Vehicle mileage estimation method, system and detection terminal

Abstract

The application relates to the technical field of vehicle condition detection, and discloses a vehicle driving mileage calculation method, a vehicle driving mileage calculation system and a detection terminal. The vehicle driving mileage calculation method comprises the following steps: when the vehicle is a new energy vehicle, acquiring real-time battery parameters, real-time driving condition coefficients and driving mileage data; when the vehicle is a fuel vehicle, acquiring driving mileage data; preprocessing the driving mileage data to obtain effective driving mileage data; when the vehicle is a new energy vehicle, inputting the real-time battery parameters and the real-time driving condition coefficients into a driving mileage mapping model to obtain first driving mileage data, and determining double-anchor-point driving mileage data of the vehicle based on the effective driving mileage data; and calculating actual driving mileage data based on the double-anchor-point driving mileage data and the effective driving mileage data. The vehicle driving mileage calculation method can accurately calculate the actual driving mileage data of the vehicle, reduces driving mileage determination errors, and has strong universality and high landing feasibility.

Description

Technical Field

[0001] This application relates to the field of vehicle condition detection technology, and in particular to a method, system and detection terminal for calculating vehicle mileage. Background Technology

[0002] Currently, the used car industry is rife with instances of tampering with odometer readings or altering mileage data in vehicle electronic control units (ECUs). Traditional testing methods typically involve simply comparing the odometer reading with the ECU's data, lacking a logical framework for accurately correcting for the vehicle's mileage. This leads to significant errors in determining the actual mileage, making it difficult to accurately ascertain the vehicle's current distance traveled, and these methods are easily circumvented by subtle tampering techniques. Summary of the Invention

[0003] In view of this, embodiments of this application provide a method, system and detection terminal for calculating vehicle mileage, which can effectively improve the problem of large errors in determining the actual mileage of a vehicle.

[0004] In a first aspect, embodiments of this application provide a method for estimating vehicle mileage, including: When the vehicle is a new energy vehicle, the real-time battery parameters, real-time driving condition coefficients and driving mileage data of the vehicle are obtained; when the vehicle is a fuel vehicle, the driving mileage data of the vehicle is obtained. The driving mileage data is preprocessed to obtain valid driving mileage data; When the vehicle is a new energy vehicle, the real-time battery parameters and the real-time driving condition coefficient are input into the driving mileage mapping model to obtain the first driving mileage data. When the vehicle is a fuel vehicle, the weighted value of each of the effective driving mileage data is calculated to obtain the first driving mileage data. The second mileage data is determined based on the deviation between the effective mileage data, and the dual-anchor point mileage data of the vehicle is determined based on the first mileage data and the second mileage data. The actual mileage of the vehicle is calculated based on the dual-anchor point mileage data and the effective mileage data.

[0005] In a first possible embodiment of the first aspect, the preprocessing of the mileage data to obtain valid mileage data includes: Identify invalid mileage data in the driving mileage data, delete the invalid mileage data, and obtain the valid driving mileage data. The invalid mileage data includes one or more of the following: abnormal mileage data, abnormal data with a cliff-like increase in speed, and abnormal data with logical contradictions.

[0006] In a second possible embodiment of the first aspect, the real-time battery parameters include battery type, battery health status, total battery cycle count, temperature deviation coefficient, and battery fast charging frequency. The step of inputting the real-time battery parameters and the real-time driving condition coefficient into the mileage mapping model to obtain first mileage data includes: The mileage mapping model is used to determine the mapping relationship between the battery parameters corresponding to the battery type and the battery health status and the mileage. Substituting the battery health status, the total number of battery cycles, the temperature deviation coefficient, the battery fast charging frequency, and the real-time driving condition coefficient into the mapping relationship between battery parameters and driving mileage, the first driving mileage data is obtained.

[0007] In a third possible embodiment of the first aspect, the effective mileage data includes the cumulative mileage of multiple electronic control units of the vehicle, and the calculation of a weighted value of each of the effective mileage data to obtain the first mileage data includes: The weighting coefficient for the cumulative mileage of each electronic control unit is determined based on the confidence level of the cumulative mileage of each electronic control unit; The cumulative mileage of each electronic control unit is weighted and summed based on the weighting coefficient of the cumulative mileage of each electronic control unit to obtain the first driving mileage data.

[0008] In a fourth possible embodiment of the first aspect, the effective mileage data of the fuel-powered vehicle includes the cumulative mileage of the engine electronic control unit, the cumulative mileage of the transmission electronic control unit, and the cumulative mileage of other electronic control units; the effective mileage data of the new energy vehicle includes the cumulative mileage of multiple electronic control units; and the step of determining the second mileage data based on the deviation between the effective mileage data includes: In the case that the vehicle is a gasoline vehicle, a first deviation is determined between the cumulative mileage of the engine electronic control unit and the cumulative mileage of the transmission electronic control unit and the cumulative mileage of the other electronic control units, respectively. The cumulative mileage corresponding to the smallest first deviation is selected as the second driving mileage data; When the vehicle is a new energy vehicle, the average cumulative mileage of each electronic control unit is calculated, and a second deviation between the cumulative mileage of each electronic control unit and the average value is determined; The cumulative mileage corresponding to the smallest second deviation is selected as the second driving mileage data.

[0009] In a fifth possible embodiment of the first aspect, the effective mileage data includes the cumulative mileage of the electronic control unit and the cumulative mileage of the battery management system, and the determination of the dual-anchorage mileage data of the vehicle based on the first mileage data and the second mileage data includes: When the vehicle is a new energy vehicle, the deviation between the first driving mileage data and the cumulative mileage of the battery management system and the cumulative mileage of the electronic control unit is calculated to obtain the mileage deviation. Based on the mileage deviation, a first weighting coefficient for the first mileage data and a second weighting coefficient for the second mileage data are determined; When the vehicle is a new energy vehicle or a fuel vehicle, the first mileage data and the second mileage data are weighted and summed based on the first weighting coefficient and the second weighting coefficient to obtain dual-anchor mileage data, wherein the first weighting coefficient is greater than the second weighting coefficient.

[0010] In a sixth possible embodiment of the first aspect, calculating the actual mileage data of the vehicle based on the dual-anchor point mileage data and the effective mileage data includes: Calculate the mean of the effective mileage data to obtain the average mileage of the vehicle; Linear fitting is performed on the effective mileage data to determine the fitted mileage data of the vehicle at the current time; Based on the confidence levels of the dual-anchor point mileage data, the mean mileage, and the fitted mileage data, a third weighting coefficient for the dual-anchor point mileage data, a fourth weighting coefficient for the mean mileage, and a fifth weighting coefficient for the fitted mileage data are determined. The actual mileage data is obtained by weighting and summing the dual-anchor point mileage data, the mean mileage, and the fitted mileage data based on the third, fourth, and fifth weighting coefficients. The third weighting coefficient is greater than the fourth weighting coefficient, and the fourth weighting coefficient is greater than the fifth weighting coefficient.

[0011] In a seventh possible embodiment of the first aspect, it further includes: Calculate the deviation between the actual mileage data and the real-time mileage displayed on the vehicle's odometer, and correct the real-time mileage displayed on the odometer based on the deviation to obtain the corrected mileage displayed on the odometer.

[0012] Secondly, embodiments of this application provide a vehicle mileage estimation system, including: The data acquisition module is used to acquire the real-time battery parameters, real-time driving condition coefficients and driving mileage data of the vehicle when the vehicle is a new energy vehicle, and to acquire the driving mileage data of the vehicle when the vehicle is a fuel vehicle. The data processing module is used to preprocess the mileage data to obtain valid mileage data; The mileage mapping module is used to input the real-time battery parameters and the real-time driving condition coefficient into the mileage mapping model when the vehicle is a new energy vehicle to obtain the first mileage data; when the vehicle is a fuel vehicle, it calculates the weighted value of each of the effective mileage data to obtain the first mileage data. The dual-anchor mileage determination module is used to determine second mileage data based on the deviation between the effective mileage data, and to determine the dual-anchor mileage data of the vehicle based on the first mileage data and the second mileage data. The actual mileage determination module is used to calculate the actual mileage data of the vehicle based on the dual-anchor point mileage data and the effective mileage data.

[0013] Thirdly, embodiments of this application provide a detection terminal, which includes a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the above-described vehicle mileage estimation method.

[0014] The embodiments of this application have the following beneficial effects: This embodiment of a vehicle mileage estimation method includes: acquiring real-time battery parameters, real-time driving condition coefficients, and mileage data when the vehicle is a new energy vehicle; acquiring mileage data when the vehicle is a gasoline vehicle; preprocessing the mileage data to obtain effective mileage data; inputting the real-time battery parameters and real-time driving condition coefficients into a mileage mapping model when the vehicle is a new energy vehicle to obtain first mileage data; calculating the weighted value of each effective mileage data when the vehicle is a gasoline vehicle to obtain the first mileage data; determining second mileage data based on the deviation between the effective mileage data; determining dual-anchor mileage data based on the first and second mileage data; and calculating the actual mileage data of the vehicle based on the dual-anchor mileage data and the effective mileage data.

[0015] Based on the above scheme, this vehicle mileage estimation method can, for new energy vehicles, integrate real-time battery parameters of battery physical aging, and output first mileage data to correct the cumulative mileage of the battery management system through a mileage mapping model. For fuel vehicles, it determines second mileage data based on the weighted value of effective mileage data and the deviation between effective mileage data, thereby obtaining highly reliable dual-anchor mileage data. Furthermore, it integrates multiple collected effective mileage data to accurately estimate the actual mileage data of the vehicle, reducing mileage determination errors, and has strong versatility and high feasibility for implementation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This paper illustrates a first flowchart of a vehicle mileage estimation method according to an embodiment of this application. Figure 2 This paper illustrates a second flowchart of the vehicle mileage estimation method according to an embodiment of this application. Figure 3 This paper illustrates a third flowchart of the vehicle mileage estimation method according to an embodiment of this application. Figure 4 This paper shows a schematic diagram of a first structure of a vehicle mileage estimation system according to an embodiment of this application; Figure 5 A second structural schematic diagram of the vehicle mileage estimation system according to an embodiment of this application is shown.

[0018] Explanation of key component symbols: 200 - Vehicle mileage estimation system; 210 - Data acquisition module; 220 - Data processing module; 230 - Mileage mapping module; 240 - Dual anchor point mileage determination module; 250 - Actual mileage determination module; 260 - Display mileage correction module. Detailed Implementation

[0019] The technical solutions in 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, and not all embodiments.

[0020] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0022] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in a generally used dictionary) shall be interpreted as having the same meaning as in the context of the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0023] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0024] The following examples illustrate the method for calculating the vehicle's mileage.

[0025] Figure 1 A flowchart illustrating a vehicle mileage estimation method according to an embodiment of this application is shown. Exemplarily, the vehicle mileage estimation method includes the following steps: S110 acquires real-time battery parameters, real-time driving condition coefficients, and mileage data of the vehicle when it is a new energy vehicle, and acquires mileage data of the vehicle when it is a fuel vehicle.

[0026] For example, the mileage data includes the vehicle's historical mileage data, the cumulative mileage of the electronic control unit, etc. The historical mileage data includes, but is not limited to, the mileage recorded by nodes such as traffic management annual inspection, 4S maintenance, insurance claims, and third-party inspections.

[0027] S120 preprocesses the mileage data to obtain valid mileage data.

[0028] In one embodiment, invalid mileage data is identified from the mileage data, deleted, and valid mileage data is obtained. Exemplarily, invalid mileage data includes one or more of the following: mileage regression anomaly data, precipitous growth anomaly data, and logically contradictory anomaly data.

[0029] In one implementation, each mileage record carries a unique recording time, accurate to the month / day, and is sorted in ascending order of time to form a time-series mileage dataset. A time-mileage trend curve is plotted with the recording time as the horizontal axis (unit: year / month) and the corresponding mileage as the vertical axis (unit: kilometer), visually presenting the mileage growth pattern over time. Annual average mileage slope calculation: Based on the sorted time-series mileage dataset, the annual average mileage slope of the vehicle is calculated. For example, a reasonable range for passenger cars is 10,000 to 25,000 kilometers per year. The slope calculation formula is as follows: ; In the formula, This represents the slope of the vehicle's average annual mileage. Indicates the latest mileage. The earliest mileage, T1 represents the time corresponding to the latest mileage, while T2 represents the time corresponding to the earliest mileage.

[0030] As an example, it can automatically identify and remove invalid mileage data based on the time-mileage trend curve and the slope of the vehicle's average annual mileage, retaining only data that conforms to the growth logic and is within a reasonable slope range.

[0031] In one embodiment, the following uses the historical mileage data of a certain family passenger vehicle (registered in 2020, with an initial factory rated mileage of 0 kilometers) as an example to explain in detail the process of identifying and removing invalid mileage data. The specific historical mileage data is shown in the table below (sorted):

[0032] In this embodiment, the criteria for identifying mileage regression anomalies are: the mileage value recorded later is less than the mileage value recorded earlier, violating the basic logic of mileage increasing over time, and is therefore determined to be false and invalid mileage data. The criteria for identifying precipitous growth anomalies are: the mileage growth rate between two adjacent time points exceeds the slope of the vehicle's average annual mileage (e.g., 10,000 to 25,000 kilometers / year), and is therefore determined to be abnormal growth rate and belongs to false and invalid mileage data. For example, serial number 4 (December 2023, 71,000 km) has a previous valid data point of serial number 2 (November 2021, 18,000 km), with a time interval of 2 years and 1 month (approximately 2.08 years). The mileage increase is 71,000 - 18,000 = 53,000 km, with an average annual growth rate of 53,000 ÷ 2.08 ≈ 25,481 km / year. This exceeds the upper limit of the reasonable range (10,000 to 25,000 km / year), and the growth rate has skyrocketed (compared to the previous average of 18,000 km / year, the growth rate has increased significantly without any reasonable explanation). Therefore, it is determined to be invalid mileage data and is removed.

[0033] The criteria for identifying logically contradictory and abnormal data are as follows: logically contradictory mileage growth across years, or excessively large deviations in mileage data of different record types at the same time point (e.g., deviation > 10%), are considered invalid data. For example, if a vehicle's third-party inspection mileage in October 2023 is 40,000 kilometers, the insurance claim mileage in December 2023 is 35,000 kilometers (mileage regression), and the 4S maintenance mileage in January 2024 is 50,000 kilometers (an increase of 15,000 kilometers in 2 months, with an average annual growth rate of 90,000 kilometers / year, which is seriously abnormal), both sets of data have logical contradictions and should be removed.

[0034] After removing invalid data in serial numbers 3 and 4, the remaining valid mileage data is shown in the table below:

[0035] As an example, the annual average mileage slope is calculated based on compliant and valid historical mileage data: the time interval (August 2020 - October 2024) is approximately 4 years, the mileage increase is 73,500 - 0 = 73,500 kilometers, and the annual average slope k = 73,500 ÷ 4 = 18,375 kilometers / year, which is within a reasonable range of 10,000 to 25,000 kilometers / year. This set of compliant data will be used to calculate actual mileage data in subsequent calculations to ensure the accuracy of the extrapolation results. The method for removing invalid mileage data from the electronic control unit's cumulative mileage and the battery management system (BMS) is the same as above and will not be repeated here.

[0036] S130: When the vehicle is a new energy vehicle, the real-time battery parameters and real-time driving condition coefficients are input into the driving mileage mapping model to obtain the first driving mileage data. When the vehicle is a fuel vehicle, the weighted value of each effective driving mileage data is calculated to obtain the first driving mileage data.

[0037] As an example, the mileage mapping model is based on the general aging law of lithium iron phosphate / ternary lithium vehicle batteries. It establishes a battery parameter-driving condition coefficient-mileage mapping model to correct the mileage deviation caused by factors such as temperature, fast charging frequency, and actual vehicle use conditions.

[0038] In one embodiment, the construction process of the mileage mapping model includes: First, obtaining the actual mileage of different vehicles under different driving conditions and with different battery parameters to obtain model training samples. Then, selecting various mainstream power batteries such as lithium iron phosphate and ternary lithium (covering different capacities and manufacturers to ensure sample representativeness), simulating actual vehicle usage scenarios, conducting long-term aging tests, and collecting core data. For each battery type, 30-50 sets of samples are selected to ensure that the samples cover different production batches and different initial states, avoiding bias caused by a single sample.

[0039] To simulate the key factors affecting battery aging in actual vehicle use, cyclic aging tests were conducted in different scenarios, and the corresponding battery parameters, driving condition coefficients and driving mileage were recorded throughout the process: (1) Cycle test: Both types of batteries started from the initial battery health state (SOH) of 100% and were cycle tested according to industry standards (charge and discharge rate 1C, standard temperature 25℃). Every 100 cycles were completed, the current SOH value and cumulative charge and discharge capacity were recorded until SOH dropped to 50% (battery scrapping threshold); (2) Temperature effect test: 500 cycles were completed at six temperature gradients of -35℃, -10℃, 0℃, 25℃, 45℃ and 60℃, and the corresponding relationship between SOH decay rate, cycle number and SOH at different temperatures was recorded; (3) Fast charging frequency effect Impact Test: Five scenarios were set up with fast charging frequencies of 0% (full slow charging), 30%, 50%, 70%, and 100% (full fast charging). 800 cycles of testing were completed at a standard temperature of 25℃, and the differences in SOH attenuation under different fast charging frequencies were recorded. (4) Operating Condition Impact Test: Three scenarios were simulated: urban congestion (low speed, frequent start-stop), high-speed cruising (uniform speed, high load), and mixed operating conditions (congestion + high speed, 50% each). 600 cycles of testing were completed, and the correlation data of battery capacity attenuation, SOH changes, and cumulative mileage under different operating conditions were recorded. Based on the above tests, a standardized database was established. Each data entry in the standardized database includes battery parameters, driving condition coefficients, and mileage to ensure data traceability and reusability.

[0040] As an example, model training samples are constructed by combining each data point from a standardized database, ensuring that the samples cover multiple battery types, all aging stages, and all usage scenarios, providing sufficient data support for model training. The core input parameters of this mileage mapping model include battery parameters and driving condition coefficients, and the output parameter is the mileage, which is the actual mileage reference value calculated by the model, used to correct deviations in the accumulated mileage of the battery management system caused by factors such as temperature.

[0041] The battery parameters include battery type, battery health status, total battery cycle life, temperature deviation coefficient, and fast charging frequency. The temperature deviation coefficient is the difference between the current average annual operating temperature and the standard temperature (25℃). The fast charging frequency is the ratio of the vehicle's historical fast charging count to the total number of charges. The driving condition coefficient can be quantified based on the proportion of urban congestion and highway cruising conditions to quantify the impact of driving conditions on mileage. For example, the formula for calculating the driving condition coefficient is: ; In the formula, Indicates the driving condition coefficient. This indicates the percentage of congested working conditions in the city. This indicates the percentage of high-speed cruising conditions.

[0042] In one implementation, 500-800 data points / samples are collected, covering various batteries such as lithium iron phosphate and ternary lithium, with a state of equilibrium (SOH) range of 50%-100% and a cycle count of 0-3000, covering different temperatures, fast charging frequencies, and vehicle operating conditions. The mileage of each sample serves as a calibration label, battery health status and total battery cycle count are used as core input features, and temperature deviation coefficient, battery fast charging frequency, and real-time driving condition coefficient are used as deviation compensation features to construct a complete model training sample. The sample set can be divided into a training set (for model training) and a test set (for model accuracy verification) in a 7:3 ratio to avoid overfitting.

[0043] As an example, the collected experimental data can be screened and fitted to eliminate abnormal data (such as data deviations caused by test errors or equipment failures). By extracting the general aging patterns of different batteries, the correlation between real-time battery parameters, real-time driving condition coefficients, and driving mileage data can be clarified.

[0044] For example, the general aging pattern of lithium iron phosphate batteries is as follows: ① Core correlation: SOH is linearly negatively correlated with the number of cycles, with no obvious inflection point. For every 100 additional cycles, SOH decreases by an average of 2%~3% (under standard temperature of 25℃, full slow charging, and mixed operating conditions); ② Temperature effect: When the temperature is below -10℃ or above 45℃, the SOH decay rate accelerates. Under the same number of cycles, SOH decreases by an additional 1%~1.5%; the aging rate is the most gradual and the decay is the most uniform between 0℃ and 25℃; ③ Fast charging effect: When the fast charging frequency is >70%, the SOH decay rate accelerates by 15%~20%, mainly because the high temperature and high current generated by fast charging exacerbate the internal side reactions of the battery; ④ Operating condition effect: Under urban congestion conditions, SOH decays 5%~8% faster than under high-speed cruising conditions, because frequent start-stop cycles cause large fluctuations in battery charging and discharging, accelerating aging.

[0045] The general aging pattern of ternary lithium batteries is as follows: ① Core correlation: SOH (State of Health) is negatively correlated with the number of cycles, with a clear inflection point; in the early stage (SOH 80%-100%), the decay is slow, and SOH decreases by 1%~2% for every 100 additional cycles; in the later stage (SOH 50%-80%), the decay accelerates, and SOH decreases by 3%~4% for every 100 additional cycles; ② Temperature effect: less sensitive to temperature than lithium iron phosphate batteries, SOH decay rate is stable within the range of -10℃~45℃; above 50℃, the decay rate accelerates, and SOH decreases by an additional 0.8%~1.2% for the same number of cycles; ③ Fast charging effect: more sensitive to fast charging, when the fast charging frequency is >60%, the SOH decay rate accelerates by 20%~25%, and aging phenomena such as capacity drop and increased internal resistance are likely to occur; ④ Operating condition effect: under high-speed cruising conditions, SOH decay is 3%~6% faster than under urban congestion conditions, because high speed and high load lead to continuous high power output of the battery, accelerating electrode material wear.

[0046] In this embodiment, the extracted aging patterns can be compared and verified with publicly available battery aging data in the industry and actual battery aging data from used car inspections (500+ new energy vehicle models). The pattern parameters can be optimized to ensure compatibility with new energy batteries of different brands and usage scenarios. Verification standards: the deviation between the predicted SOH value and cycle number and the actual data is ≤3%; the deviation of aging rate under different scenarios is ≤2%. After verification, the final universal aging pattern is determined as the core basis for establishing the mapping model.

[0047] Then, based on the general aging patterns obtained above, the model is trained and validated based on the model training samples to obtain a validated mileage mapping model. The core of model training is to achieve a precise correlation between battery parameters, driving condition coefficients and mileage.

[0048] In one implementation, a lightweight algorithm combining linear regression and piecewise fitting can be used to balance computational speed and accuracy, avoiding the computational burden on equipment caused by complex algorithms. For example, for lithium iron phosphate batteries (where SOH is linearly related to the number of cycles), a linear regression algorithm is used; for ternary lithium batteries (where SOH is non-linearly related to the number of cycles), a piecewise linear fitting algorithm (with SOH=80% as the inflection point, fitting in two segments) is used.

[0049] Model training: Using battery health status and total battery cycle count as core inputs, and temperature deviation coefficient, battery fast charging frequency, and real-time driving condition coefficient as deviation compensation factors, the model is trained and its coefficients optimized with the target driving mileage as the objective, until the error between the model output value and the sample calibration label is less than a preset threshold, such as 2%. The trained model is validated using test set samples to ensure that the error between the model's output driving mileage and the actual driving mileage is less than the preset threshold. If the error exceeds the threshold, the model coefficients are re-optimized until the target is met.

[0050] For example, the mapping relationship between battery parameters and driving range is the mapping relationship between model coefficients, battery health status, total battery cycle count, temperature deviation coefficient, battery fast charging frequency, and real-time driving condition coefficient and driving range. The mapping relationship between battery parameters corresponding to battery type and battery health status and driving range is fixed in the driving range mapping model. During detection, the battery type and battery health status are automatically read to determine the mapping relationship. The mapping relationship is then substituted into the calculation, eliminating the need for on-site training and adapting to rapid detection scenarios.

[0051] In one embodiment, a mileage mapping model is used to determine the mapping relationship between battery parameters and mileage corresponding to battery type and battery health status; the battery health status, total battery cycle count, temperature deviation coefficient, battery fast charging frequency and real-time driving condition coefficient are substituted into the mapping relationship between battery parameters and mileage to obtain the first mileage data.

[0052] As an example, the mapping relation can be expressed as: ; In the formula, This represents the first mileage data output by the mileage mapping model, i.e., the corrected cumulative mileage of the battery management system. Indicates the battery health status (%); Indicates the total number of battery cycles (times); This represents the temperature deviation coefficient (°C), ranging from -35 to 20°C. Indicates the battery fast charging frequency (%), ranging from 0% to 100%; This represents the real-time driving condition coefficient, ranging from 0 to 1.

[0053] , , , , , All represent model coefficients, for example, , , , , , Examples of possible values ​​are as follows (can be adjusted based on actual training results): Lithium iron phosphate battery: =1200, =-0.8, =500, =-0.005, =-0.003, =0.05; Ternary lithium battery (SOH≥80%): =1150, =-0.7, =450, =-0.004, =-0.004, =0.04; Ternary lithium battery (SOH < 80%): =1150, =-1.2, =450, =-0.004, =-0.004, =0.04.

[0054] In this embodiment, the first driving mileage data is the theoretical real mileage calculated using the driving mileage mapping model. This data is used to calibrate the deviation of the actual collected cumulative mileage of the battery management system. It also takes into account variables such as temperature, fast charging, and operating conditions. This ensures the accuracy and universality of the cumulative mileage of the battery management system after correction, and also ensures the accuracy of mileage counting when there are anomalies such as tampering or storage failures in the cumulative mileage of the battery management system.

[0055] For example, the cumulative mileage of the battery management system is unique to new energy vehicles, and the cumulative mileage of the battery management system can be corrected through a driving mileage mapping model. When the vehicle is a gasoline vehicle, the cumulative mileage of the electronic control unit in the effective driving mileage data can be weighted and summed to determine the first driving mileage data of the gasoline vehicle.

[0056] In one embodiment, the effective mileage data of the fuel vehicle includes the cumulative mileage of multiple electronic control units (ECUs). A weighting coefficient for the cumulative mileage of each ECU is determined based on the confidence level of that cumulative mileage. The cumulative mileages of each ECU are then summed using their respective weighting coefficients to obtain the first mileage data. In this embodiment, the greater the difficulty in tampering with the cumulative mileage of an ECU (i.e., the higher its confidence level), the larger the weighting coefficient. The sum of the weighting coefficients for the cumulative mileage of all ECUs is 1.

[0057] For example, in one embodiment, the cumulative mileage of the electronic control unit of a fuel vehicle includes, but is not limited to, the cumulative mileage of the TCU (Transmission Control Unit), the cumulative mileage of the ECM (Engine Control Module), the cumulative mileage of the ABS (Anti-lock Braking System), and the cumulative mileage of the BCM (Body Control Module).

[0058] The TCU's accumulated mileage is fixed in the underlying hardware chip and uses encrypted storage. It cannot be rewritten without dedicated equipment and original factory authorization. Even if it is forcibly rewritten, it will leave chip read and write traces and cause abnormal transmission shifting logic, which is easily detected. It is considered to be extremely difficult to tamper with without leaving a trace, so the corresponding weighting coefficient is the highest and it is set as S level.

[0059] ECM mileage accumulation is stored in an encrypted partition. Flashing requires dedicated diagnostic equipment and manufacturer authorization, and logs will remain after flashing. It is difficult to tamper with (but less difficult than TCU / BMS), and is considered a difficult-to-tamper mileage. Therefore, the weighting factor is set to A level, which is lower than S level and higher than B level.

[0060] The cumulative mileage of ABS and BCM (Body Control Module) is stored inside the ECU, but the encryption level is low. Ordinary third-party diagnostic equipment can flash the data, and there are no obvious abnormal traces after tampering. The difficulty of tampering is moderate. It is tamperable but requires certain skills. Therefore, the weight is low and it is only used as an auxiliary reference. Therefore, the weighting coefficient is set to B.

[0061] As an example, when the vehicle is a gasoline-powered vehicle, the formula for calculating the corresponding first mileage data is as follows: ; In the formula, Indicates the first Accumulated mileage of each electronic control unit Indicates the first The weighting coefficient corresponding to the cumulative mileage of each electronic control unit. This indicates the total number of miles accumulated by the electronic control unit. The ordinal number representing the cumulative mileage of the electronic control unit. This refers to the first mileage data for fuel-powered vehicles.

[0062] S140, determine the second mileage data based on the deviation between the effective mileage data, and determine the dual-anchor point mileage data of the vehicle based on the first mileage data and the second mileage data.

[0063] For example, the cumulative mileage of electronic control units in fuel vehicles includes the cumulative mileage of the engine electronic control unit, the cumulative mileage of the transmission electronic control unit, and the cumulative mileage of other electronic control units. The effective driving mileage data of new energy vehicles includes the cumulative mileage of multiple electronic control units, such as the cumulative driving mileage of VCU (Vehicle Control Unit), MCU (Motor Control Unit), ABS, etc.

[0064] In one embodiment, when the vehicle is a gasoline-powered vehicle, a first deviation is determined between the cumulative mileage of the engine electronic control unit and the cumulative mileage of the transmission electronic control unit and the cumulative mileage of the other electronic control units; the cumulative mileage corresponding to the smallest first deviation is selected as the second mileage data. When the vehicle is a new energy vehicle, the average value of the cumulative mileage of each electronic control unit is calculated, and a second deviation is determined between the cumulative mileage of each electronic control unit and the average value; the cumulative mileage corresponding to the smallest second deviation is selected as the second mileage data.

[0065] For example, the cumulative mileage of the engine control unit (ECU) is the cumulative distance traveled by the vehicle calculated and persistently stored by the engine control unit; the cumulative mileage of the transmission control unit (TCU) is the mileage value independently calculated and stored by the transmission controller; and the cumulative mileage of the other electronic control units (ECUs) is the mileage data recorded by the ECUs other than the engine control unit and the transmission controller. This first deviation includes, but is not limited to, absolute difference, standard deviation, etc., and the mileage of the ECU corresponding to the smallest deviation or the mileage of the transmission control unit can be selected as the second mileage data with higher reliability.

[0066] The VCU cumulative mileage is the vehicle's cumulative mileage calculated and persistently stored by the vehicle controller, while the MCU cumulative mileage is the vehicle's cumulative mileage calculated and persistently stored by the motor controller. This second deviation includes, but is not limited to, absolute difference, standard deviation, etc. The cumulative mileage of the electronic control unit corresponding to the smallest deviation can be selected as the more reliable second mileage data.

[0067] For example, effective mileage data includes cumulative mileage from the electronic control unit and cumulative mileage from the battery management system, where the cumulative mileage from the battery management system is the cumulative value of the driving distance calculated by the vehicle's BMS.

[0068] In one embodiment, such as Figure 2 As shown, the calculation process for dual-anchor point mileage data is as follows: S141, when the vehicle is a new energy vehicle, calculate the deviation between the first driving mileage data and the cumulative mileage of the battery management system and the cumulative mileage of the electronic control unit to obtain the mileage deviation.

[0069] In this embodiment, the first driving mileage data output by the model is compared with the collected cumulative mileage of the battery management system and the cumulative mileage of the electronic control unit to calculate the mileage deviation. The formula for calculating the mileage deviation is as follows: ; In the formula, Indicates mileage deviation. Indicates the cumulative mileage of the battery management system. This represents the cumulative mileage of the electronic control unit, which can be taken as the average of the cumulative mileage of each electronic control unit.

[0070] S142, determine the first weighting coefficient of the first mileage data and the second weighting coefficient of the second mileage data based on the mileage deviation.

[0071] As an example, the initial mileage data, as the corrected cumulative mileage of the battery management system, participates in the subsequent weighted fusion calculation of dual-anchor mileage data to ensure the accuracy of the mileage data. Based on the mileage deviation, the first weighting coefficient for the weighted fusion calculation is adjusted, thereby adjusting the weight ratio of the first and second mileage data. A larger mileage deviation corresponds to a larger first weighting coefficient, and a smaller first weighting coefficient corresponds to a smaller first weighting coefficient. The sum of the first and second weighting coefficients is 1.

[0072] S143, when the vehicle is a new energy vehicle or a fuel vehicle, the first mileage data and the second mileage data are weighted and summed based on the first weighting coefficient and the second weighting coefficient to obtain dual-anchor mileage data, wherein the first weighting coefficient is greater than the second weighting coefficient.

[0073] In this embodiment, the formula for calculating the dual-anchor point mileage data is as follows: ; In the formula, This indicates the mileage data at two anchor points. This represents the first mileage data, assuming the vehicle is a new energy vehicle. When the vehicle is a gasoline-powered vehicle, , Indicates the first weighting coefficient. This indicates the second mileage data. This represents the second weighting coefficient.

[0074] S150 calculates the vehicle's actual mileage data based on dual-anchor point mileage data and effective mileage data.

[0075] In one embodiment, such as Figure 3 As shown, the calculation of actual mileage data includes the following steps: S151, calculate the mean of the effective mileage data to obtain the average mileage of the vehicle.

[0076] In this embodiment, the average mileage is a comprehensive verification of the cumulative mileage of all electronic control units. It is used to help correct minor deviations in the mileage data of the two anchor points. The core is to merge the cumulative mileage of all electronic control units to reduce the error caused by the failure of the cumulative mileage of a single electronic control unit.

[0077] In one embodiment, for gasoline-powered vehicles, the average mileage is calculated by taking the average cumulative mileage of all electronic control units (ECUs). For new energy vehicles, the average mileage is calculated by taking the average cumulative mileage of all ECUs and the average cumulative mileage of the battery management system (BMS). For example, for a gasoline-powered vehicle, if the cumulative mileage of the TCU is 100,000 km, the cumulative mileage of the ECM is 100,200 km, the cumulative mileage of the ABS is 99,900 km, and the cumulative mileage of the BCM is 100,100 km, then the corresponding average mileage is: (100,000 + 100,200 + 99,900 + 100,100) ÷ 4 = 100,050 km.

[0078] S152, perform linear fitting on the effective mileage data to determine the fitted mileage data of the vehicle at the current time.

[0079] As an example, the fitted mileage data is based on historical mileage data (traffic management annual inspection, 4S maintenance, insurance claims, etc.). After preprocessing, a reasonable mileage reference value is obtained through a fitting algorithm to make up for the deviation of the first two sub-items and ensure the rationality of the mileage data.

[0080] In one embodiment, using the time-mileage trend curve corresponding to historical mileage data, with time as the x-axis and mileage as the y-axis, a trend line of mileage changing over time is plotted using linear fitting. The slope of this trend line is calculated, thus obtaining the fitted mileage data corresponding to the current time through linear fitting. In this embodiment, when there are slight deviations in the dual-anchor mileage data and the average mileage, the fitted mileage data is used for fallback calibration to ensure the reasonableness of the final mileage.

[0081] S153, based on the confidence levels of the dual-anchor-point mileage data, the mean mileage, and the fitted mileage data, determine the third weighting coefficient of the dual-anchor-point mileage data, the fourth weighting coefficient of the mean mileage, and the fifth weighting coefficient of the fitted mileage data.

[0082] S154. The actual mileage data is obtained by weighting and summing the dual-anchor point mileage data, the mean mileage, and the fitted mileage data based on the third, fourth, and fifth weighting coefficients; wherein the third weighting coefficient is greater than the fourth weighting coefficient, and the fourth weighting coefficient is greater than the fifth weighting coefficient.

[0083] In this embodiment, dual-anchor point mileage data serves as the core data source. This data is tamper-proof, highly continuous, and has minimal error after initial correction, making it the most reliable and reflecting the vehicle's true mileage. Therefore, it is given the highest weight to ensure the core accuracy of the fusion result. For example, the third weighting coefficient for this dual-anchor point mileage data is 0.85. The average mileage serves as an auxiliary data source. While the cumulative mileage of the electronic control unit (ECU) is generally reliable, individual ECUs may have malfunctions or be subject to minor tampering risks. Fusion reduces the error of individual modules and corrects minor deviations in the dual-anchor point data. Therefore, it is given a lower weight to assist in verification. For example, the fourth weighting coefficient for this average mileage data is 0.10. Fitted mileage data serves as a fallback data source. Historical mileage data is affected by external recording accuracy, such as maintenance record entry errors, resulting in slightly lower accuracy than the first two items. It is mainly used for fallback calibration to avoid mileage deviations caused by simultaneous anomalies in the first two items. Therefore, it is given the lowest weight. For example, the fifth weighting coefficient for this fitted mileage data is 0.05. Under this weighting factor setting, the error between the fused actual mileage data and the vehicle's actual mileage is small, meeting the patent detection accuracy requirements, and is compatible with all vehicle models, making it highly versatile.

[0084] The exemplary formula for calculating actual mileage data is as follows: ; In the formula, This represents the actual mileage data. This represents the third weighting coefficient. This represents the average mileage traveled. This represents the fourth weighting coefficient. This indicates the fitted driving mileage data. This represents the fifth weighting coefficient.

[0085] Optionally, the driving habit mileage of the vehicle can be estimated based on the user's driving habits. This driving habit mileage serves as an auxiliary calculation parameter, with its corresponding sixth weighting coefficient being relatively small, lower than the fifth weighting coefficient. The sum of the third, fourth, fifth, and sixth weighting coefficients is 1. Therefore, based on the third, fourth, fifth, and sixth weighting coefficients, the dual-anchor point mileage data, the mean mileage, the fitted mileage data, and the driving habit mileage are weighted and summed to obtain the vehicle's actual mileage data.

[0086] For example, in one embodiment, taking a lithium iron phosphate new energy vehicle as an example, the application process of this formula is explained. The known data for each component are: the first mileage is 95,441 km, the second mileage is 95,200 km, and the corresponding dual-anchor mileage is: 95,441 × 0.6 + 95,200 × 0.4 = 57,264.6 + 38,080 = 95,344.6 km; the cumulative mileage of VCU is 95,300 km, the cumulative mileage of MCU is 95,250 km, the cumulative mileage of ABS is 95,320 km, and the cumulative mileage of BMS is 95,280 km. The average mileage is: (95,300 + 95,250 + 95,320 + 95,280) ÷ 4 = 95,287.5 km; the fitted mileage is 95,300 km. Substituting the actual mileage data into the calculation formula, the actual mileage is calculated as follows: 95344.6×0.85+95287.5×0.10+95300×0.05=81042.91+9528.75+4765=95336.66 kilometers. After verification, the actual mileage of the vehicle is 95350 kilometers, and the error between the actual mileage data and the vehicle's actual mileage is approximately 0.014%, indicating high accuracy of the actual mileage data.

[0087] In one embodiment, the deviation between the actual mileage data and the vehicle's real-time displayed mileage is calculated, and the real-time displayed mileage is corrected based on the deviation to obtain the corrected displayed mileage. In this embodiment, the formula for calculating the deviation is: ; In the formula, Indicates the deviation value. This indicates the real-time mileage displayed on the meter.

[0088] In one embodiment, when the deviation value is less than a first preset deviation, no correction is made to the real-time displayed mileage; when the deviation value is greater than or equal to the first preset deviation and less than or equal to a second preset deviation, the dual-anchor point mileage data is used as the corrected displayed mileage; when the deviation value is greater than the second preset deviation, the actual mileage data is used as the corrected displayed mileage. The first preset deviation is less than the second preset deviation.

[0089] For example, the first preset deviation is the dividing point between normal error and minor caliper adjustment; exceeding the first preset deviation can be judged as minor caliper adjustment. The second preset deviation is the dividing point between minor caliper adjustment and major caliper adjustment. The first and second preset deviations can be set according to actual conditions or industry experience; for example, the first preset deviation can be set to 8%, and the second preset deviation can be set to 25%.

[0090] In this embodiment, the vehicle's instrument panel itself has an inherent display error of ±3% to ±5% (such as instrument accuracy, mechanical / electronic display deviation). The reasonable error range between the superimposed real-time mileage display and the actual mileage data is less than a first preset deviation. Therefore, the first preset deviation is set as the threshold for slight odometer tampering to avoid misjudging normal errors as odometer tampering. Thus, when the deviation value is less than the first preset deviation, the displayed mileage is basically consistent with the highly reliable actual mileage data, indicating that the instrument data has not been tampered with, or only has a normal display deviation, which is consistent with the mileage characteristics of vehicles that have not had their odometers tampered by the original manufacturer. This approach can balance detection accuracy and user readability while reducing the complexity of the detection process (without needing to discard additional instrument data), and is suitable for most common detection scenarios where the original odometer has not been tampered with.

[0091] When the deviation value is greater than or equal to the first preset deviation and less than or equal to the second preset deviation, the deviation in the real-time mileage displayed on the vehicle's instrument panel is mostly due to minor manipulation of the instrument data (such as slightly lowering the displayed mileage to increase the resale value of a used car). This type of odometer adjustment only modifies the surface data of the instrument panel and cannot tamper with the underlying fixed data of the ECU and BMS (the underlying data is stored in an encrypted chip, which is difficult and costly to tamper with). Therefore, the dual-anchor point mileage data remains accurate. At this time, the dual-anchor point mileage data can be used as a correction for the displayed mileage through slight odometer adjustment. That is, the dual-anchor point mileage data is unalterable and highly reliable. Using it as the standard can offset the deviation caused by slight odometer adjustment and avoid mileage gaps caused by discarding the real-time mileage displayed on the vehicle's instrument panel.

[0092] If the deviation value exceeds the second preset deviation, the vehicle is identified as having undergone deep odometer tampering. The real-time odometer reading is completely discarded (as the data has been severely altered and is of no reference value), and the actual mileage is used to correct the displayed mileage. Deep odometer tampering involves significant alteration of instrument data (e.g., alteration exceeding 25%, often seen in used cars where odometer tampering is used to conceal high mileage and increase selling price). This type of tampering is intentional and deceptive; the instrument data deviates completely from the true mileage and has no reference value. Dual-anchor mileage data and the second mileage data are highly reliable. The fitted mileage data has temporal continuity, and the actual mileage data can accurately restore the vehicle's true mileage, completely replacing the severely altered instrument data. Completely discarding instrument data avoids detection errors caused by relying on false data (such as used car transaction disputes and vehicle condition assessment deviations).

[0093] For example, in one implementation, taking a certain new energy vehicle as an example, the calculated actual mileage is 95336.66 kilometers. Combined with the real-time mileage displayed on the vehicle's instrument panel, the classification process is as follows: Example 1 (no odometer adjustment), the real-time mileage is 94800 kilometers, and the deviation value is: |94800-95336.66|÷95336.66×100%≈0.56%<8%, which is judged to be original factory odometer adjustment, and the displayed mileage of 94800 kilometers is accepted.

[0094] Example 2 (minor odometer tampering): The displayed mileage is 78,000 kilometers, and the deviation is |78,000-95,336.66|÷95,336.66×100%≈18.29% (8%≤18.29%≤25%). It is judged as minor odometer tampering, and the mileage data of 95,344.6 kilometers at the dual anchor points shall be used as the standard.

[0095] Example 3 (Deep Odometer Tampering): The odometer reading is 65,000 kilometers, and the deviation is |65,000-95,336.66|÷95,336.66×100%≈31.82%>25%. This is determined to be deep malicious odometer tampering. The instrument data is discarded, and only the actual mileage data of 95,336.66 kilometers is used as the standard.

[0096] In this embodiment, the smaller the deviation value, the higher the reliability of the instrument data; conversely, the larger the deviation value, the higher the probability of instrument data tampering and the lower the reliability. This allows the detection terminal to automatically calculate the deviation value and complete the classification judgment without manual intervention, making it suitable for rapid on-site detection scenarios.

[0097] Figure 4 A schematic diagram of a vehicle mileage estimation system 200 according to an embodiment of this application is shown. Exemplarily, the vehicle mileage estimation system 200 includes: The data acquisition module 210 is used to acquire real-time battery parameters, real-time driving condition coefficients and mileage data of the vehicle when the vehicle is a new energy vehicle, and to acquire mileage data of the vehicle when the vehicle is a fuel vehicle.

[0098] The data processing module 220 is used to preprocess the mileage data to obtain valid mileage data.

[0099] In one embodiment, the data processing module 220 is further configured to identify invalid mileage data in the mileage data, delete the invalid mileage data, and obtain valid mileage data. The mileage mapping module 230 is configured to input real-time battery parameters and real-time driving condition coefficients into the mileage mapping model to obtain first mileage data when the vehicle is a new energy vehicle, and to calculate the weighted value of each valid mileage data when the vehicle is a fuel vehicle to obtain the first mileage data.

[0100] In one embodiment, the real-time battery parameters include battery type, battery health status, total battery cycle count, temperature deviation coefficient, and battery fast charging frequency. The mileage mapping module 230 is further used to determine the mapping relationship between battery parameters corresponding to battery type and battery health status and mileage through a mileage mapping model; and to obtain the first mileage data by substituting the battery health status, total battery cycle count, temperature deviation coefficient, battery fast charging frequency, and real-time driving condition coefficient into the mapping relationship between battery parameters and mileage.

[0101] In one embodiment, the effective mileage data includes the cumulative mileage of multiple electronic control units of the vehicle. The mileage mapping module 230 is further used to determine the weighting coefficient of the cumulative mileage of each electronic control unit based on the confidence level of the cumulative mileage of each electronic control unit; and to perform a weighted summation of the cumulative mileage of each electronic control unit based on the weighting coefficient of the cumulative mileage of each electronic control unit to obtain the first mileage data.

[0102] The dual-anchor mileage determination module 240 is used to determine second mileage data based on the deviation between effective mileage data, and to determine the vehicle's dual-anchor mileage data based on the first mileage data and the second mileage data.

[0103] In one embodiment, the effective mileage data includes the cumulative mileage of the engine electronic control unit, the cumulative mileage of the transmission electronic control unit, and the cumulative mileage of the other electronic control units. The dual-anchor mileage determination module 240 is also used to determine the deviations between the cumulative mileage of the engine electronic control unit and the cumulative mileage of the transmission electronic control unit and the cumulative mileage of the other electronic control units, respectively; and select the cumulative mileage corresponding to the smallest deviation as the second mileage data.

[0104] In one embodiment, the effective mileage data of a fuel-powered vehicle includes the cumulative mileage of the engine electronic control unit, the cumulative mileage of the transmission electronic control unit, and the cumulative mileage of other electronic control units. The effective mileage data of a new energy vehicle includes the cumulative mileage of multiple electronic control units. The dual-anchor mileage determination module 240 is further configured to, when the vehicle is a fuel-powered vehicle, determine the first deviation between the cumulative mileage of the engine electronic control unit and the cumulative mileage of the transmission electronic control unit and the cumulative mileage of the other electronic control units; select the cumulative mileage corresponding to the smallest first deviation as the second mileage data; when the vehicle is a new energy vehicle, calculate the average value of the cumulative mileage of each electronic control unit, determine the second deviation between the cumulative mileage of each electronic control unit and the average value; and select the cumulative mileage corresponding to the smallest second deviation as the second mileage data.

[0105] The actual mileage determination module 250 is used to calculate the actual mileage data of the vehicle based on the dual-anchor point mileage data and the effective mileage data.

[0106] In one embodiment, the actual mileage determination module 250 is further configured to calculate the mean among the effective mileage data to obtain the vehicle's average mileage; perform linear fitting on the effective mileage data to determine the vehicle's fitted mileage data at the current time; determine the third weighting coefficient of the dual-anchor mileage data, the fourth weighting coefficient of the average mileage, and the fifth weighting coefficient of the fitted mileage data based on the confidence levels of the dual-anchor mileage data, the average mileage, and the fitted mileage data; and perform a weighted summation of the dual-anchor mileage data, the average mileage, and the fitted mileage data based on the third, fourth, and fifth weighting coefficients to obtain the actual mileage data; wherein the third weighting coefficient is greater than the fourth weighting coefficient, and the fourth weighting coefficient is greater than the fifth weighting coefficient.

[0107] In one embodiment, such as Figure 5 As shown, the vehicle mileage calculation system 200 also includes a display mileage correction module 260, which is used to calculate the deviation between the actual mileage data and the real-time display mileage of the vehicle, and correct the real-time display mileage according to the deviation to obtain the corrected display mileage.

[0108] It is understood that the system in this embodiment corresponds to the vehicle mileage calculation method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0109] This application also provides a detection terminal, which, by way of example, includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the detection terminal to perform the functions of the various modules in the above-described vehicle mileage estimation method or the above-described vehicle mileage estimation system.

[0110] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0111] Memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM). Memory is used to store computer programs, and the processor can execute these programs upon receiving execution instructions.

[0112] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned detection terminal. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0114] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0115] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.

[0116] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for estimating vehicle mileage, characterized in that, include: When the vehicle is a new energy vehicle, the real-time battery parameters, real-time driving condition coefficients and driving mileage data of the vehicle are obtained; when the vehicle is a fuel vehicle, the driving mileage data of the vehicle is obtained. The driving mileage data is preprocessed to obtain valid driving mileage data; When the vehicle is a new energy vehicle, the real-time battery parameters and the real-time driving condition coefficient are input into the driving mileage mapping model to obtain the first driving mileage data. When the vehicle is a fuel vehicle, the weighted value of each of the effective driving mileage data is calculated to obtain the first driving mileage data. The second mileage data is determined based on the deviation between the effective mileage data, and the dual-anchor point mileage data of the vehicle is determined based on the first mileage data and the second mileage data. The actual mileage of the vehicle is calculated based on the dual-anchor point mileage data and the effective mileage data.

2. The vehicle mileage calculation method according to claim 1, characterized in that, The step of preprocessing the mileage data to obtain valid mileage data includes: Identify invalid mileage data in the driving mileage data, delete the invalid mileage data, and obtain the valid driving mileage data. The invalid mileage data includes one or more of the following: abnormal mileage data, abnormal data with a cliff-like increase in speed, and abnormal data with logical contradictions.

3. The vehicle mileage calculation method according to claim 1, characterized in that, The real-time battery parameters include battery type, battery health status, total battery cycle count, temperature deviation coefficient, and battery fast charging frequency. The process of inputting the real-time battery parameters and the real-time driving condition coefficient into the mileage mapping model to obtain first mileage data includes: The mileage mapping model is used to determine the mapping relationship between the battery parameters corresponding to the battery type and the battery health status and the mileage. Substituting the battery health status, the total number of battery cycles, the temperature deviation coefficient, the battery fast charging frequency, and the real-time driving condition coefficient into the mapping relationship between battery parameters and driving mileage, the first driving mileage data is obtained.

4. The vehicle mileage calculation method according to claim 1, characterized in that, The effective mileage data includes the cumulative mileage of multiple electronic control units of the vehicle. The calculation of the weighted value of each of the effective mileage data points to obtain the first mileage data includes: The weighting coefficient for the cumulative mileage of each electronic control unit is determined based on the confidence level of the cumulative mileage of each electronic control unit; The cumulative mileage of each electronic control unit is weighted and summed based on the weighting coefficient of the cumulative mileage of each electronic control unit to obtain the first driving mileage data.

5. The vehicle mileage calculation method according to claim 1, characterized in that, The effective mileage data for the fuel-powered vehicle includes the cumulative mileage of the engine electronic control unit, the cumulative mileage of the transmission electronic control unit, and the cumulative mileage of other electronic control units. The effective mileage data for the new energy vehicle includes the cumulative mileage of multiple electronic control units. Determining the second mileage data based on the deviation between the effective mileage data includes: In the case that the vehicle is a gasoline vehicle, a first deviation is determined between the cumulative mileage of the engine electronic control unit and the cumulative mileage of the transmission electronic control unit and the cumulative mileage of the other electronic control units, respectively. The cumulative mileage corresponding to the smallest first deviation is selected as the second driving mileage data; When the vehicle is a new energy vehicle, the average cumulative mileage of each electronic control unit is calculated, and a second deviation between the cumulative mileage of each electronic control unit and the average value is determined; The cumulative mileage corresponding to the smallest second deviation is selected as the second driving mileage data.

6. The vehicle mileage calculation method according to claim 1, characterized in that, The effective mileage data includes the cumulative mileage of the electronic control unit and the cumulative mileage of the battery management system. Determining the dual-anchorage mileage data of the vehicle based on the first mileage data and the second mileage data includes: When the vehicle is a new energy vehicle, the deviation between the first driving mileage data and the cumulative mileage of the battery management system and the cumulative mileage of the electronic control unit is calculated to obtain the mileage deviation. Based on the mileage deviation, a first weighting coefficient for the first mileage data and a second weighting coefficient for the second mileage data are determined; When the vehicle is a new energy vehicle or a fuel vehicle, the first mileage data and the second mileage data are weighted and summed based on the first weighting coefficient and the second weighting coefficient to obtain dual-anchor mileage data, wherein the first weighting coefficient is greater than the second weighting coefficient.

7. The vehicle mileage calculation method according to claim 1, characterized in that, The calculation of the vehicle's actual mileage data based on the dual-anchor point mileage data and the effective mileage data includes: Calculate the mean of the effective mileage data to obtain the average mileage of the vehicle; Linear fitting is performed on the effective mileage data to determine the fitted mileage data of the vehicle at the current time; Based on the confidence levels of the dual-anchor point mileage data, the mean mileage, and the fitted mileage data, a third weighting coefficient for the dual-anchor point mileage data, a fourth weighting coefficient for the mean mileage, and a fifth weighting coefficient for the fitted mileage data are determined. The actual mileage data is obtained by weighting and summing the dual-anchor point mileage data, the mean mileage, and the fitted mileage data based on the third, fourth, and fifth weighting coefficients. The third weighting coefficient is greater than the fourth weighting coefficient, and the fourth weighting coefficient is greater than the fifth weighting coefficient.

8. The vehicle mileage calculation method according to claim 1, characterized in that, Also includes: Calculate the deviation between the actual mileage data and the real-time mileage displayed on the vehicle's odometer, and correct the real-time mileage displayed on the odometer based on the deviation to obtain the corrected mileage displayed on the odometer.

9. A vehicle mileage estimation system, characterized in that, include: The data acquisition module is used to acquire the real-time battery parameters, real-time driving condition coefficients and driving mileage data of the vehicle when the vehicle is a new energy vehicle, and to acquire the driving mileage data of the vehicle when the vehicle is a fuel vehicle. The data processing module is used to preprocess the mileage data to obtain valid mileage data; The mileage mapping module is used to input the real-time battery parameters and the real-time driving condition coefficient into the mileage mapping model when the vehicle is a new energy vehicle to obtain the first mileage data; when the vehicle is a fuel vehicle, it calculates the weighted value of each of the effective mileage data to obtain the first mileage data. The dual-anchor mileage determination module is used to determine second mileage data based on the deviation between the effective mileage data, and to determine the dual-anchor mileage data of the vehicle based on the first mileage data and the second mileage data. The actual mileage determination module is used to calculate the actual mileage data of the vehicle based on the dual-anchor point mileage data and the effective mileage data.

10. A detection terminal, characterized in that, The detection terminal includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the vehicle mileage estimation method according to any one of claims 1-8.

Images