CN117536709A - DPF regeneration control method, device and equipment based on machine learning - Google Patents
DPF regeneration control method, device and equipment based on machine learning Download PDFInfo
- Publication number
- CN117536709A CN117536709A CN202311535590.3A CN202311535590A CN117536709A CN 117536709 A CN117536709 A CN 117536709A CN 202311535590 A CN202311535590 A CN 202311535590A CN 117536709 A CN117536709 A CN 117536709A
- Authority
- CN
- China
- Prior art keywords
- working condition
- regeneration
- mileage
- scene
- condition scene
- 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
- 230000008929 regeneration Effects 0.000 title claims abstract description 268
- 238000011069 regeneration method Methods 0.000 title claims abstract description 268
- 238000010801 machine learning Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012937 correction Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 19
- 239000000446 fuel Substances 0.000 abstract description 7
- 230000000977 initiatory effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
- F01N9/00—Electrical control of exhaust gas treating apparatus
- F01N9/002—Electrical control of exhaust gas treating apparatus of filter regeneration, e.g. detection of clogging
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01N—GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL COMBUSTION ENGINES
- F01N2900/00—Details of electrical control or of the monitoring of the exhaust gas treating apparatus
- F01N2900/04—Methods of control or diagnosing
Abstract
DPF regeneration control method, device, equipment and computer readable storage medium based on machine learning, comprising: predicting a working condition scene of the vehicle according to the vehicle operation data by a preset machine learning model; acquiring an initial regeneration mileage and an operation distance under the working condition scene; DPF regeneration is controlled according to the running distance and the initial regeneration mileage under the working condition scene, so that the technical problem of high fuel consumption caused by frequent regeneration of vehicles in different working condition scenes in the related art is solved, and the purposes of realizing vehicle regeneration by predicting the working condition scene of the vehicle and defining the regeneration interval mileage according to different working condition scenes are achieved, and the fuel economy of the vehicle is improved.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a DPF regeneration control method, apparatus, device, and computer readable storage medium based on machine learning.
Background
Diesel particulate traps (DPF, diesel Particulate Filter) are the most effective means for reducing exhaust particulates, which need to be regenerated when a certain amount of Particulates (PM) is accumulated in the DPF. In order to prevent DPF blockage caused by deviation of accuracy of the carbon loading model, regeneration is triggered by limiting a certain regeneration mileage; however, in order to consider running vehicles in urban working conditions, suburban working conditions and the like, the regeneration mileage is generally set to be short and is generally within 3000km, while medium-long distance running vehicles are in high-speed running working conditions for a long time, one regeneration interval mileage can occur in 2-3 days, and frequent regeneration causes the problem of high fuel consumption.
Disclosure of Invention
The application provides a DPF regeneration control method, device, equipment and a computer readable storage medium based on machine learning, which can solve the technical problem that in the prior art, vehicles frequently regenerate in different working condition scenes, so that the fuel consumption is high.
In a first aspect, embodiments of the present application provide a DPF regeneration control method based on machine learning, including:
based on a preset machine learning model, predicting a working condition scene of the vehicle according to vehicle operation data;
acquiring an initial regeneration mileage and an operation distance under the working condition scene;
and controlling DPF regeneration according to the running distance and the initial regeneration mileage under the working condition scene.
With reference to the first aspect, in an implementation manner, the controlling DPF regeneration according to the running distance under the operating condition scenario and the initial regeneration mileage includes:
determining the real-time regeneration mileage of the working condition scene according to the operation distance and the initial regeneration mileage in the working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the working condition scene;
and if the real-time regeneration mileage of the working condition scene meets the preset condition, controlling DPF regeneration.
With reference to the first aspect, in an implementation manner, after determining whether the preset condition is met according to the real-time regeneration mileage, the method further includes:
if the real-time regeneration mileage does not meet the first preset condition, determining whether the working condition scene is changed or not;
if the working condition scene changes, taking the real-time regeneration mileage of the working condition scene as the initial regeneration mileage of the current working condition scene;
determining the real-time regeneration mileage of the current working condition scene according to the initial regeneration mileage of the current working condition scene and the running distance of the current working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the current working condition scene;
and if the real-time regeneration mileage of the current working condition scene meets the preset condition, controlling DPF regeneration.
With reference to the first aspect, in an implementation manner, after determining whether the first preset condition is met, the method further includes:
if the first preset regeneration condition is not met, acquiring the running path sum under each working condition scene;
and controlling DPF regeneration according to the running path sum and the preset regeneration interval mileage under each working condition scene.
With reference to the first aspect, in an implementation manner, the determining, according to the initial reproduction mileage of the current working condition scene and the running distance of the current working condition scene, the real-time reproduction mileage of the current working condition scene includes:
acquiring a path correction coefficient of the working condition scene;
and determining the real-time regeneration mileage of the working condition scene based on a first preset formula, the real-time distance of the working condition scene, the distance correction coefficient of the working condition scene and the initial regeneration mileage.
With reference to the first aspect, in an implementation manner, the predicting, based on a preset machine learning model, a working condition scene of a vehicle according to vehicle operation data includes:
inputting the acquired vehicle operation data into a preset machine learning model, so that the preset machine learning model calls a first linear equation and calculates a corresponding first predicted value based on the vehicle operation data;
determining whether a first working condition scene is met or not according to the first predicted value;
and if the first predicted value meets the first working condition scene, predicting the vehicle as the first working condition scene by using the preset machine learning model.
With reference to the first aspect, in an implementation manner, after determining whether the first working condition scene is met according to the first predicted value, the method further includes:
if the first predicted value does not meet the first working condition scene, enabling the preset machine learning model to call a second linear equation to calculate a corresponding second predicted value based on the vehicle operation data;
determining whether a second working condition scene is met according to the second predicted value;
and if the second predicted value meets the second working condition scene, predicting the vehicle as the second working condition scene by using the preset machine learning model.
With reference to the first aspect, in an implementation manner, before the predicting, based on the preset machine learning model, the working condition scene of the vehicle according to the vehicle operation data, the method further includes:
collecting vehicle operation data corresponding to different working condition scenes as a training set, wherein the vehicle operation data comprises rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature;
and training the model to be trained through the training set so as to enable the model to be trained to be in a convergence state, and generating a preset machine learning model.
In a second aspect, embodiments of the present application provide a DPF regeneration control device based on machine learning, including:
the prediction module is used for predicting the working condition scene of the vehicle according to the vehicle operation data based on a preset machine learning model;
the acquisition module is used for acquiring the initial regeneration mileage and the running distance under the working condition scene;
and the control module is used for controlling DPF regeneration according to the running distance under the working condition scene and the initial regeneration mileage.
In a third aspect, an embodiment of the present application provides a DPF regeneration control device based on machine learning, wherein the DPF regeneration control device based on machine learning includes a processor, a memory, and a re-DPF regeneration control program based on machine learning stored on the memory and executable by the processor, wherein the DPF regeneration control program based on machine learning, when executed by the processor, implements the steps of the DPF regeneration control method based on machine learning as described above.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium including a processor, a memory, and a machine learning based re-DPF regeneration control program stored on the memory and executable by the processor, wherein the machine learning based DPF regeneration control program, when executed by the processor, implements the steps of the machine learning based DPF regeneration control method as described above.
The beneficial effects that technical scheme that this application embodiment provided include: predicting a working condition scene of the vehicle according to the vehicle operation data by a preset machine learning model; acquiring an initial regeneration mileage and an operation distance under the working condition scene; DPF regeneration is controlled according to the running distance and the initial regeneration mileage under the working condition scene, so that the technical problem of high fuel consumption caused by frequent regeneration of vehicles in different working condition scenes in the related art is solved, and the purposes of realizing vehicle regeneration by predicting the working condition scene of the vehicle and defining the regeneration interval mileage according to different working condition scenes are achieved, and the fuel economy of the vehicle is improved.
Drawings
FIG. 1 is a flow chart of one embodiment of a machine learning based DPF regeneration control method of the present application;
FIG. 2 is a functional block diagram of a DPF regeneration control apparatus based on machine learning according to the present application;
fig. 3 is a schematic hardware configuration of a DPF regeneration control device based on machine learning according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
First, some technical terms in the present application are explained so as to facilitate understanding of the present application by those skilled in the art.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
In a first aspect, embodiments of the present application provide a DPF regeneration control method based on machine learning.
In one embodiment, referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a DPF regeneration control method based on machine learning according to the present application. As shown in fig. 1, the DPF regeneration control method based on machine learning includes:
s10: based on a preset machine learning model, predicting a working condition scene of the vehicle according to vehicle operation data;
s20: acquiring an initial regeneration mileage and an operation distance under the working condition scene;
s30: and controlling DPF regeneration according to the running distance and the initial regeneration mileage under the working condition scene.
The method comprises the steps of obtaining operation data of a vehicle, wherein the operation data comprise rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature, inputting the rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature into a preset machine learning model, predicting a working condition scene of the vehicle through the machine learning model based on the input rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature, obtaining a working condition scene output by the preset machine learning model, and taking the working condition scene as a working condition scene of the vehicle, wherein the working condition scene comprises a first working condition scene, a second working condition scene and a third working condition scene.
The method comprises the steps of obtaining initial regeneration mileage corresponding to a working condition scene of a vehicle and running distance of the vehicle under the working condition scene, wherein the initial regeneration interval mileage corresponding to the vehicle in the first working condition scene, the second working condition scene and the third working condition scene are the same, and the initial regeneration interval mileage is preset.
And judging whether the vehicle is regenerated or not by detecting the running distance and the initial regeneration interval mileage under the working condition scene, and if the vehicle regeneration is determined, controlling DPF regeneration. For example, acquiring the running distance of the vehicle in the first working condition scene and the corresponding initial regeneration interval mileage, comparing the initial regeneration interval mileage with the running distance in the first working condition scene, and if the running distance in the first working condition scene is greater than or equal to the initial regeneration interval mileage, determining that the vehicle meets the regeneration condition, and controlling the vehicle to regenerate; and if the running distance in the first working condition scene is smaller than the initial regeneration interval mileage, determining that the vehicle does not meet the regeneration condition.
In the embodiment, the working condition scene of the vehicle is predicted by presetting the machine learning model, so that an initial regeneration interval mileage is defined according to the working condition scene, whether the vehicle is regenerated or not is determined by the initial interval mileage and the running distance, and the problem that the vehicle is frequently regenerated due to the fact that the vehicle cannot be regenerated according to different working condition scenes of the vehicle in the related technology is solved, and the fuel economy is affected.
Further, in an embodiment, the controlling DPF regeneration according to the running distance under the operating condition scenario and the initial regeneration mileage includes:
s31: determining the real-time regeneration mileage of the working condition scene according to the operation distance and the initial regeneration mileage in the working condition scene;
s32: determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the working condition scene;
s33: and if the real-time regeneration mileage of the working condition scene meets the preset condition, controlling DPF regeneration.
Exemplary, if the working condition scene is a first working condition scene, acquiring an operation distance and an initial regeneration mileage in the first working condition scene, and determining a real-time regeneration interval mileage of the first working condition scene through the operation distance and the initial regeneration mileage in the first working condition scene. For example, subtracting the running distance under the first working condition scene from the obtained initial regeneration mileage to obtain the real-time regeneration interval mileage of the first working condition scene. And judging whether the real-time regeneration interval mileage of the first working condition scene is smaller than or equal to 0, if the real-time regeneration interval mileage of the first working condition scene is smaller than or equal to 0, determining that the real-time regeneration interval mileage of the first working condition scene meets a first preset condition, and controlling DPF regeneration. If the real-time regeneration interval mileage of the first working condition scene is not less than or equal to 0, determining that the real-time regeneration interval mileage of the first working condition scene does not meet the first preset condition.
If the working condition scene is the second working condition scene, acquiring the running distance and the running distance under the second working condition sceneAnd determining the real-time regeneration interval mileage of the second working condition scene through the running distance and the initial regeneration mileage of the second working condition scene. For example, a correction coefficient of the running distance under the second working condition scene is obtained based on a preset formula L Real time ＝L Initial initiation -L d Calculating by xK to obtain the real-time regeneration interval mileage of the second working condition scene, wherein L Real time Real-time regeneration interval mileage, L, for a second operating condition scenario Initial initiation For initial regeneration mileage, L d And K is a correction coefficient of the running distance in the second working condition scene. And judging whether the real-time regeneration interval mileage of the second working condition scene is smaller than or equal to 0, if the real-time regeneration interval mileage of the second working condition scene is smaller than or equal to 0, determining that the real-time regeneration interval mileage of the second working condition scene meets the first preset condition, and controlling DPF regeneration. If the real-time regeneration interval mileage of the second working condition scene is not less than or equal to 0, determining that the real-time regeneration interval mileage of the second working condition scene does not meet the first preset condition.
In the embodiment, by defining the initial regeneration interval mileage of different working condition scenes, the technical problem that the vehicle is frequently regenerated due to the fact that one regeneration interval mileage is adopted by different working condition scenes in the related technology is solved.
Further, in an embodiment, after determining whether the preset condition is met according to the real-time regeneration mileage, the method further includes:
s34: if the real-time regeneration mileage does not meet the first preset condition, determining whether the working condition scene is changed or not;
s35: if the working condition scene changes, taking the real-time regeneration mileage of the working condition scene as the initial regeneration mileage of the current working condition scene;
s36: determining the real-time regeneration mileage of the current working condition scene according to the initial regeneration mileage of the current working condition scene and the running distance of the current working condition scene;
s37: determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the current working condition scene;
s38: and if the real-time regeneration mileage of the current working condition scene meets the preset condition, controlling DPF regeneration.
Exemplary, if the real-time regeneration interval mileage of the first working condition scene or the second regeneration interval mileage of the second working condition scene does not meet the first preset regeneration condition, determining whether the first working condition scene or the second working condition scene changes. And if the first working condition scene or the second working condition scene changes, taking the real-time regeneration interval mileage of the first working condition scene or the real-time regeneration interval mileage of the second working condition scene as the initial regeneration interval mileage of the current working condition scene. For example, if the first working condition scene is changed into the second working condition scene, taking the real-time regeneration interval mileage of the first working condition scene as the initial regeneration interval mileage of the second working condition scene; or the second working condition scene is changed into the first working condition scene, and the real-time regeneration interval mileage of the second working condition scene is used as the initial regeneration interval mileage of the first working condition scene; the initial regeneration interval mileage of the first working condition scene after the working condition scene is changed is smaller than the initial regeneration interval mileage, or the initial regeneration interval mileage of the second working condition scene after the working condition scene is changed is smaller than the initial regeneration interval mileage.
For example, the current working condition scene is a first working condition scene, and the obtained initial regeneration interval mileage of the first working condition scene is subtracted from the running distance under the first working condition scene to obtain the real-time regeneration interval mileage of the first working condition scene. And judging whether the real-time regeneration interval mileage of the first working condition scene is smaller than or equal to 0, if the real-time regeneration interval mileage of the first working condition scene is smaller than or equal to 0, determining that the real-time regeneration interval mileage of the first working condition scene meets a first preset condition, and controlling DPF regeneration. If the real-time regeneration interval mileage of the first working condition scene is not less than or equal to 0, determining that the real-time regeneration interval mileage of the first working condition scene does not meet the first preset condition.
Or the current working condition scene is a second working condition scene, the correction coefficient of the running path under the second working condition scene is obtained, and the correction coefficient is based on a preset formula L Real time ＝L Initial initiation -L d Calculating by xK to obtain a second working condition fieldReal-time reproduction interval mileage of a scene, wherein L Real time Real-time regeneration interval mileage, L, for a second operating condition scenario Initial initiation For the initial regeneration mileage, L, of the second operating condition scene d And K is a correction coefficient of the running distance in the second working condition scene, and the range of the correction coefficient is between 0 and 1. And judging whether the real-time regeneration interval mileage of the second working condition scene is smaller than or equal to 0, if the real-time regeneration interval mileage of the second working condition scene is smaller than or equal to 0, determining that the real-time regeneration interval mileage of the second working condition scene meets the first preset condition, and controlling DPF regeneration. If the real-time regeneration interval mileage of the second working condition scene is not less than or equal to 0, determining that the real-time regeneration interval mileage of the second working condition scene does not meet the first preset condition.
In the embodiment, the initial regeneration interval mileage corresponding to the working condition scene is changed through the change of the working condition scene, so that the problem that the vehicle is frequently regenerated in the related art is solved.
Further, in an embodiment, after determining whether the first preset condition is met, the method further includes:
s41: if the first preset regeneration condition is not met, acquiring the running path sum under each working condition scene;
s42: and controlling DPF regeneration according to the running path sum under each working condition scene.
The method includes the steps that if a real-time regeneration interval mileage of a first working condition scene does not meet a first preset regeneration condition or a real-time regeneration interval mileage of a second working condition scene does not meet the first preset regeneration condition, whether the working condition scene changes is determined, and if the working condition scene changes from the first working condition scene to a third working condition scene or from the second working condition scene to the third working condition scene, the sum of the running distances of the first working condition scene and the third working condition scene, such as the sum of the running distances of the first working condition scene and the running distance of the third working condition scene, is obtained; or obtaining the cumulative sum of the running distance of the second working condition scene and the running distance of the third working condition scene. Comparing the sum of the obtained running distance with the preset maximum regeneration interval mileageAnd if the sum of the operation flows is greater than or equal to the maximum regeneration interval mileage, controlling DPF regeneration. If the sum of the operation flows is smaller than the maximum regeneration interval mileage, acquiring the real-time regeneration interval mileage of the third working condition scene, taking the acquired real-time regeneration interval mileage of the third working condition scene as the initial regeneration interval mileage of the next working condition scene, for example, acquiring the real-time regeneration interval mileage of the first working condition scene or the real-time regeneration interval mileage of the second working condition scene as the initial interval mileage of the third working condition scene, and according to the initial interval mileage of the third working condition scene, the operation distance of the third working condition scene and a preset formula L of the corresponding third working condition scene Real time ＝L Initial initiation +L d Obtaining a real regeneration interval mileage of a third working condition scene by using the X Z, wherein L Real time Real-time regeneration interval mileage, L, for third operating condition scene Initial initiation Initial regeneration mileage, L, for third operating condition scenario d And Z is a correction coefficient of the running distance in the third working condition scene, and the correction coefficient ranges from 1 to 10. When the real-time regeneration interval mileage of the third working condition scene is obtained, if the working condition scene changes, the real-time regeneration interval mileage of the third working condition scene is taken as the initial regeneration interval mileage of the next working condition scene.
In the embodiment, the vehicle regeneration is controlled by adopting the running path through the change of the working condition scene, so that the problem that the vehicle is frequently regenerated in the related technology is solved.
Further, in an embodiment, the predicting the working condition scene of the vehicle according to the vehicle operation data based on the preset machine learning model includes:
step S11: inputting the acquired vehicle operation data into a preset machine learning model, so that the preset machine learning model calls a first linear equation and calculates a corresponding first predicted value based on the vehicle operation data;
step S12: determining whether a first working condition scene is met or not according to the first predicted value;
step S13: and if the first predicted value meets the first working condition scene, predicting the first working condition scene of the vehicle by the preset machine learning model.
The obtained rotational speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature of the vehicle to be predicted are input into a preset machine learning model, a first linear equation is called in the preset machine learning model, and a corresponding first predicted value is calculated through the rotational speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure, DPF temperature and the first linear equation. For example, the first linear equation is y1=s x ×W x1 +N x ×W x2 +V x ×W x3 +D x ×W x4 +P x ×W x5 +T x ×W x6 +b 1 Wherein S is x Is the rotation speed N x Is torque, V x For the speed of the vehicle, D x Is the opening degree of an accelerator pedal, P x Is at atmospheric pressure T x Is DPF temperature, b 1 Is constant, W x1 Is the correction coefficient of the rotating speed, W x2 Is the correction coefficient of torque, W x3 Is the correction coefficient of the vehicle speed, W x4 Correction coefficient W for accelerator shift detection opening degree x5 Correction coefficient for atmospheric pressure, W x6 And substituting the rotating speed, the torque, the vehicle speed, the accelerator pedal opening, the atmospheric pressure and the DPF temperature of the vehicle to be predicted into a first linear equation to obtain a first predicted value Y1 as the correction coefficient of the DPF temperature. Comparing the obtained first predicted value Y1 with a first preset threshold value, if the first preset value is larger than the first preset threshold value, determining that the working condition scene of the vehicle to be detected is a first working condition scene, and enabling the working condition scene of the vehicle predicted by the preset machine learning model to be the first working condition scene.
Step S14: if the first predicted value does not meet the first working condition scene, enabling the preset machine learning model to call a second linear equation to calculate a corresponding second predicted value based on the vehicle operation data;
step S15: determining whether a second working condition scene is met according to the second predicted value;
step S16: and if the second predicted value meets the second working condition scene, predicting the second working condition scene of the vehicle by the preset machine learning model.
If the first predicted value Y1 is smaller than or equal to the first preset threshold, it is determined that the first working condition scene is not met, a second linear equation is called through a preset machine learning model, and a corresponding second predicted value is calculated through the second linear equation. For example, the second linear equation is y2=s x ×W x7 +N x ×W x8 +V x ×W x9 +D x ×W x10 +P x ×W x11 +T x ×W x12 +b 2 Wherein S is x Is the rotation speed N x Is torque, V x For the speed of the vehicle, D x Is the opening degree of an accelerator pedal, P x Is at atmospheric pressure T x Is DPF temperature, b 2 Is constant, W x7 Is the correction coefficient of the rotating speed, W x8 Is the correction coefficient of torque, W x9 Is the correction coefficient of the vehicle speed, W x10 Correction coefficient W for accelerator pedal opening x11 Correction coefficient for atmospheric pressure, W x12 And substituting the rotation speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature of the vehicle to be predicted into a second linear equation to obtain a second predicted value Y2 as the correction coefficient of the DPF temperature. Comparing the obtained second predicted value Y2 with a second preset threshold value, if the second preset value is larger than the second preset threshold value, determining that the working condition scene of the vehicle to be detected is a second working condition scene, and enabling the preset machine learning model to predict the working condition scene of the vehicle to be the second working condition scene. The number of the working condition scenes is multiple, the linear equation in the preset machine learning model and the various working condition scenes are in corresponding relation, namely the number of the types of the working condition scenes is the same as that of the linear equation, and the corresponding relation is not explained one by one.
In the embodiment, the working condition scene of the vehicle is predicted by presetting a machine learning model, so that the problem that the current working condition scene of the vehicle cannot be achieved in real time or accurately in the related technology is solved.
Further, in an embodiment, before predicting the working condition scene of the vehicle according to the vehicle operation data based on the preset machine learning model, the method further includes: collecting vehicle operation data corresponding to different working condition scenes as a training set, wherein the vehicle operation data comprises rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature; and training the model to be trained through the training set so as to enable the model to be trained to be in a convergence state, and generating a preset machine learning model.
The vehicle operation data collected under different working condition scenes are used as training sets, and each training set of vehicle operation data is provided with a corresponding working condition scene tag, wherein the vehicle operation data comprises rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature. For example, the rotational speed 1, torque 1, vehicle speed 1, accelerator pedal opening 1, atmospheric pressure 1 and DPF temperature 1 with the condition scene 1 label are input into a model to be trained, wherein the model to be trained comprises a linear equation W T ×X in +b=0, where W T Correction coefficients for each operating data, b being a constant, X in And substituting a plurality of rotating speeds in the working condition scene 1 labels into a linear equation for each operation data, so as to obtain correction coefficients and constants of the rotating speeds in each working condition scene 1 label. Respectively inputting the operation data of the working condition scene 1 labels in the training set into the model to be trained, and passing through a linear equation W T ×X in +b=0, obtaining a correction coefficient W of the rotation speed of the condition scene 1 label x1 Correction coefficient W of torque x2 Correction coefficient W of vehicle speed x3 Correction coefficient W of accelerator shift detection opening degree x4 Correction coefficient W of atmospheric pressure x5 Correction coefficient W of DPF temperature x6 。
The training set comprises a plurality of groups of data of the rotating speed, the torque, the vehicle speed, the accelerator pedal opening, the atmospheric pressure and the DPF temperature of different working condition scene labels or the rotating speed, the torque, the vehicle speed, the accelerator pedal opening, the atmospheric pressure and the DPF temperature of the same working condition scene label. Training the model to be trained through the training set until the model to be trained is in a convergence state, and generating a corresponding machine learning model.
In this embodiment, the model is trained by a large number of training sets with labels, so as to obtain a neural network model capable of predicting the working condition scene of the vehicle.
In a second aspect, embodiments of the present application also provide a DPF regeneration control based on machine learning.
In one embodiment, referring to fig. 2, fig. 2 is a schematic diagram of functional modules of an embodiment of the DPF regeneration control based on machine learning in the present application. As shown in fig. 2, the DPF regeneration control based on the machine learning includes:
the prediction module S51: based on a preset machine learning model, predicting a working condition scene of the vehicle according to vehicle operation data;
acquisition module S52: acquiring an initial regeneration mileage and an operation distance under the working condition scene;
control module S53: and controlling DPF regeneration according to the running distance and the initial regeneration mileage under the working condition scene.
Further, in an embodiment, the control module S53 is configured to:
determining the real-time regeneration mileage of the working condition scene according to the operation distance and the initial regeneration mileage in the working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the working condition scene;
and if the real-time regeneration mileage of the working condition scene meets the preset condition, controlling DPF regeneration.
Further, in an embodiment, the control module S53 is configured to:
if the real-time regeneration mileage does not meet the first preset condition, determining whether the working condition scene is changed or not;
if the working condition scene changes, taking the real-time regeneration mileage of the working condition scene as the initial regeneration mileage of the current working condition scene;
determining the real-time regeneration mileage of the current working condition scene according to the initial regeneration mileage of the current working condition scene and the running distance of the current working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the current working condition scene;
and if the real-time regeneration mileage of the current working condition scene meets the preset condition, controlling DPF regeneration.
Further, in an embodiment, the DPF regeneration control based on the machine learning further includes:
if the first preset regeneration condition is not met, acquiring the running path sum under each working condition scene;
and controlling DPF regeneration according to the running path sum and the preset regeneration interval mileage under each working condition scene.
Further, in an embodiment, the control module S53 is configured to:
acquiring a path correction coefficient of the working condition scene;
and determining the real-time regeneration mileage of the working condition scene based on a first preset formula, the real-time distance of the working condition scene, the distance correction coefficient of the working condition scene and the initial regeneration mileage.
Further, in an embodiment, the prediction module S51 is configured to:
inputting the acquired vehicle operation data into a preset machine learning model, so that the preset machine learning model calls a first linear equation and calculates a corresponding first predicted value based on the vehicle operation data;
determining whether a first working condition scene is met or not according to the first predicted value;
and if the first predicted value meets the first working condition scene, predicting the vehicle as the first working condition scene by using the preset machine learning model.
Further, in an embodiment, the prediction module S51 is configured to:
if the first predicted value does not meet the first working condition scene, enabling the preset machine learning model to call a second linear equation to calculate a corresponding second predicted value based on the vehicle operation data;
determining whether a second working condition scene is met according to the second predicted value;
and if the second predicted value meets the second working condition scene, predicting the vehicle as the second working condition scene by using the preset machine learning model.
Further, in an embodiment, the DPF regeneration control based on the machine learning further includes:
collecting vehicle operation data corresponding to different working condition scenes as a training set, wherein the vehicle operation data comprises rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature;
and training the model to be trained through the training set so as to enable the model to be trained to be in a convergence state, and generating a preset machine learning model.
The function implementation of each module in the DPF regeneration control device based on machine learning corresponds to each step in the embodiment of the DPF regeneration control method based on machine learning, and the function and implementation process thereof are not described in detail herein.
In a third aspect, embodiments of the present application provide a DPF regeneration control apparatus based on machine learning, which may be an apparatus having a data processing function such as a personal computer (personal computer, PC), a notebook computer, a server, or the like.
Referring to fig. 3, fig. 3 is a schematic diagram of a hardware configuration of a DPF regeneration control device based on machine learning according to an embodiment of the present application. In an embodiment of the present application, a DPF regeneration control device based on machine learning may include a processor, a memory, a communication interface, and a communication bus.
The communication bus may be of any type for implementing the processor, memory, and communication interface interconnections.
The communication interfaces include input/output (I/O) interfaces, physical interfaces, logical interfaces, and the like for implementing device interconnection inside the machine-learning-based DPF regeneration control device, and interfaces for implementing interconnection of the machine-learning-based DPF regeneration control device with other devices (e.g., other computing devices or user devices). The physical interface may be an ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device may be a Display, a Keyboard (Keyboard), or the like.
The memory may be various types of storage media such as random access memory (randomaccess memory, RAM), read-only memory (ROM), nonvolatile RAM (non-volatileRAM, NVRAM), flash memory, optical memory, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (electrically erasable PROM, EEPROM), and the like.
The processor may be a general-purpose processor, and the general-purpose processor may call a machine-learning-based DPF regeneration control program stored in the memory and execute the machine-learning-based DPF regeneration control method provided in the embodiment of the present application. For example, the general purpose processor may be a central processing unit (central processing unit, CPU). The method executed when the DPF regeneration control program based on machine learning is called may refer to various embodiments of the DPF regeneration control method based on machine learning of the present application, and will not be described herein.
Those skilled in the art will appreciate that the hardware configuration shown in fig. 3 is not limiting of the application and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium.
The present application provides a computer-readable storage medium having stored thereon a machine-learning-based DPF regeneration control program, wherein the machine-learning-based DPF regeneration control program, when executed by a processor, implements the steps of the machine-learning-based DPF regeneration control method described above.
The method implemented when the DPF regeneration control program based on machine learning is executed may refer to various embodiments of the DPF regeneration control method based on machine learning of the present application, and will not be described herein.
It should be noted that, the foregoing embodiment numbers are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments.
The terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the foregoing drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The terms "first," "second," and "third," etc. are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order, and are not limited to the fact that "first," "second," and "third" are not identical.
In the description of embodiments of the present application, "exemplary," "such as," or "for example," etc., are used to indicate an example, instance, or illustration. Any embodiment or design described herein as "exemplary," "such as" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "such as" or "for example," etc., is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, unless otherwise indicated, "/" means or, for example, a/B may represent a or B; the text "and/or" is merely an association relation describing the associated object, and indicates that three relations may exist, for example, a and/or B may indicate: the three cases where a exists alone, a and B exist together, and B exists alone, and in addition, in the description of the embodiments of the present application, "plural" means two or more than two.
In some of the processes described in the embodiments of the present application, a plurality of operations or steps occurring in a particular order are included, but it should be understood that these operations or steps may be performed out of the order in which they occur in the embodiments of the present application or in parallel, the sequence numbers of the operations merely serve to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the processes may include more or fewer operations, and the operations or steps may be performed in sequence or in parallel, and the operations or steps may be combined.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising several instructions for causing a terminal device to perform the method described in the various embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. A DPF regeneration control method based on machine learning, characterized by comprising:
based on a preset machine learning model, predicting a working condition scene of the vehicle according to vehicle operation data;
acquiring an initial regeneration mileage and an operation distance under the working condition scene;
and controlling DPF regeneration according to the running distance and the initial regeneration mileage under the working condition scene.
2. The machine learning-based DPF regeneration control method according to claim 1, wherein the controlling DPF regeneration according to the running distance in the operating condition scenario and the initial regeneration mileage includes:
determining the real-time regeneration mileage of the working condition scene according to the operation distance and the initial regeneration mileage in the working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the working condition scene;
and if the real-time regeneration mileage of the working condition scene meets the preset condition, controlling DPF regeneration.
3. The machine learning based DPF regeneration control method according to claim 2, further comprising, after determining whether a preset condition is satisfied according to the real-time regeneration mileage:
if the real-time regeneration mileage does not meet the first preset condition, determining whether the working condition scene is changed or not;
if the working condition scene changes, taking the real-time regeneration mileage of the working condition scene as the initial regeneration mileage of the current working condition scene;
determining the real-time regeneration mileage of the current working condition scene according to the initial regeneration mileage of the current working condition scene and the running distance of the current working condition scene;
determining whether a first preset regeneration condition is met or not according to the real-time regeneration mileage of the current working condition scene;
and if the real-time regeneration mileage of the current working condition scene meets the preset condition, controlling DPF regeneration.
4. The machine learning-based DPF regeneration control method according to claim 2 or 3, characterized by further comprising, after the determining whether the first preset condition is satisfied:
if the first preset regeneration condition is not met, acquiring the running path sum under each working condition scene;
and controlling DPF regeneration according to the running path sum and the preset regeneration interval mileage under each working condition scene.
5. The machine learning-based DPF regeneration control method of claim 3, wherein the determining the real-time regeneration mileage of the current operating condition scenario based on the initial regeneration mileage of the current operating condition scenario and the operating distance of the current operating condition scenario comprises:
acquiring a path correction coefficient of the working condition scene;
and determining the real-time regeneration mileage of the working condition scene based on a first preset formula, the real-time distance of the working condition scene, the distance correction coefficient of the working condition scene and the initial regeneration mileage.
6. The machine learning based DPF regeneration control method of claim 1, wherein predicting a condition scenario of a vehicle based on vehicle operation data based on a preset machine learning model comprises:
inputting the acquired vehicle operation data into a preset machine learning model, so that the preset machine learning model calls a first linear equation and calculates a corresponding first predicted value based on the vehicle operation data;
determining whether a first working condition scene is met or not according to the first predicted value;
and if the first predicted value meets the first working condition scene, predicting the vehicle as the first working condition scene by using the preset machine learning model.
7. The machine learning based DPF regeneration control method of claim 6, further comprising, after determining whether a first operating condition scenario is satisfied based on the first predicted value:
if the first predicted value does not meet the first working condition scene, enabling the preset machine learning model to call a second linear equation to calculate a corresponding second predicted value based on the vehicle operation data;
determining whether a second working condition scene is met according to the second predicted value;
and if the second predicted value meets the second working condition scene, predicting the vehicle as the second working condition scene by using the preset machine learning model.
8. The machine learning based DPF regeneration control method according to claim 1, wherein before predicting a condition scene of the vehicle based on the vehicle operation data based on the preset machine learning model, further comprising:
collecting vehicle operation data corresponding to different working condition scenes as a training set, wherein the vehicle operation data comprises rotating speed, torque, vehicle speed, accelerator pedal opening, atmospheric pressure and DPF temperature;
and training the model to be trained through the training set so as to enable the model to be trained to be in a convergence state, and generating a preset machine learning model.
9. A DPF regeneration control device based on machine learning, characterized in that the DPF regeneration control device based on machine learning includes:
the prediction module is used for predicting the working condition scene of the vehicle according to the vehicle operation data based on a preset machine learning model;
the acquisition module is used for acquiring the initial regeneration mileage and the running distance under the working condition scene;
and the control module is used for controlling DPF regeneration according to the running distance under the working condition scene and the initial regeneration mileage.
10. A machine-learning-based DPF regeneration control apparatus, characterized in that the machine-learning-based DPF regeneration control apparatus includes a processor, a memory, and a machine-learning-based re-DPF regeneration control program stored on the memory and executable by the processor, wherein the machine-learning-based DPF regeneration control program, when executed by the processor, implements the steps of the machine-learning-based DPF regeneration control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311535590.3A CN117536709A (en) | 2023-11-15 | 2023-11-15 | DPF regeneration control method, device and equipment based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311535590.3A CN117536709A (en) | 2023-11-15 | 2023-11-15 | DPF regeneration control method, device and equipment based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117536709A true CN117536709A (en) | 2024-02-09 |
Family
ID=89791301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311535590.3A Pending CN117536709A (en) | 2023-11-15 | 2023-11-15 | DPF regeneration control method, device and equipment based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117536709A (en) |
-
2023
- 2023-11-15 CN CN202311535590.3A patent/CN117536709A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10360387B2 (en) | Method and system for aggregating and ranking of security event-based data | |
| JP2862153B2 (en) | Rule-based computer system, method of calling rules executed by the rule-based computer system, and incremental function learning method executed by the rule-based computer system | |
| CN111123223A (en) | General development platform, management system and method for radar health management | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN115470936B (en) | NWDAF-based machine learning model updating method and device | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN113778776A (en) | Method and device for early warning task abnormity and storage medium | |
| CN111866017B (en) | Method and device for detecting abnormal frame interval of CAN bus | |
| CN114758268A (en) | Gesture recognition method and device and intelligent equipment | |
| CN114047710A (en) | Intelligent household data analysis method and device, terminal equipment and storage medium | |
| CN117536709A (en) | DPF regeneration control method, device and equipment based on machine learning | |
| CN113674317A (en) | Vehicle tracking method and device of high-order video | |
| CN110717537B (en) | Method and device for training user classification model and executing user classification prediction | |
| CN117272139A (en) | Shield tunneling machine attitude prediction method combining characteristic correlation and time correlation | |
| CN116842520A (en) | Anomaly perception method, device, equipment and medium based on detection model | |
| CN114244681B (en) | Equipment connection fault early warning method and device, storage medium and electronic equipment | |
| Lahann et al. | LSTM-based anomaly detection of process instances: Benchmark and tweaks | |
| CN112858725B (en) | Vehicle speed consistency detection method, terminal equipment and storage medium | |
| CN112433902B (en) | Screen replacement model training method, screen replacement detection method and device | |
| CN112445709B (en) | Method and device for solving AFL test model data imbalance through GAN | |
| CN105844176B (en) | Security strategy generation method and equipment | |
| CN116701639B (en) | Text analysis-based double-carbon knowledge graph data analysis method and system | |
| CN112685246B (en) | Time sequence data processing method and device | |
| CN114254763B (en) | Machine learning model repairing method, system, computer equipment and storage medium | |
| CN117632905B (en) | Database management method and system based on cloud use records |
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 |