CN115859123B - Vehicle driving condition online identification method based on random prediction and machine learning - Google Patents
Vehicle driving condition online identification method based on random prediction and machine learning Download PDFInfo
- Publication number
- CN115859123B CN115859123B CN202310183550.0A CN202310183550A CN115859123B CN 115859123 B CN115859123 B CN 115859123B CN 202310183550 A CN202310183550 A CN 202310183550A CN 115859123 B CN115859123 B CN 115859123B
- Authority
- CN
- China
- Prior art keywords
- vehicle speed
- time
- driving
- prediction
- working condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention belongs to the technical field of vehicle driving condition recognition, and provides a vehicle driving condition online recognition method based on random prediction and machine learning. The method solves the defects that the existing working condition identification method is accompanied with larger time delay and is unfavorable for the real-time control of the whole vehicle control system. The short-term driving condition prediction model simultaneously reads the real-time vehicle speed and the real-time driving style output by the driving style recognition model output by the data preprocessing module, and outputs a predicted vehicle speed sequence within a period of time after the current time point; the working condition data synthesis module is used for splicing the historical vehicle speed sequence updated in real time with the predicted vehicle speed sequence to construct combined working condition data containing future working condition change trend; the real-time driving condition identification model reads characteristic parameters of the combined condition data output by the condition data synthesis module. The invention takes the combination data of the historical vehicle speed sequence and the predicted vehicle speed sequence as the identification object, thereby improving the real-time performance of the identification result while ensuring the identification precision.
Description
Technical Field
The invention belongs to the technical field of vehicle driving condition identification, and particularly relates to a vehicle driving condition online identification method based on random prediction and machine learning.
Background
The driving condition recognition is to use feature extraction and classification technology to recognize the type of driving condition, and the main recognition algorithm comprises neural network, support vector machine, fuzzy classification, cluster analysis and the like.
For a traditional vehicle, the driving working condition can be used for determining the emission and fuel consumption level of the vehicle and providing basis for power matching and fuel economy optimization; for the pure electric vehicle, the calculation accuracy of the remaining driving mileage can be improved by acquiring the driving condition information in real time; for a hybrid electric vehicle, an adaptive energy management strategy can be established based on working condition data, the economy of the whole vehicle is improved, and the service lives of power system components are improved. Because the working condition of the vehicle in actual running is randomly changed, the running working condition on-line identification method with higher identification accuracy and real-time is extremely important.
The main difference of the current researches is that the dividing of the typical driving working condition and the selection method of the characteristic parameters are different, and the attempts of simplifying the neural network structure and improving the recognition accuracy by optimizing the external input parameters are all carried out, so that the better effect is obtained. However, in the existing driving condition recognition method, the history condition data with a fixed length is usually used as a recognition object, and although the type of the generated driving condition can be accurately recognized, the recognition result is often accompanied by a larger time delay, which is not beneficial to the real-time control of the whole vehicle control system.
Disclosure of Invention
The invention provides a vehicle driving condition online identification method based on random prediction and machine learning, which aims to solve at least one technical problem in the prior art.
The invention is realized by adopting the following technical scheme: a vehicle driving condition online identification method based on random prediction and machine learning comprises the following steps:
s101, a data preprocessing module reads real-time running data of a vehicle, wherein the real-time running data comprise a vehicle speed, an accelerator pedal opening and a brake pedal opening;
s102: the driving style identification model reads the real-time vehicle speed, the accelerator pedal opening, the accelerator pedal change rate, the brake pedal opening and the brake pedal change rate output by the data preprocessing module and outputs the real-time driving style type;
s103: the short-term driving condition prediction model simultaneously reads the real-time vehicle speed and the real-time driving style output by the driving style recognition model output by the data preprocessing module, and outputs a predicted vehicle speed sequence within a period of time after the current time point;
s104: the working condition data synthesis module reads a historical vehicle speed sequence in a period of time before the current time point output by the data preprocessing module and a predicted vehicle speed sequence in a period of time after the current time point output by the short-term driving working condition prediction model simultaneously, and splices the historical vehicle speed sequence updated in real time with the predicted vehicle speed sequence to construct combined working condition data containing future working condition change trend;
s105: the real-time driving condition identification model reads characteristic parameters of the combined condition data output by the condition data synthesis module and identifies the real-time driving condition type of the vehicle on line.
Preferably, in step S101, real-time running data of the vehicle is read through the CAN bus of the whole vehicle, the historical vehicle speed sequence is updated in real time in the form of a sliding time window, and the historical running data exceeding the width of the time window is discarded.
Preferably, in step S102, a driving style recognition model is built based on a learning vector quantization neural network LVQNN, wherein inputs of the input layer are a real-time vehicle speed, an accelerator pedal opening, an accelerator pedal change rate, a brake pedal opening, and a brake pedal change rate; the outputs of the output layers are respectively
The three driving styles correspond to the mild style, the normal style and the aggressive style respectively.
Preferably, in step S103, a short-term driving condition prediction model is established by using a markov chain random prediction algorithm, the markov chain uses the vehicle speed and the acceleration as the basis of the condition state division, and a state transition probability matrix is constructed according to the transition frequency between each state; and filtering the output of the short-term driving condition prediction model to obtain a final predicted vehicle speed sequence.
Preferably, in step S104, the total length of the combined working condition data is equal to the sum of the length of the historical vehicle speed sequence and the length of the predicted vehicle speed sequence, and the total length of the combined working condition data is a fixed value, and the length of the predicted vehicle speed sequence is variable, which is determined according to the root mean square error of the vehicle speed of the previous prediction period.
Preferably, the root mean square error of the vehicle speed
The expression of (2) is:
in the method, in the process of the invention,
for the predicted vehicle speed value after filtering treatment, < + >>
Is a true vehicle speed value; />
The length of the predicted time domain is equal to the length of the predicted vehicle speed sequence;
let the minimum value of the length of the prediction time domain be
Maximum value of +.>
The change step length of the prediction time domain is +.>
And (2) and
，/>
is a positive integer; />
、/>
Two preset values of the root mean square error of the vehicle speed;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is less than + ->
The length of the current prediction time domain is increased by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is greater than + ->
The length of the current prediction time domain is reduced by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
The length of the current prediction time domain remains consistent with the length of the previous prediction period.
Preferably, the minimum value of the length of the time domain is predicted
10s, maximum->
For 30s, the change step of the predicted time domain +.>
5s, preset value->
Is 3km/h, preset value +.>
5km/h.
Preferably, in step S105, a real-time driving condition recognition model is built based on the learning vector quantization neural network LVQNN, wherein the input of the input layer is a key variable extracted by principal component analysis in the characteristic parameters of the combined condition data, including an average deceleration,Maximum acceleration, maximum vehicle speed, average running vehicle speed, low-speed running time proportion, and acceleration time proportion; the output of the output layer is
The three real-time driving working condition types respectively correspond to a low-speed driving working condition, a medium-speed driving working condition and a high-speed driving working condition.
Preferably, the training and testing process of the model in the vehicle driving condition online identification method comprises the following steps:
s201: defining the type of the driving working condition, and selecting typical standard circulating working conditions of various driving working conditions from a standard circulating working condition library according to the amplitude of the vehicle speed and the change frequency of the vehicle speed;
s202: dividing the typical standard circulation working condition into segments, establishing a driving working condition data set, and dividing the driving working condition data set into a first data set and a second data set;
s203: taking the first data set as input, and training and testing a driving style identification model;
s204: taking the first data set as input, calculating Markov state transition probability matrixes under various driving styles, and acquiring a predicted vehicle speed sequence at the tail end moment of the working condition segment;
s205: combining the working condition segments in the first data set with the corresponding predicted vehicle speed sequences to construct a combined working condition data set; taking the combined working condition data set as input, and training and testing a real-time driving working condition identification model;
s206: and extracting trained model parameters, implanting the model parameters into a corresponding model of the driving condition recognition system, and testing by adopting a second data set to obtain the complete driving condition recognition system.
Preferably, the driving condition data set is composed of a plurality of typical standard circulation conditions, wherein a plurality of condition segments with unequal lengths are obtained after random segment division;
the working condition fragments are obtained by random number sampling, namely, two-dimensional random sampling is carried out on the starting time and the length of each standard working condition, and the starting time of fragment extraction
And fragment Length->
Expressed as:
in the method, in the process of the invention,
the time length is the standard working condition; />
And->
Maximum and minimum values for segment length; />
And->
A random number between 0 and 1.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a driving style recognition and random prediction algorithm is added in the traditional driving condition recognition method, so that the combination data of the historical vehicle speed data and the predicted data of the future vehicle speed are taken as recognition objects, the characteristics of the current driving condition in the recognition objects are enhanced, the dependency of the condition recognition system on the historical vehicle speed data is reduced, the driving condition recognition accuracy is ensured, and the real-time performance of the recognition result is improved. The Energy Management System (EMS) is applied to the Energy Management System (EMS) of the new energy automobile, so that the self-adaptability of the system can be enhanced, and the dynamic property, the economical efficiency and the service life of the whole automobile can be improved.
According to the invention, the data set of model training and testing is established by selecting the standard circulation working condition, so that the complex process of establishing the data set by adopting the real driving working condition data is avoided, and the development efficiency of the working condition identification system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for online identification of driving conditions in the present embodiment;
FIG. 2 is a schematic diagram of a rolling update process of data in the data preprocessing process in the present embodiment;
FIG. 3 is a schematic diagram of a learning vector quantization neural network in the present embodiment;
FIG. 4 is a schematic diagram of a Markov state transition probability matrix in a short-term driving condition prediction model in the present embodiment;
fig. 5 is a logic switching rule diagram of predicting the length of the time domain in the present embodiment;
FIG. 6 is a schematic diagram of the training and testing process of the condition recognition system in this embodiment;
FIG. 7 is a schematic diagram of typical standard cycling conditions for various types of driving conditions used to construct the condition data set in this embodiment.
Detailed Description
Technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the examples of this invention without making any inventive effort, are intended to fall within the scope of this invention.
It should be understood that the structures, proportions, sizes, etc. shown in the drawings are merely for the purpose of understanding and reading the disclosure, and are not intended to limit the scope of the invention, which is defined by the appended claims, and any structural modifications, proportional changes, or dimensional adjustments, which may be made by those skilled in the art, should fall within the scope of the present disclosure without affecting the efficacy or the achievement of the present invention, and it should be noted that, in the present disclosure, relational terms such as first and second are used solely to distinguish one entity from another entity without necessarily requiring or implying any actual relationship or order between such entities.
The present invention provides an embodiment:
as shown in fig. 1, a vehicle driving condition online identification method based on random prediction and machine learning comprises the following steps:
s101, a data preprocessing module reads real-time running data of a vehicle, wherein the real-time running data comprise a vehicle speed, an accelerator pedal opening and a brake pedal opening;
s102: the driving style identification model reads the real-time vehicle speed, the accelerator pedal opening, the accelerator pedal change rate, the brake pedal opening and the brake pedal change rate output by the data preprocessing module and outputs the real-time driving style type;
s103: the short-term driving condition prediction model simultaneously reads the real-time vehicle speed and the real-time driving style output by the driving style recognition model output by the data preprocessing module, and outputs a predicted vehicle speed sequence within a period of time after the current time point;
s104: the working condition data synthesis module reads a historical vehicle speed sequence in a period of time before the current time point output by the data preprocessing module and a predicted vehicle speed sequence in a period of time after the current time point output by the short-term driving working condition prediction model simultaneously, and splices the historical vehicle speed sequence updated in real time with the predicted vehicle speed sequence to construct combined working condition data containing future working condition change trend;
s105: the real-time driving condition identification model reads characteristic parameters of the combined condition data output by the condition data synthesis module and identifies the real-time driving condition type of the vehicle on line.
Specifically, real-time driving data of the vehicle passes through the whole vehicleThe CAN bus is used for reading, and the data preprocessing module is used for storing and updating historical driving data in real time; as shown in fig. 2, taking vehicle speed data as an example, the historical vehicle speed sequence is updated in real time by sliding a time window, and the current moment is assumed to be
The time window width is +.>
In->
At this time, the historical vehicle speed data recorded in the data preprocessing process is +.>
And discard the historical travel data beyond the time window width. In this embodiment, a sequence of vehicle speeds within the sliding window is set to be constantly updated by scrolling at 1 second intervals.
The driving style recognition model is built based on a learning vector quantization neural network LVQNN-1, as shown in fig. 3, where the learning vector quantization neural network includes an input layer, a competitive layer, and an output layer, and each neuron of the output layer is connected with only one group of neurons in the competitive layer.
Representing the connection weight between the input layer and the competing layer, during training>
Is gradually adjusted to the cluster center,>
representing the connection weight between the contention layer and the output layer, which is fixed at a value of 1. By calculating the distance between the competitive layer neuron and the input vector, the competitive layer neuron with the smallest distance is judged to win, the output neuron connected with the winning neuron outputs 1, and the other output neurons are 0.
Wherein the input of the input layer is real-time speed and accelerator pedalThe opening degree, the accelerator pedal change rate, the brake pedal opening degree, and the brake pedal change rate correspond to those in fig. 1, respectively
The method comprises the steps of carrying out a first treatment on the surface of the The outputs of the output layers are +.>
The three driving styles correspond to the mild style, the normal style and the aggressive style respectively. The number of neurons of the input layer is set to be 5, the number of neurons of the competition layer is set to be 11, the number of neurons of the linear output layer is set to be 3, the learning rate is set to be 0.01, and the error threshold is set to be 0.01.
The short-term driving working condition prediction model is established by adopting a Markov chain random prediction algorithm, the Markov chain takes the vehicle speed and the acceleration as the basis of working condition state division, and a state transition probability matrix is established according to transition frequency among all states; the vehicle speed and the acceleration are used as the basis of working condition state division, sampling points with similar running states are divided into a section, and each section is marked as a state. Selected speeds and accelerations range from 0 to 130km/h and-3 to 3m/s 2 The intervals of the state intervals are 1km/h and 0.05m/s respectively 2 。
Specifically, the model predicts the length of the time domain according to the current vehicle speed information
For the maximum time scale, the transition probability among the states in the driving working condition under different time scales is counted, a multi-step state transition probability matrix with different time scales is constructed, as shown in fig. 4, by predicting the +.>
The calling scale at the moment of speed is +.>
The probability matrix of the vehicle speed prediction method improves the accuracy of the vehicle speed prediction under different prediction time domains, and the transition probability under each time scale is expressed as follows:
in the method, in the process of the invention,
all are in state of->
Representing the Markov chain at->
Time of day->
Is a one-step transition probability on a time scale.
State transition probability matrix
Is expressed in different time scales +.>
Under the probability of transition between different states, each element in the matrix is expressed as:
in the method, in the process of the invention,
indicating the driving condition, when the predicted time length is +.>
When in state->
Transition to State->
Frequency of (2);
indicating the driving condition, when the predicted time length is +.>
When in state->
Transition to the sum of any states at the next time.
According to the current running state
And a state transition probability matrix of the corresponding time scale +.>
Decision on the state to be transferred to at the next moment by means of a random process +.>
. In this embodiment, the randomness of the vehicle speed variation is simulated by using the Monte Carlo method, i.e. a random number between 0 and 1 is generated>
The following inequality is satisfied:
time of then
The predicted vehicle speed after that can be expressed as:
in the method, in the process of the invention,
for passing->
Predicted vehicle speed after time; />
For the current vehicle speed>
For the current state->
To predictive state->
Vehicle speed span of (2); />
A speed value represented for a single vehicle speed span. />
Filtering the output of the short-term driving condition prediction model to obtain a final predicted vehicle speed sequence, smoothing the predicted result by adopting 4-point mean value filtering, eliminating high-frequency noise in the predicted result, and filtering
Predicted value of vehicle speed at time->
Expressed as:
the length of the maximum predicted time domain is set to 30 seconds and the predicted time domain interval is set to 1 second.
The total length of the combined working condition data is equal to the sum of the length of the historical vehicle speed sequence and the length of the predicted vehicle speed sequence, the total length of the combined working condition data is a fixed value, the length of the predicted vehicle speed sequence is variable, and the length of the predicted vehicle speed sequence is determined according to the root mean square error of the vehicle speed of the previous prediction period.
Root mean square error of vehicle speed
The expression of (2) is:
in the method, in the process of the invention,
for the predicted vehicle speed value after filtering treatment, < + >>
Is a true vehicle speed value; />
The length of the predicted time domain is equal to the length of the predicted vehicle speed sequence;
let the minimum value of the length of the prediction time domain be
Maximum value of +.>
The change step length of the prediction time domain is +.>
And (2) and
，/>
is a positive integer; />
、/>
Two preset values of the root mean square error of the vehicle speed;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is less than + ->
The length of the current prediction time domain is increased by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is greater than + ->
The length of the current prediction time domain is reduced by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
The length of the current prediction time domain remains consistent with the length of the previous prediction period.
Preferably, the minimum value of the length of the prediction time domain
10s, maximum->
For 30s, the change step of the predicted time domain +.>
5s, preset value->
Is 3km/h, preset value +.>
The logical switching rule predicting the length of the time domain is shown in fig. 5 for 5km/h.
The real-time driving condition identification model is built based on a learning vector quantization neural network LVQNN-2, whereinThe input of the input layer is a key variable which is extracted by the analysis of the principal component in the characteristic parameters of the combined working condition data, and comprises average deceleration, maximum acceleration, maximum vehicle speed, average running vehicle speed, low-speed running time proportion and acceleration time proportion; the output of the output layer is
The three real-time driving working condition types respectively correspond to a low-speed driving working condition, a medium-speed driving working condition and a high-speed driving working condition, the number of neurons of an input layer is set to be equal to the number of characteristic parameters, the number of neurons of a competition layer is 11, the number of neurons of a linear output layer is 3, the learning rate is 0.01, and the error threshold is 0.01.
For describing the differences between the various driving condition types, 16 characteristic parameters are defined, as shown in table 1.
In order to obtain the optimal characteristic parameter combination, repeated information is prevented from being introduced due to excessive characteristic parameters, the calculated amount of a system is increased, and the average deceleration, the maximum acceleration, the maximum vehicle speed, the average running vehicle speed, the low-speed running time proportion and the acceleration time proportion are determined to be used as the input of a real-time running condition identification model through Principal Component Analysis (PCA) and a large amount of comparison analysis.
As shown in fig. 6 and 7, the training and testing process of the model in the vehicle running condition online identification method includes the following steps:
s201: defining the type of the driving working condition, and selecting typical standard circulating working conditions of various driving working conditions from a standard circulating working condition library according to the amplitude of the vehicle speed and the change frequency of the vehicle speed; the high-speed working condition has higher average running speed, and the change frequency of the speed is lower; the average running speed of the low-speed working condition is lower, and the speed change frequency is higher; the average running speed and the speed change frequency of the medium speed working condition are at the medium and equal level;
s202: dividing the typical standard circulation working condition into segments, establishing a driving working condition data set, and dividing the driving working condition data set into a first data set and a second data set; the first data set and the second data set account for 70% and 30% of the driving condition data set, respectively.
S203: taking the first data set as input, and training and testing a driving style identification model;
s204: taking the first data set as input, calculating Markov state transition probability matrixes under various driving styles, and acquiring a predicted vehicle speed sequence at the tail end moment of the working condition segment;
s205: combining the working condition segments in the first data set with the corresponding predicted vehicle speed sequences to construct a combined working condition data set; taking the combined working condition data set as input, and training and testing a real-time driving working condition identification model;
s206: and extracting trained model parameters, implanting the model parameters into a corresponding model of the driving condition recognition system, and testing by adopting a second data set to obtain the complete driving condition recognition system.
The driving working condition data set is composed of a plurality of working condition fragments with unequal lengths, which are obtained by dividing a plurality of typical standard circulation working conditions by random fragments; the working condition fragments are obtained by random number sampling, namely, two-dimensional random sampling is carried out on the starting time and the length of each standard working condition, and the starting time of fragment extraction
And fragment Length->
Expressed as:
in the method, in the process of the invention,
the time length is the standard working condition; />
And->
Maximum and minimum values for segment length; />
And->
A random number between 0 and 1.
The classification index of the driving style is the average speed of each segment
Average acceleration->
Average addition rate->
Mean deceleration->
Average deceleration rate +.>
The calculation formula of each index is as follows: />
In the method, in the process of the invention,
and->
The speed value and the acceleration value at each moment in the working condition segment are respectively +.>
For the total number of data of the working condition segment, +.>
And->
And the total data of acceleration values greater than 0 and less than 0 in the working condition segments are respectively obtained.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present invention should be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The vehicle driving condition online identification method based on random prediction and machine learning is characterized by comprising the following steps of:
s101, a data preprocessing module reads real-time running data of a vehicle, wherein the real-time running data comprise a vehicle speed, an accelerator pedal opening and a brake pedal opening;
s102: the driving style identification model reads the real-time vehicle speed, the accelerator pedal opening, the accelerator pedal change rate, the brake pedal opening and the brake pedal change rate output by the data preprocessing module and outputs the real-time driving style type;
s103: the short-term driving condition prediction model simultaneously reads the real-time vehicle speed and the real-time driving style output by the driving style recognition model output by the data preprocessing module, and outputs a predicted vehicle speed sequence within a period of time after the current time point;
s104: the working condition data synthesis module reads a historical vehicle speed sequence in a period of time before the current time point output by the data preprocessing module and a predicted vehicle speed sequence in a period of time after the current time point output by the short-term driving working condition prediction model simultaneously, and splices the historical vehicle speed sequence updated in real time with the predicted vehicle speed sequence to construct combined working condition data containing future working condition change trend;
s105: the real-time driving condition identification model reads characteristic parameters of the combined condition data output by the condition data synthesis module and identifies the real-time driving condition type of the vehicle on line.
2. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: in step S101, real-time running data of the vehicle is read through the CAN bus of the whole vehicle, the historical vehicle speed sequence is updated in real time in a sliding time window mode, and the historical running data exceeding the width of the time window is discarded.
3. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: in the step S102, a driving style recognition model is built based on a learning vector quantization neural network LVQNN, wherein the input of the input layer is a real-time vehicle speed, an accelerator pedal opening, an accelerator pedal change rate, a brake pedal opening and a brake pedal change rate; the outputs of the output layers are respectively
The three driving styles correspond to the mild style, the normal style and the aggressive style respectively.
4. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: in step S103, a short-term driving condition prediction model is established by using a markov chain random prediction algorithm, the markov chain uses the vehicle speed and the acceleration as the basis of the condition state division, and a state transition probability matrix is constructed according to the transition frequency among the states; and filtering the output of the short-term driving condition prediction model to obtain a final predicted vehicle speed sequence.
5. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: in step S104, the total length of the combined working condition data is equal to the sum of the length of the historical vehicle speed sequence and the length of the predicted vehicle speed sequence, the total length of the combined working condition data is a fixed value, the length of the predicted vehicle speed sequence is variable, and the length of the predicted vehicle speed sequence is determined according to the root mean square error of the vehicle speed in the previous prediction period.
6. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 5, wherein the method comprises the following steps: root mean square error of the vehicle speed
The expression of (2) is:
in the method, in the process of the invention,
for the predicted vehicle speed value after filtering treatment, < + >>
Is a true vehicle speed value; />
The length of the predicted time domain is equal to the length of the predicted vehicle speed sequence;
let the minimum value of the length of the prediction time domain be
Maximum value of +.>
The change step length of the prediction time domain is +.>
And->
，/>
Is a positive integer; />
、/>
Two preset values of the root mean square error of the vehicle speed;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is smaller than
The length of the current prediction time domain is increased by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
If the length of the prediction time domain of the previous prediction period is greater than
The length of the current prediction time domain is reduced by +.>
Otherwise, the length of the current prediction time domain is kept consistent with the length of the previous prediction period;
root mean square error of vehicle speed at last prediction period
The length of the current prediction time domain remains consistent with the length of the previous prediction period.
7. According to claim 6The vehicle driving condition online identification method based on random prediction and machine learning is characterized by comprising the following steps of: minimum value of the length of the prediction time domain
10s, maximum->
For 30s, the change step of the predicted time domain +.>
5s, preset value->
Is 3km/h, preset value +.>
5km/h.
8. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: in the step S105, a real-time driving condition recognition model is built based on a learning vector quantization neural network LVQNN, wherein the input of the input layer is a key variable extracted by principal component analysis in the characteristic parameters of the combined condition data, including an average deceleration, a maximum acceleration, a maximum vehicle speed, an average driving vehicle speed, a low-speed driving time proportion and an acceleration time proportion; the output of the output layer is
The three real-time driving working condition types respectively correspond to a low-speed driving working condition, a medium-speed driving working condition and a high-speed driving working condition.
9. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 1, wherein the method comprises the following steps: the training and testing process of the model in the vehicle running condition online identification method comprises the following steps:
s201: defining the type of the driving working condition, and selecting typical standard circulating working conditions of various driving working conditions from a standard circulating working condition library according to the amplitude of the vehicle speed and the change frequency of the vehicle speed;
s202: dividing the typical standard circulation working condition into segments, establishing a driving working condition data set, and dividing the driving working condition data set into a first data set and a second data set;
s203: taking the first data set as input, and training and testing a driving style identification model;
s204: taking the first data set as input, calculating Markov state transition probability matrixes under various driving styles, and acquiring a predicted vehicle speed sequence at the tail end moment of the working condition segment;
s205: combining the working condition segments in the first data set with the corresponding predicted vehicle speed sequences to construct a combined working condition data set; taking the combined working condition data set as input, and training and testing a real-time driving working condition identification model;
s206: and extracting trained model parameters, implanting the model parameters into a corresponding model of the driving condition recognition system, and testing by adopting a second data set to obtain the complete driving condition recognition system.
10. The method for on-line identification of vehicle driving conditions based on random prediction and machine learning according to claim 9, wherein the method comprises the following steps: the running condition data set is composed of a plurality of typical standard circulation conditions which are divided by random segments to obtain condition segments with unequal lengths;
the working condition fragments are obtained by random number sampling, namely, two-dimensional random sampling is carried out on the starting time and the length of each standard working condition, and the starting time of fragment extraction
And fragment Length->
Expressed as:
in the method, in the process of the invention,
the time length is the standard working condition; />
And->
Maximum and minimum values for segment length; />
And->
A random number between 0 and 1. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310183550.0A CN115859123B (en) | 2023-03-01 | 2023-03-01 | Vehicle driving condition online identification method based on random prediction and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310183550.0A CN115859123B (en) | 2023-03-01 | 2023-03-01 | Vehicle driving condition online identification method based on random prediction and machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115859123A CN115859123A (en) | 2023-03-28 |
| CN115859123B true CN115859123B (en) | 2023-05-02 |
Family
ID=85659492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310183550.0A Active CN115859123B (en) | 2023-03-01 | 2023-03-01 | Vehicle driving condition online identification method based on random prediction and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859123B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2610836A1 (en) * | 2011-12-30 | 2013-07-03 | Seat, S.A. | Device and method for the on-line prediction of the driving cycle in an automotive vehicle |
| CN107527113A (en) * | 2017-08-01 | 2017-12-29 | 北京理工大学 | A kind of operating mode Forecasting Methodology of hybrid car travel operating mode |
| CN110254417A (en) * | 2019-06-27 | 2019-09-20 | 清华大学苏州汽车研究院（吴江） | Method for controlling hybrid power vehicle based on actual condition and the double identifications of driving style |
| CN113297685A (en) * | 2021-07-27 | 2021-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Vehicle operation condition mode identification method |
| CN115718886A (en) * | 2022-11-21 | 2023-02-28 | 长安大学 | Construction method and device for pure electric vehicle running condition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280601B2 (en) * | 2008-07-24 | 2012-10-02 | GM Global Technology Operations LLC | Adaptive vehicle control system with integrated maneuver-based driving style recognition |
-
2023
- 2023-03-01 CN CN202310183550.0A patent/CN115859123B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2610836A1 (en) * | 2011-12-30 | 2013-07-03 | Seat, S.A. | Device and method for the on-line prediction of the driving cycle in an automotive vehicle |
| CN107527113A (en) * | 2017-08-01 | 2017-12-29 | 北京理工大学 | A kind of operating mode Forecasting Methodology of hybrid car travel operating mode |
| CN110254417A (en) * | 2019-06-27 | 2019-09-20 | 清华大学苏州汽车研究院（吴江） | Method for controlling hybrid power vehicle based on actual condition and the double identifications of driving style |
| CN113297685A (en) * | 2021-07-27 | 2021-08-24 | 中汽研（天津）汽车工程研究院有限公司 | Vehicle operation condition mode identification method |
| CN115718886A (en) * | 2022-11-21 | 2023-02-28 | 长安大学 | Construction method and device for pure electric vehicle running condition |
Non-Patent Citations (6)
| Title |
|---|
| Derivation of Real-World Driving Cycles Corresponding to Traffic Situation and Driving Style on the Basis of Markov Models and Cluster Analyses;R Liessner 等;《Derivation of Real-World Driving Cycles Corresponding to Traffic Situation and Driving Style on the Basis of Markov Models and Cluster Analyses》;1-7 * |
| Prediction of vehicle driving conditions with incorporation of stochastic forecasting and machine learning and a case study in energy management of plug-in hybrid electric vehicles;Yonggang Liu 等;《Mechanical Systems and Signal Processing》;1-17 * |
| Review of driving conditions prediction and driving style recognition based control algorithms for hybrid electric vehicles;Rui Wang 等;《Review of driving conditions prediction and driving style recognition based control algorithms for hybrid electric vehicles》;1-7 * |
| 工况特征参数对客车燃油经济性的影响;刘炳文 等;《科学技术与工程》;第18卷(第17期);181-186 * |
| 电动汽车城市行驶工况构建与驾驶风格识别研究;黄春;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;C035-1675 * |
| 驾驶风格和行驶工况对纯电动汽车续驶里程的影响研究;刘荣昌 等;汽车 《2020中国工程学会年会论文集》;459-463 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115859123A (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110775065B (en) | Hybrid electric vehicle battery life prediction method based on working condition recognition | |
| CN111459995B (en) | Multi-mode vehicle speed prediction method based on driving data | |
| CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
| CN108556682A (en) | A kind of continual mileage prediction technique, device and equipment | |
| CN112327168A (en) | XGboost-based electric vehicle battery consumption prediction method | |
| CN113222385B (en) | Method for constructing and evaluating driving condition of electric automobile | |
| CN112182962A (en) | Hybrid electric vehicle running speed prediction method | |
| CN110245390B (en) | Automobile engine oil consumption prediction method based on RS-BP neural network | |
| CN115759462A (en) | Charging behavior prediction method and device for electric vehicle user and electronic equipment | |
| CN114495499A (en) | Multi-target intelligent networked vehicle collaborative optimization control method | |
| CN113297795A (en) | Method for constructing running condition of pure electric vehicle | |
| CN106875681B (en) | A kind of traffic congestion tendency prediction technique and system | |
| CN115166534A (en) | Method and system for predicting remaining service life of lithium ion battery | |
| CN114897312A (en) | Driving behavior scoring method, device, equipment and storage medium | |
| CN115859123B (en) | Vehicle driving condition online identification method based on random prediction and machine learning | |
| CN112035536A (en) | Electric automobile energy consumption prediction method considering dynamic road network traffic flow | |
| CN113537620B (en) | Vehicle speed prediction method based on Markov model optimization and working condition recognition | |
| CN113276829B (en) | Vehicle running energy-saving optimization weight-changing method based on working condition prediction | |
| Beşkardeş et al. | Data-driven-based fuzzy control system design for a hybrid electric vehicle | |
| CN111222550B (en) | User electricity consumption behavior determining method and device | |
| CN112489422B (en) | Traffic flow prediction method based on algorithm model analysis | |
| CN115146478A (en) | Running condition construction method and device based on optimization algorithm and related equipment | |
| CN114169226A (en) | Short-term power load prediction method, computer device, and storage medium | |
| CN113788007A (en) | Layered real-time energy management method and system | |
| CN114049968A (en) | Infectious disease development trend prediction method, system, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |