Evaluation Method, Device, Electronic System and Storage Medium for Vehicle Performance

Abstract

The present invention relates to the technical field of electrical digital data processing, and particularly relates to a method, device, electronic system and storage medium for evaluating vehicle performance. The method includes: extracting motion segments that meet preset high-speed conditions from the sample data of the target fleet to form a high-speed database, determining the database features of the high-speed database, calculating the state transition probability matrix of the high-speed database, constructing a basic state segment library, establishing an alternative vehicle speed segment library, and determining the high-speed working conditions of the target fleet by combining the database features and the alternative motion segments in the alternative motion segment library, so as to evaluate the high-speed performance of the vehicle by using the high-speed working conditions. Thus, the technical problems in the related art are solved. In the related art, when the short-stroke method selects samples for high-speed working conditions, it is difficult to control them within the allocated time range of the overall working conditions, and the Markov chain method has a high occupation of time and resources, both of which are not conducive to popularization and application.

Description

Technical Field

[0001] The present invention relates to the technical field of electric digital data processing, and particularly relates to a method, device, electronic system and storage medium for evaluating vehicle performance. Background Art

[0002] A driving cycle is a speed-time curve reflecting the driving characteristics of vehicles in a certain area and is used to evaluate vehicles on a drum.

[0003] In related technologies, the construction of driving cycles generally adopts the short-trip method and the Markov method.

[0004] Among them, the short-trip method can divide the collected short trips into different speed intervals; then select and combine them to generate an interval driving cycle that conforms to driving rules; finally, combine across intervals to form a complete driving cycle. When a vehicle is driving on a highway, since there are few stops and starts, the highway driving cycle is generally represented by a single short trip; due to the high vehicle speed requirement, the number of samples in the highway trip library is small; due to the long continuous driving time, the sample duration is high; therefore, when the short-trip method selects samples for the highway driving cycle, it is difficult to control it within the allocated duration range in the overall driving cycle.

[0005] The Markov chain method can establish a state transition probability matrix based on a vehicle speed database collected on an actual road, randomly generate a vehicle speed sequence of a specified duration, and select samples that can reflect the driving rules in the highway interval as the highway driving cycle. In order to make the transition probability matrix conform to the driving rules, a large amount of data calculation is required; in order to generate qualified samples that simultaneously meet the requirements of the duration range, the maximum vehicle speed and the database characteristics, a large number of sequences need to be generated, resulting in a high occupation of time and resources.

[0006] In summary, in related technologies, when the short-trip method selects samples for the highway driving cycle, it is difficult to control it within the allocated duration range in the overall driving cycle, while the Markov chain method has a high occupation of time and resources, both of which are not conducive to popularization and application and need to be improved. Summary of the Invention

[0007] The present invention provides a method, device, electronic system and storage medium for evaluating vehicle performance to solve the technical problems in related technologies that when the short-trip method selects samples for the highway driving cycle, it is difficult to control it within the allocated duration range in the overall driving cycle, while the Markov chain method has a high occupation of time and resources, both of which are not conducive to popularization and application.

[0008] An embodiment of the first aspect of the present invention provides a method for evaluating vehicle performance, including the following steps: extracting motion segments that meet preset high-speed conditions from the sample data of the target fleet, and using the motion segments to form a high-speed database; calculating multiple characteristic parameters of each motion segment in the high-speed database, and determining the database characteristics of the high-speed database according to the multiple characteristic parameters; calculating the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database; constructing a basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration; randomly converting each state segment in the basic state segment library according to a first preset random strategy to obtain a first conversion result, and establishing an alternative vehicle speed segment library according to the first conversion result; randomly converting each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to obtain a second conversion result, and establishing an alternative motion segment library according to the second conversion result, and determining the high-speed working condition of the target fleet by combining the database characteristics and the alternative motion segments in the alternative motion segment library, so as to evaluate the high-speed performance of the vehicle by using the high-speed working condition.

[0009] Optionally, in an embodiment of the present invention, after determining the database characteristics of the high-speed database according to the multiple characteristic parameters, it further includes: calculating the maximum deviation degree between each motion segment and the database characteristics by using the multiple characteristic parameters and the database characteristics; judging whether the maximum deviation degree is less than or equal to a preset deviation limit value, if it is less than or equal to the preset deviation limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment, otherwise, deleting the motion segment corresponding to the maximum deviation degree; using the qualified segments to form a new high-speed database, and determining the database characteristics of the new high-speed database according to the multiple characteristic parameters corresponding to the qualified segments.

[0010] Optionally, in an embodiment of the present invention, the calculating the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database includes: splicing the high-speed samples in the high-speed database to generate a vehicle speed sequence with a preset length; dividing the interval of the vehicle speed sequence by a preset speed step to convert the vehicle speed sequence into a driving state sequence; and obtaining the state transition probability matrix according to the driving state sequence and a preset mapping relationship between the state binary combination and the state transition scenario.

[0011] Optionally, in an embodiment of the present invention, constructing the basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration includes: starting from the initial state, randomly generating a corresponding state sequence by using the state transition probability matrix; when the maximum value of the state sequence is greater than the preset state threshold and the corresponding moment of the state sequence is within the preset high-speed working condition segment duration, inputting the state sequence into the basic state segment library until the number of state sequences in the basic state segment library reaches the preset quantity threshold.

[0012] Optionally, in an embodiment of the present invention, randomly converting each state segment in the basic state segment library according to a first preset random strategy to obtain a first conversion result, and establishing an alternative vehicle speed segment library according to the first conversion result includes: randomly converting each state segment in the basic state segment library according to the first preset random strategy to generate a corresponding first vehicle speed segment; extracting first sample segments that meet the preset compliance from all the first vehicle speed segments, and establishing the alternative vehicle speed segment library by using the first sample segments.

[0013] Optionally, in an embodiment of the present invention, randomly converting each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to obtain a second conversion result, and establishing an alternative motion segment library according to the second conversion result, and determining the high-speed working condition of the target vehicle fleet by combining the database characteristics and the alternative motion segments in the alternative motion segment library includes: randomly converting each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to generate a corresponding second vehicle speed segment; extracting second sample segments that meet the qualified conditions from all the second vehicle speed segments, and inputting the second sample segments into the alternative motion segment library of the high-speed working condition until the data of the alternative motion segments in the alternative motion segment library reaches the preset threshold; calculating the distribution of each second sample segment in the preset speed-acceleration interval, and performing a chi-square test on the distribution by using the database characteristics to obtain the high-speed working condition.

[0014] According to an embodiment of the second aspect of the present invention, a vehicle performance evaluation device is provided, including: an extraction module, configured to extract motion segments that meet preset high-speed conditions from the sample data of a target fleet, and use the motion segments to form a high-speed database, calculate a plurality of characteristic parameters of each motion segment in the high-speed database, and determine the database characteristics of the high-speed database according to the plurality of characteristic parameters; a first calculation module, configured to calculate a state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database; a first construction module, configured to construct a basic state segment library based on the state transition probability matrix and a preset high-speed working condition segment duration; a second construction module, configured to randomly transform each state segment in the basic state segment library according to a first preset random strategy to obtain a first transformation result, and establish an alternative vehicle speed segment library according to the first transformation result; an evaluation module, configured to randomly transform each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to obtain a second transformation result, and establish an alternative motion segment library according to the second transformation result, combine the database characteristics and the alternative motion segments in the alternative motion segment library to determine the high-speed working conditions of the target fleet, so as to evaluate the high-speed performance of the vehicle by using the high-speed working conditions.

[0015] Optionally, in an embodiment of the present invention, it further includes: a second calculation module, configured to calculate the maximum deviation degree between each motion segment and the database characteristics by using the plurality of characteristic parameters and the database characteristics; a judgment module, configured to judge whether the maximum deviation degree is less than or equal to a preset deviation limit value. If it is less than or equal to the preset deviation limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment; otherwise, the motion segment corresponding to the maximum deviation degree is deleted; a determination module, configured to form a new high-speed database by using the qualified segments, and determine the database characteristics of the new high-speed database according to the plurality of characteristic parameters corresponding to the qualified segments.

[0016] Optionally, in an embodiment of the present invention, the first calculation module includes: a splicing unit, configured to splice the high-speed samples in the high-speed database to generate a vehicle speed sequence with a preset length; a first transformation unit, configured to divide the interval of the vehicle speed sequence by a preset speed step and transform the vehicle speed sequence into a driving state sequence; a calculation unit, configured to obtain the state transition probability matrix according to the driving state sequence and a preset mapping relationship between the state binary combination and the state transition scenario.

[0017] Optionally, in an embodiment of the present invention, the first construction module includes: a generation unit configured to randomly vary from an initial state and generate a corresponding state sequence by using the state transition probability matrix; a first input unit configured to, when the maximum value of the state sequence is greater than a preset state threshold and the corresponding moment of the state sequence is within the preset high-speed working condition segment duration, input the state sequence into the basic state segment library until the number of state sequences in the basic state segment library reaches a preset number threshold.

[0018] Optionally, in an embodiment of the present invention, the second construction module includes: a second conversion unit configured to randomly convert each state segment in the basic state segment library according to a first preset random strategy to generate a corresponding first vehicle speed segment; a first construction unit configured to extract first sample segments that meet a preset compliance from all the first vehicle speed segments and establish the alternative vehicle speed segment library by using the first sample segments.

[0019] Optionally, in an embodiment of the present invention, the evaluation module includes: a third conversion unit configured to randomly convert each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to generate a corresponding second vehicle speed segment; a second input unit configured to extract second sample segments that meet qualified conditions from all the second vehicle speed segments and input the second sample segments into the alternative motion segment library of the high-speed working condition until the data of the alternative motion segments in the alternative motion segment library reaches a preset threshold; a test unit configured to calculate the distribution of each second sample segment in a preset speed-acceleration interval and perform a chi-square test on the distribution by using the database features to obtain the high-speed working condition.

[0020] An embodiment of the third aspect of the present invention provides an electronic system, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the vehicle performance evaluation method as described in the above embodiments.

[0021] An embodiment of the fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle performance evaluation method as described in the above embodiments.

[0022] An embodiment of the fifth aspect of the present invention provides a computer program product including a computer program, which when executed, is used to implement the vehicle performance evaluation method as described above.

[0023] Embodiments of the present invention can extract motion segments that meet preset high-speed conditions from the sample data of the target vehicle fleet to form a high-speed database, and determine the database features of the high-speed database. Then, the state transition probability matrix of the high-speed database is calculated using the high-speed sample data in the high-speed database. By establishing a single mapping from the binary combination of driving states to the state transition scenario, the counting operation is controlled within a fixed number of times, eliminating the influence of the database capacity on the occupied time, and efficiently and controllably completing this process. Furthermore, a basic state segment library is constructed based on the state transition probability matrix and the preset high-speed working condition segment duration. When randomly generating basic state segments, the duration range and the highest driving state value are controlled simultaneously, so that the randomly generated vehicle speed samples converted from the samples in the library can meet the requirements of the highest vehicle speed and duration range of the high-speed database. Each state segment in the basic state segment library is randomly converted, and a small number of alternative state segments with a high degree of conformity to the high-speed database features can be selected in a short time, thereby establishing an alternative vehicle speed segment library. Each alternative state segment in the alternative vehicle speed segment library is randomly converted to establish an alternative motion segment library. Then, the high-speed working conditions of the target vehicle fleet are determined by combining the database features and the alternative motion segments in the alternative motion segment library, and the high-speed performance of the vehicle is evaluated using the high-speed working conditions. Thus, the technical problems in the related art are solved. In the short-stroke method for selecting samples for high-speed working conditions, it is difficult to control them within the allocated duration range of the overall working condition, and the Markov chain method has a high occupation of time and resources, both of which are not conducive to popularization and application.

[0024] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. Brief Description of the Drawings

[0025] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0026] Figure 1 is a flowchart of a method for evaluating the performance of a vehicle according to an embodiment of the present invention;

[0027] Figure 2 is a flowchart of a method for evaluating the performance of a vehicle according to an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of the principle of generating basic state segments according to an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of the principle of generating alternative state segments according to an embodiment of the present invention;

[0030] Figure 5Schematic diagram of an alternative state segment and an alternative vehicle speed segment according to an embodiment of the present invention;

[0031] Figure 6 Schematic diagram of the principle for generating a high-speed motion segment according to an embodiment of the present invention;

[0032] Figure 7 Schematic diagram of the structure of an evaluation device for vehicle performance provided according to an embodiment of the present invention;

[0033] Figure 8 Schematic diagram of the structure of an electronic system provided according to an embodiment of the present invention.

[0034] Wherein, 10 - evaluation device for vehicle performance, 100 - extraction module, 200 - first calculation module, 300 - first construction module, 400 - second construction module, 500 - evaluation module; 801 - memory, 802 - processor, 803 - communication interface. Detailed implementation manners

[0035] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation to the present invention.

[0036] The following describes a method, device, electronic system, and storage medium for evaluating vehicle performance according to embodiments of the present invention. In view of the technical problems in the related art mentioned in the above background art, that is, in the short-stroke method, it is difficult to control the selection of samples for high-speed working conditions within the allocated time range of the overall working conditions, and the Markov chain method has a high occupancy of time and resources, both of which are not conducive to popularization and application. The present invention provides a method for evaluating vehicle performance. In this method, motion segments that meet the preset high-speed conditions can be extracted from the sample data of the target fleet to form a high-speed database, and the database characteristics of the high-speed database can be determined. Then, the state transition probability matrix of the high-speed database can be calculated using the high-speed sample data in the high-speed database. By establishing a single mapping from the binary combination of driving states to the state transition scenario, the counting operation can be controlled within a fixed number of times, eliminating the influence of the database capacity on the occupied time, and efficiently and controllably completing this process. Furthermore, a basic state segment library can be constructed based on the state transition probability matrix and the preset high-speed working condition segment duration. When randomly generating basic state segments, the duration range and the highest driving state value are controlled at the same time, so that the randomly generated vehicle speed samples converted from the samples in the library can meet the requirements of the highest vehicle speed and duration range of the high-speed database. Each state segment in the basic state segment library can be randomly converted, and a small number of alternative state segments with a high degree of conformity to the high-speed database characteristics can be selected in a short time, thereby establishing an alternative vehicle speed segment library. Each alternative state segment in the alternative vehicle speed segment library can be randomly converted to establish an alternative motion segment library. Then, the high-speed working conditions of the target fleet can be determined by combining the database characteristics and the alternative motion segments in the alternative motion segment library, and the high-speed performance of the vehicle can be evaluated using the high-speed working conditions. Thus, the technical problems in the related art, that is, in the short-stroke method, it is difficult to control the selection of samples for high-speed working conditions within the allocated time range of the overall working conditions, and the Markov chain method has a high occupancy of time and resources, both of which are not conducive to popularization and application, are solved.

[0037] Specifically, Figure 1 is a schematic flowchart of a method for evaluating vehicle performance provided by an embodiment of the present invention.

[0038] As Figure 1 shown, the method for evaluating vehicle performance includes the following steps:

[0039] In step S101, motion segments that meet the preset high-speed conditions are extracted from the sample data of the target fleet, and a high-speed database is formed using the motion segments. Multiple characteristic parameters of each motion segment in the high-speed database are calculated, and the database characteristics of the high-speed database are determined based on the multiple characteristic parameters.

[0040] In the actual implementation process, embodiments of the present invention can form a target fleet, and after a period of stable free running, collect corresponding sample data, such as vehicle speed data, and extract motion segments that meet the preset high-speed conditions from the sample data. For example, extract motion segments with a maximum vehicle speed greater than a certain vehicle speed, and establish a high-speed database based on these motion segments.

[0041] Calculate the characteristic parameters of each motion segment in the high-speed database. Among them, the characteristic parameters may include: average speed, acceleration ratio, deceleration ratio, uniform speed ratio, average acceleration, and average deceleration, etc. Embodiments of the present invention can, based on the above characteristic parameters, statistically analyze the overall operating condition characteristics corresponding to the high-speed database.

[0042] For example, average speed (km / h): the average vehicle speed of all seconds in the motion segment;

[0043] Acceleration ratio (%): the ratio of the number of seconds with an acceleration a ≥ 0.15m / s 2 in the motion segment to the duration of the motion segment;

[0044] Deceleration ratio (%): in the motion segment a ≤ -0.15m / s 2 the ratio of the number of seconds to the duration of the motion segment;

[0045] Uniform speed ratio (%): in the motion segment, -0.15 < a <0.15m / s 2 the ratio of the number of seconds to the duration of the motion segment;

[0046] Average acceleration (m / s 2 ): the average acceleration of all accelerating seconds in the motion segment;

[0047] Average deceleration (m / s 2 ): the average acceleration of all decelerating seconds in the motion segment.

[0048] Optionally, in an embodiment of the present invention, after determining the database characteristics of the high-speed database according to multiple characteristic parameters, it further includes: calculating the maximum deviation degree between each motion segment and the database characteristics using the multiple characteristic parameters and the database characteristics; determining whether the maximum deviation degree is less than or equal to a preset deviation limit value. If it is less than or equal to the preset deviation limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment. Otherwise, delete the motion segment corresponding to the maximum deviation degree; form a new high-speed database using the qualified segments, and determine the database characteristics of the new high-speed database according to the multiple characteristic parameters corresponding to the qualified segments.

[0049] As a possible implementation manner, embodiments of the present invention may define the maximum deviation degree between the motion segment and the corresponding working condition characteristics of the high-speed database:

[0050] D max (%) = Max(abs(segment feature i - database feature i) / database feature i)) (i = 1, 2, …6).

[0051] In order to effectively reflect the actual road high-speed driving law of the vehicle, the motion segment of the final generated high-speed working condition should conform to the corresponding database characteristics. For example, D max not higher than the specified limit D high of the sample is a qualified motion segment of the high-speed working condition.

[0052] It should be noted that the preset deviation limit, that is, the specified limit D high can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0053] In step S102, the state transition probability matrix of the high-speed database is calculated by using the high-speed sample data in the high-speed database.

[0054] Embodiments of the present invention can calculate the state transition probability matrix of the high-speed database. Compared with the counting operation of the massive second-by-second vehicle speed transition scenarios in the related art, embodiments of the present invention can control the counting operation within a fixed number of times by establishing a single mapping from the binary combination of driving states to the state transition scenario, eliminating the influence of the database capacity on the occupied time, and efficiently and controllably completing the calculation process.

[0055] Optionally, in an embodiment of the present invention, calculating the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database includes: splicing the high-speed samples in the high-speed database to generate a vehicle speed sequence with a preset length; dividing the interval of the vehicle speed sequence with a preset speed as the step length, and converting the vehicle speed sequence into a driving state sequence; and obtaining the state transition probability matrix according to the driving state sequence and the preset mapping relationship between the binary combination of states and the state transition scenario.

[0056] In some embodiments, embodiments of the present invention may splice the high-speed samples in the high-speed database to generate a vehicle speed sequence with a length of l of v (t), and divide the interval of the vehicle speed sequence through a certain speed step length to convert the vehicle speed sequence into a driving state sequence.

[0057] For example, in the embodiments of the present invention, intervals can be divided with a step of 5 km / h and converted into a driving state sequence s(t): that is, the vehicle speed values within the interval [5, 10) are used as state 1, the vehicle speed values within the interval [10, 15) are used as state 2, and so on, until the state S corresponding to the highest interval. max That is, it is the downward rounding value obtained by dividing the highest value of the vehicle speed sequence by 5.

[0058] It can be understood that the Markov method believes that the current driving state will affect the next state, that is, the transition between adjacent states reflects the driving law of the vehicle.

[0059] Therefore, the s(t) sequence contains l N-1 binary combinations representing the transition scenarios between adjacent states: {[s(1), s(2)],…[s(t-1), s(t)],…[s( l N-1), s( l )]}, and through l N-1 counting operations, the proportion of [s(t)=i, s(t+1)=j] is statistically obtained, that is, the state transition probability matrix P ij is obtained. The driving conditions generated by randomly changing the control state based on it can reflect the driving law of the high-speed database.

[0060] However, the time taken for the statistical process is highly affected by the database capacity. To eliminate this influence, the embodiments of the present invention can define a single mapping S-S(i, j) from the state binary combination [i, j] to the state transition scenario. By statistically obtaining the proportion of the corresponding transition scenario mapping result sequence {S-S(s(1), s(2)),…S-S(s( l N-1), s( l ))} of each mapping result in s(t), the counting operation can be controlled from l N-1 to S max 2 times, and the P ij matrix can be generated efficiently and controllably.

[0061] In step S103, a basic state segment library is constructed based on the state transition probability matrix and the preset high-speed driving condition segment duration.

[0062] In the embodiments of the present invention, a basic state segment library can be established according to a certain high-speed driving condition segment duration. Among them, the preset high-speed driving condition segment duration can be set accordingly by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0063] In the actual implementation process, when constructing the basic state segment library in the embodiments of the present invention, the Markov chain method can be applied to randomly generate basic state segments, and at the same time, control their duration range and the highest driving state value, so that the randomly generated vehicle speed samples converted from the samples in the library can meet the requirements of the highest vehicle speed and duration range of the high-speed database.

[0064] Optionally, in an embodiment of the present invention, constructing a basic state segment library based on a state transition probability matrix and a preset high-speed working condition segment duration includes: starting from the initial state, randomly varying using the state transition probability matrix to generate a corresponding state sequence; when the maximum value of the state sequence is greater than a preset state threshold and the corresponding moment of the state sequence is within the preset high-speed working condition segment duration, entering the state sequence into the basic state segment library until the number of state sequences in the basic state segment library reaches a preset number threshold.

[0065] For example, the embodiments of the present invention can define that the high-speed working condition segment duration is between T min and T max . The highest vehicle speed of the high-speed segment is greater than 80 km / h, and the corresponding highest state of the segment should be greater than 16.

[0066] Starting from the initial state [t = 0, s(0) = 1], the embodiments of the present invention can apply P ij to control the random change from state s(t) = i to s(t + 1) = j to generate a state sequence:

[0067] ,

[0068] where r is a random number uniformly distributed in the (0 1) interval.

[0069] When it comes to the situation where t reaches between T min and T max , s(t) returns to 1, and the maximum value Max(s(t)) that appears between s(1) and s(t) is higher than 16, the sequence at this time is entered into the basic state segment library. The samples in the library all meet the requirements of the highest vehicle speed and duration range. When t exceeds T max and still does not meet the conditions, return to the initial state and start generating the sequence again.

[0070] Repeat the above operations until the number of basic state segments in the library reaches a certain amount.

[0071] In step S104, each state segment in the basic state segment library is randomly converted according to the first preset random strategy to obtain a first conversion result, and an alternative vehicle speed segment library is established according to the first conversion result.

[0072] Further, embodiments of the present invention can randomly transform the state segments in the basic state segment library to obtain corresponding vehicle speed segments, and screen the obtained vehicle speed segments, thereby establishing an alternative state segment library.

[0073] Embodiments of the present invention can perform a small number of vehicle speed conversions and feature validations on the state segments in the basic state segment library, and select a small number of alternative state segments with a high degree of conformity to the high-speed database features in a short time. Based on the above-mentioned small number of samples, vehicle speed conversions and feature validations are repeatedly performed, so as to generate a number of vehicle speed segments that meet the feature requirements in a short time, as alternative motion segments for the final output working conditions.

[0074] Optionally, in an embodiment of the present invention, each state segment in the basic state segment library is randomly transformed according to a first preset random strategy to obtain a first transformation result, and an alternative vehicle speed segment library is established according to the first transformation result, including: randomly transforming each state segment in the basic state segment library according to the first preset random strategy to generate corresponding first vehicle speed segments; extracting first sample segments that meet the preset conformity from all the first vehicle speed segments, and using the first sample segments to establish an alternative vehicle speed segment library.

[0075] As a possible implementation manner, embodiments of the present invention can define a formula for randomly transforming the state segment s(t) to generate the vehicle speed segment v(t):

[0076] v(t)=(s(t)-1)+r*5km / h,

[0077] where r is a random number uniformly distributed in the interval (0, 1). The deviation between the vehicle speed segments generated by the same state segment transformation is within 10 km / h.

[0078] Among them, the random transformation method can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0079] If a certain state segment can generate a vehicle speed segment that initially meets the feature conformity through a small number of transformation operations, it indicates that its conformity to the high-speed database is high. The possibility of generating a vehicle speed segment that finally meets the conformity through repeated transformation operations is high.

[0080] Therefore, a small number of vehicle speed segments are randomly generated for each basic state segment. If the conversion deviation D max is less than D high *(1 + 10 / average vehicle speed of the high-speed database) of the sample, it is considered that the corresponding basic state segment initially conforms to the working condition characteristics of the high-speed database, and thus it is recorded in the alternative state segment library.

[0081] In step S105, each alternative state segment in the alternative vehicle speed segment library is randomly transformed according to a second preset random strategy to obtain a second transformation result, and an alternative motion segment library is established based on the second transformation result. The high-speed condition of the target vehicle fleet is determined by combining the database features and the alternative motion segments in the alternative motion segment library, so as to evaluate the high-speed performance of the vehicle using the high-speed condition.

[0082] In an embodiment of the present invention, a vehicle speed segment can be randomly generated by randomly transforming each alternative state segment, and the generated vehicle speed segments are screened. Then, an alternative motion segment library is established according to the screening result. The high-speed condition of the target vehicle fleet is determined by combining the database features and the alternative motion segments in the alternative motion segment library, so as to evaluate the vehicle performance of the target vehicle fleet under the high-speed condition.

[0083] The embodiment of the present invention can efficiently and stably generate a high-speed condition that simultaneously meets the requirements of duration, vehicle speed, and actual road database condition characteristics, so as to effectively reflect the high-speed driving law of the vehicle. Using it for drum testing is of great significance for evaluating the various performances of the vehicle under high-speed conditions.

[0084] Optionally, in an embodiment of the present invention, randomly transforming each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to obtain a second transformation result, and establishing an alternative motion segment library based on the second transformation result, and determining the high-speed condition of the target vehicle fleet by combining the database features and the alternative motion segments in the alternative motion segment library includes: randomly transforming each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to generate corresponding second vehicle speed segments; extracting second sample segments that meet the qualified conditions from all the second vehicle speed segments, and entering the second sample segments into the alternative motion segment library of the high-speed condition until the data of the alternative motion segments in the alternative motion segment library reaches a preset threshold; calculating the distribution of each second sample segment in a preset speed-acceleration interval, and performing a chi-square test on the distribution using the database features to obtain the high-speed condition.

[0085] For example, in an embodiment of the present invention, each alternative state segment can be randomly transformed according to a second preset random strategy to generate vehicle speed segments, and the qualified samples with D max less than D high are entered into the alternative motion segment library of the high-speed condition. Among them, the specific random transformation method can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0086] Repeat the above operations until there are 5 alternative motion segments in the library.

[0087] The embodiment of the present invention can calculate the distribution of each sample in each span of [5 km / h - 0.5 m / s2 The ratio of the number of seconds in the speed (v)-acceleration (a) interval of [] to its total duration, that is, the combined speed distribution of the segment, is subjected to a chi-square test with the corresponding distribution in the high-speed database. The sample with the highest confidence level is selected as the high-speed motion segment, and an idling segment with a fixed duration is added after it to generate a high-speed working condition.

[0088] Combined with Figures 2 to 6 As shown in [], the working principle of the vehicle performance evaluation method according to the embodiment of the present invention will be described in detail with an example.

[0089] Taking the example of forming a fleet of 10 vehicles and collecting vehicle speed data of about 40,000 kilometers after 1 month of stable free operation.

[0090] As Figure 2 shown, the embodiment of the present invention may include the following steps:

[0091] Step S201: Establish a high-speed database for motion segments. In the embodiment of the present invention, motion segments with a maximum vehicle speed greater than 80 km / h can be selected to establish a high-speed database. The working condition characteristics of the database are shown in Table 1, where Table 1 is the high-speed database feature table.

[0092] Table 1

[0093]

[0094] Among them, the maximum vehicle speed of the high-speed database is 106 km / h, corresponding to 22 driving states.

[0095] In the embodiment of the present invention, the mapping between the state binary combination and the transition scenario can be defined as S-S(i,j) = i×(1 / (j + 0.3)+j).

[0096] After verification, for 22*22 combinations, the 484 S-S calculation results are all different. As shown in Table 2, where Table 2 is the mapping matrix table between the state combination and the transition scenario.

[0097] It should be noted that the dark part intersection point in Table 2 represents the transition scenario from state 9 to 10, that is, the transition scenario when the current vehicle speed is in [40~45 km / h) and the adjacent vehicle speed in the next second is in [45~50 km / h). Its mapping result is 9×(1 / (10 + 0.3)+10), that is, 90.87 in the black grid at the 9th row and 10th column in the table.

[0098] Table 2

[0099]

[0100] Stitch all the high-speed database segments to generate a vehicle speed sequence v(t), as shown in the second column of Table 3, is converted into a driving state sequence s(t), as shown in the third column of the table. Calculate the mapping results for each adjacent state combination [i, j], as shown in the third column of the table, where Table 3 is the vehicle speed - state conversion and mapping calculation result table of the sequence.

[0101] It should be noted that, as shown in bold in Table 3, the mapping result of the transition from state 9 at the 8th second to state 10 at the 9th second is 90.87.

[0102] Table 3

[0103]

[0104] Count the proportion of 484 mapping values in the fourth column of Table 3 to obtain the state transition probability matrix [Pij] of the high - speed database.

[0105] Step S202: Establish a basic state segment library. In the embodiment of the present invention, it can be stipulated that the duration of the high - speed working condition segment is within the range of 400*(1 ± 5%) seconds. Starting from state 1, a state sequence is randomly generated by applying the probability conversion matrix. When the maximum value of the sequence exceeds 16 and reaches 1 between 380 and 420 s, it is entered into the basic state segment library. The specific process can be as Figure 3 shown. Repeat the above process until the number of samples in the library reaches 2000.

[0106] Step S203: Select an alternative state segment library based on a small number of vehicle speed conversions and preliminary feature verifications. The average vehicle speed of the high - speed database is 58 km / h. In the embodiment of the present invention, the deviation limit for feature inspection can be defined as 8%, that is, the maximum deviation value D max should ≤ 8%. Then the preliminary deviation limit of the alternative state segment library is 9.3% = 8%*(1 + 10 / 58).

[0107] Randomly generate 20 vehicle speed segments for each sample in the basic state library. If there are samples with D max ≤ 9.3%, then enter the corresponding basic state segments into the alternative state segment library. The specific process is as Figure 4 shown. The alternative state segment library generated in the embodiment of the present invention contains 2 samples, as shown by the light - colored lines in Figure 5 it.

[0108] Step S204: Establish an alternative vehicle speed segment library based on vehicle speed conversion and feature verification. Randomly generate 2 corresponding vehicle speed segments based on 2 alternative state segments, and calculate the 2 Ds obtained from the features. max If there is a case where ≤ 8% in Figure 6 it, then record the corresponding qualified vehicle speed segments. The specific process is as

[0109] After repeating the above operation 2,189 times in the embodiment of the present invention, 5 qualified samples were generated.

[0110] Step S205: Generate an optimal high-speed working condition based on the chi-square test. In the embodiment of the present invention, the chi-square confidence of the speed-acceleration distribution of each qualified sample and the high-speed database can be calculated, and the sample with the highest confidence is selected as the high-speed motion segment, and the segment duration is 406 seconds, as Figure 5 shown by the black line in the following figure. Add an idle segment of 32 s after it to complete the development of the high-speed working condition. The deviation between the characteristic parameters of the working condition and the actual road database is within 5%, as shown in Table 4, where Table 4 is the characteristic table of the output high-speed working condition.

[0111] Table 4

[0112]

[0113] From the above example, it can be seen that the embodiment of the present invention can efficiently and stably generate a high-speed working condition that meets both the custom duration requirement and the actual road driving law.

[0114] According to the vehicle performance evaluation method proposed by the embodiment of the present invention, a motion segment that meets the preset high-speed condition can be extracted from the sample data of the target fleet to form a high-speed database, and the database characteristics of the high-speed database can be determined, so as to calculate the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database, so as to control the counting operation at a fixed number of times by establishing a single mapping from the binary combination of driving states to the state transition scenario, eliminate the influence of the database capacity on the occupied time, complete this process efficiently and controllably, and then construct a basic state segment library according to the state transition probability matrix and the preset high-speed working condition segment duration. When randomly generating the basic state segment, the duration range and the highest driving state value are controlled at the same time, so that the randomly generated vehicle speed samples generated by the conversion of the samples in the library can meet the requirements of the highest vehicle speed and duration range of the high-speed database. Each state segment in the basic state segment library can be randomly converted, and a small number of alternative state segments with high conformity to the high-speed database characteristics can be selected in a short time, so as to establish an alternative vehicle speed segment library. Each alternative state segment in the alternative vehicle speed segment library can be randomly converted to establish an alternative motion segment library, so as to determine the high-speed working condition of the target fleet by combining the database characteristics and the alternative motion segments in the alternative motion segment library, so as to evaluate the high-speed performance of the vehicle by using the high-speed working condition. Thus, the technical problems in the related art are solved. When the short-stroke method selects samples for the high-speed working condition, it is difficult to control them within the allocated duration range of the overall working condition, while the Markov chain method has a high occupation of time and resources, which are not conducive to popularization and application.

[0115] Next, an evaluation device for vehicle performance proposed according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0116] Figure 7 It is a block diagram of an evaluation device for vehicle performance according to an embodiment of the present invention.

[0117] As Figure 7 shown, the evaluation device 10 for vehicle performance includes:

[0118] Specifically, an extraction module 100 is configured to extract motion segments that meet preset high-speed conditions from the sample data of the target fleet, and use the motion segments to form a high-speed database, calculate multiple characteristic parameters of each motion segment in the high-speed database, and determine the database characteristics of the high-speed database according to the multiple characteristic parameters.

[0119] A first calculation module 200 is configured to calculate the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database.

[0120] A first construction module 300 is configured to construct a basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration.

[0121] A second construction module 400 is configured to randomly transform each state segment in the basic state segment library according to a first preset random strategy to obtain a first transformation result, and establish an alternative vehicle speed segment library according to the first transformation result.

[0122] An evaluation module 500 is configured to randomly transform each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to obtain a second transformation result, and establish an alternative motion segment library according to the second transformation result, combine the database characteristics and the alternative motion segments in the alternative motion segment library to determine the high-speed working conditions of the target fleet, so as to evaluate the high-speed performance of the vehicle by using the high-speed working conditions.

[0123] Optionally, in an embodiment of the present invention, the evaluation device 10 for vehicle performance further includes: a second calculation module, a judgment module, and a determination module.

[0124] Among them, the second calculation module is configured to calculate the maximum deviation degree between each motion segment and the database characteristics by using the multiple characteristic parameters and the database characteristics.

[0125] The judgment module is configured to judge whether the maximum deviation degree is less than or equal to a preset deviation degree limit value. If it is less than or equal to the preset deviation degree limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment. Otherwise, the motion segment corresponding to the maximum deviation degree is deleted.

[0126] The determination module is configured to form a new high-speed database by using the qualified segments, and determine the database characteristics of the new high-speed database according to the multiple characteristic parameters corresponding to the qualified segments.

[0127] Optionally, in an embodiment of the present invention, the first calculation module 200 includes: a splicing unit, a first conversion unit, and a calculation unit.

[0128] The splicing unit is configured to splice high-speed samples in the high-speed database to generate a vehicle speed sequence with a preset length.

[0129] The first conversion unit is configured to divide the interval of the vehicle speed sequence at a preset speed step and convert the vehicle speed sequence into a driving state sequence.

[0130] The calculation unit is configured to obtain a state transition probability matrix according to the driving state sequence and a preset mapping relationship between the state binary combination and the state transition scenario.

[0131] Optionally, in an embodiment of the present invention, the first construction module 300 includes: a generation unit and a first input unit.

[0132] Wherein, the generation unit is configured to start from the initial state and randomly generate a corresponding state sequence by using the state transition probability matrix.

[0133] The first input unit is configured to, when the maximum value of the state sequence is greater than a preset state threshold and the corresponding moment of the state sequence is within the preset high-speed working condition segment duration, input the state sequence into the basic state segment library until the number of state sequences in the basic state segment library reaches a preset number threshold.

[0134] Optionally, in an embodiment of the present invention, the second construction module 400 includes: a second conversion unit and a first construction unit.

[0135] Wherein, the second conversion unit is configured to randomly convert each state segment in the basic state segment library according to a first preset random strategy to generate a corresponding first vehicle speed segment.

[0136] The first construction unit is configured to extract first sample segments that meet a preset compliance from all the first vehicle speed segments and establish an alternative vehicle speed segment library by using the first sample segments.

[0137] Optionally, in an embodiment of the present invention, the evaluation module 500 includes: a third conversion unit, a second input unit, and an inspection unit.

[0138] Wherein, the third conversion unit is configured to randomly convert each alternative state segment in the alternative vehicle speed segment library according to a second preset random strategy to generate a corresponding second vehicle speed segment.

[0139] A second input unit, configured to extract second sample segments that meet the qualified conditions from all the second vehicle speed segments, and input the second sample segments into an alternative motion segment library for the high-speed working condition until the data of the alternative motion segments in the alternative motion segment library reaches a preset threshold.

[0140] An inspection unit, configured to calculate the distribution of each second sample segment in a preset speed-acceleration interval, and perform a chi-square test on the distribution using database features to obtain the high-speed working condition.

[0141] It should be noted that the foregoing explanations of the embodiments of the vehicle performance evaluation method are also applicable to the vehicle performance evaluation device of this embodiment, and will not be elaborated here.

[0142] According to the vehicle performance evaluation device provided by an embodiment of the present invention, motion segments that meet preset high-speed conditions can be extracted from the sample data of a target fleet to form a high-speed database, and the database features of the high-speed database can be determined, so as to calculate the state transition probability matrix of the high-speed database using the high-speed sample data in the high-speed database. By establishing a single mapping from the binary combination of driving states to the state transition scenario, the counting operation is controlled within a fixed number of times, eliminating the influence of the database capacity on the occupied time, and efficiently and controllably completing this process. Furthermore, a basic state segment library is constructed according to the state transition probability matrix and the preset high-speed working condition segment duration. When randomly generating basic state segments, the duration range and the highest driving state value are controlled at the same time, so that the randomly generated vehicle speed samples generated by the conversion of the samples in the library can meet the requirements of the highest vehicle speed and duration range of the high-speed database. Each state segment in the basic state segment library is randomly converted, and a small number of alternative state segments with high conformity to the high-speed database features can be selected in a short time, thereby establishing an alternative vehicle speed segment library. Each alternative state segment in the alternative vehicle speed segment library is randomly converted to establish an alternative motion segment library, so as to determine the high-speed working condition of the target fleet in combination with the database features and the alternative motion segments in the alternative motion segment library, and use the high-speed working condition to evaluate the high-speed performance of the vehicle. Thus, the technical problems in the related art are solved. In the short-stroke method, it is difficult to control the selection of samples for the high-speed working condition within the allocated duration range of the overall working condition, while the Markov chain method has a high occupation of time and resources, both of which are not conducive to popularization and application.

[0143] Figure 8 The structural schematic diagram of the electronic system provided by an embodiment of the present invention. The vehicle may include:

[0144] A memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

[0145] When the processor 802 executes the program, it implements the vehicle performance evaluation method provided in the foregoing embodiments.

[0146] Furthermore, the electronic system further includes:

[0147] A communication interface 803 for communication between the memory 801 and the processor 802.

[0148] A memory 801 for storing a computer program that can run on the processor 802.

[0149] The memory 801 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0150] If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0151] Optionally, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a single chip, the memory 801, the processor 802, and the communication interface 803 can communicate with each other through an internal interface.

[0152] The processor 802 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0153] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above vehicle performance evaluation method is implemented.

[0154] This embodiment of the present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the vehicle performance evaluation method provided by the embodiments of the present invention is implemented.

[0155] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0156] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0157] Any process or method description shown in a flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a manner that is not in the order shown or discussed, including in a substantially simultaneous manner according to the functions involved or in a reverse order, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0158] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0159] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0160] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0161] In addition, each functional unit in various embodiments of the present invention may be integrated into one processing module, may exist separately as individual physical units, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0162] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for evaluating vehicle performance, characterized in that, Including the following steps: Extract motion segments that meet the preset high-speed conditions from the sample data of the target vehicle fleet, and use the motion segments to form a high-speed database. Calculate multiple characteristic parameters of each motion segment in the high-speed database, and determine the database characteristics of the high-speed database according to the multiple characteristic parameters; Calculate the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database; Construct a basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration; Randomly transform each state segment in the basic state segment library according to the first preset random strategy to obtain a first transformation result, and establish an alternative vehicle speed segment library according to the first transformation result; Randomly transform each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to obtain a second transformation result, and establish an alternative motion segment library according to the second transformation result. Combine the database characteristics and the alternative motion segments in the alternative motion segment library to determine the high-speed working conditions of the target vehicle fleet, so as to evaluate the high-speed performance of the vehicle by using the high-speed working conditions.

2. The evaluation method of vehicle performance according to claim 1, characterized in that After determining the database characteristics of the high-speed database according to the multiple characteristic parameters, it further includes: Calculate the maximum deviation degree between each motion segment and the database characteristics by using the multiple characteristic parameters and the database characteristics; Judge whether the maximum deviation degree is less than or equal to the preset deviation limit value. If it is less than or equal to the preset deviation limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment. Otherwise, delete the motion segment corresponding to the maximum deviation degree; Use the qualified segments to form a new high-speed database, and determine the database characteristics of the new high-speed database according to the multiple characteristic parameters corresponding to the qualified segments.

3. The method for evaluating vehicle performance according to claim 1, wherein The calculating the state transition probability matrix of the high-speed database by using the high-speed sample data in the high-speed database includes: Concatenate the high-speed samples in the high-speed database to generate a vehicle speed sequence with a preset length; Divide the interval of the vehicle speed sequence with a preset speed as the step length, and convert the vehicle speed sequence into a driving state sequence; Obtain the state transition probability matrix according to the driving state sequence and the preset mapping relationship between the state binary combination and the state transition scenario.

4. The method for evaluating vehicle performance according to claim 1, wherein, The constructing a basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration includes: Starting from the initial state, randomly generate a corresponding state sequence by using the state transition probability matrix; When the maximum value of the state sequence is greater than the preset state threshold and the corresponding moment of the state sequence is within the preset high-speed working condition segment duration, record the state sequence into the basic state segment library until the number of state sequences in the basic state segment library reaches the preset number threshold.

5. The method for evaluating vehicle performance according to claim 1, wherein, The randomly transforming each state segment in the basic state segment library according to the first preset random strategy to obtain a first transformation result, and establishing an alternative vehicle speed segment library according to the first transformation result includes: Randomly transform each state segment in the basic state segment library according to the first preset random strategy to generate corresponding first vehicle speed segments; Extract first sample segments that meet the preset compliance from all the first vehicle speed segments, and use the first sample segments to establish the alternative vehicle speed segment library.

6. The method for evaluating vehicle performance according to claim 1, characterized in that, The step of randomly transforming each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to obtain a second transformation result, and establishing an alternative motion segment library based on the second transformation result, and determining the high-speed working condition of the target vehicle fleet in combination with the database characteristics and the alternative motion segments in the alternative motion segment library includes: Randomly transform each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to generate corresponding second vehicle speed segments; Extract second sample segments that meet the qualified conditions from all the second vehicle speed segments, and input the second sample segments into the alternative motion segment library of the high-speed working condition until the data of the alternative motion segments in the alternative motion segment library reaches a preset threshold; Calculate the distribution of each second sample segment in the preset speed-acceleration interval, and perform a chi-square test on the distribution using the database characteristics to obtain the high-speed working condition.

7. An evaluation device for vehicle performance, characterized in that, Including: An extraction module, configured to extract motion segments that meet the preset high-speed conditions from the sample data of the target vehicle fleet, and use the motion segments to form a high-speed database, calculate multiple characteristic parameters of each motion segment in the high-speed database, and determine the database characteristics of the high-speed database according to the multiple characteristic parameters; A first calculation module, configured to calculate the state transition probability matrix of the high-speed database using the high-speed sample data in the high-speed database; A first construction module, configured to construct a basic state segment library based on the state transition probability matrix and the preset high-speed working condition segment duration; A second construction module, configured to randomly transform each state segment in the basic state segment library according to the first preset random strategy to obtain a first transformation result, and establish an alternative vehicle speed segment library according to the first transformation result; An evaluation module, configured to randomly transform each alternative state segment in the alternative vehicle speed segment library according to the second preset random strategy to obtain a second transformation result, and establish an alternative motion segment library according to the second transformation result, and determine the high-speed working condition of the target vehicle fleet in combination with the database characteristics and the alternative motion segments in the alternative motion segment library, so as to evaluate the high-speed performance of the vehicle using the high-speed working condition.

8. The evaluation device for vehicle performance according to claim 7, characterized in that It further includes: A second calculation module, configured to calculate the maximum deviation degree between each motion segment and the database characteristics using the multiple characteristic parameters and the database characteristics; A judgment module, configured to judge whether the maximum deviation degree is less than or equal to a preset deviation limit value. If it is less than or equal to the preset deviation limit value, the motion segment corresponding to the maximum deviation degree is a qualified segment; otherwise, delete the motion segment corresponding to the maximum deviation degree. A determination module, configured to form a new high-speed database by using the qualified segments, and determine database features of the new high-speed database according to a plurality of feature parameters corresponding to the qualified segments.

9. An electronic system, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the vehicle performance evaluation method according to any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the vehicle performance evaluation method according to any one of claims 1-6.

Images