Vehicle battery monitoring method, electronic equipment and vehicle

Abstract

The invention relates to the technical field of vehicle batteries, and provides a vehicle battery monitoring method, electronic equipment and a vehicle, and the method comprises the steps: determining the harmonic distortion rate of a vehicle battery, obtaining the state information of the vehicle battery, and determining a predicted battery health state value according to the harmonic distortion rate and the state information of the battery; in response to the harmonic distortion rate and / or the predicted battery health state value meeting a preset battery abnormal condition, obtaining battery operation information, and determining a target abnormal reason according to the harmonic distortion rate, the battery state information and the battery operation information; and determining a target battery maintenance strategy according to the target abnormal reason, and outputting the target battery maintenance strategy. According to the method, the corresponding target battery maintenance strategy is determined by analyzing the target abnormal reason, accurate monitoring and early warning of the vehicle battery are realized, and the corresponding maintenance strategy is provided for the user, so that the user can maintain the vehicle battery in advance, normal vehicle use of the user is prevented from being affected by battery aging, and the user experience is improved. And the vehicle use experience of the user is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle battery technology, and in particular to a vehicle battery monitoring method, electronic equipment, and vehicle. Background Technology

[0002] Performance degradation and sudden failures of vehicle batteries are key factors affecting vehicle reliability. Currently, battery health is mainly assessed by monitoring basic parameters such as voltage, current, and temperature. This relies on fixed thresholds and cannot detect the aging of the battery's internal microstructure, resulting in poor accuracy in battery life prediction and an inability to provide users with reliable battery replacement or maintenance advice. Summary of the Invention

[0003] In view of this, the purpose of this disclosure is to propose a vehicle battery monitoring method, electronic device and vehicle to solve the problems that the current battery health status relies on fixed thresholds for judgment, cannot detect the aging of the battery's internal microstructure, resulting in poor accuracy in battery life prediction and inability to provide users with reliable battery replacement or maintenance advice.

[0004] To achieve the above objectives, a first aspect of this disclosure provides a vehicle battery monitoring method, the method comprising:

[0005] Determine the harmonic distortion rate of the vehicle battery, obtain the vehicle battery status information, and determine the predicted battery health status value based on the harmonic distortion rate and the battery status information. In response to the harmonic distortion rate and / or the predicted battery health status value meeting preset battery abnormality conditions, battery operation information is obtained, and the cause of the target abnormality is determined based on the harmonic distortion rate, the battery status information, and the battery operation information. Determine the target battery maintenance strategy based on the cause of the target anomaly, and output the target battery maintenance strategy.

[0006] Based on the same inventive concept, a second aspect of this disclosure proposes a vehicle battery monitoring device, comprising: The data acquisition module is configured to determine the harmonic distortion rate of the vehicle battery, acquire vehicle battery status information, and determine a predicted battery health status value based on the harmonic distortion rate and the battery status information. The abnormal cause determination module is configured to, in response to the harmonic distortion rate and / or the predicted battery health status value satisfying a preset battery abnormal condition, acquire battery operating information and determine the target abnormal cause based on the harmonic distortion rate, the battery status information and the battery operating information; The strategy determination module is configured to determine a target battery maintenance strategy based on the cause of the target anomaly and output the target battery maintenance strategy.

[0007] Based on the same inventive concept, a third aspect of this disclosure proposes an electronic device including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor, when executing the computer program, implements the vehicle battery monitoring method as described above.

[0008] Based on the same inventive concept, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the vehicle battery monitoring method as described above.

[0009] Based on the same inventive concept, the fifth aspect of this disclosure provides a vehicle including the vehicle battery monitoring device described in the second aspect, the electronic device described in the third aspect, or the storage medium described in the fourth aspect.

[0010] As can be seen from the above, this disclosure proposes a vehicle battery monitoring method, electronic device, and vehicle. It determines the harmonic distortion rate (HCR) of the vehicle battery, acquires the vehicle battery status information, and determines a predicted battery health status value based on the HCR and the battery status information. The HCR reflects the nonlinear changes within the battery. By considering the battery's HCR when predicting the battery health status value, early, non-destructive detection of microscopic aging such as plate sulfation is achieved, overcoming the limitations of traditional external parameter monitoring. When the HCR and / or the predicted battery health status value meet preset battery abnormality conditions, it indicates that the battery may subsequently experience an abnormality. The cause of the abnormality should be determined, and preventative measures should be taken in advance. Battery operating information is acquired, and the target abnormality cause is determined based on the HCR, the battery status information, and the battery operating information. A target battery maintenance strategy is determined based on the target abnormality cause, and the target battery maintenance strategy is output. By analyzing the causes of target anomalies, corresponding target battery maintenance strategies are determined, enabling accurate monitoring and early warning of vehicle batteries. This provides users with corresponding maintenance strategies to maintain vehicle batteries in advance, avoiding disruptions to normal vehicle use due to battery aging and improving the user experience. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a vehicle battery monitoring method according to an embodiment of the present disclosure; Figure 2 This is a structural block diagram of a vehicle battery monitoring device according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0014] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0015] The following are definitions of terms used in this disclosure: SOH: Vehicle SOH (State of Health) is a core indicator for measuring the aging of power batteries. It is expressed as a percentage, representing the ratio of the current maximum usable capacity to the factory rated capacity.

[0016] THD: Total Harmonic Distortion (THD) is a key indicator for measuring the degree of signal waveform distortion. It is defined as the percentage of the square root of the sum of the squares of the effective values ​​of all harmonic components to the effective value of the fundamental component. The lower the THD value, the closer the signal is to an ideal sine wave, and the higher the power quality. Conversely, a higher THD value indicates severe harmonic pollution, which may cause equipment overheating, malfunctions, or increased power grid losses.

[0017] OTA: Over-the-Air (OTA) refers to the direct wireless push and installation of upgrade packages via mobile networks or Wi-Fi, allowing mobile phones, automotive devices, and other equipment to remotely update system firmware, applications, or configurations without connecting to a computer or disassembling them, thereby enabling rapid bug fixes, feature iterations, and reduced maintenance costs.

[0018] AM-GRU: AM-GRU (Attention-Mechanism Gated Recurrent Unit) is a hybrid sequence model that introduces an attention mechanism on top of the Gated Recurrent Unit (GRU). It first uses the GRU to capture long-range dependencies in the time series, and then uses the attention layer to adaptively assign weights to key time steps, thereby highlighting important features, suppressing redundant information, and significantly improving prediction accuracy and interpretability.

[0019] BMS: The vehicle BMS (Battery Management System) is the "brain" of the electric vehicle's power battery. It monitors the voltage, current, and temperature of each cell in real time. Through equalization, thermal management, and safety protection strategies, it ensures that the battery is charged and discharged efficiently within a safe range, extends its lifespan, and prevents risks such as overcharging, over-discharging, and short circuits. At the same time, it reports key status information to the vehicle controller, providing accurate data support for range estimation, energy recovery, and driving strategies.

[0020] ADC chip: The vehicle's ADC chip is responsible for converting the analog signals output by sensors such as cameras, millimeter-wave radar, and lidar into digital code streams in real time and with high precision, providing high-fidelity, low-latency raw data for autonomous driving domain control. Its sampling rate, bit width, and anti-interference capability directly determine the recognition accuracy of perception algorithms for complex road conditions and the system's safety redundancy.

[0021] Performance degradation and sudden failures of vehicle batteries are key factors affecting vehicle reliability. Currently, battery health is mainly assessed by monitoring basic parameters such as voltage, current, and temperature, but relying on fixed thresholds has significant limitations. Firstly, relying on fixed thresholds for judgment, such as triggering an alarm when the voltage falls below a certain value, fails to detect the aging of the battery's internal microstructure, such as plate sulfation and SEI film growth, resulting in delayed warnings and a high false alarm rate. Secondly, related technologies use only single types of data, such as analyzing only the variance of charge / discharge rates or comparing only historical voltage curves, which has poor adaptability to changes in operating conditions such as ambient temperature and charge / discharge rates, and the accuracy of long-term estimations easily degrades. Finally, although there are detection methods such as no-load voltage and start-up voltage, these cannot achieve non-destructive and continuous internal state monitoring during charge / discharge cycles without requiring system separation.

[0022] In addition, while existing vehicle-to-everything (V2X) solutions can collect data, they lack analysis of the root causes affecting battery life (SOH), such as the combined effects of multiple factors including driving habits, charging behavior, and temperature conditions. This makes it difficult to provide forward-looking and personalized maintenance recommendations, resulting in poor accuracy in battery life prediction and an inability to provide users with reliable battery replacement or maintenance advice.

[0023] Therefore, there is an urgent need for a technical solution that can accurately and early warn of battery aging during daily vehicle use and guide optimized usage. To address the above problems, this embodiment proposes a vehicle battery monitoring method, such as... Figure 1 As shown, the method includes: Step 101: Determine the harmonic distortion rate of the vehicle battery, obtain the vehicle battery status information, and determine the predicted battery health status value based on the harmonic distortion rate and the battery status information.

[0024] In practice, the harmonic distortion rate of the vehicle battery is determined, wherein the harmonic distortion rate is the harmonic distortion rate of the vehicle battery voltage, which reflects the proportion of higher harmonics of the voltage relative to the fundamental frequency.

[0025] In this embodiment, after the vehicle is turned off and enters sleep mode, a high-frequency, low-amplitude sine wave signal is generated by a dedicated circuit in the vehicle terminal. For example, the frequency of the sine wave signal is 1kHz. The sine wave signal is injected through the positive and negative terminals of the battery, and then a high-precision ADC chip acquires the voltage response signal across the battery terminals at a rate higher than the Nyquist frequency. The voltage harmonic distortion rate of the vehicle battery is calculated based on the acquired voltage response signal.

[0026] Specifically, the calculation process for the voltage harmonic distortion rate of the vehicle battery includes: The voltage response signal is a time-domain signal. It is converted to a frequency-domain signal using a Fast Fourier Transform. In this embodiment, the focus is on the amplitude variations of odd harmonics, such as the 3rd and 5th harmonics. The voltage harmonic distortion rate is expressed by the formula:

[0027] Where THD is the voltage harmonic distortion rate, V1 is the effective value of the fundamental voltage, and Vn is the effective value of the nth harmonic voltage. Experiments show that the THD value of aged batteries can be increased by 20% to 50% compared to new batteries, and they are extremely sensitive to microscopic changes such as plate sulfation.

[0028] The vehicle battery status information is acquired, and a predicted battery health status value is determined based on the harmonic distortion rate and the battery status information. The predicted battery health status value reflects the health status of the vehicle battery over a future period.

[0029] In this embodiment, the battery status information reflects the actual state of the vehicle battery. The battery status information includes the battery internal resistance and battery temperature. The battery internal resistance refers to the resistance encountered when current passes through the inside of the battery, which is the sum of various impedances inside the battery.

[0030] Step 102: In response to the harmonic distortion rate and / or the predicted battery health status value meeting the preset battery abnormality conditions, obtain battery operation information, and determine the cause of the target abnormality based on the harmonic distortion rate, the battery status information, and the battery operation information.

[0031] In specific implementation, in response to the harmonic distortion rate and / or the predicted battery health status value meeting the preset battery abnormality conditions, battery operation information is obtained. The battery operation information is relevant information of the vehicle battery during operation, and specifically includes the actual battery output voltage and the actual battery output current.

[0032] In this embodiment, the preset battery abnormality condition is a condition that needs to be set beforehand to determine that the vehicle battery is abnormal. Specifically, the preset battery abnormality condition is that the rate of decline of the battery health status value is greater than a preset decline threshold, or the rate of increase of the harmonic distortion rate is greater than a preset increase threshold. That is, the preset battery abnormality condition is met when the battery health status value deteriorates rapidly or the harmonic distortion rate increases abnormally.

[0033] Therefore, when determining whether a preset battery abnormality condition is met based on the harmonic distortion rate and the predicted battery health status value, the harmonic distortion rate is compared with the historical harmonic distortion rate to determine the rate of increase of the harmonic distortion rate. The predicted battery health status value is compared with the current battery health status value to determine the rate of decrease of the battery health status value. If the rate of decrease of the battery health status value is greater than a preset decrease threshold, and / or the rate of increase of the harmonic distortion rate is greater than a preset increase threshold, the preset battery abnormality condition is determined to be met.

[0034] After acquiring battery operating information, the target anomaly cause is determined based on the harmonic distortion rate, the battery status information, and the battery operating information. The target anomaly cause is the reason that leads to the battery malfunction.

[0035] Step 103: Determine the target battery maintenance strategy based on the cause of the target anomaly, and output the target battery maintenance strategy.

[0036] In practice, a target battery maintenance strategy is determined based on the target cause of the anomaly, and then output. This target battery maintenance strategy is a preventative strategy to address the anticipated battery anomaly caused by the target cause, in order to avoid battery malfunctions.

[0037] In this embodiment, the target battery maintenance strategy corresponding to the target abnormality can be determined by searching the database based on the target abnormality cause. The database stores the correspondence between abnormality causes and battery maintenance strategies.

[0038] For example, if the cause of the target anomaly is determined to be insufficient charging, then the target battery maintenance strategy corresponding to the cause of the target anomaly is to recommend a long-distance drive (greater than 30 minutes) once a week to fully charge the battery.

[0039] In another example, if the cause of the target anomaly is determined to be the influence of high temperature, then the corresponding target battery maintenance strategy is to avoid prolonged exposure of vehicles to direct sunlight. For a fleet of vehicles, optimal maintenance station routes can be planned.

[0040] In this embodiment, when determining the target battery maintenance strategy, the specific user's driving scenario can also be considered to obtain a battery maintenance strategy that better suits the actual driving scenario. Specifically, user driving scenario tags are identified, such as primarily short-distance commuting in the city, frequent ride-hailing operations, frequent long-distance highway driving, lack of fixed parking spaces, and difficulty in home charging. These tags can be automatically obtained by analyzing data such as mileage, charging locations, and time distribution.

[0041] A knowledge base is pre-maintained, containing optimal and user-executable maintenance operation suggestions for different anomaly causes and in different scenarios. Once the root cause analysis results and user scenarios are determined, the corresponding rules are matched from the knowledge base to obtain the target battery maintenance strategy.

[0042] The above scheme determines the harmonic distortion rate of the vehicle battery, obtains the vehicle battery status information, and determines the predicted battery health status value based on the harmonic distortion rate and the battery status information. The harmonic distortion rate reflects the nonlinear changes within the battery. By considering the battery's harmonic distortion rate when predicting the battery health status value, early and non-destructive detection of micro-aging processes such as plate sulfation is achieved, overcoming the limitations of traditional external parameter monitoring. If the harmonic distortion rate and / or the predicted battery health status value meet preset battery abnormality conditions, it indicates that the battery may subsequently experience an abnormality. The cause of the abnormality should be determined, and preventative measures should be taken in advance. Battery operating information is obtained, and the target abnormality cause is determined based on the harmonic distortion rate, the battery status information, and the battery operating information. A target battery maintenance strategy is determined based on the target abnormality cause and outputs the target battery maintenance strategy. By analyzing the causes of target anomalies, corresponding target battery maintenance strategies are determined, enabling accurate monitoring and early warning of vehicle batteries. This provides users with corresponding maintenance strategies to maintain vehicle batteries in advance, avoiding disruptions to normal vehicle use due to battery aging and improving the user experience.

[0043] In some embodiments, after determining the harmonic distortion rate, it can be coupled with the internal resistance growth value for analysis. If there is a strong positive correlation between the harmonic distortion rate and the internal resistance growth value, such as a correlation greater than 0.8, then the battery aging is determined to be caused by the deterioration of the battery's internal chemical properties. That is, the target cause of the battery abnormality is the deterioration of the battery's internal chemical properties, which significantly improves the diagnostic confidence.

[0044] In this embodiment, the internal resistance increase value is the internal resistance increase value measured by the AC injection method. This involves applying a small-amplitude AC signal of a specific frequency to the battery and then measuring the AC voltage response generated across the battery terminals. The AC impedance value at that frequency can be calculated using Ohm's law, and this AC impedance value is very close to the battery's ohmic or DC internal resistance. Comparing the AC impedance value with the current actual internal resistance value yields the internal resistance increase value.

[0045] In some embodiments, the battery state information includes the actual battery internal resistance. When determining the predicted battery health state value, the battery internal resistance and harmonic distortion rate are considered comprehensively. That is, the step 101 of determining the predicted battery health state value based on the harmonic distortion rate and the battery state information specifically includes: Step 1011: Obtain the actual energy throughput and total energy throughput of the vehicle battery at the current moment, and determine the target capacity decay value based on the actual energy throughput and the total energy throughput; Step 1012: Determine the predicted battery health status value based on the target capacity decay value, the actual battery internal resistance, and the harmonic distortion rate.

[0046] In specific implementation, the actual energy throughput and total energy throughput of the vehicle battery at the current moment are obtained, wherein the total energy throughput of the vehicle battery remains constant throughout its lifespan. Then, a target capacity decay value is determined based on the actual energy throughput and the total energy throughput, wherein the target capacity decay value is expressed by the formula:

[0047] in, The target capacity decay value, The rated capacity of the battery. To preset the empirical coefficient, For actual energy throughput, This represents the total energy throughput.

[0048] After determining the target capacity decay value, a predicted battery health state value is determined based on the target capacity decay value, the actual battery internal resistance, and the harmonic distortion rate. The specific process for determining the predicted battery health state value includes: Step 10121: Obtain a preset standard capacity decay value, and determine a first health status value based on the target capacity decay value and the standard capacity decay value; Step 10122: Obtain the standard battery internal resistance, and determine the second health state value based on the actual battery internal resistance and the standard battery internal resistance; Step 10123: Determine the third health state value based on the harmonic distortion rate, determine the target fusion weight, and perform weighted processing on the first health state value, the second health state value, and the third health state value based on the target fusion weight to obtain the predicted battery health state value.

[0049] In practice, a preset standard capacity decay value is obtained, and a first health status value is determined based on the target capacity decay value and the standard capacity decay value. Specifically, the target capacity decay value and the standard capacity decay value are compared, and the resulting first ratio is the first health status value.

[0050] Obtain the internal resistance of a standard battery, and determine a second health state value based on the actual battery internal resistance and the standard battery internal resistance. Specifically, the ratio of the actual battery internal resistance to the standard battery internal resistance is calculated to obtain a second ratio. The difference between a first preset coefficient and the second ratio is then calculated, and the difference is the second health state value.

[0051] The third health status value is determined based on the harmonic distortion rate. Specifically, the difference between the second preset coefficient and the harmonic distortion rate is the third health status value.

[0052] To determine the target fusion weight, specifically, since temperature has a significant impact on the internal chemical state of the battery, that is, temperature has a significant impact on the battery's internal resistance and harmonic distortion rate, the ambient temperature of the current vehicle environment can be obtained, and the fusion weight corresponding to the ambient temperature can be determined based on the ambient temperature.

[0053] In this embodiment, since low temperature has a more significant impact on the internal chemical state of the battery, the fusion weights corresponding to the second and third health state values ​​are higher in a low temperature environment, while the fusion weight corresponding to the first health state value is lower.

[0054] The first health status value, the second health status value, and the third health status value are weighted according to the target fusion weight to obtain a predicted battery health status value, wherein the predicted battery health status value is expressed by the formula:

[0055] in, To predict battery health status values, This is the standard capacity decay value. This represents the actual internal resistance of the battery. The internal resistance of a standard battery, , , To merge weights, and It is understood that the predicted health status value is a specific numerical coefficient, which does not include units of measurement. Therefore, when calculating the predicted health status value, the parameters on the right side of the formula are also calculated without units of measurement, using only the specific numerical value.

[0056] The above scheme comprehensively considers multiple sources of information, such as energy throughput, THD, and internal resistance, when determining the predicted health status value. In other words, it abandons the single model and integrates multiple sources of information such as energy throughput, THD, and internal resistance through dynamic weighting, so that the determination of the predicted health status value is more robust and accurate when facing complex operating conditions such as temperature changes and different driving habits.

[0057] In some embodiments, when preset abnormal conditions are met, it is necessary to determine the cause of the target abnormality. To ensure the accuracy of the cause of the target abnormality, the harmonic distortion rate, the battery status information, and the battery operation information are analyzed from multiple perspectives. That is, determining the cause of the target abnormality based on the harmonic distortion rate, the battery status information, and the battery operation information in step 102 specifically includes: Step 1021: Obtain the pre-trained anomaly detection model, input the harmonic distortion rate, the battery state information and the battery operation information into the anomaly detection model, and process them through the anomaly detection model to obtain the first set of anomaly causes; Step 1022: Determine predicted operating information based on the harmonic distortion rate and the battery status information; determine a second set of abnormal causes based on the predicted operating information and the battery operating information. Step 1023: Determine the third set of abnormal causes based on the battery operation information and historical battery fault information; Step 1024: Take the same cause in the first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes as the target abnormal cause.

[0058] In specific implementation, a pre-trained anomaly detection model is obtained, and the harmonic distortion rate, the battery state information, and the battery operation information are input into the anomaly detection model. The anomaly detection model processes these information to obtain a first set of anomaly causes. This first set of anomaly causes includes at least one first anomaly cause.

[0059] In this embodiment, the training process of the anomaly detection model specifically includes: Obtain a training dataset and an initial anomaly detection model. The training dataset includes historical harmonic distortion rate, historical battery state information, historical battery operation information, and a set of historical anomaly causes. Input the training data from the training dataset into the initial anomaly detection model for training. Determine if a preset training termination condition is met to obtain the anomaly detection model.

[0060] The preset training termination condition includes at least one of the following: determining that all data in the training dataset has been input into the initial anomaly detection model for training, determining that the loss function of the initial anomaly detection model has converged to the convergence threshold, or determining that the initial anomaly detection model has been iterated for training to a preset number of iterations.

[0061] For example, the preset training termination condition is that all data in the training dataset has been input into the initial anomaly detection model for training: The training dataset contains fifty sets of data, each set including historical harmonic distortion rate, historical battery status information, historical battery operation information, and a set of historical anomaly causes. The preset training termination condition is that all data in the training dataset has been input into the initial anomaly detection model for training. That is, when all fifty sets of data have been input into the initial anomaly detection model, there is no training data in the training dataset that has not yet been input into the initial anomaly detection model. At this point, the initial anomaly detection model training is considered complete, and the anomaly detection model is obtained.

[0062] Another example is that the training termination condition is determined by ensuring that the loss function of the initial anomaly detection model converges to a convergence threshold: Training data from the training dataset is input into the initial anomaly detection model for training, and the training results are output. A loss function is determined based on the training results and the historical anomaly cause set. The loss function may include at least one of the following: mean squared error loss function, cross-entropy loss function, logarithmic loss function, exponential loss function, squared loss function, or absolute value loss function, etc. When the loss function converges to a convergence threshold, a preset training termination condition is met, and the anomaly detection model is obtained.

[0063] Another example is that the preset training termination condition is to determine the initial anomaly detection model to be trained iteratively to a preset number of iterations.

[0064] The training data in the training dataset is input into the initial anomaly detection model for iterative training. The number of iterations is recorded. When the number of iterations equals the preset number of iterations, the preset training termination condition is met, and the anomaly detection model is obtained.

[0065] In this embodiment, the anomaly detection model employs unsupervised learning algorithms such as Isolation Forest to perform anomaly detection in a high-dimensional feature space constructed from battery operating information, battery state information, and harmonic distortion rate. This effectively identifies which parameter combinations deviate from the normal pattern, thereby quickly locating the anomaly. For example, the first set of identified anomaly causes may be an abnormal increase in the internal resistance of a certain cell or a deterioration in the temperature uniformity of the entire battery pack.

[0066] Based on the harmonic distortion rate and the battery state information, predicted operating information is determined, and based on the predicted operating information and the battery operating information, a second set of abnormal causes is determined. The predicted operating information is the predicted operating information of the battery after a certain period of time, and the second set of abnormal causes contains at least one second abnormal cause.

[0067] Based on the battery operation information and historical battery fault information, a third set of abnormal causes is determined. The first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes are traversed. The common causes in the first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes are taken as target abnormal causes. That is, the intersection of the first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes is selected as the target abnormal cause.

[0068] For example, if the first set of abnormal causes includes abnormal cause A and abnormal cause B, the second set of abnormal causes includes abnormal cause A, abnormal cause C and abnormal cause D, and the third set of abnormal causes includes abnormal cause A and abnormal cause E, then abnormal cause A will be used as the target abnormal cause.

[0069] In some embodiments, when predicting vehicle operation information, the harmonic distortion rate and battery state information can be determined based on a battery prediction model. Specifically, step 1022, which involves determining the predicted operation information based on the harmonic distortion rate and battery state information, includes: Step 10221: Obtain the pre-trained battery prediction model; Step 10222: Input the harmonic distortion rate and the battery status information into the battery prediction model, and process them through the battery prediction model to obtain the predicted operation information.

[0070] In practice, a pre-trained battery prediction model is obtained, and the harmonic distortion rate and the battery state information are input into the battery prediction model.

[0071] In this embodiment, the battery status information includes battery internal resistance and battery temperature. Based on the harmonic distortion rate, battery internal resistance and battery temperature, a multi-dimensional feature sequence is constructed. The multi-dimensional feature sequence is then input into the battery prediction model. After processing by the battery prediction model, predicted operating information is obtained.

[0072] In this embodiment, the battery prediction model is a neural network structure model, specifically an AM-GRU network architecture model, used to process multi-dimensional feature sequences and predict aging trends to obtain predicted operating information. The AM-GRU network is a model that combines an attention mechanism with a GRU recurrent neural network. By introducing an attention module on top of the standard GRU, it can dynamically capture the importance differences of different parts in the input sequence, thereby enhancing the model's ability to focus on key information. By weighting and integrating the hidden states of the GRU through attention weights, the information dilution problem in long sequence modeling is effectively solved.

[0073] In some embodiments, when determining the second set of causes of anomalies, the determination is based on the deviation between the predicted battery operating conditions and the actual battery operating conditions. Specifically, step 1022, which involves determining the second set of causes of anomalies based on the predicted operating information and the battery operating information, includes: Step 1022A: Determine the target deviation amount based on the predicted operating information and the battery operating information; Step 1022B: Obtain a preset dynamic causal graph, and search the dynamic causal graph according to the target deviation to obtain a second set of abnormal causes.

[0074] In specific implementation, the target deviation is determined based on the predicted operating information and the battery operating information. Specifically, the battery operating information includes the actual battery output voltage and the actual battery output current, and the predicted operating information includes the predicted battery output voltage and the predicted battery output current. The voltage deviation is obtained by subtracting the predicted battery output voltage from the actual battery output voltage. The current deviation is obtained by subtracting the predicted battery output current from the actual battery output current. That is, the voltage deviation and the current deviation are the target deviation.

[0075] Obtain a pre-constructed dynamic causal graph, which is a formalized and visualized representation of the temporal causal relationships implicit in the data. The construction process of the dynamic causal graph specifically includes: The multi-source heterogeneous data is cleaned, aligned according to a unified timestamp, and missing values ​​are filled in to prepare high-quality time series data for causal analysis. The multi-source heterogeneous data refers to current and voltage deviations.

[0076] Statistical methods such as Granger causality tests are employed to analyze the lead-lag relationships between different time series. For example, if the change in the environmental high temperature time series leads the change in the THD harmonic distortion rate time series, and this lead relationship is statistically significant, then the system can initially establish a causal boundary from environmental high temperature to THD anomalies. For more complex nonlinear relationships, information-theoretic-based measurement methods may be used.

[0077] Simultaneously, the system utilizes natural language processing technology to extract causal descriptions from unstructured text such as maintenance records and reports. For example, from a record stating that frequent deep discharges lead to accelerated battery capacity degradation, the causal relationship between deep discharge and capacity degradation can be extracted.

[0078] Integrating the causal relationships discovered in the above steps—that is, the nodes and edges—forms the initial dynamic causal graph. Each node in the graph represents a variable or event, and directed edges represent causal relationships. Because the system continuously monitors new data, the resulting causal graph is dynamically changing. That is, if new time-series data strengthens the confidence of a causal edge, that edge will be retained and strengthened. If new data contradicts existing causal relationships or reveals new causal paths, the causal graph will be dynamically adjusted and updated.

[0079] The dynamic causal graph is searched based on the target deviation to obtain a second set of anomaly causes. Specifically, a graph traversal algorithm is used to search for the key degradation path nodes that cause performance degradation, thus obtaining the second set of anomaly causes.

[0080] In this embodiment, the graph traversal algorithm is a depth-first search algorithm, which is an algorithm used to traverse or search graph structures. Its strategy is to explore the branches of the graph as deeply as possible. Starting from a starting node, for example, based on observed capacity decay, DFS will continuously explore forward along a path until the end node, then backtrack and start exploring the next path.

[0081] For example, a particular abuse behavior (such as frequent fast charging) leads to a series of specific internal micro-short circuit events, which in turn triggers THD anomalies and an accelerated increase in internal resistance.

[0082] The above approach identifies key nodes that appear in most failure paths or have a decisive impact on the path by traversing all possible related paths. These key nodes often correspond to the core factors leading to performance degradation, resulting in a more accurate second set of anomaly causes.

[0083] In some embodiments, determining the third set of abnormal causes based on the battery operating information and historical battery fault information in step 1023 specifically includes: Step 10231: Based on the battery operation information, search for the historical battery fault information and determine the initial abnormality cause corresponding to the battery operation information; Step 10232: Determine the target probability corresponding to each initial abnormal cause based on the Bayesian network, and take the initial abnormal causes with target probabilities greater than the preset probability threshold as the third abnormal causes. Step 10233: Count all third abnormal causes to obtain the third abnormal cause set.

[0084] In practice, the historical battery fault information is retrieved based on the battery operation information to determine the initial cause of the abnormality corresponding to the battery operation information. Specifically, the historical battery fault information contains the correspondence between the cause of the abnormality and the historical battery operation information.

[0085] In this embodiment, a knowledge base containing a large number of historical failure cases is pre-established. Statistical analysis of these historical cases can identify the causes that frequently lead to the final failure. For example, data analysis might show that before 80% of cases of accelerated battery capacity degradation occurred, there were records of vehicles being parked in high-temperature environments for extended periods and frequently using DC fast charging. Therefore, high-temperature parking and abuse of DC fast charging are identified as two important pre-defined root causes, i.e., initial causes of abnormality.

[0086] After obtaining multiple initial causes of anomalies, a target probability corresponding to each initial cause is determined based on a Bayesian network; that is, the posterior probability corresponding to each initial cause is determined using a Bayesian network. Specifically, by constructing a causal directed graph and combining prior and conditional probability tables, after observing evidence of anomalies, the posterior probability of each initial cause is calculated using Bayes' theorem, thereby quantifying the likelihood of different causes leading to anomalies and identifying the root cause.

[0087] In this embodiment, in new scenarios lacking sufficient historical data or for novel faults, expert knowledge in the battery field can be used to predefine some reasonable causal assumptions. For example, based on electrochemical principles, experts can presuppose that lithium plating at the negative electrode is a possible root cause of a specific internal resistance growth pattern. These expert experiences, once formalized, can also be incorporated into a Bayesian network as presupposed root causes.

[0088] The target probability corresponding to each initial abnormal cause is compared with a preset probability threshold. The initial abnormal causes with a target probability greater than the preset probability threshold are taken as the third abnormal causes. All third abnormal causes are counted to obtain the third abnormal cause set.

[0089] For example, with a preset probability threshold of 70%, the Bayesian network calculates the posterior probability of various preset root causes based on historical battery fault information, such as the posterior probability of frequent short-distance driving, high-temperature fast charging, and cell consistency degradation. This results in a quantitative root cause analysis report. That is, there is an 85% probability that this accelerated aging is caused by insufficient battery charging due to frequent short-distance driving.

[0090] In some embodiments, when determining the target battery maintenance strategy based on the target anomaly cause, to avoid prediction errors, the battery maintenance strategy determined based on the target anomaly cause is simulated and verified, and then output as the target battery maintenance strategy after successful verification. That is, determining the target battery maintenance strategy based on the target anomaly cause in step 103 specifically includes: Step 1031: Determine the initial battery maintenance strategy corresponding to the target anomaly cause based on the target anomaly cause; Step 1032: Send the initial battery maintenance strategy to a preset simulation test model to obtain simulation test results, wherein the simulation test results include strategy operation risk values; Step 1033: In response to the strategy operation risk value being less than or equal to a preset risk threshold, the initial battery maintenance strategy is adopted as the target battery maintenance strategy; or, Step 1034: In response to the strategy operation risk value being greater than a preset risk threshold, an abnormal prompt message is determined, and the abnormal prompt message is used as the target battery maintenance strategy.

[0091] In practice, based on the target anomaly cause, a database is searched to determine the initial battery maintenance strategy corresponding to the target anomaly cause. The initial battery maintenance strategy is then sent to a preset simulation test model to obtain simulation test results, which include strategy operation risk values.

[0092] In this embodiment, a simulation test model is pre-built, which is a digital twin. It integrates real-time data from the Internet of Vehicles, such as output voltage, output current, battery temperature and harmonic distortion rate, and combines it with vehicle usage data, such as charging habits, mileage and ambient temperature, to form a holographic digital profile of the battery.

[0093] In this embodiment, to ensure the accuracy of the simulation test model's predictions, the system continuously compares the simulation data (such as predicted internal resistance) of the simulation test model with the actual detection values ​​of the sensor and calculates the deviation. When the deviation exceeds a threshold, optimization algorithms, such as particle swarm optimization, are used to automatically adjust the model parameters inside the simulation test model, such as the aging rate coefficient, to achieve bidirectional dynamic calibration between the virtual model and the physical entity.

[0094] Before outputting the initial battery maintenance strategy, virtual simulation verification is performed in the simulation prediction model. The effectiveness and potential risks of the initial battery maintenance strategy are evaluated by simulating thousands of possible execution effects through Monte Carlo simulation, ensuring the safety and economy of the solution.

[0095] The strategy operation risk value in the simulation test results is compared with the preset risk threshold. If the strategy operation risk value is less than or equal to the preset risk threshold, it means that the initial battery maintenance strategy is relatively accurate and the risk is small. Therefore, the initial battery maintenance strategy is taken as the target battery maintenance strategy.

[0096] If the risk value of the strategy exceeds a preset risk threshold, it indicates a large error in the initial battery maintenance strategy, posing a significant risk. Therefore, an anomaly warning message is identified and used as the target battery maintenance strategy. This anomaly warning message alerts the user to potential future battery risks, urging them to monitor battery health and avoid impacting normal vehicle operation.

[0097] For example, simulation test results show that, under the current internal resistance conditions, deep discharge equalization carries a 5% risk of causing the voltage to be too low, which is greater than the preset risk threshold of 2%. Therefore, a more lenient approach is recommended, such as alerting the user that the battery may be at risk.

[0098] In some embodiments, for battery management systems (BMS) that support remote upgrades, simulation prediction models can generate optimized BMS parameters, such as charging curve thresholds, and update them remotely via OTA (Over-The-Air) updates to achieve hardware and software co-optimization, making the battery look newer over time.

[0099] Specifically, a simulation test model is pre-built, which is a digital twin that integrates real-time data from the Internet of Vehicles, such as output voltage, output current, battery temperature and harmonic distortion rate. Its output is an accurate prediction of the short-term state and long-term performance of the battery, wherein the short-term state is such as battery current and the long-term performance is such as battery health status value.

[0100] Clearly define the objectives of parameter optimization. For example, maximizing regenerative braking efficiency while ensuring the battery surface temperature does not exceed 45°C, or optimizing the charge-discharge curve to slow down internal resistance growth while meeting acceleration performance requirements. These objectives are often multiple and may even involve trade-offs.

[0101] The simulation prediction model is automatically run thousands of times. The simulation prediction model systematically adjusts the controllable parameters of the BMS, such as the charging cutoff voltage, maximum charging current, coefficients of the SOC estimation algorithm, and temperature control threshold, and observes the expected performance of the battery under different parameter combinations, such as driving range, fast charging time, and lifespan degradation rate.

[0102] By analyzing all simulation results, the optimal combination of BMS parameters is determined that best satisfies the optimization objective (e.g., maximizing battery life) without violating any safety constraints. This process may utilize optimization algorithms to efficiently search the vast parameter space, such as genetic algorithms and gradient descent.

[0103] The determined BMS parameter combination is downloaded to the actual vehicle's BMS via OTA (Over-The-Air) technology. The simulation prediction model continuously monitors the real battery performance under the new parameters, forming a closed-loop feedback loop for subsequent model calibration and further parameter fine-tuning.

[0104] In some embodiments, after the target battery maintenance strategy is output and its execution is confirmed, the effects are continuously monitored and fed back to the simulation prediction model to verify the accuracy of the prediction. Simultaneously, this new data and behavioral feedback are used to update and maintain the knowledge base, enabling the model to self-correct and optimize based on actual results.

[0105] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0106] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] Based on the same inventive concept, corresponding to any of the above embodiments, this disclosure also provides a vehicle battery monitoring device.

[0108] refer to Figure 2 , Figure 2 The vehicle battery monitoring device of the embodiment includes: The data acquisition module 201 is configured to determine the harmonic distortion rate of the vehicle battery, acquire vehicle battery status information, and determine a predicted battery health status value based on the harmonic distortion rate and the battery status information. The abnormal cause determination module 202 is configured to, in response to the harmonic distortion rate and / or the predicted battery health status value meeting the preset battery abnormal conditions, acquire battery operating information and determine the target abnormal cause based on the harmonic distortion rate, the battery status information and the battery operating information; The strategy determination module 203 is configured to determine a target battery maintenance strategy based on the cause of the target anomaly and output the target battery maintenance strategy.

[0109] In some embodiments, the battery status information includes the actual battery internal resistance, and the data acquisition module 201 is specifically configured to: Obtain the actual energy throughput and total energy throughput of the vehicle battery at the current moment, and determine the target capacity decay value based on the actual energy throughput and the total energy throughput; The predicted battery health status value is determined based on the target capacity decay value, the actual battery internal resistance, and the harmonic distortion rate.

[0110] In some embodiments, the data acquisition module 201 is specifically configured as follows: Obtain a preset standard capacity decay value, and determine a first health status value based on the target capacity decay value and the standard capacity decay value; Obtain the standard battery internal resistance, and determine the second health state value based on the actual battery internal resistance and the standard battery internal resistance; The third health status value is determined based on the harmonic distortion rate. The target fusion weight is then determined. The first health status value, the second health status value, and the third health status value are weighted according to the target fusion weight to obtain the predicted battery health status value.

[0111] In some embodiments, the anomaly cause determination module 202 is specifically configured as follows: A pre-trained anomaly detection model is obtained, and the harmonic distortion rate, the battery status information, and the battery operation information are input into the anomaly detection model. The anomaly detection model processes the data to obtain a first set of anomaly causes. Based on the harmonic distortion rate and the battery status information, predictive operating information is determined, and based on the predictive operating information and the battery operating information, a second set of abnormal causes is determined; A third set of abnormal causes is determined based on the battery operation information and historical battery fault information; The common causes in the first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes are taken as the target abnormal causes.

[0112] In some embodiments, the anomaly cause determination module 202 is specifically configured as follows: Obtain the pre-trained battery prediction model; The harmonic distortion rate and the battery status information are input into the battery prediction model, and the predicted operating information is obtained through processing by the battery prediction model.

[0113] In some embodiments, the anomaly cause determination module 202 is specifically configured as follows: The target deviation is determined based on the predicted operating information and the battery operating information. Obtain a preset dynamic causal graph, and search the dynamic causal graph according to the target deviation to obtain a second set of abnormal causes.

[0114] In some embodiments, the anomaly cause determination module 202 is specifically configured as follows: Based on the battery operation information, the historical battery fault information is retrieved to determine the initial cause of the abnormality corresponding to the battery operation information; Based on a Bayesian network, the target probability corresponding to each initial abnormal cause is determined, and the initial abnormal cause with a target probability greater than a preset probability threshold is taken as the third abnormal cause. By statistically analyzing all the third abnormal causes, we obtain the set of third abnormal causes.

[0115] In some embodiments, the strategy determination module 203 is specifically configured as follows: Based on the cause of the target anomaly, determine the initial battery maintenance strategy corresponding to the cause of the target anomaly; The initial battery maintenance strategy is sent to a preset simulation test model to obtain simulation test results, wherein the simulation test results include strategy operation risk values; In response to a risk value less than or equal to a preset risk threshold, the initial battery maintenance strategy is adopted as the target battery maintenance strategy; or... In response to the risk value of the strategy operation being greater than a preset risk threshold, an abnormal prompt message is determined, and the abnormal prompt message is used as the target battery maintenance strategy.

[0116] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0117] The apparatus of the above embodiments is used to implement the corresponding vehicle battery monitoring method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0118] Based on the same inventive concept, corresponding to any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle battery monitoring method described in any of the above embodiments.

[0119] Figure 3 This embodiment illustrates a more specific hardware structure of an electronic device. The device may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0120] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0121] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0122] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0123] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0124] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0125] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0126] The electronic devices described above are used to implement the corresponding vehicle battery monitoring methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0127] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the vehicle battery monitoring method as described in any of the above embodiments.

[0128] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0129] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the vehicle battery monitoring method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0130] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a vehicle, including the vehicle battery monitoring device in the above embodiments, the electronic device in the above embodiments, and the computer-readable storage medium in the above embodiments, wherein the vehicle device implements the vehicle battery monitoring method described in any of the above embodiments.

[0131] The vehicles described in the above embodiments are used to implement the vehicle battery monitoring method described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0132] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0133] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0134] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0135] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0136] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0137] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0138] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0139] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for monitoring vehicle batteries, characterized in that, include: Determine the harmonic distortion rate of the vehicle battery, obtain the vehicle battery status information, and determine the predicted battery health status value based on the harmonic distortion rate and the battery status information. In response to the harmonic distortion rate and / or the predicted battery health status value meeting preset battery abnormality conditions, battery operation information is obtained, and the cause of the target abnormality is determined based on the harmonic distortion rate, the battery status information, and the battery operation information. Determine the target battery maintenance strategy based on the cause of the target anomaly, and output the target battery maintenance strategy.

2. The method according to claim 1, characterized in that, The battery status information includes the actual internal resistance of the battery. The step of determining the predicted battery health status value based on the harmonic distortion rate and the battery status information includes: Obtain the actual energy throughput and total energy throughput of the vehicle battery at the current moment, and determine the target capacity decay value based on the actual energy throughput and the total energy throughput; The predicted battery health status value is determined based on the target capacity decay value, the actual battery internal resistance, and the harmonic distortion rate.

3. The method according to claim 2, characterized in that, The step of determining the predicted battery health status value based on the target capacity decay value, the actual battery internal resistance, and the harmonic distortion rate includes: Obtain a preset standard capacity decay value, and determine a first health status value based on the target capacity decay value and the standard capacity decay value; Obtain the standard battery internal resistance, and determine the second health state value based on the actual battery internal resistance and the standard battery internal resistance; The third health status value is determined based on the harmonic distortion rate. The target fusion weight is then determined. The first health status value, the second health status value, and the third health status value are weighted according to the target fusion weight to obtain the predicted battery health status value.

4. The method according to claim 1, characterized in that, The step of determining the cause of the target anomaly based on the harmonic distortion rate, the battery status information, and the battery operation information includes: A pre-trained anomaly detection model is obtained, and the harmonic distortion rate, the battery status information, and the battery operation information are input into the anomaly detection model. The anomaly detection model processes the data to obtain a first set of anomaly causes. Based on the harmonic distortion rate and the battery status information, predictive operating information is determined, and based on the predictive operating information and the battery operating information, a second set of abnormal causes is determined; A third set of abnormal causes is determined based on the battery operation information and historical battery fault information; The common causes in the first set of abnormal causes, the second set of abnormal causes, and the third set of abnormal causes are taken as the target abnormal causes.

5. The method according to claim 4, characterized in that, The step of determining the predicted operating information based on the harmonic distortion rate and the battery state information includes: Obtain the pre-trained battery prediction model; The harmonic distortion rate and the battery status information are input into the battery prediction model, and the predicted operating information is obtained through processing by the battery prediction model.

6. The method according to claim 4, characterized in that, The step of determining the second set of abnormal causes based on the predicted operating information and the battery operating information includes: The target deviation is determined based on the predicted operating information and the battery operating information. Obtain a preset dynamic causal graph, and search the dynamic causal graph according to the target deviation to obtain a second set of abnormal causes.

7. The method according to claim 4, characterized in that, The step of determining the third set of abnormal causes based on the battery operation information and historical battery fault information includes: Based on the battery operation information, the historical battery fault information is retrieved to determine the initial cause of the abnormality corresponding to the battery operation information; Based on a Bayesian network, the target probability corresponding to each initial abnormal cause is determined, and the initial abnormal cause with a target probability greater than a preset probability threshold is taken as the third abnormal cause. By statistically analyzing all the third abnormal causes, we obtain the set of third abnormal causes.

8. The method according to claim 1, characterized in that, The step of determining the target battery maintenance strategy based on the cause of the target anomaly includes: Based on the cause of the target anomaly, determine the initial battery maintenance strategy corresponding to the cause of the target anomaly; The initial battery maintenance strategy is sent to a preset simulation test model to obtain simulation test results, wherein the simulation test results include strategy operation risk values; In response to a risk value less than or equal to a preset risk threshold, the initial battery maintenance strategy is adopted as the target battery maintenance strategy; or... In response to the risk value of the strategy operation being greater than a preset risk threshold, an abnormal prompt message is determined, and the abnormal prompt message is used as the target battery maintenance strategy.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 9.

Images