CN114662620A - Automobile endurance load data processing method and device for market users - Google Patents
Automobile endurance load data processing method and device for market users Download PDFInfo
- Publication number
- CN114662620A CN114662620A CN202210566586.2A CN202210566586A CN114662620A CN 114662620 A CN114662620 A CN 114662620A CN 202210566586 A CN202210566586 A CN 202210566586A CN 114662620 A CN114662620 A CN 114662620A
- Authority
- CN
- China
- Prior art keywords
- data
- signal data
- working condition
- key
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Traffic Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method and a device for processing automobile endurance load data of market users, wherein the method comprises the following steps: the method comprises the steps of defining key durable load signals of new energy automobile market user data, and introducing selection and basis of the durable load signals by taking a motor driving system assembly as an example; defining a sub-working condition segment of a market user endurance load signal, and in the proposal, a motor driving system assembly is taken as an example to introduce an algorithm for compressing and cutting market user endurance load data into sub-working conditions in detail; clustering operation is carried out on the market user endurance load data sub-working condition segments, a mean vector and a covariance matrix of a probability density function of the market user endurance load data are solved on the basis of a multi-step iteration method, dispersion distances from different sub-working conditions to a center working condition are calculated on the basis of the mean vector and the covariance matrix, and multi-step iteration is carried out on the basis of the dispersion distances, so that a market user endurance load data sub-working condition segment set is generated through clustering and is used for guiding the formulation of finished automobile and rack endurance test specifications of automobiles.
Description
Technical Field
The invention relates to the technical field of automobile durability, in particular to an automobile durable load data processing method and device for market users.
Background
The endurance test of the automobile is generally established according to the development experience of a host factory, or the service condition of a user is investigated according to the questionnaire of a market user. However, the endurance test of the automobile is actually inseparable from the development process of the host factory and the actual use situation of the user.
That is to say, the result of the car endurance test verification in the related art is one-sided, and only depends on the development experience of the host factory, or only depends on the user experience collected from the user using process in the questionnaire to implement the car endurance test, so that the accuracy of the car endurance test is low, and the optimal balance of the whole car cost and the safety and reliability of the whole car cannot be realized.
Disclosure of Invention
The embodiment of the application provides a method and a device for processing automobile endurance load data of market users, solves the technical problems of one-sidedness and low accuracy of test results of automobile endurance tests in the prior art, realizes combination of actual use working conditions of users, obtains automobile working condition data of the users in the use process, and improves the comprehensiveness of the automobile endurance tests and the technical effect of verifying the accuracy.
In a first aspect, the present application provides a method for processing data of automobile endurance load of market users, the method comprising:
acquiring key durable load signal data of a target system assembly of an automobile;
dividing various types of data in the key durable load signal data into F sub-working condition segments respectively according to the time sequence of the last parking vehicle speed, the maximum peak value of the vehicle speed and the time sequence of the next parking time, wherein F is a positive integer;
and clustering the F sub-working condition fragments to obtain K types of target working conditions, wherein the K types of target working conditions are used for carrying out an endurance test on the automobile.
Further, when the target system assembly is a motor drive system assembly, acquiring critical endurance load signal data of the target system assembly of the automobile, comprising:
obtaining key durable load signal data of the motor driving system assembly, wherein the key durable load signal data comprises driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
Further, acquiring differential signal data of the motor drive system assembly comprises:
acquiring left wheel speed signal data and right wheel speed signal data of an automobile;
and determining differential signal data according to the difference value of the left wheel speed signal data and the right wheel speed signal data.
Further, after obtaining the critical endurance load signal data of the target system assembly of the automobile, before dividing each kind of data in the critical endurance load signal data into F sub-operating condition segments, the method further includes:
acquiring monitoring signal data of the automobile from an automobile networking system of the automobile, wherein the monitoring signal data comprises speed signal data, steering wheel signal data, brake pedal signal data and wheel speed signal data;
identifying whether abnormal data exist in the key durable load signal data according to the variation trend of the monitoring signal data;
and when abnormal data exists in the key durable load signal data, correcting the abnormal data, and updating the key durable load signal data according to the corrected abnormal data.
Further, after updating the critical endurance load signal data depending on the corrected abnormal data, before dividing each kind of data in the critical endurance load signal data into F sub-condition segments, the method further includes:
identifying key point data of the key durable load signal data according to a preset key point data screening condition;
acquiring a preset threshold value of a data channel of a weight-related signal of a target system assembly;
and on the premise of reserving all key point data in the key durable load signal data, removing the signal data smaller than the preset threshold value of the critical durable load signal data channel from the key durable load signal data to obtain the compressed key durable load signal data.
Further, clustering the F sub-working condition segments to obtain K types of target working conditions, including:
step 1, determining a mean vector and a covariance matrix of each sub-working condition segment in F sub-working condition segments;
step 2, randomly selecting K sub-working condition segments from the F sub-working condition segments as the central working condition of the K-type target working condition;
step 3, determining the dispersion distance between each non-central working condition and each central working condition according to the mean vector and the covariance matrix of each non-central working condition fragment in the F sub-working condition fragments and the mean vector and the covariance matrix of each central working condition in the K central working conditions;
step 4, dividing each non-central working condition into data sets of K types of target working conditions according to the dispersion distance between each non-central working condition and each central working condition to obtain K data sets;
step 5, aiming at each data set, connecting the sub-working condition segments in the data set into new data segments according to the time sequence, determining the mean vector and covariance matrix of the new data segments, and taking the mean vector and covariance matrix of the new data segments as the mean vector and covariance matrix after the central working condition corresponding to the data set is updated;
and 6, repeating the steps 3-5 aiming at the updated mean vector and covariance matrix of each central working condition until the variation amplitude of the mean vector and covariance matrix of each data set in the K data sets is smaller than a preset amplitude threshold value.
In a second aspect, the present application provides a market consumer's automobile endurance load data processing apparatus, comprising:
the key durable load signal data acquisition module is used for acquiring key durable load signal data of a target system assembly of the automobile;
the sub-working condition segment dividing module is used for dividing various types of data in the key durable load signal data into F sub-working condition segments according to the time sequence of the last parking vehicle speed, the time of the maximum peak value of the vehicle speed and the time of the next parking vehicle, wherein F is a positive integer;
and the clustering module is used for clustering the F sub-working condition fragments to obtain K types of target working conditions, and the K types of target working conditions are used for carrying out an endurance test on the automobile.
Further, the key endurance load signal data acquisition module is specifically configured to:
when the target system assembly is the motor driving system assembly, key durable load signal data of the motor driving system assembly are obtained, wherein the key durable load signal data comprise driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
In a third aspect, the present application provides an electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute to implement a market user's automobile endurance load data processing method as provided in the first aspect.
In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a method of processing automobile endurance load data for a market user as provided in the first aspect.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of firstly defining key durable load signals of new energy automobile market user data, and specifically, taking a motor driving system assembly of a new energy automobile as an example to describe selection and basis of the durable load signals in detail; then, defining a sub-working condition segment of the market user durable load signal, and specifically, describing an algorithm for compressing and cutting market user durable load data into sub-working conditions in detail by taking a motor driving system assembly of the new energy automobile as an example; finally, clustering operation is carried out on the market user durable load data sub-working condition segments, specifically, taking a motor driving system of a new energy automobile as an example, a mean vector and a covariance matrix of a probability density function for solving the market user durable load data based on a multi-step iteration method are introduced in detail, the dispersion distance from different sub-working conditions to a central working condition is calculated based on the mean vector and the covariance matrix, multi-step iteration is carried out based on the dispersion distance, so that a market user durable load data sub-working condition segment set is generated through clustering, and the obtained sub-working condition segment set can be used for guiding the formulation of the finished automobile and rack durable test specifications of the automobile.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for processing automobile endurance load data of market users according to the present application;
FIG. 2 is a schematic structural diagram of an automobile endurance load data processing apparatus for market users according to the present application;
fig. 3 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
The embodiment of the application provides a method for processing automobile endurance load data of market users, and solves the technical problems that in the prior art, the test result of an automobile endurance test has one-sidedness and low accuracy.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
a method for processing automobile endurance load data of market users comprises the following steps: acquiring key durable load signal data of a target system assembly of an automobile; dividing various types of data in the key durable load signal data into F sub-working condition segments respectively according to the time sequence of the last parking vehicle speed, the maximum peak value of the vehicle speed and the time sequence of the next parking time, wherein F is a positive integer; and clustering the F sub-working condition fragments to obtain K types of target working conditions, wherein the K types of target working conditions are used for carrying out an endurance test on the automobile.
The method comprises the steps of firstly defining a key endurance load signal of new energy automobile market user data, and specifically, taking a motor driving system assembly of a new energy automobile as an example to describe selection and basis of the endurance load signal in detail; then, defining a sub-working condition segment of the market user durable load signal, and specifically, describing an algorithm for compressing and cutting market user durable load data into sub-working conditions in detail by taking a motor driving system assembly of the new energy automobile as an example; finally, clustering operation is carried out on the market user durable load data sub-working condition segments, specifically, taking a motor driving system of a new energy automobile as an example, a mean vector and a covariance matrix of a probability density function for solving the market user durable load data based on a multi-step iteration method are introduced in detail, the dispersion distance from different sub-working conditions to a central working condition is calculated based on the mean vector and the covariance matrix, multi-step iteration is carried out based on the dispersion distance, so that a market user durable load data sub-working condition segment set is generated through clustering, and the obtained sub-working condition segment set can be used for guiding the formulation of the finished automobile and rack durable test specifications of the automobile.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
First, it is stated that the term "and/or" appearing herein is merely one type of associative relationship that describes an associated object, meaning that three types of relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The new energy automobiles delivered to market users are all provided with TBOX systems (Telematics Box, Internet of vehicles, TBOX for short), the TBOX can provide services such as driving data acquisition, remote query and control, fault monitoring and the like for the automobiles by using remote communication and information science technologies, and can also provide services such as fault diagnosis, road rescue, remote unlocking, air conditioner control and the like for the users. The TBOX stores the internal signal data of the automobile in the driving process, and automobile manufacturers can call the data in the TBOX through the big data platform under the permission of users so as to read the internal signal data of the automobile in the driving process.
The automobile comprises a plurality of different subsystems, each subsystem is subjected to different endurance load excitations, so that relevant data of the corresponding subsystem are acquired from different signal data channels of TBOX aiming at endurance tests of the different subsystems. The types of the automobile subsystems and the corresponding key signal data channels of the subsystems can be referred to table 1.
TABLE 1
The method for processing the automobile endurance load data provided by the embodiment is mainly taken as an example of a motor driving system, and the method for processing the automobile endurance load data is explained.
Specifically, the present embodiment provides a method for processing automobile endurance load data of a market user as shown in fig. 1, which includes steps S11-S13.
And step S11, acquiring key durable load signal data of the target system assembly of the automobile.
The target system assembly may be a suspension system, a steering system, a braking system, a vehicle body system, a power system, etc. in table 1, or may be other system assemblies in an automobile, which is not limited in this embodiment. In the following description, a motor driving system of a new energy vehicle is taken as an example to illustrate a method for processing vehicle endurance load data of a market user.
When the target system assembly is a motor drive system assembly, obtaining key endurance load signal data of the target system assembly of the automobile, comprising: obtaining key durable load signal data of the motor driving system assembly, wherein the key durable load signal data comprises driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
New energy automobile's motor drive system assembly includes: motor assembly, reduction gear assembly, differential mechanism assembly.
For a motor assembly and a reducer assembly, a signal data channel within the TBOX comprises: the driving motor torque signal data, the driving motor rotating speed signal data and the motor water temperature signal data, wherein the 3 signal data can represent mechanical loads (namely the driving motor torque load and the driving motor rotating speed load) and environmental loads (namely the motor water temperature) borne by the motor assembly and the reducer assembly.
For the differential assembly, in addition to the torque and rotation speed load input by the driving motor, the differential assembly is also subjected to differential load of left and right wheel speeds, and a signal data channel in the TBOX has no differential signal data of the left and right wheel speeds, but contains single wheel speed signal data, so that the differential signal data of the left and right wheel speeds can be obtained by subtracting the right wheel speed signal data from the left wheel speed signal data.
Specifically, left wheel speed signal data and right wheel speed signal data of the automobile can be acquired from the TBOX; and determining differential signal data according to the difference value of the left wheel speed signal data and the right wheel speed signal data.
According to the structure composition and the load composition of the motor driving system assembly, the torque signal data of the driving motor, the rotating speed signal data of the driving motor, the water temperature signal data of the motor and the differential signal data of the left wheel speed and the right wheel speed are taken as the key durable load signal data of the motor driving system assembly of the automobile, so as to explain the processing method of durable load data of users in the automobile market.
And step S12, dividing each kind of data in the key durable load signal data into F sub-working condition segments respectively according to the time of the last parking vehicle speed, the time of the maximum peak value of the vehicle speed and the time sequence of the next parking time, wherein F is a positive integer.
In the actual processing, the acquired torque signal data of the driving motor, the rotational speed signal data of the driving motor, the water temperature signal data of the driving motor, and the differential signal data of the left and right wheel speeds may be defined as the following expressions:
wherein:
time series data representing a new energy vehicle market user data matrix, e.g. A1The matrix includes the number of T time slices;
differential signal data representing left and right wheel speeds of new energy vehicle market users;
-data values at time i in time series in differential signal data representing left and right wheel speeds.
For the new energy automobile market user data matrix a, the following operations 1 and 2 may be implemented.
[ operation 1 ]
Based on monitored signal data inside the TBOX of the new energy market consumer vehicle, for example: the data matrix A comprises vehicle speed signal data, steering wheel signal data, brake pedal signal data, wheel speed signal data and the like, and the data matrix A is identified to determine whether peak value abnormality, mean value drift and the like exist so as to ensure the validity of the data.
The method specifically comprises the following steps:
step 1, after obtaining key durable load signal data of a target system assembly (a motor driving system assembly is taken as an example for explanation here) of an automobile, before dividing various types of data in the key durable load signal data into F sub-working condition segments respectively, obtaining monitoring signal data of the automobile from an automobile networking system of the automobile, wherein the monitoring signal data comprises speed signal data, steering wheel signal data, brake pedal signal data and wheel speed signal data;
step 2, identifying whether abnormal data exist in the key durable load signal data according to the variation trend of the monitoring signal data;
and 3, when abnormal data exist in the key durable load signal data, correcting the abnormal data, and updating the key durable load signal data according to the corrected abnormal data.
For example, the vehicle speed and the motor speed are in a correlation, and in a normal case, the vehicle speed is high, and the motor speed is also high, so that whether the driving motor speed signal data is abnormal or not can be determined through the variation trend of the vehicle speed, and if the driving motor speed signal data is abnormal, the abnormal data is processed, specifically, the abnormal data can be removed, corrected or supplemented, and a proper processing mode can be adopted according to the actual situation.
[ operation 2 ]
For the critical durable load signal data of the target system assembly (the motor driving system assembly is taken as an example for explanation), a threshold value can be set, and when the critical durable load signal data is smaller than the threshold value, the data does not participate in subsequent calculation, so that the purpose of compressing the data scale is realized, and the subsequent calculation amount is reduced. In the data compression, the data size of the data matrix a should be compressed as much as possible without reducing the critical point data to reduce the amount of subsequent calculation. The method can be specifically decomposed into the following steps:
step 1, after updating key endurance load signal data depending on corrected abnormal data, identifying key point data of the key endurance load signal data according to a preset key point data screening condition before dividing various types of data in the key endurance load signal data into F sub-working condition segments respectively;
step 2, acquiring a preset threshold value of a data channel of a weight-off signal of the motor driving system assembly;
and 3, removing the signal data smaller than the preset threshold of the critical durable load signal data channel from the critical durable load signal data on the premise of keeping all the critical point data in the critical durable load signal data to obtain the compressed critical durable load signal data.
The preset key point data filtering conditions may include the following conditions 1 and 2. If the data point in the critical endurance load signal data (i.e., user data matrix A)And if the following two conditions are met, the data is defined as key point data:
wherein:
-data values representing the j-th signal data in the critical endurance load signal data at time instant i in time series,wherein j =1 is represented as drive motor torque signal data, wherein j =2 is represented as drive motor rotational speed signal data, wherein j =3 is represented as motor water temperature signal data, and wherein j =4 is represented as differential signal data of left and right wheel speeds;
、、、-data values of the jth signal data in the critical endurance load signal data at time sequences (i-1), (i + 1), i, e, respectively;
-a data vector representing the j-th signal data in the critical endurance load signal data at time instant i in time series;
-a data vector representing the j-th signal data in the critical endurance load signal data at time instance e in time series;
Screening key point data in the key durable load signal data according to the two conditions, removing signal data smaller than a preset threshold value of a key important signal data channel from the key durable load signal data on the premise of keeping all key point data in the key durable load signal data to obtain compressed key durable load signal data, and finally obtaining a compressed new energy automobile market user data matrixThe expression is defined as follows:
wherein:
representing compressed driving motor rotating speed signal data of new energy automobile market users;
the compressed motor water temperature signal data of the new energy automobile market user are represented;
differential signal data representing left and right wheel speeds of the compressed new energy automobile market users.
According to the variation trend of the vehicle speed signal data V, namely from the time close to the parking vehicle speed (for example, the time when the vehicle speed is 0) to the time when the next vehicle speed is maximum to the time close to the parking vehicle speed (for example, the time when the vehicle speed is 0), the data matrixDividing the operation condition into F sub-operation condition segments, and defining an expression as follows:
wherein:
f represents the total number of the sub-working conditions of the new energy automobile market user data matrix;
when data representing the g-th segment of the water temperature signal data of the motorAn order vector;
-a time sequence vector of the g-th piece of differential signal data representing left and right wheel speeds;
-a value of the h data of the g segment of differential signal data representing left and right wheel speeds;
And step S13, clustering the F sub-working condition fragments to obtain K types of target working conditions, wherein the K types of target working conditions are used for carrying out an endurance test on the automobile.
Step S13 can be specifically decomposed into the following steps:
step 1, determining a mean vector and a covariance matrix of each sub-working condition segment in F sub-working condition segments;
step 2, randomly selecting K sub-working condition segments from the F sub-working condition segments as the central working condition of the K-type target working condition;
step 3, determining the dispersion distance between each non-central working condition and each central working condition according to the mean vector and the covariance matrix of each non-central working condition fragment in the F sub-working condition fragments and the mean vector and the covariance matrix of each central working condition in the K central working conditions;
step 4, dividing each non-central working condition into data sets of K types of target working conditions according to the dispersion distance between each non-central working condition and each central working condition to obtain K data sets;
step 5, aiming at each data set, connecting the sub-working condition segments in the data set into new data segments according to the time sequence, determining the mean vector and covariance matrix of the new data segments, and taking the mean vector and covariance matrix of the new data segments as the mean vector and covariance matrix after the central working condition corresponding to the data set is updated;
and 6, repeating the steps 3-5 aiming at the updated mean vector and covariance matrix of each central working condition until the variation amplitude of the mean vector and covariance matrix of each data set in the K data sets is smaller than a preset amplitude threshold value.
The method for determining the mean vector and the covariance matrix of each of the F sub-regime segments may specifically include:
probability density function for appointing new energy automobile market user data matrix variableThe expression of (a) is as follows:
wherein:
-representing a variable vector, wherein: variables ofData variable representing torque signal of driving motorData variable representing speed signal of driving motorData variable, variable representing motor water temperature signalDifferential signal data variables representing left and right wheel speeds;
the proposal totally has 4 data channels, namely torque signal data of a driving motor, rotating speed signal data of the driving motor, water temperature signal data of the motor and differential signal data of left and right wheel speeds, so that the value is 4;
Data matrix for the g-th segment of the F sub-condition segmentsPerforming a probability density functionSolving, i.e. solving the data matrixCorresponding mean vectorAnd covariance matrixThe corresponding solving expression is as follows:
Iterate until、、If the variation of the threshold value is smaller than the preset threshold value or the maximum iteration number is reached, the iteration is stopped.
Wherein:
the sum of the elements on the main diagonal (diagonal from top left to bottom right) of the solution matrix is represented;
-representation matrixAnd matrixIs a Hadamard product, which is a type of operation of a matrix if A = (a =)ij) And B = (B)ij) Are two matrices of the same order, if cij=aij×bijThen, the matrix C = (C)ij) The Hadamard product or base product of A and B;
the 1-norm representing the solution matrix, for example: matrix A, the 1-norm of matrix A being represented as,I.e. the maximum of the sum of the absolute values of all matrix column vectors;
-representing the F-norm of the solution matrix, the F-norm of the matrix being the number of the roots after summing the squares of each element in a matrix;
Through the steps, the market user data matrix can be obtainedThe mean vector and covariance matrix corresponding to the probability density function of any segment data, for example: g-th fragment data matrixFunction of probability densityCorresponding mean vectorAnd covariance matrixThereby making a needleClustering the sub-working conditions of the new energy automobile market user data matrix, wherein the specific clustering process is as follows:
according to the foregoing, the user data matrix for the new energy automobile marketData matrixDividing the operation condition into F sub-operation condition segments, and defining an expression as follows:
and randomly selecting K sub-working condition segments from the F sub-working condition segments, and taking the K sub-working condition segments as a tentative central working condition of the K target working conditions, wherein the K target working conditions can be determined according to actual experience of the project and can also be set according to the project requirements. Within a reasonable range, the larger the K is, the more the working condition types are, and the larger the calculation amount is. For example, F is 10000, K is 10, 10000 sub-operating condition segments are respectively marked as N1, N2, …, N999, and N10000, 10 sub-operating condition segments are randomly selected from the 10000 sub-operating condition segments, for example, N2, N9, N81, N350, N450, N600, N750, N850, N950, and N999 are selected, N2 is taken as a central operating condition of a first target operating condition, N9 is taken as a central operating condition of a second target operating condition, and so on. In general, the greater the difference between F and K, the more obvious the advantage of the solution of the present embodiment will be, and the present embodiment is suitable for durable data processing with F being ten thousand.
And recording other working conditions except the selected K central working conditions in the F sub-working condition segments as non-central working conditions (F-K non-central working conditions), and determining the dispersion distance between the non-central working conditions and each central working condition according to each non-central working condition.
Record any off-center operating conditions asWill renThe operating conditions of the center are recordedThe corresponding dispersion distance is recorded asThe expression for solving the dispersion distance is as follows:
wherein:
-off-centre segments representing market user data matricesCentral operating mode of user data matrixThe dispersion distance between;
And classifying the non-central working conditions according to the dispersion distance between each non-central working condition and each central working condition, and dividing the non-central working conditions into data sets corresponding to each central working condition. If the dispersion distance between a certain non-center working condition and a certain center working condition in each center working condition is the minimum, classifying the non-center working condition into the center working condition with the minimum dispersion distance.
And completing a round of classification according to the rule.
And according to the data set corresponding to each central working condition, re-determining the mean vector and the covariance matrix corresponding to each data set according to the provided calculation mode of the mean vector and the covariance matrix, and taking the re-determined mean vector and covariance matrix as the mean vector and the covariance matrix of the central working condition corresponding to the data set.
And repeating the steps 3-6 according to the updated mean vector and covariance matrix, determining the dispersion distance between the non-central working condition and each central working condition aiming at each non-central working condition (F-K non-central working conditions), namely determining the mean vector and covariance matrix corresponding to the non-central working condition and the dispersion distance between the mean vector and covariance matrix updated by each central working condition, classifying the non-central working conditions according to the dispersion distances until the variation amplitude of the mean vector and covariance matrix in each obtained data set accords with a preset condition (namely is smaller than a preset amplitude threshold), and then terminating the operation of the clustering algorithm.
Each finally obtained data set (particularly K-type data sets) represents K target working conditions, the data sets can be used as typical working conditions to be input into a whole vehicle endurance test and a bench endurance test, and when the vehicle is subsequently subjected to endurance test verification, data corresponding to the K target working conditions can be input into the test, so that the actual use working conditions of users are considered in the endurance test, and the comprehensiveness and the verification accuracy of the vehicle endurance test are improved.
The embodiment provides a method for processing automobile endurance load data of market users, which comprises the steps of firstly defining key endurance load signals of new energy automobile market user data (in the embodiment, the selection and the basis of the endurance load signals are described in detail by taking the motor driving system assembly of a new energy automobile as an example), then defining sub-working condition segments of the market user endurance load signals (in the proposal, the algorithm for compressing and cutting the market user endurance load data into sub-working conditions is described in detail by taking the motor driving system assembly of the new energy automobile as an example), finally, carrying out clustering operation on the sub-working condition segments of the market user endurance load data, specifically, taking the motor driving system assembly of the new energy automobile as an example, describing in detail a mean vector and a covariance matrix of a probability density function for solving the market user endurance load data based on a multi-step iteration method, calculating dispersion distances from different sub-working conditions to a center working condition based on the mean vector and the covariance matrix, and performing multi-step iteration based on the dispersion distance so as to cluster to generate a market user endurance load data sub-working condition segment set, wherein the obtained sub-working condition segment set can be used for guiding the formulation of the finished automobile and bench endurance test specifications of the automobile.
The embodiment directly analyzes the data based on the automobile user endurance load in the TBOX, further summarizes the sub-working condition set of the data of the automobile endurance load, and can be applied to guiding the formulation of the whole automobile and bench endurance test specifications. The embodiment strongly associates the durability test verification of the automobile with the use working condition of an automobile user, so that the optimal balance of the whole automobile cost and the whole automobile safety and reliability is realized on the design source. The scheme provided by the embodiment has strong application expansion and can be applied to determination of the sub-working conditions of other subsystems except the motor driving system assembly of the new energy automobile.
Based on the same inventive concept, the present embodiment provides a durable loading data processing device of a market user's automobile as shown in fig. 2, the device comprising:
a key endurance load signal data acquisition module 21, configured to acquire key endurance load signal data of a target system assembly of an automobile;
the sub-working condition segment dividing module 22 is configured to divide each kind of data in the key durable load signal data into F sub-working condition segments according to the time sequence from the last parking vehicle speed time, the maximum peak vehicle speed time, and the time to the next parking time, where F is a positive integer;
and the clustering module 23 is configured to perform clustering operation on the F sub-working condition segments to obtain K types of target working conditions, and the K types of target working conditions are used for performing an endurance test on the vehicle.
Further, the critical endurance load signal data acquisition module 21 is configured to:
when the target system assembly is the motor driving system assembly, key durable load signal data of the motor driving system assembly are obtained, wherein the key durable load signal data comprise driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
Further, the critical endurance load signal data obtaining module 21 is specifically configured to:
acquiring left wheel speed signal data and right wheel speed signal data of an automobile;
and determining differential signal data according to the difference value of the left wheel speed signal data and the right wheel speed signal data.
Further, the apparatus further comprises:
the monitoring signal data acquisition module is used for acquiring monitoring signal data of the automobile from an automobile networking system of the automobile after acquiring key durable load signal data of a target system assembly of the automobile and before dividing various data in the key durable load signal data into F sub-working condition fragments respectively, wherein the monitoring signal data comprises automobile speed signal data, steering wheel signal data, brake pedal signal data and wheel speed signal data;
the abnormal data identification module is used for identifying whether abnormal data exist in the key durable load signal data according to the change trend of the monitoring signal data;
and the abnormal data correction module is used for correcting the abnormal data when the abnormal data exists in the key durable load signal data and updating the key durable load signal data depending on the corrected abnormal data.
Further, the apparatus further comprises:
the key point data identification module is used for identifying key point data of the key durable load signal data according to preset key point data screening conditions before dividing various types of data in the key durable load signal data into F sub-working condition segments respectively after the key durable load signal data is updated depending on the corrected abnormal data;
the system comprises a preset threshold value acquisition module of a heavy signal data channel, a data acquisition module and a data acquisition module, wherein the preset threshold value acquisition module is used for acquiring the preset threshold value of the heavy signal data channel of a target system assembly;
and the compression module is used for removing the signal data smaller than the preset threshold of the critical durable load signal data channel from the critical durable load signal data on the premise of reserving all the critical point data in the critical durable load signal data to obtain the compressed critical durable load signal data.
Further, the clustering module 23 is specifically configured to perform:
step 1, determining a mean vector and a covariance matrix of each sub-working condition segment in F sub-working condition segments;
step 2, randomly selecting K sub-working condition segments from the F sub-working condition segments as the central working condition of the K-type target working condition;
step 3, determining the dispersion distance between each non-central working condition and each central working condition according to the mean vector and the covariance matrix of each non-central working condition fragment in the F sub-working condition fragments and the mean vector and the covariance matrix of each central working condition in the K central working conditions;
step 4, dividing each non-central working condition into data sets of K types of target working conditions according to the dispersion distance between each non-central working condition and each central working condition to obtain K data sets;
step 5, aiming at each data set, connecting the sub-working condition segments in the data set into new data segments according to the time sequence, determining the mean vector and covariance matrix of the new data segments, and taking the mean vector and covariance matrix of the new data segments as the mean vector and covariance matrix after the central working condition corresponding to the data set is updated;
and 6, repeating the steps 3-5 aiming at the updated mean vector and covariance matrix of each central working condition until the variation amplitude of the mean vector and covariance matrix of each data set in the K data sets is smaller than a preset amplitude threshold value.
Based on the same inventive concept, the present embodiment provides an electronic device as shown in fig. 3, including:
a processor 31;
a memory 32 for storing instructions executable by the processor 31;
wherein the processor 31 is configured to execute to implement a market user's automobile endurance load data processing method as provided above.
Based on the same inventive concept, the present embodiment provides a non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor 31 of an electronic device, so that the electronic device can perform a method of implementing the automobile endurance load data processing of one market user as provided above.
Since the electronic device described in this embodiment is an electronic device used for implementing the method for processing information in this embodiment, a person skilled in the art can understand the specific implementation manner of the electronic device of this embodiment and various variations thereof based on the method for processing information described in this embodiment, and therefore, how to implement the method in this embodiment by the electronic device is not described in detail here. Electronic devices used by those skilled in the art to implement the method for processing information in the embodiments of the present application are all within the scope of the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for processing automobile endurance load data of market users, the method comprising:
acquiring key durable load signal data of a target system assembly of an automobile;
dividing various types of data in the key durable load signal data into F sub-working condition segments respectively according to the time sequence of the last parking vehicle speed, the maximum peak value of the vehicle speed and the time sequence of the next parking time, wherein F is a positive integer;
and clustering the F sub-working condition fragments to obtain K types of target working conditions, wherein the K types of target working conditions are used for carrying out an endurance test on the automobile.
2. The method of claim 1, wherein said obtaining key endurance load signal data for a target system assembly of an automobile when the target system assembly is a motor drive system assembly comprises:
obtaining key durable load signal data of the motor driving system assembly, wherein the key durable load signal data comprises driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
3. The method of claim 2, wherein said obtaining differential signal data for said electric motor drive system assembly comprises:
acquiring left wheel speed signal data and right wheel speed signal data of an automobile;
and determining the differential signal data according to the difference value of the left wheel speed signal data and the right wheel speed signal data.
4. The method of claim 1, wherein after obtaining the key endurance load signal data for the target system assembly of the automobile, before dividing each category of data in the key endurance load signal data into F sub-operating condition segments, respectively, the method further comprises:
acquiring monitoring signal data of an automobile from an internet of vehicles system of the automobile, wherein the monitoring signal data comprises speed signal data, steering wheel signal data, brake pedal signal data and wheel speed signal data;
identifying whether abnormal data exist in the key durable load signal data according to the variation trend of the monitoring signal data;
and when abnormal data exists in the key durable load signal data, correcting the abnormal data, and updating the key durable load signal data according to the corrected abnormal data.
5. The method of claim 4, wherein after updating the critical endurance load signal data in dependence on the corrected anomaly data, before dividing each category of data in the critical endurance load signal data into F sub-operating condition segments, respectively, the method further comprises:
identifying key point data of the key durable load signal data according to a preset key point data screening condition;
acquiring a preset threshold value of a data channel of a weight-off signal of the target system assembly;
and on the premise of reserving all key point data in the key durable load signal data, removing the signal data smaller than the preset threshold value of the key durable load signal data channel from the key durable load signal data to obtain the compressed key durable load signal data.
6. The method of claim 1, wherein the clustering the F sub-condition segments to obtain K types of target conditions comprises:
step 1, determining a mean vector and a covariance matrix of each sub-working condition segment in the F sub-working condition segments;
step 2, randomly selecting K sub-working condition segments from the F sub-working condition segments as central working conditions of K types of target working conditions;
step 3, determining the dispersion distance between each non-central working condition and each central working condition according to the mean vector and the covariance matrix of each non-central working condition fragment in the F sub-working condition fragments and the mean vector and the covariance matrix of each central working condition in the K central working conditions;
step 4, dividing each non-central working condition into data sets of K types of target working conditions according to the dispersion distance between each non-central working condition and each central working condition to obtain K data sets;
step 5, aiming at each data set, connecting the sub-working condition segments in the data set into new data segments according to the time sequence, determining the mean vector and covariance matrix of the new data segments, and taking the mean vector and covariance matrix of the new data segments as the mean vector and covariance matrix after the central working condition corresponding to the data set is updated;
and 6, repeating the steps 3-5 aiming at the updated mean vector and covariance matrix of each central working condition until the variation amplitude of the mean vector and covariance matrix of each data set in the K data sets is smaller than a preset amplitude threshold value.
7. An automotive endurance load data processing apparatus for a market consumer, said apparatus comprising:
the key durable load signal data acquisition module is used for acquiring key durable load signal data of a target system assembly of the automobile;
the sub-working condition segment dividing module is used for dividing various types of data in the key durable load signal data into F sub-working condition segments according to the time of the last parking vehicle speed, the time of the maximum peak value of the vehicle speed and the time sequence from the next parking time, wherein F is a positive integer;
and the clustering module is used for clustering the F sub-working condition fragments to obtain K types of target working conditions, and the K types of target working conditions are used for carrying out an endurance test on the automobile.
8. The apparatus of claim 7, wherein the critical endurance load signal data acquisition module is specifically configured to:
when the target system assembly is a motor driving system assembly, obtaining key durable load signal data of the motor driving system assembly, wherein the key durable load signal data comprises driving motor torque signal data, driving motor rotating speed signal data, motor water temperature signal data and differential signal data.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute to implement a market user's automobile endurance load data processing method as claimed in any one of claims 1 to 6.
10. A non-transitory computer readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform a method of implementing a market user's automobile endurance load data processing as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210566586.2A CN114662620B (en) | 2022-05-24 | 2022-05-24 | Automobile endurance load data processing method and device for market users |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210566586.2A CN114662620B (en) | 2022-05-24 | 2022-05-24 | Automobile endurance load data processing method and device for market users |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114662620A true CN114662620A (en) | 2022-06-24 |
CN114662620B CN114662620B (en) | 2022-10-21 |
Family
ID=82037960
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210566586.2A Active CN114662620B (en) | 2022-05-24 | 2022-05-24 | Automobile endurance load data processing method and device for market users |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114662620B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114841292A (en) * | 2022-07-04 | 2022-08-02 | 岚图汽车科技有限公司 | Method and device for obtaining endurance test load of automobile steering system rack |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108919755A (en) * | 2018-06-11 | 2018-11-30 | 宁波大学 | A kind of distributed fault detection method based on muti-piece Nonlinear and crossing relational model |
CN109615014A (en) * | 2018-12-17 | 2019-04-12 | 清华大学 | A kind of data sorting system and method based on the optimization of KL divergence |
CN111896274A (en) * | 2020-08-14 | 2020-11-06 | 东风汽车集团有限公司 | Method for making endurance test of whole vehicle electric drive assembly of two-drive electric vehicle type |
CN112650063A (en) * | 2020-12-30 | 2021-04-13 | 浙江大学 | Self-adaptive soft measurement method based on semi-supervised incremental Gaussian mixture regression |
CN114136656A (en) * | 2021-11-29 | 2022-03-04 | 中国第一汽车股份有限公司 | Method for constructing motor bench test working condition of pure electric operation automobile |
CN114298184A (en) * | 2021-12-20 | 2022-04-08 | 北京理工大学 | New energy public transport working condition construction method based on machine learning and optimization algorithm |
-
2022
- 2022-05-24 CN CN202210566586.2A patent/CN114662620B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108919755A (en) * | 2018-06-11 | 2018-11-30 | 宁波大学 | A kind of distributed fault detection method based on muti-piece Nonlinear and crossing relational model |
CN109615014A (en) * | 2018-12-17 | 2019-04-12 | 清华大学 | A kind of data sorting system and method based on the optimization of KL divergence |
CN111896274A (en) * | 2020-08-14 | 2020-11-06 | 东风汽车集团有限公司 | Method for making endurance test of whole vehicle electric drive assembly of two-drive electric vehicle type |
CN112650063A (en) * | 2020-12-30 | 2021-04-13 | 浙江大学 | Self-adaptive soft measurement method based on semi-supervised incremental Gaussian mixture regression |
CN114136656A (en) * | 2021-11-29 | 2022-03-04 | 中国第一汽车股份有限公司 | Method for constructing motor bench test working condition of pure electric operation automobile |
CN114298184A (en) * | 2021-12-20 | 2022-04-08 | 北京理工大学 | New energy public transport working condition construction method based on machine learning and optimization algorithm |
Non-Patent Citations (2)
Title |
---|
JIUSUN ZENG 等: "Detecting abnormal situations using the Kullback-leibler divergence", 《RESEARCHGATE.NET》 * |
文政颖等: "一种基于模糊层次聚类分析的大数据挖掘算法", 《河南工程学院学报(自然科学版)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114841292A (en) * | 2022-07-04 | 2022-08-02 | 岚图汽车科技有限公司 | Method and device for obtaining endurance test load of automobile steering system rack |
Also Published As
Publication number | Publication date |
---|---|
CN114662620B (en) | 2022-10-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Okuda et al. | Modeling and analysis of driving behavior based on a probability-weighted ARX model | |
CN114662620B (en) | Automobile endurance load data processing method and device for market users | |
CN109543710B (en) | Model training method and related equipment | |
Cho et al. | CPS approach to checking norm operation of a brake-by-wire system | |
CN111340074B (en) | Driver braking intention identification method based on improved RBF neural network | |
CN115675099A (en) | Pure electric vehicle braking energy recovery method based on driver style recognition | |
CN112016756A (en) | Data prediction method and device | |
Kim et al. | Predictive evaluation of spectrogram-based vehicle sound quality via data augmentation and explainable artificial Intelligence: Image color adjustment with brightness and contrast | |
CN114329921A (en) | Method, device, equipment and medium for evaluating reliability performance of whole vehicle | |
CN113799788A (en) | Method, computer program and device for processing a signal | |
CN111047142B (en) | Automobile scoring method and system based on analytic hierarchy process | |
CN113433931B (en) | Automobile CAN bus key signal analysis method based on characteristic working conditions | |
Apfelbeck et al. | Predicting Subjective Impressions of the Roll Dynamics of Passenger Cars Using Characteristic Values in the Time and Frequency Domains | |
CN114162132B (en) | Driving mode identification method based on subjective and objective evaluation | |
CN115438731A (en) | Fair perception integrated model training method based on mixed sampling | |
CN113919189A (en) | Physical tire model-based whole vehicle road noise analysis method | |
CN110475258B (en) | Reliability evaluation method and system for base station | |
CN115115531A (en) | Image denoising method and device, vehicle and storage medium | |
CN112734203A (en) | Vehicle damage calculation method, device and system based on road surface and storage medium | |
CN115221599A (en) | Chassis abnormal sound diagnosis method and system and automobile | |
Zehelein et al. | Automotive damper defect detection using novelty detection methods | |
US11620817B2 (en) | Hardware-accelerated operation of artificial neural networks | |
Li et al. | Research on Vehicle Risk Rating Based on The Generalized Linear Model | |
CN111126455A (en) | Abrasive particle two-stage identification method based on Lightweight CNN and SVM | |
CN115266152B (en) | Automobile tire lateral force detection method and system based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |