A health status inspection platform and method for new energy vehicles
The annual health status inspection platform for new energy vehicles utilizes charging testing equipment and intelligent analysis models to fill the gap in battery health status testing during the annual inspection of new energy vehicles, improving testing efficiency and safety while reducing costs.
Patent Information
- Application Number
- CN202311430798.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-31
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-10-31
AI Technical Summary
The current annual inspection process for new energy vehicles lacks testing of battery health, which fails to ensure vehicle safety and stability, leading to potential safety hazards.
Design a health status annual inspection platform for new energy vehicles, including charging testing equipment, online and offline testing subsystems. By collecting battery parameter information and analyzing historical operating data, the platform generates battery health status detection results and combines deep convolutional neural networks and electrochemical mechanism models for accurate detection.
It enables comprehensive detection of the health status of new energy vehicle batteries, improves the efficiency and safety of annual inspections, reduces hardware costs, and facilitates the maintenance and iteration of detection algorithms.
Smart Images

Figure CN117347078B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle inspection technology, specifically to a platform and method for annual health status inspection of new energy vehicles. Background Technology
[0002] Annual vehicle inspection is a crucial step in ensuring the safety, legality, and performance of motor vehicles, playing a vital role in safeguarding daily vehicle use and road traffic safety. With the rapid development and widespread adoption of new energy vehicle technology, the number of new energy vehicles is continuously increasing, bringing new safety challenges while meeting people's travel needs.
[0003] Battery state of health (SOH) has a crucial impact on a vehicle's driving range and driving safety. A healthy battery ensures the vehicle's stability and safety during operation, providing a longer driving range and making the vehicle more convenient for the driver. If the battery has problems, such as overcharging, over-discharging, or aging, it can lead to serious safety incidents. These problems may cause the vehicle to suddenly lose power while driving, or even result in a fire during charging.
[0004] However, the current annual inspection process for new energy vehicles is no different from that for gasoline vehicles, and there is a lack of testing methods for the core component of new energy vehicles—the battery—making it impossible to test the battery's health status. This cannot ensure the safe operation of new energy vehicles. Therefore, battery testing is particularly important in the annual inspection. To ensure the safe operation of new energy vehicles, inspection agencies need to develop corresponding testing methods for battery performance and health status, promptly identify and resolve potential battery problems, and ensure the safe and stable operation of the vehicle. Summary of the Invention
[0005] The purpose of this invention is to propose a health status annual inspection platform and method for new energy vehicles. This technical solution provides a testing method for new energy vehicles, enabling comprehensive testing of new energy vehicles, including battery health status.
[0006] To achieve the above objectives, in a first aspect, embodiments of this disclosure provide a health status annual inspection platform for new energy vehicles, including: Charging testing equipment is used to collect parameter information of the battery system of new energy vehicles; The registration module is used to select inspection items and register vehicle information to generate a list of vehicles to be inspected; The online inspection subsystem is used to collect historical operating data from the vehicle terminal according to the selected inspection items, analyze the historical operating data through the cloud platform, and generate a vehicle annual inspection report. The online inspection subsystem includes an accelerator pedal inspection module, a motor temperature inspection module, an operating energy consumption inspection module, and a battery consistency inspection module. The offline testing subsystem is used to analyze the parameter information collected by the charging testing equipment and generate test results of the battery health status.
[0007] The beneficial effects of the basic solution are as follows: The charging testing equipment enables real-time collection of vehicle battery system parameter information at offline vehicle inspection stations, allowing these stations to collect more testing data for new energy vehicles. This facilitates the generation of more comprehensive inspection reports, including battery health status test results. The registration module can statistically analyze vehicles to be inspected and their corresponding testing items, enabling the platform to better allocate testing resources. The online testing module, based on a cloud platform, reduces the hardware costs of inspection stations while increasing the computing power resources of the cloud platform for data analysis, improving testing efficiency, reducing the backlog of vehicles to be inspected, and facilitating the maintenance and iteration of related testing algorithms through unified algorithms on the cloud platform. The offline testing subsystem mainly focuses on battery health status detection. Since the offline testing subsystem is primarily responsible for battery health status detection, its computing power requirements are not high. It can be easily integrated with the charging testing equipment to modify existing vehicle inspection stations, reducing modification costs and facilitating the promotion of this technical solution.
[0008] As a feasible preferred solution, the charging test equipment includes a charging test parameter setting module and a reverse connection protection module; the charging test parameter setting module is used to set the battery capacity, charging cut-off SOC, maximum single cell temperature, default auxiliary power parameters and single cell voltage parameters; the reverse connection protection module is used to detect the positive and negative polarity of the battery and cut off the power supply when reverse polarity is detected.
[0009] As a feasible preferred solution, the offline testing subsystem includes a first battery health testing module and a second battery health testing module; the first battery health testing module is used to quickly detect the health status of electric vehicle batteries and includes a model building submodule and a first health analysis submodule; the second battery health testing module is used to accurately detect the health status of electric vehicle batteries and includes a parameter pre-identification submodule and a second health analysis submodule.
[0010] As a feasible and preferred embodiment, the model building submodule is used to build the battery model and the SOH estimation model, specifically including the following: By rotating the drum, the prototype vehicle of the target test model is fully discharged to SOC=0% or the battery management system automatically cuts off the power. Then, the prototype vehicle is charged with multi-stage constant current at a charging rate of 0.1C. Every time 10% of the rated capacity is charged, the vehicle is powered off, left to stand for 1 hour, and then charged again until SOC=100% or the charging current is automatically disconnected. Calculate the charging capacity during the entire charging process and the cumulative charging capacity before each rest period to obtain the current capacity and the actual SOC at each rest period; after each rest period, record the battery terminal voltage as OCV to obtain the correspondence between SOC and OCV, and obtain the SOC-OCV lookup table through linear interpolation. The vehicle was discharged to 50% SOC and subjected to constant current pulse excitation for 10 minutes to obtain voltage feedback data. The parameters of the equivalent circuit model were identified using the least squares method with forgetting factor, thereby establishing the battery model. To obtain the feature sequence, the state of harmonics (SOH) of the battery model was randomly defined using simulation software, and an excitation period of 5 minutes with a current rate of 0.3C was input. The generated voltage data was then normalized to obtain the feature sequence. A deep convolutional neural network model is built, with the feature sequence as the model input and the corresponding randomly defined SOH as the model output. The model is then trained to obtain the SOH estimation model.
[0011] As a feasible preferred solution, the first health analysis submodule controls the charging detection equipment to perform a 5-minute charging excitation at a current rate of 0.3C for the vehicle with unknown SOH, and collects voltage data in real time to obtain a feature sequence. The feature sequence is then input into the SOH estimation model to output an estimated SOH value.
[0012] As a feasible preferred solution, the parameter pre-identification submodule is used to determine a reasonable range of parameters for electric vehicles of various models, including the following: HPPC full-charge tests were conducted on electric vehicles of various models to obtain test data, including the total battery system voltage, the highest single-cell voltage, current, and SOC. The number of cells in series in the battery system was estimated using the total battery system voltage and the highest single-cell voltage to obtain the average single-cell voltage data of the battery system. Based on the material system used in the battery, set the parameter range in the electrochemical mechanism model; The parameters in the electrochemical mechanism model are identified using an optimization algorithm. The objective optimization equation is as follows:
[0013] In the formula, To measure voltage, To detect the vehicle's identification voltage, To measure SOC, To identify SOC;
[0014] Check if the root mean square error of the voltage is less than 30mV; otherwise, reset the parameter range.
[0015] As a feasible preferred embodiment, the second health analysis submodule is used to detect the battery health status of the electric vehicle under test, specifically including: The charging testing equipment is controlled to charge the vehicle under current conditions and collect voltage data. Based on the detected vehicle model, the corresponding parameter group in the model parameter library is called as the initial parameters for the optimization algorithm to re-identify the model parameters; Substituting the identified parameters into the capacity calculation formula, the available capacity Q of the detected vehicle is obtained. The calculation formula is as follows:
[0016] Where F is the Faraday constant and A is the electrode area. The negative porosity, This represents the maximum lithium-ion concentration at the negative electrode. This refers to the lithium intercalation range of the negative electrode.
[0017] The health status of the vehicle's battery is calculated using the following formula:
[0018] In the formula, The rated capacity of the battery on the vehicle's nameplate is used as the average of multiple calculations to obtain the final SOH.
[0019] As a feasible preferred solution, the offline detection subsystem also includes a model selection module, which selects to call either the first battery health detection module or the second battery health detection module based on the number of vehicles to be detected.
[0020] As a feasible preferred solution, the model selection module is also used to analyze historical data to predict the detection needs and trends in different time periods in the future. The historical data includes the number of vehicles to be detected in the past, the historical detection time and the historical detection results. Based on the prediction results, the module can adjust the call to the first battery health detection module or the second battery detection module in advance.
[0021] Secondly, this disclosure also provides a method for annual health status inspection of new energy vehicles, which utilizes the aforementioned new energy vehicle health status inspection platform and includes the following steps: Step S100: After arriving at the vehicle inspection station, the user selects the required new energy vehicle inspection items and registers them. Step S200: After registration is completed, the registration information will be sent to the platform. The platform will determine whether to retrieve the vehicle's historical driving information and whether to use the charging detection equipment based on the vehicle's registration information. In step S300, the online inspection subsystem generates an annual inspection report by calling up historical vehicle information; Step S400: If it is necessary to check the battery health status, the testing personnel will drive the user's vehicle to the new energy vehicle charging testing equipment and insert the charging gun. In step S500, select the vehicle to be tested from the registration list. The charging test equipment detects that the charging gun is in use and starts the test. During the test, the charging test equipment transmits the parameter information to the platform through the SOCKET interface. In step S600, after the platform receives the message that the test is completed, the offline testing subsystem uses the registered business information and the data collected by the charging testing equipment to test the health status of the electric vehicle battery, displays the test results, and updates the information into the vehicle's annual inspection report. Step S700: After the annual inspection report is generated, the report is reviewed. Once the review is approved, the report is sent to the annual inspection station. Attached Figure Description
[0022] Figure 1 A schematic diagram of a health status annual inspection platform for new energy vehicles; Figure 2 This is a schematic diagram of the single-particle model structure; Figure 3 This is a schematic diagram of the current operating condition; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0023] To make the technical solution and advantages of this application clearer, the technical solution of the present invention will be further described in detail below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are only some embodiments of the present invention, and are only used to explain this application, not to limit it. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated; they can be combined with each other to achieve better technical effects. The same reference numerals appearing in the accompanying drawings of the following embodiments represent the same features or components, and can be applied to different embodiments.
[0024] Furthermore, unless otherwise defined, the technical or scientific terms used in this invention description shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains.
[0025] Furthermore, it should be noted that in the description of this invention, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0026] The present invention will now be described in further detail with reference to the accompanying drawings: Explanation of reference numerals in the attached drawings: Electronic device 500, processor 501, communication interface 502, memory 503, bus 504.
[0027] Reference Figure 1 A health status annual inspection platform for new energy vehicles, comprising: Charging testing equipment is used to collect parameter information of the battery system of new energy vehicles. The equipment can read some basic parameters of the battery system and collect environmental parameters and some static vehicle information through sensors and manual input interfaces.
[0028] The charging testing equipment includes a charging parameter setting module, which is used to set battery capacity, State of Charge (SOC), maximum cell temperature, default auxiliary power parameters, and cell voltage parameters. Once connected to the device, the charging testing equipment can use its built-in algorithms and installed hardware to collect real-time battery system parameter information from new energy vehicles.
[0029] The charging testing equipment also includes a reverse polarity protection module, used to detect the positive and negative polarities of the battery and immediately cut off the power supply when reverse polarity is detected to prevent battery overheating and damage, ensuring the safety of equipment use. The charging testing equipment can be designed with reverse polarity protection circuitry or can analyze voltage and current during the charging process to determine if reverse polarity has occurred.
[0030] The registration module is used to select the new energy vehicle testing items to be carried out and register the vehicle information, including vehicle model, license plate number, vehicle identification number, etc., and generate a list of vehicles to be tested.
[0031] The online inspection subsystem collects historical operating data from the vehicle's infotainment system, analyzes the data via a cloud platform, and generates a vehicle annual inspection report. The online inspection subsystem includes modules for accelerator pedal detection, motor temperature detection, energy consumption detection, and battery consistency detection.
[0032] The accelerator pedal detection module is used to detect whether there are any abnormal response issues with the accelerator pedal. It includes a pedal data processing submodule, a pedal analysis submodule, and a pedal anomaly detection submodule.
[0033] The pedal data processing submodule, as shown in Table 1, is used to perform data validity processing on the pedal data in the vehicle's historical driving information.
[0034] Table 1
[0035] The pedal analysis submodule is mainly used for calculation and analysis of accelerator pedal data, specifically including the following: The safety element is extracted, and in this application, the safety element index is the ratio of the accelerator pedal or brake pedal torque to the output motor torque, calculated using the following formula:
[0036] In the formula, ACCELERATIONPEDAL indicates the accelerator pedal opening degree, BRAKEPEDAL indicates the brake pedal opening degree, and MOTORTORQUE indicates the drive motor torque.
[0037] The signal is amplified and securely quantized using the following formula:
[0038]
[0039] In the formula, This represents the magnification factor, typically taken as 20. The safety element is represented by the signal amplification function, which amplifies the differences to facilitate subsequent quantization processing; n is the sequence length, U is the result after signal amplification, and p is the variance entropy.
[0040] The cumulative probability of risk is calculated using the following formula:
[0041]
[0042] In the formula, It is the probability of stable operation within the time window, i.e., the variance entropy; 1-p is its risk probability; and Sp is the risk integral sequence within the current time window. The Sp series value represents the maximum risk within the current observation period. This represents the cumulative risk up to the present moment. This represents the cumulative risk up to the previous observation time, determined by the current absolute risk Q value. (0≤) ≤l) is a measure of the rate of risk change; if there is no significant risk change in the current observation period... =0.
[0043] The accelerator pedal anomaly detection submodule is used to calculate and determine whether the accelerator pedal is malfunctioning based on the calculation results. Specifically, it includes: The relative rate of risk accumulation η is calculated using the following formula:
[0044] MaxRiskSpeed is used to apply speed filtering to the Sp risk integral sequence and then obtain the maximum risk speed, while NormalRiskSpeed is used to calculate the mean of the squares of the Sp risk integral sequence.
[0045] Set judgment conditions, and issue an early warning when any condition is met, indicating that the vehicle has a high risk of abnormal starting.
[0046] The judgment conditions include: ①η>50; ②Pc>0.5; ③MaxRiskSpeed>0.0025; ④MaxRiskSpeed<0.0025; ⑤Number of risk frequencies R>3.
[0047] The motor temperature detection module is used to detect whether the temperature of the drive motor of a new energy vehicle is abnormally high, effectively reducing the probability of abnormal temperature rise in the drive motor and ensuring the safety of users' lives and property. It includes a motor data processing submodule, a temperature analysis submodule, and a motor anomaly detection submodule.
[0048] The motor data processing submodule extracts motor temperature detection data from the vehicle's infotainment system and cleans up invalid and empty data. The motor temperature detection report must include: time, total vehicle current, total voltage, drive motor information, and battery temperature probe information.
[0049] The temperature analysis submodule is used to analyze the data from each continuous operation segment. It selects the minimum probe temperature as the ambient temperature reference and calculates the difference and variance between the motor temperature and the minimum probe temperature at each moment. The calculation formula is as follows:
[0050]
[0051]
[0052] In the formula, This represents the motor temperature at time t. This represents the probe temperature at time t. Indicates the minimum temperature of the probe. This represents the difference between the motor temperature and the minimum probe temperature at time t. Let represent the variance at time t.
[0053] For each segment of operation, abnormal motor temperature rise is identified. The data is normalized using variance entropy, and calculated using a cumulative integral method. The integral sequence is then filtered using speed filtering, and the maximum value after filtering is taken as the cumulative fault probability. Based on this cumulative fault probability, it is determined whether a risk exists or a fault has already occurred. The calculation formula is as follows:
[0054]
[0055] In the formula, This represents the variance entropy at time t. This represents the cumulative probability of failure at time t.
[0056] The motor anomaly detection submodule determines the current status of the drive motor based on a threshold, outputs a warning result, and sets a risk threshold. and fault threshold In this embodiment,
[0057]
[0058]
[0059] There is a medium to high risk of abnormal temperature rise:
[0060] There is a risk of abnormally high temperature: .
[0061] The energy consumption detection module is used to detect abnormal energy consumption in electric vehicles, and can promptly identify vehicles with aging batteries or abnormal wear in the transmission system. It includes an energy consumption data processing submodule, an energy consumption analysis submodule, and an energy consumption anomaly detection submodule.
[0062] The energy consumption data processing submodule is used to collect energy consumption data of electric vehicles, including cumulative mileage, total voltage, and total current. Missing values are removed and the data is cleaned, and driving segments are divided. In this embodiment, the data is divided according to the cumulative mileage of 1000km.
[0063] The energy consumption analysis submodule extracts discharge segments for each driving segment and calculates feature-based energy consumption assessments. It extracts discharge segments with a total current greater than 0 from each driving segment, extracts the total current I and total voltage U data for these discharge segments, and calculates the energy A required to cover the corresponding cumulative mileage of the electric vehicle. The calculation formula is as follows: ;
[0064] In the formula, Energy consumption value To consume voltage, To consume current.
[0065] The energy consumption anomaly detection submodule is used to determine whether there are anomalies in energy consumption data. It analyzes the energy consumption of a driving segment as a statistical measure, establishing an abnormal energy consumption threshold X, as shown in the following formula:
[0066] In the formula, The average energy consumption value. The standard deviation of energy consumption values; application 3 The rule establishes the abnormal energy consumption threshold X for the statistical quantity, and the threshold can be adjusted appropriately for different vehicle models and driving environments.
[0067] Based on the abnormal energy consumption threshold, the energy consumption values of each test vehicle in each driving segment are assessed for abnormality, and anomaly assessment results are generated. Specifically, the energy consumption value of each test vehicle in each driving segment is compared with the abnormal energy consumption threshold. If the energy consumption value is less than the abnormal energy consumption threshold, the vehicle is considered normal; otherwise, it is considered abnormal.
[0068] The battery consistency detection module is used to promptly detect inconsistencies in the battery pack, such as voltage differences and capacity differences, preventing battery overheating, overcharging, and over-discharging malfunctions caused by inconsistencies, thereby improving battery pack safety. It includes a battery data acquisition submodule, a consistency analysis submodule, and a consistency judgment submodule.
[0069] The battery data acquisition submodule is used to collect and process battery signal data, including Time, Charge_Status, Sum_Current, and V (voltage matrix). It cleans the battery signal data, deleting invalid data such as NANs and spaces. If outliers are found, a moving average is used for cleaning. Data with voltage values greater than 6V and less than 1V is deleted.
[0070] The consistency analysis submodule is used to calculate and analyze battery signal data. It selects voltage data from the discharge state for calculation, specifically extracting the Time and V corresponding to (Charge_status==3).
[0071] Calculate the average voltage between each cell; perform feature extraction on the voltage data V. The voltage data V has N columns, each column representing a cell, and there are N cells in total. The row number represents time, in seconds. Then calculate the average voltage between cells in each row. The formula for the m-th row is as follows: ;
[0072] Calculate the difference between the voltage value of each cell and its average voltage value, that is: calculate the difference between the voltage value of each column in each row and the average voltage value of the row. The calculation formula for the m-th row is as follows:
[0073] The absolute value of the difference is taken as the voltage difference matrix D.
[0074] The consistency judgment submodule is used to determine whether there are anomalies in the voltage difference data. It iterates through the row vectors in the voltage difference matrix D, calculates the 25th and 75th quantiles of the values, i.e., sorts the row vectors and calculates the digit j = C × 75% (where C is the column number). If C × 75% is not an integer, it is rounded up to obtain the final 75th quantile. Let be the average of the j-th term and the (j+1)-th term, i.e. Similarly, the 25th quantile can be obtained. Finally, the upper limit of the outlier threshold is obtained. The upper limit of the abnormal threshold changes in real time according to the changes in cell voltage.
[0075] Iterate through the N voltage difference values in each row of the voltage difference matrix D, and determine whether each voltage difference value is greater than the upper limit of the abnormal threshold. If the condition is met, i.e.: If i represents time and j represents the j-th cell, then determine whether the voltage difference between adjacent time points is greater than the upper limit of the abnormal threshold.
[0076] If the voltage difference between adjacent time points exceeds the upper limit of the abnormal threshold, then this time point is marked. The system determines the frequency of anomaly detection within a given period, specifically the number of times the voltage difference exceeds the upper limit of the anomaly threshold. If the condition is met, the anomaly detection must be satisfied at least once every two hours after the marked time. This condition of satisfying the anomaly detection at least once every two hours is accumulated, and so on. When the condition is met more than four times and the time condition is satisfied, a consistency anomaly is determined to have indeed occurred, and the time and cell number of the anomaly are marked.
[0077] The offline testing subsystem analyzes the testing data collected by the charging testing equipment, generates an annual battery health status report, and includes a first battery health testing module, a second battery health testing module, and a model selection module.
[0078] The first battery health detection module is used to quickly detect the health status of lithium batteries in electric vehicles. It includes a model building submodule and a first health analysis submodule.
[0079] The model building submodule is used to build battery models and SOH estimation models, and specifically includes the following: First, the target vehicle model is fully discharged to SOC=0% or the battery management system (BMS) automatically shuts off by running a drum. Then, the vehicle is charged in multiple stages with constant current at a charging rate of 0.1C. Every time 10% of the rated capacity is charged, the vehicle is powered off, left to stand for 1 hour, and then charged again until SOC=100% or the charging current is automatically disconnected.
[0080] The charging capacity and the cumulative charging capacity before each rest period are calculated using the ampere-hour integration method to obtain the current capacity and the actual SOC at each rest period. After each rest period, the battery terminal voltage is recorded as OCV, thus obtaining the correspondence between SOC and OCV, and a SOC-OCV lookup table is obtained through linear interpolation.
[0081] The vehicle is discharged to 50% SOC and subjected to constant current pulse excitation for 10 minutes to obtain voltage feedback data. The parameters of the equivalent circuit model are identified using the least squares method with forgetting factor, thereby establishing the battery model (first-order equivalent digital twin model).
[0082] To obtain the characteristic sequence, the State of Emergency (SOH) of the battery model is randomly defined using simulation software, and an excitation period of 5 minutes with a current rate of 0.3C is input. The battery model under different SOHs will produce different voltage feedbacks. The generated voltage data is normalized to obtain the characteristic sequence. The specific method for obtaining the characteristic sequence is: voltage at each sampling point / cutoff voltage when the battery is fully charged, thus obtaining the normalized voltage sequence. The voltage sequence and the excitation current sequence are used as the characteristic sequence.
[0083] A deep convolutional neural network model is built, with the feature sequence as the model input and the corresponding randomly defined SOH as the model output. The model is then trained to obtain the SOH estimation model.
[0084] The first health analysis submodule is used to obtain the SOH estimate of the electric vehicle. For vehicles with unknown SOH, the charging detection equipment is controlled to perform a 5-minute charging excitation at a current rate of 0.3C, and voltage data is collected in real time. The feature sequence is obtained through the aforementioned feature sequence acquisition method, and the feature sequence is input into the SOH estimation model to output the SOH estimate, thus realizing rapid SOH detection.
[0085] The second battery health detection module is used to more accurately detect the health status of electric vehicle batteries. It includes a parameter pre-identification submodule and a second health analysis submodule.
[0086] Lithium-ion batteries are complex electrochemical systems. Electrochemical mechanism models simulate battery performance by describing the migration, diffusion, and charge transfer behavior of lithium ions within the battery. (Refer to...) Figure 2 It is a single-particle model (SPM), which has high simulation accuracy and high calculation speed at discharge rates below 1C.
[0087] The parameter pre-identification submodule is used to determine the reasonable range of parameters for electric vehicles of various models. Specifically, it includes: HPPC full-charge tests were conducted on electric vehicles of various models to obtain test data such as total battery system voltage, highest single-cell voltage, current, and SOC. The number of cells connected in series in the battery system was estimated using the total battery system voltage and the highest single-cell voltage to obtain the average single-cell voltage data of the battery system.
[0088] Based on the material system used in the battery, a reasonable parameter range is set for the parameters in the electrochemical mechanism model.
[0089] Using the particle swarm optimization algorithm, 18 parameters in the electrochemical mechanism model were identified. The objective optimization equation of the algorithm is as follows:
[0090] In the formula, To measure voltage, To detect the vehicle's identification voltage, To measure SOC, To identify SOC.
[0091] Check if the root mean square error of the voltage is less than 30mV; otherwise, reset the parameter range.
[0092] The second health analysis submodule is used to detect the battery health status of the electric vehicle under test. Specific functions include: Reference Figure 3 The charging detection equipment is controlled to charge the vehicle under current conditions and collect data such as voltage.
[0093] Based on the detected vehicle model, the corresponding parameter set in the model parameter library is called as the initial parameters for the particle swarm optimization algorithm to re-identify the model parameters.
[0094] Substituting the identified parameters into the capacity calculation formula, the available capacity Q of the detected vehicle is obtained. The calculation formula is as follows:
[0095] Where F is the Faraday constant and A is the electrode area. The negative porosity, This represents the maximum lithium-ion concentration at the negative electrode. This refers to the range of lithium intercalation at the negative electrode.
[0096] The health status of the vehicle battery under inspection is calculated using the following formula:
[0097] In the formula, The rated capacity of the battery on the vehicle's nameplate is used as the average of multiple calculations to obtain the final SOH.
[0098] The model selection module is used to select the battery health detection module based on the number of vehicles to be tested. At the same time, it predicts the future vehicles to be tested based on historical data. The model selection module will adjust the detection model in advance to minimize the backlog of vehicles to be tested.
[0099] The model selection module will also analyze historical data, collecting information such as the number of vehicles to be inspected, inspection times, and inspection results. By analyzing this data, it can predict inspection demand and trends for different time periods.
[0100] The model selection module will adjust and select the appropriate battery health detection module in advance based on the predicted detection needs and trends, so as to optimize the overall detection efficiency and resource utilization.
[0101] This disclosure also provides a method for annual health status inspection of new energy vehicles, which utilizes a new energy vehicle health status inspection platform and includes the following steps: Step S100: After arriving at the vehicle inspection station, the user selects the required new energy vehicle inspection items and registers them.
[0102] In step S200, after the user completes the registration, the registration information will be sent to the platform. The platform will determine whether to retrieve the vehicle's historical driving information and whether to use the charging detection equipment based on the vehicle's registration information.
[0103] In step S300, the online inspection subsystem generates an annual inspection report by calling up the vehicle's historical information.
[0104] Step S400: If it is necessary to check the battery health status, the testing personnel will drive the user's vehicle to the new energy vehicle charging testing equipment and insert the charging gun.
[0105] In step S500, the testing personnel need to select the vehicle to be tested from the registration list on the device. The new energy vehicle charging testing device detects that the charging gun is in use and starts the test. During the test, the new energy vehicle charging testing device transmits the parameter information to the platform through the SOCKET interface.
[0106] In step S600, after the platform receives the message indicating the end of the test, the offline testing subsystem uses the business information registered by the user and the data collected by the charging testing equipment to test the health status of the electric vehicle battery, feeds back the test results to the equipment for display, and updates the information in the vehicle's annual inspection report.
[0107] Step S700: After the annual inspection report is generated, the inspection personnel will review the report and send it to the annual inspection station after the review is approved.
[0108] This disclosure also provides a storage medium storing a computer program. When the computer program is executed by a processor, it can implement all the contents of the annual health status inspection platform for new energy vehicles described in the above embodiments.
[0109] Those skilled in the art will understand that implementing all or part of a health status annual inspection platform for new energy vehicles can be accomplished by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the content of an embodiment of the health status annual inspection platform for new energy vehicles. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0110] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the content of the annual health status inspection platform for new energy vehicles described in the above embodiments. In this application embodiment, the processor is the control center of the computer system; it can be a physical machine processor or a virtual machine processor.
[0111] Reference Figure 4The electronic device 500 includes at least one processor 501, at least one communication interface 502, at least one memory 503, and at least one bus 504. The bus 504 is used for communication between these components, the communication interface 502 is used for signaling or data communication with other node devices, and the memory 503 stores machine-readable instructions executable by the processor 501. When the electronic device 500 is running, the processor 501 communicates with the memory 503 via the bus 504. When the machine-readable instructions are invoked by the processor 501, they execute the content of a new energy vehicle health status annual inspection platform as described in the above embodiment.
[0112] The above content is merely an embodiment of the present invention. Commonly known structures and characteristics of the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can improve and implement this solution based on the guidance provided in this application and their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.
Claims
1. A health status annual inspection platform for new energy vehicles, characterized in that: include: Charging testing equipment is used to collect parameter information of the battery system of new energy vehicles; The registration module is used to select inspection items and register vehicle information to generate a list of vehicles to be inspected; The online inspection subsystem is used to collect historical operating data from the vehicle terminal according to the selected inspection items, analyze the historical operating data through the cloud platform, and generate a vehicle annual inspection report. The online inspection subsystem includes an accelerator pedal inspection module, a motor temperature inspection module, an operating energy consumption inspection module, and a battery consistency inspection module. The offline testing subsystem is used to analyze the parameter information collected by the charging testing equipment and generate test results of the battery health status. The offline testing subsystem includes a first battery health testing module and a second battery health testing module. The first battery health detection module is used to quickly detect the health status of electric vehicle batteries, and includes a model building submodule and a first health analysis submodule. The second battery health detection module is used to accurately detect the health status of electric vehicle batteries, including a parameter pre-identification submodule and a second health analysis submodule; The model building submodule is used to build the battery model and the SOH estimation model, and specifically includes the following: By rotating the drum, the prototype vehicle of the target test model is fully discharged to SOC=0% or the battery management system automatically cuts off the power. Then, the prototype vehicle is charged with multi-stage constant current at a charging rate of 0.1C. Every time 10% of the rated capacity is charged, the vehicle is powered off, left to stand for 1 hour, and then charged again until SOC=100% or the charging current is automatically disconnected. Calculate the charging capacity during the entire charging process and the cumulative charging capacity before each rest period to obtain the current capacity and the actual SOC at each rest period; after each rest period, record the battery terminal voltage as OCV to obtain the correspondence between SOC and OCV, and obtain the SOC-OCV lookup table through linear interpolation. The vehicle was discharged to 50% SOC and subjected to constant current pulse excitation for 10 minutes to obtain voltage feedback data. The parameters of the equivalent circuit model were identified using the least squares method with forgetting factor, thereby establishing the battery model. To obtain the feature sequence, the state of harmonics (SOH) of the battery model was randomly defined using simulation software, and an excitation period of 5 minutes with a current rate of 0.3C was input. The generated voltage data was then normalized to obtain the feature sequence. A deep convolutional neural network model is built, with the feature sequence as the model input and the corresponding randomly defined SOH as the model output. The model is then trained to obtain the SOH estimation model. For vehicles with unknown SOH, the first health analysis submodule will control the charging detection equipment to perform a 5-minute charging excitation at a current rate of 0.3C and collect voltage data in real time to obtain a feature sequence. This feature sequence will then be input into the SOH estimation model to output an estimated SOH value. The parameter pre-identification submodule is used to determine the reasonable range of parameters for each type of electric vehicle. The second health analysis submodule is used to detect the battery health status of the electric vehicle under test.
2. The annual health status inspection platform for new energy vehicles according to claim 1, characterized in that: The charging testing equipment includes a charging test parameter setting module and a reverse connection protection module; The charging and testing parameter setting module is used to set the battery capacity, charging cutoff SOC, maximum cell temperature, default auxiliary power parameters, and cell voltage parameters. The reverse polarity protection module is used to detect the positive and negative polarities of the battery and cut off the power supply when reverse polarity is detected.
3. The annual health status inspection platform for new energy vehicles according to claim 2, characterized in that: The parameter pre-identification submodule is used to determine the reasonable range of parameters for each electric vehicle model, including the following: HPPC full-charge tests were conducted on electric vehicles of various models to obtain test data, including the total battery system voltage, the highest single-cell voltage, current, and SOC. The number of cells in series in the battery system was estimated using the total battery system voltage and the highest single-cell voltage to obtain the average single-cell voltage data of the battery system. Based on the material system used in the battery, set the parameter range in the electrochemical mechanism model; The parameters in the electrochemical mechanism model are identified using an optimization algorithm. The objective optimization equation is as follows: In the formula, To measure voltage, To detect the vehicle's identification voltage, To measure SOC, To identify SOC; Check if the root mean square error of the voltage is less than 30mV; otherwise, reset the parameter range.
4. The annual health status inspection platform for new energy vehicles according to claim 3, characterized in that: The second health analysis submodule is used to detect the battery health status of the electric vehicle under test, and its specific contents include: The charging testing equipment is controlled to charge the vehicle under current conditions and collect voltage data. Based on the detected vehicle model, the corresponding parameter group in the model parameter library is called as the initial parameters for the optimization algorithm to re-identify the model parameters; Substituting the identified parameters into the capacity calculation formula, the available capacity Q of the detected vehicle is obtained. The calculation formula is as follows: Where F is the Faraday constant and A is the electrode area. The negative porosity, This represents the maximum lithium-ion concentration at the negative electrode. This refers to the lithium intercalation range of the negative electrode. The health status of the vehicle's battery is calculated using the following formula: In the formula, The rated capacity of the battery on the vehicle's nameplate is used as the average of multiple calculations to obtain the final SOH.
5. A health status annual inspection platform for new energy vehicles according to any one of claims 1-4, characterized in that: The offline detection subsystem also includes a model selection module, which selects to call the first battery health detection module or the second battery health detection module based on the number of vehicles to be detected.
6. The annual health status inspection platform for new energy vehicles according to claim 5, characterized in that: The model selection module is also used to analyze historical data to predict the detection needs and trends in different time periods in the future. The historical data includes the number of vehicles to be detected in the past, the historical detection time and the historical detection results. Based on the prediction results, the module can adjust and call the first battery health detection module or the second battery detection module in advance.
7. A method for annual health status inspection of new energy vehicles, utilizing a new energy vehicle health status inspection platform as described in any one of claims 1-6, comprising the following steps: Step S100: After arriving at the vehicle inspection station, the user selects the required new energy vehicle inspection items and registers them. Step S200: After registration is completed, the registration information will be sent to the platform. The platform will determine whether to retrieve the vehicle's historical driving information and whether to use the charging detection equipment based on the vehicle's registration information. In step S300, the online inspection subsystem generates an annual inspection report by calling up historical vehicle information; Step S400: If it is necessary to check the battery health status, the testing personnel will drive the user's vehicle to the new energy vehicle charging testing equipment and insert the charging gun. In step S500, select the vehicle to be tested from the registration list. The charging test equipment detects that the charging gun is in use and starts the test. During the test, the charging test equipment transmits the parameter information to the platform through the SOCKET interface. In step S600, after the platform receives the message that the test is completed, the offline testing subsystem uses the registered business information and the data collected by the charging testing equipment to test the health status of the electric vehicle battery, displays the test results, and updates the information into the vehicle's annual inspection report. Step S700: After the annual inspection report is generated, the report is reviewed. Once the review is approved, the report is sent to the annual inspection station.
Citation Information
Patent Citations
SOH estimation method and battery health state estimation system based on single-particle model
CN115877248A
Method for Detecting Storage Battery of Vehicle and Battery Detection Device
US20230152389A1
