CN110406539A - A kind of method and device identifying vehicle load state - Google Patents
A kind of method and device identifying vehicle load state Download PDFInfo
- Publication number
- CN110406539A CN110406539A CN201910660131.5A CN201910660131A CN110406539A CN 110406539 A CN110406539 A CN 110406539A CN 201910660131 A CN201910660131 A CN 201910660131A CN 110406539 A CN110406539 A CN 110406539A
- Authority
- CN
- China
- Prior art keywords
- torque
- vehicle load
- section
- gear
- speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/12—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to parameters of the vehicle itself, e.g. tyre models
- B60W40/13—Load or weight
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2510/00—Input parameters relating to a particular sub-units
- B60W2510/06—Combustion engines, Gas turbines
- B60W2510/0657—Engine torque
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2510/00—Input parameters relating to a particular sub-units
- B60W2510/10—Change speed gearings
- B60W2510/1005—Transmission ratio engaged
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The embodiment of the present invention provides a kind of method and device for identifying vehicle load state, which comprises determines the torque section of the engine of vehicle;The torque section is the corresponding torque section in gear section that torque percentage is greater than zero;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is determined according to engine speed and speed;It calculates and the index parameter of torque percentage, gear value and the corresponding state of vehicle load for identification of speed in the torque section;All index parameters are inputted to preset vehicle load condition identification model, and determine the recognition result of the vehicle load state according to the output result of the preset vehicle load condition identification model.Described device executes the above method.The method and device of identification vehicle load state provided in an embodiment of the present invention, can accurately identify vehicle load state.
Description
Technical field
The present invention relates to vehicle recongnition technique field more particularly to a kind of method and devices for identifying vehicle load state.
Background technique
The load condition of identification vehicle is with a wide range of applications, such as asks to efficiently solve shedding for slag-soil truck
Topic, it is desirable that tarpaulin is covered when slag-soil truck is fully loaded with;For the slag-soil truck of full load not canopy cover cloth, need to carry out slag-soil truck
Speed limit processing.
The commonplace way of the prior art is exactly: installing weighing sensor to obtain the load-carrying weight of vehicle, then again
Compared with the maximum capacity of the vehicle, thus to judge whether the load condition of vehicle is fully loaded with;Another way is: collecting vehicle
The video image of wagon box, judges whether the load condition of vehicle is fully loaded with by video analysis.But both ways have as follows
Several drawbacks: first, it needs using equipment, such as weighing sensor, video image acquisition device etc., it is at high cost;Second, it is above-mentioned
Equipment installation is more troublesome;Third, under specific usage scenario, such as the use of slag-soil truck so that equipment be more easier by
Damage.
Therefore, how drawbacks described above is avoided, identifies vehicle load state without above equipment, additionally it is possible to accurately identify vehicle
Load condition, becoming need solve the problems, such as.
Summary of the invention
In view of the problems of the existing technology, the embodiment of the present invention provides a kind of method and dress for identifying vehicle load state
It sets.
The embodiment of the present invention provides a kind of method for identifying vehicle load state, comprising:
Determine the torque section of the engine of vehicle;The torque section is the gear section pair that torque percentage is greater than zero
The torque section answered;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is
It is determined according to engine speed and speed;
It calculates and torque percentage, gear value and the speed corresponding vehicle for identification load in the torque section
The index parameter of weight state;
All index parameters are inputted to preset vehicle load condition identification model, and according to the preset vehicle load condition
The output result of identification model determines the recognition result of the vehicle load state;Wherein, the vehicle load state recognition mould
Type is obtained using sample data training neural network;The sample data includes torque percentage, gear value and speed point
Not corresponding data.
The embodiment of the present invention provides a kind of device for identifying vehicle load state, comprising:
Determination unit, the torque section of the engine for determining vehicle;The torque section is that torque percentage is greater than
The corresponding torque section in zero gear section;The difference of any two gear value in the gear section is respectively less than default threshold
Value;The gear value is determined according to engine speed and speed;
Computing unit, for calculate in the torque section torque percentage, gear value and speed it is corresponding
The index parameter of vehicle load state for identification;
Recognition unit, for inputting all index parameters to preset vehicle load condition identification model, and according to described pre-
If the output result of vehicle load state recognition model determines the recognition result of the vehicle load state;Wherein, the vehicle
Load condition identification model is obtained using sample data training neural network;The sample data include torque percentage,
Gear value and the corresponding data of speed.
The embodiment of the present invention provides a kind of electronic equipment, comprising: memory, processor and storage are on a memory and can be
The computer program run on processor, wherein
The processor realizes following method and step when executing the computer program:
Determine the torque section of the engine of vehicle;The torque section is the gear section pair that torque percentage is greater than zero
The torque section answered;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is
It is determined according to engine speed and speed;
It calculates and torque percentage, gear value and the speed corresponding vehicle for identification load in the torque section
The index parameter of weight state;
All index parameters are inputted to preset vehicle load condition identification model, and according to the preset vehicle load condition
The output result of identification model determines the recognition result of the vehicle load state;Wherein, the vehicle load state recognition mould
Type is obtained using sample data training neural network;The sample data includes torque percentage, gear value and speed point
Not corresponding data.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, is stored thereon with computer program, should
Following method and step is realized when computer program is executed by processor:
Determine the torque section of the engine of vehicle;The torque section is the gear section pair that torque percentage is greater than zero
The torque section answered;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is
It is determined according to engine speed and speed;
It calculates and torque percentage, gear value and the speed corresponding vehicle for identification load in the torque section
The index parameter of weight state;
All index parameters are inputted to preset vehicle load condition identification model, and according to the preset vehicle load condition
The output result of identification model determines the recognition result of the vehicle load state;Wherein, the vehicle load state recognition mould
Type is obtained using sample data training neural network;The sample data includes torque percentage, gear value and speed point
Not corresponding data.
The method and device of identification vehicle load state provided in an embodiment of the present invention, passes through the torsion in input torque section
Square percentage, gear value and the corresponding index parameter of speed are to preset vehicle load condition identification model, and according to the mould
The output result of type determines the recognition result of vehicle load state, identifies vehicle load state without equipment such as weighings, additionally it is possible to
Accurately identify vehicle load state.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the embodiment of the method flow chart of present invention identification vehicle load state;
Fig. 2 is the schematic diagram in gear of embodiment of the present invention section;
Fig. 3 is the schematic diagram in torque of embodiment of the present invention section;
Fig. 4 is the schematic diagram of neural network of the embodiment of the present invention;
Fig. 5 is the Installation practice structural schematic diagram of present invention identification vehicle load state;
Fig. 6 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the embodiment of the method flow chart of present invention identification vehicle load state, as shown in Figure 1, the embodiment of the present invention
A kind of method of the identification vehicle load state provided, comprising the following steps:
S101: the torque section of the engine of vehicle is determined;The torque section is the gear that torque percentage is greater than zero
The corresponding torque section in section;The difference of any two gear value in the gear section is respectively less than preset threshold;The shelves
Place value is determined according to engine speed and speed.
Specifically, device determines the torque section of the engine of vehicle;The torque section is that torque percentage is greater than zero
The corresponding torque section in gear section;The difference of any two gear value in the gear section is respectively less than preset threshold;
The gear value is determined according to engine speed and speed.Device can be the equipment etc. comprising processor in vehicle,
It is not especially limited.It should be noted that the power that vehicle advances comes from engine;Full load, the torque meeting of engine output
Increase;When unloaded, the torque of engine output is relatively small.But there also is Railway Projects: during 1. vehicle slidings, hair
Motivation does not need output power, so when torque may be 0;2. vehicle is when at the uniform velocity advancing, regardless of unloaded or fully loaded, hair
The output power of motivation is all smaller, can not thus judge vehicle load state;3. vehicle is in different gears, even together
The zero load of sample is fully loaded, and the torque of engine output is also different.
In view of these problems, the core concept of the recognition methods is: calculating under different gears, has output work in engine
In the period of rate, the summation of the output acting of engine and the acceleration of generation are worth, i.e., the gear of different gears this 3
Value, the summation of engine output acting, acceleration are as the factor for influencing recognition result.
It should be understood that the summation of the output acting of engine can use cumulative and the substitution, gear of torque percentage
Value can be calculated by engine speed with speed, acceleration can be calculated by the variation of speed.Engine speed
It can be by CAN bus from electronic control unit (Electronic Control Unit, referred to as " ECU ") with torque percentage
Middle reading, speed can be read from ECU or from instrument by CAN bus, and speed can also be calculated by pulsed quantity.
Fig. 2 is the schematic diagram in gear of embodiment of the present invention section, is collected as shown in Fig. 2, horizontal axis indicates continuous in time
Each numerical value quantity (such as engine speed, speed, gear value, the revolving speed with Fig. 2, speed * 50 (multiplied by certain numerical value, this
In be 50 for convenient for unified calculation), gear value * 25 respectively corresponds), collection period is identical, i.e., set period intrinsic motivation revolving speed,
Speed, the quantity of gear value acquisition are identical, such as 1~10 corresponding section intrinsic motivation revolving speed, speed, gear value are adopted in Fig. 2
The quantity of collection is all 10.Vertical pivot indicates the specific value size of each numerical value, i.e. Fig. 2 integrally reflect engine speed, speed,
The numerical values recited of gear value with collecting quantity changing rule.
Fig. 3 is the schematic diagram in torque of embodiment of the present invention section, as shown in figure 3, the horizontal axis and vertical pivot in Fig. 3 indicate interior
Appearance is identical as Fig. 2, repeats no more.It should be understood that torque section is that torque percentage is corresponding greater than zero gear section
Torque section, gear section, that is, engine of the torque percentage greater than zero have the gear section of output power, therefore referring to Fig. 3,
It can be seen that the torque siding-to-siding block length in Fig. 3 is smaller than gear siding-to-siding block length.
The torque section of the engine of vehicle can be determined in the following way:
First determine vehicle engine gear section, comprising: according to the sampling period continuously acquire engine speed (e),
Torque percentage (tq) and speed (v), calculate gear value (g) according to revolving speed and speed, have:
G=e/v is wherein (v > 0).
Gear section is determined according to each gear value (g), so that the difference of any two gear value in gear section is small
In preset threshold, further, it is chosen as so that the difference of any two gear value in gear section is respectively less than preset threshold
Longest gear section, i.e., gear section as shown in Figure 2.Preset threshold can be independently arranged according to the actual situation, reference
The convex portion in Fig. 2 middle gear section has respectively corresponded m engine speed value, m vehicle speed value, m gear value, according to fig. 2
As can be seen that this m gear value numerical value is all relatively, and corresponding two gear values in two sides adjacent with the convex portion
Then differ more with any gear value in m gear value of convex portion.
Torque section is determined according to gear section and torque percentage, referring to the corresponding torque hundred of horizontal axis 81~91 in Fig. 3
Dividing ratio is zero, and torque section is the corresponding torque section in gear section that torque percentage is greater than zero, therefore, rejecting horizontal axis 81~
91 corresponding gear sections, the corresponding torque section in remaining gear section are the torque area for determining the engine of obtained vehicle
Between.The torque section has respectively corresponded n engine speed value, n vehicle speed value, n gear value, it is possible to understand that n is less than m.
S102: calculate in the torque section torque percentage, gear value and speed it is corresponding for identification
The index parameter of vehicle load state.
Specifically, device calculates and torque percentage, gear value and the corresponding use of speed in the torque section
In the index parameter of identification vehicle load state.
The calculating of each index parameter can specifically include:
Index parameter corresponding with the torque percentage is calculated according to the following formula:
Wherein, tq_sum is index parameter corresponding with the torque percentage, tqiFor i-th of torque percentage, n
For the quantity of all torque percentages in the torque section.Tq_sum can reflect the size that engine externally does work.
Index parameter corresponding with the gear value is calculated according to the following formula:
Wherein, g_avg is index parameter corresponding with the gear value, giIt is the torque for i-th of gear value, n
The quantity of all gear values in section.All gear values in torque section are averaging to obtain gear average value g_avg.
Index parameter corresponding with the speed is calculated according to the following formula:
Δ v=vmax-vmin
Wherein, Δ v is index parameter corresponding with the speed, vmaxFor in all speeds in the torque section
Maximum value, vminFor the minimum value in all speeds in the torque section.Speed difference Δ v reflects torque section
The acceleration situation of interior vehicle.
S103: inputting all index parameters to preset vehicle load condition identification model, and is carried according to the preset vehicle
The output result of state recognition model determines the recognition result of the vehicle load state again;Wherein, the vehicle load state
Identification model is obtained using sample data training neural network;The sample data include torque percentage, gear value and
The corresponding data of speed.
Specifically, device inputs all index parameters to preset vehicle load condition identification model, and according to described default
The output result of vehicle load state recognition model determines the recognition result of the vehicle load state;Wherein, the vehicle carries
State recognition model is obtained using sample data training neural network again;The sample data includes torque percentage, shelves
Place value and the corresponding data of speed.All index parameters include above-mentioned tq_sum, g_avg, Δ v;The output result can
To include the probability value pf for indicating that vehicle is fully loaded and the probability value pe for indicating vehicle zero load;Correspondingly, according to the preset vehicle
The output result of load condition identification model determines the recognition result of the vehicle load state, specifically includes:
If judgement knows that pf is greater than pe and pf is greater than default loading thresholds dpf, it is determined that the recognition result is at vehicle
In full load condition;The specific value of dpf can be independently arranged according to the actual situation.If judgement knows that pf is less than pe and pe is greater than
Default zero load threshold value dpe, it is determined that the recognition result is that vehicle is in light condition.The specific value of dpe can be according to reality
Border situation is independently arranged.In addition to above-mentioned two situations, it is believed that the output result of the model is invalid.
Fig. 4 is the schematic diagram of neural network of the embodiment of the present invention, as shown in figure 4, the input layer of neural network includes 3 minds
Through member, respectively tq_sum, g_avg, Δ v;Hidden layer is made of x neuron;Output layer includes 2 neurons, respectively table
Show fully loaded probability and unloaded probability.
The training of neural network can be specific as follows:
Neural network needs to obtain the weight file F of network model by study in advance.In neural network learning, need
Prepare a large amount of sample data, these sample datas need to acquire and be obtained by calculation by real vehicle.
Calculating process can be such that
1. the collected data of real vehicle (engine speed, engine output torque percentage, speed) are by asking torque area
Between obtain the data group in c torque section, specifically can refer to above description.
2. the data group in pair each torque section asks tq_sum, g_avg, Δ v, the c group sample number in c torque section is obtained
According to A, each sample A [j] includes 3 data tq_sum, g_avg, Δ v;Wherein j is sample data sum.
3. this A sample is divided into two classes according to the vehicle load situation recorded in advance, one kind is the sample of vehicle full load
This H (include a sample), the sample L (comprising b sample, wherein a+b=c) when one kind is vehicle zero load.
4. a label (tag) is added to each fully loaded sample H [j], and set tag=1;To each zero load sample L [j]
A label (tag) is added, and sets tag=0;Sample each in this way contains 4 data, be respectively tq_sum, g_avg,
Δ v and tag.
5. fully loaded sample H and zero load sample L are merged into learning sample D, then D includes c sample, and each sample includes 4
A data are tq_sum, g_avg, Δ v and tag respectively.
6. duplication portion sample space D is D1.
7. a sample D1 [j] is taken out at random from sample space D1, tq_sum, g_avg, the Δ v in sample D1 [j]
It is input in the neural network of above-mentioned construction, neural network exports output value, asks output's and D1 [j] by loss function
Penalty values between tag adjust the parameter of neural network by optimizer.
8. step 7 is executed repeatedly, until D1 is empty.
9. step 6, step 7, step 8 repeat n times (N > 10000).
10. saving the weighted value of neural network to weight file F, study terminates.
The method of identification vehicle load state provided in an embodiment of the present invention, passes through the torque percentage in input torque section
Index parameter more corresponding than, gear value and speed is to preset vehicle load condition identification model, and according to the defeated of the model
Result determines the recognition result of vehicle load state out, identifies vehicle load state without equipment such as weighings, additionally it is possible to accurate to know
Other vehicle load state.
On the basis of the above embodiments, the output result includes the probability value pf for indicating that vehicle is fully loaded and expression vehicle
Unloaded probability value pe;Correspondingly, described according to the determination of the output result of the preset vehicle load condition identification model
The recognition result of vehicle load state, comprising:
If judgement knows that pf is greater than pe and pf is greater than default loading thresholds dpf, it is determined that the recognition result is at vehicle
In full load condition.
Specifically, if device judgement knows that pf is greater than pe and pf is greater than default loading thresholds dpf, it is determined that the identification
As a result full load condition is in for vehicle.It can refer to above description, repeat no more.
If judgement knows that pf is less than pe and pe is greater than default unloaded threshold value dpe, it is determined that the recognition result is at vehicle
In light condition.
Specifically, if device judgement knows that pf is less than pe and pe is greater than default unloaded threshold value dpe, it is determined that the identification
As a result light condition is in for vehicle.It can refer to above description, repeat no more.
The method of identification vehicle load state provided in an embodiment of the present invention, by indicating vehicle fully loaded probability value and table
Show the comparison result between the probability value of vehicle zero load and the comparison result with corresponding threshold value, is further able to standard
Really identification vehicle load state.
On the basis of the above embodiments, the gear value is determined according to engine speed and speed, comprising:
The gear value is calculated according to the following formula:
G=e/v
Wherein, g is the gear value, e is the engine speed, v is the speed.
Specifically, device calculates the gear value according to the following formula:
G=e/v
Wherein, g is the gear value, e is the engine speed, v is the speed.It can refer to above description, no longer
It repeats.
The method of identification vehicle load state provided in an embodiment of the present invention, calculates gear value by specific formula, guarantees
This method can be normally carried out.
On the basis of the above embodiments, the calculating and torque percentage, gear value and the vehicle in the torque section
The index parameter of the corresponding state of vehicle load for identification of speed, comprising:
Index parameter corresponding with the torque percentage is calculated according to the following formula:
Wherein, tq_sum is index parameter corresponding with the torque percentage, tqiFor i-th of torque percentage, n
For the quantity of all torque percentages in the torque section.
Specifically, device calculates index parameter corresponding with the torque percentage according to the following formula:
Wherein, tq_sum is index parameter corresponding with the torque percentage, tqiFor i-th of torque percentage, n
For the quantity of all torque percentages in the torque section.It can refer to above description, repeat no more.
The method of identification vehicle load state provided in an embodiment of the present invention, is calculated and torque percentage by specific formula
Corresponding index parameter helps further to accurately identify vehicle load state.
On the basis of the above embodiments, the calculating and torque percentage, gear value and the vehicle in the torque section
The index parameter of the corresponding state of vehicle load for identification of speed, comprising:
Index parameter corresponding with the gear value is calculated according to the following formula:
Wherein, g_avg is index parameter corresponding with the gear value, giIt is the torque for i-th of gear value, n
The quantity of all gear values in section.
Specifically, device calculates index parameter corresponding with the gear value according to the following formula:
Wherein, g_avg is index parameter corresponding with the gear value, giIt is the torque for i-th of gear value, n
The quantity of all gear values in section.It can refer to above description, repeat no more.
The method of identification vehicle load state provided in an embodiment of the present invention, is calculated opposite with gear value by specific formula
The index parameter answered helps further to accurately identify vehicle load state.
On the basis of the above embodiments, the calculating and torque percentage, gear value and the vehicle in the torque section
The index parameter of the corresponding state of vehicle load for identification of speed, comprising:
Index parameter corresponding with the speed is calculated according to the following formula:
Δ v=vmax-vmin
Wherein, Δ v is index parameter corresponding with the speed, vmaxFor in all speeds in the torque section
Maximum value, vminFor the minimum value in all speeds in the torque section.
Specifically, device calculates index parameter corresponding with the speed according to the following formula:
Δ v=vmax-vmin
Wherein, Δ v is index parameter corresponding with the speed, vmaxFor in all speeds in the torque section
Maximum value, vminFor the minimum value in all speeds in the torque section.It can refer to above description, repeat no more.
The method of identification vehicle load state provided in an embodiment of the present invention, is calculated corresponding with speed by specific formula
Index parameter, help further to accurately identify vehicle load state.
Fig. 5 is the Installation practice structural schematic diagram of present invention identification vehicle load state, as shown in figure 5, the present invention is real
It applies example and provides a kind of device for identifying vehicle load state, including determination unit 501, computing unit 502 and recognition unit
503, in which:
Determination unit 501 is used to determine the torque section of the engine of vehicle;The torque section is that torque percentage is big
In the zero corresponding torque section in gear section;The difference of any two gear value in the gear section is respectively less than default threshold
Value;The gear value is determined according to engine speed and speed;Computing unit 502 is in calculating and the torque section
Torque percentage, gear value and the corresponding state of vehicle load for identification of speed index parameter;Recognition unit 503
It is identified for inputting all index parameters to preset vehicle load condition identification model, and according to the preset vehicle load condition
The output result of model determines the recognition result of the vehicle load state;Wherein, the vehicle load state recognition model is
It is obtained using sample data training neural network;The sample data includes that torque percentage, gear value and speed are right respectively
The data answered.
Specifically, determination unit 501 is used to determine the torque section of the engine of vehicle;The torque section is torque hundred
Divide torque section more corresponding than the gear section for being greater than zero;The difference of any two gear value in the gear section is respectively less than
Preset threshold;The gear value is determined according to engine speed and speed;Computing unit 502 is for calculating and the torque
The index parameter of the corresponding state of vehicle load for identification of torque percentage, gear value and speed in section;Identification
Unit 503 is for inputting all index parameters to preset vehicle load condition identification model, and according to the preset vehicle load-carrying
The output result of state recognition model determines the recognition result of the vehicle load state;Wherein, the vehicle load state is known
Other model is obtained using sample data training neural network;The sample data includes torque percentage, gear value and vehicle
The corresponding data of speed.
The device of identification vehicle load state provided in an embodiment of the present invention, passes through the torque percentage in input torque section
Index parameter more corresponding than, gear value and speed is to preset vehicle load condition identification model, and according to the defeated of the model
Result determines the recognition result of vehicle load state out, identifies vehicle load state without equipment such as weighings, additionally it is possible to accurate to know
Other vehicle load state.
It is real that the device of identification vehicle load state provided in an embodiment of the present invention specifically can be used for executing above-mentioned each method
The process flow of example is applied, details are not described herein for function, is referred to the detailed description of above method embodiment.
Fig. 6 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention, as shown in fig. 6, the electronic equipment
It include: processor (processor) 601, memory (memory) 602 and bus 603;
Wherein, the processor 601, memory 602 complete mutual communication by bus 603;
The processor 601 is used to call the program instruction in the memory 602, to execute above-mentioned each method embodiment
Provided method, for example, determine the torque section of the engine of vehicle;The torque section is that torque percentage is greater than
The corresponding torque section in zero gear section;The difference of any two gear value in the gear section is respectively less than default threshold
Value;The gear value is determined according to engine speed and speed;It calculates and torque percentage, the shelves in the torque section
The index parameter of place value and the corresponding state of vehicle load for identification of speed;All index parameters are inputted to preset vehicle
Load condition identification model, and the vehicle load is determined according to the output result of the preset vehicle load condition identification model
The recognition result of state;Wherein, the vehicle load state recognition model is obtained using sample data training neural network;
The sample data includes torque percentage, gear value and the corresponding data of speed.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out method provided by above-mentioned each method embodiment, for example, determines the engine of vehicle
Torque section;The torque section is the corresponding torque section in gear section that torque percentage is greater than zero;The gear area
Between in the difference of any two gear value be respectively less than preset threshold;The gear value is determined according to engine speed and speed
's;It calculates and torque percentage, gear value and the corresponding vehicle load shape for identification of speed in the torque section
The index parameter of state;All index parameters are inputted to preset vehicle load condition identification model, and are carried according to the preset vehicle
The output result of state recognition model determines the recognition result of the vehicle load state again;Wherein, the vehicle load state
Identification model is obtained using sample data training neural network;The sample data include torque percentage, gear value and
The corresponding data of speed.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute method provided by above-mentioned each method embodiment, example
Such as comprise determining that the torque section of the engine of vehicle;The torque section is the gear section pair that torque percentage is greater than zero
The torque section answered;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is
It is determined according to engine speed and speed;It calculates and distinguishes with torque percentage, gear value and the speed in the torque section
The index parameter of the corresponding state of vehicle load for identification;It inputs all index parameters to preset vehicle load condition and identifies mould
Type, and determine according to the output result of the preset vehicle load condition identification model identification knot of the vehicle load state
Fruit;Wherein, the vehicle load state recognition model is obtained using sample data training neural network;The sample data
Including torque percentage, gear value and the corresponding data of speed.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (9)
1. a kind of method for identifying vehicle load state characterized by comprising
Determine the torque section of the engine of vehicle;The torque section is that torque percentage is corresponding greater than zero gear section
Torque section;The difference of any two gear value in the gear section is respectively less than preset threshold;The gear value is basis
What engine speed and speed determined;
It calculates and torque percentage, gear value and the corresponding vehicle load shape for identification of speed in the torque section
The index parameter of state;
All index parameters are inputted to preset vehicle load condition identification model, and are identified according to the preset vehicle load condition
The output result of model determines the recognition result of the vehicle load state;Wherein, the vehicle load state recognition model is
It is obtained using sample data training neural network;The sample data includes that torque percentage, gear value and speed are right respectively
The data answered.
2. the method for identification vehicle load state according to claim 1, which is characterized in that the output result includes table
Show the fully loaded probability value pf of vehicle and indicates the probability value pe of vehicle zero load;Correspondingly, described according to the preset vehicle load-carrying
The output result of state recognition model determines the recognition result of the vehicle load state, comprising:
If judgement knows that pf is greater than pe and pf is greater than default loading thresholds dpf, it is determined that the recognition result is that vehicle is in full
Load state;
If judgement knows that pf is less than pe and pe is greater than default unloaded threshold value dpe, it is determined that the recognition result is that vehicle is in sky
Load state.
3. the method for identification vehicle load state according to claim 1, which is characterized in that according to engine speed and vehicle
Speed determines the gear value, comprising:
The gear value is calculated according to the following formula:
G=e/v
Wherein, g is the gear value, e is the engine speed, v is the speed.
4. it is according to any one of claims 1 to 3 identification vehicle load state method, which is characterized in that it is described calculating with
The index of torque percentage, gear value and the corresponding state of vehicle load for identification of speed in the torque section is joined
Number, comprising:
Index parameter corresponding with the torque percentage is calculated according to the following formula:
Wherein, tq_sum is index parameter corresponding with the torque percentage, tqiIt is described for i-th of torque percentage, n
The quantity of all torque percentages in torque section.
5. it is according to any one of claims 1 to 3 identification vehicle load state method, which is characterized in that it is described calculating with
The index of torque percentage, gear value and the corresponding state of vehicle load for identification of speed in the torque section is joined
Number, comprising:
Index parameter corresponding with the gear value is calculated according to the following formula:
Wherein, g_avg is index parameter corresponding with the gear value, giIt is in the torque section for i-th of gear value, n
All gear values quantity.
6. it is according to any one of claims 1 to 3 identification vehicle load state method, which is characterized in that it is described calculating with
The index of torque percentage, gear value and the corresponding state of vehicle load for identification of speed in the torque section is joined
Number, comprising:
Index parameter corresponding with the speed is calculated according to the following formula:
Δ v=vmax-vmin
Wherein, Δ v is index parameter corresponding with the speed, vmaxFor in all speeds in the torque section most
Big value, vminFor the minimum value in all speeds in the torque section.
7. a kind of device for identifying vehicle load state characterized by comprising
Determination unit, the torque section of the engine for determining vehicle;The torque section is that torque percentage is greater than zero
The corresponding torque section in gear section;The difference of any two gear value in the gear section is respectively less than preset threshold;Institute
Stating gear value is determined according to engine speed and speed;
Computing unit, for calculating and the torque percentage in the torque section, gear value and speed is corresponding is used for
Identify the index parameter of vehicle load state;
Recognition unit, for inputting all index parameters to preset vehicle load condition identification model, and according to the default vehicle
The output result of load condition identification model determines the recognition result of the vehicle load state;Wherein, the vehicle load
State recognition model is obtained using sample data training neural network;The sample data includes torque percentage, gear
It is worth data corresponding with speed.
8. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized when executing described program such as any one of claim 1 to 6 the method
Step.
9. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer journey
It is realized when sequence is executed by processor such as the step of any one of claim 1 to 6 the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910660131.5A CN110406539A (en) | 2019-07-22 | 2019-07-22 | A kind of method and device identifying vehicle load state |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910660131.5A CN110406539A (en) | 2019-07-22 | 2019-07-22 | A kind of method and device identifying vehicle load state |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110406539A true CN110406539A (en) | 2019-11-05 |
Family
ID=68362302
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910660131.5A Pending CN110406539A (en) | 2019-07-22 | 2019-07-22 | A kind of method and device identifying vehicle load state |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110406539A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689723A (en) * | 2019-11-06 | 2020-01-14 | 北京交通大学 | Truck overload identification method based on power distribution and vehicle self-learning |
CN113173175A (en) * | 2021-06-09 | 2021-07-27 | 一汽解放汽车有限公司 | Vehicle weight determination method and device |
US11661760B1 (en) | 2022-01-24 | 2023-05-30 | China Three Gorges Co., Ltd. | Longitudinal seam caulking and monitoring restore device and longitudinal seam caulking restore method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103984229A (en) * | 2014-05-04 | 2014-08-13 | 新乡市起重机厂有限公司 | Neural network control method for speed regulating system of hoisting mechanism of tower crane |
CN107680375A (en) * | 2017-09-29 | 2018-02-09 | 深圳市易成自动驾驶技术有限公司 | A kind of vehicle load computational methods, device and storage medium |
CN107901916A (en) * | 2017-11-15 | 2018-04-13 | 康明斯天远(河北)科技有限公司 | A kind of vehicle load acquisition methods that need not be installed in addition with sensor |
CN108305350A (en) * | 2018-01-05 | 2018-07-20 | 杭州鸿泉物联网技术股份有限公司 | A kind of vehicle load state identification method and system |
CN109377046A (en) * | 2018-10-18 | 2019-02-22 | 上海经达信息科技股份有限公司 | Overload of vehicle method of discrimination, system and device based on BP neural network |
CN109767023A (en) * | 2019-01-16 | 2019-05-17 | 北京经纬恒润科技有限公司 | A kind of predictor method and system of vehicle load state |
CN109767520A (en) * | 2019-01-11 | 2019-05-17 | 清华四川能源互联网研究院 | A kind of vehicle load processing method and processing device |
CN109808699A (en) * | 2017-11-16 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of method and system for estimating vehicle load |
-
2019
- 2019-07-22 CN CN201910660131.5A patent/CN110406539A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103984229A (en) * | 2014-05-04 | 2014-08-13 | 新乡市起重机厂有限公司 | Neural network control method for speed regulating system of hoisting mechanism of tower crane |
CN107680375A (en) * | 2017-09-29 | 2018-02-09 | 深圳市易成自动驾驶技术有限公司 | A kind of vehicle load computational methods, device and storage medium |
CN107901916A (en) * | 2017-11-15 | 2018-04-13 | 康明斯天远(河北)科技有限公司 | A kind of vehicle load acquisition methods that need not be installed in addition with sensor |
CN109808699A (en) * | 2017-11-16 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of method and system for estimating vehicle load |
CN108305350A (en) * | 2018-01-05 | 2018-07-20 | 杭州鸿泉物联网技术股份有限公司 | A kind of vehicle load state identification method and system |
CN109377046A (en) * | 2018-10-18 | 2019-02-22 | 上海经达信息科技股份有限公司 | Overload of vehicle method of discrimination, system and device based on BP neural network |
CN109767520A (en) * | 2019-01-11 | 2019-05-17 | 清华四川能源互联网研究院 | A kind of vehicle load processing method and processing device |
CN109767023A (en) * | 2019-01-16 | 2019-05-17 | 北京经纬恒润科技有限公司 | A kind of predictor method and system of vehicle load state |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689723A (en) * | 2019-11-06 | 2020-01-14 | 北京交通大学 | Truck overload identification method based on power distribution and vehicle self-learning |
WO2021088381A1 (en) * | 2019-11-06 | 2021-05-14 | 北京交通大学 | Power distribution and vehicle self-learning-based truck overload identification method |
CN113173175A (en) * | 2021-06-09 | 2021-07-27 | 一汽解放汽车有限公司 | Vehicle weight determination method and device |
US11661760B1 (en) | 2022-01-24 | 2023-05-30 | China Three Gorges Co., Ltd. | Longitudinal seam caulking and monitoring restore device and longitudinal seam caulking restore method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110406539A (en) | A kind of method and device identifying vehicle load state | |
CN110956202B (en) | Image training method, system, medium and intelligent device based on distributed learning | |
CN110533032A (en) | A kind of method and apparatus obtaining high-purity cryogenic steel | |
CN110301920A (en) | Multi-modal fusion method and device for psychological pressure detection | |
CN115457395A (en) | Lightweight remote sensing target detection method based on channel attention and multi-scale feature fusion | |
CN104883158B (en) | The filtering method and filter of acceleration pedal of electric automobile signal | |
CN109625033A (en) | ATO controls accurate shutdown phase stopping accuracy prediction technique and device when vehicle | |
CN110689070A (en) | Training method and device of business prediction model | |
CN109910819A (en) | A kind of environment inside car setting method, device, readable storage medium storing program for executing and terminal device | |
CN116502175A (en) | Method, device and storage medium for diagnosing fault of graph neural network | |
CN113392937A (en) | 3D point cloud data classification method and related device thereof | |
CN108305350A (en) | A kind of vehicle load state identification method and system | |
CN115969329A (en) | Sleep staging method, system, device and medium | |
CN113591509A (en) | Training method of lane line detection model, image processing method and device | |
CN115169809A (en) | Smart city evaluation method and device | |
CN114283321A (en) | Target vehicle detection method and device and computer | |
CN113554350A (en) | Activity evaluation method and apparatus, electronic device and computer readable storage medium | |
CN113435324A (en) | Vehicle target detection method and device and computer readable storage medium | |
CN116350190B (en) | Driving capability determining method, electronic equipment and storage medium | |
CN115063986B (en) | Tunnel exit safety vehicle speed calculation method and device | |
CN111461932A (en) | Administrative punishment discretion rationality assessment method and device based on big data | |
CN116225708A (en) | GPU resource scheduling method and device | |
CN113837220A (en) | Robot target identification method, system and equipment based on online continuous learning | |
CN109858561A (en) | Body-sensing prediction technique, device and terminal | |
CN111914765B (en) | Service area environment comfort level detection method and device and readable 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
RJ01 | Rejection of invention patent application after publication |