Method, device and electronic equipment for diagnosing state of charge of vehicle

Abstract

The application discloses a vehicle state of charge diagnosis method and device and electronic equipment, and relates to the technical field of battery state diagnosis. The method comprises the following steps: obtaining target running data of a target vehicle, and a mapping relationship between the state of charge value and the remaining battery capacity of the target vehicle which is constructed in advance; performing error detection on the energy change in the charging stage based on the data of the charging stage in the target running data and the mapping relationship, obtaining a first error difference value; performing error detection on the input and output energy of the battery based on the data in a preset time interval in the target running data and the mapping relationship, obtaining a second error difference value; and analyzing the first error difference value and the second error difference value to determine the attribution diagnosis information of the false high state of charge of the target vehicle. Through the technical scheme, the specific cause of the false high state of charge of the vehicle can be effectively diagnosed and located, so that the driving safety and user experience are improved.

Description

Technical Field

[0001] This application relates to the field of battery state diagnostic technology, specifically to methods, devices, and electronic equipment for diagnosing the state of charge of vehicles. Background Technology

[0002] The State of Charge (SOC) of an electric vehicle is a core parameter characterizing the remaining usable charge of the battery. Its accuracy directly affects the vehicle's range prediction, energy management strategy formulation, driving safety, and user experience. In actual operation, due to the combined effects of various complex factors such as battery aging, sensor measurement deviations, and limitations of the Battery Management System (BMS) algorithm, the estimated SOC value may deviate significantly from the true value, especially the problem of inflated SOC (i.e., the displayed value is higher than the actual value). This issue may cause the vehicle to deplete its charge prematurely while driving, leading to driving interruptions or even safety hazards. Summary of the Invention

[0003] This application provides a method, apparatus, and electronic device for diagnosing the state of charge of a vehicle, thereby improving the accuracy of vehicle state of charge estimation.

[0004] In a first aspect, this application provides a method for diagnosing the state of charge (SBC) of a vehicle, comprising: acquiring target operating data of a target vehicle and a pre-constructed mapping relationship between the SBC value of the target vehicle and the remaining battery capacity; performing error detection of energy changes during the charging phase based on the data and mapping relationship in the target operating data to obtain a first error difference; performing error detection of battery input and output energy based on the data and mapping relationship within a preset time interval in the target operating data to obtain a second error difference; and analyzing the first error difference and the second error difference to determine attribution diagnostic information for an artificially high SBC of the target vehicle.

[0005] In one optional implementation, obtaining target operating data of the target vehicle includes: obtaining the original operating data of the target vehicle; identifying the original operating data to obtain an identification result; if the identification result indicates that there are missing values ​​in the original operating data, then processing the missing values ​​according to the data type corresponding to the missing values ​​to obtain the target operating data.

[0006] In one optional implementation, the missing values ​​are processed according to their corresponding data types to obtain target running data, including: if the data type corresponding to the missing value is a unique identifier, then the data records containing the missing values ​​in the original running data are deleted to obtain the target running data; if the data type corresponding to the missing value is continuous physical parameter data, then the missing value is filled forward using the nearest valid value to obtain the target running data; if the data type corresponding to the missing value is non-continuous physical parameter data, then the null values ​​corresponding to the missing values ​​are retained, and the missing values ​​are marked to obtain the target running data.

[0007] In one optional implementation, the original operating data is identified to obtain an identification result, including: obtaining a preset parameter range corresponding to each operating parameter in the original operating data; for any operating parameter value in the original operating data, if the parameter value is not within the preset parameter range of the corresponding operating parameter, then the identification result is determined to include an outlier in the original operating data; obtaining the target operating data of the target vehicle, further including: if the identification result indicates that there is an outlier in the original operating data, then the outlier is treated as a missing value to obtain the target operating data.

[0008] In one optional implementation, error detection of energy changes during the charging phase is performed based on the data and mapping relationship of the charging phase in the target operating data to obtain a first error difference. This includes: identifying at least one charging phase of the target vehicle based on the charging state signal in the target operating data; for any charging phase, extracting current and voltage data from the target operating data between the charging start time and the charging end time, and obtaining a first state of charge value corresponding to the charging start time and a second state of charge value corresponding to the charging end time; performing integration processing on the current and voltage data to determine the actual charging amount of the target vehicle during the charging phase; querying the mapping relationship based on the first and second state of charge values ​​to obtain the remaining capacity of the first battery corresponding to the first state of charge value and the remaining capacity of the second battery corresponding to the second state of charge value; determining the first difference between the remaining capacity of the second battery and the remaining capacity of the first battery as the estimated charging amount of the target vehicle during the charging phase; and determining the second difference between the estimated charging amount and the actual charging amount as the first error difference.

[0009] In one optional implementation, error detection of battery input and output energy is performed based on data and mapping relationships within a preset time interval in the target operating data to obtain a second error difference. This includes: parsing the target operating data to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within the preset time interval, and obtaining the third state of charge value at the start time corresponding to the preset time interval, and the fourth state of charge value at the end time corresponding to the preset time interval; querying the mapping relationship based on the third and fourth state of charge values ​​to obtain the remaining third battery charge corresponding to the third state of charge value and the remaining fourth battery charge corresponding to the fourth state of charge value; determining the battery input energy of the target vehicle within the preset time interval based on the superposition result between the remaining third battery charge and the cumulative power integral charging amount; determining the battery output energy of the target vehicle within the preset time interval based on the superposition result between the remaining fourth battery charge and the cumulative net energy consumption; determining the battery input-output difference ratio of the target vehicle based on the third difference between the battery input energy and the battery output energy; and determining the battery input-output difference ratio as the second error difference.

[0010] In one optional implementation, parsing the target operating data to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within a preset time interval includes: based on the charging status signal in the target operating data, filtering out charging status data and non-charging status data within the preset time interval from the target operating data; performing integral processing on the current data and voltage data included in the charging status data to obtain the cumulative power integral charging amount; and performing integral processing on the current data and voltage data included in the non-charging status data to obtain the cumulative net energy consumption.

[0011] In one optional implementation, the first error difference and the second error difference are analyzed to determine the attribution diagnosis information of the target vehicle's falsely high state of charge, including: if the first error difference exceeds a first preset threshold, it is determined that the target vehicle has a problem with a falsely high state of charge, and the reason for the falsely high state of charge of the target vehicle is a defect in the target vehicle's battery management system; if the second error difference exceeds a second preset threshold, it is determined that the target vehicle has a problem with current calculation error or battery abnormality, and the reason for the falsely high state of charge of the target vehicle is that the target vehicle's current sensor has an error, or the target vehicle's battery has abnormal heating or leakage.

[0012] Secondly, this application provides a diagnostic device for the state of charge (SBC) of a vehicle, comprising: an acquisition module for acquiring target operating data of a target vehicle and a pre-constructed mapping relationship between the SBC value of the target vehicle and the remaining battery capacity; a first detection module for detecting errors in energy changes during the charging phase based on the data and mapping relationship in the target operating data to obtain a first error difference; a second detection module for detecting errors in battery input and output energy based on the data and mapping relationship within a preset time interval in the target operating data to obtain a second error difference; and an analysis module for analyzing the first error difference and the second error difference to determine attribution diagnostic information for an artificially high SBC of the target vehicle.

[0013] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle charge state diagnosis method of the first aspect or any corresponding embodiment described above.

[0014] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle charge state diagnostic method of the first aspect or any corresponding embodiment described above.

[0015] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the vehicle charge state diagnostic method of the first aspect or any corresponding embodiment described above.

[0016] The vehicle state of charge (SBC) diagnostic method provided in this application achieves precise adaptation to the specific vehicle's battery characteristics by acquiring the target vehicle's operating data and a mapping relationship between the SBC value and the remaining battery capacity, thus providing a reliable basis for subsequent error detection. A dual diagnostic mechanism is designed, based on error detection using charging stage data and error detection based on battery input / output energy within a preset time interval. This comprehensively identifies SBC anomalies from both the charging process and overall energy balance dimensions, improving the diagnostic coverage and reliability. Further comprehensive analysis of the first and second error differences determines the specific cause of the falsely high SBC, not only detecting the problem but also providing clear diagnostic evidence for subsequent targeted processing, effectively improving the accuracy and operability of the diagnosis. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of a first method for diagnosing the state of charge of a vehicle according to an embodiment of this application; Figure 2 This is a schematic diagram of a second process for diagnosing the state of charge of a vehicle according to an embodiment of this application; Figure 3 This is a schematic diagram of the third process of a vehicle charge state diagnosis method according to an embodiment of this application; Figure 4 This is a structural block diagram of a vehicle charge state diagnostic device according to an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained.

[0023] (1) Battery state of charge (SOC) refers to the ratio of the current remaining charge of the power battery to its nominal total capacity, usually expressed as a percentage. This parameter is a key basis for evaluating the driving range of electric vehicles, conducting energy management and charge / discharge control, and its accuracy directly affects driving safety and user experience.

[0024] (2) Battery Management System (BMS) is an electronic control unit that performs real-time monitoring, state estimation, equalization control, thermal management, and fault diagnosis of power battery packs. Its main functions include collecting parameters such as battery voltage, current, and temperature, estimating the battery's SOC and SOH (State of Health), and ensuring that the battery operates within a safe and efficient range.

[0025] (3) Electric vehicles are vehicles that use on-board power batteries as their energy source and rely on drive motors to provide driving power. Depending on the configuration of the power system, they can be divided into pure electric vehicles and plug-in hybrid electric vehicles, etc.

[0026] The accuracy of the State of Charge (SOC) of an electric vehicle directly impacts range prediction, energy management strategies, and the user's driving experience. Especially during actual vehicle operation, accurate SOC estimation is crucial for preventing overcharging and over-discharging, ensuring driving safety, and extending battery lifespan. However, due to multiple factors such as battery aging characteristics, long-term drift of current and voltage sensors, and algorithmic deviations in the battery management system, an inflated SOC often occurs in actual vehicle operation. This means that the remaining charge displayed on the instrument panel or system is significantly higher than the actual discharge capacity of the battery. This problem can easily lead to sudden vehicle stalling within the expected driving range, causing a breakdown risk, seriously affecting user trust, and posing a potential threat to road safety.

[0027] Currently, the detection and diagnosis of artificially high SOC mainly rely on estimation algorithms and fault diagnosis strategies within the BMS based on real-time parameters such as voltage, current, and temperature. These methods are effective within ranges where the relationship between battery voltage and SOC is clear. However, in the typical operating range of batteries such as lithium iron phosphate (LFP), their open-circuit voltage-capacity curves exhibit significant flatness. Large changes in SOC correspond to minimal voltage fluctuations, causing a significant decrease in the sensitivity of traditional voltage-based diagnostic methods, making it difficult to effectively identify slow, artificially high SOC shifts.

[0028] The vehicle state of charge (SOC) diagnostic method provided in this application acquires vehicle operating data and a preset SOC-remaining charge mapping relationship. Based on this mapping relationship, it performs two independent error detections on energy changes during the charging phase and within a preset time interval, obtaining a first error difference and a second error difference. Finally, it analyzes these two error differences to determine the attribution diagnostic information for inflated SOC. This application constructs a diagnostic path that does not directly rely on the linear correspondence between real-time battery voltage changes and SOC by designing a dual-path error detection and comparative analysis process. This addresses the failure of traditional voltage monitoring methods in the flat range of the battery voltage-capacity curve, enabling effective detection and diagnosis of inflated SOC.

[0029] According to an embodiment of this application, a method for diagnosing the state of charge of a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a method for diagnosing the state of charge of a vehicle, which can be used in electronic devices, such as servers. Figure 1 This is a flowchart of a vehicle state of charge diagnostic method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain the target operating data of the target vehicle, as well as the pre-built mapping relationship between the state of charge value and the remaining battery power of the target vehicle.

[0031] The target vehicle refers to a specific electric vehicle selected for analysis to detect whether it has an inflated State of Charge (SOC) issue, such as a lithium iron phosphate battery electric vehicle. Target operational data refers to multi-dimensional time-series data collected and uploaded in real-time from the target vehicle's Battery Management System (BMS). This data may include the Vehicle Identification Number (VIN), data recording timestamps, total battery voltage, total battery current, BMS-estimated SOC, battery temperature, charging status (whether charging is in progress), and vehicle speed. Specifically, during operation or charging, the target vehicle's BMS continuously monitors and generates a series of data reflecting the battery's state, such as voltage, current, and estimated remaining charge percentage. This data is uploaded in real-time or near real-time to a cloud-based data platform or backend server via the vehicle's network communication module (such as a T-Box). Therefore, for the diagnostic analysis end (such as a server), acquiring this data means querying, receiving, or retrieving all relevant raw data sequences uploaded by the target vehicle over a period of time from the cloud data platform, thus providing a data foundation for subsequent analysis.

[0032] The State of Charge (SOC) value refers to the percentage of remaining battery capacity estimated and displayed by the vehicle's BMS (Battery Management System), for example, displaying 80% remaining capacity. Remaining battery capacity refers to a more physically accurate value of electrical energy, calculated based on battery physical characteristics (such as the cell SOC-voltage curve provided by the supplier) and actual measurement data (voltage and current integrals), typically measured in kilowatt-hours (kWh). The mapping relationship refers to a pre-built lookup table for the target vehicle's battery, mapping the actual SOC value to the remaining battery capacity. This table is built based on standard cell data and battery pack configuration (number of cells, nominal capacity), etc. Specifically, obtaining the mapping relationship is an offline calculation or modeling process based on battery physical characteristic parameters. Its core relies on standard test data provided by the battery cell manufacturer, typically a curve showing the relationship between battery SOC and terminal voltage at a specific temperature and rate (e.g., 25°C, 1C charge / discharge rate). Using these standard data, combined with the specific specifications of the battery pack in the target vehicle (such as the number of cells connected in series and the nominal total battery capacity), a complete mapping table from the state of charge (SOC) value to the remaining battery energy value is calculated through certain mathematical models or calculation methods (e.g., integrating the voltage curve with respect to the charge). For SOC values ​​not directly listed in the table, linear interpolation methods can be used to calculate their corresponding remaining charge, thus forming a mapping relationship covering the entire SOC range for subsequent queries. Once this relationship is established, it is stored as a benchmark knowledge base and called upon when diagnostics are needed to convert the SOC value reported by the BMS into the theoretically stored energy value.

[0033] Step S102: Based on the data and mapping relationship of the charging stage in the target operation data, perform error detection on the energy change during the charging stage to obtain the first error difference value.

[0034] The charging phase refers to the complete data period from the start to the end of charging, identified from the target operating data. The current during this phase is typically negative (energy flows into the battery), making it a crucial data window for large error detection (i.e., error detection of energy changes during the charging phase based on the data and mapping relationship within the target operating data). The first error difference is a key difference calculated in the large error detection process. Specifically, large error detection compares the energy the battery should add with the energy it actually adds. During the charging phase, relevant operating data within the time interval where the vehicle is charging is extracted. Combined with the mapping relationship, the theoretical charging energy estimated based on the change in state of charge can be calculated. Simultaneously, using the actual electrical parameters (such as voltage and current) collected within this charging interval, the actual energy value input to the battery is calculated using the corresponding energy accumulation method. The difference between the theoretical charging energy and the actual input energy is the first error difference. This difference reflects the consistency level of energy metering during the charging process.

[0035] Step S103: Based on the data and mapping relationship within the preset time interval in the target operating data, perform error detection on the battery input and output energy to obtain the second error difference value.

[0036] The preset time interval refers to an arbitrarily selected, sufficiently long analysis time window used for small error detection (i.e., error detection of battery input and output energy based on data and mapping relationships within the preset time interval in the target operating data). This interval can include multiple charge-discharge cycles, not just a single charging phase. Its purpose is to evaluate the battery's energy "balance" over a longer time scale. The second error difference, calculated in the small error detection stage, is used to identify systematic errors. Specifically, small error detection aims to assess the overall energy balance of the battery over a longer period. Based on the mapping relationship, the theoretical remaining energy of the battery at the start and end times of the preset time interval can be calculated. Simultaneously, using the operating data within this interval, the total input energy and total output energy of the battery are cumulatively calculated. By comparing the difference between the theoretical energy change and the actual cumulative energy balance, the second error difference is obtained. This difference is used to assess the cumulative deviation of the battery throughout the entire energy flow process.

[0037] Step S104: Analyze the first error difference and the second error difference to determine the attribution diagnosis information of the target vehicle's falsely high state of charge.

[0038] Attribution diagnostic information refers to a conclusive judgment about the root cause of inflated State of Charge (SOC) by comprehensively analyzing the first and second error differences. By analyzing the different patterns and severity of the two error detection results, the most likely root cause of the inflated SOC can be inferred. Specifically, the first and second error differences reveal inconsistencies in energy measurement and state estimation of the battery system from different dimensions. A diagnostic logic can be constructed by comprehensively evaluating the magnitude, direction, and occurrence scenarios of these two differences. For example, a significant first error difference may point to a localized problem related to the charging process or a specific state estimation; a significant second error difference may suggest an overall energy measurement deviation or continuous abnormal energy dissipation. Further integration with other auxiliary information such as vehicle model, operating environment, and data quality allows for the classification and attribution of abnormal patterns, thereby outputting targeted diagnostic conclusions to guide subsequent inspections or maintenance and improve the reliability of state estimation.

[0039] The vehicle state of charge (SBC) diagnostic method provided in this application achieves precise adaptation to the specific vehicle's battery characteristics by acquiring the target vehicle's operating data and a mapping relationship between the SBC value and the remaining battery capacity, thus providing a reliable basis for subsequent error detection. A dual diagnostic mechanism is designed, based on error detection using charging stage data and error detection based on battery input / output energy within a preset time interval. This comprehensively identifies SBC anomalies from both the charging process and overall energy balance dimensions, improving the diagnostic coverage and reliability. Further comprehensive analysis of the first and second error differences determines the specific cause of the falsely high SBC, not only detecting the problem but also providing clear diagnostic evidence for subsequent targeted processing, effectively improving the accuracy and operability of the diagnosis.

[0040] This embodiment provides a method for diagnosing the state of charge of a vehicle, which can be used in electronic devices, such as servers. Figure 2 This is a flowchart of a vehicle state of charge diagnostic method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain the target operating data of the target vehicle, as well as the pre-built mapping relationship between the state of charge value and the remaining battery power of the target vehicle.

[0041] Specifically, acquiring the target vehicle's target operational data includes: Step a1: Obtain the raw operating data of the target vehicle.

[0042] Raw operational data refers to the initial data stream directly collected from the target vehicle's battery management system and related sensors, without any cleaning or correction. It typically includes various fields such as timestamps, battery voltage, current, BMS-estimated SOC value, and charging status signals, and may contain transmission errors, noise, or interruptions. Specifically, through sensors deployed on the target vehicle (such as battery voltage and current sensors) and onboard communication terminals, the vehicle continuously generates time-series data reflecting its state during operation. This data is automatically and periodically sent to a remote cloud server or data center via the vehicle's network connection. Therefore, for the diagnostic analysis end (such as a server), the acquisition operation means retrieving or receiving, on demand, all unprocessed initial data packets uploaded by a specified vehicle (matched by its vehicle identification number) within a specific time period from its connected data storage platform or message queue. This process typically relies on preset vehicle-to-cloud communication protocols and interfaces to achieve automated data transmission and reception.

[0043] Step a2: Identify the original running data to obtain the identification results.

[0044] The identification result refers to the conclusive output formed after preliminary inspection and judgment of the raw operating data. It is used to identify what quality problems exist in the data, such as whether missing data is detected or whether there are obviously unreasonable values. Specifically, the received raw data sequence is traversed, and each line or field is scanned and judged according to predefined logical criteria. This mainly includes two types of checks: completeness check and reasonableness check. After these checks are completed, a structured identification result is generated, which clearly indicates what problems exist in the data, where the problems occur, and what type they are, providing a basis for subsequent targeted processing.

[0045] Step a3: If the identification result indicates that there are missing values ​​in the original running data, then the missing values ​​are processed according to the data type corresponding to the missing values ​​to obtain the target running data.

[0046] Missing values ​​refer to data points in the original running data sequence that should have existed but were not recorded or failed to be received. They manifest as blank data fields or obviously invalid placeholders, typically caused by communication interruptions, acquisition failures, or other reasons. Specifically, when the identification results indicate the presence of missing values, a single processing method is not adopted; instead, the processing strategy is determined based on the nature (i.e., data type) of the data field containing the missing value. The core idea is to balance data continuity, information integrity, and the potential biases introduced by repair. First, it is determined whether the missing field belongs to critical identifying information, continuously changing physical quantities, or discontinuous state or event information. Then, corresponding processing sub-processes are triggered for different types. All processed or confirmed retained fields are then re-integrated to form a quality-controlled target running dataset that can be used for subsequent analysis. This process ensures the refinement and adaptability of data quality management.

[0047] The vehicle charge state diagnostic method provided in this application acquires raw operating data and actively detects missing values ​​in the data through an identification step, demonstrating a pre-verification of data integrity. Furthermore, based on the identification results, it performs differentiated processing on the specific data type corresponding to the missing values. This design allows the data preprocessing method to adapt to the requirements of different data characteristics, avoiding deviations or information loss that may be introduced by a single processing method. This ensures that the target operating data used in the end is a reliable data source that has undergone integrity identification and targeted repair, laying an accurate and consistent data foundation for subsequent error detection and diagnostic analysis, effectively improving the robustness of the entire diagnostic process and the reliability of the results.

[0048] In some optional implementations, the missing values ​​are processed according to the data type corresponding to the missing values ​​to obtain the target runtime data, including: Step b1: If the data type corresponding to the missing value is a unique identifier, then delete the data records containing the missing value in the original running data to obtain the target running data.

[0049] Unique identifiers refer to crucial, non-repeatable, and non-substitutable identifying information in data used to uniquely distinguish different vehicles, typically the Vehicle Identification Number (VIN). If this information is missing, the entire record cannot be accurately associated with a specific vehicle and must be deleted. Specifically, when a missing value is determined to be in a unique identifier field (such as the VIN), the strategy is to directly delete the entire data record containing this missing value. This is because such identifiers are the foundation for accurately associating data records with specific target vehicles and are non-substitutable. If this field is missing, the record loses its clear attribution and cannot be reliably used for subsequent analyses requiring vehicle-by-vehicle association. Deleting it fundamentally avoids confusing or erroneous analytical conclusions due to incorrect associations. After deletion, the remaining valid records constitute a cleaner and more accurately traceable set of target operational data.

[0050] Step b2: If the data type corresponding to the missing value is continuous physical parameter data, then the missing value is filled forward using the nearest valid value to obtain the target running data.

[0051] The most recent valid value refers to the closest observation in the time series that has been confirmed as correct and has not been marked as anomaly or missing, preceding the missing point. Specifically, when missing values ​​occur in continuous physical parameter fields such as voltage and current, the strategy used is forward imputation. This method is based on the reasonable assumption that such physical quantities typically do not undergo abrupt changes over short timescales. The specific operation involves locating the missing data point in the time series, then searching forward along the time axis (i.e., in the past direction) for the closest observation that has not been marked as invalid or missing, and using this value to fill the current missing position. The aim is to maintain the continuity of the data time series to the maximum extent possible while acknowledging data gaps, thus meeting the basic requirement of data continuity for subsequent time-based analysis algorithms (such as integration), thereby forming usable target running data.

[0052] When using the forward filling method to process missing values ​​of continuous physical parameters, if the number of consecutive missing data points exceeds the preset maximum filling interval (e.g., 5 sampling periods, corresponding to 5 seconds), filling will no longer be performed. Instead, the data segment will be marked as invalid to avoid introducing significant errors due to long-term data interruption.

[0053] Step b3: If the data type corresponding to the missing value is non-continuous physical parameter data, then retain the null value corresponding to the missing value and mark the missing value to obtain the target running data.

[0054] For missing values ​​in discontinuous physical parameter data (such as certain fault codes or status flags), the strategy is to retain null values ​​and add a marker. This is because such data may represent the sudden occurrence of an event or a jump in state, and its values ​​themselves do not possess the characteristic of continuous change in the short term. Blindly filling in missing values ​​may introduce misleading information. Therefore, the missing state of the data point is kept unchanged (i.e., retaining null values ​​or placeholders), but a special marker or label is added to indicate that the data is missing in its original form. This approach not only maintains the original authenticity of the data to the greatest extent possible, avoiding distortion of facts due to improper guesswork, but also provides clear prompts for subsequent analysis stages through marking, enabling the analysis program to be aware of the situation and take appropriate action when necessary (such as ignoring the record or making special considerations), ultimately forming a transparent, accurate, and reliable target operational data.

[0055] In the above implementation, by distinguishing unique identifier data and directly deleting missing records of this type, the data matching errors or association confusion that may result from missing identifier information are effectively avoided, ensuring the uniqueness and accuracy of the data. For continuous physical parameter data, a forward imputation method based on the most recent valid value is used. This method can maximize the temporal or logical continuity and smoothness of the data sequence, providing reliable input for subsequent analysis and calculations that rely on data continuity. For discontinuous physical parameter data, a method of retaining and marking null values ​​is adopted. This avoids the noise or misleading information that may be introduced by blindly filling in null values, and the marking makes it possible to focus on these data points in subsequent analysis. Thus, while maintaining data authenticity, it enhances the flexibility and depth of data analysis. Through the above classification and processing mechanism, this application achieves an optimized balance between data integrity, continuity, and authenticity, and constructs a set of efficient and reliable data preprocessing specifications.

[0056] In some optional implementations, obtaining the target vehicle's target operating data further includes: if the identification result indicates that there are outliers in the original operating data, then the outliers are treated as missing values ​​to obtain the target operating data.

[0057] Outliers refer to values ​​in the original operational data that significantly exceed the reasonable physical or technical range of a parameter, and are therefore judged as unreliable or erroneous. For example, battery temperature exhibiting highly improbable positive or negative extreme values. Specifically, when certain data points are confirmed as outliers (i.e., obviously unreasonable or erroneous values) through inspection (such as threshold judgment), they are not directly corrected or subjected to complex processing. Instead, they are marked and treated as a special type of missing value. Specifically, these outliers are removed or invalidated from the original data sequence, leaving a gap to be processed in their original location. This gap is then incorporated into the same classification and processing flow as for native missing values. Based on the data type of the field in which it resides, a decision is made as to whether to delete the entire record, fill it, or mark it as retained. The purpose of this is to consolidate data quality issues (outliers and missing values) from different sources but of similar nature into a unified processing framework, simplifying system design and ensuring that all suspicious or unreliable data undergoes standardized cleaning, ultimately forming a set of target operational data with controllable quality.

[0058] In the above implementation, after identifying outliers, they are not directly discarded or subjected to complex special corrections. Instead, they are categorized and transformed into missing value problems, thus cleverly reusing the established, systematic processing framework for missing values. This design significantly improves the simplicity, consistency, and scalability of the preprocessing process. On the one hand, it avoids the need to develop complex processing rules separately for outliers, reducing the complexity of system implementation and maintenance costs. On the other hand, it enables outliers to automatically adapt to subsequently defined fine-grained processing strategies (such as deletion, forward imputation, or mark-and-hold) based on their data type, ensuring that data problems of different natures are handled in a standardized and appropriate manner. Through this unified paradigm of outlier-to-missing-value processing, the ability to tolerate and handle various defects during data acquisition is enhanced, further solidifying the data quality foundation upon which subsequent diagnostic analysis relies.

[0059] In some alternative implementations, step a2 above includes: Step a21: Obtain the preset parameter range corresponding to each running parameter in the original running data.

[0060] Operating parameters refer to each independent measured or state variable that makes up the raw data, such as total battery voltage, total battery current, estimated SOC, vehicle speed, etc. Each parameter represents specific information about a certain aspect of the battery or vehicle. Preset parameter ranges refer to the upper and lower limits of a reasonable range of values ​​pre-defined for each operating parameter. These ranges are typically determined based on physical principles, technical specifications, or historical experience, and are used to automatically screen and identify abnormal data that exceeds the limits. Specifically, the process of obtaining preset parameter ranges essentially involves establishing a set of reasonable judgment criteria for each monitored physical or state quantity. These ranges are usually pre-defined and stored in a configuration knowledge base based on various prior knowledge during system deployment or initialization. Their sources may include, for example, the extreme operating ranges specified in the technical specifications of the vehicle or battery module model; theoretically feasible boundaries determined by relevant physical laws or chemical properties; and normal value ranges observed through long-term historical data statistics. When performing data quality identification, the electronic device directly queries this knowledge base to obtain the corresponding upper and lower limits for each operating parameter that needs to be checked, serving as a benchmark for automatically screening abnormal data. For example, the reasonable range for battery temperature parameters can be set to -40℃ to 150℃. If the data shows values ​​that are significantly outside this range, such as 255℃, they are considered abnormal values.

[0061] Step a22: For any parameter value in the original running data, if the parameter value is not within the preset parameter range of the corresponding running parameter, then the identification result is determined to include the presence of abnormal values ​​in the original running data.

[0062] The process iterates through each data point in the raw operational data, and for each data point's associated operational parameter, extracts the preset range (minimum and maximum values) for that parameter. Then, the actual value of the data point is compared to this range. If the value is less than the minimum or greater than the maximum, meaning it falls outside the preset reasonable range, the data point is determined to be an outlier. This determination is recorded and summarized in the identification results of this data scan, clearly indicating that an anomaly was found at a specific time point and on a specific parameter. This process enables rapid, batch initial screening of massive amounts of raw data, automatically identifying data that clearly does not conform to common sense or technical specifications.

[0063] In the above implementation, reasonable numerical boundaries are defined for different operating parameters based on prior knowledge or historical data, freeing the determination of outliers from subjective experience and providing quantifiable and reproducible standards. During the identification process, logical comparison—checking whether each data point exceeds the preset range of its corresponding parameter—can quickly and automatically complete the initial screening of massive amounts of operating data, identifying obviously unreasonable or physically impossible values.

[0064] Step S202: Based on the data and mapping relationship of the charging stage in the target operation data, perform error detection on the energy change during the charging stage to obtain the first error difference value.

[0065] Specifically, step S202 includes: Step S2021: Based on the charging status signal in the target operating data, identify at least one charging stage of the target vehicle.

[0066] A charging status signal is a clearly defined status indicator or signal provided by the vehicle system to indicate whether the vehicle is currently in the charging process. Specifically, the system scans the target operational data for the signal channel that specifically indicates the charging status. This signal typically has two distinct states, such as charging in progress and not charging in progress. The identification algorithm finds the starting edge where the signal transitions from not charging in progress to charging in progress, marking this point as the start of a charging phase. Monitoring continues until the signal transitions back from charging in progress to not charging in progress, marking this point as the end of the charging phase. By identifying all such "start-end" signal pairs, one or more clearly defined time data segments, i.e., charging phases, corresponding to the vehicle's charging process, are segmented from the continuous operational data stream.

[0067] The charging status signal may abruptly change due to noise or brief fluctuations in the time series. To accurately identify the start and end of a charging phase, a threshold for the duration or amplitude of the change can be set. That is, a charging phase is considered to have started only when the charging status signal remains in a charging state for a certain period; similarly, a charging phase is considered to have ended only when the signal continuously returns to a non-charging state for a certain period. For example, for each identified charging phase, its duration (i.e., the difference between the charging end time and the charging start time) is calculated. If the duration of a charging phase is not greater than 0, the charging phase is deemed invalid and excluded. Only valid charging phases with a duration greater than 0 are used for subsequent error detection calculations. This screening step filters out invalid segments caused by instantaneous changes in the charging status signal or abnormal data acquisition, ensuring the physical rationality and calculation accuracy of subsequent energy integration and comparative analysis.

[0068] Step S2022: For any charging stage, extract the current and voltage data from the target operation data between the charging start time and the charging end time of the charging stage, and obtain the first state of charge value corresponding to the charging start time and the second state of charge value corresponding to the charging end time.

[0069] The first state of charge (SOC) and the second state of charge (SOC) refer to the percentage of remaining battery charge estimated and recorded in real time by the vehicle's battery management system (BMS) at the start and end times of an identified charging phase, respectively. Specifically, for a defined charging phase (defined by start and end timestamps), all data records falling within this time period are extracted from the time series of target operational data, using these two timestamps as boundaries. Then, from these records, the time-varying numerical sequences of current and voltage are specifically extracted, which will be used for subsequent physical calculations. Simultaneously, the specific data records corresponding to the start and end times are located, and the SOC values ​​reported and recorded by the vehicle's BMS at these two specific times are read. The SOC value at the start time is called the first SOC, and the SOC value at the end time is called the second SOC.

[0070] Step S2023: Integrate the current data and voltage data to determine the actual charging amount of the target vehicle during the charging phase.

[0071] Actual charge amount refers to the total electrical energy actually flowing into the battery pack during a charging phase, calculated through physical integration based on directly measured voltage and current data. It is a quantitative description of the physical facts of the charging process. Specifically, the extracted current and voltage sequences, varying over time during the charging phase, are used as input. The integral of the product of current and voltage over time is calculated. Since the data is discretely sampled (e.g., one point per second), this integral is usually approximated using numerical integration methods (such as accumulating the current and voltage products over each small time interval). The physical meaning of this calculation result is the total electrical energy actually flowing into the battery pack from the grid (or charging station) during the charging period. This value, calculated based on directly measured signals, is considered an objective physical fact of the energy increase during this charging process, i.e., the actual charge amount.

[0072] For example, the moment charging begins and the time when charging ends The data between them, through the current With voltage In time Integrating the power on the battery side, the actual charging amount is calculated. The specific formula is as follows:

[0073] Step S2024: Based on the first state of charge value and the second state of charge value, query the mapping relationship to obtain the remaining power of the first battery corresponding to the first state of charge value and the remaining power of the second battery corresponding to the second state of charge value.

[0074] The remaining capacity of the first battery and the remaining capacity of the second battery refer to the theoretical remaining energy values ​​of the battery, calculated by converting the first state of charge (SOC) value and the second SOC value using a mapping relationship. These are estimates of battery energy storage based on a benchmark model. Specifically, the first SOC value at the start of charging and the second SOC value at the end of charging are used as inputs to look up the pre-built mapping relationship. This mapping relationship acts like a lookup table or function, defining a corresponding theoretical remaining battery energy value for each possible SOC percentage. By looking up the table (or calculating), the remaining capacity of the first battery corresponding to the first SOC value and the remaining capacity of the second battery corresponding to the second SOC value are obtained. These two values ​​represent how much energy the battery should store at the start and end of charging, based on the standard battery model; they serve as benchmarks for subsequent comparative analysis.

[0075] Step S2025: The first difference between the remaining charge of the second battery and the remaining charge of the first battery is determined as the estimated charge amount of the target vehicle during the charging phase.

[0076] The first difference refers to the numerical result obtained by subtracting the remaining capacity of the first battery from the remaining capacity of the second battery. It represents the theoretically expected increase in battery energy from the start to the end of charging, based on the SOC change reported by the BMS and the benchmark model. The estimated charging amount is the first difference. It serves as a theoretical reference benchmark in the detection algorithm for comparison with the actual charging amount. Specifically, the first difference is obtained by subtracting the remaining capacity of the first battery (theoretical energy storage at the start of charging) from the remaining capacity of the second battery (theoretical energy storage at the end of charging) obtained from the table. This difference indicates how much the energy stored in the battery should theoretically have increased during this charging process, based on the SOC change reported by the BMS and the standard model.

[0077] Step S2026: The second difference between the estimated charging amount and the actual charging amount is determined as the first error difference.

[0078] The second difference refers to the numerical result obtained by subtracting the actual charging amount from the estimated charging amount. This value is the core output of large error detection. Specifically, the second difference is obtained by subtracting the actual charging amount calculated through physical integration from the estimated charging amount. This second difference is the same as the first error difference. It quantifies the deviation between the energy increase claimed by the vehicle system and the actual energy increase that actually occurs.

[0079] The vehicle state of charge (SOC) diagnostic method provided in this application identifies the complete charging stage based on the charging state signal, ensuring the clarity and specificity of the analysis scenario. It then simultaneously acquires the SOC values ​​at the start and end times of this stage, as well as the raw current and voltage data within the corresponding time window. By numerically integrating the current and voltage data, the actual physical charge received by the battery can be calculated, directly reflecting the true energy input. Simultaneously, using a pre-built mapping relationship, the SOC values ​​at the start and end times are converted into the corresponding remaining battery capacity, and the estimated charge based on the SOC change is calculated using the difference. Subtracting the estimated charge from the actual charge yields a clear first error difference. This application establishes a direct comparison channel between theoretical estimation and physical measurement on the same charging event, enabling the deviation in SOC estimation to be quantitatively and accurately captured and presented, providing solid and intuitive data evidence for subsequent judgment of whether there is an inflated SOC.

[0080] Step S203: Based on the data and mapping relationship within a preset time interval in the target operating data, perform error detection on the battery input and output energy to obtain a second error difference value. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0081] Step S204: Analyze the first error difference and the second error difference to determine the attribution diagnosis information for the falsely high state of charge of the target vehicle. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0082] This embodiment provides a method for diagnosing the state of charge of a vehicle, which can be used in electronic devices, such as servers. Figure 3 This is a flowchart of a vehicle state of charge diagnostic method according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain the target vehicle's target operating data, and the pre-built mapping relationship between the target vehicle's state of charge (SOC) value and the remaining battery capacity. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0083] Step S302: Based on the data and mapping relationship of the charging stage in the target operation data, error detection is performed on the energy change during the charging stage to obtain the first error difference value. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0084] Step S303: Based on the data and mapping relationship within the preset time interval in the target operating data, perform error detection on the battery input and output energy to obtain the second error difference value.

[0085] Specifically, step S303 includes: Step S3031: Analyze the target operating data to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within the preset time interval, and obtain the third state of charge value at the start time corresponding to the preset time interval and the fourth state of charge value at the end time corresponding to the preset time interval.

[0086] Cumulative power integral charging refers to the sum of the total electrical energy actually charged into the battery pack during all charging processes of the target vehicle within a selected preset time interval, calculated using real-time integral voltage and current data. It represents the total energy injected into the battery from the outside during that time period. Cumulative net energy consumption refers to the sum of the total net electrical energy output from the battery when the vehicle is in a non-charging state (such as driving or idling) within the same preset time interval. It represents the net energy consumed by the battery for vehicle driving and other activities during that time period (after deducting reverse charging such as energy recovery). Specifically, the corresponding data segments are extracted from the target operating data, using the start and end times of the preset time interval as boundaries. All operating records representing energy input processes within that time period are aggregated and cumulatively calculated according to a predetermined algorithm to obtain the estimated total energy flowing into the system within that period. Similarly, all operating records representing energy consumption or output processes within that time period are independently aggregated and cumulatively calculated to obtain the estimated total energy consumed or output by the system during the same period.

[0087] The third and fourth state-of-charge (SOC) values ​​refer to the remaining battery charge percentages reported and recorded in real time by the vehicle's battery management system (BMS) at the start and end times of a preset time interval, respectively. These serve as the start and end points for energy calculation within that time period. Specifically, the SOC values ​​reported by the BMS at the start and end times of the time interval are directly read from the target operating data and used as the third and fourth SOC values, respectively. This process quantifies the energy flow and start / end states within the time window.

[0088] In some optional implementations, the target operating data is parsed to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within a preset time interval, including: Step c1: Based on the charging status signal in the target operating data, filter out the charging status data and non-charging status data that are within a preset time interval from the target operating data.

[0089] Charging status data and non-charging status data refer to two subsets of data separated from the target operational data based on charging status signals. Charging status data includes all parameters marked as being charged; non-charging status data includes parameters for periods when the vehicle is not charging. Specifically, within a pre-defined time interval, each data record is traversed. It examines the signal field in each record that specifically indicates the charging status: if the signal indicates the vehicle is charging, the record is assigned to the charging status data set; otherwise, it is assigned to the non-charging status data set. Through this classification rule, the mixed time-series data stream is effectively divided into two sets of data representing energy input and energy output (or non-input) processes, respectively, laying the foundation for subsequent calculations of energy income and expenditure.

[0090] Step c2 involves integrating the current and voltage data included in the charging status data to obtain the cumulative power integral charging amount.

[0091] For the charging state data set, the current and voltage time series are extracted. The product of current and voltage over time is calculated using a numerical integration method; the physical result is the energy input to the battery from the external power source during that charging process. The integral results of all identified charging segments within a preset time interval are summed to obtain the cumulative power integral charging amount, representing the total charging energy for that time period.

[0092] Step c3 involves integrating the current and voltage data included in the non-charging state data to obtain the cumulative net energy consumption.

[0093] For the non-charging state data set, the same integral calculation operation is performed. The integral result here represents the net energy output of the battery when the vehicle is driving, idling, etc. (the reverse charging effect during negative current periods, such as energy recovery, has been naturally deducted). The cumulative net energy consumption is obtained by summing the integral results of all non-charging states within this time period, representing the total net energy consumed by the battery during that time period.

[0094] In the above implementation, the target operating data within a preset time interval is clearly divided into charging state data and non-charging state data using the clear operating condition identifier of the charging state signal. This division method is direct and objective, avoiding the ambiguity that may arise from complex operating condition judgments based on current direction or other derived indicators. Then, for the charging state data, the current and voltage data are directly integrated to obtain the cumulative power integral charging amount, which accurately reflects the actual energy received by the battery. For the non-charging state data, the current and voltage data are similarly integrated to obtain the cumulative net energy consumption, which characterizes the net energy consumption of the battery during vehicle operation. This process of classifying and integrating according to state strictly adheres to the essential differences between charging and driving (or idling, etc.) physical processes, making the physical definitions of the two cumulative quantities clear. The calculation results directly correspond to the actual energy input and output, ensuring the accuracy and reliability of the cumulative quantity data provided for subsequent error detection.

[0095] Step S3032: Based on the mapping relationship between the third state of charge value and the fourth state of charge value, obtain the remaining power of the third battery corresponding to the third state of charge value and the remaining power of the fourth battery corresponding to the fourth state of charge value.

[0096] The remaining capacity of the third and fourth batteries refers to the theoretical remaining battery energy values ​​obtained by converting the third and fourth state-of-charge (SOC) values ​​using a mapping relationship. These are theoretical estimates of battery energy storage at the start and end points of a time interval based on a standard model. Specifically, the third and fourth SOC values, representing the start and end states of the time interval, are used as input to look up a pre-built mapping relationship (SOC-remaining capacity conversion table). Through table lookup or calculation, the theoretical remaining battery energy values ​​based on the standard model for these two points are obtained, namely the remaining capacity of the third and fourth batteries. These two values ​​serve as benchmarks for evaluating changes in the battery's state of energy storage.

[0097] Step S3033: Based on the superposition result between the remaining charge of the third battery and the cumulative power integral charge, determine the battery input energy of the target vehicle within the preset time interval.

[0098] Battery input energy refers to the total income of the battery energy account within a preset time interval. Specifically, the theoretical energy storage at the beginning of the time interval (the remaining capacity of the third battery) is added to the total energy actually obtained from the outside during that interval (cumulative power integral charging amount), and the sum is the total income or total input energy of the battery energy account during that time period.

[0099] Step S3034: Based on the superposition result between the remaining power of the fourth battery and the cumulative net energy consumption, determine the battery output energy of the target vehicle within a preset time interval.

[0100] Battery output energy refers to the total expenditure of the battery energy account within the same preset time interval. Specifically, the theoretical energy storage at the end of the time interval (the remaining capacity of the fourth battery) is added to the total net energy consumed by the battery within that interval (cumulative net energy consumption). The sum is the total expenditure or total output energy of the battery energy account during that time period. Ideally, the input energy should equal the output energy.

[0101] In calculating the cumulative power integral charging amount and cumulative net energy consumption, the energy input and output processes are distinguished based on the charging status signal in the target operating data, and precise measurement is performed in conjunction with the current direction: When the vehicle is in a charging state, the current is usually negative, and the integral result of current and voltage (power integral charging amount) is negative, indicating that energy is input into the battery; when the vehicle is in a non-charging state such as driving or idling, the current is mostly positive, representing that energy is output from the battery, and the integral result is included in the net energy consumption. It should be noted that under special operating conditions such as energy recovery, negative current may also occur in the non-charging state. In this case, this part of energy is regarded as reverse charging input and will be deducted from the cumulative net energy consumption. Therefore, in most scenarios, the cumulative net energy consumption is positive, but under operating conditions such as heavy-load downhill driving with abnormally strong energy recovery, the cumulative net energy consumption may be calculated as negative, indicating that the total battery energy increases rather than decreases during this period.

[0102] Step S3035: Based on the third difference between the battery input energy and the battery output energy, determine the battery input-output difference ratio of the target vehicle; and determine the battery input-output difference ratio as the second error difference.

[0103] The third difference refers to the absolute difference between the battery input energy and the battery output energy. It directly reflects the absolute amount of energy imbalance within the battery during the statistical period. The battery input-output difference ratio is the ratio of the third difference to the battery input energy (usually expressed as a percentage). This ratio eliminates the influence of absolute energy magnitude and quantifies the relative severity of energy imbalance, serving as a key indicator for determining the existence of systematic errors or abnormal losses. Specifically, the absolute difference between the battery input energy and the battery output energy (i.e., the third difference) is calculated. Then, this absolute difference is divided by the battery input energy to obtain a ratio, namely the battery input-output difference ratio. This ratio eliminates the influence of the battery system's own energy scale and reflects the relative severity of energy imbalance. This ratio is defined as the second error difference. As a core indicator, it is used to determine whether there are systematic or abnormal deviations or losses in the energy measurement and metering of the battery system throughout the entire time window. The specific formula is shown below:

[0104] The vehicle state of charge (SBC) diagnostic method provided in this application selects a preset time interval and fully analyzes the vehicle's cumulative power integral charging amount and cumulative net energy consumption within that interval. These two data points represent the actual total energy input and output of the battery during the period. Simultaneously, the SBC values ​​at the start and end of the time interval are obtained and converted into the corresponding remaining battery capacity using a mapping relationship. The battery input energy is obtained by superimposing the remaining capacity at the start time with the cumulative charging amount; the battery output energy is obtained by superimposing the remaining capacity at the end time with the cumulative net energy consumption. The relative difference ratio between the battery input energy and output energy is calculated and used as a second error difference value. From the perspective of energy conservation, this application performs a closed-loop verification of the theoretical energy state change and actual energy flow accumulation of the battery over a complete time period. By calculating the relative ratio, the influence of different battery capacities or initial states can be effectively normalized, thereby revealing long-term systematic errors that are difficult to detect in a single charging event, providing a key quantitative indicator for diagnosing potential sensor drift or battery performance degradation.

[0105] Step S304: Analyze the first error difference and the second error difference to determine the attribution diagnosis information of the target vehicle's falsely high state of charge.

[0106] Specifically, step S304 includes: Step d1: If the first error difference exceeds the first preset threshold, it is determined that the target vehicle has a problem of falsely high state of charge, and the reason for the falsely high state of charge of the target vehicle is that there is a defect in the battery management system of the target vehicle.

[0107] A first preset threshold is used to determine whether the first error difference (i.e., the charging deviation in large error detection) is severe enough to indicate an inflated State of Charge (SOC) problem; for example, it can be 20 kWh. Specifically, the calculated first error difference (i.e., the deviation between the BMS-estimated charging amount and the actual charging amount in a single charge) is compared with a pre-set first preset threshold. If the first error difference is greater than the threshold, it is determined that the vehicle does indeed have an inflated SOC problem. The reason for attributing the cause to a defect in the Battery Management System (BMS) is that this error directly reflects a serious discrepancy between the SOC change estimated by the BMS's internal algorithm and the actual energy increase measured in the physical world during a specific charging event. This strongly points to a problem with the core algorithm logic responsible for state estimation, rather than simply sensor data errors.

[0108] Step d2: If the second error difference exceeds the second preset threshold, it is determined that the target vehicle has a current calculation error or a battery abnormality. The reason for the falsely high state of charge of the target vehicle is that the current sensor of the target vehicle has an error, or the battery of the target vehicle has abnormal heating or leakage.

[0109] The second preset threshold is used to determine whether the second error difference (i.e., the energy imbalance rate in small error detection) is significant enough to indicate a systematic current error or battery anomaly; for example, it can be 8%. Specifically, the calculated second error difference (i.e., the relative imbalance rate of battery energy balance over a long time window) is compared with another preset second threshold. If the second error difference is greater than this threshold, a persistent problem is determined. Possible causes are inferred to be two categories: first, current calculation error, which usually stems from calibration errors in the sensor measuring the current, leading to distortion of the basic data for measuring all energy flows; second, battery anomalies, such as abnormal heating or leakage, which means that some of the input energy is not effectively stored or measured, but is lost in an unexpected way. Both of these situations will disrupt the long-term energy balance of the battery system and indirectly lead to inaccurate SOC estimations that rely on current integration.

[0110] The vehicle state of charge (SOC) diagnostic method provided in this application establishes two clear logical judgment paths by setting independent diagnostic thresholds for the first and second error differences. When the error representing energy inconsistency during the charging phase exceeds the first preset threshold, the root cause of the problem can be clearly pointed to an algorithmic or logical defect in the battery management system. When the error representing long-term energy imbalance (i.e., the battery input-output difference ratio) exceeds the second preset threshold, the problem can be diagnosed as originating from measurement errors of the current sensor or physical faults such as abnormal heating or leakage of the battery itself. This analysis method based on quantified thresholds and preset rules allows complex SOC inflated phenomena to be classified and traced back to specific technical aspects, transforming abstract large errors into specific fault locations, thus providing highly operational and clear guidance for subsequent maintenance, calibration, or software upgrades.

[0111] This embodiment also provides a diagnostic device for the state of charge of a vehicle, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0112] This embodiment provides a diagnostic device for the state of charge of a vehicle, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire the target operating data of the target vehicle, as well as the pre-built mapping relationship between the state of charge value and the remaining battery power of the target vehicle. The first detection module 402 is used to detect the error of energy change during the charging stage based on the data and mapping relationship of the charging stage in the target operation data, and to obtain the first error difference value. The second detection module 403 is used to detect the error of battery input and output energy based on the data and mapping relationship within a preset time interval in the target running data, and obtain the second error difference value. Analysis module 404 is used to analyze the first error difference and the second error difference to determine the attribution diagnosis information of the target vehicle's falsely high state of charge.

[0113] In some optional implementations, the acquisition module 401 includes: The acquisition submodule is used to acquire the raw operating data of the target vehicle; The first identification submodule is used to identify the original running data and obtain the identification result; The first processing submodule is used to process the missing values ​​according to the data type corresponding to the missing values ​​if the identification result indicates that there are missing values ​​in the original running data, so as to obtain the target running data.

[0114] In some alternative implementations, the processing submodule includes: The deletion unit is used to delete data records containing missing values ​​in the original running data if the data type corresponding to the missing value is a unique identifier, so as to obtain the target running data. The filling unit is used to fill the missing value with the nearest valid value if the data type corresponding to the missing value is continuous physical parameter data, so as to obtain the target running data. The marking unit is used to retain the null value corresponding to the missing value and mark the missing value if the data type corresponding to the missing value is non-continuous physical parameter data, so as to obtain the target running data.

[0115] In some alternative implementations, the identification submodule includes: The acquisition unit is used to acquire the preset parameter range corresponding to each running parameter in the original running data; The determination unit is used to determine the presence of anomalies in the original operating data if the parameter value of any operating parameter in the original operating data is not within the preset parameter range of the corresponding operating parameter.

[0116] In some optional implementations, the acquisition module 401 further includes: The second processing submodule is used to treat outliers as missing values ​​if the identification result indicates that there are outliers in the original running data, so as to obtain the target running data.

[0117] In some alternative implementations, the first detection module 402 includes: The second identification submodule is used to identify at least one charging stage of the target vehicle based on the charging status signal in the target operating data. The extraction submodule is used to extract the current and voltage data from the target operation data for any charging stage from the charging start time to the charging end time, and to obtain the first state of charge value corresponding to the charging start time and the second state of charge value corresponding to the charging end time. The third processing submodule is used to integrate the current data and voltage data to determine the actual amount of charging of the target vehicle during the charging phase. The first query submodule is used to query the mapping relationship based on the first state of charge value and the second state of charge value to obtain the remaining power of the first battery corresponding to the first state of charge value and the remaining power of the second battery corresponding to the second state of charge value. The first determining submodule is used to determine the first difference between the remaining power of the second battery and the remaining power of the first battery as the estimated charging amount of the target vehicle during the charging phase. The second determining submodule is used to determine the second difference between the estimated charging amount and the actual charging amount as the first error difference.

[0118] In some alternative implementations, the second detection module 403 includes: The parsing submodule is used to parse the target operating data, determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within the preset time interval, and obtain the third state of charge value at the start time corresponding to the preset time interval, and the fourth state of charge value at the end time corresponding to the preset time interval. The second query submodule is used to query the mapping relationship based on the third state of charge value and the fourth state of charge value to obtain the remaining power of the third battery corresponding to the third state of charge value and the remaining power of the fourth battery corresponding to the fourth state of charge value. The third determination submodule is used to determine the battery input energy of the target vehicle within a preset time interval based on the superposition result between the remaining charge of the third battery and the cumulative power integral charging amount. The fourth determination submodule is used to determine the battery output energy of the target vehicle within a preset time interval based on the superposition result between the remaining power of the fourth battery and the cumulative net energy consumption. The fifth determination submodule is used to determine the battery input-output difference ratio of the target vehicle based on the third difference between the battery input energy and the battery output energy; The sixth determination submodule is used to determine the battery input-output difference ratio as the second error difference.

[0119] In some optional implementations, the parsing submodule includes: The filtering unit is used to filter out charging status data and non-charging status data within a preset time interval from the target operating data based on the charging status signal in the target operating data. The first processing unit is used to integrate the current data and voltage data included in the charging status data to obtain the cumulative power integral charging amount. The second processing unit is used to integrate the current and voltage data included in the non-charging state data to obtain the cumulative net energy consumption.

[0120] In some alternative implementations, the analysis module 404 includes: The first determination submodule is used to determine that if the first error difference exceeds the first preset threshold, the target vehicle has a problem of falsely high state of charge, and to determine that the reason for the falsely high state of charge of the target vehicle is that the battery management system of the target vehicle has a defect. The second determination submodule is used to determine that if the second error difference exceeds the second preset threshold, the target vehicle has a current calculation error or a battery abnormality, and to determine that the reason for the falsely high state of charge of the target vehicle is that the current sensor of the target vehicle has an error, or that the battery of the target vehicle has abnormal heating or leakage.

[0121] The vehicle state of charge diagnostic device provided in this application embodiment can execute the vehicle state of charge diagnostic method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0122] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0123] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0124] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0125] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory 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 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the vehicle state-of-charge diagnostic method of embodiments of this application.

[0126] Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0127] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the vehicle state-of-charge diagnostic method shown in the above embodiments is implemented.

[0128] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0129] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for diagnosing the state of charge of a vehicle, characterized in that, The method includes: Acquire the target vehicle's target operating data, as well as the pre-constructed mapping relationship between the target vehicle's state of charge value and the remaining battery capacity; Based on the data of the charging stage in the target operation data and the mapping relationship, the error of energy change during the charging stage is detected to obtain the first error difference; Based on the data within a preset time interval in the target operating data and the mapping relationship, the error of battery input and output energy is detected to obtain a second error difference; Analyze the first error difference and the second error difference to determine the attribution diagnosis information of the falsely high state of charge of the target vehicle.

2. The method according to claim 1, characterized in that, The acquisition of the target vehicle's target operating data includes: Obtain the original operating data of the target vehicle; The original operating data is identified to obtain the identification result; If the identification result indicates that there are missing values ​​in the original running data, then the missing values ​​are processed according to the data type corresponding to the missing values ​​to obtain the target running data.

3. The method according to claim 2, characterized in that, The step of processing the missing values ​​according to the data type corresponding to the missing values ​​to obtain the target running data includes: If the data type corresponding to the missing value is a unique identifier, then delete the data record containing the missing value in the original running data to obtain the target running data; If the data type corresponding to the missing value is continuous physical parameter data, then the missing value is filled forward using the nearest valid value to obtain the target running data; If the data type corresponding to the missing value is non-continuous physical parameter data, then the null value corresponding to the missing value is retained, and the missing value is marked to obtain the target running data.

4. The method according to claim 2, characterized in that, The process of identifying the original operating data to obtain the identification result includes: Obtain the preset parameter range corresponding to each operating parameter in the original operating data; If the parameter value of any operating parameter in the original operating data is not within the preset parameter range of the corresponding operating parameter, then the identification result is determined to include the presence of anomalies in the original operating data. The acquisition of the target vehicle's target operating data also includes: If the identification result indicates that there are outliers in the original running data, then the outliers are treated as missing values ​​to obtain the target running data.

5. The method according to claim 1, characterized in that, The step of detecting the error in energy change during the charging phase based on the data from the charging phase in the target operating data and the mapping relationship, to obtain a first error difference, includes: Based on the charging status signal in the target operating data, at least one charging stage of the target vehicle is identified; For any of the charging stages, current and voltage data from the start time to the end time of the charging stage are extracted from the target operation data, and a first state of charge value corresponding to the start time of charging and a second state of charge value corresponding to the end time of charging are obtained. The current data and the voltage data are integrated to determine the actual amount of charge the target vehicle receives during the charging phase. Based on the first state of charge value and the second state of charge value, the mapping relationship is queried to obtain the remaining power of the first battery corresponding to the first state of charge value and the remaining power of the second battery corresponding to the second state of charge value. The first difference between the remaining charge of the second battery and the remaining charge of the first battery is determined as the estimated charge amount of the target vehicle during the charging phase. The second difference between the estimated charging amount and the actual charging amount is determined as the first error difference.

6. The method according to claim 1, characterized in that, The step of detecting the error in battery input and output energy based on data within a preset time interval in the target operating data and the mapping relationship to obtain a second error difference includes: The target operating data is analyzed to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within the preset time interval, and the third state of charge value at the start time corresponding to the preset time interval and the fourth state of charge value at the end time corresponding to the preset time interval are obtained. Based on the third state of charge value and the fourth state of charge value, the mapping relationship is queried to obtain the remaining power of the third battery corresponding to the third state of charge value and the remaining power of the fourth battery corresponding to the fourth state of charge value; Based on the superposition result between the remaining charge of the third battery and the cumulative power integral charge, the battery input energy of the target vehicle within the preset time interval is determined. Based on the superposition result between the remaining power of the fourth battery and the cumulative net energy consumption, the battery output energy of the target vehicle within the preset time interval is determined; The battery input-output difference ratio of the target vehicle is determined based on the third difference between the battery input energy and the battery output energy. The battery input-output difference ratio is determined as the second error difference.

7. The method according to claim 6, characterized in that, The step of parsing the target operating data to determine the cumulative power integral charging amount and cumulative net energy consumption of the target vehicle within the preset time interval includes: Based on the charging status signal in the target operating data, charging status data and non-charging status data within the preset time interval are filtered out from the target operating data; The current data and voltage data included in the charging status data are integrated to obtain the cumulative power integral charging amount; The cumulative net energy consumption is obtained by integrating the current and voltage data included in the non-charging state data.

8. The method according to claim 1, characterized in that, The step of analyzing the first error difference and the second error difference to determine the attribution diagnostic information for the falsely high state of charge of the target vehicle includes: If the first error difference exceeds the first preset threshold, it is determined that the target vehicle has a problem of falsely high state of charge, and the reason for the falsely high state of charge of the target vehicle is that the battery management system of the target vehicle has a defect. If the second error difference exceeds the second preset threshold, it is determined that the target vehicle has a current calculation error or a battery abnormality, and the reason for the falsely high state of charge of the target vehicle is that the current sensor of the target vehicle has an error, or the battery of the target vehicle has abnormal heating or leakage.

9. A diagnostic device for the state of charge of a vehicle, characterized in that, The device includes: The acquisition module is used to acquire the target operating data of the target vehicle, as well as the pre-constructed mapping relationship between the state of charge value and the remaining battery power of the target vehicle. The first detection module is used to detect the error of energy change during the charging stage based on the data of the charging stage in the target operation data and the mapping relationship, and to obtain the first error difference value. The second detection module is used to detect the error of battery input and output energy based on the data within a preset time interval in the target operating data and the mapping relationship, and to obtain a second error difference value. The analysis module is used to analyze the first error difference and the second error difference to determine the attribution diagnosis information of the falsely high state of charge of the target vehicle.

10. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the diagnostic method for the vehicle's state of charge as described in any one of claims 1 to 8.

Images