CN114757058A - Automobile time domain load extrapolation method and device based on particle swarm optimization - Google Patents

Automobile time domain load extrapolation method and device based on particle swarm optimization Download PDF

Info

Publication number
CN114757058A
CN114757058A CN202210665472.3A CN202210665472A CN114757058A CN 114757058 A CN114757058 A CN 114757058A CN 202210665472 A CN202210665472 A CN 202210665472A CN 114757058 A CN114757058 A CN 114757058A
Authority
CN
China
Prior art keywords
load signal
signal data
particle
threshold
vehicle
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.)
Pending
Application number
CN202210665472.3A
Other languages
Chinese (zh)
Inventor
丁鼎
韩广宇
张永仁
卢放
马德慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lantu Automobile Technology Co Ltd
Original Assignee
Lantu Automobile Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lantu Automobile Technology Co Ltd filed Critical Lantu Automobile Technology Co Ltd
Priority to CN202210665472.3A priority Critical patent/CN114757058A/en
Publication of CN114757058A publication Critical patent/CN114757058A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses an automobile time domain load extrapolation method and device based on a particle swarm algorithm, which are applied to the field of vehicle endurance tests, and the method comprises the following steps: collecting load signal data of a vehicle on a public road; establishing a time domain load extrapolation calculation model according to load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function; and solving the super-threshold probability density function by adopting a particle swarm algorithm, and carrying out time-domain load extrapolation according to the solved result of the super-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle. The invention solves the technical problem that the load signal data obtained by the time domain extrapolation method is inaccurate.

Description

Automobile time domain load extrapolation method and device based on particle swarm optimization
Technical Field
The invention belongs to the field of vehicle endurance tests, and particularly relates to an automobile time domain load extrapolation method and device based on a particle swarm algorithm.
Background
The automobile can carry out a large amount of whole automobile endurance road tests in a test yard in the research and development stage. The collection of the load signals of the automobile on the public road is an important input for making a whole automobile endurance road test in a test yard. The design life of the whole automobile is generally 24-30 kilometers, and the load signal acquisition of the automobile on a public road is usually limited by time and cost, so that the load signal of the automobile on the public road can be acquired only by tens of kilometers at most, and the acquired load signal of the automobile on the public road needs to be extrapolated, so that the load signal of the automobile in the whole life cycle can be estimated, and the load signal can be more reasonably applied to making a whole automobile endurance road test specification.
The time domain extrapolation method is to directly extrapolate on a time domain signal, the extreme value of the time domain signal accords with generalized pareto distribution, and the core step of time domain signal extrapolation is to solve the parameter corresponding to the probability density function of the generalized pareto distribution. In the past, parameters for solving the generalized pareto distribution probability density function are often not optimal solutions in a solution space and are not accurate enough, so that load signal data obtained by a time domain extrapolation method are inaccurate.
Disclosure of Invention
In view of the above technical problems in the prior art, the embodiment of the present invention provides an automobile time domain load extrapolation method and apparatus based on a particle swarm algorithm.
In a first aspect, an embodiment of the present invention provides an automobile time-domain load extrapolation method based on a particle swarm algorithm, including:
collecting load signal data of a vehicle on a public road;
establishing a time domain load extrapolation calculation model according to the load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function;
and solving the super-threshold probability density function by adopting a particle swarm algorithm, and carrying out time-domain load extrapolation according to the solved result of the super-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle.
Optionally, the acquiring load signal data of the vehicle on a public road includes:
arranging a wheel center six-component force sensor and a three-way acceleration sensor on the vehicle, arranging a non-contact type transmission shaft torque sensor on a transmission shaft of the vehicle, and arranging a rod force sensor on a suspension rod of the vehicle;
planning the total mileage of the public roads and the driving route of each public road, wherein the mileage of the urban road is in proportion to the mileage of the urban road
Figure 954806DEST_PATH_IMAGE001
The mileage of the expressway is expressed as
Figure 903171DEST_PATH_IMAGE002
The mileage of suburb roads is
Figure 606814DEST_PATH_IMAGE003
The mileage of the national provincial road is in proportion
Figure 171788DEST_PATH_IMAGE004
The mileage of the bad road is
Figure 352233DEST_PATH_IMAGE005
The mileage of the mountain road is
Figure 951842DEST_PATH_IMAGE006
Wherein:
Figure 808808DEST_PATH_IMAGE007
；
during the process that the vehicle runs on the public road, load signal data on the public road are collected in any one of the following modes: the method comprises the following steps that a wheel center six-component sensor arranged on a vehicle acquires wheel center six-component signals, a three-way acceleration sensor adapted to the arrangement on the vehicle acquires wheel center three-way acceleration signals, a non-contact transmission shaft torque sensor arranged on a transmission shaft of the vehicle acquires transmission shaft torque signals, and a rod force sensor arranged on a suspension rod of the vehicle acquires rod force signals;
And checking and cleaning the load signal data on the public road.
Optionally, the method further comprises:
setting a target mileage of the vehicle in a full life cycle;
and determining the multiple N for extrapolating the load signal of the public road according to the target mileage and the total mileage of the vehicles driving on various public roads.
Optionally, the establishing a time-domain load extrapolation calculation model according to the load signal data on the public road includes:
defining the load signal data on the public road;
defining a threshold parameter, a shape parameter and a size parameter;
defining the load signal data larger than the threshold parameter as a super threshold;
and establishing the above-threshold probability distribution function and the above-threshold probability density function according to the load signal data of the public road, the threshold parameter, the shape parameter and the size parameter.
Optionally, the solving the above-threshold probability density function by using a particle swarm algorithm includes:
step 1: uniformly and randomly generating particles to form a particle swarm, wherein each particle in the particle swarm comprises a position vector and a velocity vector;
And 2, step: calculating a fitness function of each particle in the particle swarm set;
and 3, step 3: defining an individual optimal particle position and a global optimal particle position;
and 4, step 4: performing mutation operation on all particles in the particle swarm;
and 5: updating a velocity vector and a position vector for the particles;
step 6: judging whether an iteration ending condition is met, if so, terminating iteration, and solving to obtain a position vector solution set of the particles, and if not, skipping to executing the step 2, the step 3, the step 4 and the step 5 until the iteration ending condition is met or the maximum iteration frequency is reached;
and 7: and taking the position of the particle with the maximum threshold parameter in the position vector solution set as a solving result of the probability density function of the load signal exceeding the threshold.
Optionally, the individual optimal particle position is defined as a particle position corresponding to the individual particle when the fitness value is maximum in the iterative process; the global optimal particle position is defined as the particle position corresponding to the maximum fitness value in the iterative process of the particle swarm.
Optionally, the performing time-domain load extrapolation according to the solution result of the above-threshold probability density function to obtain load signal data of the vehicle in the full life cycle includes:
Extracting data exceeding a threshold parameter from the load signal data on the public road;
aiming at the data exceeding the threshold parameter, repeating the operation for N times by adopting the solving result of the probability density function exceeding the threshold, and randomly generating new load signal data for replacing the original data in each operation;
carrying out end-to-end connection on load signal data generated by repeating the operations for N times to obtain an extrapolated N-times time domain load signal;
and taking the time domain load signal of which the extrapolation time is N times as the load signal data of the vehicle in the full life cycle.
In a second aspect, an embodiment of the present invention provides an automobile time-domain load extrapolation apparatus based on a particle swarm optimization, including:
the data acquisition unit is used for acquiring load signal data of the vehicle on a public road;
the model establishing unit is used for establishing a time domain load extrapolation calculation model according to the load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function;
the model solving unit is used for solving the probability density function of the super threshold value by adopting a particle swarm algorithm;
and the extrapolation execution unit is used for carrying out time-domain load extrapolation according to the solving result of the above-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle.
In a third aspect, an embodiment of the present invention provides an electronic device for performing time-domain load extrapolation for an automobile based on a particle swarm optimization, including: a memory, a processor and code stored on the memory and executable on the processor, wherein the processor implements the method according to any of the embodiments of the first aspect when executing the code.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method described in any one of the implementation manners of the first aspect.
One or more technical solutions provided by the embodiments of the present invention at least achieve the following technical effects or advantages:
collecting load signal data of vehicles on a public road through a particle swarm algorithm; establishing a time domain load extrapolation calculation model according to load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function; and solving the super-threshold probability density function by adopting a particle swarm algorithm, and carrying out time-domain load extrapolation according to the solved result of the super-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle. The generalized pareto distribution probability density function obtained by solving through the particle swarm optimization can meet the error precision of collected data, the solving precision is high, and the method is suitable for extrapolation of any time-domain load signal. Therefore, automatic load signal extrapolation is realized, and the obtained load signal data in the full life cycle is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of an automobile time-domain load extrapolation method based on a particle swarm optimization in the embodiment of the invention;
FIG. 2 is a schematic structural diagram of an automobile time-domain load extrapolation apparatus based on a particle swarm optimization in the embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device based on a particle swarm algorithm in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an automobile time-domain load extrapolation method based on a particle swarm optimization, including the following steps S101 to S103:
s101, collecting load signal data of a vehicle on a public road.
In some embodiments, step S101 specifically includes the following sub-steps:
s1011, arranging a wheel center six-component force sensor and a three-way acceleration sensor on the vehicle, arranging a non-contact type transmission shaft torque sensor on a transmission shaft of the vehicle, and arranging a rod force sensor on a suspension rod of the vehicle.
It should be understood that only one or more of the sensors may be arranged depending on the type of load signal data that needs to be collected.
And S1012, planning the total mileage of the public roads and the driving route of each public road.
Wherein, in the total mileage A, the mileage proportion of the urban road is
Figure 595499DEST_PATH_IMAGE008
The mileage of the expressway is expressed as
Figure 579635DEST_PATH_IMAGE009
The mileage of suburb roads is
Figure 33750DEST_PATH_IMAGE010
The mileage of the national provincial road is in proportion
Figure 609088DEST_PATH_IMAGE011
The mileage of the bad road is
Figure 132342DEST_PATH_IMAGE012
The mileage of the mountain road is
Figure 654590DEST_PATH_IMAGE013
And satisfy
Figure 697633DEST_PATH_IMAGE014
。
Specifically, the respective driving route needs to be planned for each of the following public roads: the planning driving route of urban roads, expressway roads, suburb roads, national and provincial roads, bad roads and mountain roads.
S1013, in the process that the vehicle runs on the public road, collecting load signal data on the public road in any one or more of the following modes: the method comprises the following steps that a wheel center six-component sensor arranged on a vehicle acquires wheel center six-component signals, a three-way acceleration sensor adapted to the arrangement on the vehicle acquires wheel center three-way acceleration signals, a non-contact transmission shaft torque sensor arranged on a transmission shaft of the vehicle acquires transmission shaft torque signals, and a rod force sensor arranged on a suspension rod of the vehicle acquires rod force signals;
and S1014, checking and cleaning the collected load signal data on the public road.
Specifically, the collected load signals on the public roads need to be subjected to data inspection and cleaning such as data validity check, deburring and drifting.
Further, in step S101, the method further includes:
setting a target mileage of the vehicle in a full life cycle; determining a multiple N for extrapolating the load signal on the public road according to the target mileage and a total mileage traveled by the vehicle on the plurality of public roads.
Setting the target mileage of the vehicle in the full life cycle as B, and carrying out extrapolation for the acquired load signal by N times, wherein the expression is as follows:
Figure 647134DEST_PATH_IMAGE015
Wherein:
Figure 923264DEST_PATH_IMAGE016
represents the target mileage of the vehicle over the full life cycle,
Figure 452465DEST_PATH_IMAGE017
represents the aggregate mileage over which the load signal is collected,
Figure 881172DEST_PATH_IMAGE018
the extrapolated multiples are indicated.
S102, establishing a time domain load extrapolation calculation model according to the load signal data of the public road, wherein the time domain load extrapolation calculation model comprises an over-threshold probability distribution function and an over-threshold probability density function.
The collected load signal data may be the wheel center six-component load signal or the wheel center three-way acceleration signal or the transmission shaft torque signal or the rod force signal collected in step S101.
Defining the load signal data on the public road; defining a threshold parameter, a shape parameter and a size parameter; defining the load signal data larger than the threshold parameter as a super threshold; and establishing the above-threshold probability distribution function and the above-threshold probability density function according to the load signal data of the public road, the threshold parameter, the shape parameter and the size parameter.
In particular, the collected load signal data is defined as
Figure 516422DEST_PATH_IMAGE019
Definition of
Figure 499421DEST_PATH_IMAGE020
Defining the absolute value of the collected load signal data to be larger than the data threshold parameter for the data threshold parameter
Figure 363472DEST_PATH_IMAGE020
The load signal data of (2) is an over-threshold value
Figure 646686DEST_PATH_IMAGE021
The expression is as follows:
Figure 734728DEST_PATH_IMAGE022
wherein,
Figure 719870DEST_PATH_IMAGE023
indicating that the threshold is exceeded, i.e. the load signal data having an absolute value greater than the threshold parameter u,
Figure 387612DEST_PATH_IMAGE024
representing the collected load signal data;
Figure 525332DEST_PATH_IMAGE025
indicating a threshold parameter.
Wherein, adoptOver-threshold probability distribution function for aggregated payload signal data
Figure 721958DEST_PATH_IMAGE026
And probability density function
Figure 194397DEST_PATH_IMAGE027
The expression is as follows:
Figure 462567DEST_PATH_IMAGE028
Figure 454794DEST_PATH_IMAGE029
Figure 87901DEST_PATH_IMAGE030
wherein,
Figure 532788DEST_PATH_IMAGE031
representing a super-threshold probability distribution function;
Figure 791600DEST_PATH_IMAGE032
representing a threshold-exceeding probability density function;
Figure 638333DEST_PATH_IMAGE033
load signal data representing a supra-threshold, i.e., an absolute value greater than a threshold parameter u;
Figure 504658DEST_PATH_IMAGE034
-representing the collected load signal data;
Figure 436842DEST_PATH_IMAGE035
representing a threshold parameter;
Figure 250077DEST_PATH_IMAGE036
representing a shape parameter;
Figure 206444DEST_PATH_IMAGE037
the dimensional parameters are indicated.
S103, solving the super-threshold probability density function by adopting a particle swarm algorithm, and carrying out time-domain load extrapolation according to the solved result of the super-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle.
In step S103, the solving the above-threshold probability density function by using a particle swarm algorithm includes:
step 1: uniformly and randomly generating particles to form a particle swarm, wherein each particle in the particle swarm comprises a position vector and a velocity vector;
Specifically, in step 1, uniform random generation is performed
Figure 181353DEST_PATH_IMAGE038
Each particle constitutes a particle swarm assembly:
Figure 600833DEST_PATH_IMAGE039
，
wherein any particle in the particle group set
Figure 952180DEST_PATH_IMAGE040
Position vector of (2)
Figure 570244DEST_PATH_IMAGE041
And velocity vector
Figure 965322DEST_PATH_IMAGE042
The expression is as follows:
Figure 872098DEST_PATH_IMAGE043
Figure 27136DEST_PATH_IMAGE044
Figure 702968DEST_PATH_IMAGE045
Figure 81996DEST_PATH_IMAGE046
Figure 725336DEST_PATH_IMAGE047
Figure 152906DEST_PATH_IMAGE048
Figure 948824DEST_PATH_IMAGE049
Figure 436437DEST_PATH_IMAGE050
Figure 567073DEST_PATH_IMAGE051
wherein:
Figure 860651DEST_PATH_IMAGE052
the total number of particles in the particle group set is expressed, and in order to make the result of the final solution more diverse,
Figure 511075DEST_PATH_IMAGE052
the numerical value of (c) may take a larger value;
Figure 435169DEST_PATH_IMAGE053
represents any one particle in a particle group
Figure 538254DEST_PATH_IMAGE054
A position vector of (a);
Figure 822474DEST_PATH_IMAGE055
represents any one particle in a particle group
Figure 327405DEST_PATH_IMAGE054
A velocity vector of (a);
Figure 422400DEST_PATH_IMAGE056
a first row numerical value, a second row numerical value and a third row numerical value of a position vector of any particle i in the particle swarm;
Figure 12781DEST_PATH_IMAGE057
representing a first row numerical value, a second row numerical value and a third row numerical value of the velocity vector of any particle i in the particle swarm;
Figure 648162DEST_PATH_IMAGE058
a correlation coefficient constant parameter representing a position vector and a velocity vector of the particle;
Figure 522446DEST_PATH_IMAGE059
and
Figure 788342DEST_PATH_IMAGE060
a minimum value and a maximum value constant which represent the j row numerical value of the position vector of the particle swarm; when the particle position vector iteration is subsequently carried out, when the jth row number value of the particle position vector is smaller than the minimum constant or larger than the maximum constant, the minimum constant or the maximum constant is assigned to the jth row number value of the particle position vector;
Figure 866019DEST_PATH_IMAGE061
And
Figure 977195DEST_PATH_IMAGE062
the minimum value and the maximum value constant of the j row of values of the speed vector of the particle swarm set are represented; when the position and speed of the particle are iterated subsequently, when the jth row number of the particle speed vector is smaller than the minimum constant or larger than the maximum constant, assigning the minimum constant or the maximum constant to the jth row number of the particle speed vector;
Figure 705985DEST_PATH_IMAGE063
a threshold parameter representing a super-threshold probability density function corresponding to the position vector of the particle i;
Figure 611624DEST_PATH_IMAGE064
representing a shape parameter of a super-threshold probability density function corresponding to the position vector of the particle i;
Figure 442177DEST_PATH_IMAGE065
and the size parameter represents the over-threshold probability density function corresponding to the position vector of the particle i.
Step 2: and calculating a fitness function of each particle in the particle swarm set. The expression of the fitness function of any particle i is as follows:
Figure 75153DEST_PATH_IMAGE066
and (3) iteration ending conditions:
Figure 409182DEST_PATH_IMAGE067
wherein:
Figure 282460DEST_PATH_IMAGE068
representing load signal data representing a threshold exceeded, i.e. having an absolute value greater than a threshold parameter u;
Figure 578138DEST_PATH_IMAGE069
representing data corresponding to the over-threshold probability density function corresponding to the position vector of the particle i; m represents the number of load signal data;
Figure 296695DEST_PATH_IMAGE070
representing the fitness value of any particle i;
Figure 485231DEST_PATH_IMAGE071
the iteration error constant is indicated.
It should be noted that the rule for uniformly and randomly generating D particles is: the minimum and maximum value intervals for each line of the position vector and the velocity vector of the particle are divided into E segments, and the center of each segment is taken as initial data.
And 3, step 3: defining an individual optimal particle position and a global optimal particle position.
The individual optimal particle position is defined as the particle position corresponding to the individual particle with the maximum fitness value in the iterative process, and the global optimal particle position is defined as the particle position corresponding to the particle swarm with the maximum fitness value in the iterative process.
And 4, step 4: and carrying out mutation operation on all particles in the particle swarm.
Wherein, in step 4, for each particle i in the particle swarm set, a region is respectively and randomly produced
Figure 60569DEST_PATH_IMAGE072
Uniform random number in between
Figure 600135DEST_PATH_IMAGE073
. And carrying out mutation operation on the particles i according to the generated uniform random numbers and the mutation probability.
In the implementation process, the mutation probability
Figure 106071DEST_PATH_IMAGE074
The expression of (a) is as follows:
Figure 414693DEST_PATH_IMAGE075
；
Figure 364194DEST_PATH_IMAGE076
；
Figure 391056DEST_PATH_IMAGE077
；
Figure 248154DEST_PATH_IMAGE078
；
Figure 660549DEST_PATH_IMAGE079
；
wherein:
Figure 46531DEST_PATH_IMAGE080
representing the mutation probability;
Figure 29531DEST_PATH_IMAGE081
is a section
Figure 159161DEST_PATH_IMAGE082
The random number of (2);
Figure 426063DEST_PATH_IMAGE083
and
Figure 717367DEST_PATH_IMAGE084
representing an error constant parameter;
Figure 453242DEST_PATH_IMAGE085
representing an error calculation variable;
Figure 120984DEST_PATH_IMAGE086
representing the average value of the particle swarm fitness value;
Figure 773551DEST_PATH_IMAGE087
representing the fitness value of the particle i;
Figure 235756DEST_PATH_IMAGE088
a fitness value representing the optimal position of each particle i;
Figure 458927DEST_PATH_IMAGE038
representing the number of particles in the particle group set;
Figure 664780DEST_PATH_IMAGE089
a theoretical optimal solution representing a fitness function of the particle;
Figure 47220DEST_PATH_IMAGE090
the representation represents an iterative error constant;
Figure 742644DEST_PATH_IMAGE091
The intermediate calculation variables representing the fitness of the particle are represented.
The mutation operation specifically includes: if it is used
Figure 702378DEST_PATH_IMAGE092
Updating the individual optimal positions of the particles i, and randomly generating a corresponding positive distribution
Figure 180764DEST_PATH_IMAGE093
Random number of (2)
Figure 89814DEST_PATH_IMAGE094
The expression for the individual optimal position of particle i is as follows:
Figure 893822DEST_PATH_IMAGE095
wherein:
Figure 826006DEST_PATH_IMAGE096
j (th) representing the individual optimal position of the position vector of particle i at the k (th) iterationRow data;
Figure 622930DEST_PATH_IMAGE097
representing coincidence with a positive-Taiwan distribution
Figure 386486DEST_PATH_IMAGE098
The random number of (2).
And 5: and updating the velocity vector and the position vector aiming at the particles.
Specifically, the velocity vector and position vector update may be performed for particle i based on the following expression:
Figure 626975DEST_PATH_IMAGE099
Figure 780876DEST_PATH_IMAGE100
Figure 132223DEST_PATH_IMAGE101
Figure 750286DEST_PATH_IMAGE102
Figure 416803DEST_PATH_IMAGE103
Figure 323579DEST_PATH_IMAGE104
wherein:
Figure 947458DEST_PATH_IMAGE105
the value of the jth row of data representing the velocity vector of particle i at the (k + 1) th iteration;
Figure 888869DEST_PATH_IMAGE106
the value of the jth row of data representing the velocity vector of particle i at the kth iteration;
Figure 267898DEST_PATH_IMAGE107
representing the inertial parameters of the kth iteration;
Figure 380079DEST_PATH_IMAGE108
and
Figure 73229DEST_PATH_IMAGE109
the maximum constant parameter and the minimum constant parameter which represent inertia parameters, wherein the maximum value is 0.9, and the minimum value is 0.4;
Figure 56097DEST_PATH_IMAGE110
representing the number of iterations;
Figure 606027DEST_PATH_IMAGE111
a constant parameter representing the maximum number of iterations;
Figure 487396DEST_PATH_IMAGE112
and
Figure 984236DEST_PATH_IMAGE113
representing a learning factor parameter;
Figure 634660DEST_PATH_IMAGE114
and
Figure 542442DEST_PATH_IMAGE115
representing an initial value parameter of a learning factor;
Figure 645527DEST_PATH_IMAGE116
and
Figure 680480DEST_PATH_IMAGE117
a parameter representing a learning factor end value;
Figure 450989DEST_PATH_IMAGE118
A parameter representing a time factor is given by,
Figure 529673DEST_PATH_IMAGE119
and
Figure 385633DEST_PATH_IMAGE120
represent
Figure 224276DEST_PATH_IMAGE121
A random number in between;
Figure 583713DEST_PATH_IMAGE122
j row data representing an individual optimal position of the position vector of the particle i at the kth iteration;
Figure 98877DEST_PATH_IMAGE123
j row data representing the global optimal position of the particle swarm location vector in the kth iteration;
Figure 176555DEST_PATH_IMAGE124
a value of the jth line data representing the position vector of the particle i at the (k + 1) th iteration;
Figure 818889DEST_PATH_IMAGE125
the value of the jth line of data representing the position vector of particle i at the kth iteration.
Step 6: judging whether an iteration ending condition is met, if the iteration ending condition is met, ending the iteration, and solving to obtain a position vector solution set of the particles, and if the iteration ending condition is not met, skipping to execute the step 2, the step 3, the step 4 and the step 5 until the iteration ending condition is met or the maximum iteration times is reached, and stopping the iteration.
The optimal position searched by the particle swarm meets the minimum allowable error of the fitness function or reaches the maximum iteration times
Figure 563991DEST_PATH_IMAGE126
The iteration is ended. To make the final solution result more diverse, the maximum number of iterations
Figure 453318DEST_PATH_IMAGE127
The value of (d) may take a larger value.
Specifically, a position vector solution set of particles is obtained
Figure 752713DEST_PATH_IMAGE128
The expression is as follows:
Figure 182426DEST_PATH_IMAGE129
Figure 250876DEST_PATH_IMAGE130
Figure 858575DEST_PATH_IMAGE131
Figure 910844DEST_PATH_IMAGE132
Figure 161827DEST_PATH_IMAGE133
Wherein:
Figure 615942DEST_PATH_IMAGE134
a set of position vector solutions representing the particles;
Figure 128963DEST_PATH_IMAGE135
represents the position vector solution of particle j;
Figure 668528DEST_PATH_IMAGE136
a first row numerical solution representing a position vector of particle j;
Figure 440044DEST_PATH_IMAGE137
a second row numerical solution representing the position vector of particle j;
Figure 748666DEST_PATH_IMAGE138
a third row numerical solution of a position vector representing particle j;
Figure 963746DEST_PATH_IMAGE139
a threshold parameter of the probability density function which represents the over threshold corresponding to the position vector of the particle j;
Figure 725029DEST_PATH_IMAGE140
the shape parameter of the probability density function which represents the position vector of the particle j and corresponds to the super threshold value;
Figure 300236DEST_PATH_IMAGE141
and a size parameter representing a probability density function of the particle j corresponding to the position vector exceeding the threshold value.
And 7: and taking the position of the particle with the maximum threshold parameter in the position vector solution set as a solving result of the probability density function of the load signal exceeding the threshold.
Taking a set of position vector solutions
Figure 197785DEST_PATH_IMAGE142
The position of the particle at which the threshold parameter is maximum is taken as a parameter of the probability density function that the loading signal exceeds the threshold, and these parameters include: threshold parameter
Figure 318187DEST_PATH_IMAGE143
Shape parameter of
Figure 832345DEST_PATH_IMAGE144
Size parameter of
Figure 945664DEST_PATH_IMAGE145
。
Carrying out time-domain load extrapolation according to the solving result of the above threshold probability density function to obtain load signal data of the vehicle in the whole life cycle, wherein the load signal data comprises the following steps:
extracting data exceeding a threshold parameter from load signal data on a public road; for the data exceeding the threshold parameter, repeating the operation for N times by adopting the solving result of the probability density function exceeding the threshold, and randomly generating new load signal data to replace the original data in each operation; carrying out end-to-end connection on load signal data generated by repeating the operations for N times to obtain an extrapolated N-time domain load signal; and taking the time domain load signal of the extrapolated N times as load signal data of the vehicle in the full life cycle.
In particular, for the acquired load signal data as
Figure 963298DEST_PATH_IMAGE146
Extracting the parameters exceeding the threshold value
Figure 520182DEST_PATH_IMAGE147
The data of (a); for these parameters exceeding the threshold
Figure 256056DEST_PATH_IMAGE148
Using a super-threshold probability density function
Figure 173066DEST_PATH_IMAGE149
Randomly generating data bitsAnd (3) changing original data, repeating the process for N times (N is an extrapolation multiple), and connecting the load signal data generated by repeating the operation for N times end to obtain a time domain load signal extrapolated by N times. Solved super threshold probability density function
Figure 45207DEST_PATH_IMAGE150
The expression is as follows:
Figure 772991DEST_PATH_IMAGE151
Figure 996162DEST_PATH_IMAGE152
wherein:
Figure 451283DEST_PATH_IMAGE153
load signal data representing a threshold exceeded, i.e., greater than a threshold parameter u;
Figure 240248DEST_PATH_IMAGE154
representing the collected load signal data;
Figure 342196DEST_PATH_IMAGE155
representing a threshold parameter;
Figure 787084DEST_PATH_IMAGE156
representing a shape parameter;
Figure 593366DEST_PATH_IMAGE157
the dimensional parameters are indicated.
According to the embodiment of the invention, the particle swarm optimization solving algorithm is applied, so that the solving precision is improved, the solved generalized pareto distribution probability density function can meet the error precision of the acquired data, all solution sets of the solution space are solved, and the problem that the optimal solution in the solution space cannot be obtained by solving the threshold value parameters in the prior art is solved; suitable for extrapolation of any time-domain load signal; the embodiment of the invention has higher degree of flow, and can realize the automatic processing work of time-domain load signal extrapolation based on software programming.
Based on the same inventive concept, the embodiment of the invention provides an automobile time domain load extrapolation apparatus based on a particle swarm algorithm, and as shown in reference to fig. 2, the apparatus comprises:
the data acquisition unit 201 is used for acquiring load signal data of the vehicle on a public road;
the model establishing unit 202 is configured to establish a time-domain load extrapolation calculation model according to the load signal data on the public road, where the time-domain load extrapolation calculation model includes a super-threshold probability distribution function and a super-threshold probability density function;
the model solving unit 203 is used for solving the super-threshold probability density function by adopting a particle swarm algorithm;
and the extrapolation execution unit 204 is configured to perform time-domain load extrapolation according to a solution result of the above-threshold probability density function, so as to obtain load signal data of the vehicle in a full life cycle.
In some embodiments, the data acquisition unit 201 includes:
an arrangement subunit for arranging a wheel center six-component force sensor and a three-way acceleration sensor on the vehicle, a non-contact transmission shaft torque sensor on a transmission shaft of the vehicle, and a rod force sensor on a suspension rod of the vehicle;
A planning subunit for planning the total mileage on the public roads and the driving route on each public road, wherein the mileage of the urban road is in proportion to the mileage of the urban road
Figure 954946DEST_PATH_IMAGE158
The mileage of the expressway is expressed as
Figure 758954DEST_PATH_IMAGE159
The mileage of suburb roads is
Figure 956717DEST_PATH_IMAGE160
Of national and provincial roadsMileage is in proportion
Figure 504373DEST_PATH_IMAGE161
The mileage of the bad road is
Figure 454880DEST_PATH_IMAGE162
The mileage of the mountain road is
Figure 429789DEST_PATH_IMAGE163
Wherein:
Figure 911586DEST_PATH_IMAGE164
；
the collecting subunit is used for collecting load signal data on the public road in any one of the following modes in the process that the vehicle runs on the public road: the method comprises the following steps that a wheel center six-component force sensor arranged on a vehicle acquires wheel center six-component force signals, a three-way acceleration sensor adapted to the arrangement on the vehicle acquires wheel center three-way acceleration signals, a non-contact transmission shaft torque sensor arranged on a transmission shaft of the vehicle acquires transmission shaft torque signals, and a rod force sensor arranged on a suspension rod of the vehicle acquires rod force signals;
and the processing subunit is used for checking and cleaning the load signal data on the public road.
In some embodiments, the data acquisition unit 201 includes:
The setting subunit is used for setting a target mileage of the vehicle in a full life cycle;
and the multiple determining subunit is used for determining the multiple N for extrapolating the load signals on the public roads according to the target mileage and the total mileage of the vehicles driving on various public roads.
In some embodiments, the model establishing unit 202 is specifically configured to: defining the load signal data on the public road; defining a threshold parameter, a shape parameter and a size parameter; defining the load signal data larger than the threshold parameter as a super threshold; and establishing the above-threshold probability distribution function and the above-threshold probability density function according to the load signal data of the public road, the threshold parameter, the shape parameter and the size parameter.
In some embodiments, the model solving unit 203 is specifically configured to perform the following steps 1 to 7:
step 1: uniformly and randomly generating particles to form a particle swarm, wherein each particle in the particle swarm comprises a position vector and a velocity vector;
step 2: calculating a fitness function of each particle in the particle swarm set;
and step 3: defining an individual optimal particle position and a global optimal particle position;
And 4, step 4: performing mutation operation on all particles in the particle swarm;
and 5: updating a velocity vector and a position vector for the particles;
and 6: judging whether an iteration ending condition is met or not, if so, terminating iteration, solving to obtain a position vector solution set of the particles, and if not, skipping to execute the step 2, the step 3, the step 4 and the step 5 until the iteration ending condition is met or the maximum iteration times is reached.
And 7: and taking the position of the particle with the maximum threshold value parameter in the position vector solution set as a solving result of the probability density function of the load signal exceeding the threshold value.
In some embodiments, the individual optimal particle position is defined as a particle position corresponding to an individual particle when the fitness value is maximum in the iterative process; the global optimal particle position is defined as the particle position corresponding to the maximum fitness value in the iterative process of the particle swarm.
In some embodiments, the extrapolation execution unit 204 is specifically configured to: extracting data exceeding a threshold parameter from the load signal data on the public road; for the data exceeding the threshold parameter, repeating the operation for N times by adopting the solving result of the probability density function exceeding the threshold, and randomly generating new load signal data to replace the original data in each operation; carrying out end-to-end connection on load signal data generated by repeating the operations for N times to obtain an extrapolated N-time domain load signal; and taking the time domain load signal of the extrapolated N times as load signal data of the vehicle in the full life cycle.
The particle swarm algorithm-based automobile time-domain load extrapolation device is a device for executing the particle swarm algorithm-based automobile time-domain load extrapolation method, and more implementation details of the device can refer to the particle swarm algorithm-based automobile time-domain load extrapolation method embodiment, which is not described herein again.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device for performing automobile time-domain load extrapolation based on a particle swarm algorithm, as shown in fig. 3, the electronic device includes a memory 304, a processor 302, and a computer program stored in the memory 304 and operable on the processor 302, and when the processor 302 executes the program, the foregoing automobile time-domain load extrapolation method based on the particle swarm algorithm is implemented.
Where, in fig. 3, the bus 300 may include any number of interconnected buses and bridges, the bus 300 links together various circuits including one or more processors, represented by a processor 302, and memory, represented by a memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be one and the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Based on the same inventive concept, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the foregoing time-domain load extrapolation method for an automobile based on a particle swarm algorithm is implemented.
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 preferred embodiments and all such alterations and modifications as 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. An automobile time domain load extrapolation method based on a particle swarm algorithm is characterized by comprising the following steps:
collecting load signal data of a vehicle on a public road;
establishing a time domain load extrapolation calculation model according to the load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function;
And solving the super-threshold probability density function by adopting a particle swarm algorithm, and carrying out time-domain load extrapolation according to the solved result of the super-threshold probability density function to obtain load signal data of the vehicle in the whole life cycle.
2. The method of claim 1, wherein collecting load signal data of a vehicle on a public road comprises:
arranging a wheel center six-component force sensor and a three-way acceleration sensor on the vehicle, arranging a non-contact transmission shaft torque sensor on a transmission shaft of the vehicle, and arranging a rod force sensor on a suspension rod of the vehicle;
planning a total mileage for driving on public roads and a driving route on each public road, wherein the mileage of the urban road accounts for the total mileage
Figure 206811DEST_PATH_IMAGE001
The mileage of the expressway is expressed as
Figure 301806DEST_PATH_IMAGE002
The mileage of suburb roads is
Figure 688925DEST_PATH_IMAGE003
The mileage of the national provincial road is in proportion
Figure 527568DEST_PATH_IMAGE004
The mileage of the bad road is
Figure 136272DEST_PATH_IMAGE005
The mileage of the mountain road is
Figure 402169DEST_PATH_IMAGE006
Wherein:
Figure 479846DEST_PATH_IMAGE007
；
during the process that the vehicle runs on the public road, load signal data on the public road are collected in any one of the following modes: the method comprises the following steps that a wheel center six-component force sensor arranged on a vehicle acquires wheel center six-component force signals, a three-way acceleration sensor adapted to the arrangement on the vehicle acquires wheel center three-way acceleration signals, a non-contact transmission shaft torque sensor arranged on a transmission shaft of the vehicle acquires transmission shaft torque signals, and a rod force sensor arranged on a suspension rod of the vehicle acquires rod force signals;
And checking and cleaning the load signal data on the public road.
3. The method of claim 2, further comprising:
setting a target mileage of the vehicle in a full life cycle;
and determining the multiple N for extrapolating the load signals of the public roads according to the target mileage and the total mileage of the vehicles on various public roads.
4. The method of claim 3, wherein said building a time-domain load extrapolation computation model based on said load signal data on the public road comprises:
defining the load signal data on the public road;
defining a threshold parameter, a shape parameter and a size parameter;
defining the load signal data larger than the threshold parameter as a super threshold;
and establishing the above-threshold probability distribution function and the above-threshold probability density function according to the load signal data of the public road, the threshold parameter, the shape parameter and the size parameter.
5. The method of claim 3, wherein solving the above-threshold probability density function using a particle swarm algorithm comprises:
step 1: uniformly and randomly generating particles to form a particle swarm, wherein each particle in the particle swarm comprises a position vector and a velocity vector;
And 2, step: calculating a fitness function of each particle in the particle swarm set;
and 3, step 3: defining an individual optimal particle position and a global optimal particle position;
and 4, step 4: performing mutation operation on all particles in the particle swarm;
and 5: updating a velocity vector and a position vector for the particles;
and 6: judging whether an iteration ending condition is met, if so, terminating iteration, and solving to obtain a position vector solution set of the particles, and if not, skipping to executing the step 2, the step 3, the step 4 and the step 5 until the iteration ending condition is met or the maximum iteration frequency is reached;
and 7: and taking the position of the particle with the maximum threshold parameter in the position vector solution set as a solving result of the probability density function of the load signal exceeding the threshold.
6. The method of claim 5, wherein:
the individual optimal particle position is defined as the corresponding particle position when the fitness value of the individual particle is maximum in the iteration process;
the global optimal particle position is defined as the particle position corresponding to the maximum fitness value in the iterative process of the particle swarm.
7. The method of claim 3, wherein said time-domain load extrapolation from the solution to the above-threshold probability density function to obtain load signal data of the vehicle over a full life cycle comprises:
Extracting data exceeding a threshold parameter from the load signal data on the public road;
aiming at the data exceeding the threshold parameter, repeating the operation for N times by adopting the solving result of the probability density function exceeding the threshold, and randomly generating new load signal data for replacing the original data in each operation;
carrying out end-to-end connection on load signal data generated by repeating the operations for N times to obtain an extrapolated N-times time domain load signal;
and taking the time domain load signal of which the extrapolation time is N times as the load signal data of the vehicle in the full life cycle.
8. The utility model provides an automobile time domain load extrapolation device based on particle swarm algorithm which characterized in that includes:
the data acquisition unit is used for acquiring load signal data of the vehicle on a public road;
the model establishing unit is used for establishing a time domain load extrapolation calculation model according to the load signal data of the public road, wherein the time domain load extrapolation calculation model comprises a super-threshold probability distribution function and a super-threshold probability density function;
the model solving unit is used for solving the probability density function exceeding the threshold value by adopting a particle swarm algorithm;
and the extrapolation execution unit is used for carrying out time-domain load extrapolation according to the solving result of the super-threshold probability density function to obtain load signal data of the vehicle in the full life cycle.
9. An electronic device for carrying out automobile time domain load extrapolation based on a particle swarm algorithm is characterized by comprising the following components: a memory, a processor, and code stored on the memory and executable on the processor, the processor implementing the method of any of claims 1-7 when executing the code.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 7.
CN202210665472.3A 2022-06-14 2022-06-14 Automobile time domain load extrapolation method and device based on particle swarm optimization Pending CN114757058A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210665472.3A CN114757058A (en) 2022-06-14 2022-06-14 Automobile time domain load extrapolation method and device based on particle swarm optimization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210665472.3A CN114757058A (en) 2022-06-14 2022-06-14 Automobile time domain load extrapolation method and device based on particle swarm optimization

Publications (1)

Publication Number Publication Date
CN114757058A true CN114757058A (en) 2022-07-15

Family

ID=82337095

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210665472.3A Pending CN114757058A (en) 2022-06-14 2022-06-14 Automobile time domain load extrapolation method and device based on particle swarm optimization

Country Status (1)

Country Link
CN (1) CN114757058A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933490A (en) * 2015-07-03 2015-09-23 浙江大学 Earth-rock deployment optimization method of earth and rockfill dam engineering considering social vehicle
CN108108532A (en) * 2017-12-06 2018-06-01 华南理工大学 With the method for particle cluster algorithm optimization power electronic circuit
CN113435018A (en) * 2021-06-09 2021-09-24 中国汽车技术研究中心有限公司 Damage calculation method for road load spectrum of automobile user
CN113919047A (en) * 2021-08-23 2022-01-11 中汽研汽车检验中心（天津）有限公司 Complete vehicle test field durability user association modeling solving method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933490A (en) * 2015-07-03 2015-09-23 浙江大学 Earth-rock deployment optimization method of earth and rockfill dam engineering considering social vehicle
CN108108532A (en) * 2017-12-06 2018-06-01 华南理工大学 With the method for particle cluster algorithm optimization power electronic circuit
CN113435018A (en) * 2021-06-09 2021-09-24 中国汽车技术研究中心有限公司 Damage calculation method for road load spectrum of automobile user
CN113919047A (en) * 2021-08-23 2022-01-11 中汽研汽车检验中心（天津）有限公司 Complete vehicle test field durability user association modeling solving method

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
N. HIGASHI等: "Particle Swarm Optimization with Gaussian Mutation", 《PROCEEDINGS OF THE 2003 IEEE SWARM INTELLIGENCE SYMPOSIUM》 *
YAN HUANG等: "Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection", 《IEEE ACCESS》 *
杨小兵: "基于道路载荷的轿车轮毂疲劳寿命研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *
王剑峰: "洪水超定量序列频率分析计算", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *
田维波等: "常用载荷谱外推算法概述", 《南方农机》 *
马国庆等: "学习因子和时间因子随权重调整的粒子群算法", 《计算机应用研究》 *

Similar Documents

Publication Publication Date Title
CN110091751B (en) Electric automobile endurance mileage prediction method, device and medium based on deep learning
CN114323644B (en) Gear box fault diagnosis and signal acquisition method and device and electronic equipment
CN107544290B (en) New energy automobile performance evaluation analysis and optimization system and method
CN110348103B (en) Vehicle damage resistance assessment method based on digital twins
JP6918137B2 (en) Driving behavior evaluation method, device and computer-readable storage medium
US8090560B2 (en) Systems and methods for haul road management based on greenhouse gas emissions
CN109033643B (en) Sensitivity analysis-based automobile operation stability transient performance parameter optimization method
CN102208132B (en) Traffic predicting device, traffic predicting method
CN105527110B (en) The appraisal procedure and device of automobile fuel ecomomy
CN114329921A (en) Method, device, equipment and medium for evaluating reliability performance of whole vehicle
CN118228591A (en) Intelligent automobile standard test scene generation method based on inverse reinforcement learning
CN112765726B (en) Life prediction method and device
Shen et al. Real-time scenario-based stochastic optimal energy management strategy for HEVs
CN114757058A (en) Automobile time domain load extrapolation method and device based on particle swarm optimization
CN117787585A (en) Method and device for predicting number of charging piles driven by data
CN115964800A (en) Method and device for vehicle AEB calibration, electronic equipment and storage medium
CN110481538B (en) Method and device for distributing torque of hybrid vehicle and intelligent networked vehicle system
CN114778141B (en) Method, device and equipment for formulating durability test of automobile electric drive assembly rack
CN113740082B (en) Method and device for converting load of vehicle public road and endurance test load
CN111709160A (en) Method and system for analyzing and optimizing driving dynamic performance based on truck chassis
CN113450565B (en) Method and system for reducing noise of asphalt pavement
CN115688957A (en) Vehicle energy consumption determination method and device, electronic equipment and storage medium
CN113808388A (en) Traffic jam analysis method comprehensively considering operation of cars and public traffic
CN113607392A (en) Spring arm durability test method and device
CN118228555A (en) Fatigue calculation method and device for battery frame of vehicle

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20220715