CN111561567B - Vehicle transmission gear recognition method and computer-readable storage medium - Google Patents

Vehicle transmission gear recognition method and computer-readable storage medium Download PDF

Info

Publication number
CN111561567B
CN111561567B CN201910112634.9A CN201910112634A CN111561567B CN 111561567 B CN111561567 B CN 111561567B CN 201910112634 A CN201910112634 A CN 201910112634A CN 111561567 B CN111561567 B CN 111561567B
Authority
CN
China
Prior art keywords
gear
clutch
sample data
probability
signal
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.)
Active
Application number
CN201910112634.9A
Other languages
Chinese (zh)
Other versions
CN111561567A (en
Inventor
阮志毅
洪志新
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.)
Xiamen Yaxon Networks Co Ltd
Original Assignee
Xiamen Yaxon Networks 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 Xiamen Yaxon Networks Co Ltd filed Critical Xiamen Yaxon Networks Co Ltd
Priority to CN201910112634.9A priority Critical patent/CN111561567B/en
Publication of CN111561567A publication Critical patent/CN111561567A/en
Application granted granted Critical
Publication of CN111561567B publication Critical patent/CN111561567B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16H—GEARING
    • F16H63/00—Control outputs from the control unit to change-speed- or reversing-gearings for conveying rotary motion or to other devices than the final output mechanism
    • F16H63/40—Control outputs from the control unit to change-speed- or reversing-gearings for conveying rotary motion or to other devices than the final output mechanism comprising signals other than signals for actuating the final output mechanisms
    • F16H63/42—Ratio indicator devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16H—GEARING
    • F16H59/00—Control inputs to control units of change-speed-, or reversing-gearings for conveying rotary motion
    • F16H59/36—Inputs being a function of speed
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16H—GEARING
    • F16H59/00—Control inputs to control units of change-speed-, or reversing-gearings for conveying rotary motion
    • F16H59/36—Inputs being a function of speed
    • F16H59/38—Inputs being a function of speed of gearing elements
    • F16H59/40—Output shaft speed
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16H—GEARING
    • F16H59/00—Control inputs to control units of change-speed-, or reversing-gearings for conveying rotary motion
    • F16H59/50—Inputs being a function of the status of the machine, e.g. position of doors or safety belts
    • F16H59/56—Inputs being a function of the status of the machine, e.g. position of doors or safety belts dependent on signals from the main clutch
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16H—GEARING
    • F16H59/00—Control inputs to control units of change-speed-, or reversing-gearings for conveying rotary motion
    • F16H59/36—Inputs being a function of speed
    • F16H2059/366—Engine or motor speed

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Control Of Transmission Device (AREA)

Abstract

The invention discloses a method for identifying a gear of a vehicle gearbox and a storage medium, wherein the method comprises the following steps: pre-marking the operating gear without clutch signal sample data according to the configuration information of the gearbox; calculating prior probability and probability distribution of each gear under the condition of no clutch signal according to the pre-marking result; calculating posterior probability of each gear, and selecting the gear corresponding to the maximum value as a gear identification result of the gearbox under the condition of no clutch signal; pre-marking the operating gear with clutch signal sample data according to a gear identification result under the condition of no clutch signal; calculating probability distribution under half linkage according to the pre-marking result; calculating prior probability of each gear and semi-linkage under the condition of clutch signals; and calculating the posterior probability of each gear and the semi-linkage, and selecting the gear corresponding to the maximum value as the gear recognition result of the gearbox under the condition of clutch signals. The invention can realize simple, efficient, accurate and reliable identification of the operating gears.

Description

Vehicle transmission gear identification method and computer readable storage medium
Technical Field
The invention relates to the technical field of vehicle gear identification, in particular to a vehicle gearbox gear identification method and a computer readable storage medium.
Background
In the prior art, the position of the shift fork shaft of the operating mechanism is detected by physical means such as sensing type, contact type and voltage mutual inductance type, so as to identify gears, such as a multi-gear motor gear identification device with the publication number of CN101783648a and an identification method thereof, a manual transmission gear identification device with the publication number of CN202418544U and a simple motor gear identification device with the publication number of CN202798576U based on the voltage mutual inductance technology. However, this requires additional detecting elements or devices at corresponding positions, which increases the cost of the apparatus.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: a method for identifying the gear of gear box of vehicle features that the data collected by data bus is used to easily, efficiently, accurately and reliably identify the gear of gear box.
In order to solve the technical problems, the invention adopts the technical scheme that: a vehicle transmission gear identification method comprising:
collecting sample data in a preset first time period, wherein the sample data comprises a timestamp, an engine rotating speed, a rotating speed of an output shaft of a gearbox and a trampling state of a clutch pedal;
obtaining sample data of a clutch pedal in a non-treading state to obtain sample data of a non-clutch signal;
pre-marking the operating gear of the clutch-free signal sample data according to gearbox configuration information, wherein the gearbox configuration information comprises the number of gears of a gearbox, the transmission ratio of each non-neutral gear and the engine speed at neutral idle speed;
respectively calculating to obtain a first prior probability of each gear and a first probability distribution of the engine rotating speed of each gear and the rotating speed of an output shaft of the gearbox according to the operation gears pre-marked by the clutch-free signal sample data;
dividing continuously acquired clutch-free signal sample data into the same group according to the timestamp to obtain a plurality of clutch-free signal sample data groups;
respectively calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear and the first probability distribution of each gear, and respectively determining the operating gear of each non-clutch signal sample data set according to the posterior probability;
acquiring sample data of a clutch pedal in a trampling state to obtain sample data of a clutch signal;
acquiring continuous clutch signal sample data within a preset second time period to obtain a plurality of clutch signal sample data sets, and pre-marking the operating gears of the clutch signal sample data sets as the operating gears of the previous clutch signal sample data set;
calculating to obtain the probability distribution of the engine rotating speed in a semi-linkage state and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch signal sample data set;
calculating a second prior probability and a prior probability of a semi-linkage state of each gear according to the multiple sample data groups with the clutch signals and the previous sample data group without the clutch signals;
acquiring a preset number of continuous newly-acquired clutch signal data to obtain a clutch signal data set;
respectively calculating the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state;
according to the second prior probability of each gear, the prior probability of the semi-linkage state and the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state, respectively calculating the posterior probability of the clutch signal data set corresponding to each gear and the semi-linkage state through a Bayes formula;
and marking the operating gear with the clutch signal data set as a gear corresponding to the maximum posterior probability.
The invention also relates to a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps as described above.
The invention has the beneficial effects that: according to the method, through a Bayes analysis method, the operating gears without clutch signal sample data are pre-marked according to configuration information of a gearbox, then according to a pre-marking result, the prior probability of each gear under the condition of no clutch signal and the probability distribution of the engine rotating speed of each gear and the rotating speed of an output shaft of the gearbox are obtained through calculation, then the posterior probability of each gear is calculated according to a Bayes formula, and the gear corresponding to the maximum value of the posterior probability is selected as the gear recognition result of the gearbox under the condition of no clutch signal. Similarly, the operating gear with clutch signal sample data is pre-marked according to a gear identification result of the clutch signal-free sample data through a Bayes analysis method, then probability distribution under a semi-linkage state is calculated according to the pre-marking result, then prior probability of each gear under the condition of clutch signal and prior probability under the semi-linkage state are calculated by combining the clutch signal-free sample data, then posterior probability of each gear and the semi-linkage state is calculated according to a Bayes formula by combining the probability distribution of each gear under the condition of clutch signal, and the gear corresponding to the maximum value of the posterior probability is selected as a gear identification result of the gearbox under the condition of clutch signal.
According to the invention, the gear of the gearbox can be identified and obtained only by means of data which can be directly acquired by a data bus, such as a timestamp, the rotating speed of an engine, the rotating speed of an output shaft of the gearbox and the treading state of a clutch pedal, and the simple, efficient, accurate and reliable identification of the operating gear is realized in a data driving mode.
Drawings
FIG. 1 is a flow chart of a method of identifying a gear position of a transmission of a vehicle according to the present invention;
FIG. 2 is a flowchart of a method for identifying a transmission gear based on clutch-less data according to a first embodiment of the present invention;
FIG. 3 is a two-dimensional scatter plot of engine speed versus transmission output shaft speed for a first embodiment of the present invention;
fig. 4 is a flowchart of a transmission gear identification method based on clutch data according to a first embodiment of the present invention.
Detailed Description
In order to explain the technical contents, the objects and the effects of the present invention in detail, the following description is made in conjunction with the embodiments and the accompanying drawings.
The most key concept of the invention is as follows: and analyzing the sample data of the clutch-free signal and the sample data of the clutch-containing signal in sequence by a Bayesian analysis method.
Referring to fig. 1, a method for identifying a gear position of a transmission of a vehicle includes:
collecting sample data in a preset first time period, wherein the sample data comprises a timestamp, the rotating speed of an engine, the rotating speed of an output shaft of a gearbox and the treading state of a clutch pedal;
obtaining sample data of a clutch pedal in a non-treading state to obtain sample data of a non-clutch signal;
pre-marking the operating gear of the clutch-free signal sample data according to gearbox configuration information, wherein the gearbox configuration information comprises the number of gears of a gearbox, the transmission ratio of each non-neutral gear and the engine speed at neutral idle speed;
respectively calculating to obtain a first prior probability of each gear and a first probability distribution of the engine rotating speed of each gear and the rotating speed of an output shaft of the gearbox according to the operation gears pre-marked by the clutch-free signal sample data;
dividing continuously acquired clutch-free signal sample data into the same group according to the timestamp to obtain a plurality of clutch-free signal sample data groups;
respectively calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear and the first probability distribution of each gear, and respectively determining the operating gear of each non-clutch signal sample data set according to the posterior probability;
acquiring sample data of a clutch pedal in a trampling state to obtain sample data of a clutch signal;
acquiring continuous on-off signal sample data within a preset second time period to obtain a plurality of on-off signal sample data sets, and pre-marking the operating gears of the on-off signal sample data sets as the operating gears of the previous off-off signal sample data set respectively;
calculating to obtain probability distribution of the engine rotating speed in a semi-linkage state and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch signal sample data set;
calculating a second prior probability and a prior probability of a semi-linkage state of each gear according to the multiple sample data sets with the clutch signal and the sample data set without the clutch signal before the sample data sets;
acquiring a preset number of continuous newly-acquired clutch signal data to obtain a clutch signal data set;
respectively calculating the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state;
respectively calculating posterior probabilities of the clutched signal data set corresponding to each gear and the semi-linkage state through a Bayes formula according to the second prior probability of each gear, the prior probability of the semi-linkage state and the likelihood of the clutched signal data set corresponding to each gear and the semi-linkage state;
and marking the operating gear with the clutch signal data set as a gear corresponding to the maximum posterior probability.
From the above description, the beneficial effects of the present invention are: the simple, efficient, accurate and reliable identification of the operating gears can be realized.
Further, the pre-marking the operating gear of the clutch-free signal sample data according to the configuration information of the gearbox specifically comprises:
according to the engine speed during the idle speed of the neutral position, pre-marking the running gear of the no-clutch signal sample data with the engine speed within a preset range as the neutral position;
respectively calculating the ratio of the engine rotating speed of other sample data without clutch signals to the rotating speed of the output shaft of the gearbox, and comparing the ratio with the transmission ratio of each non-neutral gear;
and pre-marking the operating gears of other sample data without clutch signals as gears corresponding to the transmission ratio closest to the ratio of the operating gears.
According to the description, the operation gear of the clutch-free signal sample data is pre-marked according to the configuration information of the gearbox, so that the accuracy of pre-marking is improved, and the accuracy of the subsequent posterior probability calculation is improved.
Further, the step of respectively calculating a first prior probability of each gear and a first probability distribution of the engine speed of each gear and the transmission output shaft speed according to the operation gear pre-marked by the clutch-free signal sample data specifically comprises:
respectively counting the frequency of each gear shifted from other gears according to the operation gears pre-marked by the clutch-free signal sample data to obtain a first prior probability of each gear;
calculating statistics of sample data of the clutch-free signal of each gear respectively, and acquiring a first two-dimensional probability density function of the engine speed and the speed of an output shaft of the gearbox of each gear according to the statistics;
and respectively carrying out discretization and normalization processing on the first two-dimensional probability density function of each gear to obtain a first probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear.
According to the above description, the probability of the sample data of the clutch-free signal appearing in each gear is calculated according to the result of the pre-marking, the probability is used as the prior probability, and the probability of the engine rotating speed in the sample data of the clutch-free signal and the probability of the rotating speed of the output shaft of the gearbox taking different values in each gear are calculated and obtained as the probability distribution.
Further, the step of respectively calculating posterior probabilities of the non-clutch signal sample data sets corresponding to the gears according to the first prior probabilities of the gears and the first probability distribution of the gears, and respectively determining the operating gears of the non-clutch signal sample data sets according to the posterior probabilities specifically includes:
according to the first probability distribution of each gear, respectively acquiring the probability of each non-clutch signal sample data in a non-clutch signal sample data set corresponding to each gear;
multiplying the probability of each non-clutch signal sample data in the non-clutch signal sample data group corresponding to the same gear to obtain the likelihood of the non-clutch signal sample data group corresponding to the same gear;
according to the first prior probability of each gear and the likelihood of the sample data set of the clutchless signal corresponding to each gear, respectively calculating the posterior probability of the sample data set of the clutchless signal corresponding to each gear through a Bayes formula;
and marking the operating gear of the clutch-free signal sample data set as a gear corresponding to the maximum posterior probability.
According to the above description, the posterior probability is obtained through calculation according to the prior probability and the likelihood, that is, the conditional probability of each gear is taken on the premise of the sample data set of the clutch-free signal, and the gear corresponding to the maximum value of the posterior probability is selected as the gear identification result.
Further, the calculating, according to the first prior probability of each gear and the first probability distribution of each gear, the posterior probability of each gear corresponding to each non-clutch signal sample data set, and determining, according to the posterior probability, the operating gear of each non-clutch signal sample data set, further includes:
and updating the first prior probability of each gear and the first probability distribution of each gear according to the operating gears of the clutch-free signal sample data set.
From the above description, by updating the prior probability and the probability distribution, the accuracy of the subsequent identification is improved.
Further, the probability distribution of the engine speed in the semi-linkage state and the transmission output shaft speed calculated according to the operation gear pre-marked by the clutch signal sample data set is specifically as follows:
respectively calculating statistics of sample data of the clutch signal of each gear, and acquiring a second two-dimensional probability density function of the engine speed and the speed of the output shaft of the gearbox of each gear according to the statistics;
discretizing and normalizing the second two-dimensional probability density function of each gear respectively to obtain a second probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear;
respectively calculating the occupation ratios of the clutch signal sample data corresponding to the gears according to the operation gears pre-marked by the clutch signal sample data sets and the number of the sample data in the operation gears;
and taking the ratio as a weight, and carrying out weighted summation on the second probability distribution of each gear to obtain the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in a semi-linkage state.
According to the description, the second probability distribution of the semi-linkage state after each gear is obtained, and then the weighted summation is carried out according to the proportion, so that the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in the semi-linkage state is obtained.
Further, the calculating a second prior probability and a prior probability of the semi-linkage state of each gear according to the multiple sample data sets of the clutched signal and the sample data set of the previous clutchless signal specifically includes:
respectively acquiring a previous non-clutch signal sample data set of the multiple sample data sets with clutch signals, and calculating the total number of sample data corresponding to each gear and the total number of sample data of the non-clutch signals according to the operating gear of the previous non-clutch signal sample data set and the number of sample data in the previous non-clutch signal sample data set;
calculating the total number of the sample data of the clutch signals according to the sample data groups of the clutch signals;
adding the total number of the sample data of the clutch-free signal and the total number of the sample data of the clutch signal to obtain a first total number;
dividing the total number of sample data corresponding to each gear by the first total number to obtain a second prior probability of each gear;
and dividing the total number of the sample data of the clutch signal by the first total number to obtain the prior probability of the semi-linkage state.
According to the above description, the non-clutch signal sample data corresponding to each gear is used as data in each gear, and the clutch signal sample data set with short start-end time difference is used as data in the semi-linkage state, so that the probability of occurrence of each gear and the semi-linkage state is calculated.
Further, the calculating, according to the first probability distribution of each gear and the probability distribution of the semi-linkage state, the likelihood that the clutch signal data set corresponds to each gear and the semi-linkage state specifically includes:
respectively acquiring the probability of each clutch signal data in the clutch signal data group corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state;
multiplying the probability that each clutch signal data in the clutch signal data group corresponds to the same gear to obtain the likelihood that the clutch signal data group corresponds to the same gear;
and multiplying the probability of the semi-linkage state corresponding to each clutch signal data in the clutch signal data group to obtain the likelihood of the semi-linkage state corresponding to the clutch signal data group.
Further, the step of marking the operating gear of the data set with the clutch signal as the gear corresponding to the maximum posterior probability specifically includes:
judging whether the maximum value of the posterior probability corresponds to a semi-linkage state or not;
if not, marking the operating gear with the clutch signal data set as a gear corresponding to the maximum value of the posterior probability;
and if so, marking the operating gear of the clutch signal data group as the operating gear of the clutch signal data group in the first non-semi-linkage state after the clutch signal data group.
As can be seen from the above description, when the maximum posterior probability value corresponds to the semi-linkage state, the operating gear of the clutch signal data set in the next non-semi-linkage state (i.e., the newly acquired clutch signal-free data set or clutch signal-available data set in the non-semi-linkage state) is acquired and used as the gear identification result of the clutch signal-available data set.
Further, after the step of marking the operating gear of the clutch signal data set as the gear corresponding to the maximum a posteriori probability, the method further comprises the following steps:
and updating the second prior probability of each gear, the prior probability of the semi-linkage state, the second probability distribution of each gear and the probability distribution of the semi-linkage state according to the operating gears with the clutch signal data set.
From the above description, the accuracy of the subsequent identification is improved by updating the prior probability and the probability distribution.
Further, after the posterior probabilities of the clutched signal data sets corresponding to the gears and the semi-linkage states are respectively calculated through a bayesian formula, the method further includes:
if the maximum value of the posterior probability corresponds to a semi-linkage state, judging that the clutch state is a semi-linkage state;
if the gear corresponding to the maximum value of the posterior probability is a neutral gear, judging that the clutch state is an equivalent complete separation state;
if the gear corresponding to the maximum value of the posterior probability is not neutral, the clutch state is determined to be the almost complete engagement state.
From the above description, it can be seen that the state of the clutch in the presence of the clutch signal can also be identified.
The invention also proposes a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps as described above.
Example one
Referring to fig. 2-4, a first embodiment of the present invention is: a method for recognizing the gear of speed variator of vehicle features that the data directly collected by data bus is only used to recognize the gear of speed variator.
The method analyzes clutch-free data (sample data of the clutch pedal in a non-treading state) and clutch-having data (sample data of the clutch pedal in a treading state) respectively.
As shown in fig. 2, the method for identifying the gear position of the gearbox based on clutch-free data comprises the following steps:
s101: collecting sample data in a preset first time period, wherein the sample data comprises a timestamp t and an engine rotating speed omega e Speed omega of output shaft of speed changing box t And a clutch pedal depressed state c; that is, sample data of a period of time is continuously acquired through a data bus (such as a CAN bus) according to a preset acquisition frequency (such as 1 Hz), and the ith sample data CAN be expressed as (t) i ，ω e,i ，ω t,i ，c i ) Or may be represented directly as (ω) e,i ，ω t,i )。
S102: and obtaining sample data of the clutch pedal in a non-treading state to obtain sample data of a non-clutch signal.
S103: pre-marking the operating gear of the clutch-free signal sample data according to gearbox configuration information, wherein the gearbox configuration information comprises the number of gears of a gearbox, the transmission ratio of each non-neutral gear and the engine speed at neutral idle speed;neutral idle, as used herein, refers to a transmission gear that is neutral and an accelerator pedal is in a fully released position, i.e., no accelerator is applied. The transmission configuration information is pre-known, where in this embodiment non-neutral refers to forward, with s 0 Representing the gear in which the gearbox is operating without a clutch signal, having n +1 different values, i.e. s 0 =0,1, …, n for neutral, first gear, … …, n gear, respectively.
For a transmission operating range, when the transmission is not neutral, the ratio of the input shaft speed to the output shaft speed of the transmission is the transmission ratio of the range, or fluctuates within a small range around the transmission ratio; in the neutral state, the engine speed is maintained within a certain idling range with a high probability although the ratio of the engine speeds is not fixed.
Therefore, the operating range without the clutch signal sample data in which the engine speed is within the preset range is pre-marked as neutral according to the engine speed at the time of neutral. The preset range can be obtained according to the corresponding relationship between the rotation speed of the output shaft of the gearbox and the rotation speed of the transmitter, as shown in a two-dimensional scatter diagram in fig. 3, it can be seen from fig. 3 that there are approximately 5 inclined straight lines and a straight line parallel to the horizontal axis, wherein the 5 inclined straight lines correspond to the corresponding relationship between the rotation speed of the output shaft of the gearbox and the rotation speed of the transmitter when 5 non-neutral gears are provided, the straight line parallel to the horizontal axis corresponds to the corresponding relationship between the rotation speed of the output shaft of the gearbox and the rotation speed of the transmitter when the gearbox is at neutral idle speed, and it can be seen from fig. 3 that the rotation speed of the engine is 750rpm when the engine is at neutral idle speed, further, the rotation speed is within the range of 700-800rpm, therefore, the preset range can be set to 700-800rpm, that is, and the operation gear of the no-clutch signal sample data with the rotation speed of the engine within the range of 700-800rpm is marked as neutral position.
Then respectively calculating the ratio of the engine rotating speed of other sample data without clutch signals to the rotating speed of the output shaft of the gearbox, and comparing the ratio with the transmission ratio of each non-neutral gear; and pre-marking the operating gears of other sample data without clutch signals as gears corresponding to the transmission ratio closest to the ratio of the operating gears. For other non-clutch signal sample data which are not pre-marked, the ratio of the engine speed to the gearbox output shaft speed is compared with the transmission ratio of each non-neutral gear, the transmission ratio with the minimum difference with the ratio is selected according to the principle of being nearby, and then the operating gear of the non-clutch signal sample data is pre-marked as the gear corresponding to the transmission ratio with the minimum difference.
S104: and respectively calculating to obtain a first prior probability of each gear and a first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch-free signal sample data.
Specifically, according to the operation gears pre-marked by the clutch-free signal sample data, the frequency of shifting each gear from other gears is respectively counted to obtain a first prior probability of each gear. The method comprises the steps of counting the frequency of shifting gears from other gears according to the sequence of timestamps, or sequencing sample data of clutch-free signals according to the sequence of the timestamps, classifying the sample data of the clutch-free signals which are continuous and pre-marked and have consistent operating gears into one section, wherein the sample data of the clutch-free signals corresponds to the same operating gear, counting the number of sections of sample data of the clutch-free signals which correspond to each gear respectively, and obtaining the frequency of shifting gears corresponding to each gear, and then dividing the frequency of shifting gears corresponding to each gear by the total frequency (namely the sum of the frequency of shifting gears of each gear) respectively to obtain the frequency of shifting gears, wherein the frequency is approximate to be the first prior probability of each gear.
Then, calculating statistics of the sample data of the clutch-free signal of each gear respectively, and acquiring a first two-dimensional probability density function of the engine speed and the gearbox output shaft speed of each gear according to the statistics; and respectively carrying out discretization and normalization processing on the first two-dimensional probability density function of each gear to obtain first probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear. Specifically, all possible values of the data acquisition precision according to the engine speed and the gearbox output shaft speed are taken and substituted into the first two-dimensional probability density function to calculate a function value so as to carry out discretization processing, and then normalization processing is carried out, for example, the acquisition precision is set to be 0.1rpm, and the possible values of the data acquisition precision include values with the interval of 0.1 in a certain range, such as 782.0, 1000.5, 2531.7 and the like.
That is, according to the result of pre-marking the operating gear, calculating statistics of the no-clutch signal sample data of the neutral gear, the first gear, the … … and the n gear respectively, wherein the statistics depend on the distribution type of the two-dimensional probability density function, for example, for the two-dimensional probability density function of the two-dimensional normal distribution, the statistics comprise the mean value of the rotating speed of the engine, the variance of the rotating speed of the engine, the mean value of the rotating speed of the output shaft of the gearbox, the variance of the rotating speed of the output shaft of the gearbox and the covariance of the rotating speed of the engine and the rotating speed of the output shaft of the gearbox. For two-dimensional probability density functions of other distribution types, it is possible to compute other statistics.
The two-dimensional probability density function is a continuous function related to continuous independent variables, but because the engine rotating speed and the rotating speed of the output shaft of the gearbox in sample data are discrete values, discretization and normalization processing are required, so that corresponding probabilities, namely probability distribution, when the engine rotating speed and the rotating speed of the output shaft of the gearbox take all different values under different gears are obtained.
S105: and dividing continuously acquired clutch-free signal sample data into the same group according to the time stamp to obtain a plurality of clutch-free signal sample data groups. The continuous acquisition means that the time difference of two adjacent sample data of the clutchless signal is less than or equal to the sampling time interval, and if the acquisition frequency of the sample data is 1Hz, the time difference is not more than 1s. Therefore, the time difference between adjacent clutchless signal sample data in the same clutchless signal sample data group is less than or equal to the sampling time interval.
S106: and respectively calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear and the first probability distribution of each gear, and respectively determining the operating gear of each non-clutch signal sample data set according to the posterior probability.
Specifically, according to the first probability distribution of each gear, the probability of each non-clutch signal sample data in a non-clutch signal sample data set corresponding to each gear is respectively obtained; and multiplying the probability of each non-clutch signal sample data in the non-clutch signal sample data group corresponding to the same gear to obtain the likelihood of the non-clutch signal sample data group corresponding to the same gear.
Then, according to the first prior probability of each gear and the likelihood of the sample data set of the clutchless signal corresponding to each gear, respectively calculating the posterior probability of each gear corresponding to the sample data set of the clutchless signal through a Bayesian formula; and marking the operating gear of the clutch-free signal sample data set as a gear corresponding to the maximum posterior probability.
According to the engine rotating speed and the rotating speed of the output shaft of the gearbox in each sample data of the clutch-free signal in the group, matching is carried out in the first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox respectively, and the probability of the sample data of each clutch-free signal appearing in each gear is obtained; and then multiplying the probability of the sample data of each non-clutch signal in the group corresponding to the same gear to obtain the likelihood of the group corresponding to the gear, and so on to obtain the likelihood of the group corresponding to each gear.
For example, assume Φ 0 ＝s 0 The case operation state is s when the clutch signal is not applied 0 ”，P(Φ 0 ＝s 0 ) Representing the first prior probability of each gear without clutch signal, the probability of no clutch signal sample data occurring in each gear can be represented as P ((omega) () e,i ，ω t,i )|Φ 0 ＝s 0 ) I.e. at phi 0 ＝s 0 Probability of occurrence of the ith sample data under the condition of occurrence.
The likelihood can be expressed as
Figure BDA0001968792120000111
Wherein p is 0 For the position index of the first clutch-less signal sample data in the clutch-less signal sample data set, q 0 Indexing the position of the last sample data of the clutch-free signal, wherein the likelihood is the pth 0 To q 0 Corresponding gear s of clutch-free signal sample data set consisting of sample data 0 The likelihood of (d).
Then, calculating the posterior probability of each gear corresponding to the sample data group of the clutchless signal according to a Bayes formula, wherein the Bayes formula is as follows:
Figure BDA0001968792120000121
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0001968792120000122
is a normalized constant with a corresponding formula of
Figure BDA0001968792120000123
And then acquiring a gear corresponding to the maximum posterior probability as an operating gear of the clutch-free signal sample data set.
S107: updating the first prior probability of each gear and the first probability distribution of each gear according to the operating gears of the clutch-free signal sample data set; according to the identification result of the operating gear of each non-clutch signal sample data set, the switching-in probability of each gear and the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox are counted again.
And subsequently, for newly acquired clutch-free signal data, calculating the likelihood of the newly acquired clutch-free signal data by using the updated first probability distribution of each gear, calculating the posterior probability of each gear corresponding to the newly acquired clutch-free signal data by combining the updated first prior probability of each gear, and taking the gear corresponding to the maximum value of the posterior probability as the operating gear of the newly acquired clutch-free signal data.
Similarly, after the identification of the operation gear of the newly acquired clutch-free signal data is completed, the first prior probability and the first probability distribution of each gear are updated.
The clutch data is roughly divided into three states of equivalent complete separation, almost complete engagement and half linkage in consideration of the contact condition between the driving disk and the driven disk of the clutch.
The equivalent complete disengagement state means that the driving disk and the driven disk are not in contact at all, and the situation can be regarded as neutral in the clutch-free data, so that the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in the equivalent complete disengagement state is set as the probability distribution of the neutral corresponding to the updated clutch-free signal sample data.
Almost complete engagement indicates that there is a clutch signal (clutch pedal is stepped), but there is almost no speed difference between the driving and driven disks, and it can be regarded as a non-neutral case such as first gear, second gear, … …, n gear in the non-clutch data, and therefore, the probability distributions of the engine speed and the transmission output shaft speed in the almost complete engagement state are set to be respectively in one-to-one correspondence with the probability distribution of the non-neutral case corresponding to the non-clutch signal sample data after updating.
That is, the probability distributions of the engine speed and the transmission output shaft speed in the equivalent fully disengaged state and the almost fully engaged state correspond to the first probability distribution of the engine speed and the transmission output shaft speed of each gear in the above-described no-clutch data. And for the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in the semi-linkage state, the probability distribution needs to be obtained through additional calculation.
As shown in fig. 4, the method for identifying the gear position of the gearbox based on the clutch data comprises the following steps:
s201: and acquiring sample data of the clutch pedal in a trampling state to obtain sample data of a clutch signal.
S202: acquiring continuous clutch signal sample data within a preset second time period to obtain a plurality of clutch signal sample data sets, and pre-marking the operating gears of the clutch signal sample data sets as the operating gears of the previous clutch signal sample data set; preferably, the second time period is 3s, that is, screening out continuous on-off signal sample data with a time difference not greater than 3 s.
S203: and calculating to obtain the probability distribution of the engine rotating speed in the semi-linkage state and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch signal sample data set.
Specifically, calculating statistics of sample data of clutch signals of each gear respectively, and acquiring a second two-dimensional probability density function of the engine speed and the gearbox output shaft speed of each gear according to the statistics; and respectively carrying out discretization and normalization processing on the second two-dimensional probability density function of each gear to obtain a second probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear.
Then, respectively calculating the occupation ratio of the clutch signal sample data corresponding to each gear according to the operation gears pre-marked by the clutch signal sample data sets and the number of the sample data in the operation gears; the method comprises the steps of acquiring a sample data set with clutch signals corresponding to the same gear, then counting the total number of sample data corresponding to the same gear according to the number of the sample data in the sample data set with clutch signals, and so on to obtain the total number of the sample data corresponding to each gear, thereby obtaining the occupation ratio of the sample data with clutch signals of each gear. And then taking the ratio as a weight, and carrying out weighted summation on the second probability distribution of each gear to obtain the probability distribution of the engine rotating speed in the semi-linkage state and the rotating speed of the output shaft of the gearbox.
S204: and calculating a second prior probability and a prior probability of a semi-linkage state of each gear according to the plurality of sample data groups with the clutch signal and the sample data group without the clutch signal before the sample data group with the clutch signal.
Specifically, a previous clutch-free signal sample data set of the multiple clutch signal sample data sets is respectively obtained, and the total number of sample data corresponding to each gear and the total number of sample data of the clutch-free signal sample are calculated according to the operating gear of the previous clutch-free signal sample data set and the number of sample data in the previous clutch-free signal sample data set;
calculating the total number of sample data of the clutch signal according to the plurality of sample data sets of the clutch signal;
adding the total number of the sample data of the clutch-free signal and the total number of the sample data of the clutch signal to obtain a first total number;
dividing the total number of sample data corresponding to each gear by the first total number to obtain a second prior probability of each gear;
and dividing the total number of the sample data of the clutch signal by the first total number to obtain the prior probability of the semi-linkage state.
Suppose phi 1 ＝s 1 The case operation state s when the clutch signal is present 1 ”，s 1 Representing the operating gear or clutch state in the presence of a clutch signal, having different values in n +2, i.e. s 1 =0,1, …, n, n +1, respectively representing neutral, first gear, … …, n gear, and half-linked state. Then P (phi) 1 ＝s 1 ) And representing a second prior probability of each gear and a prior probability of a semi-linkage state when the clutch signal exists.
S205: acquiring a preset number of continuous newly-acquired clutch signal data to obtain a clutch signal data set; namely, for the subsequent newly acquired data with the clutch signal, the data group with the clutch signal can be acquired in the form of a time window (such as 3 data lengths).
The clutch signal data set can be represented as W 1,u ，u＝p 1 ,…,q 1 ，p 1 For the position index of the first clutch signal data in the clutch signal data set, q 1 And indexing the position of the last clutch signal data in the clutch signal data group.
S206: and respectively calculating the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state.
Specifically, according to the first probability distribution of each gear and the probability distribution of the semi-linkage state, the probability that each clutch signal data in the clutch signal data set corresponds to each gear and the semi-linkage state is respectively obtained; multiplying the probability that each clutch signal data in the clutch signal data group corresponds to the same gear to obtain the likelihood that the clutch signal data group corresponds to the same gear; and multiplying the probability of the semi-linkage state corresponding to each clutch signal data in the clutch signal data group to obtain the likelihood of the semi-linkage state corresponding to the clutch signal data group.
According to the engine rotating speed and the gearbox output shaft rotating speed in each clutch signal data in the clutch signal data group, matching is carried out in the first probability distribution of the engine rotating speed and the gearbox output shaft rotating speed of each gear respectively to obtain the probability of each clutch signal data appearing in each gear, then the probability corresponding to the same gear is multiplied to obtain the likelihood of the clutch signal data group corresponding to the gear, and the likelihood of the clutch signal data group corresponding to each gear is obtained by analogy.
Meanwhile, according to the engine rotating speed and the gearbox output shaft rotating speed in each clutch signal data in the clutch signal data group, matching is carried out in probability distribution of the engine rotating speed in the semi-linkage state and the gearbox output shaft rotating speed to obtain the probability of each clutch signal data in the semi-linkage state, and then the probabilities are multiplied to obtain the likelihood of the clutch signal data group corresponding to the semi-linkage state.
Suppose that the clutch signal data group comprises 3 clutch signal data, denoted as W 1,u ＝{(ω e,u-1 ,ω t,u-1 ),(ω e,u ,ω t,u ),(ω e,u+1 ,ω t,u+1 ) }. The likelihood in this step is also at phi 1 ＝s 1 Condition of occurrence of W 1,u The probability of occurrence, can be expressed as P (W) 1,u |Φ 1 ＝s 1 ) For a clutch signal data set having 3 data, the corresponding likelihood can be expressed as
Figure BDA0001968792120000151
S207: and respectively calculating the posterior probability of the clutch signal data group corresponding to each gear and the semi-linkage state through a Bayes formula according to the second prior probability of each gear, the prior probability of the semi-linkage state and the likelihood of the clutch signal data group corresponding to each gear and the semi-linkage state.
The Bayesian formula in the step is as follows:
Figure BDA0001968792120000152
wherein, P (W) 1,u ) Is a normalized constant with a corresponding formula of
Figure BDA0001968792120000153
S208: and judging whether the maximum posterior probability corresponds to a semi-linkage state, namely whether the posterior probability of the semi-linkage state is greater than the posterior probabilities of other gears, if so, executing step S209, and otherwise, executing step S210.
S209: and marking the running gear of the clutch signal data set as the running gear of the clutch signal data set in the first non-semi-linkage state after the clutch signal data set, and marking the running gear of the clutch signal data set as the gear corresponding to the clutch signal data set which is identified as the first non-neutral, almost completely engaged state or equivalent completely disengaged state after the running gear of the clutch signal data set. And the clutch signal data set in the non-semi-linkage state is a newly acquired clutch-free signal data set or a clutch signal data set in the non-semi-linkage state. Further, at this time, the clutch state may be considered to be a half-interlocked state.
S210: and marking the operation gear of the data group with the clutch signal as a gear corresponding to the maximum posterior probability. Namely, the gear corresponding to the maximum posterior probability is obtained as the operating gear of the clutch signal data set.
S211: and updating the second prior probability of each gear, the prior probability of the semi-linkage state, the second probability distribution of each gear and the probability distribution of the semi-linkage state according to the operating gears with the clutch signal data set. According to the identification result of the operation gears with the clutch signal data set, recalculating the second prior probability of each gear, the prior probability of the semi-linkage state, the second probability distribution of each gear and the probability distribution of the semi-linkage state.
And subsequently, for newly acquired clutch signal data, continuing to execute the steps S207-S211 according to the updated data.
Further, according to the operation gear which is marked at last by the clutch signal data set, the contact condition of the driving disk and the driven disk can be known, namely if the clutch signal data set is marked to be neutral, the clutch state is equivalent complete separation state; if the clutched signal data set is marked as not neutral, the clutch state is an almost fully engaged state.
According to the method, through a data driving mode, the data which can be directly acquired by a data bus are utilized, such as the timestamp, the engine rotating speed, the rotating speed of the output shaft of the gearbox and the pedal treading state of the clutch, the simple, efficient, accurate and reliable identification of the operating gear is achieved, the state of the clutch when a clutch signal exists can be identified, the rotating speed difference between the driving disc and the driven disc during semi-linkage can be inferred subsequently, the abrasion loss can be approximately estimated by combining information such as materials, and therefore the residual service life of the clutch can be predicted.
Example two
The present embodiment is a computer-readable storage medium corresponding to the above-mentioned embodiments, on which a computer program is stored, which when executed by a processor implements the steps of:
collecting sample data in a preset first time period, wherein the sample data comprises a timestamp, an engine rotating speed, a rotating speed of an output shaft of a gearbox and a trampling state of a clutch pedal;
obtaining sample data of a clutch pedal in a non-treading state to obtain sample data of a non-clutch signal;
pre-marking the operating gear of the clutch-free signal sample data according to gearbox configuration information, wherein the gearbox configuration information comprises the number of gears of a gearbox, the transmission ratio of each non-neutral gear and the engine speed at neutral idle speed;
respectively calculating to obtain a first prior probability of each gear and a first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch-free signal sample data;
dividing continuously acquired clutch-free signal sample data into the same group according to the timestamp to obtain a plurality of clutch-free signal sample data groups;
respectively calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear and the first probability distribution of each gear, and respectively determining the operating gear of each non-clutch signal sample data set according to the posterior probability;
acquiring sample data of a clutch pedal in a trampling state to obtain sample data of a clutch signal;
acquiring continuous on-off signal sample data within a preset second time period to obtain a plurality of on-off signal sample data sets, and pre-marking the operating gears of the on-off signal sample data sets as the operating gears of the previous off-off signal sample data set respectively;
calculating to obtain probability distribution of the engine rotating speed in a semi-linkage state and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch signal sample data set;
calculating a second prior probability and a prior probability of a semi-linkage state of each gear according to the multiple sample data groups with the clutch signals and the previous sample data group without the clutch signals;
acquiring a preset number of continuous newly-acquired clutch signal data to obtain a clutch signal data set;
respectively calculating the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state;
according to the second prior probability of each gear, the prior probability of the semi-linkage state and the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state, respectively calculating the posterior probability of the clutch signal data set corresponding to each gear and the semi-linkage state through a Bayes formula;
and marking the operating gear with the clutch signal data set as a gear corresponding to the maximum posterior probability.
Further, the pre-marking the operating gear of the clutch-free signal sample data according to the configuration information of the gearbox specifically comprises:
according to the engine speed during the idle speed of the neutral position, pre-marking the running gear of the no-clutch signal sample data with the engine speed within a preset range as the neutral position;
respectively calculating the ratio of the engine rotating speed of other sample data without clutch signals to the rotating speed of the output shaft of the gearbox, and comparing the ratio with the transmission ratio of each non-neutral gear;
and pre-marking the operating gears of other sample data of the clutch-free signal as the gears corresponding to the transmission ratio closest to the ratio of the operating gears.
Further, the step of respectively calculating a first prior probability of each gear and a first probability distribution of the engine speed of each gear and the transmission output shaft speed according to the operation gear pre-marked by the clutch-free signal sample data specifically comprises:
respectively counting the frequency of each gear shifted from other gears according to the operation gears pre-marked by the clutch-free signal sample data to obtain a first prior probability of each gear;
calculating statistics of sample data of the clutch-free signal of each gear respectively, and acquiring a first two-dimensional probability density function of the engine speed and the speed of an output shaft of the gearbox of each gear according to the statistics;
and respectively carrying out discretization and normalization processing on the first two-dimensional probability density function of each gear to obtain a first probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear.
Further, the step of respectively calculating posterior probabilities of the non-clutch signal sample data sets corresponding to the gears according to the first prior probabilities of the gears and the first probability distribution of the gears, and respectively determining the operating gears of the non-clutch signal sample data sets according to the posterior probabilities specifically includes:
according to the first probability distribution of each gear, respectively acquiring the probability of each non-clutch signal sample data in a non-clutch signal sample data set corresponding to each gear;
multiplying the probability of each non-clutch signal sample data in the non-clutch signal sample data group corresponding to the same gear to obtain the likelihood of the non-clutch signal sample data group corresponding to the same gear;
according to the first prior probability of each gear and the likelihood of the sample data set of the clutchless signal corresponding to each gear, respectively calculating the posterior probability of the sample data set of the clutchless signal corresponding to each gear through a Bayes formula;
and marking the operating gear of the clutch-free signal sample data set as a gear corresponding to the maximum posterior probability.
Further, the calculating, according to the first prior probability of each gear and the first probability distribution of each gear, the posterior probability of each gear corresponding to each non-clutch signal sample data set, and determining, according to the posterior probability, the operating gear of each non-clutch signal sample data set, further includes:
and updating the first prior probability of each gear and the first probability distribution of each gear according to the operating gears of the clutch-free signal sample data set.
Further, the calculating the probability distribution of the engine rotation speed in the semi-linkage state and the transmission output shaft rotation speed according to the operation gear pre-marked by the clutch signal sample data set specifically comprises:
respectively calculating statistics of sample data of the clutch signal of each gear, and acquiring a second two-dimensional probability density function of the engine speed and the speed of the output shaft of the gearbox of each gear according to the statistics;
discretizing and normalizing the second two-dimensional probability density function of each gear to obtain a second probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear;
respectively calculating the occupation ratios of the clutch signal sample data corresponding to the gears according to the operation gears pre-marked by the clutch signal sample data sets and the number of the sample data in the operation gears;
and taking the ratio as a weight, and carrying out weighted summation on the second probability distribution of each gear to obtain the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in a semi-linkage state.
Further, the calculating a second prior probability and a prior probability of the semi-linkage state of each gear according to the multiple sample data sets of the clutched signal and the sample data set of the previous clutchless signal specifically includes:
respectively acquiring a previous non-clutch signal sample data set of the multiple sample data sets with clutch signals, and calculating the total number of sample data corresponding to each gear and the total number of sample data of the non-clutch signals according to the operating gear of the previous non-clutch signal sample data set and the number of sample data in the previous non-clutch signal sample data set;
calculating the total number of sample data of the clutch signal according to the plurality of sample data sets of the clutch signal;
adding the total number of the sample data of the clutch-free signal and the total number of the sample data of the clutch signal to obtain a first total number;
dividing the total number of sample data corresponding to each gear by the first total number to obtain a second prior probability of each gear;
and dividing the total number of the sample data of the clutch signal by the first total number to obtain the prior probability of the semi-linkage state.
Further, the calculating, according to the first probability distribution of each gear and the probability distribution of the semi-linkage state, the likelihood that the clutch signal data set corresponds to each gear and the semi-linkage state specifically includes:
respectively acquiring the probability of each clutch signal data in the clutch signal data group corresponding to each gear and the semi-linkage state according to the first probability distribution of each gear and the probability distribution of the semi-linkage state;
multiplying the probability that each clutch signal data in the clutch signal data group corresponds to the same gear to obtain the likelihood that the clutch signal data group corresponds to the same gear;
and multiplying the probability of the semi-linkage state corresponding to each clutch signal data in the clutch signal data group to obtain the likelihood of the semi-linkage state corresponding to the clutch signal data group.
Further, the step of marking the operating gear of the clutch signal data set as the gear corresponding to the maximum posterior probability specifically is:
judging whether the maximum value of the posterior probability corresponds to a semi-linkage state or not;
if not, marking the operating gear with the clutch signal data set as a gear corresponding to the maximum value of the posterior probability;
and if so, marking the operating gear of the clutch signal data group as the operating gear of the clutch signal data group in the first non-semi-linkage state after the clutch signal data group.
Further, after the operation gear of the clutch signal data set is marked as the gear corresponding to the maximum a posteriori probability, the method further comprises the following steps:
and updating the second prior probability of each gear, the prior probability of the semi-linkage state, the second probability distribution of each gear and the probability distribution of the semi-linkage state according to the operating gears with the clutch signal data set.
Further, after the posterior probabilities of the data group with the clutch signal corresponding to the gears and the semi-linkage state are respectively calculated through a bayesian formula, the method further comprises the following steps:
if the maximum value of the posterior probability corresponds to a semi-linkage state, judging that the clutch state is a semi-linkage state;
if the gear corresponding to the maximum value of the posterior probability is a neutral gear, judging that the clutch state is an equivalent complete separation state;
if the gear corresponding to the maximum value of the posterior probability is not neutral, the clutch state is determined to be the almost complete engagement state.
In summary, according to the vehicle transmission gear identification method and the computer-readable storage medium provided by the invention, through a bayesian analysis method, the operating gear without clutch signal sample data is pre-marked according to the transmission configuration information, then the prior probability of each gear under the condition of no clutch signal and the probability distribution of the engine rotating speed of each gear and the rotating speed of the transmission output shaft are calculated according to the pre-marking result, then the posterior probability of each gear is calculated according to a bayesian formula, and the gear corresponding to the maximum value of the posterior probability is selected as the transmission gear identification result under the condition of no clutch signal. Similarly, the operating gear with clutch signal sample data is pre-marked according to a gear identification result of the clutch signal-free sample data through a Bayes analysis method, then probability distribution under a semi-linkage state is calculated according to the pre-marking result, then prior probability of each gear under the condition of clutch signal and prior probability under the semi-linkage state are calculated by combining the clutch signal-free sample data, then posterior probability of each gear and the semi-linkage state is calculated according to a Bayes formula by combining the probability distribution of each gear under the condition of clutch signal, and the gear corresponding to the maximum value of the posterior probability is selected as a gear identification result of the gearbox under the condition of clutch signal.
According to the invention, the gear of the gearbox can be identified and obtained only by means of data which can be directly acquired by a data bus, such as a timestamp, the rotating speed of an engine, the rotating speed of an output shaft of the gearbox and the pedal state of a clutch pedal, and the operating gear can be simply, efficiently, accurately and reliably identified in a data driving mode.
The above description is only an embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent modifications made by the present invention and the contents of the accompanying drawings, which are directly or indirectly applied to the related technical fields, are included in the scope of the present invention.

Claims (12)

1. A vehicle transmission gear identification method, comprising:
collecting sample data in a preset first time period, wherein the sample data comprises a timestamp, the rotating speed of an engine, the rotating speed of an output shaft of a gearbox and the treading state of a clutch pedal;
obtaining sample data of a clutch pedal in a non-treading state to obtain sample data of a non-clutch signal;
pre-marking the operating gear of the clutch-free signal sample data according to the configuration information of the gearbox, wherein the configuration information of the gearbox comprises the gear number of the gearbox, the transmission ratio of each non-neutral gear and the engine speed at neutral idle speed;
respectively calculating to obtain a first prior probability of each gear and a first probability distribution of the engine rotating speed of each gear and the rotating speed of an output shaft of the gearbox according to the operation gears pre-marked by the clutch-free signal sample data;
dividing continuously acquired clutch-free signal sample data into the same group according to the timestamp to obtain a plurality of clutch-free signal sample data groups;
respectively calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear, the first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox, and respectively determining the operating gear of each non-clutch signal sample data set according to the posterior probability;
acquiring sample data of a clutch pedal in a trampling state to obtain sample data of a clutch signal;
acquiring continuous on-off signal sample data within a preset second time period to obtain a plurality of on-off signal sample data sets, and pre-marking the operating gears of the on-off signal sample data sets as the operating gears of the previous off-off signal sample data set respectively;
calculating to obtain the probability distribution of the engine rotating speed in a semi-linkage state and the rotating speed of the output shaft of the gearbox according to the operation gear pre-marked by the clutch signal sample data set;
calculating a second prior probability and a prior probability of a semi-linkage state of each gear according to the multiple sample data sets with the clutch signal and the sample data set without the clutch signal before the sample data sets;
acquiring a preset number of continuous newly-acquired clutch signal data to obtain a clutch signal data set;
respectively calculating the likelihood of the clutch signal data set corresponding to each gear and the semi-linkage state according to the first probability distribution of the engine speed of each gear and the speed of the output shaft of the gearbox and the probability distribution of the engine speed of the semi-linkage state and the speed of the output shaft of the gearbox;
respectively calculating posterior probabilities of the clutched signal data set corresponding to each gear and the semi-linkage state through a Bayes formula according to the second prior probability of each gear, the prior probability of the semi-linkage state and the likelihood of the clutched signal data set corresponding to each gear and the semi-linkage state;
and marking the operating gear with the clutch signal data set as a gear corresponding to the maximum posterior probability.
2. The method for identifying a gear position of a vehicle transmission according to claim 1, wherein the pre-marking the operating gear position of the sample data of the clutch-free signal according to the transmission configuration information specifically comprises:
according to the engine speed during the idle speed of the neutral position, pre-marking the running gear of the no-clutch signal sample data with the engine speed within a preset range as the neutral position;
respectively calculating the ratio of the engine rotating speed of other sample data without clutch signals to the rotating speed of the output shaft of the gearbox, and comparing the ratio with the transmission ratio of each non-neutral gear;
and pre-marking the operating gears of other sample data without clutch signals as gears corresponding to the transmission ratio closest to the ratio of the operating gears.
3. The method for identifying the gear position of the vehicle gearbox according to claim 1, wherein the first prior probability of each gear position and the first probability distribution of the engine speed and the gearbox output shaft speed of each gear position are respectively calculated according to the operation gear position pre-marked by the clutch-free signal sample data and specifically comprise the following steps:
respectively counting the frequency of each gear shifted from other gears according to the operation gears pre-marked by the clutch-free signal sample data to obtain a first prior probability of each gear;
calculating statistics of sample data of the clutch-free signal of each gear respectively, and acquiring a first two-dimensional probability density function of the engine speed and the speed of an output shaft of the gearbox of each gear according to the statistics;
and respectively carrying out discretization and normalization processing on the first two-dimensional probability density function of each gear to obtain a first probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear.
4. The method according to claim 1, wherein the step of calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear according to the first prior probability of each gear and the first probability distribution of the engine speed and the transmission output shaft speed of each gear respectively, and determining the operating gear of each non-clutch signal sample data set according to the posterior probability specifically comprises:
respectively acquiring the probability of each non-clutch signal sample data corresponding to each gear in a non-clutch signal sample data set according to the first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox;
multiplying the probability of each non-clutch signal sample data in the non-clutch signal sample data group corresponding to the same gear to obtain the likelihood of the non-clutch signal sample data group corresponding to the same gear;
according to the first prior probability of each gear and the likelihood of the sample data set of the clutchless signal corresponding to each gear, respectively calculating the posterior probability of the sample data set of the clutchless signal corresponding to each gear through a Bayes formula;
and marking the operation gear of the clutchless signal sample data set as a gear corresponding to the maximum posterior probability.
5. The method for identifying a gear position of a transmission of a vehicle according to claim 1, wherein after calculating the posterior probability of each non-clutch signal sample data set corresponding to each gear position according to the first prior probability of each gear position and the first probability distribution of the engine speed and the transmission output shaft speed of each gear position, and determining the operating gear position of each non-clutch signal sample data set according to the posterior probability, further comprising:
and updating the first prior probability of each gear and the first probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear according to the operating gear of the clutch-free signal sample data set.
6. The method for identifying the gear position of the vehicle gearbox according to claim 1, wherein the probability distribution of the engine speed and the gearbox output shaft speed in the semi-linkage state calculated according to the pre-marked operating gear position with the clutch signal sample data set is specifically as follows:
respectively calculating statistics of sample data of the clutch signal of each gear, and acquiring a second two-dimensional probability density function of the engine speed and the speed of the output shaft of the gearbox of each gear according to the statistics;
discretizing and normalizing the second two-dimensional probability density function of each gear respectively to obtain a second probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox of each gear;
respectively calculating the occupation ratio of the clutch signal sample data corresponding to each gear according to the operation gears pre-marked by the clutch signal sample data sets and the number of the sample data in the operation gears;
and taking the ratio as a weight, and carrying out weighted summation on the engine rotating speed of each gear and the second probability distribution of the rotating speed of the output shaft of the gearbox to obtain the probability distribution of the engine rotating speed and the rotating speed of the output shaft of the gearbox in a semi-linkage state.
7. The method for identifying a gear position of a transmission of a vehicle according to claim 1, wherein the calculating a second prior probability and a prior probability of the semi-linkage state of each gear according to the multiple sample data sets of clutch signals and the sample data set of previous clutch-free signals specifically comprises:
respectively acquiring a previous non-clutch signal sample data set of the multiple sample data sets with clutch signals, and calculating the total number of sample data corresponding to each gear and the total number of sample data of the non-clutch signals according to the operating gear of the previous non-clutch signal sample data set and the number of sample data in the previous non-clutch signal sample data set;
calculating the total number of sample data of the clutch signal according to the plurality of sample data sets of the clutch signal;
adding the total number of the sample data of the clutch-free signal and the total number of the sample data of the clutch signal to obtain a first total number;
dividing the total number of sample data corresponding to each gear by the first total number to obtain a second prior probability of each gear;
and dividing the total number of the sample data of the clutch signal by the first total number to obtain the prior probability of the semi-linkage state.
8. The method according to claim 1, wherein the calculating the likelihood that the clutch signal data set corresponds to each gear and the semi-linkage state respectively according to the first probability distribution of the engine speed and the transmission output shaft speed of each gear and the probability distribution of the engine speed and the transmission output shaft speed of the semi-linkage state is specifically:
respectively acquiring the probability of each clutch signal data in the clutch signal data group corresponding to each gear and the semi-linkage state according to the first probability distribution of the engine rotating speed of each gear and the rotating speed of the output shaft of the gearbox and the probability distribution of the engine rotating speed of the semi-linkage state and the rotating speed of the output shaft of the gearbox;
multiplying the probability that each clutch signal data in the clutch signal data group corresponds to the same gear to obtain the likelihood that the clutch signal data group corresponds to the same gear;
and multiplying the probability of the semi-linkage state corresponding to each clutch signal data in the clutch signal data group to obtain the likelihood of the semi-linkage state corresponding to the clutch signal data group.
9. The method for identifying a gear position of a transmission of a vehicle according to claim 1, wherein the step of marking the operating gear position of the clutched signal data set as the gear position corresponding to the maximum a posteriori probability is specifically:
judging whether the maximum value of the posterior probability corresponds to a semi-linkage state or not;
if not, marking the operating gear with the clutch signal data set as a gear corresponding to the maximum value of the posterior probability;
and if so, marking the operating gear of the clutch signal data group as the operating gear of the clutch signal data group in the first non-semi-linkage state after the clutch signal data group.
10. The method of identifying a gear position in a transmission of a vehicle according to claim 1, wherein said marking the operating gear position in said clutch signal data set as the gear position corresponding to the maximum a posteriori probability further comprises:
and updating the second prior probability of each gear, the prior probability of the semi-linkage state, the second probability distribution of the engine speed of each gear and the speed of the output shaft of the gearbox and the probability distribution of the engine speed of the semi-linkage state and the speed of the output shaft of the gearbox according to the running gear with the clutch signal data set.
11. The method for identifying the gear position of the transmission of the vehicle according to claim 1, wherein after the calculating the posterior probability of the clutch signal data set corresponding to each gear position and the semi-linkage state respectively through the Bayesian formula, the method further comprises:
if the maximum value of the posterior probability corresponds to a semi-linkage state, judging that the clutch state is a semi-linkage state;
if the gear corresponding to the maximum posterior probability is a neutral gear, judging that the clutch state is an equivalent complete separation state;
if the gear corresponding to the maximum posterior probability is not neutral, the clutch state is judged to be a nearly complete engagement state.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-11.
CN201910112634.9A 2019-02-13 2019-02-13 Vehicle transmission gear recognition method and computer-readable storage medium Active CN111561567B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910112634.9A CN111561567B (en) 2019-02-13 2019-02-13 Vehicle transmission gear recognition method and computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910112634.9A CN111561567B (en) 2019-02-13 2019-02-13 Vehicle transmission gear recognition method and computer-readable storage medium

Publications (2)

Publication Number Publication Date
CN111561567A CN111561567A (en) 2020-08-21
CN111561567B true CN111561567B (en) 2023-04-18

Family

ID=72071329

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910112634.9A Active CN111561567B (en) 2019-02-13 2019-02-13 Vehicle transmission gear recognition method and computer-readable storage medium

Country Status (1)

Country Link
CN (1) CN111561567B (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IT1399015B1 (en) * 2009-02-13 2013-04-05 Magneti Marelli Spa METHOD OF IDENTIFYING THE OPTIMAL GEAR FOR A VEHICLE TRANSMISSION
JP5790524B2 (en) * 2012-02-03 2015-10-07 トヨタ自動車株式会社 Speed change instruction device
CN106704573A (en) * 2016-12-13 2017-05-24 北京汇通天下物联科技有限公司 Vehicle state judging method, device and system based on vehicle gear
CN106938648B (en) * 2017-04-07 2019-06-04 安徽江淮汽车集团股份有限公司 The power downshift scaling method and system of double clutch gearbox

Also Published As

Publication number Publication date
CN111561567A (en) 2020-08-21

Similar Documents

Publication Publication Date Title
CN110782659B (en) Road condition determining method, road condition determining device, server and storage medium
JP6330651B2 (en) Anomaly detection device
JP5856387B2 (en) Vehicle data analysis method and vehicle data analysis system
CN108960434B (en) Method and device for analyzing data based on machine learning model interpretation
EP3155608B1 (en) Method of following a music score and associated modelization
RU2549578C1 (en) Information representation device to be used in vehicle
CN104512404B (en) Determine the short-term method for driving tendency and the system using this method control gearshift
CN108488375A (en) A kind of method of vehicle automatic transmission shift quality under improvement accelerating mode
Lestyan et al. Extracting vehicle sensor signals from CAN logs for driver re-identification
CN103842772A (en) Navigation method and navigation device
CN111561567B (en) Vehicle transmission gear recognition method and computer-readable storage medium
JP2017010206A (en) Driving operation determination device
CN112406875B (en) Vehicle energy consumption analysis method and device
CN111561566B (en) Method for identifying gear of vehicle gearbox in no-clutch signal state and storage medium
CN114889613A (en) Vehicle driving control method and device and vehicle
EP3386829A1 (en) A vehicle drivability evaluation system and method
CN114386892A (en) Transportation vehicle load management method, system, storage medium and equipment
DE102014117792B4 (en) Driving tendency determination method and shift control system using the same
CN113173175B (en) Vehicle weight determination method and device
KR102552169B1 (en) Method for determining vehicle driving pattern
US10807602B2 (en) Evaluating apparatus
CN113742841B (en) Automobile gear shifting performance testing method and device, storage medium and computer equipment
WO2023005681A1 (en) Longitudinal vehicle-following control method and apparatus, and electronic device and storage medium
CN112785055B (en) Method and equipment for predicting vehicle refueling date
CN114228719A (en) Vehicle auxiliary braking method, electronic device and storage medium

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