A method and system for detecting mileage error in a pure electric vehicle instrument display

Abstract

This application provides a method and system for detecting mileage error in the instrument display of a pure electric vehicle, relating to the field of transportation technology. It enables the quantification and comparison of mileage error results under different vehicle models and operating conditions, forming a unified evaluation system for instrument display mileage. The method includes: testing the vehicle after determining the target test method based on the vehicle's test environment temperature and driving range; collecting test data consisting of first and second mileage data displayed on the vehicle's instrument panel, where the second mileage data includes mileage data from a rotating device. Specifically, when the target test method is a first or second shortening method, the second mileage data includes equivalent mileage data determined based on the discharge amount during the constant speed period and the average energy consumption during the cycle period; determining the overall error, segmental errors, and single-point errors based on the first and second mileage data, and evaluating the vehicle's instrument display error in conjunction with corresponding thresholds.

Description

Technical Field

[0001] This application relates to the field of transportation technology, and in particular to a method and system for detecting mileage error in the instrument display of a pure electric vehicle. Background Technology

[0002] Pure electric vehicles are vehicles powered by batteries. With the increasing global awareness of environmental protection and the development of new energy vehicle technology, pure electric vehicles are gradually becoming one of the mainstream vehicles in the automotive market.

[0003] However, compared to gasoline-powered vehicles, pure electric vehicles face more complex technical challenges in predicting driving range, especially in extreme weather conditions such as low and high temperatures. Battery performance is affected by temperature, and the use of air conditioning and other systems consumes battery power, all of which impact actual driving range. Under these conditions, the mileage displayed on the instrument panel of a pure electric vehicle often differs significantly from the actual distance traveled, especially when the battery is low and the displayed range is inflated. This not only causes driver anxiety but can also lead to safety hazards such as sudden vehicle stalling or being unable to continue driving due to insufficient battery power, severely hindering the widespread adoption of electric vehicles in cold regions. Furthermore, existing evaluation systems for instrument panel mileage display lack uniformity. Different testing institutions and different testing conditions can lead to incomparable test results, making it difficult to fairly and objectively assess the performance of different models in predicting driving range.

[0004] Therefore, there is an urgent need for an error detection method that allows for the quantification and comparison of mileage error results displayed on instrument panels under different vehicle models and operating conditions. Summary of the Invention

[0005] This application provides a method and system for detecting the mileage error of a pure electric vehicle instrument display, which enables the mileage error results of instrument displays under different vehicle models and operating conditions to be quantified and the data to be compared, forming a unified evaluation system for instrument display mileage.

[0006] Firstly, a method for detecting mileage display error in the instrument panel of a pure electric vehicle is provided, including:

[0007] The target test method is determined based on the vehicle's ambient temperature and driving range. Under normal ambient temperature conditions, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method, which involves continuous testing according to the CLTC-P cycle. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortened method, which involves testing according to a first test structure. The first test structure includes the following operating condition segments in sequence: a cyclic segment, a constant speed segment, and a cyclic segment. The test structure consists of two CLTC-P cycles in the first test structure, which includes a continuous operating condition test and a constant speed test. Under low temperature or high temperature test conditions, vehicles with a range of ≤8 CLTC-P cycles are tested using the continuous operating condition test method, while vehicles with a range of >8 CLTC-P cycles are tested using the second shortened test method. The second shortened test method is a test method conducted according to the second test structure. The operating condition sections of the second test structure are, in order, the cyclic section and the constant speed test. The cyclic section of the second test structure includes 6 CLTC-P cycles.

[0008] The vehicle is tested according to the target test method, and the test data of the vehicle is collected. The test data includes the first mileage data and the second mileage data displayed by the instrument. The second mileage data includes the mileage data of the rotating device. In the case that the target test method is the first shortening method or the second shortening method, the second mileage data also includes the equivalent mileage data determined based on the discharge amount of the constant speed section and the average power consumption of the cycle section.

[0009] The total error, segment errors, and single-point errors are determined based on the first mileage data and the second mileage data. The total error is statistically analyzed based on the sampling points throughout the entire test cycle. The segment errors are calculated based on the sampling points of the high-capacity segment, medium-capacity segment, or low-capacity segment divided by the battery state of charge interval. The single-point errors are calculated based on a single sampling point.

[0010] The instrument display error of the vehicle is evaluated based on the total error, total error threshold, segment error, segment error threshold, single-point error, and single-point error threshold.

[0011] In a feasible design, when the target testing method is either the first shortening method or the second shortening method, the steps for collecting equivalent mileage data include:

[0012] After excluding the acceleration and immersion processes in the constant speed section, the constant speed section is divided into multiple micro constant speed sections according to a preset time interval.

[0013] Determine the discharge quantity corresponding to each micro-constant velocity segment;

[0014] Determine the average power consumption of the corresponding cycle segment;

[0015] The micro-constant velocity range is determined based on the following formula. Equivalent mileage data :

[0016] ;

[0017] in, Indicates the micro-constant speed range Equivalent mileage data, Indicates the micro-constant speed range The discharge quantity, where i represents the number of the micro-constant velocity segment. This represents the average power consumption of the cycle segment, where the test method is the first shortening method. This represents the average power consumption of the 3rd and 4th CLTC-P cycles, under the second shortening method of testing. This represents the average power consumption of the 5th and 6th CLTC-P cycles.

[0018] In a feasible design, test data of the vehicle is collected, including:

[0019] Acquire the video recorded by the recording device on the instrument display screen during the test;

[0020] Extract mileage data from each instrument display on the video at a frequency of once per second;

[0021] The mileage data displayed by each instrument is sampled according to the first sampling rule to obtain the first mileage data. The first mileage data includes the mileage data corresponding to each sampling point. The first sampling rule is used to stipulate that the mileage data corresponding to the sampling point of the cycle segment is the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point. The sampling point of the cycle segment is the time between the end of the current cycle segment and the beginning of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point, and the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0022] In one feasible design, the mileage data displayed on each instrument is extracted from the video at a frequency of once per second, including:

[0023] Video is captured at a frequency of 5 frames per second to form an image data sequence;

[0024] For the mileage number region in each frame of the image data sequence, a pre-trained digit recognition model is used to independently identify it, and output 5 sets of results per second containing the specific digit and the corresponding confidence level.

[0025] Based on the highest confidence level selection mechanism, the number with the highest confidence level is selected from the 5 sets of results corresponding to each second as the mileage data displayed on the instrument for that second.

[0026] In a feasible design, the process of identifying the mileage digit region in each frame of image includes the following steps:

[0027] If the current frame image is the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the initial frame are determined by the target detection algorithm, and the offsets of the four vertices of the mileage number region in the initial frame relative to the preset screen boundary are recorded as four reference parameters.

[0028] If the current frame is not the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the current frame are determined by calculating the image translation based on phase correlation tracking technology. The similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated. If all similarities are higher than the similarity threshold, the mileage number region of the next frame is identified until the mileage number region of each frame in the image data sequence is identified. If there is a similarity below the similarity threshold, the coordinates of the four vertices of the mileage number region in the current frame are determined again based on phase correlation tracking technology, and the similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated again, until all similarities in the current frame are higher than the similarity threshold.

[0029] In a feasible design, test data of the vehicle is collected, including:

[0030] The cumulative mileage of the vehicle is recorded in real time by a rotating device, generating a cumulative value every second to obtain a cumulative value sequence;

[0031] The cumulative value sequence is sampled according to the second sampling rule to obtain the mileage data of the hub device. The second sampling rule is used to specify that the mileage data corresponding to the sampling point of the cycle segment is the difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point. The sampling point of the cycle segment is the time after the end of the current cycle segment and before the start of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point. The difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0032] In a feasible design, the total error includes the total mean absolute error and the total root mean square error. The total error is determined based on the first mileage data and the second mileage data, including:

[0033] Acquire the instrument display mileage data from each valid sampling point in the first mileage data, excluding the zero point and the initial point;

[0034] Obtain the measured mileage data of each valid sampling point in the second mileage data. Wherein, when the target test method is the continuous working condition method, the measured mileage data is the mileage data of the hub equipment. When the target test method is the first shortening method or the second shortening method, the measured mileage data is the equivalent mileage data.

[0035] The mean absolute error over the entire process is determined using the following formula:

[0036] ;

[0037] in, This represents the average absolute error over the entire process. Indicates the number of the valid sampling point. This indicates the number of valid sampling points throughout the entire testing period. Indicates valid sampling points The instrument panel displays mileage data. Indicates valid sampling points Actual mileage data;

[0038] The root mean square error throughout the entire process is determined using the following formula:

[0039] ;

[0040] in, This represents the root mean square error over the entire process.

[0041] In a feasible design, the segmentation error includes the segmented mean absolute error and the segmented root mean square error. Determining the segmentation error of the high-battery segment based on the first mileage data and the second mileage data includes the following steps:

[0042] The segmented average absolute error of the high-capacity range is determined using the following formula:

[0043] ;

[0044] in, This represents the segmented average absolute error of the high-charge segment. This indicates the number of the first valid sampling point in the high-charge segment. This indicates the number of the last valid sampling point in the high-charge range;

[0045] The piecewise root mean square error of the high-electricity segment is determined according to the following formula;

[0046] ;

[0047] in, This represents the piecewise root mean square error of the high-charge segment.

[0048] In a feasible design, determining the individual point errors based on the first mileage data and the second mileage data includes the following steps:

[0049] The absolute value of the difference between the instrument display mileage at each valid sampling point in the first mileage data and the measured mileage data at the corresponding valid sampling point in the second mileage data is determined as the single-point error of the corresponding valid sampling point.

[0050] Secondly, a pure electric vehicle instrument display mileage error detection system is provided, including:

[0051] The test method determination module is used to determine the target test method based on the vehicle's test environment temperature and driving range. Specifically, under normal test environment temperature, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method, which involves continuous testing according to CLTC-P cycles. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortened method, which involves testing according to a first test structure. The first test structure includes the following operating condition segments in sequence: a cycle segment, a constant operating condition segment, and a constant operating condition segment. The test structure consists of three sections: speed range, cycle range, and constant speed range. The cycle range of the first test structure includes two CLTC-P cycles. Under low-temperature or high-temperature test environments, vehicles with a range of ≤8 CLTC-P cycles are tested using the continuous operating condition method. Vehicles with a range of >8 CLTC-P cycles are tested using the second shortened method. The second shortened method is a test method conducted according to the second test structure. The operating condition sections of the second test structure are, in order, the cycle range and the constant speed range. The cycle range of the second test structure includes six CLTC-P cycles.

[0052] The test module is used to test the vehicle according to the target test method and collect the test data of the vehicle. The test data includes the first mileage data and the second mileage data displayed by the instrument. The second mileage data includes the mileage data of the rotating device. In the case that the target test method is the first shortening method or the second shortening method, the second mileage data also includes the equivalent mileage data determined based on the discharge amount of the constant speed section and the average power consumption of the cycle section.

[0053] The error calculation module is used to determine the total error, segment errors and single-point errors based on the first mileage data and the second mileage data. The total error is calculated based on the sampling points within the entire test cycle. The segment errors are calculated based on the sampling points of the high-capacity segment, medium-capacity segment or low-capacity segment divided by the battery state of charge interval. The single-point error is calculated based on a single sampling point.

[0054] The evaluation module is used to evaluate the instrument display error of the vehicle based on the overall error, the overall error threshold, the errors of each segment, the segment error threshold, the errors of each single point, and the single point error threshold.

[0055] This application first establishes a comprehensive and unified testing framework by precisely determining the target testing method based on the vehicle's test environment temperature and driving range. This framework ensures that suitable testing methods can be found for vehicles operating in normal, low, or high temperature environments, and for vehicles with long or short driving ranges. This innovative approach provides a standardized operating procedure and data collection foundation for subsequent error detection, ensuring the comparability of test data across different vehicle models and operating conditions from the outset, and building a solid framework for solving technical problems. Specifically, for vehicles with a driving range ≤ 8 CLTC-P cycles under normal temperature test conditions, the continuous driving cycle method is used. This testing method closely matches the actual driving conditions of the vehicle, comprehensively reflecting its range performance in common driving scenarios such as urban roads. Because the testing time for short-range vehicles is relatively short, the continuous driving cycle method can fully capture the energy consumption and mileage display characteristics of the vehicle at different driving stages, ensuring the comprehensiveness and accuracy of error detection. For vehicles with a range greater than 8 CLTC-P cycles, the first shortened method is used. Its test structure includes a sequential cycle segment, a constant speed segment, another cycle segment, and another constant speed segment. This design considers both the long driving range and the simulation of high-speed driving scenarios through the constant speed segment. This test structure effectively shortens the test time while ensuring the representativeness of the test results, balancing the testing efficiency and accuracy of long-range vehicles. In low-temperature or high-temperature testing environments, vehicles with a range ≤ 8 CLTC-P cycles also use the continuous operating condition method. This is because, under extreme temperature conditions, the vehicle's energy consumption and range performance are significantly affected, and the continuous operating condition method can fully expose the vehicle's performance under these special conditions. For vehicles with a range greater than 8 CLTC-P cycles, the second shortened method is used, with a test structure consisting of a cycle segment followed by a constant speed segment. This design considers both the testing efficiency of long-range vehicles under extreme temperatures and the simulation of energy consumption during high-speed or stable driving through the constant speed segment, ensuring the reliability of the test results.

[0056] Secondly, when testing vehicles and collecting test data according to the target test method, if the target test method is the first shortening method or the second shortening method, the collected second mileage data not only includes the mileage data of the rotating device, but also innovatively introduces equivalent mileage data determined based on the discharge amount in the constant speed section and the average power consumption in the cyclic section. This improvement effectively solves the problem of large deviation in the total mileage of the rotating device due to high-speed discharge in the shortening method test, making the measured mileage data more accurate and objectively reflect the actual driving conditions of the vehicle. The introduction of equivalent mileage data not only enriches the dimensions of the test data, but also enhances the scientific nature and comparability of the data, further improving the accuracy of vehicle performance evaluation under different operating conditions, providing more reliable data support for subsequent error calculation, and significantly improving the accuracy and reliability of error detection.

[0057] Finally, through comprehensive analysis and calculation of the collected first and second mileage data, the overall error, segmental errors, and individual point errors were determined. The overall error reflects the overall deviation trend, the segmental errors precisely pinpoint the error characteristics of different battery charge segments, and the individual point errors refine the display accuracy at each sampling moment. This multi-dimensional error quantification method makes the error results more detailed and comparable. Simultaneously, by comparing with preset error thresholds, a precise assessment of the vehicle's instrument display error was achieved, providing a strong basis for improving the accuracy of pure electric vehicle instrument display mileage and evaluating the performance of different models. This comprehensive and detailed error assessment system not only accurately identifies the mileage display errors of different models under various operating conditions but also provides precise data support for subsequent vehicle improvements and optimizations. This makes the displayed range error under different models and operating conditions detectable, quantifiable, and comparable, unifying the evaluation system for instrument display mileage error. Attached Figure Description

[0058] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic flowchart of an exemplary embodiment of a pure electric vehicle instrument display mileage error detection method provided in this application;

[0060] Figure 2 This is a schematic flowchart illustrating yet another example of a pure electric vehicle instrument display mileage error detection method provided in an exemplary embodiment of this application;

[0061] Figure 3 This is a schematic diagram of an exemplary embodiment of a pure electric vehicle instrument display mileage error detection system provided in this application. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] To address the lack of uniformity in existing evaluation systems for instrument-displayed mileage, this application provides a method and device for detecting mileage display errors in pure electric vehicles. The method establishes corresponding test matrices based on multiple temperature scenarios and operating conditions, and establishes a graded error evaluation system of "full-range error + segmented error + single-point error," enabling the detection, quantification, and comparison of mileage display errors under different vehicle models and operating conditions, thereby achieving the goal of unifying the evaluation system for instrument-displayed mileage.

[0064] Figure 1 This is a schematic flowchart illustrating an exemplary embodiment of a method for detecting mileage error in the instrument display of a pure electric vehicle, as provided in this application. Figure 1 As shown, it includes:

[0065] S110 determines the target test method based on the vehicle's ambient temperature and driving range.

[0066] Among them, under normal test ambient temperature, vehicles with a driving range ≤ 8 cycles of the China Light-duty Vehicle Test Cycle (Passenger Car, CLTC-P) are tested using the continuous driving cycle method. The continuous driving cycle method is a test method that continuously tests according to the CLTC-P cycle. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortened method. The first shortened method is a test method that tests according to the first test structure. The first test structure (also known as the first test matrix) includes the driving cycle segments as follows: Dynamic Segment (DS) and Constant Speed ​​Segment (DS). The test method for vehicles with a range of ≤8 CLTC-P cycles is the continuous operating condition method, and the test method for vehicles with a range of >8 CLTC-P cycles is the second shortened method. The second shortened method is a test method that is conducted according to the second test structure. The second test structure (also known as the second test matrix) includes the operating condition segments as follows: the continuous operating condition segment and the constant speed segment.

[0067] For example, the first and second loop segments of the first test structure each include two CLTC-P loops. The loop segment of the second test structure includes six CLTC-P loops.

[0068] For example, the operating speed of the constant speed section of the first test structure and the operating speed of the constant speed section of the second test structure are both set to a constant value of 100 (km) / h.

[0069] For example, the ambient temperature for the room temperature test is 23°C.

[0070] For example, the low-temperature test environment temperature is -7°C.

[0071] For example, the high-temperature test environment temperature is 30°C.

[0072] As can be seen, in the continuous operating condition method, the vehicle starts with a full charge and runs continuously at the operating speed specified by CLTC-P. If the vehicle fails to meet the specified operating speed requirement for 4 consecutive seconds, the test ends. In the first or second shortened method, the vehicle starts with a full charge and runs according to the specified test structure, the operating speed specified by CLTC-P, and the operating speed specified in the constant speed section. If the vehicle fails to meet the specified operating speed requirement for 4 consecutive seconds, the test ends.

[0073] S120 tests the vehicle according to the target test method and collects the vehicle's test data.

[0074] The test data includes first and second mileage data displayed on the instrument panel. The second mileage data includes mileage data from the rotating device. When the target test method is either the first or second shortening method, the second mileage data also includes equivalent mileage data determined based on the discharge amount during the constant speed period and the average energy consumption during the cyclic period. Average energy consumption is the average discharge amount consumed per kilometer by the vehicle during the cyclic, constant speed, or micro-constant speed periods, measured in watt-hours per kilometer.

[0075] In a feasible design, the first mileage data of the vehicle is collected in the following ways:

[0076] Acquire the video recorded by the recording device on the instrument display screen during the test;

[0077] Extract mileage data from each instrument display on the video at a frequency of once per second;

[0078] The mileage data displayed by each instrument is sampled according to the first sampling rule to obtain the first mileage data. The first mileage data includes the mileage data corresponding to each sampling point. The first sampling rule is used to stipulate that the mileage data corresponding to the sampling point of the cycle segment is the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point. The sampling point of the cycle segment is the time between the end of the current cycle segment and the beginning of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point, and the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0079] For example, when testing a vehicle using the first shortening method, the first CLTC-P cycle in the first cycle segment starts at second 1 and ends at second 200. The second CLTC-P cycle starts at second 202. Therefore, the sampling point corresponding to the first CLTC-P cycle is second 201, and the mileage data corresponding to this sampling point is the absolute value (10km) of the difference (-10km) between the mileage displayed on the instrument panel at second 201 (590km) and the mileage displayed on the instrument panel at second 0 (the moment before the start of the current cycle segment) (600km). Similarly, the second CLTC-P cycle ends at second 401, and the corresponding sampling point is second 402. The mileage data corresponding to this sampling point is the absolute value (12km) of the difference (-12km) between the mileage displayed on the instrument panel at second 402 (578km) and the mileage displayed on the instrument panel at second 201 (590km).

[0080] Therefore, the sampling point in this application can be understood as the sampling time.

[0081] For example, the recording device uses a high-definition camera with a resolution of 1920×1080 pixels and a frame rate of 60 frames per second.

[0082] For example, the recording device is equipped with a stabilization bracket, a heat dissipation module, and a data processing module.

[0083] The image stabilization bracket uses high-strength shock-absorbing material, and its extension length is adjustable. The heat dissipation module ensures the stability of the equipment during long-term operation. The data processing module analyzes the video recorded by the recording device to extract mileage data displayed on each instrument panel once per second. The recording device, image stabilization bracket, heat dissipation module, and data processing module together constitute the instrument display data acquisition device, which is part of the testing module.

[0084] The above example demonstrates how collecting vehicle test data enables precise monitoring and analysis of vehicle performance. First, video recordings of the instrument panel displays during the test are acquired. Second, by extracting mileage data from each instrument panel at a rate of once per second from the video, continuous and detailed vehicle mileage information is obtained. Then, the extracted mileage data from each instrument panel is sampled according to sampling rules. The mileage data corresponding to each sampling point constitutes the first mileage data, providing a reliable foundation for subsequent vehicle performance analysis and evaluation.

[0085] In a feasible design, the mileage data displayed on each instrument is extracted from the video at a frequency of once per second, as follows:

[0086] Video is captured at a frequency of 5 frames per second to form an image data sequence;

[0087] For the mileage number region in each frame of the image data sequence, a pre-trained digit recognition model is used to independently identify it, and output 5 sets of results per second containing the specific digit and the corresponding confidence level.

[0088] Based on the highest confidence level selection mechanism, the number with the highest confidence level is selected from the 5 sets of results corresponding to each second as the mileage data displayed on the instrument for that second.

[0089] For example, output is only confirmed when the number with the highest confidence level appears more than a preset threshold number of times in its corresponding 5 frames, which can effectively filter out instantaneous recognition errors. The threshold number can be set according to actual needs, and this application does not limit it.

[0090] This design samples video at a frequency of 5 frames per second to form an image data sequence, providing a sufficiently dense data foundation for subsequent digit recognition and ensuring data continuity and integrity. For the mileage digit region in each frame, a pre-trained digit recognition model is used for independent recognition, outputting 5 sets of results. This process introduces redundancy, effectively increasing the accuracy and reliability of recognition; even with errors in some results, correct data can still be obtained from multiple sets. Furthermore, a highest confidence filtering mechanism selects the digit with the highest confidence among the results corresponding to each sampling point as the final instrument display mileage data, directly filtering out low-quality and unreliable recognition results. This ensures that the extracted mileage data has high accuracy and reliability, effectively improving the overall quality and efficiency of extracting instrument display mileage data from video.

[0091] In a feasible design, to address the dynamic offset of digit regions in video, this application employs a precise positioning and tracking strategy to identify mileage digit regions in each frame of the image:

[0092] If the current frame image is the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the initial frame are determined by the target detection algorithm, and the offsets of the four vertices of the mileage number region in the initial frame relative to the preset screen boundary are recorded as four reference parameters.

[0093] If the current frame is not the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the current frame are determined by calculating the image translation based on phase correlation tracking technology. The similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated. If all similarities are higher than the similarity threshold, the mileage number region of the next frame is identified until the mileage number region of each frame in the image data sequence is identified. If there is a similarity below the similarity threshold, the coordinates of the four vertices of the mileage number region in the current frame are determined again based on phase correlation tracking technology, and the similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated again, until all similarities in the current frame are higher than the similarity threshold.

[0094] The similarity threshold can be set according to actual needs, and this application does not impose any restrictions on it.

[0095] The above example, by analyzing the phase spectrum information of adjacent frames, can maintain high tracking accuracy in scenes with changing illumination or slight blur, ensuring that the digital region remains within the recognition box. Simultaneously, the system continuously calculates the similarity between the current frame and the initial reference frame. When the similarity falls below a threshold, a relocalization mechanism is triggered to prevent tracking failure due to severe jitter.

[0096] For example, before recognizing the mileage digit regions in each frame of the image, the image is preprocessed using adaptive histogram equalization to enhance the contrast between the digits and the background. Illumination robustness features are also embedded into the digit recognition model to reduce the impact of brightness fluctuations on the recognition results and enhance adaptability to changes in lighting conditions. Furthermore, a multi-frame difference method is used to remove abnormal pixels in reflective areas of the image, and morphological operations are combined to repair the digit edges.

[0097] In a feasible design, the mileage data of the hub-and-spoke device is collected in the following ways:

[0098] The cumulative mileage of the vehicle is recorded in real time by a rotating device, generating a cumulative value every second to obtain a cumulative value sequence;

[0099] The cumulative value sequence is sampled according to the second sampling rule to obtain the mileage data of the hub device. The second sampling rule is used to specify that the mileage data corresponding to the sampling point of the cycle segment is the difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point. The sampling point of the cycle segment is the time after the end of the current cycle segment and before the start of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point. The difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0100] The above example achieves the acquisition of mileage data for the rotating hub by recording the vehicle's cumulative mileage in real time and generating a cumulative value every second, resulting in a continuous sequence of cumulative values. According to specific sampling rules, the cumulative value sequence is sampled to obtain the mileage data of the rotating hub. The sampling rules define the sampling points for the cyclic segment, where the mileage data at each sampling point is the difference between the current and previous cumulative values. Furthermore, for constant speed segments, the rules further specify dividing the segment into multiple micro-constant speed segments at preset time intervals, using the endpoints of these micro-constant speed segments as sampling points, and using the difference between the current and previous cumulative values ​​as the corresponding mileage data. This technical solution ensures accurate mileage data acquisition while optimizing the data processing process, improving data processing efficiency and accuracy.

[0101] Through the synergistic effect of the above technologies, the solution proposed in this application can stably and accurately extract dashboard mileage data in complex environments, providing reliable support for subsequent data analysis and applications.

[0102] In a feasible design, when the target testing method is either the first shortening method or the second shortening method, the steps for collecting equivalent mileage data include:

[0103] After excluding the acceleration and immersion processes in the constant speed section, the constant speed section is divided into multiple micro constant speed sections according to a preset time interval.

[0104] Determine the discharge quantity corresponding to each micro-constant velocity segment;

[0105] Determine the average power consumption of the corresponding cycle segment;

[0106] The micro-constant velocity segment is determined according to the following formula (1). Equivalent mileage data :

[0107] ;Formula (1);

[0108] in, Indicates the micro-constant speed range Equivalent mileage data (in kilometers). Indicates the micro-constant speed range Discharge amount (watt-hours). Indicates the number of the constant speed range. This represents the average power consumption of the cycle segment, where the test method is the first shortening method. This represents the average power consumption of the 3rd and 4th CLTC-P cycles, under the second shortening method of testing. This represents the average power consumption of the 5th and 6th CLTC-P cycles.

[0109] In this embodiment, by first eliminating acceleration and immersion sections from the constant speed segment under the first or second shortening method, and then subdividing it into several micro constant speed segments according to a fixed duration, and then using the average power consumption of the corresponding cycle segment as a benchmark, the discharge amount of each micro constant speed segment is converted into an equivalent mileage. This process can convert the driving mileage of the high power consumption condition (constant speed segment) into the equivalent mileage of the low power consumption condition (cycle segment) according to the power consumption ratio. This eliminates the significant deviation caused by the high-speed discharge of the shortening method, which results in the total mileage of the hub only reaching 70% to 80% of the battery's rated energy. This makes the final measured mileage data consistent and comparable with the mileage displayed on the instrument under a unified energy consumption benchmark, improving the accuracy and repeatability of the instrument display error detection for pure electric vehicles.

[0110] S130 determines the overall error, segment errors, and individual point errors based on the first mileage data and the second mileage data.

[0111] Among them, the full-process error is statistically calculated based on the sampling points throughout the entire test cycle, the segmented error is calculated based on the sampling points of the high charge segment (charge > 80%), medium charge segment (20% ≤ charge ≤ 80%), or low charge segment (charge < 20%) divided into battery charge state intervals, and the single-point error is calculated based on a single sampling point.

[0112] For example, based on the battery state of charge from high to low, this application divides all sampling points into 5 categories, where zero points and initial points are not included in error calculation. Zero points are sampling points where the instrument display shows 0 mileage, "-", or no mileage is displayed. Initial points are sampling points corresponding to the vehicle's displayed mileage before the test begins. The sampling points for the high-charge segment, low-charge segment, and medium-charge segment below do not include zero points and initial points.

[0113] The sampling points for the high-charge range refer to the sampling points corresponding to the end of the first two CLTC-P cycles during the test. For example, in the continuous operating condition test, the sampling points for the high-charge range include the sampling points corresponding to the end of the first CLTC-P cycle and the sampling points corresponding to the end of the second CLTC-P cycle.

[0114] During the first shortening method test, the sampling points in the low-charge segment include the sampling points corresponding to the end of the last two CLTC-P cycles, and all sampling points corresponding to the constant-speed segment after the end of the last CLTC-P cycle. During the continuous operating condition method and the second shortening method test, the sampling points in the low-charge segment include all sampling points where the battery state of charge (SOC) is below 20%.

[0115] The sampling points for the medium charge segment include all sampling points that are located in time between the last sampling point of the high charge segment and the first sampling point of the low charge segment.

[0116] In the example above, by dividing the sampling points into high-charge, low-charge, and medium-charge segments based on the battery's state of charge (SBC) from high to low, error calculations can be performed separately for each SBC segment. This method allows for a comprehensive evaluation of the accuracy of the electric vehicle's instrument panel display under different SBC states, thus providing users with more reliable mileage information.

[0117] In a feasible design, the total error includes the total mean absolute error and the total root mean square error, which is determined based on the first mileage data and the second mileage data in the following way:

[0118] Acquire the instrument display mileage data from each valid sampling point in the first mileage data, excluding the zero point and the initial point;

[0119] Obtain the measured mileage data of each valid sampling point in the second mileage data. Wherein, when the target test method is the continuous working condition method, the measured mileage data is the mileage data of the hub equipment. When the target test method is the first shortening method or the second shortening method, the measured mileage data is the equivalent mileage data.

[0120] The mean absolute error over the entire process is determined according to the following formula (2):

[0121] ;Formula (2);

[0122] in, This represents the average absolute error over the entire process. Indicates the number of the valid sampling point. This indicates the number of valid sampling points throughout the entire testing period. Indicates valid sampling points The instrument panel displays mileage data (in kilometers). Indicates valid sampling points Measured mileage data (in kilometers);

[0123] The root mean square error for the entire process is determined according to the following formula (3):

[0124] ;Formula (3);

[0125] in, This represents the root mean square error over the entire process.

[0126] This embodiment innovatively introduces a dual-indicator collaborative evaluation system of total mean absolute error and total root mean square error by precisely focusing on a refined calculation process for the entire range of errors. In the data preprocessing stage, zero-value points and initial points in the first mileage data are removed, accurately selecting the instrument display mileage data of valid sampling points, effectively avoiding interference from invalid data in error calculation. In determining the measured mileage data, conditional data selection is performed based on the target testing method, ensuring that the data used accurately matches the requirements of the entire range of error calculation. In the calculation of the total mean absolute error, the average absolute value of the difference between the instrument display mileage and the measured mileage at valid sampling points effectively characterizes the average deviation between the instrument display mileage and the measured mileage throughout the entire testing period; while the total root mean square error, calculated by the square root of the mean of squared errors, further amplifies the impact of large error points, making error assessment more sensitive. This dual-indicator system comprehensively quantifies errors from different dimensions, significantly improving the accuracy of the entire range of error assessment and enhancing the stability and reliability of the assessment results, providing solid data support for subsequent error determination.

[0127] In a feasible design, the segmentation error includes the segmented mean absolute error and the segmented root mean square error. Determining the segmentation error of the high-battery segment based on the first mileage data and the second mileage data includes the following steps:

[0128] The segmented average absolute error of the high-electricity range is determined according to the following formula (4):

[0129] ;Formula (4);

[0130] in, This represents the segmented average absolute error of the high-charge segment. This indicates the number of the first valid sampling point in the high-charge segment. This indicates the number of the last valid sampling point in the high-charge range;

[0131] The segmented root mean square error of the high charge segment is determined according to the following formula (5);

[0132] ;Formula (5);

[0133] in, This represents the piecewise root mean square error of the high-charge segment.

[0134] This embodiment achieves precise quantification of the mileage display error in the high-charge range by introducing a dual-index evaluation system of segmented average absolute error and segmented root mean square error, specifically targeting the segmented error calculation for high-charge range. This design not only clearly defines the start and end sampling point range of the high-charge range but also calculates the average absolute error and root mean square error based on the difference between the instrument display mileage and the measured mileage at each sampling point within this range. The segmented average absolute error accurately reflects the average deviation between the instrument display and the measured mileage within the high-charge range, providing fundamental data for overall error assessment; while the segmented root mean square error focuses more on highlighting the impact of larger errors, helping to promptly identify potentially significant error points within the high-charge range. This targeted segmented error assessment method makes the error analysis of the high-charge range more accurate and comprehensive, facilitating in-depth analysis of the accuracy of the instrument display mileage under different charge ranges, and providing a strong basis for subsequent error optimization and vehicle performance improvement.

[0135] In a feasible design, the segmentation error includes the segmented average absolute error and the segmented root mean square error. Determining the segmentation error of the medium-capacity segment based on the first mileage data and the second mileage data includes the following steps:

[0136] The piecewise average absolute error of the medium-voltage segment is determined according to the following formula (6):

[0137] ;Formula (6);

[0138] in, This represents the piecewise average absolute error of the medium-voltage range. This indicates the number of the first valid sampling point in the medium-voltage range. This indicates the number of the last valid sampling point in the medium-voltage range;

[0139] The piecewise root mean square error of the medium-electric range is determined according to the following formula (7);

[0140] ;Formula (7);

[0141] in, This represents the piecewise root mean square error of the medium-voltage range.

[0142] This embodiment achieves precise quantification of the mileage display error in the medium-capacity range by introducing a dual-index evaluation system of segmented average absolute error and segmented root mean square error, specifically targeting the segmented error calculation for the medium-capacity range. This design not only clearly defines the start and end sampling point range of the medium-capacity range but also calculates the average absolute error and root mean square error based on the difference between the instrument display mileage and the measured mileage at each sampling point within this range. The segmented average absolute error accurately reflects the average deviation between the instrument display and the measured mileage within the medium-capacity range, providing fundamental data for overall error assessment; while the segmented root mean square error focuses more on highlighting the impact of larger errors, helping to promptly identify potentially significant error points within the medium-capacity range. This targeted segmented error assessment method makes the error analysis of the medium-capacity range more accurate and comprehensive, facilitating in-depth analysis of the accuracy of the instrument display mileage under different capacity ranges, and providing a strong basis for subsequent error optimization and vehicle performance improvement.

[0143] In a feasible design, the segmentation error includes the segmented mean absolute error and the segmented root mean square error. Determining the segmentation error of the low battery segment based on the first mileage data and the second mileage data includes the following steps:

[0144] The segmented average absolute error of the low-power segment is determined according to the following formula (8):

[0145] ;Formula (8);

[0146] in, This represents the segmented average absolute error for the low battery range. This indicates the number of the first valid sampling point in the low-charge segment. Indicates the number of the last valid sampling point in the low-charge segment;

[0147] The segmented root mean square error of the low-power segment is determined according to the following formula (9);

[0148] ;Formula (9);

[0149] in, This represents the piecewise root mean square error of the low-charge segment.

[0150] This embodiment achieves precise quantification of the mileage display error in the low-battery range by introducing a dual-index evaluation system of segmented average absolute error and segmented root mean square error, specifically designed for segmented error calculation in the low-battery range. This design not only clearly defines the start and end sampling point range of the low-battery range but also calculates the average absolute error and root mean square error based on the difference between the mileage displayed on the instrument panel and the measured mileage at each sampling point within this range. The segmented average absolute error accurately reflects the average deviation between the instrument display and the measured mileage within the low-battery range, providing fundamental data for overall error assessment; while the segmented root mean square error focuses more on highlighting the impact of larger errors, helping to promptly identify potentially significant error points within the low-battery range. This targeted segmented error evaluation method makes the error analysis in the low-battery range more accurate and comprehensive, facilitating in-depth analysis of the accuracy of the mileage displayed on the instrument panel under different battery levels, and providing a strong basis for subsequent error optimization and vehicle performance improvement.

[0151] In a feasible design, determining the individual point errors based on the first mileage data and the second mileage data includes the following steps:

[0152] The absolute value of the difference between the instrument display mileage at each valid sampling point in the first mileage data and the measured mileage data at the corresponding valid sampling point in the second mileage data is determined as the single-point error of the corresponding valid sampling point.

[0153] This embodiment calculates the single-point error by directly measuring the absolute value of the difference between the instrument display mileage and the actual mileage at each valid sampling point, achieving a precise assessment of the accuracy of the mileage display at each sampling point. Presenting the error in absolute value form intuitively reflects the specific degree of deviation between the instrument display and the actual mileage at that sampling point. The error quantification is detailed down to each sampling moment, making the error analysis more refined. This facilitates the rapid identification of abnormal sampling points with large errors, providing strong support for subsequent targeted analysis of mileage display issues at specific moments. It also helps to optimize the instrument display logic at a micro level, improving the overall accuracy and reliability of the driving range display.

[0154] S140 evaluates the instrument display error of the vehicle based on the total error, total error threshold, segment error, segment error threshold, single-point error, and single-point error threshold.

[0155] For example, based on the preliminary results of surveys of representative models in the industry, the overall error threshold L1=5, the segmented error threshold L2=7, and the single-point error threshold L3=10 are set.

[0156] For example, if the vehicle's overall error is less than the overall error threshold, the errors of each segment are less than the segment error threshold, and the errors of each individual point are less than the individual point error threshold, then the vehicle's instrument display error is determined to meet the threshold requirements. Otherwise, the vehicle's instrument display error is determined not to meet the threshold requirements.

[0157] Based on the above method embodiments, this application provides an example of testing the accuracy of the remaining mileage displayed on the instrument panel of a pure electric vehicle under normal temperature, low temperature, and high temperature conditions, combined with sampling data examples. The following is a detailed explanation... Figure 2 The steps shown illustrate a detection example.

[0158] Install the instrument display data acquisition device, including mounting a high-strength, shock-absorbing video recording device above the driver's side instrument display screen with its anti-shake function enabled. The requirements for the video recording device are: high-definition digital display resolution, high-speed anti-shake capability, and that heat dissipation, memory, and power supply be handled by an external power source for extended use. Recording begins at the start of the test and continues uninterrupted until the test concludes.

[0159] The target test method is determined based on the vehicle's ambient temperature and driving range, and the vehicle is tested according to this method. During each test, the following data needs to be recorded: mileage displayed on the instrument panel, mileage data from the actual test on the rotating device, and battery state-of-charge data displayed on the instrument panel. Secondary mileage data includes the mileage data from the rotating device. Specifically, if the target test method is either the first or second shortening method, the secondary mileage data also includes equivalent mileage data determined based on the discharge amount during the constant speed period and the average energy consumption during the cycle period. The requirements for recording the mileage data from the rotating device are: record the cumulative mileage traveled by the vehicle on the rotating device, generating a cumulative value per second to obtain a sequence of cumulative values ​​for the rotating device.

[0160] (1) Under normal temperature test environment, the test method used for vehicles with a driving range ≤ 8 CLTC-P cycles is the continuous operating condition method, that is, the test is carried out continuously according to the CLTC-P test cycle. The test method used for vehicles with a driving range > 8 CLTC-P cycles is the first shortening method. The normal temperature shortening method is tested according to the structure of DS1-CSSm-DS2-CSSe, where DS1 and DS2 are two test cycle segments, each test cycle segment includes two consecutive CLTC-P cycles, and the cycle numbers are 1 to 4 according to the cycle sequence, that is, CLTC-P1, CLTC-P2, CLTC-P3, CLTC-P4. CSSm is the first constant speed segment, and CSSe is the second constant speed segment. The operating condition vehicle speed is a constant value of 100 (km) / h. After being fully charged, the test begins at a 23℃ environment on a rotating drum.

[0161] (2) Under low-temperature test environment temperature, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method. For vehicles with a driving range exceeding 8 CLTC-P cycles, the second shortening method is used. The second shortening method is conducted according to the DS-CSS structure, where DS is the test cycle segment, consisting of 6 CLTC-P cycles, numbered 1 to 6 in sequence, namely CLTC-P1, CLTC-P2, CLTC-P3, CLTC-P4, CLTC-P5, and CLTC-P6; CSS is the constant speed segment, with a constant vehicle speed of 100 km / h. After being fully charged, the vehicle is immersed in a -7℃ test environment chamber for 12 hours before the test begins.

[0162] (3) Under high temperature test environment temperature, the test method used for vehicles with a driving range of ≤8 CLTC-P cycles is the continuous operating condition method. For vehicles with a driving range of more than 8 CLTC-P cycles, the test is conducted according to the second shortening method. After being fully charged, the vehicle is immersed in the test environment chamber at 30℃ for 0.5 hours before the test begins.

[0163] After each test, the data were organized and output according to the sampling point requirements. For videos containing mileage data displayed on the instrument panel, video processing and data extraction were performed using the accompanying software, extracting data at a frequency of once per second. The final data sample table is shown in Table 1.

[0164] Table 1

[0165]

[0166] The sampling rules for sampling the cumulative numerical sequence of the hub equipment are as follows: For each cyclic segment, the mileage data corresponding to the sampling point is the difference between the cumulative value of the hub equipment at the current sampling point and the cumulative value at the previous sampling point. For a constant speed segment, after dividing it into multiple micro-constant speed segments every 10 minutes, the time at the endpoint of each micro-constant speed segment is used as the sampling point, and the difference between the cumulative value of the hub equipment at the current sampling point and the cumulative value at the previous sampling point is taken as the mileage data corresponding to the current sampling point. The sampling point for a cyclic segment is the time between the end of that cyclic segment and the beginning of the next cyclic segment.

[0167] When the target test method is the first shortening method or the second shortening method, it is also necessary to calculate the equivalent mileage data for each micro-constant speed segment according to formula (1) (which can be called equivalent conversion of the constant speed segment). For example, when the test method is the first shortening method, the example of equivalent conversion of the constant speed segment is shown in Table 2:

[0168] Table 2

[0169]

[0170] The average power consumption of the CLTC-P3 and CLTC-P4 cycles in Table 2 is 122.7 watt-hours per kilometer. "micro-CSS" indicates the micro-constant speed range, and the following numbers indicate the micro-constant speed range number.

[0171] For example, when the test method is the second shortening method, the equivalent conversion of the constant speed segment is shown in Table 3:

[0172] Table 3

[0173]

[0174] The average power consumption of the CLTC-P5 and CLTC-P6 cycles in Table 3 is 142 watt-hours per kilometer.

[0175] After each test, the total error, segmental error, and single-point error (mean absolute error and root mean square error) at the corresponding ambient temperature are obtained. Each error is compared with its corresponding error threshold to evaluate the error displayed on the vehicle's instrument panel. The calculation methods for the total error, segmental error, and single-point error are described in the aforementioned formulas.

[0176] For example, after conducting the first shortening test on a vehicle at ambient temperature, the recorded data for the hub mileage, equivalent mileage, instrument display mileage, and single-point error for the CLTC-P1 cycle, CLTC-P2 cycle, and micro-CSS3 to micro-CSS20 micro constant speed cycles are shown in Table 4.

[0177] Table 4

[0178]

[0179] Table 5 shows the recorded data for hub mileage, equivalent mileage, instrument display mileage, and single-point error for the CLTC-P3 cycle, CLTC-P4 cycle, and micro-CSS21 to micro-CSS38 micro-constant speed ranges:

[0180] Table 5

[0181]

[0182] Based on the data in Tables 4 and 5, when testing vehicles using the first shortening method, the average absolute error is 2.1 for the entire test, 2.5 for the high charge segment, 1.9 for the medium charge segment, 3.1 for the low charge segment, and the maximum single-point error is 5.3. The root mean square error (RMS) is 2.5 for the entire test, 3.2 for the high charge segment, 2.2 for the medium charge segment, and 3.8 for the low charge segment. Single-point RMS errors are not calculated.

[0183] Further shortening tests were conducted on the vehicle under high-temperature and low-temperature ambient temperatures, and the error results are as follows:

[0184] High temperature test:

[0185] The average absolute error for the entire range is 6.3, the average absolute error for the high-capacity range is 6.7, the average absolute error for the medium-capacity range is 6.5, the average absolute error for the low-capacity range is 5.1, and the maximum single-point error is 12.4. The root mean square error (RMS) for the entire range is 6.5, the RMS for the high-capacity range is 6.9, the RMS for the medium-capacity range is 6.7, and the RMS for the low-capacity range is 5.3. Single-point RMS errors are not calculated.

[0186] During low-temperature testing:

[0187] The average absolute error for the entire range is 8.7, the average absolute error for the high-capacity segment is 8.7, the average absolute error for the medium-capacity segment is 9.6, the average absolute error for the low-capacity segment is 5.1, and the maximum single-point error is 13.3. The root mean square error (RMS) for the entire range is 9.0, the RMS for the high-capacity segment is 8.8, the RMS for the medium-capacity segment is 9.8, and the RMS for the low-capacity segment is 5.3. Single-point RMS errors are not calculated.

[0188] The above vehicles were evaluated based on the overall error threshold L1=5, the segmented error threshold L2=7, and the single-point error threshold L3=10. The results are as follows:

[0189] Under normal temperature test environment, the vehicle's instrument display error (or accuracy) meets all threshold requirements; under low temperature test environment and high temperature test environment, the vehicle's instrument display error does not meet some threshold requirements.

[0190] This application first establishes a comprehensive and unified testing framework by precisely determining the target testing method based on the vehicle's ambient temperature and driving range. This framework ensures that suitable testing methods can be found for vehicles operating in normal, low, or high-temperature environments, and for vehicles with varying driving ranges. This innovative approach provides a standardized operating procedure and data acquisition foundation for subsequent error detection, ensuring the comparability of test data across different vehicle models and operating conditions from the outset, and building a solid framework for solving technical problems. Specifically, for vehicles with a driving range ≤ 8 CLTC-P cycles under normal ambient temperature testing conditions, the continuous driving cycle method is used. This testing method closely matches the actual driving conditions of vehicles, comprehensively reflecting their range performance in common driving scenarios such as urban roads. Because the testing time for vehicles with short driving ranges is relatively short, the continuous driving cycle method can fully capture the energy consumption and mileage display characteristics of vehicles at different driving stages, ensuring the comprehensiveness and accuracy of error detection. For vehicles with a range greater than 8 CLTC-P cycles, the first shortened method is used. Its test structure includes a sequential cycle segment, a constant speed segment, another cycle segment, and another constant speed segment. This design considers both the long driving range and the simulation of high-speed driving scenarios through the constant speed segment. This test structure effectively shortens the test time while ensuring the representativeness of the test results, balancing the testing efficiency and accuracy of long-range vehicles. In low-temperature or high-temperature testing environments, vehicles with a range ≤ 8 CLTC-P cycles also use the continuous operating condition method. This is because, under extreme temperature conditions, the vehicle's energy consumption and range performance are significantly affected, and the continuous operating condition method can fully expose the vehicle's performance under these special conditions. For vehicles with a range greater than 8 CLTC-P cycles, the second shortened method is used, with a test structure consisting of a cycle segment followed by a constant speed segment. This design considers both the testing efficiency of long-range vehicles under extreme temperatures and the simulation of energy consumption during high-speed or stable driving through the constant speed segment, ensuring the reliability of the test results.

[0191] Secondly, when testing vehicles and collecting test data according to the target test method, if the target test method is the first shortening method or the second shortening method, the collected second mileage data not only includes the mileage data of the rotating device, but also innovatively introduces equivalent mileage data determined based on the discharge amount in the constant speed section and the average power consumption in the cyclic section. This improvement effectively solves the problem of large deviation in the total mileage of the rotating device due to high-speed discharge in the shortening method test, making the measured mileage data more accurate and objectively reflect the actual driving conditions of the vehicle. The introduction of equivalent mileage data not only enriches the dimensions of the test data, but also enhances the scientific nature and comparability of the data, further improving the accuracy of vehicle performance evaluation under different operating conditions, providing more reliable data support for subsequent error calculation, and significantly improving the accuracy and reliability of error detection.

[0192] Finally, through comprehensive analysis and calculation of the collected first and second mileage data, the overall error, segmental errors, and individual point errors were determined. The overall error reflects the overall deviation trend, the segmental errors precisely pinpoint the error characteristics of different battery charge segments, and the individual point errors refine the display accuracy at each sampling moment. This multi-dimensional error quantification method makes the error results more detailed and comparable. Simultaneously, by comparing with preset error thresholds, a precise assessment of the vehicle's instrument display error was achieved, providing a strong basis for improving the accuracy of pure electric vehicle instrument display mileage and evaluating the performance of different models. This comprehensive and detailed error assessment system not only accurately identifies the mileage display errors of different models under various operating conditions but also provides precise data support for subsequent vehicle improvements and optimizations. This makes the displayed range error under different models and operating conditions detectable, quantifiable, and comparable, unifying the evaluation system for instrument display mileage error.

[0193] like Figure 3 As shown, this application provides a pure electric vehicle instrument display mileage error detection system, including:

[0194] The test method determination module is used to determine the target test method based on the vehicle's test environment temperature and driving range. Specifically, under normal test environment temperature, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method, which involves continuous testing according to CLTC-P cycles. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortened method, which involves testing according to a first test structure. The first test structure includes the following operating condition segments in sequence: a cycle segment, a constant operating condition segment, and a constant operating condition segment. The test structure consists of three sections: speed range, cycle range, and constant speed range. The cycle range of the first test structure includes two CLTC-P cycles. Under low-temperature or high-temperature test environments, vehicles with a range of ≤8 CLTC-P cycles are tested using the continuous operating condition method. Vehicles with a range of >8 CLTC-P cycles are tested using the second shortened method. The second shortened method is a test method conducted according to the second test structure. The operating condition sections of the second test structure are, in order, the cycle range and the constant speed range. The cycle range of the second test structure includes six CLTC-P cycles.

[0195] The test module is used to test the vehicle according to the target test method and collect the test data of the vehicle. The test data includes the first mileage data and the second mileage data displayed by the instrument. The second mileage data includes the mileage data of the rotating device. In the case that the target test method is the first shortening method or the second shortening method, the second mileage data also includes the equivalent mileage data determined based on the discharge amount of the constant speed section and the average power consumption of the cycle section.

[0196] The error calculation module is used to determine the total error, segment errors and single-point errors based on the first mileage data and the second mileage data. The total error is calculated based on the sampling points within the entire test cycle. The segment errors are calculated based on the sampling points of the high-capacity segment, medium-capacity segment or low-capacity segment divided by the battery state of charge interval. The single-point error is calculated based on a single sampling point.

[0197] The evaluation module is used to evaluate the instrument display error of the vehicle based on the overall error, the overall error threshold, the errors of each segment, the segment error threshold, the errors of each single point, and the single point error threshold.

[0198] In a feasible design, when the target testing method is either the first shortening method or the second shortening method, the testing module collects equivalent mileage data in the following way:

[0199] After excluding the acceleration and immersion processes in the constant speed section, the constant speed section is divided into multiple micro constant speed sections according to a preset time interval.

[0200] Determine the discharge quantity corresponding to each micro-constant velocity segment;

[0201] Determine the average power consumption of the corresponding cycle segment;

[0202] The micro-constant velocity range is determined based on the following formula. Equivalent mileage data :

[0203] ;

[0204] in, Indicates the micro-constant speed range Equivalent mileage data, Indicates the micro-constant speed range The amount of discharge, Indicates the number of the constant speed range. This represents the average power consumption of the cycle segment, where the test method is the first shortening method. This represents the average power consumption of the 3rd and 4th CLTC-P cycles, under the second shortening method of testing. This represents the average power consumption of the 5th and 6th CLTC-P cycles.

[0205] In a feasible design, the test module collects vehicle test data in the following way:

[0206] Acquire the video recorded by the recording device on the instrument display screen during the test;

[0207] Extract mileage data from each instrument display on the video at a frequency of once per second;

[0208] The mileage data displayed by each instrument is sampled according to the first sampling rule to obtain the first mileage data. The first mileage data includes the mileage data corresponding to each sampling point. The first sampling rule is used to stipulate that the mileage data corresponding to the sampling point of the cycle segment is the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point. The sampling point of the cycle segment is the time between the end of the current cycle segment and the beginning of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point, and the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0209] In a feasible design, the test module extracts mileage data from each instrument display at a frequency of once per second from the video feed in the following manner:

[0210] Video is captured at a frequency of 5 frames per second to form an image data sequence;

[0211] For the mileage number region in each frame of the image data sequence, a pre-trained digit recognition model is used to independently identify it, and output 5 sets of results per second containing the specific digit and the corresponding confidence level.

[0212] Based on the highest confidence level selection mechanism, the number with the highest confidence level is selected from the 5 sets of results corresponding to each second as the mileage data displayed on the instrument for that second.

[0213] In a feasible design, the test module identifies the mileage numeral regions in each frame of image in the following manner:

[0214] If the current frame image is the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the initial frame are determined by the target detection algorithm, and the offsets of the four vertices of the mileage number region in the initial frame relative to the preset screen boundary are recorded as four reference parameters.

[0215] If the current frame is not the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the current frame are determined by calculating the image translation based on phase correlation tracking technology. The similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated. If all similarities are higher than the similarity threshold, the mileage number region of the next frame is identified until the mileage number region of each frame in the image data sequence is identified. If there is a similarity below the similarity threshold, the coordinates of the four vertices of the mileage number region in the current frame are determined again based on phase correlation tracking technology, and the similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated again, until all similarities in the current frame are higher than the similarity threshold.

[0216] In a feasible design, the test module collects vehicle test data in the following way:

[0217] The cumulative mileage of the vehicle is recorded in real time by a rotating device, generating a cumulative value every second to obtain a cumulative value sequence;

[0218] The cumulative value sequence is sampled according to the second sampling rule to obtain the mileage data of the hub device. The second sampling rule is used to specify that the mileage data corresponding to the sampling point of the cycle segment is the difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point. The sampling point of the cycle segment is the time after the end of the current cycle segment and before the start of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point. The difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point is used as the mileage data corresponding to the current sampling point.

[0219] In a feasible design, the total error includes the total mean absolute error and the total root mean square error. The error calculation module determines the total error based on the first mileage data and the second mileage data in the following way:

[0220] Acquire the instrument display mileage data from each valid sampling point in the first mileage data, excluding the zero point and the initial point;

[0221] Obtain the measured mileage data of each valid sampling point in the second mileage data. Wherein, when the target test method is the continuous working condition method, the measured mileage data is the mileage data of the hub equipment. When the target test method is the first shortening method or the second shortening method, the measured mileage data is the equivalent mileage data.

[0222] The mean absolute error over the entire process is determined using the following formula:

[0223] ;

[0224] in, This represents the average absolute error over the entire process. Indicates the number of the valid sampling point. This indicates the number of valid sampling points throughout the entire testing period. Indicates valid sampling points The instrument panel displays mileage data. Indicates valid sampling points Actual mileage data;

[0225] The root mean square error throughout the entire process is determined using the following formula:

[0226] ;

[0227] in, This represents the root mean square error over the entire process.

[0228] In a feasible design, the segmented error includes the segmented mean absolute error and the segmented root mean square error. The error calculation module determines the segmented error of the high-battery segment based on the first mileage data and the second mileage data in the following way:

[0229] The segmented average absolute error of the high-capacity range is determined using the following formula:

[0230] ;

[0231] in, This represents the segmented average absolute error of the high-charge segment. This indicates the number of the first valid sampling point in the high-charge segment. This indicates the number of the last valid sampling point in the high-charge range;

[0232] The piecewise root mean square error of the high-electricity segment is determined according to the following formula;

[0233] ;

[0234] in, This represents the piecewise root mean square error of the high-charge segment.

[0235] In a feasible design, the error calculation module determines the individual point errors based on the first mileage data and the second mileage data in the following way:

[0236] The absolute value of the difference between the instrument display mileage at each valid sampling point in the first mileage data and the measured mileage data at the corresponding valid sampling point in the second mileage data is determined as the single-point error of the corresponding valid sampling point.

[0237] Other implementation methods and effects of the above-mentioned device can be found in the description of the embodiment of the pure electric vehicle instrument display mileage error detection method, and will not be repeated here.

[0238] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0239] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0240] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0241] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0242] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0243] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for detecting mileage display error in a pure electric vehicle's instrument panel, characterized in that, include: The target test method is determined based on the vehicle's ambient temperature and driving range. Under normal ambient temperature conditions, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method, which involves continuous testing according to the CLTC-P cycle. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortening method, which involves testing according to a first test structure. The first test structure includes the following operating condition segments in sequence: a cyclic segment, a constant speed segment, and a cyclic segment. The constant speed section of the first test structure includes two CLTC-P cycles. Under low temperature or high temperature test environment, vehicles with a range of ≤8 CLTC-P cycles are tested using the continuous operating condition method, while vehicles with a range of >8 CLTC-P cycles are tested using the second shortened method. The second shortened method is a test method conducted according to the second test structure. The operating condition sections of the second test structure are, in order, the cyclic section and the constant speed section. The cyclic section of the second test structure includes six CLTC-P cycles. The vehicle is tested according to the target test method, and the test data of the vehicle is collected. The test data includes the first mileage data and the second mileage data displayed by the instrument. The second mileage data includes the mileage data of the rotating device. In the case that the target test method is the first shortening method or the second shortening method, the second mileage data also includes the equivalent mileage data determined based on the discharge amount of the constant speed section and the average power consumption of the cycle section. The total error, segment errors, and single-point errors are determined based on the first mileage data and the second mileage data. The total error is statistically analyzed based on the sampling points throughout the entire test cycle. The segment errors are calculated based on the sampling points of the high-capacity segment, medium-capacity segment, or low-capacity segment divided into battery state-of-charge intervals. The single-point errors are calculated based on a single sampling point. The instrument display error of the vehicle is evaluated based on the total error, total error threshold, segment error, segment error threshold, single-point error, and single-point error threshold.

2. The method according to claim 1, characterized in that, When the target test method is the first shortening method or the second shortening method, the steps for collecting equivalent mileage data include: After excluding the acceleration and immersion processes in the constant speed section, the constant speed section is divided into multiple micro constant speed sections according to a preset time interval. Determine the discharge quantity corresponding to each micro-constant velocity segment; Determine the average power consumption of the corresponding cycle segment; The micro-constant velocity range is determined based on the following formula. Equivalent mileage data : ； in, Indicates the micro-constant speed range Equivalent mileage data, Indicates the micro-constant speed range The amount of discharge, Indicates the number of the constant speed range. This represents the average power consumption of the cycle segment, where the test method is the first shortening method. This represents the average power consumption of the 3rd and 4th CLTC-P cycles, under the second shortening method of testing. This represents the average power consumption of the 5th and 6th CLTC-P cycles.

3. The method according to claim 1 or 2, characterized in that, The test data collected from the vehicles includes: Acquire the video recorded by the recording device on the instrument display screen during the test; The video is processed to extract mileage data from each instrument display once per second. The mileage data displayed by each instrument is sampled according to the first sampling rule to obtain the first mileage data. The first mileage data includes the mileage data corresponding to each sampling point. The first sampling rule is used to stipulate that the mileage data corresponding to the sampling point of the cycle segment is the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point. The sampling point of the cycle segment is the time between the end of the current cycle segment and the beginning of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to the preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point, and the absolute value of the difference between the mileage data displayed by the instrument at the current sampling point and the mileage data displayed by the instrument at the previous sampling point is used as the mileage data corresponding to the current sampling point.

4. The method according to claim 3, characterized in that, The step of extracting mileage data from each instrument display on the video at a frequency of once per second includes: The video is captured at a frequency of 5 frames per second to form an image data sequence; For the mileage number region in each frame of the image data sequence, a pre-trained digit recognition model is used to independently identify it, and output 5 sets of results per second containing specific numbers and corresponding confidence levels. Based on the highest confidence level selection mechanism, the number with the highest confidence level is selected from the 5 sets of results corresponding to each second as the mileage data displayed on the instrument for that second.

5. The method according to claim 4, characterized in that, The process of identifying the mileage digit region in each frame of an image includes the following steps: If the current frame image is the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the initial frame are determined by the target detection algorithm, and the offsets of the four vertices of the mileage number region in the initial frame relative to the preset screen boundary are recorded as four reference parameters. If the current frame is not the initial frame in the image data sequence, the coordinates of the four vertices of the mileage number region in the current frame are determined by calculating the image translation based on phase correlation tracking technology. The similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated. If all similarities are higher than the similarity threshold, the mileage number region of the next frame is identified until the mileage number region of each frame in the image data sequence is identified. If there is a similarity lower than the similarity threshold, the coordinates of the four vertices of the mileage number region in the current frame are determined again based on phase correlation tracking technology, and the similarity between the offset of each vertex coordinate in the current frame relative to the preset image boundary and the corresponding reference parameters of the initial frame is calculated again, until all similarities in the current frame are higher than the similarity threshold.

6. The method according to claim 1 or 2, characterized in that, The test data collected from the vehicles includes: The cumulative mileage of the vehicle is recorded in real time by a rotating device, generating a cumulative value every second to obtain a cumulative value sequence; According to the second sampling rule, the cumulative value sequence is sampled to obtain the mileage data of the hub device. The second sampling rule is used to specify that the mileage data corresponding to the sampling point of the cycle segment is the difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point. The sampling point of the cycle segment is the time after the end of the current cycle segment and before the start of the next cycle segment. After the constant speed segment is divided into multiple micro constant speed segments according to a preset time interval, the time of the endpoint of each micro constant speed segment is used as the sampling point. The difference between the cumulative value of the hub device at the current sampling point and the cumulative value of the hub device at the previous sampling point is used as the mileage data corresponding to the current sampling point.

7. The method according to claim 1 or 2, characterized in that, The total error includes the total mean absolute error and the total root mean square error. The total error is determined based on the first mileage data and the second mileage data, including: Acquire the instrument display mileage data for each valid sampling point in the first mileage data, excluding the zero point and the initial point; Obtain the measured mileage data of each valid sampling point in the second mileage data. Wherein, when the target test method is the continuous working condition method, the measured mileage data is the mileage data of the hub equipment. When the target test method is the first shortening method or the second shortening method, the measured mileage data is the equivalent mileage data. The mean absolute error over the entire process is determined using the following formula: ； in, This represents the average absolute error over the entire process. Indicates the number of the valid sampling point. This indicates the number of valid sampling points throughout the entire testing period. Indicates valid sampling points The instrument panel displays mileage data. Indicates valid sampling points Actual mileage data; The root mean square error throughout the entire process is determined using the following formula: ； in, This represents the root mean square error over the entire process.

8. The method according to claim 3, characterized in that, Segmentation error includes segmented average absolute error and segmented root mean square error. Determining the segmentation error of the high-battery segment based on the first mileage data and the second mileage data includes the following steps: The segmented average absolute error of the high-capacity range is determined using the following formula: ； in, This represents the segmented average absolute error of the high-charge segment. This indicates the number of the first valid sampling point in the high-charge segment. This indicates the number of the last valid sampling point in the high-charge range; The piecewise root mean square error of the high-electricity segment is determined according to the following formula; ； in, This represents the piecewise root mean square error of the high-charge segment.

9. The method according to claim 7, characterized in that, Determining the individual point error based on the first mileage data and the second mileage data includes the following steps: The absolute value of the difference between the instrument display mileage of each valid sampling point in the first mileage data and the measured mileage data of the corresponding valid sampling point in the second mileage data is determined as the single-point error of the corresponding valid sampling point.

10. A mileage error detection system for a pure electric vehicle instrument panel display, characterized in that, include: The test method determination module is used to determine the target test method based on the vehicle's test environment temperature and driving range. Specifically, under normal test environment temperature, vehicles with a driving range ≤ 8 CLTC-P cycles are tested using the continuous operating condition method, which is a test method that continuously performs tests according to CLTC-P cycles. Vehicles with a driving range > 8 CLTC-P cycles are tested using the first shortening method, which is a test method that performs tests according to a first test structure. The first test structure includes the following operating condition segments in sequence: a cyclic segment, a constant speed segment, and a... The test structure consists of three segments: a cyclic segment, a constant speed segment, and a continuous operating condition segment. The cyclic segment of the first test structure includes two CLTC-P cycles. Under low-temperature or high-temperature test environments, vehicles with a range of ≤8 CLTC-P cycles are tested using the continuous operating condition method, while vehicles with a range of >8 CLTC-P cycles are tested using the second shortened method. The second shortened method is a test method conducted according to the second test structure. The operating condition segments of the second test structure are, in order, a cyclic segment and a constant speed segment. The cyclic segment of the second test structure includes six CLTC-P cycles. The testing module is used to test the vehicle according to the target testing method and collect the vehicle's test data. The test data includes first mileage data and second mileage data displayed on the instrument panel. The second mileage data includes mileage data from the rotating device. When the target testing method is the first shortening method or the second shortening method, the second mileage data also includes equivalent mileage data determined based on the discharge amount in the constant speed section and the average power consumption in the cycle section. The error calculation module is used to determine the total error, segment errors and single-point errors based on the first mileage data and the second mileage data. The total error is calculated based on the sampling points within the entire test cycle. The segment errors are calculated based on the sampling points of the high-capacity segment, medium-capacity segment or low-capacity segment divided into battery state-of-charge intervals. The single-point errors are calculated based on a single sampling point. The evaluation module is used to evaluate the instrument display error of the vehicle based on the overall error, the overall error threshold, the errors of each segment, the segment error threshold, the errors of each single point, and the single point error threshold.

Images