consequences are not serious for the time being), a lower-level warning can be given, the main purpose of which is to remind users to pay attention and arrange maintenance.

[0097] Figure 6 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this disclosure. In a preferred embodiment, see [link to flowchart]. Figure 6 Optionally, the warning level corresponding to the anomaly can be divided according to the predicted temperature curve and the probability corresponding to the anomaly type, including: Step S61: Obtain the predicted temperature of the charging port within a preset time based on the predicted temperature curve.

[0098] In one embodiment, the system obtains the predicted temperature of the charging port 110 within a preset time (e.g., within the next 10 seconds) based on the predicted temperature curve, and then classifies the temperature based on different temperature thresholds.

[0099] Step S62: When the predicted temperature reaches the first threshold, the anomaly level is classified as Level 1.

[0100] Step S63: When the predicted temperature reaches the second threshold, the anomaly level is classified as the second level.

[0101] Step S64: When the probability corresponding to the anomaly type is greater than the second preset value, but the predicted temperature is less than the third threshold, the anomaly level is classified as the third level.

[0102] Among them, the first threshold is greater than the second threshold, the second threshold is greater than the third threshold, and the degree of danger represented by the first level, the second level and the third level decreases step by step.

[0103] In one embodiment, the second preset value is used to determine whether the confidence level of the output result of the anomaly classification model is high enough to trigger an early warning. When the probability of a certain anomaly type output by the anomaly classification model is greater than the second preset value, it indicates that the system believes with a high degree of confidence that the current thermal behavior deviates from the normal mode and belongs to the specific anomaly type.

[0104] In one embodiment, when the predicted temperature reaches a first threshold, the system classifies the anomaly level as a first level (e.g., L3 - Danger Level), which may mean that charging needs to be interrupted immediately; when the predicted temperature reaches a second threshold, the system classifies the anomaly level as a second level (e.g., L2 - Warning Level), which may mean that the charging current needs to be reduced and an inspection needs to be arranged; when the probability corresponding to the anomaly type is greater than a second preset value, but the predicted temperature is less than a third threshold, the system classifies the anomaly level as a third level (e.g., L1 - Concern Level), which may mean that although there is no immediate danger, the system has identified some early signs that warrant attention.

[0105] Based on the above method, the prediction temperature is combined with the probability of anomalies for comprehensive level determination, realizing dynamic quantification and hierarchical mapping of risks, effectively solving the problem of delayed fault response. By setting up a combination rule of multi-level thresholds and probability conditions, the proactiveness of security protection is improved, while optimizing the allocation of operation and maintenance resources and user experience.

[0106] Figure 7 This is a flowchart illustrating the charging port charging anomaly early warning method provided in this disclosure. In a preferred embodiment, see [link to flowchart]. Figure 7 After outputting a warning signal to indicate a charging abnormality at the charging port, the method further includes: Step S71: Execute a dynamic adjustment charging strategy based on the warning signal.

[0107] Among them, dynamically adjusting the charging strategy includes at least one of reducing the charging current of the battery during the charging process or shutting off the charging process.

[0108] In one embodiment, dynamically adjusting the charging strategy generally refers to the real-time and automatic adjustment and control of the electrical parameters or state of the charging process based on the probability corresponding to the level or type of anomaly. The implementation of this charging strategy includes, but is not limited to: linearly or stepwise reducing the charging current according to a preset mapping relationship; adjusting the voltage setpoint during the constant voltage charging phase; switching charging modes (e.g., switching from a high-power fast charging mode to a standard charging mode); and completely shutting down the charging circuit when the risk is highest.

[0109] For example, when the system determines the level of the abnormality to be L2 - warning level, the controller 140 sends a command to the charging pile 170 to reduce the current; when the level of the abnormality is determined to be L3 - danger level, a shutdown command is sent directly.

[0110] Step S72: Upload the warning signal, charging status of the charging port, abnormality type and the probability corresponding to the abnormality type to the cloud server to establish a health record for charging port 110.

[0111] In one embodiment, a health record refers to a structured data set established for a single charging port 110 to record its entire lifecycle status and historical events. This record is created and maintained in a cloud server 190, and its content is continuously updated and accumulated based on data from multiple charging processes. Furthermore, the cloud's big data resources can be used to continuously perform incremental learning or version updates on temperature prediction models, anomaly classification models, etc., enabling them to adapt to more diverse charging conditions and emerging fault modes.

[0112] The information contained in the health record includes, but is not limited to: historical thermal characteristic parameter sequences and their statistical characteristics, warning records of each triggered charging anomaly, covering the anomaly type, occurrence time, associated probability value and final warning level, details and results of the executed dynamic adjustment charging strategy, and records of subsequent manual inspection, maintenance or replacement.

[0113] In some embodiments, longitudinal analysis of historical health records can further assess the impact on the lifespan and damage status of the charging port 110 or charging pile 170. Specifically, this can be achieved by statistically analyzing the frequency of warnings triggered by the charging port 110 during multiple charging processes, the distribution evolution of abnormality types, and the changing trend of thermal characteristic parameter sequences over time. For example, if the probability of a poor contact type abnormality at a charging port shows a monotonically increasing trend, or if its average temperature rise rate under normal operating conditions continues to increase slowly, it can be determined that the physical condition of its connector is deteriorating and its lifespan is affected. Based on this, predictive maintenance prompts can be generated, or its remaining reliable service life can be quantitatively assessed.

[0114] Based on the above method, the charging strategy is dynamically adjusted and the data is uploaded to the cloud simultaneously, which directly transforms the early warning into control actions, realizing proactive closed-loop control of risks. The health record is constructed to enable continuous iteration and optimization of the cloud-based artificial intelligence model, thereby improving the system's early warning capabilities.

[0115] The following describes a specific application scenario: an electric vehicle enters a fast charging station for charging. The vehicle is equipped with a charging system 100 that implements this charging port anomaly warning method. After the charging gun 160 is inserted into the vehicle's charging port 110, the system starts. During the initial charging phase, the system collects real-time data on the charging current and the temperatures of the DC+ and DC- terminals of the charging port 110, recording this data 10 times per second. Simultaneously, a temperature prediction model and anomaly classification model run continuously in the background. At the 15-minute mark of charging, the temperature prediction model predicts the temperature based on the thermal characteristic parameter sequence of the past 60 seconds (including temperature rise rate, stage indicators, etc.) and outputs a predicted temperature curve for the next 60 seconds. At the same time, the anomaly classification model analyzes the temperature sequence for this period and finds that: The current temperature of the charging port 110 is only 45℃, which is lower than the threshold alarm of 80℃. However, the predicted temperature curve shows that if the current temperature rise rate continues, the temperature will exceed 70℃ (the second threshold) in 120 seconds. Furthermore, the anomaly classification model determines with a high confidence of 92% (greater than the second preset value of 90%) that the current thermal behavior pattern belongs to the poor contact type anomaly. Based on this, the system determines that the current anomaly is the second level L2-warning level.

[0116] The system sent a warning message to the driver's mobile phone via the vehicle network: there is a risk of poor contact at charging port 110, and it is recommended to check the terminals of charging gun 160. The system is actively reducing the charging current to ensure safety. At the same time, the system sends a command to charging pile 170 via the CAN bus to linearly reduce the charging current. The vehicle continues to charge with the reduced current. After charging is completed, the system encrypts and uploads the complete data of this event (including the original thermal characteristic parameter sequence, predicted curve, diagnostic conclusions and actions) to cloud server 190.

[0117] This application provides a charging port charging anomaly early warning method. The charging port is connected to a battery and a charging pile respectively. The method includes: acquiring a thermal characteristic parameter sequence during the charging process of the charging pile charging the battery through the charging port; wherein, the thermal characteristic parameter sequence includes parameters used to characterize the temperature state of the charging port; acquiring a predicted temperature curve of the charging port based on the thermal characteristic parameter sequence, and determining whether the charging state of the charging port is abnormal based on the predicted temperature curve; if it is determined that the charging state of the charging port is abnormal based on the predicted temperature curve, then classifying the abnormality and outputting an early warning signal to characterize the existence of a charging anomaly in the charging port.

[0118] Based on the above, thermal characteristic parameters related to the charging port temperature are used to predict future temperatures, thereby detecting charging anomalies early, classifying and issuing warnings, solving the problems of delayed warnings and the inability to identify and predict charging anomalies in the early stages, and significantly improving safety.

[0119] Figure 8 This is a schematic diagram of a vehicle provided according to an embodiment of the present disclosure. The vehicle 800 includes a charging port 810, a power battery 820, and a charging controller 830.

[0120] The power battery 820 is connected to the charging port 810; the charging controller 830 is connected to the charging port 810 and the power battery 820, and is configured to execute the charging port charging abnormality warning method as described above.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0122] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0124] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0126] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program verification codes, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] Furthermore, it should be noted that the combination of the various technical features in this case is not limited to the combination methods described in the claims of this case or the combination methods described in the specific embodiments. All technical features described in this case can be freely combined or combined in any way, unless they contradict each other.

[0128] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

[0129] It should be understood that the terms "first," "second," etc., mentioned in the embodiments of the present invention are used only to more clearly describe the technical solutions of the embodiments of the present invention, and cannot be used to limit the scope of protection of the present invention.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for early warning of charging port abnormalities, characterized in that, The charging port is connected to the battery and the charging station respectively, and the method includes: The thermal characteristic parameter sequence of the charging pile during the charging process of the battery through the charging port is obtained; wherein, the thermal characteristic parameter sequence includes parameters used to characterize the temperature state of the charging port; The predicted temperature curve of the charging port is obtained based on the thermal characteristic parameter sequence, and the charging state of the charging port is determined to be abnormal based on the predicted temperature curve. If the charging state of the charging port is determined to be abnormal based on the predicted temperature curve, the abnormality is classified and an early warning signal is output to characterize the existence of a charging abnormality in the charging port. The warning signal includes the abnormality type corresponding to the charging abnormality, and the abnormality type includes poor contact type, overcurrent type, line fault type, and heat dissipation blockage type.

2. The method according to claim 1, characterized in that, The step of obtaining the predicted temperature curve of the charging port based on the thermal characteristic parameter sequence includes: The thermal characteristic parameter sequence is input into the temperature prediction model to predict the temperature change within N future time windows, where N≥1; Output the predicted temperature curve for the next T seconds based on the prediction results, where T≥1.

3. The method according to claim 1, characterized in that, The step of determining whether the charging status of the charging port is abnormal based on the predicted temperature curve includes: The remaining time for the charging port temperature to reach the warning temperature is determined based on the predicted temperature curve. If the remaining time is less than a first preset value, the charging state of the charging port is determined to be abnormal; wherein, the first preset value is determined based on the time required for the charging port to reach the warning temperature under normal charging conditions.

4. The method according to claim 1, characterized in that, The classification of the anomalies includes: The anomaly type and the probability corresponding to the anomaly type are determined based on the thermal characteristic parameter sequence and the predicted temperature curve.

5. The method according to claim 4, characterized in that, The step of determining the anomaly type and the probability corresponding to the anomaly type based on the thermal feature parameter sequence and the predicted temperature curve includes: The thermal feature parameter sequence and the predicted temperature curve are input into the anomaly classification model to extract anomaly features; The anomalies are classified according to their abnormal characteristics; Based on the classification results, output the anomaly type and the probability corresponding to the anomaly type.

6. The method according to claim 4, characterized in that, After determining the anomaly type and the probability corresponding to the anomaly type based on the thermal characteristic parameter sequence and the predicted temperature curve, the method further includes: The warning level corresponding to the anomaly is determined based on the predicted temperature curve and the probability corresponding to the anomaly type.

7. The method according to claim 6, characterized in that, The step of classifying the warning level corresponding to the anomaly based on the predicted temperature curve and the probability corresponding to the anomaly type includes: The predicted temperature of the charging port within a preset time is obtained based on the predicted temperature curve. When the predicted temperature reaches the first threshold, the anomaly is classified as level one. When the predicted temperature reaches the second threshold, the anomaly is classified as level two. When the probability corresponding to the anomaly type is greater than the second preset value, but the predicted temperature is less than the third threshold, the anomaly is classified as the third level. Wherein, the first threshold is greater than the second threshold, the second threshold is greater than the third threshold, and the degree of danger represented by the first level, the second level and the third level decreases progressively.

8. The method according to claim 4, characterized in that, After the output is used to characterize a warning signal indicating a charging abnormality at the charging port, the method further includes: A dynamic adjustment charging strategy is executed based on the warning signal; wherein the dynamic adjustment charging strategy includes at least one of reducing the charging current of the battery during the charging process and shutting off the charging process. The warning signal, the charging status of the charging port, the abnormality type, and the probability corresponding to the abnormality type are uploaded to the cloud server to establish a health record for the charging port.

9. The method according to claim 1, characterized in that, The step of obtaining the thermal characteristic parameter sequence of the charging port during the charging process of the battery includes: The charging current of the battery during the charging process, the stage identifier of the charging port during the charging process, and the temperature sequence are obtained; wherein, the stage identifier indicates that the charging port is at least in one of the constant current charging stage and the trickle charging stage, and the temperature sequence includes multiple temperature values ​​collected by the charging port at a fixed frequency during the charging process. Calculate the temperature rise rate, temperature rise acceleration, total temperature rise, and temperature rise per unit of electricity for the charging port based on the temperature sequence. The charging current, the stage identifier, the temperature rise rate, the temperature rise acceleration, the total temperature rise, and the temperature rise per unit of electricity are fused together to obtain the thermal characteristic parameter sequence.

10. A vehicle, characterized in that, include: Charging port; The power battery is connected to the charging port; A charging controller, connected to the power battery, is configured to execute the charging port charging abnormality early warning method as described in any one of claims 1-9.

Images