CN114412988A - Uphill predictive gear shifting control method based on road information and machine learning - Google Patents

Uphill predictive gear shifting control method based on road information and machine learning Download PDF

Info

Publication number
CN114412988A
CN114412988A CN202210127546.8A CN202210127546A CN114412988A CN 114412988 A CN114412988 A CN 114412988A CN 202210127546 A CN202210127546 A CN 202210127546A CN 114412988 A CN114412988 A CN 114412988A
Authority
CN
China
Prior art keywords
gear
vehicle
uphill
predictive
maximum
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210127546.8A
Other languages
Chinese (zh)
Other versions
CN114412988B (en
Inventor
付尧
王杰
雷雨龙
李兴忠
阴晓峰
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.)
Jilin University
Original Assignee
Jilin University
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 Jilin University filed Critical Jilin University
Priority to CN202210127546.8A priority Critical patent/CN114412988B/en
Publication of CN114412988A publication Critical patent/CN114412988A/en
Application granted granted Critical
Publication of CN114412988B publication Critical patent/CN114412988B/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
    • F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
    • F16H61/02—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used
    • F16H61/0202—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric
    • F16H61/0204—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric for gearshift control, e.g. control functions for performing shifting or generation of shift signal
    • F16H61/0213—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric for gearshift control, e.g. control functions for performing shifting or generation of shift signal characterised by the method for generating shift signals
    • 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
    • F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
    • F16H61/18—Preventing unintentional or unsafe shift, e.g. preventing manual shift from highest gear to reverse gear
    • 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
    • F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
    • F16H61/02—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used
    • F16H61/0202—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric
    • F16H61/0204—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric for gearshift control, e.g. control functions for performing shifting or generation of shift signal
    • F16H61/0213—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing characterised by the signals used the signals being electric for gearshift control, e.g. control functions for performing shifting or generation of shift signal characterised by the method for generating shift signals
    • F16H2061/022—Calculation or estimation of optimal gear ratio, e.g. best ratio for economy drive or performance according driver preference, or to optimise exhaust emissions

Landscapes

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

Abstract

The invention discloses an uphill predictive gear shifting control method based on road information and machine learning, which comprises the following steps of: step one, judging whether the front of the vehicle is on an uphill slope according to vehicle navigation data: if the front of the vehicle is on an uphill slope, predicting the operation behavior habit of a driver to obtain the advanced distance of predictive gear shifting control, and acquiring the horizontal driving distance before the vehicle goes uphill slope, the maximum gradient of the slope, the length of the slope and the vehicle speed; step two, calculating the required torque and the required gear of the vehicle passing through the front uphill; and step three, adjusting the gear of the vehicle to the required gear and finishing gear shifting after the vehicle passes through safety check. The invention has the characteristics of avoiding continuous upshifting and downshifting in the uphill process, avoiding accidental gear shifting and frequent gear shifting, reducing the gear shifting times of uphill and improving the driving safety of passing through a ramp.

Description

Uphill predictive gear shifting control method based on road information and machine learning
Technical Field
The invention relates to the technical field of automobiles, in particular to an uphill predictive gear shifting control method based on road information and machine learning.
Background
During the slope driving of the vehicle, a driver can repeatedly upshift before an uphill and downshift after the uphill, which can cause repeated power interruption and frequent gear shifting in the uphill process and influence the slope driving safety of the vehicle. The reasonable gear change strategy of the automatic transmission can improve the passing safety of the vehicle.
Meanwhile, in the driving process of a vehicle, the front road information is constantly changed, in the prior art, gear shifting is generally controlled manually by a driver, the road information can only be evaluated subjectively by the driver, and the condition that gear change is unreasonable or gear shifting is accidental can occur.
The current research on the gear shifting rule lies in a self-adaptive gear shifting strategy based on a 'human-vehicle-road-environment', but the current problem still exists in a fatal problem which is difficult to solve, and because a vehicle state parameter sensor can estimate a reasonable vehicle state through an algorithm only when a vehicle enters a special road section, the real-time performance of acquiring road condition information is poor, a delay phenomenon exists, and the establishment of the gear shifting strategy is in a passive response state. With the gradual improvement of road traffic facilities and the increasingly improved use of GPS and GIS on automobiles, the automobiles can more accurately acquire road information in front. The gear shifting strategy for the automobile to pass through is designed in advance based on the front road information parameters, so that the problems of complex self-adaptive gear shifting algorithm, poor real-time performance and high delay of the current self-adaptive gear shifting algorithm can be solved, and the adaptability of the automobile to special road conditions is improved.
Disclosure of Invention
The invention aims to design and develop an uphill predictive gear shifting control method based on road information and machine learning, aiming at an uphill working condition in predictive cruising, setting an automatic gear shifting control strategy based on vehicle safety according to various uphill parameters, and improving the driving safety of passing a ramp.
The technical scheme provided by the invention is as follows:
an uphill predictive gear shifting control method based on road information and machine learning comprises the following steps:
step one, judging whether the front of the vehicle is on an uphill slope according to vehicle navigation data:
if the front of the vehicle is on an uphill slope, predicting the operation behavior habit of a driver to obtain the advance distance of predictive gear shifting control, and acquiring the horizontal driving distance before the uphill slope, the maximum gradient of the slope, the length of the slope and the vehicle speed as uphill slope parameters;
step two, calculating the required torque of the vehicle passing through the front uphill slope, and determining a required gear;
wherein the vehicle satisfies by a required torque of the front uphill:
Figure BDA0003501112140000021
in the formula, TxG is the total weight of the vehicle, f is the rolling resistance coefficient, CDIs the air resistance coefficient, A is the frontal area of the vehicle, ρ is the air density, u is the air resistance coefficientaFor vehicle speed, i is the maximum slope of the ramp, δ is the rotating mass conversion factor, m is the total mass of the vehicle, r is the wheel radius, ηrTo the wheel mechanical efficiency;
and step three, adjusting the gear of the vehicle to the required gear and finishing gear shifting after the vehicle passes through safety check.
Preferably, the vehicle navigation data is obtained by a road information system including three-dimensional information of a road ahead during vehicle travel, road shape and distance information, and road surface adhesion coefficient information.
Preferably, the predicting the operation behavior habit of the driver and obtaining the advance distance of the predictive gear shift control specifically include:
and respectively training and predicting the operation behavior habit data of the driver by using a support vector machine and a BP neural network under the current uphill condition, and preferentially determining the advance distance of predictive gear shifting control according to two prediction results.
Preferably, the support vector machine includes:
the input vector is p ═ p1,p2,p3}；
The output vector is t ═ t1}；
Wherein p is1As a maximum slope parameter of the ramp, p2As a ramp length parameter, p3The maximum gradient parameter of the ramp, the length parameter of the ramp and the vehicle speed parameter are respectively obtained by normalizing the maximum gradient of the ramp, the length of the ramp and the vehicle speed, and t1And after the anti-normalization processing, the data label is obtained.
Preferably, the data labels of the support vector machine are:
and setting the distance between the vehicle and the uphill entrance every 50m when the driver operates the accelerator pedal as a category interval, wherein the data label of the support vector machine is the maximum value of each category interval, and the data label of the support vector machine is used as the prediction result of the support vector machine.
Preferably, the BP neural network has a three-layer structure:
the input layer vector is x ═ x1,x2,x3Mapping the input layer vector to an intermediate layer, wherein the intermediate layer vector is y ═ y1,y2,......,ynThe output layer vector is o ═ o1}；
Wherein x is1As maximum slope parameter, x2As a ramp length parameter, x3The maximum gradient parameter, the ramp length parameter and the vehicle speed parameter are respectively obtained by normalization processing of the maximum gradient of the ramp, the ramp length and the vehicle speed, n is the number of nodes, o1And obtaining a prediction result after the denormalization treatment.
Preferably, the preferentially determining the advance distance of the predictive shift control according to the two prediction results specifically includes:
if the prediction result of the support vector machine is greater than the prediction result of the BP neural network, the prediction result of the support vector machine is a final prediction result;
and if the prediction result of the support vector machine is not greater than the prediction result of the BP neural network, adding the prediction result of the BP neural network and the corresponding correction distance to obtain a final prediction result.
Preferably, the determining the required gear specifically includes:
calculating the maximum torque of each gear of the vehicle, wherein the required gear is the maximum gear meeting the required torque;
the maximum torque of the vehicle at each gear meets the following requirements:
Tmaxi＝Ttqmaxkgk0ηT；
in the formula, TmaxiFor maximum torque in each gear of the vehicle, TtqmaxIs the maximum output torque of the engine, kgFor the current gear transmission ratio, k0Is the main reducer transmission ratio etaTThe efficiency of the transmission system is in addition to the wheel.
Preferably, the adjusting the vehicle gear to the required gear specifically includes:
calculating the maximum number of gears which can be shifted in a grade-crossing way when the engine runs in an economic rotating speed range:
Figure BDA0003501112140000041
in the formula, ne(n+1)For the post-shift engine speed, ne(n)For the engine speed at the time of gear shifting, qbIs the product of the average ratio of the gear ratios before and after shifting, and qb＝qvQ is the average ratio of the transmission ratio between two adjacent gears of the transmission, and v is the number of gear shifting stages;
if d is0-dpWhen the gear number is larger than v, the transmission repeatedly executes the maximum number of gears capable of being shifted in a stepped mode until a normal gear shifting interval is met, and then the transmission is down shifted along with the vehicle speed until the required gear is fixed;
the normal shift interval is:
if 0 < d0-dpWhen v is less than v, the transmission limits upshifting and performs speed-dependent downshifting according to the basic gear shifting curve of each gearUntil the gear is required and fixed;
if d is0-dpWhen the speed is equal to v, the transmission executes the step-by-step downshift along with the vehicle speed until the required gear is reached and is fixed;
if d is0-dpWhen the gear is less than or equal to 0, the limiting gear of the transmission does not exceed the required gear, and the transmission is shifted up along with the vehicle speed until the required gear is fixed;
wherein d is0Is the current gear position, dpThe required gear is adopted.
Preferably, the security check specifically includes:
when the transmission is in the required gear, a is more than or equal to 0m/s when the acceleration of the vehicle is stable2If so, the vehicle keeps the current gear to continue running;
if the acceleration of the vehicle is stable, a is less than 0m/s2If the speed changer reduces the first gear and then maintains the gear, and the vehicle continues to run;
where a is the vehicle acceleration.
The invention has the following beneficial effects:
the invention designs and develops an uphill predictive gear-shifting control method based on road information and machine learning, aiming at an uphill working condition in predictive cruising, an automatic gear-shifting control strategy based on vehicle safety is set according to information such as the maximum gradient, the length of a ramp, the distance from the uphill and the like provided by a road information system, meanwhile, a behavior habit of a driver before uphill is predicted through two machine learning algorithms, the advance distance of predictive gear-shifting control is determined to improve the control effect, and gear predictive automatic control in the uphill process is realized, so that continuous upshifting and downshifting in the uphill process are avoided, accidental gear shifting and frequent gear-shifting are avoided, the number of gear-shifting times of the uphill is reduced, and the driving safety of the ramp is improved on the basis of ensuring the dynamic property of an uphill vehicle.
Drawings
Fig. 1 is a schematic flow chart of an uphill predictive gear shifting control method based on road information and machine learning according to the present invention.
FIG. 2 is a schematic diagram of a preferred strategy flow of the support vector machine and the BP neural network according to the present invention.
Fig. 3 is a schematic diagram of an optimal dynamic upshift curve of the vehicle according to the embodiment of the present invention.
Fig. 4 is a schematic diagram of an optimal dynamic downshift curve of the vehicle according to the embodiment of the invention.
FIG. 5 is a diagram of the operation range of the step-by-step shift and the skip-by-step shift in the embodiment of the present invention.
FIG. 6 is a schematic diagram of a hill-crossing shift strategy according to an embodiment of the present invention.
FIG. 7 is a schematic diagram comparing uphill vehicle speed and gear with an unforeseen shift control method in the embodiment of the invention.
Detailed Description
The present invention is described in further detail below in order to enable those skilled in the art to practice the invention with reference to the description.
As shown in fig. 1, the uphill predictive gear shifting control method based on road information and machine learning provided by the present invention specifically includes the following steps:
step one, judging whether the front is on the uphill according to the automobile navigation data acquired by a road information system:
if the front of the vehicle is on the uphill, predicting the operation behavior habit of the driver according to the operation behavior habit data of the driver before the uphill, which are recorded in advance, obtaining the advance distance of predictive gear shifting control, recording the operation behavior habit data as a sample for next training, and collecting the horizontal driving distance before the uphill, the maximum gradient of the ramp, the length of the ramp and the vehicle speed as uphill parameters.
The road information system comprises three-dimensional information of a front road, road shape and distance information, road adhesion coefficient information and the like in the process of automobile traveling, the speed of the automobile is obtained through a vehicle state sensor, the horizontal traveling distance before an uphill slope is the distance between the automobile and an uphill slope entrance, and the maximum gradient of a ramp is the maximum road gradient in the process of finishing the whole uphill slope.
The predicting the operation behavior habit of the driver and obtaining the advance distance of the predictive gear shifting control specifically comprises the following steps:
as shown in fig. 2, the distance between the vehicle and the entrance of the uphill is taken as operation behavior habit data when the driver operates the accelerator pedal according to the uphill parameters before the uphill, the support vector machine and the BP neural network are used for respectively training and predicting the operation behavior habit data of the driver under the current uphill condition, and the advance distance of predictive gear shifting control is preferentially determined according to two prediction results, so that the control can be performed before the driver operates to change the gear, and the control effect is improved.
The support vector machine includes:
the input vector is p ═ p1,p2,p3}；
The output vector is t ═ t1}；
Wherein p is1As a maximum slope parameter of the ramp, p2As a ramp length parameter, p3The maximum gradient parameter of the ramp, the length parameter of the ramp and the vehicle speed parameter are respectively obtained by normalizing the maximum gradient of the ramp, the length of the ramp and the vehicle speed, and t1After the anti-normalization processing, the data label is obtained;
the data labels of the support vector machine are as follows:
the support vector machine predicts the required behavior habit data, namely the distance from a driver to an uphill entrance during operation, and the data habit data needs to be arranged into a data label form according to the predicted data characteristics of the support vector machine so as to facilitate training and prediction. With the combination of the strategy and the driving characteristics of the vehicle, an appropriate data interval is adopted, in this embodiment, if the distance from the vehicle to the uphill entrance when the driver operates the accelerator pedal is set to every 50m as a category section, the data label of the support vector machine is the maximum value of each category section, and the data label of the support vector machine is the prediction result of the support vector machine, such as: setting the data label to be 50m if the distance from the driver to the uphill entrance is 0-50m during operation; if the distance from the driver to the uphill entrance is 50m-100m during operation, the data tag is 100 m; and if the distance from the driver to the uphill entrance is 100m-150m during operation, the data tag is 150m, and the like.
The BP neural network is of a three-layer structure:
the input layer vector is x ═ x1,x2,x3Mapping the input layer vector to an intermediate layer, wherein the intermediate layer vector is y ═ y1,y2,......,ynThe output layer vector is o ═ o1}；
Wherein x is1As maximum slope parameter, x2As a ramp length parameter, x3The maximum gradient parameter, the ramp length parameter and the vehicle speed parameter are respectively obtained by normalization processing of the maximum gradient of the ramp, the ramp length and the vehicle speed, n is the number of nodes, o1And obtaining a prediction result after the denormalization treatment.
The preferentially determining the advance distance of the predictive gear shifting control according to the two prediction results specifically comprises:
if the prediction result of the support vector machine is greater than the prediction result of the BP neural network, the prediction result of the support vector machine is a final prediction result;
if the prediction result of the support vector machine is not greater than the prediction result of the BP neural network, adding the prediction result of the BP neural network and the corresponding correction distance to obtain a final prediction result, wherein the correction distance is shown in Table 1:
TABLE 1 correction of distances
Figure BDA0003501112140000071
Step two, calculating the required torque of the vehicle passing through the front uphill slope, and determining a required gear;
wherein the vehicle satisfies by a required torque of the front uphill:
Figure BDA0003501112140000072
in the formula, TxG is the total weight of the vehicle, f is the rolling resistance coefficient, CDIs an air resistance coefficient, A isFrontal area of vehicle, ρ is air density, uaFor vehicle speed, i is the maximum slope of the ramp, δ is the rotating mass conversion factor, m is the total mass of the vehicle, r is the wheel radius, ηrTo the wheel mechanical efficiency;
the determining of the required gear specifically includes:
calculating the maximum torque of the vehicle at each gear to obtain a required gear of the vehicle on an uphill slope, wherein the required gear is the maximum gear meeting the required torque;
the maximum torque of the vehicle at each gear meets the following requirements:
Tmaxi＝Ttqmaxkgk0ηT；
in the formula, TmaxiFor maximum torque in each gear of the vehicle, TtqmaxIs the maximum output torque of the engine, kgFor the current gear transmission ratio, k0Is the main reducer transmission ratio etaTThe efficiency of the transmission system is in addition to the wheel.
And step three, adjusting the gear of the vehicle to the required gear, judging the end of the whole process of ascending through a road information system signal and finishing the control after passing the safety check, namely displaying that the vehicle has driven out of the ramp by the road information system parameter at the current moment and finishing the whole process of ascending.
Adjusting the vehicle gear to the demanded gear specifically includes:
for the grade-crossing downshift when a heavy commercial vehicle ascends a slope, a driver generally steps on an accelerator pedal to accelerate a slope before the vehicle ascends the slope, so that the vehicle speed is increased, and the gear is also lifted.
The maximum number of the grade-crossing downshifts is determined by the transmission ratio of the gears, the average engine speed during gear shifting is estimated to determine the working range of the engine speed of the multistage downshifts, and the multistage gear shifting number of the engine running in an economic speed range can be ensured to be the maximum number of the grade-crossing downshifts.
When the transmission is shifted, assuming that the speeds before and after shifting are the same, the engine speed relationship before and after shifting is obtained according to a speed formula and the ratio relationship of two gears (the maximum number of gears which can be shifted by steps when the engine runs in an economic speed interval):
Figure BDA0003501112140000081
in the formula, ne(n+1)For the post-shift engine speed, ne(n)For the engine speed at the time of gear shifting, qbIs the product of the average ratio of the gear ratios before and after shifting, and qb＝qvQ is the average ratio of the transmission ratio between two adjacent gears of the transmission, v is the number of gear shifting steps, taking the gear upshift as an example, the vehicle speed before and after the gear upshift is approximately kept unchanged, and q is used for shifting gears at the next gearbQ; the more two-step gear shifting, qb＝q2；
If d is0-dpWhen the gear number is larger than v, the transmission repeatedly executes the maximum number of gears capable of being shifted in a stepped mode until a normal gear shifting interval is met, and then the transmission is down shifted along with the vehicle speed until the required gear is fixed;
the normal shift interval is:
if 0 < d0-dpWhen the gear shifting speed is less than v, the transmission limits gear shifting and performs gear shifting along with the vehicle speed according to the basic gear shifting curve of each gear until the gear is required and is fixed;
wherein the base shift profile data is obtained by base shift logic built into the transmission controller.
If d is0-dpWhen the speed is equal to v, the transmission executes the step-by-step downshift along with the vehicle speed until the required gear is reached and is fixed;
if d is0-dpAnd when the gear is less than or equal to 0, the limiting gear of the transmission does not exceed the required gear, and the transmission is shifted up along with the vehicle speed until the rear of the required gear is fixed.
The safety check specifically comprises:
when the transmission is in the required gear, a is more than or equal to 0m/s when the vehicle is stable2If so, the vehicle keeps the current gear to continue running;
if the vehicle is stable, a is less than 0m/s2And if the speed changer lowers the first gear, the gear is maintained, and the vehicle continues to run.
Examples
The vehicle model of this embodiment is a heavy commercial vehicle, and specific vehicle parameter data is shown in table 2:
TABLE 2 vehicle model parameter data
Figure BDA0003501112140000091
The transmission gear and transmission ratio of the vehicle are shown in table 3:
gear and ratio for 316-speed transmission
Figure BDA0003501112140000092
The method specifically comprises the following steps:
step 1, the road information system judges that the front of the vehicle has an uphill slope.
And 2, acquiring the horizontal driving distance (dynamic change) of the automobile before the automobile enters the uphill, wherein the maximum gradient of the ramp is 0.15, the length of the ramp is 300m, and the speed of the automobile is 40 km/h.
And 3, training a data set of the operation support vector machine and the BP neural network according to the pre-recorded operation behavior habit data of the driver before the uphill slope.
Table 4 driver behavior habit data before uphill
Figure BDA0003501112140000101
Figure BDA0003501112140000111
After normalization processing is carried out on the maximum slope of the ramp of 0.15, the ramp length of 300m and the vehicle speed of 40km/h, the input vector p of the support vector machine in the prediction is {0.4,0.8333,0.1791}, and the prediction result of the support vector machine is 100 m;
the input vector of the BP neural network in this prediction is x ═ {0.4,0.8333,0.1791}, and the prediction result of the BP neural network is 94.14 m.
And determining that the predictive gear shifting control advance distance is 100m according to a preferred strategy, namely, intervening the predictive gear shifting control strategy when the distance from the uphill is 100 m.
And 4, calculating the required torque of the vehicle passing through the front uphill slope:
Figure BDA0003501112140000121
that is, the required torque for the vehicle to pass through the front uphill is 43278N · m.
Step 5, calculating the maximum torque of the vehicle in each gear, as shown in table 5:
TABLE 5 maximum drive Torque provided in Each Gear
Figure BDA0003501112140000122
Figure BDA0003501112140000131
Wherein, can satisfy the maximum torque that the required torque is close to the fender position, 6 keep off: 56050N · m, 7 th gear: 47045N · m, 8 th gear: 39425N m, the comparison shows that the demanded gear is gear 7.
And 6, acquiring basic gear shifting curve data of each gear of the automatic transmission, wherein the basic gear shifting curve data are respectively an upshift curve and a downshift curve as shown in fig. 3 and 4.
And 7, judging the maximum number of the downshifts which can be stepped more than once, wherein when the dynamic gear shifting is carried out, the gear shifting point is about 1400rpm, and the rotating speed of the engine after the gear shifting is1167rpm, and the shift speed interval is 1167-e(n)＝1400，
Figure BDA0003501112140000132
However, as analyzed above, when the vehicle speed is fast reduced on an uphill slope, the gears are continuously and fast changed, the problems that the gear shifting is frequent, the clutch is always in a slip state and the like are easily caused, and the driving safety is not facilitated, so that the gear-shifting is required to be arranged in a downshifting mode on the uphill slope. Therefore, in the case of the downshifting with more steps, if the rotating speed of the gear shifting point is properly increased to 1450rpm in the downshifting with more steps, the rotating speed interval of the engine is 1007-1450rpm (at the moment ne(n)＝1450，
Figure BDA0003501112140000133
1450 x 1/1.2/1.2 1007), slightly exceeding the maximum torque speed interval, but still guaranteeing power economy. If the gear shifting is carried out in three steps, the engine speed is reduced to an engine-uneconomical speed range (if the gear shifting point is increased to 1500, the range is 868 + 1500, and exceeds 1000 + 1400 of the maximum torque speed range), so the two-step gear shifting is the best choice for ensuring the vehicle dynamic property, the maximum number of the downshiftable gear positions is 2, and the downshifting is determined to be carried out in the embodiment, as shown in fig. 5, the operating range diagram of the step-by-step gear shifting and the downshifting is shown.
At this time, as shown in fig. 6, the current gear is 10, the required gear is 7, the difference is greater than 2, the upshift is limited first, it is determined that the overdrive downshift needs to be performed, the maximum number of the overdrive downshifts of the vehicle is 2, and the overdrive downshift is performed once along with the vehicle speed to reduce the downshift to the 7 gear and is fixed;
and after the gear is in the required gear and the gear is fixed, performing safety check, and maintaining the original gear after the safety check is passed.
And 8, judging the end of the whole uphill process through the road information system signal and finishing the control, namely displaying that the automobile is driven out of the slope at the current moment through the road information system parameter and finishing the whole uphill process.
As shown in fig. 7, it can be seen that the continuous upshifting and downshifting of the driver are avoided, the number of gear changes after the predictive control is applied is three times less than that of the gear changes without the predictive control, the frequent gear shifting is avoided, the number of gear shifting in the ramp is greatly reduced, and the ramp driving safety is ensured.
The invention designs and develops an uphill predictive gear-shifting control method based on road information and machine learning, aiming at an uphill working condition in predictive cruising, an automatic gear-shifting control strategy based on vehicle safety is set according to information such as the maximum gradient, the length of a ramp, the distance from the uphill and the like provided by a road information system, meanwhile, a behavior habit of a driver before uphill is predicted through two machine learning algorithms, the advance distance of predictive gear-shifting control is determined to improve the control effect, and gear predictive automatic control in the uphill process is realized, so that continuous upshifting and downshifting in the uphill process are avoided, accidental gear shifting and frequent gear-shifting are avoided, the number of gear-shifting times of the uphill is reduced, and the driving safety of the ramp is improved on the basis of ensuring the dynamic property of an uphill vehicle.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable to various fields of endeavor for which the invention may be embodied with additional modifications as would be readily apparent to those skilled in the art, and the invention is therefore not limited to the details given herein and to the embodiments shown and described without departing from the generic concept as defined by the claims and their equivalents.

Claims (10)

1. An uphill predictive gear shifting control method based on road information and machine learning is characterized by comprising the following steps:
step one, judging whether the front of the vehicle is on an uphill slope according to vehicle navigation data:
if the front of the vehicle is on an uphill slope, predicting the operation behavior habit of a driver to obtain the advance distance of predictive gear shifting control, and acquiring the horizontal driving distance before the uphill slope, the maximum gradient of the slope, the length of the slope and the vehicle speed as uphill slope parameters;
step two, calculating the required torque of the vehicle passing through the front uphill slope, and determining a required gear;
wherein the vehicle satisfies by a required torque of the front uphill:
Figure FDA0003501112130000011
in the formula, TxG is the total weight of the vehicle, f is the rolling resistance coefficient, CDIs the air resistance coefficient, A is the frontal area of the vehicle, ρ is the air density, u is the air resistance coefficientaFor vehicle speed, i is the maximum slope of the ramp, δ is the rotating mass conversion factor, m is the total mass of the vehicle, r is the wheel radius, ηrTo the wheel mechanical efficiency;
and step three, adjusting the gear of the vehicle to the required gear and finishing gear shifting after the vehicle passes through safety check.
2. The uphill predictive shift control method based on road information and machine learning according to claim 1, wherein the vehicle navigation data is obtained by a road information system, the road information system comprising three-dimensional information of a road ahead during vehicle travel, road shape and distance information, and road adhesion coefficient information.
3. The uphill predictive gear-shifting control method based on road information and machine learning according to claim 2, wherein the predicting the operation behavior habit of the driver to obtain the advance distance of predictive gear-shifting control specifically comprises:
and respectively training and predicting the operation behavior habit data of the driver by using a support vector machine and a BP neural network under the current uphill condition, and preferentially determining the advance distance of predictive gear shifting control according to two prediction results.
4. The uphill predictive shift control method based on road information and machine learning of claim 3, wherein the support vector machine comprises:
the input vector is p ═ p1,p2,p3}；
The output vector is t ═ t1}；
Wherein p is1As a maximum slope parameter of the ramp, p2As a ramp length parameter, p3The maximum gradient parameter of the ramp, the length parameter of the ramp and the vehicle speed parameter are respectively obtained by normalizing the maximum gradient of the ramp, the length of the ramp and the vehicle speed, and t1And after the anti-normalization processing, the data label is obtained.
5. The uphill predictive shift control method based on road information and machine learning according to claim 4, wherein the data labels of the support vector machine are:
and setting the distance between the vehicle and the uphill entrance every 50m when the driver operates the accelerator pedal as a category interval, wherein the data label of the support vector machine is the maximum value of each category interval, and the data label of the support vector machine is used as the prediction result of the support vector machine.
6. The uphill predictive gear-shifting control method based on road information and machine learning according to claim 5, characterized in that the BP neural network is a three-layer structure:
the input layer vector is x ═ x1,x2,x3Mapping the input layer vector to an intermediate layer, wherein the intermediate layer vector is y ═ y1,y2,......,ynThe output layer vector is o ═ o1}；
Wherein x is1As maximum slope parameter, x2As a ramp length parameter, x3The maximum gradient parameter, the ramp length parameter and the vehicle speed parameter are respectively obtained by normalization processing of the maximum gradient of the ramp, the ramp length and the vehicle speed, n is the number of nodes, o1And obtaining a prediction result after the denormalization treatment.
7. The uphill predictive shift control method based on road information and machine learning according to claim 6, wherein the preferentially determining an advance distance of predictive shift control based on two prediction results specifically comprises:
if the prediction result of the support vector machine is greater than the prediction result of the BP neural network, the prediction result of the support vector machine is a final prediction result;
and if the prediction result of the support vector machine is not greater than the prediction result of the BP neural network, adding the prediction result of the BP neural network and the corresponding correction distance to obtain a final prediction result.
8. The hill advance predictive shift control method based on road information and machine learning according to claim 7, characterized in that the determining the required gear specifically includes:
calculating the maximum torque of each gear of the vehicle, wherein the required gear is the maximum gear meeting the required torque;
the maximum torque of the vehicle at each gear meets the following requirements:
Tmaxi＝Ttqmaxkgk0ηT；
in the formula, TmaxiFor maximum torque in each gear of the vehicle, TtqmaxIs the maximum output torque of the engine, kgFor the current gear transmission ratio, k0Is the main reducer transmission ratio etaTThe efficiency of the transmission system is in addition to the wheel.
9. The hill anticipation shift control method based on road information and machine learning of claim 8, wherein the adjusting the vehicle gear to the demanded gear specifically comprises:
calculating the maximum number of gears which can be shifted in a grade-crossing way when the engine runs in an economic rotating speed range:
Figure FDA0003501112130000031
in the formula, ne(n+1)For the post-shift engine speed, ne(n)For the engine speed at the time of gear shifting, qbIs the product of the average ratio of the gear ratios before and after shifting, and qb＝qvQ is the average ratio of the transmission ratio between two adjacent gears of the transmission, and v is the number of gear shifting stages;
if d is0-dpWhen the gear number is larger than v, the transmission repeatedly executes the maximum number of gears capable of being shifted in a stepped mode until a normal gear shifting interval is met, and then the transmission is down shifted along with the vehicle speed until the required gear is fixed;
the normal shift interval is:
if 0 < d0-dpWhen the gear shifting speed is less than v, the transmission limits gear shifting and performs gear shifting along with the vehicle speed according to the basic gear shifting curve of each gear until the gear is required and is fixed;
if d is0-dpWhen the speed is equal to v, the transmission executes the step-by-step downshift along with the vehicle speed until the required gear is reached and is fixed;
if d is0-dpWhen the gear is less than or equal to 0, the limiting gear of the transmission does not exceed the required gear, and the transmission is shifted up along with the vehicle speed until the required gear is fixed;
wherein d is0Is the current gear position, dpThe required gear is adopted.
10. The uphill predictive gear-shifting control method based on road information and machine learning according to claim 9, wherein the safety check specifically comprises:
when the transmission is in the required gear, a is more than or equal to 0m/s when the acceleration of the vehicle is stable2If so, the vehicle keeps the current gear to continue running;
if the acceleration of the vehicle is stable, a is less than 0m/s2If the speed changer reduces the first gear and then maintains the gear, and the vehicle continues to run;
where a is the vehicle acceleration.
CN202210127546.8A 2022-02-11 2022-02-11 Uphill predictive gear shifting control method based on road information and machine learning Active CN114412988B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210127546.8A CN114412988B (en) 2022-02-11 2022-02-11 Uphill predictive gear shifting control method based on road information and machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210127546.8A CN114412988B (en) 2022-02-11 2022-02-11 Uphill predictive gear shifting control method based on road information and machine learning

Publications (2)

Publication Number Publication Date
CN114412988A true CN114412988A (en) 2022-04-29
CN114412988B CN114412988B (en) 2022-11-29

Family

ID=81278496

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210127546.8A Active CN114412988B (en) 2022-02-11 2022-02-11 Uphill predictive gear shifting control method based on road information and machine learning

Country Status (1)

Country Link
CN (1) CN114412988B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115264048A (en) * 2022-07-26 2022-11-01 重庆大学 Automatic transmission intelligent gear decision design method based on data mining
CN115435077A (en) * 2022-08-31 2022-12-06 中国重汽集团济南动力有限公司 Gear control method and device based on heavy-duty vehicle and storage medium
CN117704061A (en) * 2024-01-17 2024-03-15 浙江博通汽车科技有限公司 Gear shifting control method and system for automobile AMT gearbox

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106184208A (en) * 2015-05-07 2016-12-07 比亚迪股份有限公司 The control method of automobile up slope traveling and system
CN107492251A (en) * 2017-08-23 2017-12-19 武汉大学 It is a kind of to be identified and driving condition supervision method based on the driver identity of machine learning and deep learning
CN109101980A (en) * 2018-07-18 2018-12-28 上海理工大学 A kind of automobile weightlessness Detection & Controling method based on machine learning
CN113586706A (en) * 2021-07-09 2021-11-02 东风汽车集团股份有限公司 Automatic gear shifting method based on driving habits of driver and vehicle controller
CN113606329A (en) * 2021-06-25 2021-11-05 东风汽车集团股份有限公司 Vehicle, determination method and determination system of driving mode of vehicle and TCU

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106184208A (en) * 2015-05-07 2016-12-07 比亚迪股份有限公司 The control method of automobile up slope traveling and system
CN107492251A (en) * 2017-08-23 2017-12-19 武汉大学 It is a kind of to be identified and driving condition supervision method based on the driver identity of machine learning and deep learning
CN109101980A (en) * 2018-07-18 2018-12-28 上海理工大学 A kind of automobile weightlessness Detection & Controling method based on machine learning
CN113606329A (en) * 2021-06-25 2021-11-05 东风汽车集团股份有限公司 Vehicle, determination method and determination system of driving mode of vehicle and TCU
CN113586706A (en) * 2021-07-09 2021-11-02 东风汽车集团股份有限公司 Automatic gear shifting method based on driving habits of driver and vehicle controller

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115264048A (en) * 2022-07-26 2022-11-01 重庆大学 Automatic transmission intelligent gear decision design method based on data mining
CN115435077A (en) * 2022-08-31 2022-12-06 中国重汽集团济南动力有限公司 Gear control method and device based on heavy-duty vehicle and storage medium
CN117704061A (en) * 2024-01-17 2024-03-15 浙江博通汽车科技有限公司 Gear shifting control method and system for automobile AMT gearbox
CN117704061B (en) * 2024-01-17 2024-06-04 浙江博通汽车科技有限公司 Gear shifting control method and system for automobile AMT gearbox

Also Published As

Publication number Publication date
CN114412988B (en) 2022-11-29

Similar Documents

Publication Publication Date Title
CN114412988B (en) Uphill predictive gear shifting control method based on road information and machine learning
CN107100993B (en) A kind of fluid drive shift modification method of vehicle mass and hill gradient identification
CN108284836B (en) Vehicle longitudinal following control method
CN102753865B (en) For determining the method with handover optimization gear in the automobile comprising automatic transmission before sailing bend into
EP2440422B1 (en) Module in a vehicle control system
EP2440440B1 (en) Method and module for determining of reference values for a vehicle control system
CN107117170A (en) A kind of real-time estimate cruise control system driven based on economy
CN110792762B (en) Method for controlling prospective gear shifting of commercial vehicle in cruise mode
US9085293B2 (en) Method for controlling shifting in a semi-automatic gear transmission
CN103195917A (en) Control apparatus for vehicle automatic transmission
CN104696504A (en) Vehicle gear shift control method and device
CN105292119A (en) Gear-shifting correction system for automatic transmission and correction method for gear-shifting correction system
JP7195035B2 (en) platooning system
CN113653796B (en) Vehicle AMT gear shifting method based on road parameters
SE0950971A1 (en) Procedure and system for driving a vehicle
JP3126525B2 (en) Automatic transmission control device for automobile
CN103119335A (en) Method for controlling the shifting of an automatic geared transmission
CN111252072A (en) Method for realizing ramp detection processing aiming at pure electric vehicle
CN108227582A (en) The remained capacity control method of vehicle
CN108253134B (en) Load recognition control system for vehicle and functional module architecture
CN105201663B (en) A kind of control method for realizing engine optimal economic rotating speed
CN114658838B (en) Automatic transmission gear control method and computer storage medium
CN113790264B (en) Gear shifting method and gear shifting device of AMT (automated mechanical Transmission)
JP4935065B2 (en) Vehicle driving force control device
CN114427600B (en) Curve predictive gear shifting control strategy based on geographic information and machine learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant