CN109872075B - Evaluation method and system for fuel consumption related driving behaviors - Google Patents
Evaluation method and system for fuel consumption related driving behaviors Download PDFInfo
- Publication number
- CN109872075B CN109872075B CN201910164100.0A CN201910164100A CN109872075B CN 109872075 B CN109872075 B CN 109872075B CN 201910164100 A CN201910164100 A CN 201910164100A CN 109872075 B CN109872075 B CN 109872075B
- Authority
- CN
- China
- Prior art keywords
- driving behavior
- fuel consumption
- vehicle
- driving
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006399 behavior Effects 0.000 title claims abstract description 274
- 239000000446 fuel Substances 0.000 title claims abstract description 205
- 238000011156 evaluation Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 description 23
- 238000007726 management method Methods 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention provides an evaluation method and system for fuel consumption related driving behaviors, wherein the method comprises the following steps: the method comprises the steps of obtaining driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, wherein the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance. And calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data. And taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated. In the scheme, a fuel consumption scoring model is established in advance based on the corresponding relation between different driving behaviors and fuel consumption. The driving behavior indexes corresponding to different driving behaviors are calculated based on the driving behavior data by extracting the driving behavior data of the vehicle to be evaluated, the driving behavior indexes are used as input values of the fuel consumption scoring model to calculate and obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
Description
Technical Field
The invention relates to the technical field of vehicle data processing, in particular to a method and a system for evaluating fuel consumption related driving behaviors.
Background
At present, a common transportation mode is vehicle transportation, and in the process of using the vehicle for transportation, oil consumption management of a transportation fleet becomes one of key concerns of each transportation company.
In the automobile transportation process, the oil consumption management of a transportation fleet is usually managed by depending on manual experience, and the influence of the transportation distance and the transportation time on the oil consumption is mainly studied manually. However, on the other hand, the fuel consumption management of a transportation vehicle fleet through manual experience is low objectivity due to the influence of human subjectivity. On the other hand, only by studying the influence of the transportation distance and the transportation time on the fuel consumption, the influence of the driving behavior of the driver on the fuel consumption during the driving is not studied, resulting in low evaluation accuracy in the fuel consumption evaluation of the transportation vehicle fleet.
Therefore, the conventional method for managing the fuel consumption of the transport vehicle fleet has the problems of low objectivity, low accuracy and the like.
Disclosure of Invention
In view of this, embodiments of the present invention provide an evaluation method and system for fuel consumption-related driving behaviors, so as to solve the problems of low objectivity and low accuracy in the existing fuel consumption management method for a transportation fleet.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the embodiment of the invention discloses a method for evaluating driving behaviors related to oil consumption in a first aspect, which comprises the following steps:
the method comprises the steps of obtaining driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, wherein the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance;
calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data;
and taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, wherein the fuel consumption scoring model is constructed by a driving behavior sample index and a fuel consumption related coefficient based on a sample vehicle.
Optionally, the fuel consumption scoring model is constructed by a driving behavior sample index and a fuel consumption correlation coefficient based on a sample vehicle, and includes:
acquiring running sample data of the sample vehicle;
carrying out data preprocessing on the driving sample data to obtain processed driving sample data;
determining a plurality of driving behaviors;
dividing the total driving mileage of the sample vehicle into m sections of preset mileage, and calculating the oil consumption of the sample vehicle in each preset mileage;
calculating a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data aiming at each preset mileage;
calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption for each preset mileage;
taking the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and carrying out Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model;
and combining the oil consumption scoring submodel with a preset average value calculating submodel to obtain the oil consumption scoring model.
Optionally, the calculating the fuel consumption of the sample vehicle within each preset mileage includes:
based on
Calculating the oil consumption Y of the sample vehicle in each preset mileage, wherein t is the time required by the sample vehicle to travel the preset mileage, and FRIs the instantaneous fuel consumption rate of the sample vehicle.
Optionally, calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption includes:
based on
Calculating the fuel consumption correlation coefficient A corresponding to each driving behavior sample indexiWherein N is the total number of driving behavior sample indexes, Y is the oil consumption of the sample vehicle in the preset mileage, and XiIs a driving behavior sample index.
Optionally, the calculating, with the driving behavior index as an input value of a preset fuel consumption scoring model, to obtain a total fuel consumption-related driving behavior evaluation score of the vehicle to be evaluated includes:
taking the driving behavior index as an input value of a fuel consumption scoring sub-model to obtain fuel consumption related driving behavior scores in each preset mileage;
taking the n fuel consumption related driving behavior scores as input values of the average value calculation submodel, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated;
the oil consumption scoring model is composed of the oil consumption scoring submodel and the average value calculating submodel.
Optionally, the calculating the total fuel consumption-related driving behavior evaluation score of the vehicle to be evaluated by using the n fuel consumption-related driving behavior scores as the input value of the average value calculation submodel includes:
taking the n fuel consumption related driving behavior scores as the average value calculation submodel
The total score G of the fuel consumption related driving behavior evaluation of the vehicle to be evaluated is obtained through calculationiWherein j is the serial number of the preset mileage, YpjAnd scoring the fuel consumption related driving behavior corresponding to the jth preset mileage.
The second aspect of the embodiment of the invention discloses an evaluation system for fuel consumption related driving behaviors, which comprises:
the system comprises an acquisition unit, a judgment unit and a display unit, wherein the acquisition unit is used for acquiring driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, and the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance;
the calculation unit is used for calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data;
and the evaluation unit is used for calculating to obtain the total evaluation score of the fuel consumption related driving behaviors of the vehicle to be evaluated by taking the driving behavior index as an input value of a preset fuel consumption evaluation model, wherein the fuel consumption evaluation model is constructed by a driving behavior sample index and a fuel consumption related coefficient based on a sample vehicle.
Optionally, the scoring unit includes:
the acquisition module is used for acquiring the driving sample data of the sample vehicle;
the processing module is used for carrying out data preprocessing on the driving sample data to obtain processed driving sample data;
a determination module to determine a plurality of driving behaviors;
the oil consumption calculation module is used for dividing the total driving mileage of the sample vehicle into m sections of the preset mileage and calculating the oil consumption of the sample vehicle in each preset mileage;
the first calculation module is used for calculating a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data aiming at each preset mileage;
the second calculation module is used for calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption for each preset mileage;
the training module is used for taking the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and carrying out Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model;
and the construction module is used for combining the oil consumption scoring submodel and a preset average value calculating submodel to obtain the oil consumption scoring model.
Optionally, the scoring unit includes:
the first scoring module is used for taking the driving behavior index as an input value of the fuel consumption scoring submodel to obtain fuel consumption related driving behavior scores within each preset mileage;
the second grading module is used for taking the grades of the n fuel consumption related driving behaviors as input values of the average value calculation submodel and calculating to obtain a total evaluation score of the fuel consumption related driving behaviors of the vehicle to be evaluated;
the oil consumption scoring model is composed of the oil consumption scoring submodel and the average value calculating submodel.
Optionally, the second scoring module is specifically configured to use the n fuel consumption-related driving behavior scores as the average-value-calculating submodel
The total score G of the fuel consumption related driving behavior evaluation of the vehicle to be evaluated is obtained through calculationiWherein j is the serial number of the preset mileage, YpjAnd scoring the fuel consumption related driving behavior corresponding to the jth preset mileage.
Based on the method and the system for evaluating the driving behavior related to the oil consumption, provided by the embodiment of the invention, the method comprises the following steps: the method comprises the steps of obtaining driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, wherein the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance. And calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data. And taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated. In the scheme, a fuel consumption scoring model is established in advance based on the corresponding relation between different driving behaviors and fuel consumption. The driving behavior indexes corresponding to different driving behaviors are calculated based on the driving behavior data by extracting the driving behavior data of the vehicle to be evaluated, the driving behavior indexes are used as input values of the fuel consumption scoring model to calculate and obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an evaluation method for fuel consumption-related driving behavior according to an embodiment of the present invention;
fig. 2 is a flowchart for establishing a fuel consumption scoring model according to an embodiment of the present invention;
fig. 3 is a block diagram of a fuel consumption-related driving behavior evaluation system according to an embodiment of the present invention;
fig. 4 is a block diagram of a structure of an evaluation system of fuel consumption-related driving behavior according to an embodiment of the present invention;
fig. 5 is a block diagram of a structure of an evaluation system of fuel consumption-related driving behavior according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
As can be seen from the background art, at present, fuel consumption management for a transport vehicle fleet generally depends on manual experience for management, and mainly by manually studying the influence of transport distance and transport time on fuel consumption. However, due to the influence of human subjectivity and the fact that the influence of driving behaviors of drivers on fuel consumption in the driving process is not researched, the existing fuel consumption management method for the transport vehicle fleet has the problems of low objectivity, low accuracy and the like.
Therefore, the embodiment of the invention provides an evaluation method and system for fuel consumption-related driving behaviors, and a fuel consumption scoring model is established in advance based on corresponding relations between different driving behaviors and fuel consumption. And calculating driving behavior indexes corresponding to different driving behaviors of the vehicle to be evaluated, and calculating to obtain a driving behavior evaluation total score related to the fuel consumption of the vehicle to be evaluated by taking the driving behavior indexes as input values of the fuel consumption scoring model so as to improve the objectivity and accuracy of vehicle fuel consumption management.
Referring to fig. 1, a flowchart of a method for evaluating fuel consumption-related driving behavior according to an embodiment of the present invention is shown, where the method includes the following steps:
step S101: and acquiring driving behavior data corresponding to each preset mileage of the vehicle to be evaluated.
In the process of implementing the step S101 specifically, vehicle driving data of the vehicle to be evaluated is acquired from a vehicle networking data storage background, and the vehicle driving data is acquired by a vehicle mounted remote information processor (Telematics BOX, T-BOX). The vehicle driving data at least comprises a total driving range of the vehicle to be evaluated and the driving behavior data.
And dividing the total driving range of the vehicle to be evaluated into n sections of the preset range, for example, assuming that the preset range is 100 kilometers and the total driving range of the vehicle to be evaluated is 10000 kilometers, dividing the total driving range of the vehicle to be evaluated into 100 sections of the preset range.
It should be noted that, if the total driving range of the vehicle to be evaluated cannot be divided by the preset range, n is only an integer part, and a remainder part is ignored. Such as: assuming that the preset mileage is 100 kilometers, the total driving mileage of the vehicle to be evaluated is 10090 kilometers, and the total driving mileage divided by the preset mileage is equal to 100 and 90, n is equal to 100, and the remainder 90 is ignored.
It should be noted that after the vehicle driving data of the vehicle to be evaluated is acquired, the vehicle driving data needs to be preprocessed, and the preprocessing manner at least includes: outlier processing and missing value processing.
The manner in which the vehicle travel data is preprocessed is described in detail below.
Abnormal value processing: and deleting abnormal data in the vehicle driving data. It should be noted that there are various reasons that the vehicle driving data transmission error may be caused when the vehicle driving data is collected and transmitted. However, in order to occupy space or represent a special meaning, an abnormal value may occur in the collected vehicle driving data, and the abnormal value has no meaning for the data processing related to the embodiment of the present invention, so that the abnormal value needs to be deleted. For example, the rows of abnormal speed and abnormal neutral signal values in the vehicle driving data are screened out by adopting a screening mode.
Missing value processing: and if blank signals of any data type appear in the vehicle driving data, carrying out interpolation filling on the blank signals based on a previous signal value and a next signal value of the blank signals. The Vehicle travel signals that need to be advanced are predetermined, such as a Vehicle Identification Number (VIN), a time signal, an odometer (ODO), a Vehicle speed signal, an engine speed signal, a neutral signal, an accelerator pedal opening signal, and a brake pedal opening signal. And assuming that the vehicle speed signal has a partial blank value, and carrying out interpolation filling on the blank value based on a previous signal value and a next signal value of the blank value.
Step S102: and calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data.
In the process of implementing step S102 specifically, the driving behavior of the vehicle to be evaluated is determined based on the characteristics of different driving behaviors, and the types of the driving behaviors include: neutral coasting, non-neutral coasting, over-running, too long idle speed, and accelerator bump during parking. And calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data corresponding to the driving behaviors. The driving behavior data is: and driving data of the vehicle to be evaluated during driving by adopting different driving behaviors, such as neutral sliding time, non-neutral sliding time, over-rotating speed, idling time and the like.
For better explanation, how to determine the driving behavior of the vehicle to be evaluated and the driving behavior indexes corresponding to different driving behaviors are explained. How to determine the driving behavior of the vehicle to be evaluated is illustrated by examples a1-a5 below, and driving behavior indicators corresponding to different driving behaviors are illustrated by examples B1-B5.
Examples A1-A5:
a1, driving behavior: and (4) sliding in a neutral gear. Determining conditions: the initial speed of the vehicle is greater than a preset value, the speed is greater than 0 in the driving process, the opening degree of an accelerator pedal and the opening degree of a brake pedal are both 0, and a neutral gear signal is 1.
A2, driving behavior: non-neutral coasting. Determining conditions: the initial speed of the vehicle is greater than a preset value, the speed is greater than 0 in the driving process, the opening degree of an accelerator pedal and the opening degree of a brake pedal are both 0, and a neutral gear signal is 0.
A3, driving behavior: and (4) over-rotating. Determining conditions: the rotating speed of the vehicle engine is greater than a preset value and lasts for more than a preset time.
A4, driving behavior: the idle speed is too long. Determining conditions: the vehicle idle time exceeds a threshold.
A5, driving behavior: the vehicle is parked to roll the throttle. Determining conditions: the vehicle speed is 0, and the opening degree of an accelerator pedal is larger than 0.
Examples B1-B5:
b1, driving behavior: and (4) sliding in a neutral gear. The driving behavior index is as follows: ratio X of neutral coasting time11Mean value of time to coast in neutral gear X12Neutral glide time variance X13Ratio of neutral sliding distance to X14Neutral sliding distance mean X15Neutral sliding distance variance X16。
B2, driving behavior: non-neutral coasting. The driving behavior index is as follows: ratio X of non-neutral coasting time21Mean value of non-neutral coast time X22Non-neutral coast time variance X23Ratio of non-neutral glide distance24Mean value of non-neutral sliding distance X25Non-neutral sliding distance variance X26。
B3, driving behavior: and (4) over-rotating. The driving behavior index is as follows: mean value of over-rotation average rotating speed X31Mean rotational speed variance X of over-revolution32Over-running time ratio X33Mean value of over-run time X34Over-rotation time variance X35。
B4, driving behavior: the idle speed is too long. The driving behavior index is as follows: ratio of idling for too long time X41Mean value X of idle speed over long time42Idle over time variance X43Idle for too long a time and X44。
B5, driving behavior: the vehicle is parked to roll the throttle. Driving deviceAs indexes: average accelerator pedal X for vehicle running51Maximum accelerator pedal X for vehicle parking52Variance X of accelerator pedal during accelerator bombing in parking53Time X of stopping to roll over the throttle54The ratio of the time of stopping to the time of rolling over the throttle is X55And the number of times of stopping to roll over the throttle is X56。
It should be noted that the contents shown in the above examples a1-a5 and examples B1-B5 are for illustration only.
Step S103: and taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated.
In the process of implementing step S103 specifically, the driving behavior sample data based on the sample vehicle is preselected, the driving behavior sample index and the fuel consumption correlation coefficient of the sample vehicle are calculated, and the fuel consumption scoring model is constructed and obtained according to the driving behavior sample index and the fuel consumption correlation coefficient. Wherein. The oil consumption scoring model is composed of an oil consumption scoring submodel and an average value calculating submodel.
In the process of specifically calculating the total fuel consumption-related driving behavior evaluation score of the vehicle to be evaluated, based on the fact that the total driving mileage of the vehicle to be evaluated is divided into n sections of preset mileage involved in the step S101, the driving behavior index corresponding to each preset mileage is used as an input value of the fuel consumption scoring sub-model, fuel consumption-related driving behavior scores in each preset mileage are obtained, and n fuel consumption-related driving behavior scores are obtained in total. And taking the n fuel consumption related driving behavior scores as input values of the average value submodel, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated. Wherein the averaging submodel is represented by formula (1), and in formula (1), GiThe evaluation total score of the driving behavior related to the oil consumption of the vehicle to be evaluated is given, j is the serial number of the preset mileage, YpjAnd scoring the fuel consumption related driving behavior corresponding to the jth preset mileage.
It should be noted that, when the total driving range of the vehicle to be evaluated is divided into n preset ranges, each preset range in the n preset ranges is sorted according to a front-back sequence and a sequence number from 1 to n.
In the embodiment of the invention, the fuel consumption scoring model is established in advance based on the corresponding relation between different driving behaviors and fuel consumption. The driving behavior indexes corresponding to different driving behaviors are calculated based on the driving behavior data by extracting the driving behavior data of the vehicle to be evaluated, the driving behavior indexes are used as input values of the fuel consumption scoring model to calculate and obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
The construction process of the fuel consumption scoring model related to the step S103 is shown in fig. 2, which is a flowchart for establishing the fuel consumption scoring model according to the embodiment of the present invention, and includes the following steps:
step S201: and acquiring the driving sample data of the sample vehicle.
In the process of implementing step S201 specifically, a sample vehicle is selected in advance, and the driving sample data of the sample vehicle is acquired.
Step S202: and carrying out data preprocessing on the driving sample data to obtain processed driving sample data.
In the process of implementing step S202, for the processing procedure of the driving sample data, reference is made to the content corresponding to step S101 disclosed in fig. 1 in the embodiment of the present invention.
Step S203: a plurality of driving behaviors are determined.
In the process of specifically implementing step S203, the types of the driving behaviors refer to the corresponding contents of step S102 disclosed in fig. 1 of the embodiment of the present invention, and are not described in detail herein.
Step S204: and dividing the total driving mileage of the sample vehicle into m sections of the preset mileage, and calculating the oil consumption of the sample vehicle in each preset mileage.
In the specific implementation process of step S204, the fuel consumption Y of the sample vehicle within each preset mileage is calculated based on the formula (2). In the formula (2), t is a time required for the sample vehicle to travel the preset mileage, FRIs the instantaneous fuel consumption rate of the sample vehicle.
Step S205: and calculating a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data aiming at each preset mileage.
In the process of specifically implementing step S205, for specific contents of the driving behavior sample index, refer to the corresponding contents of step S102 disclosed in fig. 1 in the embodiment of the present invention, which are not described in detail herein.
Step S206: and calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption for each preset mileage.
In the process of specifically implementing step S207, the fuel consumption correlation coefficient a corresponding to each driving behavior sample index is calculated based on the formula (3)i。
In the formula (3), N is the total number of driving behavior sample indexes, Y is the fuel consumption of the sample vehicle within the preset mileage, and XiIs a driving behavior sample index.
To better explain how to calculate the fuel consumption correlation coefficient corresponding to the driving behavior sample index, the following description is given by combining the 27 driving behavior indexes in the examples B1-B5 disclosed in fig. 1:
the neutral coasting time is compared with X11Substituting the sum Y into the formula (3) to calculate and obtain a correlation coefficient A of the ratio of the neutral coasting time to the fuel consumption11. Will be describedMean value X of neutral gear sliding time12Substituting the sum Y into the formula (3) to obtain a correlation coefficient A of the neutral gear sliding time average value and the oil consumption12。
Similarly, the other driving behavior sample indexes and the oil consumption are substituted into the formula (3) to calculate the oil consumption correlation coefficient corresponding to the driving behavior sample index. The larger the correlation coefficient, the greater the influence of the driving behavior on fuel consumption.
Step S207: and taking the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and carrying out Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model.
In the process of specifically implementing step S207, the driving behavior sample index and the fuel consumption correlation coefficient in step S206 are used as weight factors of a Lasso regression model, and the Lasso regression model is subjected to Lasso regression training to obtain a fuel consumption scoring sub-model.
It should be noted that the fuel consumption scoring sub-model is constructed by taking the driving behavior sample index as a characteristic variable and taking the fuel consumption related driving behavior score as a result variable. The loss function of the Lasso regression is shown in equation (4).
In the formula (4), X is a sample vector, Y is an output variable, θ is a coefficient vector, n is a sample dimension, a is a constant coefficient, | | θ | | Y1Is L1And (4) norm. Note that a is adjusted by a skilled person according to actual conditions.
It should be noted that the Lasso regression is to obtain the corresponding functional relationship between each driving behavior sample index and the fuel consumption based on the above formula (4).
Step S208: and combining the oil consumption scoring submodel with a preset average value calculating submodel to obtain the oil consumption scoring model.
In the process of specifically implementing the step S208, the fuel consumption scoring sub-model is used as a first-layer sub-model of the fuel consumption scoring model, the average-value-obtaining sub-model is used as a second-layer sub-model of the fuel consumption scoring model, and the fuel consumption scoring model is constructed. The averaging submodel is shown in the above formula (1).
In the implementation example of the invention, the fuel consumption scoring sub-model is constructed through the driving sample data and the fuel consumption correlation coefficient of the sample vehicle. And combining the oil consumption scoring sub-model with a preset average value calculating sub-model to obtain an oil consumption scoring model. The driving behavior index is used as an input value of the fuel consumption scoring model to calculate to obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
Corresponding to the method for evaluating the driving behavior related to fuel consumption provided by the embodiment of the present invention, referring to fig. 3, an embodiment of the present invention further provides a structural block diagram of a system for evaluating the driving behavior related to fuel consumption, where the system includes:
the obtaining unit 301 is configured to obtain driving behavior data corresponding to each preset range of the vehicle to be evaluated, where the total driving range of the vehicle to be evaluated is divided into n preset ranges in advance.
In a specific implementation, the specific process of obtaining the driving behavior data and the process of preprocessing the driving behavior data refer to the content corresponding to step S101 disclosed in fig. 1 in the embodiment of the present invention.
A calculating unit 302, configured to calculate, based on the driving behavior data, driving behavior indexes corresponding to different driving behaviors within each preset mileage. In a specific implementation, the specific process of obtaining the driving behavior index refers to the content corresponding to step S102 disclosed in fig. 1 in the embodiment of the present invention.
And the scoring unit 303 is configured to calculate to obtain a total fuel consumption-related driving behavior evaluation score of the vehicle to be evaluated by using the driving behavior index as an input value of a preset fuel consumption scoring model, where the fuel consumption scoring model is constructed by a driving behavior sample index and a fuel consumption related coefficient based on a sample vehicle.
In the embodiment of the invention, the fuel consumption scoring model is established in advance based on the corresponding relation between different driving behaviors and fuel consumption. The driving behavior indexes corresponding to different driving behaviors are calculated based on the driving behavior data by extracting the driving behavior data of the vehicle to be evaluated, the driving behavior indexes are used as input values of the fuel consumption scoring model to calculate and obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
Referring to fig. 4, a block diagram of a system for evaluating fuel consumption-related driving behavior according to an embodiment of the present invention is shown, where the scoring unit 303 includes: the fuel consumption calculation method comprises an acquisition module 3031, a processing module 3032, a determination module 3033, a fuel consumption calculation module 3034, a first calculation module 3035, a second calculation module 3036, a training module 3037 and a construction module 3038.
An obtaining module 3031, configured to obtain driving sample data of the sample vehicle.
A processing module 3032, configured to perform data preprocessing on the driving sample data to obtain processed driving sample data.
A determination module 3033 determines a plurality of driving behaviors.
And the oil consumption calculating module 3034 is configured to divide the total driving mileage of the sample vehicle into m preset mileage segments, and calculate the oil consumption of the sample vehicle in each preset mileage segment.
Preferably, the fuel consumption calculating module 3034 is specifically configured to calculate the fuel consumption of the sample vehicle within each preset mileage based on the above formula (2).
A first calculating module 3035, configured to calculate, for each preset mileage, a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data.
A second calculating module 3036, configured to calculate, for each preset mileage, a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption.
Preferably, the second calculating module 3036 is specifically configured to calculate the fuel consumption correlation coefficient corresponding to each driving behavior sample index based on the above formula (3).
A training module 3037, configured to use the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and perform Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model.
The building module 3038 is configured to combine the oil consumption scoring sub-model and a preset average value calculating sub-model to obtain the oil consumption scoring model.
In the implementation example of the invention, the fuel consumption scoring sub-model is constructed through the driving sample data and the fuel consumption correlation coefficient of the sample vehicle. And combining the oil consumption scoring sub-model with a preset average value calculating sub-model to obtain an oil consumption scoring model. The driving behavior index is used as an input value of the fuel consumption scoring model to calculate to obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
Referring to fig. 5, a block diagram of a system for evaluating fuel consumption-related driving behavior according to an embodiment of the present invention is shown, where the scoring unit 303 includes:
and the first scoring module 3039 is configured to use the driving behavior index as an input value of the fuel consumption scoring sub-model to obtain a fuel consumption-related driving behavior score within each preset mileage.
And the second scoring module 3010 is configured to use the n fuel consumption-related driving behavior scores as input values of the average value submodel, and calculate a total fuel consumption-related driving behavior evaluation score of the vehicle to be evaluated.
The oil consumption scoring model is composed of the oil consumption scoring submodel and the average value calculating submodel.
Preferably, the second scoring module 3010 is specifically configured to use the n fuel consumption-related driving behavior scores as input values of the formula (1), and calculate a total fuel consumption-related driving behavior evaluation score G of the vehicle to be evaluatedi。
In summary, the embodiment of the present invention provides an evaluation method and system for fuel consumption-related driving behavior, where the method includes: the method comprises the steps of obtaining driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, wherein the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance. And calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data. And taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated. In the scheme, a fuel consumption scoring model is established in advance based on the corresponding relation between different driving behaviors and fuel consumption. The driving behavior indexes corresponding to different driving behaviors are calculated based on the driving behavior data by extracting the driving behavior data of the vehicle to be evaluated, the driving behavior indexes are used as input values of the fuel consumption scoring model to calculate and obtain the fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated, and the objectivity and the accuracy of vehicle fuel consumption management can be improved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for assessing fuel consumption-related driving behavior, the method comprising:
the method comprises the steps of obtaining driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, wherein the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance;
calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data;
taking the driving behavior index as an input value of a preset fuel consumption scoring model, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated;
the fuel consumption scoring model is constructed by a driving behavior sample index and a fuel consumption correlation coefficient based on a sample vehicle, and specifically comprises the following steps:
acquiring running sample data of the sample vehicle;
carrying out data preprocessing on the driving sample data to obtain processed driving sample data;
determining a plurality of driving behaviors;
dividing the total driving mileage of the sample vehicle into m sections of preset mileage, and calculating the oil consumption of the sample vehicle in each preset mileage;
calculating a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data aiming at each preset mileage;
calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption for each preset mileage;
taking the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and carrying out Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model;
and combining the oil consumption scoring submodel with a preset average value calculating submodel to obtain the oil consumption scoring model.
2. The method of claim 1, wherein the calculating the fuel consumption of the sample vehicle within each of the predetermined mileage comprises:
based on
Calculating the oil consumption Y of the sample vehicle in each preset mileage, wherein t is the time required by the sample vehicle to travel the preset mileage, and FRIs the instantaneous fuel consumption rate of the sample vehicle.
3. The method of claim 1, wherein calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample indicator based on the driving behavior sample indicator and fuel consumption comprises:
based on
Calculating the fuel consumption correlation coefficient A corresponding to each driving behavior sample indexiWherein N is the total number of driving behavior sample indexes, Y is the oil consumption of the sample vehicle in the preset mileage, and XiIs a driving behavior sample index.
4. The method according to any one of claims 1 to 3, wherein the step of calculating the fuel consumption-related driving behavior evaluation total score of the vehicle to be evaluated by taking the driving behavior index as an input value of a preset fuel consumption scoring model comprises the following steps:
taking the driving behavior index as an input value of a fuel consumption scoring sub-model to obtain fuel consumption related driving behavior scores in each preset mileage;
taking the n fuel consumption related driving behavior scores as input values of the average value calculation submodel, and calculating to obtain a fuel consumption related driving behavior evaluation total score of the vehicle to be evaluated;
the oil consumption scoring model is composed of the oil consumption scoring submodel and the average value calculating submodel.
5. The method according to claim 4, wherein the step of calculating the total evaluation score of the fuel consumption related driving behaviors of the vehicle to be evaluated by taking the n fuel consumption related driving behavior scores as the input values of the average value calculation submodel comprises the following steps of:
taking the n fuel consumption related driving behavior scores as the average value calculation submodel
The total score G of the fuel consumption related driving behavior evaluation of the vehicle to be evaluated is obtained through calculationiWherein j is the serial number of the preset mileage, YpjAnd scoring the fuel consumption related driving behavior corresponding to the jth preset mileage.
6. A fuel consumption-related driving behavior evaluation system, characterized in that the system comprises:
the system comprises an acquisition unit, a judgment unit and a display unit, wherein the acquisition unit is used for acquiring driving behavior data corresponding to each preset mileage of a vehicle to be evaluated, and the total driving mileage of the vehicle to be evaluated is divided into n preset miles in advance;
the calculation unit is used for calculating driving behavior indexes corresponding to different driving behaviors in each preset mileage based on the driving behavior data;
the evaluation unit is used for calculating to obtain an oil consumption related driving behavior evaluation total score of the vehicle to be evaluated by taking the driving behavior index as an input value of a preset oil consumption evaluation model, wherein the oil consumption evaluation model is constructed by a driving behavior sample index and an oil consumption related coefficient based on a sample vehicle;
the scoring unit comprises:
the acquisition module is used for acquiring the driving sample data of the sample vehicle;
the processing module is used for carrying out data preprocessing on the driving sample data to obtain processed driving sample data;
a determination module to determine a plurality of driving behaviors;
the oil consumption calculation module is used for dividing the total driving mileage of the sample vehicle into m sections of the preset mileage and calculating the oil consumption of the sample vehicle in each preset mileage;
the first calculation module is used for calculating a driving behavior sample index corresponding to each driving behavior based on the processed driving sample data aiming at each preset mileage;
the second calculation module is used for calculating a fuel consumption correlation coefficient corresponding to the driving behavior sample index based on the driving behavior sample index and the fuel consumption for each preset mileage;
the training module is used for taking the driving behavior sample index and the fuel consumption correlation coefficient as weight factors of a Lasso regression model, and carrying out Lasso regression training on the Lasso regression model to obtain a fuel consumption scoring sub-model;
and the construction module is used for combining the oil consumption scoring submodel and a preset average value calculating submodel to obtain the oil consumption scoring model.
7. The system of claim 6, wherein the scoring unit comprises:
the first scoring module is used for taking the driving behavior index as an input value of the fuel consumption scoring submodel to obtain fuel consumption related driving behavior scores within each preset mileage;
the second grading module is used for taking the grades of the n fuel consumption related driving behaviors as input values of the average value calculation submodel and calculating to obtain a total evaluation score of the fuel consumption related driving behaviors of the vehicle to be evaluated;
the oil consumption scoring model is composed of the oil consumption scoring submodel and the average value calculating submodel.
8. The system of claim 7, wherein the second scoring module is specifically configured to use the n fuel consumption-related driving behavior scores as the averaging submodel
The total score G of the fuel consumption related driving behavior evaluation of the vehicle to be evaluated is obtained through calculationiWherein j is the serial number of the preset mileage, YpjAnd scoring the fuel consumption related driving behavior corresponding to the jth preset mileage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910164100.0A CN109872075B (en) | 2019-03-05 | 2019-03-05 | Evaluation method and system for fuel consumption related driving behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910164100.0A CN109872075B (en) | 2019-03-05 | 2019-03-05 | Evaluation method and system for fuel consumption related driving behaviors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109872075A CN109872075A (en) | 2019-06-11 |
| CN109872075B true CN109872075B (en) | 2021-02-02 |
Family
ID=66919758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910164100.0A Active CN109872075B (en) | 2019-03-05 | 2019-03-05 | Evaluation method and system for fuel consumption related driving behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872075B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689131A (en) * | 2019-09-26 | 2020-01-14 | 长安大学 | Vehicle energy consumption influence analysis method based on naive Bayes model |
| CN111210537A (en) * | 2019-10-10 | 2020-05-29 | 中国第一汽车股份有限公司 | Oil consumption analysis method, device, equipment and storage medium |
| CN112734144A (en) * | 2019-10-14 | 2021-04-30 | 中移智行网络科技有限公司 | Driving behavior evaluation method and device, storage medium and computer equipment |
| CN111523701A (en) * | 2020-03-27 | 2020-08-11 | 广州亚美信息科技有限公司 | Method and device for evaluating vehicle running condition, computer equipment and storage medium |
| CN114254473A (en) * | 2020-09-24 | 2022-03-29 | 华为技术有限公司 | Vehicle energy consumption scoring method and device |
| CN113250836B (en) * | 2021-06-07 | 2022-10-14 | 一汽解放汽车有限公司 | Engine control method, engine control device, computer equipment and storage medium |
| CN113469458B (en) * | 2021-07-22 | 2024-06-14 | 南京领行科技股份有限公司 | Driving habit evaluation method and device and electronic equipment |
| CN114021931A (en) * | 2021-10-28 | 2022-02-08 | 东风商用车有限公司 | Economical evaluation method and system for driving behaviors |
| CN114426025B (en) * | 2022-03-17 | 2023-11-14 | 一汽解放汽车有限公司 | Driving assistance method, driving assistance device, computer device, and storage medium |
| CN114954299B (en) * | 2022-05-19 | 2023-02-17 | 李诣坤 | Fuel consumption early warning method and system for reducing fuel consumption of automobile |
| CN117114209B (en) * | 2023-10-23 | 2024-02-06 | 湖北君邦环境技术有限责任公司 | Method, device and equipment for predicting carbon emission of automobile in full life cycle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200267A (en) * | 2014-09-23 | 2014-12-10 | 清华大学 | Vehicle driving economy evaluation system and vehicle driving economy evaluation method |
| CN104599346A (en) * | 2013-12-11 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Driving behavior evaluation method and driving behavior evaluation apparatus |
| CN104832299A (en) * | 2015-03-05 | 2015-08-12 | 东软集团股份有限公司 | High-fuel consumption driving state judgment method, apparatus and system |
| CN106777625A (en) * | 2016-12-02 | 2017-05-31 | 潍柴动力股份有限公司 | Evaluation method and system that driving behavior influences on oil consumption |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI421177B (en) * | 2011-03-18 | 2014-01-01 | Ind Tech Res Inst | Methods and systems of saving energy control |
| CN104809160B (en) * | 2015-03-30 | 2019-01-11 | 东软集团股份有限公司 | A kind of high Fuel consumption analysis method and apparatus based on gear shift behavior |
| CN108269325A (en) * | 2016-12-30 | 2018-07-10 | 中国移动通信有限公司研究院 | A kind of analysis method and device of driving behavior oil consumption economy |
| CN108407816B (en) * | 2018-01-19 | 2020-07-10 | 杭州砺玛物联网科技有限公司 | Method and system for evaluating driving of automobile driver |
-
2019
- 2019-03-05 CN CN201910164100.0A patent/CN109872075B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104599346A (en) * | 2013-12-11 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Driving behavior evaluation method and driving behavior evaluation apparatus |
| CN104200267A (en) * | 2014-09-23 | 2014-12-10 | 清华大学 | Vehicle driving economy evaluation system and vehicle driving economy evaluation method |
| CN104832299A (en) * | 2015-03-05 | 2015-08-12 | 东软集团股份有限公司 | High-fuel consumption driving state judgment method, apparatus and system |
| CN104832299B (en) * | 2015-03-05 | 2017-03-08 | 东软集团股份有限公司 | A kind of high oil consumption driving condition decision method, equipment and system |
| CN106777625A (en) * | 2016-12-02 | 2017-05-31 | 潍柴动力股份有限公司 | Evaluation method and system that driving behavior influences on oil consumption |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109872075A (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872075B (en) | Evaluation method and system for fuel consumption related driving behaviors | |
| CN110148230B (en) | Whole vehicle load prediction method based on LSTM neural network | |
| EP2701959B1 (en) | Fuel saving-aimed motor vehicle driving style evaluation | |
| CN109670970B (en) | Driving behavior scoring method and device and computer readable storage medium | |
| Zhou et al. | Development of a transient fuel consumption model | |
| CN111461185A (en) | Driving behavior analysis method based on improved K-means | |
| DE112009002674T5 (en) | navigation device | |
| CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
| CN109635852B (en) | User portrait construction and clustering method based on multi-dimensional attributes | |
| CN112937591B (en) | Driving safety monitoring method, device, equipment and computer readable storage medium | |
| CN108475359B (en) | Method and system for evaluating driver's trip performance | |
| CN108431837B (en) | Method and system for evaluating driver's trip performance | |
| WO2015099645A1 (en) | Vehicle ratings via measured driver behavior | |
| CN113173175B (en) | Vehicle weight determination method and device | |
| CN113246999A (en) | Driving behavior analysis method and device and readable storage medium | |
| CN108122045B (en) | Logistics vehicle scheduling device and logistics vehicle scheduling method | |
| CN116092296B (en) | Traffic state evaluation method, device, electronic equipment and storage medium | |
| CN116703612A (en) | Automobile insurance risk level assessment method | |
| CN114426025B (en) | Driving assistance method, driving assistance device, computer device, and storage medium | |
| Kan et al. | Development of a novel engine power model to estimate heavy-duty truck fuel consumption | |
| CN110689131A (en) | Vehicle energy consumption influence analysis method based on naive Bayes model | |
| KR20160063652A (en) | Economic driving analysis system | |
| CN114999150A (en) | Road section congestion judging method and device, vehicle and storage medium | |
| CN112734144A (en) | Driving behavior evaluation method and device, storage medium and computer equipment | |
| CN114750765B (en) | Road spectrum data determining method, device, equipment, medium and product of vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| 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 Hirain Technologies Co.,Inc. Address before: 8 / F, block B, No. 11, Anxiang Beili, Chaoyang District, Beijing 100101 Applicant before: Beijing Jingwei HiRain Technologies Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |