Fast charging overcurrent protection method and device and storage medium

Abstract

The invention discloses a fast charging overcurrent protection method and device and a storage medium, and relates to the technical field of overcurrent protection, and the fast charging overcurrent protection method comprises the steps that fast charging data in the fast charging process are acquired in real time based on a preset sampling frequency, the fast charging data comprise charging parameters and battery working condition parameters during fast charging, and the charging parameters and the battery working condition parameters are acquired in real time; and calculating the overcurrent probability of fast charging based on the fast charging data, preset risk mapping logic, a preset risk calculation formula and a predetermined overcurrent calculation weight, and performing fast charging overcurrent protection based on the overcurrent probability. The fast charging data used for calculating the overcurrent probability comprises the working condition parameters of the battery besides the parameters related to charging, so that the working condition of the battery which can influence the overcurrent is considered in addition to the charging parameters when the overcurrent is judged. And the overcurrent protection is carried out through the overcurrent probability, and fixed current and voltage thresholds are not needed to carry out overcurrent protection, so that the overcurrent false alarm rate is reduced.

Description

Technical Field

[0001] This application relates to the field of overcurrent protection technology, and in particular to fast charging overcurrent protection methods, devices and storage media. Background Technology

[0002] With the continuous development of new energy vehicle charging technology, fast charging technologies such as high-power charging piles and dual-gun charging have been widely used, which has increased the risk of overcurrent during new energy vehicle charging. Therefore, overcurrent protection is needed for fast charging of new energy vehicles.

[0003] Current overcurrent protection methods for fast charging of new energy vehicles rely on fixed current and voltage thresholds for triggering protection. However, the occurrence of overcurrent states can also be affected by factors other than voltage and current, resulting in a relatively high false alarm rate for current overcurrent protection methods. Summary of the Invention

[0004] The main purpose of this application is to provide a fast charging overcurrent protection method, device and storage medium, which aims to solve the technical problem of high overcurrent false alarm rate.

[0005] To achieve the above objectives, this application proposes a fast charging overcurrent protection method, the method comprising: Based on a preset sampling frequency, fast charging data during the fast charging process is acquired in real time, wherein the fast charging data includes charging parameters and battery operating parameters during fast charging. Based on the fast charging data, the preset risk mapping logic, the preset risk calculation formula, and the predetermined overcurrent calculation weight, the overcurrent probability of fast charging is calculated. Based on the overcurrent probability, fast charging overcurrent protection is implemented.

[0006] In one embodiment, the step of calculating the overcurrent probability of fast charging based on the fast charging data, a preset risk mapping logic, a preset risk calculation formula, and a predetermined overcurrent calculation weight includes: Based on the charging parameters, the battery operating condition parameters, and the preset risk mapping logic, a first risk mapping value corresponding to the charging parameters and a second risk mapping value corresponding to the battery operating condition parameters are determined. The overcurrent probability is calculated based on the first risk mapping value, the second risk mapping value, the risk calculation formula, and the overcurrent calculation weight.

[0007] In one embodiment, the charging parameters include charging current, maximum charging voltage, and requested current; the battery condition parameters include maximum battery temperature and battery health; the first risk mapping value includes a current risk mapping value and a voltage risk mapping value; the second risk mapping value includes a temperature risk mapping value and a health risk mapping value; and the step of determining the first risk mapping value corresponding to the charging parameters and the second risk mapping value corresponding to the battery condition parameters based on the charging parameters, the battery condition parameters, and a preset risk mapping logic includes: Calculate the current load ratio of the charging current and the requested current; The current risk mapping value is determined based on the current load ratio and the current risk threshold in the risk mapping logic; The voltage risk mapping value is determined based on the highest voltage and the voltage risk threshold in the risk mapping logic; The temperature risk mapping value is determined based on the battery's highest temperature and the temperature risk threshold in the risk mapping logic; Calculate the difference between the preset maximum risk value and the battery health status, and use the difference as the health risk mapping value.

[0008] In one embodiment, after the step of acquiring fast charging data in real time based on a preset sampling frequency, the method further includes: The acquired fast charging data is used as sample data, and it is determined whether the number of fast charging data in the sample data reaches a preset threshold. If the quantity threshold is reached, the data distribution of the sample data and the overcurrent physical characteristics of fast charging are determined based on each of the fast charging data. Based on the data distribution and the overcurrent physical characteristics, the target risk threshold and target overcurrent weight are determined; The risk mapping logic is adjusted based on the target risk threshold, and the overcurrent calculation weight is adjusted based on the target overcurrent weight.

[0009] In one embodiment, the step of determining the target risk threshold and the target overcurrent weight based on the data distribution and the overcurrent physical characteristics includes: Based on the data distribution and the physical characteristics, a candidate threshold set corresponding to each type of parameter in the sample data is determined, wherein the candidate threshold set includes multiple candidate thresholds; Based on the candidate threshold and the fast charging data, the parameter in the fast charging data is used as the root node, the root node is split, the split gain of each split node is calculated, a corresponding number of decision trees are obtained, and the split node obtained from each decision tree is used as the target risk threshold. Calculate the sum of the split gains of each split node in each decision tree to obtain the total decision tree gain for each decision tree; Calculate the sum of the total gains of each decision tree to obtain the optimized total gain; Calculate the ratio of the total gain of each of the aforementioned parameters to the total optimized gain, and use the calculated ratio as the corresponding target overcurrent weight.

[0010] In one embodiment, the risk mapping logic includes an initial risk threshold, and the step of adjusting the risk mapping logic based on the target risk threshold and adjusting the overcurrent calculation weight based on the target overcurrent weight includes: Calculate the difference between each target risk threshold and the original risk threshold to obtain the risk threshold change value; Calculate the ratio of the risk threshold change value to the original risk threshold to obtain the threshold adjustment range of each target risk threshold relative to the original risk threshold; The target risk threshold with the largest split gain, whose threshold adjustment range does not exceed the preset adjustment range threshold, is selected and replaced with the original risk threshold. Calculate the difference between the target overcurrent weight and the calculated overcurrent weight to obtain the weight change value; Calculate the ratio of the weight change value to the overcurrent calculation weight to obtain the weight adjustment range; Determine whether the weight adjustment range is higher than the adjustment range threshold. If it is higher, adjust the overcurrent calculation weight based on the adjustment range threshold.

[0011] In one embodiment, the step of performing fast charging overcurrent protection based on the overcurrent probability includes: If the time during which the overcurrent probability is within a preset first overcurrent range exceeds a preset first time threshold, then the current reduction value of the fast charging overcurrent protection is determined based on the overcurrent probability. Based on the current reduction value, the charging current of fast charging is reduced until the time when the overcurrent probability is in the preset safe overcurrent range exceeds the preset safe time threshold, wherein the first overcurrent range is higher than the safe overcurrent range. If the overcurrent probability remains within a preset second overcurrent range for a period exceeding a preset second time threshold, fast charging will be stopped, and a notification will be sent via a preset associated application.

[0012] In one embodiment, the step of performing fast charging overcurrent protection based on the overcurrent probability further includes: Determine whether the time during which the current load ratio is higher than the current risk threshold exceeds a preset mandatory protection time threshold, or whether the time during which the highest voltage is higher than the voltage risk threshold exceeds the mandatory protection time threshold; If the limit is exceeded, fast charging will stop and a notification will be sent through a pre-set associated app.

[0013] In addition, to achieve the above objectives, this application also proposes a fast charging overcurrent protection device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fast charging overcurrent protection method described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the fast charging overcurrent protection method described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application acquires fast charging data in real time during the fast charging process based on a preset sampling frequency. The fast charging data includes charging parameters and battery operating parameters during fast charging. Based on the fast charging data, a preset risk mapping logic, a preset risk calculation formula, and a predetermined overcurrent calculation weight, the overcurrent probability of fast charging is calculated. Based on the overcurrent probability, fast charging overcurrent protection is performed.

[0016] To address the issue that current overcurrent protection methods for fast charging of new energy vehicles rely on fixed current and voltage thresholds for triggering protection, resulting in a relatively high false alarm rate, this application calculates the overcurrent probability based on real-time acquired fast charging data and performs overcurrent protection based on this probability. When performing overcurrent protection, this application first calculates the overcurrent probability based on fast charging data, which includes not only charging-related parameters but also battery operating parameters. Therefore, when judging overcurrent, this application considers battery operating conditions that affect overcurrent in addition to charging parameters. Furthermore, by using the calculated overcurrent probability for overcurrent protection, this application eliminates the need for fixed current and voltage thresholds, thereby reducing the false alarm rate. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the fast charging overcurrent protection method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the fast charging overcurrent protection method of this application. Figure 3 This is a flowchart illustrating Embodiment 3 of the fast charging overcurrent protection method of this application. Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the fast charging overcurrent protection method in the embodiments of this application; Figure 5 This is a schematic diagram illustrating the data acquisition consent process involved in the fast charging overcurrent protection method in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a fast charging overcurrent protection device. The following description uses a fast charging overcurrent protection device as an example to illustrate this embodiment and the subsequent embodiments.

[0024] With the continuous development of new energy vehicle charging technology, fast charging technologies such as high-power charging piles and dual-gun charging have been widely used, which has increased the risk of overcurrent during new energy vehicle charging. Therefore, overcurrent protection is needed for fast charging of new energy vehicles.

[0025] The outbreak of overcurrent risk stems from multi-dimensional contradictions in fast charging systems. On the one hand, some dual-gun charging piles have defects in current coordination control, which may cause the output current to reach twice the vehicle's requested value. On the other hand, charging piles are prone to problems such as circuit aging and increased contact resistance under high temperature and high load conditions. Coupled with users' operations such as fast charging while the air conditioner is on, this can easily cause abnormal current surges. More importantly, the charging process involves a time-series chain reaction of continuously rising current, a sudden voltage lag, and a slow temperature rise, as well as the dynamic coupling of variables such as battery health degradation and ambient temperature fluctuations. This makes the overcurrent risk exhibit strong nonlinear and time-dependent characteristics.

[0026] Current overcurrent protection methods for fast charging of new energy vehicles rely on fixed current and voltage thresholds for triggering protection. However, the occurrence of overcurrent states can also be affected by factors other than voltage and current, resulting in a relatively high false alarm rate for current overcurrent protection methods.

[0027] Furthermore, current overcurrent protection methods for fast charging of new energy vehicles lack timing prediction capabilities. They can only passively alarm and forcibly cut off power after an overcurrent occurs, failing to capture the precursory characteristics of charging overcurrent and missing the window for early intervention. Moreover, when implementing protection, current overcurrent protection methods for fast charging of new energy vehicles only offer two options: no intervention and forced power cut-off. They fail to reduce current in advance during low-risk situations and directly interrupt charging during high-risk situations, which wastes battery life and seriously damages the user's charging experience.

[0028] Based on this, the embodiments of this application provide a fast charging overcurrent protection method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the fast charging overcurrent protection method of this application.

[0029] In this embodiment, the fast charging overcurrent protection method includes steps S10~S30: Step S10: Based on a preset sampling frequency, acquire fast charging data in real time during the fast charging process, wherein the fast charging data includes charging parameters and battery operating parameters during fast charging. It should be noted that the sampling frequency refers to the number of times relevant data during the fast charging process is collected per unit time, used to determine the time interval for data acquisition. In this embodiment, the sampling frequency is preset to once per second. The fast charging process refers to the operation phase in which a new energy vehicle rapidly charges its power battery through a high-power charging pile, starting from the detection of the charging gun insertion and ending with the user removing the charging gun. Fast charging data refers to a set of key parameters reflecting the charging status and battery status collected during the fast charging process. Charging parameters refer to physical quantities describing the characteristics of the current charging behavior, while battery operating condition parameters refer to physical quantities reflecting the current operating status of the power battery.

[0030] It is understood that this embodiment continuously collects five key fast charging data points throughout the entire fast charging process at a preset sampling frequency of 1 second. These data are recorded from the moment the vehicle detects the plug signal until the user unplugs the plug, ensuring coverage of the entire charging event. This provides highly timely and complete input features for the subsequent overcurrent risk prediction model, supporting the AI ​​model to accurately identify and dynamically respond to potential overcurrent risks.

[0031] This embodiment synchronously acquires multi-dimensional fast charging data covering charging behavior and battery status at a fixed sampling frequency. This includes charging parameters that directly reflect the degree of current anomalies and key operating condition parameters that characterize the battery's safety boundary, thus providing a comprehensive and time-continuous input basis for overcurrent risk prediction. Through the aforementioned high-frequency, multi-dimensional data acquisition method, this embodiment can effectively capture overcurrent precursor characteristics with strong time-dependence, such as continuously rising current, sudden voltage hysteresis, and slow temperature increases. This enables subsequent AI models to identify complex nonlinear risk patterns, thereby improving the timeliness and accuracy of overcurrent warnings.

[0032] Step S20: Calculate the overcurrent probability of fast charging based on the fast charging data, the preset risk mapping logic, the preset risk calculation formula, and the predetermined overcurrent calculation weight. It should be noted that the risk mapping logic refers to the method of converting each physical quantity in the original fast charging data into a standardized risk contribution value according to a preset nonlinear rule, which is used to quantify the relative impact of each parameter on overcurrent risk. The risk calculation formula is a mathematical expression used to calculate the final overcurrent probability by combining each risk contribution value with its corresponding weight. The overcurrent calculation weight refers to the weighting coefficient assigned to each risk contribution value, which is used to reflect the importance of different characteristics to overcurrent risk under the current operating conditions.

[0033] It is understood that in this embodiment, the fast charging data first is substituted into the preset risk mapping logic to obtain multiple standardized risk contribution values. Then, combined with the pre-determined overcurrent calculation weight, these risk contribution values ​​are input into the risk calculation formula to calculate the overcurrent probability of fast charging at the current moment. The value range is limited to 0% to 100%, thereby realizing the quantitative assessment of overcurrent risk during fast charging and providing an operable numerical basis for subsequent graded protection decisions.

[0034] This embodiment, based on multi-dimensional fast charging data, transforms physical quantities into standardized contribution values ​​with clear risk semantics through a preset risk mapping logic. It then incorporates overcurrent calculation weights, which are initially set based on experience and support dynamic optimization, into a unified risk calculation formula, thereby achieving a refined and quantifiable assessment of overcurrent risk. This method avoids the limitations of traditional fixed threshold judgments, and can differentiate the risk weights of each parameter based on dynamic factors such as battery health status and temperature. This ensures that the overcurrent probability output reflects both the true degree of danger under the current operating condition and retains the flexibility for subsequent strategy adjustments, laying the foundation for precise graded protection.

[0035] In one feasible implementation, the specific implementation of calculating the overcurrent probability of fast charging based on the fast charging data, preset risk mapping logic, preset risk calculation formula, and predetermined overcurrent calculation weight can also be: Based on the charging parameters, the battery operating condition parameters, and the preset risk mapping logic, a first risk mapping value corresponding to the charging parameters and a second risk mapping value corresponding to the battery operating condition parameters are determined. Based on the first risk mapping value, the second risk mapping value, the risk calculation formula, and the overcurrent calculation weight, the overcurrent probability is calculated.

[0036] It should be noted that the first risk mapping value refers to the risk contribution calculated from charging parameters according to the preset risk mapping logic. The second risk mapping value refers to the risk contribution calculated from battery operating parameters respectively according to the preset risk mapping logic.

[0037] Understandably, this embodiment first inputs charging parameters into a preset risk mapping logic to calculate a first risk mapping value. Simultaneously, it substitutes multiple battery operating parameters into their respective risk mapping logics to obtain a second risk mapping value. Subsequently, the first and second risk mapping values ​​are used together as inputs, combined with pre-determined overcurrent calculation weights, and substituted into the risk calculation formula to finally calculate the overcurrent probability of fast charging. By clearly distinguishing the risk contributions of charging behavior characteristics and battery state characteristics, a risk quantification process with a clear structure and hierarchical logic is achieved, improving the interpretability of the model.

[0038] This embodiment categorizes fast charging data into charging parameters and battery condition parameters based on their sources. It then generates a first risk mapping value and a second risk mapping value through risk mapping logic, respectively. These are then uniformly incorporated into the risk calculation formula for weighted fusion. This approach maintains overall calculation consistency while enhancing the differentiated processing of parameters with different physical meanings. Through this grouping and mapping mechanism, the system can more clearly separate the independent impacts of abnormal external charging behavior and internal battery condition degradation on overcurrent risk, thereby improving the structural integrity and robustness of risk assessment.

[0039] In one feasible implementation, the charging parameters include charging current, maximum charging voltage, and requested current; the battery condition parameters include maximum battery temperature and battery health; the first risk mapping value includes a current risk mapping value and a voltage risk mapping value; and the second risk mapping value includes a temperature risk mapping value and a health risk mapping value. A further specific implementation of determining the first risk mapping value corresponding to the charging parameters and the second risk mapping value corresponding to the battery condition parameters based on the charging parameters, the battery condition parameters, and preset risk mapping logic can be: Calculate the current load ratio of the charging current and the requested current. Based on the current load ratio and the current risk threshold in the risk mapping logic, determine the current risk mapping value. Based on the highest voltage and the voltage risk threshold in the risk mapping logic, determine the voltage risk mapping value. Based on the highest battery temperature and the temperature risk threshold in the risk mapping logic, determine the temperature risk mapping value. Calculate the difference between the preset highest risk value and the battery health status, and use the difference as the health risk mapping value.

[0040] It should be noted that the charging current refers to the actual current value I_real received by the battery pack during fast charging, which reflects the actual output level of the current charging power. The maximum charging voltage refers to the highest voltage value U_max measured in a single battery cell during fast charging, which characterizes the state of the battery approaching full charge or the risk of overvoltage.

[0041] Requested current refers to the desired charging current command value I_rqst sent by the vehicle to the charging station, representing the target current actively set by the system. Maximum battery temperature refers to the highest temperature value T_max recorded by all temperature sensors within the battery module during fast charging, used to assess the risk of thermal runaway or insufficient heat dissipation. Battery health refers to the battery's current capacity as a percentage of its initial nominal capacity (SOH), used to measure the degree of battery aging.

[0042] The current load ratio, I_real / I_rqst, is the ratio of the charging current to the requested current, used to determine whether the actual current exceeds the expected load range. The current risk threshold is one or more preset critical values ​​in the risk mapping logic, used to map the current load ratio to a standardized current risk mapping value. The voltage risk threshold is a preset voltage critical value in the risk mapping logic, used to map the highest charging voltage to a standardized voltage risk mapping value. The temperature risk threshold is a preset temperature critical value in the risk mapping logic, used to map the highest battery temperature to a standardized temperature risk mapping value. The highest risk value is a preset constant value representing the upper limit of the risk mapping value; the health risk mapping value is obtained by the difference between this value and the battery health status, reflecting the inverse relationship that lower health status corresponds to higher risk.

[0043] It should also be noted that the current risk threshold, voltage risk threshold, and temperature risk threshold in this embodiment each include multiple risk sub-thresholds. This allows for the use of different mapping methods to map charging parameters within different threshold ranges, increasing the accuracy of overcurrent probability calculation. The specific risk sub-thresholds and corresponding mapping methods are shown in the table below:

[0044] Where I1 is the variable risk sub-threshold of the current, and its specific value is calculated by a corresponding algorithm. T1 is the variable risk sub-threshold of the battery temperature, and its specific value is calculated by a corresponding algorithm.

[0045] Understandably, this embodiment first calculates the current load ratio of the charging current to the requested current, and compares this ratio with a preset current risk threshold in the risk mapping logic to determine the current risk mapping value. Subsequently, the highest charging voltage is compared with the voltage risk threshold to determine the voltage risk mapping value, and the highest battery temperature is compared with the temperature risk threshold to determine the temperature risk mapping value. Finally, the difference between the preset highest risk value and the battery health level is directly used as the health risk mapping value. These four mapping values ​​together constitute the first risk mapping value and the second risk mapping value, thereby achieving a precise conversion from raw fast charging data to structured risk characteristics.

[0046] This implementation method employs mapping mechanisms tailored to the physical characteristics of different types of fast charging data. For current, it uses the actual / request ratio combined with a threshold judgment; for voltage and temperature, it compares absolute values ​​with risk thresholds; and for health status, it uses an inverse mapping method of subtracting the state of harmonics (SOH) from the upper limit. This allows the risk contribution of various parameters to more accurately reflect their role in the overcurrent mechanism. Specifically, the current load ratio effectively captures the precursors of overcurrent caused by abnormal charging pile output or command mismatch, while the inverse mapping of health status reasonably reflects that aging batteries are more prone to localized overheating or current concentration due to increased internal resistance. Through these differentiated and physically meaningful mapping strategies, this embodiment not only improves the accuracy of risk characteristics but also enhances the interpretability and applicability of the entire overcurrent probability model.

[0047] Step S30: Based on the overcurrent probability, perform fast charging overcurrent protection.

[0048] It should be noted that fast charging overcurrent protection refers to taking appropriate levels of intervention measures based on the calculated overcurrent probability to prevent safety accidents caused by abnormal current.

[0049] It is understood that this embodiment accurately calculates the overcurrent probability based on different mapping logics and specific overcurrent probability calculation formulas. Furthermore, the overcurrent probability is affected not only by current and voltage but also by battery parameters. Therefore, overcurrent protection based on the calculated overcurrent probability avoids relying solely on current and voltage for protection, improving the flexibility of threshold judgment and reducing the false alarm rate.

[0050] In summary, this embodiment acquires fast charging data in real time during the fast charging process based on a preset sampling frequency. The fast charging data includes charging parameters and battery operating parameters during fast charging. Based on the fast charging data, preset risk mapping logic, preset risk calculation formula, and predetermined overcurrent calculation weight, the overcurrent probability of fast charging is calculated. Based on the overcurrent probability, fast charging overcurrent protection is performed.

[0051] To address the issue that current overcurrent protection methods for fast charging of new energy vehicles rely on fixed current and voltage thresholds for triggering protection, resulting in a relatively high false alarm rate, this application calculates the overcurrent probability based on real-time acquired fast charging data and performs overcurrent protection based on this probability. In this embodiment, the overcurrent probability is first calculated based on fast charging data, which includes not only charging-related parameters but also battery operating parameters. Therefore, this embodiment considers battery operating conditions that affect overcurrent conditions in addition to charging parameters when determining overcurrent. Furthermore, by using the calculated overcurrent probability for overcurrent protection, this embodiment eliminates the need for fixed current and voltage thresholds, thereby reducing the false alarm rate.

[0052] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After step S10, the fast charging overcurrent protection method further includes steps S11 to S14: Step S11: Use the acquired fast charging data as sample data, and determine whether the number of fast charging data in the sample data reaches a preset number threshold. It should be noted that sample data refers to the historical fast charging data set collected during the fast charging process and used for model optimization. Each sample set contains multi-dimensional parameters from a complete charging event. The quantity threshold refers to the preset minimum amount of sample data required to trigger the update of AI model weights and mapping rules. In this embodiment, the quantity threshold can be 500 sets.

[0053] Understandably, in this embodiment, the fast charging data acquired this time is stored in the historical database as a new set of sample data. Then, it is determined whether the total amount of accumulated sample data has reached a preset threshold. If it has not reached the threshold, it continues to wait for the accumulation of data from subsequent charging events. If it has reached the threshold, it enters the subsequent model optimization process, thereby providing a stable and sufficient data foundation for the optimization of dynamic weights and mapping rules.

[0054] Step S12: If the quantity threshold is reached, then based on each of the fast charging data, determine the data distribution of the sample data and the overcurrent physical characteristics of fast charging; It should be noted that data distribution refers to the statistical characteristics of each fast-charging data feature in the sample data, including its value range, central tendency, and dispersion, which are used to guide the generation of candidate splitting thresholds. Overcurrent physical characteristics refer to the engineering or electrochemical laws related to battery overcurrent safety, including the lithium plating critical voltage and the highest acceptable charging temperature of the battery, which are used to screen candidate thresholds with practical significance.

[0055] Understandably, after confirming that the amount of sample data has reached the preset threshold, this embodiment first performs statistical analysis on all fast charging data in all sample data to extract its data distribution characteristics. At the same time, combined with the overcurrent physical characteristics of the battery system in the fast charging scenario, it comprehensively determines the effective value range and key risk boundary of each characteristic parameter, providing a basis that is both data-driven and engineering-rational for the subsequent construction of candidate splitting threshold sets, ensuring that the selected thresholds reflect the actual operating condition distribution and conform to the battery safety mechanism.

[0056] This embodiment utilizes the statistical distribution of sample data and the overcurrent physical characteristics during fast charging before model optimization, thereby generating a feature analysis basis that is both close to actual operating data and has clear safety significance. This avoids the generation of thresholds without engineering significance and also prevents the neglect of the diversity of actual operating conditions by relying solely on manual experience to set thresholds.

[0057] Step S13: Based on the data distribution and the overcurrent physical characteristics, determine the target risk threshold and the target overcurrent weight; It should be noted that the target risk threshold refers to the value selected from the candidate split thresholds and used to update the key boundary point in the risk mapping logic. Specifically, it includes the current risk threshold I1 and the temperature risk threshold T1. The selection is based on maximizing the split gain and must meet the constraints of the overcurrent physical characteristics.

[0058] The target overcurrent weight refers to the attention layer weights that have been redistributed and are used to replace the current weights to more accurately reflect the actual contribution of each feature to the overcurrent risk.

[0059] Understandably, this embodiment performs a split gain maximization search based on both data distribution and overcurrent physical characteristics. This allows for the automatic identification of the target risk threshold and target overcurrent weight that best discriminates overcurrent prediction, while ensuring engineering feasibility. This enables mapping thresholds such as current and temperature to adaptively adjust with battery aging or environmental changes, and also allows the weight allocation of each feature to dynamically reflect its actual risk contribution under different operating conditions. Therefore, this embodiment, through the synergistic optimization of data-driven and physical constraints, can significantly improve the accuracy and timeliness of overcurrent risk assessment.

[0060] In one feasible implementation, the specific implementation of determining the target risk threshold and target overcurrent weight based on the data distribution and the overcurrent physical characteristics can also be: Based on the data distribution and physical characteristics, candidate threshold sets corresponding to various parameters in the sample data are determined, wherein the candidate threshold sets include multiple candidate thresholds. Based on the candidate thresholds and the fast charging data, the parameters in the fast charging data are used as root nodes, and the root nodes are split. The split gain of each split node is calculated to obtain a corresponding number of decision trees. The split node obtained from each decision tree is used as the target risk threshold. The sum of the split gains of each split node in each decision tree is calculated to obtain the total gain of each decision tree. The sum of the total gains of each decision tree is calculated to obtain the optimized total gain. The ratio of the total gain of each parameter in the optimized total gain is calculated, and the calculated ratio is used as the corresponding target overcurrent weight.

[0061] It should be noted that the candidate threshold set is a set of thresholds generated for each fast-charging parameter based on its data distribution and overcurrent physical characteristics, which may be used for decision tree splitting. It typically contains 4-6 engineering-reasonable and data-common candidate values. The root node is the initial unsplit node containing all samples when constructing a single decision tree. Its feature is a specific fast-charging parameter, used to initiate the recursive splitting process. A splitting node is the decision point in the decision tree that divides the parent node into left and right child nodes based on a certain feature and the corresponding candidate threshold. Split gain is an indicator that measures the improvement in model prediction performance caused by a single split. The total decision tree gain refers to the sum of the split gains of a specific parameter at all splitting nodes in a single decision tree, reflecting the overall contribution of that parameter in the tree. The optimized total gain refers to the sum of the total decision tree gains of all decision trees, used as the denominator for weight normalization.

[0062] It is understandable that data-driven continuous optimization is achieved through the XGBoost (eXtreme Gradient Boosting) model, specifically including the selection of split nodes and the calculation of split gains. The steps for selecting split nodes include: For each feature (I_real / I_rqst, U_max, T_max, SOH), a candidate threshold set T = {t1, t2, ..., t} is generated based on the statistical distribution of the sample data and the battery overcurrent physical characteristics. m} where m is the number of candidate thresholds, ranging from 4 to 6. Thresholds with extremely low probability of occurrence in reality and no engineering significance are eliminated to ensure that all candidate thresholds fall within the range of actual occurrences. For each candidate feature-threshold (a,t) combination, a split gain is calculated, and the (a,t) combination with the largest split gain is selected as the split node for the current node. If the gain of all candidate combinations is ≤0, splitting stops, and this node becomes a leaf node. The formula for calculating the split gain is:

[0063] Among them, G （a,t） It is the split gain, L p N represents the loss value of the parent node. p N l N r L represents the number of samples for the parent node, left child node (eigenvalue ≤ t), and right child node (eigenvalue > t), respectively. l L r γ represents the loss values ​​of the left and right child nodes, respectively; γ is the regularization parameter, which in this embodiment can be 0.01~0.1, used to suppress invalid splits with too small a gain.

[0064] After obtaining the decision tree corresponding to the features of each sample, this embodiment calculates the split gain G of each decision tree in the model across all split nodes. (a,t) By summing the results, we can obtain the feature gain of a single tree. , where k is the feature index and i is the tree index.

[0065] The feature gains of all decision trees are calculated. Then, the split gains of all decision trees corresponding to the same feature are summed to obtain the total split gain of the k-th feature. The specific calculation formula is as follows:

[0066] Where M is the total number of decision trees. In this embodiment, the sample size can be 500, that is, a weight iteration is performed every 500 sets of data collected.

[0067] Then, based on the proportion of the total feature gain (information gain) value, the attention layer weights are dynamically adjusted, using the following formula:

[0068] Wk is the weight of the k-th feature (k=1 corresponds to I_real / I_rqst, k=2 corresponds to U_max, k=3 corresponds to T_max, k=4 corresponds to SOH); Gk is the total gain value of the k-th feature, specifically referring to a certain feature; Gj is the total gain value of the j-th feature, used in the summation traversal scenario of the weight formula. It is distinguished from Gk by only the symbol, and the two are calculated in the same way.

[0069] This embodiment unifies the determination of the target risk threshold and the allocation of the target overcurrent weights within the XGBoost interpretability framework by systematically constructing a candidate threshold set, performing decision tree splitting based on split gain, and quantifying the proportion of each parameter's total gain in the entire model. Because this embodiment uses the node with the largest split gain as a child node when constructing the decision tree, it ensures that the selected threshold not only has the greatest discriminative power, but also that the weight allocation directly reflects the actual contribution strength of each parameter in real overcurrent events. Therefore, this embodiment avoids the subjective bias of manually setting thresholds and weights through the above steps, while ensuring the accuracy of model updates.

[0070] Furthermore, since all candidate thresholds are subject to both data distribution and physical characteristics, the resulting target risk thresholds are both statistically representative and safety reasonable, thereby significantly improving the adaptive capability and long-term stability of the overcurrent protection system.

[0071] Step S14: Adjust the risk mapping logic based on the target risk threshold, and adjust the overcurrent calculation weight based on the target overcurrent weight.

[0072] It is understood that this embodiment updates the risk mapping logic and overcurrent calculation weights synchronously based on the optimized target risk threshold and target overcurrent weights, thereby enabling the overcurrent protection mechanism to have continuous learning and adaptive capabilities while ensuring system stability. Specifically, the adjustment of the risk mapping logic allows the judgment boundary for current overrun or temperature rise to be dynamically calibrated according to the evolution of actual operating conditions, such as a lower safe current threshold corresponding to aging batteries, while the update of the overcurrent calculation weights ensures that the model always focuses on the most predictive feature at present, such as the voltage weight increasing under low temperature conditions. Therefore, through the above steps, this embodiment can effectively solve the problem of accuracy decay of traditional fixed rule algorithms throughout the entire life cycle, significantly improving the long-term robustness and accuracy of the fast charging overcurrent protection system.

[0073] In one feasible implementation, the risk mapping logic includes an original risk threshold. The specific implementation of adjusting the risk mapping logic based on the target risk threshold and adjusting the overcurrent calculation weight based on the target overcurrent weight can also be: Calculate the difference between each target risk threshold and the original risk threshold to obtain a risk threshold change value. Calculate the ratio of the risk threshold change value to the original risk threshold to obtain the threshold adjustment range of each target risk threshold relative to the original risk threshold. Select the target risk threshold whose threshold adjustment range does not exceed a preset adjustment range threshold and has the largest split gain, and replace the original risk threshold. Calculate the difference between the target overcurrent weight and the overcurrent calculation weight to obtain a weight change value. Calculate the ratio of the weight change value to the overcurrent calculation weight to obtain the weight adjustment range. Determine whether the weight adjustment range is higher than the adjustment range threshold. If it is higher, adjust the overcurrent calculation weight based on the adjustment range threshold.

[0074] It should be noted that the original risk threshold refers to the initial or previously optimized threshold parameters currently used in the risk mapping logic, including the current risk threshold I1 and the temperature risk threshold T1. The risk threshold change value refers to the absolute difference between the target risk threshold and the original risk threshold, used to measure the magnitude of the threshold update. The threshold adjustment magnitude refers to the relative change ratio of the risk threshold change value relative to the original risk threshold, used to assess the drasticness of the adjustment. The adjustment magnitude threshold presets the maximum relative change ratio allowed for a single adjustment; in this embodiment, the adjustment magnitude threshold can be 0.05%, used to limit abrupt changes in model parameters. The weight change value refers to the difference between the target overcurrent weight and the current overcurrent calculation weight. The weight adjustment magnitude refers to the relative change ratio of the weight change value relative to the current overcurrent calculation weight.

[0075] Understandably, this implementation method avoids drastic parameter jumps in the AI ​​model due to a small number of abnormal samples or short-term operating condition fluctuations by limiting the single adjustment range of the threshold and weight to no more than a preset adjustment threshold, thus preventing false triggering of current reduction or power outages. Simultaneously, while satisfying stability constraints, it prioritizes the target risk threshold with the largest splitting gain, ensuring that each update moves towards improving predictive capabilities. This preserves the data-driven advantages of the XGBoost model while enhancing the reliability and user experience consistency of the entire overcurrent protection system during long-term operation.

[0076] In summary, this embodiment stores the data in a sample pool after each fast-charging data collection and determines whether the accumulated sample size reaches a preset threshold. If it does, a candidate threshold set for each parameter is generated based on the data distribution of these samples and the battery's overcurrent physical characteristics. Subsequently, the root node is split using the model, the splitting gain of each split node is calculated, multiple decision trees are constructed, and the target risk threshold and target overcurrent weight are extracted from them. Finally, without exceeding the adjustment range threshold, the original risk threshold is replaced with the one that maximizes the splitting gain, and the overcurrent calculation weight is progressively adjusted.

[0077] This embodiment, based on candidate thresholds generated from real fast charging data distribution, avoids subjective biases caused by manual setting, while maximizing split gain ensures that the selected threshold has the strongest discriminative power. Simultaneously, the preset adjustment range limit in this embodiment effectively suppresses false protection or oscillations caused by parameter mutations, thereby significantly improving the accuracy and generalization ability of overcurrent prediction.

[0078] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S30 of the fast charging overcurrent protection method further includes steps S31 to S33: Step S31: If the time during which the overcurrent probability is in the preset first overcurrent interval exceeds the preset first time threshold, then the current reduction value of the fast charging overcurrent protection is determined based on the overcurrent probability. It should be noted that the first overcurrent range refers to a preset overcurrent probability range. In this embodiment, the first overcurrent range can be (30, 80), representing a slight overcurrent risk level. The first time threshold refers to the duration condition required to determine whether to trigger current reduction protection. In this embodiment, the first time threshold can be 20 seconds. The current reduction value refers to the amount of charging current reduction calculated based on the current overcurrent probability, used to perform a stepped current reduction operation.

[0079] In this embodiment, based on the graded protection implemented in step S30, it is further refined into step S31: when the overcurrent probability is detected to be in the first overcurrent range, and the duration of this state exceeds a preset first time threshold, the system no longer maintains the original charging current, but calculates the corresponding current reduction value according to the specific value of the current overcurrent probability and a preset rule. The specific calculation rule includes a 15% current reduction for every 10% increase in risk. For example, when the overcurrent probability is 50%, the corresponding current reduction is 30%. This embodiment achieves a quantitative response to minor overcurrent risks through the above steps, avoiding false triggering of current reduction due to instantaneous fluctuations, while ensuring timely suppression of current growth when the real risk persists, preventing the risk from escalating.

[0080] Understandably, because this embodiment linearly maps the current reduction value to the overcurrent probability, it effectively filters out short-term noise interference while ensuring response sensitivity. This design avoids frequent malfunctions caused by relying solely on instantaneous thresholds in traditional solutions, and also overcomes the charging efficiency loss caused by premature intervention without a time confirmation mechanism. Furthermore, the stepped current reduction strategy ensures that current adjustment is strictly matched to the risk level, both slowing down the overcurrent development trend and maximizing the retention of usable charging power, significantly improving the user's charging experience and system safety.

[0081] Step S32: Reduce the charging current of fast charging based on the current reduction value until the time when the overcurrent probability is in the preset safe overcurrent range exceeds the preset safe time threshold, wherein the first overcurrent range is higher than the safe overcurrent range. It should be noted that the safe overcurrent range refers to a preset low-risk overcurrent probability range. In this embodiment, the safe overcurrent range can be [0, 30], indicating that the system is in a safe state and no intervention is required. The safe time threshold refers to the duration required to determine that the risk has sufficiently subsided and full-power charging can be resumed. In this embodiment, the safe time threshold can be 10 seconds.

[0082] It is understood that, after determining the current reduction value, this embodiment immediately reduces the fast charging current according to the current reduction value and continuously monitors the change in the overcurrent probability. Under this current reduction state, the risk is determined to be effectively eliminated only when the overcurrent probability falls back to the safe overcurrent range and is maintained in this state for more than the preset safe time threshold. This ensures that the current reduction measure not only responds in a timely manner, but also that the exit conditions have sufficient time to be verified, avoiding repeated rises and falls in current due to short-term fluctuations, and ensuring the stability of the charging process and the thermal stability of the battery system.

[0083] Step S33: If the time during which the overcurrent probability is in the preset second overcurrent interval exceeds the preset second time threshold, then fast charging is stopped and a notification is sent through a preset associated application.

[0084] It should be noted that the second overcurrent range refers to a preset high-risk overcurrent probability range, which is (80, 100] in this patent, representing a severe overcurrent risk level. The second time threshold refers to the duration condition required to determine whether to trigger a forced charging stop; in this embodiment, the second time threshold is 30 seconds. The associated application refers to a user terminal application bound to the vehicle or charging system, used to push safety alarm information to the user.

[0085] Understandably, when the system detects that the overcurrent probability is in the second overcurrent range and this state lasts for more than a preset second time threshold, it determines that there is a serious overcurrent risk and immediately performs a forced stop to fast charging, cutting off the charging circuit. At the same time, it sends a real-time notification to the user through a preset associated application, explaining that charging has been interrupted due to a safety risk and suggesting subsequent actions. This effectively avoids false power outages caused by instantaneous spikes or sensor noise, while ensuring timely intervention when a real serious overcurrent risk persists.

[0086] In one feasible implementation, the specific implementation of fast charging overcurrent protection based on the overcurrent probability can also be: The system determines whether the time during which the current load ratio is higher than the current risk threshold exceeds a preset mandatory protection time threshold, or whether the time during which the highest voltage is higher than the voltage risk threshold exceeds the mandatory protection time threshold. If either exceeds the threshold, fast charging is stopped, and a notification is sent through a preset associated application.

[0087] It should be noted that the mandatory protection time threshold refers to the continuous over-limit tolerance time set for key physical parameters (such as current load ratio and maximum voltage). In this embodiment, the mandatory protection time threshold can be 30 seconds, which is used to trigger the hard safety protection mechanism.

[0088] Understandably, this embodiment continuously monitors the current load ratio and the maximum voltage, determining whether the duration of exceeding the corresponding current risk threshold or voltage risk threshold reaches a preset mandatory protection time threshold. If either condition is met, regardless of the current overcurrent probability value, a fast charging stop operation is immediately executed, and a safety alarm notification is sent to the user through a preset associated application. This provides a reliable protection path when the AI ​​model may fail due to data latency, complex feature coupling, or extreme operating conditions.

[0089] In addition to probability-based intelligent protection, this embodiment adds a dual hard threshold mandatory protection mechanism based on current load ratio and maximum voltage. It requires that the over-limit state persist for more than a mandatory protection time threshold before charging is triggered, avoiding the risk of missed detections in edge scenarios using pure AI methods. Furthermore, a time confirmation mechanism prevents malfunctions caused by transient interference. Therefore, this embodiment significantly enhances the safety redundancy capability of the fast charging system under extreme or abnormal operating conditions, ensuring that even with insufficient model confidence, it can still promptly cut off dangerous sources based on clear electrochemical safety boundaries.

[0090] In summary, this embodiment provides graded protection for the vehicle's fast charging process based on the real-time overcurrent probability during charging and the duration of that overcurrent probability. Furthermore, this embodiment also includes a hard protection mechanism independent of the overcurrent probability; if the current load or maximum voltage exceeds a preset threshold for a preset time, forced charging is triggered.

[0091] This embodiment effectively filters out transient noise interference by introducing a duration threshold, avoiding accidental current reduction or power outages. Furthermore, it achieves precise power regulation by linearly linking the current reduction value to the risk probability, balancing efficiency and safety. A robust protection mechanism ensures that even when model predictions are inaccurate, the dangerous source can still be promptly cut off based on the electrochemical safety boundary. Therefore, this embodiment significantly reduces the overcurrent accident rate and ensures the stability of the charging process through the above steps.

[0092] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the fast charging overcurrent protection method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0093] The fast charging overcurrent protection device provided in this application, employing the fast charging overcurrent protection method in the above embodiments, can solve the technical problem of high false overcurrent alarm rate. Compared with the prior art, the beneficial effects of the fast charging overcurrent protection device provided in this application are the same as those of the fast charging overcurrent protection method provided in the above embodiments, and other technical features in the fast charging overcurrent protection device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0094] This application provides a fast charging overcurrent protection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the fast charging overcurrent protection method in the first embodiment described above.

[0095] The following is for reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing the fast charging overcurrent protection device in the embodiments of this application. The fast charging overcurrent protection device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, tablets, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The fast charging overcurrent protection device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0096] like Figure 4As shown, the fast-charging overcurrent protection device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the fast-charging overcurrent protection device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the fast-charging overcurrent protection device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows fast-charging overcurrent protection devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0097] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0098] The fast charging overcurrent protection device provided in this application, employing the fast charging overcurrent protection method in the above embodiments, can solve the technical problem of high false overcurrent alarm rate. Compared with the prior art, the beneficial effects of the fast charging overcurrent protection device provided in this application are the same as those of the fast charging overcurrent protection method provided in the above embodiments, and other technical features of the fast charging overcurrent protection device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0099] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0100] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0101] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the fast charging overcurrent protection method in the above embodiments.

[0102] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0103] The aforementioned computer-readable storage medium may be included in the fast charging overcurrent protection device; or it may exist independently and not assembled into the fast charging overcurrent protection device.

[0104] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the fast charging overcurrent protection device, cause the fast charging overcurrent protection device to perform the aforementioned fast charging overcurrent protection method.

[0105] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0107] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0108] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described fast charging overcurrent protection method, thereby solving the technical problem of high false overcurrent alarm rate. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the fast charging overcurrent protection method provided in the above embodiments, and will not be repeated here.

[0109] All user-related data involved in this application was obtained with the user's permission or consent, as per [reference]. Figure 5 In other words, when this application is applied to a specific product or technology, user permission is required to acquire and process the relevant data, and the processing of the relevant data must comply with the relevant laws, regulations and regulatory standards of the relevant countries and regions.

[0110] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A fast charging overcurrent protection method, characterized in that, The method includes: Based on a preset sampling frequency, fast charging data during the fast charging process is acquired in real time, wherein the fast charging data includes charging parameters and battery operating parameters during fast charging. Based on the fast charging data, the preset risk mapping logic, the preset risk calculation formula, and the predetermined overcurrent calculation weight, the overcurrent probability of fast charging is calculated. Based on the overcurrent probability, fast charging overcurrent protection is implemented.

2. The method as described in claim 1, characterized in that, The step of calculating the overcurrent probability of fast charging based on the fast charging data, preset risk mapping logic, preset risk calculation formula, and predetermined overcurrent calculation weight includes: Based on the charging parameters, the battery operating condition parameters, and the preset risk mapping logic, a first risk mapping value corresponding to the charging parameters and a second risk mapping value corresponding to the battery operating condition parameters are determined. The overcurrent probability is calculated based on the first risk mapping value, the second risk mapping value, the risk calculation formula, and the overcurrent calculation weight.

3. The method as described in claim 2, characterized in that, The charging parameters include charging current, maximum charging voltage, and requested current; the battery operating condition parameters include maximum battery temperature and battery health; the first risk mapping value includes a current risk mapping value and a voltage risk mapping value; the second risk mapping value includes a temperature risk mapping value and a health risk mapping value; the step of determining the first risk mapping value corresponding to the charging parameters and the second risk mapping value corresponding to the battery operating conditions based on the charging parameters, the battery operating condition parameters, and a preset risk mapping logic includes: Calculate the current load ratio of the charging current and the requested current; The current risk mapping value is determined based on the current load ratio and the current risk threshold in the risk mapping logic; The voltage risk mapping value is determined based on the highest voltage and the voltage risk threshold in the risk mapping logic; The temperature risk mapping value is determined based on the battery's highest temperature and the temperature risk threshold in the risk mapping logic; Calculate the difference between the preset maximum risk value and the battery health status, and use the difference as the health risk mapping value.

4. The method as described in claim 1, characterized in that, After the step of acquiring fast charging data in real time based on a preset sampling frequency, the method further includes: The acquired fast charging data is used as sample data, and it is determined whether the number of fast charging data in the sample data reaches a preset threshold. If the quantity threshold is reached, the data distribution of the sample data and the overcurrent physical characteristics of fast charging are determined based on each of the fast charging data. Based on the data distribution and the overcurrent physical characteristics, the target risk threshold and target overcurrent weight are determined; The risk mapping logic is adjusted based on the target risk threshold, and the overcurrent calculation weight is adjusted based on the target overcurrent weight.

5. The method as described in claim 4, characterized in that, The steps of determining the target risk threshold and target overcurrent weight based on the data distribution and the overcurrent physical characteristics include: Based on the data distribution and the physical characteristics, a candidate threshold set corresponding to each type of parameter in the sample data is determined, wherein the candidate threshold set includes multiple candidate thresholds; Based on the candidate threshold and the fast charging data, the parameter in the fast charging data is used as the root node, the root node is split, the split gain of each split node is calculated, a corresponding number of decision trees are obtained, and the split node obtained from each decision tree is used as the target risk threshold. Calculate the sum of the split gains of each split node in each decision tree to obtain the total decision tree gain for each decision tree; Calculate the sum of the total gains of each decision tree to obtain the optimized total gain; Calculate the ratio of the total gain of each of the aforementioned parameters to the total optimized gain, and use the calculated ratio as the corresponding target overcurrent weight.

6. The method as described in claim 5, characterized in that, The risk mapping logic includes an initial risk threshold. The steps of adjusting the risk mapping logic based on the target risk threshold and adjusting the overcurrent calculation weight based on the target overcurrent weight include: Calculate the difference between each target risk threshold and the original risk threshold to obtain the risk threshold change value; Calculate the ratio of the risk threshold change value to the original risk threshold to obtain the threshold adjustment range of each target risk threshold relative to the original risk threshold; The target risk threshold with the largest split gain, whose threshold adjustment range does not exceed the preset adjustment range threshold, is selected and replaced with the original risk threshold. Calculate the difference between the target overcurrent weight and the calculated overcurrent weight to obtain the weight change value; Calculate the ratio of the weight change value to the overcurrent calculation weight to obtain the weight adjustment range; Determine whether the weight adjustment range is higher than the adjustment range threshold. If it is higher, adjust the overcurrent calculation weight based on the adjustment range threshold.

7. The method as described in claim 1, characterized in that, The steps for performing fast charging overcurrent protection based on the overcurrent probability include: If the time during which the overcurrent probability is within a preset first overcurrent range exceeds a preset first time threshold, then the current reduction value of the fast charging overcurrent protection is determined based on the overcurrent probability. Based on the current reduction value, the charging current of fast charging is reduced until the time when the overcurrent probability is in the preset safe overcurrent range exceeds the preset safe time threshold, wherein the first overcurrent range is higher than the safe overcurrent range. If the overcurrent probability remains within a preset second overcurrent range for a period exceeding a preset second time threshold, fast charging will be stopped, and a notification will be sent via a preset associated application.

8. The method as described in claim 3, characterized in that, The step of performing fast charging overcurrent protection based on the overcurrent probability further includes: Determine whether the time during which the current load ratio is higher than the current risk threshold exceeds a preset mandatory protection time threshold, or whether the time during which the highest voltage is higher than the voltage risk threshold exceeds the mandatory protection time threshold; If the limit is exceeded, fast charging will stop and a notification will be sent through a pre-set associated app.

9. A fast charging overcurrent protection device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fast charging overcurrent protection method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the fast charging overcurrent protection method as described in any one of claims 1 to 8.

Images