CN109767023A - A kind of predictor method and system of vehicle load state - Google Patents
A kind of predictor method and system of vehicle load state Download PDFInfo
- Publication number
- CN109767023A CN109767023A CN201910039360.5A CN201910039360A CN109767023A CN 109767023 A CN109767023 A CN 109767023A CN 201910039360 A CN201910039360 A CN 201910039360A CN 109767023 A CN109767023 A CN 109767023A
- Authority
- CN
- China
- Prior art keywords
- data
- target vehicle
- running data
- training sample
- load condition
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of predictor methods of vehicle load state, comprising: obtains the running data of target vehicle；The running data is pre-processed, effective running data is obtained；According to effective running data, training sample is divided；Calculate characteristic parameter relevant to load condition in the training sample；Clustering algorithm is carried out according to the characteristic parameter, obtains the load condition estimation results of the target vehicle.Above-mentioned predictor method can carry out load condition estimation based on the running data for the vehicle intelligent terminal that vehicle itself is installed, and not need installation load measuring sensor.
Description
Technical field
The present invention relates to technical field of automotive electronics more particularly to a kind of predictor methods and system of vehicle load state.
Background technique
All kinds of haulage vehicle ownerships of China are continuously improved at present, and the requirement to carrying capacity also constantly enhances.It needs fast
The fast loading situation for grasping haulage vehicle in time, just can be reduced no-load ratio in this way, improve market carrying capacity.Vehicle load at present
The acquisition modes of state are usually to install load measuring sensor additional on vehicle chassis, in the process of moving can real-time detection vehicle cargo
Unloaded and full load conditions.
Inventor carries out the study found that load measuring sensor holds in use the acquisition methods of existing vehicle load state
Easy to damage and maintenance cost is high.
Summary of the invention
In view of this, the present invention provides the predictor methods and system of a kind of vehicle load state, to solve existing skill
The problem that load measuring sensor is easily damaged in use in art and maintenance cost is high.Concrete scheme is as follows:
A kind of predictor method of vehicle load state, comprising:
Obtain the running data of target vehicle；
The running data is pre-processed, effective running data is obtained；
According to effective running data, training sample is divided；
Calculate characteristic parameter relevant to load condition in the training sample；
Clustering algorithm is carried out according to the characteristic parameter, obtains the load condition estimation results of the target vehicle.
Above-mentioned method, it is optionally, described according to effective running data, divide training sample, comprising:
Judge whether the target vehicle is in dead ship condition according to effective running data；
If being in the dead ship condition, judge whether parking duration reaches preset time threshold, it, will parking if reaching
The data of front and back are divided into two training samples；If not up to, the data of the parking front and back and of short duration shutdown phase are returned
Enter in the same training sample.
Above-mentioned method, it is optionally, described to judge whether vehicle is in dead ship condition, comprising:
Obtain speed, mileage variable quantity and the engine speed of the target vehicle；
If the speed is zero, the mileage variable quantity is less than pre-set limit, the engine speed is less than preset rotation speed
Limit value then judges that the target vehicle is in halted state.
Above-mentioned method, it is optionally, described to calculate characteristic parameter relevant to load condition in the training sample, packet
It includes:
Obtain the speed of the target vehicle；
According to the speed, running time and instantaneous oil consumption of the target vehicle in the state of giving it the gun are screened；
According to the speed, kinetic energy factor is calculated；
According to the instantaneous oil consumption and the running time, fuel consumption is calculated；
Acceleration is calculated according to the speed and the running time.
Above-mentioned method, it is optionally, described to carry out clustering algorithm according to the characteristic parameter, obtain the target vehicle
Load condition estimation results, comprising:
Determine required cluster classification number；
Using K-meas clustering algorithm, the characteristic parameter is clustered according to the cluster classification number, obtains institute
State the load condition estimation results of target vehicle.
Above-mentioned method, optionally, the cluster classification number are 2.
Above-mentioned method optionally clusters the characteristic parameter according to the cluster classification number, obtains described
The load condition estimation results of target vehicle, comprising:
According to cluster result, the data sample for the state of giving it the gun adds data label；
Give it the gun the data label of state according to described in, determine driven at a constant speed in same training sample, Reduced Speed Now and
The data label of dead ship condition；
The number that the different types of data label occurs in the same training sample is counted, frequency of occurrence is most
Target labels of the data label as the same training sample；
According to the target labels, the load condition estimation results of the target vehicle are determined.
Above-mentioned method, it is optionally, described according to the target labels, determine that the load condition of the target vehicle is estimated
As a result, comprising:
The data label of the target vehicle according to known load condition determines that each data label represents
The load condition type.
A kind of Prediction System of vehicle load state, comprising:
Module is obtained, for obtaining the running data of target vehicle；
Preprocessing module obtains effective running data for pre-processing to the running data；
Division module, for dividing training sample according to effective running data；
Computing module, for calculating characteristic parameter relevant to load condition in the training sample；
Cluster module obtains the load condition of the target vehicle for carrying out clustering algorithm according to the characteristic parameter
Estimation results.
Above-mentioned system, optionally, the division module includes:
First judgment module, for judging whether vehicle is in dead ship condition according to effective running data；
Second judgment module, for when the first judgment module judging result, which is, is, judging whether parking duration reaches
To preset time threshold, if reaching, the data of parking front and back are divided into two training samples；If not up to, by institute
The data for stating parking front and back and of short duration shutdown phase are included into the same training sample.
Compared with prior art, the present invention includes the following advantages:
The invention discloses a kind of predictor methods of vehicle load state, comprising: the running data of target vehicle is obtained, it will
Running data is pre-processed to obtain effective running data, and effective running data is divided into different training samples, meter
Characteristic parameter relevant to load condition in each training sample is calculated, clustering algorithm is carried out to characteristic parameter, obtains the target
The estimation results of the load condition of vehicle, it is no longer necessary to install load measuring sensor and load condition is estimated.
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 only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of predictor method flow chart of vehicle load state disclosed in the embodiment of the present application；
Fig. 2 is a kind of another flow chart of predictor method of vehicle load state disclosed in the embodiment of the present application；
Fig. 3 is a kind of another flow chart of predictor method of vehicle load state disclosed in the embodiment of the present application；
Fig. 4 is a kind of another flow chart of predictor method of vehicle load state disclosed in the embodiment of the present application；
Fig. 5 is a kind of Prediction System structural block diagram of vehicle load state disclosed in the embodiment of the present application.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The invention discloses a kind of predictor method of vehicle load state, the predictor method is applied in all kinds of haulage vehicles
In the estimation procedure of load condition, the execution process of the predictor method as shown in Figure 1, comprising steps of
S101, the running data for obtaining target vehicle；
In the embodiment of the present invention, running data is the vehicle intelligent terminal equipment (example by being mounted on the target vehicle
Such as TBOX) upload to car networking service background, wherein the running data be a period of time running data, each when
Corresponding one group of running data parameter is carved, running data reflects the real time running state of vehicle, such as every group of running data parameter can
It includes at least: time (t), speed (VhlSpd), engine speed (EngSpd), mileage (ODO) and instantaneous oil consumption
(FuelRate), data sampling frequency is to upload within every 30 seconds once (to can also be used for data transmission environments of the frequency less than 1 time/30s
Under, set according to user demand).
S102, the running data is pre-processed, obtains effective running data；
In the embodiment of the present invention, when GPS signal strength is low or engine misses/starting, the mark running data has
There may be abnormal data, this, which will result in car networking data, has signal quality, it is necessary first to the running data
It is pre-processed, pretreatment main purpose is to reject problem data.Common data quality problem includes following several:
(1) same timestamp uploads a plurality of running data；
In the embodiment of the present invention, when same timestamp uploads a plurality of running data, screened by window function with for the moment
Between the vehicle that uploads sail data, select upload target travel data of the last item data as current time stamp.
(2) dropouts such as mileage or vehicle speed data；
In the embodiment of the present invention, when the dropouts such as mileage or vehicle speed data, lost by window function extraction
The signals such as the mileage of mistake or vehicle speed data, a nearest non-empty running data of selection distance are filled.
(3) mileage signal jumps；
In the embodiment of the present invention, incremental characteristic is presented in the numerical value of mileage signal, and in two kinds of situation, one is jumps for jump
Normal zone of reasonableness out is negative value one is jump (current mileage is less than last moment mileage).Processing mode is as follows: according to upper
The frequency for passing data is 1 time/30s, vehicle maximum speed limit 100km/h, former and later two moment mileage travelled jump amount limit values are about
833m, by taking current time as an example, if the jump range of a mileage is excessive (833m or more) on current chainage, then it is assumed that
The process error that this time mileage uploads, directly filters out the data at current time；If jump range is that (mileage value subtracts negative value
It is small), then current time mileage is replaced by the way of the mileage averaged at upper one and next moment.
In the embodiment of the present invention, the condition of the running data is extracted to above-mentioned several problem numbers by window function setting
According to the operation for taking merging, filling or deletion.
S103, according to effective running data, divide training sample；
In the embodiment of the present invention, it is considered that, vehicle continuously drive or refuel, driver's rest etc. of short duration was stopped
The case where in journey, load condition be will not change, and load condition can change is vehicle parking front and back for a long time.Therefore, according to vehicle
The length of time of parking divides effective running data, i.e., described in the down time determination according to the target vehicle
The training sample number that target travel data sample includes, when docking process is shorter, by of short duration parking and the number of parking front and back
According to being included into the same training sample, if down time is too long, the data of parking front and back are divided into two training samples, for
The data of dead ship condition between two training samples can incorporate into any one training sample adjacent thereto for carry out after
Continuous machine learning algorithm.
S104, characteristic parameter relevant to load condition in the training sample is calculated；
In the embodiment of the present invention, includes of short duration dead ship condition in each training sample, drives at a constant speed state and accelerate row
The data sample for sailing state, Reduced Speed Now state, screens it, obtains the data sample of state wherein included of giving it the gun
This, calculates in each status data sample that gives it the gun that there are associated acceleration informations, kinetic energy factor number with load condition
According to fuel consumption data, it should be noted that load condition is incessantly only related to above-mentioned several characteristic parameters, remaining can reflect
The parameter of load condition all can serve as characteristic parameter extraction, the present invention to the type of parameter without limitation.
S105, clustering algorithm is carried out according to the characteristic parameter, obtains the load condition estimation results of the target vehicle.
In the embodiment of the present invention, the acceleration information, the kinetic energy factor data and the fuel consumption data are used
Clustering algorithm is clustered, and the load condition estimation results of the target vehicle are obtained, wherein the number of the cluster classification can
To be set according to actual conditions, the clustering algorithm can be K-means, K-MEDOIDS, Clara and Clarans etc..
The invention discloses a kind of predictor methods of vehicle load state, comprising: the running data of target vehicle is obtained, it will
Running data is pre-processed to obtain effective running data, and effective running data is divided into different training samples, meter
Characteristic parameter relevant to load condition in each training sample is calculated, clustering algorithm is carried out to characteristic parameter, obtains the target
The estimation results of the load condition of vehicle, it is no longer necessary to install load measuring sensor and load condition is estimated.
In the embodiment of the present invention, during carrying out clustering, by acceleration information, kinetic energy factor data and oil consumption
Data are measured as input, load condition estimation results are as output.Process of cluster analysis as shown in Fig. 2, comprising steps of
S201, training sample is divided, filters out the status data that gives it the gun in the training sample；
In the embodiment of the present invention, effective running data is divided into using method described in S101-S103 by different training
Sample filters out the data sample for each state of giving it the gun for including in the training sample, calculates each and give it the gun
There are associated acceleration information, kinetic energy factor data and fuel consumption data with load condition in status data sample.
S202, it determines cluster classification, the status data that gives it the gun in the training sample is clustered；
In the embodiment of the present invention, because carrier vehicle is in fully loaded and unloaded two states mostly in practice, therefore with cluster
Classification is to be illustrated (cluster classification number can be according to actual conditions depending on) for 2 classes, using K-means clustering algorithm by institute
Stating all data aggregates in each status data sample that gives it the gun is two classes, obtains 0 and 1 data label, 0 and 1 represent
Fully loaded and unloaded two different states, need subsequent operation to determine specific corresponding to relationship.
S203, data label is determined for driving at a constant speed in the training sample, Reduced Speed Now and dead ship condition；
According to nearby principle, running data non-classified in same training sample (including is driven at a constant speed into status data sample
Originally, Reduced Speed Now state and parking status data sample or other transport condition data samples) it also adds and adjacent upper one
Classified (or next section of classified, selection according to the actual situation) the identical data label of running data label of section.So far,
All running datas in training sample T, which all mark, has gone up data label.
In addition, in embodiments of the present invention, the running data label in same training sample uses the principle voted,
Choose weight in 0 and 1 it is big (can using frequency of occurrence number define) label as the training sample unique objects label.
It is illustrated below: if comprising following data parameters in some training sample T divided:
Wherein, t1~tiAnd tj~tnCorresponding is the status data sample that gives it the gun, then according to the data in time period
Characteristic parameter is extracted, and carries out focusing solutions analysis, obtains 0 or 1 data label；ti+1~tj-1It is corresponding be at the uniform velocity, slow down
Or dead ship condition, therefore, the running data in the stage marks without clustering algorithm and above sails data label phase with lastrow
Same label.Finally, according to the number of the label number of data label 0 and 1 in this training sample T, by the mark more than frequency of occurrence
The target labels of training sample T thus are arranged in label.
S204, the load condition for determining data label.
In the embodiment of the present invention, and not yet explicitly 0 and 1 which kind of load condition (unloaded or fully loaded) is specifically corresponded to, according to known to
The data label of the target vehicle of load condition determines the load condition type that each data label represents.
For example, it is assumed that cluster classification number is 2 (fully loaded and unloaded), it is known that target vehicle is in full load condition, obtains by clustering algorithm
The data label of target vehicle time period out is 1, can represent full load condition for 1,0 represents light condition.This is only one
The illustrative method of kind, is not limited to the above method particularly for the determination process of load condition representated by data label.
Finally obtain the empty full load condition at the target vehicle each moment.The preset state estimations model can be disposed
In offline environment, load condition identification is carried out to a large amount of history car networking data, on the other hand can also be deployed in car networking service
Platform, the load condition of each haulage vehicle of online query.
The invention discloses a kind of predictor methods of vehicle load state, comprising: the running data of target vehicle is obtained, it will
Running data is pre-processed to obtain effective running data, and effective running data is divided into different training samples, meter
Characteristic parameter relevant to load condition in the training sample is calculated, clustering algorithm is carried out to the characteristic parameter, is obtained described
The estimation results of the load condition of target vehicle, it is no longer necessary to install load measuring sensor and load condition is estimated.
It is described according to effective running data in the embodiment of the present invention, divide method flow such as Fig. 3 institute of training sample
Show, comprising steps of
S301, judge whether the target vehicle is in dead ship condition according to effective running data；
In the embodiment of the present invention, each moment speed in effective running data sample is obtained in car networking service background
VhlSpd (km/h), mileage ODO (km), engine speed EngSpd (rpm).Wherein, according to the mileage ODO at each moment
(km), mileage ODO (km) variable quantity of corresponding period is determined.According to the vehicle velocity V hlSpd (km/h), the mileage ODO
(km) variable quantity, engine speed EngSpd (rpm) signal judges dead ship condition.
Judge whether speed, mileage variable quantity and the engine speed at each moment meet corresponding threshold value.The present invention
In embodiment, if the speed is zero, the mileage variable quantity less than 0.1 and the engine speed be less than idling speed or
It is all satisfied requirement for 0, then judges that the target vehicle is in halted state.If either condition is unsatisfactory for requiring in three, hold
Row step S305.
S302, if so, judge stop duration whether reach preset time threshold；
When vehicle is in halted state, judge whether down time reaches preset time threshold c, wherein c is according to warp
It tests value or actual conditions is set, specifically can be set to 1 hour.
If S303, reaching, the data of parking front and back are divided into two training samples.
In the embodiment of the present invention, if the down time reaches the preset time threshold, it is possible to occur unloading or
Loading, it may be assumed that
tend-tini>c (1)
Wherein, tend indicates the parking end time, and tini indicates the parking time started, and c indicates preset time threshold.
The data of parking front and back are then divided into two training samples.
If S304, not up to, parking front and back and the data of of short duration shutdown phase are included into the same training sample；
In the embodiment of the present invention, if the down time reaches the preset time threshold c, before and after the parking
Data and the data of of short duration parking be included into the same training sample.
S305, the target vehicle are in driving status.
In the embodiment of the present invention, the method flow diagram of characteristic parameter relevant to the load condition training sample Nei is calculated
As shown in Figure 4, wherein the characteristic parameter can be chosen according to concrete condition.In the embodiment of the present invention, with the feature
Parameter is that acceleration, kinetic energy factor and fuel consumption are illustrated.Calculate comprising steps of
S401, the speed for obtaining the target vehicle；
In the embodiment of the present invention, the target vehicle is obtained according to velocity sensor or other preferred implementations
The speed at each moment in corresponding training sample.
S402, according to the speed, screen running time and instantaneous oil consumption of the target vehicle in the state of giving it the gun；
In the embodiment of the present invention, according to the speed at each moment, determine the target vehicle in corresponding trained sample
The status data sample that gives it the gun in this, screens the data sample that gives it the gun, and determines that it corresponds to running time
With instantaneous oil consumption.
S403, according to the speed, calculate kinetic energy factor；
In the embodiment of the present invention, according to Kinetic Energy Calculation formula:
Known to: under identical velocity conditions, the kinetic energy that quality difference generates is different.Here a new characteristic quantity is defined ---
Kinetic energy factor Δ e, calculation formula are as follows:
Wherein, Vini- accelerating sections initial speed, Vend- accelerate to terminate end speed.
S404, according to the instantaneous oil consumption and the running time, calculate fuel consumption；
In the embodiment of the present invention, fuel consumption is calculated according to fuel consumption calculation formula (4).
FuelCon=FuelRate × 3600 × Δ t (4)
Wherein, FuelCon is fuel consumption, and unit L, FuelRate are oil consumption rate, and unit L/h, Δ t are when accelerating
Between, unit s.
S405, acceleration is calculated according to the speed and the running time.
Obtain give it the gun status data sample initial speed and end speed according to corresponding initial time and at the end of
Between, acceleration is calculated according to acceleration formula (5).
Wherein, Vini- initial speed, Vend- end speed, Vini- initial time, Vend- end time.
Based on a kind of predictor method of above-mentioned vehicle load state, in the embodiment of the present invention, a kind of load-carrying is additionally provided
The structural block diagram of the Prediction System of state, the Prediction System is as shown in Figure 5, comprising:
Obtain module 501, preprocessing module 502, division module 503, computing module 504 and cluster module 505.
Wherein,
The acquisition module 501, for obtaining the running data of target vehicle；
The preprocessing module 502 obtains effective running data for pre-processing to the running data；
The division module 503, for dividing training sample according to effective running data；
The computing module 504, for calculating characteristic parameter relevant to load condition in the training sample；
The cluster module 505 obtains the load of the target vehicle for carrying out clustering algorithm according to the characteristic parameter
Weight state estimations result.
The invention discloses a kind of Prediction Systems of vehicle load state, comprising: the running data of target vehicle is obtained, it will
Running data is pre-processed to obtain effective running data, and effective running data is divided into different training samples, meter
Characteristic parameter relevant to load condition in each training sample is calculated, clustering algorithm is carried out to characteristic parameter, obtains the target
The estimation results of the load condition of vehicle, it is no longer necessary to install load measuring sensor and load condition is estimated.
In the embodiment of the present invention, the division module 503 includes:
First judgment module and the second judgment module.
First judgment module, for judging whether vehicle is in dead ship condition according to effective running data；
Second judgment module, if judging whether parking duration reaches preset time threshold for being in the dead ship condition
The data of parking front and back are divided into two training samples if reaching by value；If not up to, will be before and after the parking and short
The data of pause car state are included into the same training sample.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can
It realizes by means of software and necessary general hardware platform.Based on this understanding, technical solution of the present invention essence
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment or embodiment of the invention
Method described in part.
The predictor method and system of a kind of vehicle load state provided by the present invention are described in detail above, this
Apply that a specific example illustrates the principle and implementation of the invention in text, the explanation of above example is only intended to
It facilitates the understanding of the method and its core concept of the invention；At the same time, for those skilled in the art, think of according to the present invention
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
Limitation of the invention.
Claims (10)
1. a kind of predictor method of vehicle load state characterized by comprising
Obtain the running data of target vehicle；
The running data is pre-processed, effective running data is obtained；
According to effective running data, training sample is divided；
Calculate characteristic parameter relevant to load condition in the training sample；
Clustering algorithm is carried out according to the characteristic parameter, obtains the load condition estimation results of the target vehicle.
2. the method according to claim 1, wherein described according to effective running data, division training sample
This, comprising:
Judge whether the target vehicle is in dead ship condition according to effective running data；
If being in dead ship condition, judge whether parking duration reaches preset time threshold, if reaching, by the institute of parking front and back
It states effective running data and is divided into two training samples；If not up to, will be described in parking front and back and of short duration shutdown phase
Effective running data is included into the same training sample.
3. according to the method described in claim 2, it is characterized in that, described judge whether vehicle is in dead ship condition, comprising:
Obtain speed, mileage variable quantity and the engine speed of the target vehicle；
If the speed is zero, the mileage variable quantity is less than pre-set limit, the engine speed is less than preset rotation speed limit value,
Then judge that the target vehicle is in the halted state.
4. the method according to claim 1, wherein related to load condition in the calculating training sample
Characteristic parameter, comprising:
Obtain the speed of the target vehicle；
According to the speed, running time and instantaneous oil consumption of the target vehicle in the state of giving it the gun are screened；
According to the speed, kinetic energy factor is calculated；
According to the instantaneous oil consumption and the running time, fuel consumption is calculated；
Acceleration is calculated according to the speed and the running time.
5. being obtained the method according to claim 1, wherein described carry out clustering algorithm according to the characteristic parameter
To the load condition estimation results of the target vehicle, comprising:
Determine required cluster classification number；
Using K-means clustering algorithm, the characteristic parameter is clustered according to the cluster classification number, obtains the mesh
Mark the load condition estimation results of vehicle.
6. according to the method described in claim 5, it is characterized in that, the cluster classification number is 2.
7. according to the method described in claim 5, it is characterized in that, described join the feature according to the cluster classification number
Number is clustered, and the load condition estimation results of the target vehicle are obtained, comprising:
According to cluster result, the data sample for the state of giving it the gun adds data label；
Give it the gun the data label of state according to described in, determine driven at a constant speed in same training sample, Reduced Speed Now and parking
The data label of state；
The number that the different types of data label occurs in the same training sample is counted, by the most number of frequency of occurrence
Target labels according to label as the same training sample；
According to the target labels, the load condition estimation results of the target vehicle are determined.
8. determining the target carriage the method according to the description of claim 7 is characterized in that described according to the target labels
Load condition estimation results, comprising:
The data label of the target vehicle according to known load condition determines the load that each data label represents
Weight Status Type.
9. a kind of Prediction System of vehicle load state characterized by comprising
Module is obtained, for obtaining the running data of target vehicle；
Preprocessing module obtains effective running data for pre-processing to the running data；
Division module, for dividing training sample according to effective running data；
Computing module, for calculating characteristic parameter relevant to load condition in the training sample；
Cluster module, for carrying out clustering algorithm according to the characteristic parameter, the load condition for obtaining the target vehicle is estimated
As a result.
10. system according to claim 9, which is characterized in that the division module includes:
First judgment module, for judging whether the target vehicle is in dead ship condition according to effective running data；
Second judgment module, for when the first judgment module judging result, which is, is, judging whether parking duration reaches pre-
If time threshold, if reaching, by parking front and back data be divided into two training samples；If not up to, stopping described
After Chinese herbaceous peony and the data of of short duration shutdown phase are included into the same training sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039360.5A CN109767023A (en) | 2019-01-16 | 2019-01-16 | A kind of predictor method and system of vehicle load state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039360.5A CN109767023A (en) | 2019-01-16 | 2019-01-16 | A kind of predictor method and system of vehicle load state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767023A true CN109767023A (en) | 2019-05-17 |
Family
ID=66454070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910039360.5A Pending CN109767023A (en) | 2019-01-16 | 2019-01-16 | A kind of predictor method and system of vehicle load state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767023A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223139A (en) * | 2019-05-24 | 2019-09-10 | 深圳市轱辘汽车维修技术有限公司 | Use management method, device, server and the storage medium of vehicle trunk |
| CN110406539A (en) * | 2019-07-22 | 2019-11-05 | 杭州鸿泉物联网技术股份有限公司 | A kind of method and device identifying vehicle load state |
| CN110779607A (en) * | 2019-09-29 | 2020-02-11 | 成都亿盟恒信科技有限公司 | Oil consumption calculation-based muck truck empty and heavy load identification method |
| CN111060153A (en) * | 2019-12-23 | 2020-04-24 | 北京中交兴路车联网科技有限公司 | Method and device for detecting cargo state of truck and storage medium |
| CN111252019A (en) * | 2020-01-07 | 2020-06-09 | 吴金凤 | Electric vehicle safety driving detection method, vehicle-mounted detector and vehicle-mounted detection system |
| CN112309113A (en) * | 2020-09-22 | 2021-02-02 | 北京智科车联科技有限公司 | Vehicle load monitoring method, device, system, medium and equipment |
| CN113128929A (en) * | 2021-04-02 | 2021-07-16 | 北京知藏云道科技有限公司 | Vehicle load state identification method and device, computer equipment and medium |
| CN113280901A (en) * | 2021-05-20 | 2021-08-20 | 北京海博思创科技股份有限公司 | Method and device for determining vehicle load |
| CN114220191A (en) * | 2021-12-13 | 2022-03-22 | 平安国际融资租赁有限公司 | Driving state identification method and device, computer equipment and readable storage medium |
| CN114735015A (en) * | 2022-04-14 | 2022-07-12 | 广西玉柴机器股份有限公司 | Diesel engine commercial vehicle load assessment method |
| CN115879230A (en) * | 2023-02-16 | 2023-03-31 | 中汽信息科技(天津)有限公司 | Automobile load analysis model construction and analysis method based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105718956A (en) * | 2016-01-26 | 2016-06-29 | 上海经达信息科技股份有限公司 | Overload determining method based on support vector machine |
| 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 |
| KR20180031439A (en) * | 2016-09-20 | 2018-03-28 | 현대자동차주식회사 | Apparatus and method for recognizing driving patten based on vehicle driving data |
| 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 |
| CN108734963A (en) * | 2018-06-29 | 2018-11-02 | 上海经达信息科技股份有限公司 | A kind of overload of vehicle determination method based on Multiple Non Linear Regression |
| CN109017797A (en) * | 2018-08-17 | 2018-12-18 | 大陆汽车投资（上海）有限公司 | Driver's Emotion identification method and the vehicular control unit for implementing this method |
-
2019
- 2019-01-16 CN CN201910039360.5A patent/CN109767023A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105718956A (en) * | 2016-01-26 | 2016-06-29 | 上海经达信息科技股份有限公司 | Overload determining method based on support vector machine |
| KR20180031439A (en) * | 2016-09-20 | 2018-03-28 | 현대자동차주식회사 | Apparatus and method for recognizing driving patten based on vehicle driving data |
| 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 |
| CN108734963A (en) * | 2018-06-29 | 2018-11-02 | 上海经达信息科技股份有限公司 | A kind of overload of vehicle determination method based on Multiple Non Linear Regression |
| CN109017797A (en) * | 2018-08-17 | 2018-12-18 | 大陆汽车投资（上海）有限公司 | Driver's Emotion identification method and the vehicular control unit for implementing this method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223139A (en) * | 2019-05-24 | 2019-09-10 | 深圳市轱辘汽车维修技术有限公司 | Use management method, device, server and the storage medium of vehicle trunk |
| CN110406539A (en) * | 2019-07-22 | 2019-11-05 | 杭州鸿泉物联网技术股份有限公司 | A kind of method and device identifying vehicle load state |
| CN110779607B (en) * | 2019-09-29 | 2021-11-16 | 成都亿盟恒信科技有限公司 | Oil consumption calculation-based muck truck empty and heavy load identification method |
| CN110779607A (en) * | 2019-09-29 | 2020-02-11 | 成都亿盟恒信科技有限公司 | Oil consumption calculation-based muck truck empty and heavy load identification method |
| CN111060153A (en) * | 2019-12-23 | 2020-04-24 | 北京中交兴路车联网科技有限公司 | Method and device for detecting cargo state of truck and storage medium |
| CN111252019A (en) * | 2020-01-07 | 2020-06-09 | 吴金凤 | Electric vehicle safety driving detection method, vehicle-mounted detector and vehicle-mounted detection system |
| CN112309113A (en) * | 2020-09-22 | 2021-02-02 | 北京智科车联科技有限公司 | Vehicle load monitoring method, device, system, medium and equipment |
| CN113128929A (en) * | 2021-04-02 | 2021-07-16 | 北京知藏云道科技有限公司 | Vehicle load state identification method and device, computer equipment and medium |
| CN113280901A (en) * | 2021-05-20 | 2021-08-20 | 北京海博思创科技股份有限公司 | Method and device for determining vehicle load |
| CN113280901B (en) * | 2021-05-20 | 2023-08-15 | 北京海博思创科技股份有限公司 | Method and device for determining load of vehicle |
| CN114220191A (en) * | 2021-12-13 | 2022-03-22 | 平安国际融资租赁有限公司 | Driving state identification method and device, computer equipment and readable storage medium |
| CN114220191B (en) * | 2021-12-13 | 2023-11-21 | 平安国际融资租赁有限公司 | Driving state identification method and device, computer equipment and readable storage medium |
| CN114735015A (en) * | 2022-04-14 | 2022-07-12 | 广西玉柴机器股份有限公司 | Diesel engine commercial vehicle load assessment method |
| CN114735015B (en) * | 2022-04-14 | 2024-03-29 | 广西玉柴机器股份有限公司 | Load assessment method for commercial diesel vehicle |
| CN115879230A (en) * | 2023-02-16 | 2023-03-31 | 中汽信息科技(天津)有限公司 | Automobile load analysis model construction and analysis method based on deep learning |
| CN115879230B (en) * | 2023-02-16 | 2023-05-05 | 中汽信息科技(天津)有限公司 | Deep learning-based automobile load analysis model construction and analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767023A (en) | A kind of predictor method and system of vehicle load state | |
| EP3525180A1 (en) | Telematically monitoring and predicting a vehicle battery state | |
| CN106097709B (en) | Driving behavior recognition methods based on intelligent vehicle mounted terminal | |
| CN102881057B (en) | Based on vehicle management system and the vehicles management method thereof of iOBD | |
| CN101590832B (en) | Travel energy learning device and method | |
| CN105814583B (en) | Method for monitoring component operation | |
| CN104590275A (en) | Driving behavior analyzing method | |
| CN107444404B (en) | A kind of evaluation method and device of driving behavior standard degree | |
| CN111912506A (en) | Method and device for determining the load state of a motor vehicle | |
| CN108269325A (en) | A kind of analysis method and device of driving behavior oil consumption economy | |
| CN111016917B (en) | Vehicle load capacity detection method and device, computer readable storage medium and vehicle | |
| CN105438178A (en) | Vehicle loading predicting method and system | |
| EP3391304B1 (en) | Method and system for assessing the trip performance of a driver | |
| CN106980313B (en) | Automobile driving mode optimizing system and optimizing method | |
| CN111997709B (en) | On-line monitoring method and system for vehicle-mounted engine oil | |
| WO2019207882A1 (en) | Indication diagnosis device and method | |
| CN111707476B (en) | Longitudinal driving capability detection method for automatic driving automobile | |
| CN106875677A (en) | Method, analysis platform and system for analyzing driving behavior | |
| CN113919597A (en) | Method and device for predicting the landing load of an aircraft | |
| CN114526930A (en) | Intelligent network connection automobile fault detection method and system | |
| EP3891512A1 (en) | System and method for providing an indication of driving performance | |
| CN113918890A (en) | Low-load working condition construction method based on moving window library | |
| CN113834546A (en) | Liquid level display device and method based on gyroscope | |
| CN114136390A (en) | Automobile driving condition development device and method comprising road gradient | |
| CN117093818B (en) | Method and system for measuring and calculating carbon emission of urban distribution logistics vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 4 / F, building 1, No.14 Jiuxianqiao Road, Chaoyang District, Beijing 100020 Applicant after: Beijing Jingwei Hengrun Technology Co., Ltd Address before: 8 / F, block B, No. 11, Anxiang Beili, Chaoyang District, Beijing 100101 Applicant before: Beijing Jingwei HiRain Technologies Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |