CN115271001B - Vehicle driving condition identification method and device, vehicle and storage medium - Google Patents
Vehicle driving condition identification method and device, vehicle and storage medium Download PDFInfo
- Publication number
- CN115271001B CN115271001B CN202211194619.1A CN202211194619A CN115271001B CN 115271001 B CN115271001 B CN 115271001B CN 202211194619 A CN202211194619 A CN 202211194619A CN 115271001 B CN115271001 B CN 115271001B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- speed
- characteristic parameter
- average
- time ratio
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a device for identifying the running condition of a vehicle, the vehicle and a storage medium, wherein the method comprises the following steps: collecting driving data of a preset characteristic parameter combination of a vehicle in the driving process; inputting the driving data combined by the preset characteristic parameters into a trained vehicle working condition recognition model to obtain the driving working condition of the vehicle; the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination; the preset characteristic parameter combination is obtained by screening a plurality of candidate characteristic parameter combinations based on the test result of each candidate characteristic parameter combination; and the test result of each candidate characteristic parameter combination is a test result tested by using a corresponding candidate vehicle working condition identification model, and each candidate vehicle working condition identification model is obtained by training a training sample based on the candidate characteristic parameter combination. The method for identifying the vehicle running condition has higher identification accuracy.
Description
Technical Field
The invention relates to the technical field of vehicle driving, in particular to a method and a device for identifying a vehicle driving condition, a vehicle and a storage medium.
Background
The vehicle running working condition, namely the vehicle running working condition, is a working condition of the vehicle during transportation running, reflects a speed-time curve of the urban running vehicle, and is mainly used for vehicle performance calibration and vehicle oil consumption calibration.
The driving working condition has great influence on the fuel economy, the battery power consumption and the endurance mileage of the vehicle, and different vehicle energy management strategies can be formulated according to different working conditions. For a hybrid power vehicle, in the process of formulating an energy management strategy, if the type of the current running working condition can be identified, the control strategy is adjusted and switched in real time, the optimal power distribution among different power sources is realized, and the fuel economy of the vehicle is further improved. For the pure electric vehicle, the working condition type is identified, the battery consumption level under different types of working conditions is obtained, and the accuracy of estimating the remaining driving range of the pure electric vehicle is improved.
However, the existing working condition identification model has low identification accuracy, and cannot accurately identify the driving working condition of the vehicle.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying a vehicle running condition, a vehicle and a storage medium, and aims to solve the problem of low identification accuracy of a current working condition identification model.
In a first aspect, an embodiment of the present invention provides a method for identifying a driving condition of a vehicle, including:
acquiring running data of a preset characteristic parameter combination of a vehicle in a running process;
inputting the driving data combined by the preset characteristic parameters into a trained vehicle working condition recognition model to obtain the driving working condition of the vehicle;
the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination; the preset characteristic parameter combination is obtained by screening a plurality of candidate characteristic parameter combinations based on the test result of each candidate characteristic parameter combination; and the test result of each candidate characteristic parameter combination is a test result tested by using a corresponding candidate vehicle working condition recognition model, and each candidate vehicle working condition recognition model is obtained by training a training sample based on the candidate characteristic parameter combination.
In one possible implementation manner, each candidate characteristic parameter combination comprises a plurality of characteristic parameters, and the plurality of characteristic parameters are obtained by performing characteristic extraction on historical driving data of the vehicle; the combination of the multiple candidate characteristic parameters is obtained by screening the multiple characteristic parameters based on a principal component analysis method and combining several characteristic parameters reserved after screening.
In a possible implementation manner, the training sample of each candidate characteristic parameter combination is a data set which is based on the candidate characteristic parameter combination and used for carrying out cluster analysis on historical driving data of the vehicle to obtain multiple preset working condition types of the candidate characteristic parameter combination; respectively selecting all or part of data from the data sets of each working condition type in the candidate characteristic parameter combination as training samples; wherein the type of operating condition comprises at least one of: congestion working conditions, urban working conditions, suburban working conditions and high-speed working conditions.
In a possible implementation manner, the historical driving data of the vehicle needs to be preprocessed before feature extraction, and the preprocessed driving data is divided into a plurality of short condition segments.
In one possible implementation mode, the preprocessing is to perform GPS signal missing processing on historical driving data of the vehicle, and perform moving average filtering processing on the processed data; wherein the historical travel data of the vehicle includes travel data for a plurality of different road segments and a plurality of different drivers.
In one possible implementation, the plurality of characteristic parameters includes at least one of: the system comprises a running distance, an average speed, an average running speed, a highest vehicle speed, a speed standard deviation, an acceleration absolute value average value, an acceleration absolute value standard deviation, an acceleration time ratio, a deceleration time ratio, an idle speed time ratio and a uniform speed time ratio; wherein, the average speed is the average value of speeds in a certain segment, and the average running speed is the average value of speeds greater than 0 in the segment;
the plurality of candidate feature parameter combinations include at least one of the following 7 candidate feature parameter combinations: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination.
In one possible implementation, the test result includes a recognition accuracy and/or a time taken for recognition;
the preset characteristic parameter combination is a combination of average speed, an average value of absolute values of acceleration, a uniform speed time ratio and an idle speed time ratio.
In a second aspect, an embodiment of the present invention provides an apparatus for identifying a driving condition of a vehicle, including:
the data acquisition module is used for acquiring running data of a preset characteristic parameter combination in the running process of the vehicle;
the working condition recognition module is used for inputting the driving data combined by the preset characteristic parameters into the trained vehicle working condition recognition model so as to obtain the driving working conditions of the vehicle;
the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination; the preset characteristic parameter combination is obtained by screening a plurality of candidate characteristic parameter combinations based on the test result of each candidate characteristic parameter combination; and the test result of each candidate characteristic parameter combination is a test result tested by using a corresponding candidate vehicle working condition recognition model, and each candidate vehicle working condition recognition model is obtained by training a training sample based on the candidate characteristic parameter combination.
In one possible implementation manner, each candidate characteristic parameter combination comprises a plurality of characteristic parameters, and the plurality of characteristic parameters are obtained by performing characteristic extraction on historical driving data of the vehicle; the multiple candidate characteristic parameters are obtained by screening multiple characteristic parameters based on a principal component analysis method and combining several characteristic parameters reserved after screening.
In a possible implementation manner, the training sample of each candidate characteristic parameter combination is a data set which is based on the candidate characteristic parameter combination and used for carrying out cluster analysis on historical driving data of the vehicle to obtain multiple preset working condition types of the candidate characteristic parameter combination; respectively selecting all or part of data from the data sets of each working condition type in the candidate characteristic parameter combination as training samples; wherein the type of operating condition comprises at least one of: congestion conditions, urban conditions, suburban conditions and high-speed conditions.
In a possible implementation manner, the historical driving data of the vehicle needs to be preprocessed before feature extraction, and the preprocessed driving data is divided into a plurality of short condition segments.
In one possible implementation mode, the preprocessing is to perform GPS signal missing processing on historical driving data of the vehicle and perform moving average filtering processing on the processed data; wherein the historical driving data of the vehicle comprises driving data of a plurality of different road sections and a plurality of different drivers.
In one possible implementation, the plurality of characteristic parameters includes at least one of: the system comprises a running distance, an average speed, an average running speed, a highest vehicle speed, a speed standard deviation, an acceleration absolute value average value, an acceleration absolute value standard deviation, an acceleration time ratio, a deceleration time ratio, an idle speed time ratio and a uniform speed time ratio; wherein, the average speed is the average value of speeds in a certain segment, and the average running speed is the average value of speeds in the segment, the speeds of which are more than 0;
the plurality of candidate feature parameter combinations include at least one of the following 7 candidate feature parameter combinations: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average value of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination.
In one possible implementation, the test result includes a recognition accuracy and/or a time taken for recognition;
the preset characteristic parameter combination is a combination of average speed, an average value of absolute values of acceleration, a uniform speed time ratio and an idle speed time ratio.
In a third aspect, the present application provides a vehicle comprising an electronic device, the electronic device comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor, when executing the computer program, implements the steps of the method for identifying a driving condition of the vehicle as described in the first aspect or any one of the possible implementations of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for identifying a driving condition of a vehicle according to the first aspect or any one of the possible implementations of the first aspect.
The embodiment of the invention provides a method and a device for identifying the running condition of a vehicle, the vehicle and a storage medium. The vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination. Therefore, when the vehicle working condition is identified, the driving working condition of the vehicle can be obtained only by inputting the driving data of the preset characteristic parameter combination of the vehicle in the driving process into the vehicle working condition identification model.
The optimal preset characteristic parameter combination capable of accurately representing the working condition is screened from the multiple candidate characteristic parameter combinations, and the neural network obtained by training the optimal preset characteristic parameter combination is determined as the vehicle working condition recognition model. The driving data of the preset characteristic parameter combination is only input into the vehicle working condition recognition model, so that the processing time of the vehicle working condition recognition model can be shortened, the recognition accuracy of the working conditions can be improved, and the driving working conditions of the vehicle can be recognized more accurately.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions 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 it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of an implementation of a method for determining a preset feature parameter combination and a vehicle condition recognition model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of processing historical vehicle travel speed data using moving average filtering according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an implementation of a method for identifying a driving condition of a vehicle according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a test result of a vehicle condition recognition model on a test set according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a test result of a vehicle condition recognition model on real-time acquired driving data according to an embodiment of the present invention
FIG. 6 is a graphical representation of the results of identifying the operating conditions of FIG. 5;
FIG. 7 is a schematic structural diagram of a device for identifying a driving condition of a vehicle according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of an electronic device of a vehicle provided by an embodiment of the invention;
fig. 9 is a schematic diagram of a vehicle according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following description is made by way of specific embodiments with reference to the accompanying drawings.
The running condition has great influence on the fuel economy, the battery power consumption and the endurance mileage of the vehicle. For a hybrid power vehicle, in the process of formulating an energy management strategy, if the type of the current running working condition can be accurately identified, the control strategy is adjusted and switched in real time, the optimal power distribution among different power sources is realized, and the fuel economy of the vehicle is further improved. For the pure electric vehicle, the working condition type is identified, the battery consumption level under different types of working conditions is obtained, and the accuracy of estimating the remaining driving range of the pure electric vehicle is improved.
If the control strategy can be adjusted and switched in real time according to the change of the actual running working condition, the fuel economy of the vehicle can be improved, and the emission of harmful pollutants is reduced. However, the recognition accuracy of the current recognition model is low.
In order to solve the prior art problems, the embodiment of the invention provides a method and a device for identifying a vehicle running condition, a vehicle and a storage medium. The following first describes a method for identifying a vehicle driving condition according to an embodiment of the present invention.
The main body of the vehicle driving condition identification method may be a vehicle driving condition identification device, and the vehicle driving condition identification device may be an electronic device with a processor and a memory, such as a mobile electronic device or a non-mobile electronic device. The embodiments of the present invention are not particularly limited.
Before the method for identifying the vehicle running condition provided by the embodiment of the invention is introduced, a determination process of a preset characteristic parameter combination and a training process of a vehicle condition identification model need to be introduced first. And when the preset characteristic parameter combination and the vehicle working condition recognition model are determined, the vehicle working condition can be recognized.
In some embodiments, the preset feature parameter combination is selected from a plurality of candidate feature parameter combinations based on a test result of each candidate feature parameter combination. The vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination.
The test result of each candidate characteristic parameter combination is a test result of a candidate vehicle working condition recognition model obtained by training a training sample based on the candidate characteristic parameter combination.
As shown in fig. 1, it shows a flowchart of an implementation of the method for determining the preset feature parameter combination and the vehicle condition identification model according to the embodiment of the present invention, which is detailed as follows:
step S110 is to extract a plurality of feature parameters from the historical travel data of the vehicle, and to select a plurality of candidate feature parameter combinations from the plurality of feature parameters.
The vehicle may be a scooter, a truck, a bus, a taxi, a commercial vehicle, or a passenger vehicle, and is not limited herein.
Wherein each candidate feature parameter combination comprises at least two of the plurality of feature parameters.
In some embodiments, the historical driving data of the vehicle includes the historical driving data of the vehicle of different drivers and different road sections collected by a vehicle data collector, a vehicle data collecting system and the like.
Specifically, historical driving data of different road sections such as commercial areas, residential areas, suburbs, urban and rural areas, expressways, main roads, highways and the like can be selected. Historical driving data of drivers of different genders, ages and driving ages can be selected.
In some embodiments, during the historical driving data collection process of the vehicle, due to the influence of the precision of the collection equipment, the traffic environment and the like, the data is lost, abnormal and the like, and the data quality is reduced. In order to ensure the reliability of the historical driving data of the vehicle, the historical driving data of the vehicle needs to be preprocessed and analyzed.
In this embodiment, since the vehicle-mounted GPS signal is missing or the positioning is not accurate due to a road section such as a high-rise building or a tunnel, and the vehicle travel data is missing, it is necessary to perform GPS signal missing processing on the acquired historical travel data of the vehicle.
Specifically, the historical driving data of the vehicle may be processed by interpolation or elimination.
In addition, due to the influence of external factors, abnormal noise interference may occur in the speed of the historical travel data of the vehicle, so that an error may occur in the historical travel speed of the vehicle, and thus, a filtering process is required.
Specifically, a moving average filtering algorithm may be used to filter the original speed in the historical driving data of the vehicle, and a sliding window with a fixed length is used for the original speed, and the average value of several data in the neighborhood replaces the original data in the corresponding position to form a new sequence of average values.
y(t)Is the average value of the values,t=1,2...n。nfor the purpose of the total data length,Tin order to be a step of time,x(t)is a vehicleHistorical travel speed data of the vehicle.
In fig. 2, the solid line is the original speed, and the chain line is the filtered speed, and it can be seen from fig. 2 that the original speed data has a sharp peak before the moving average filtering, and after the filtering process, the speed curve becomes smooth, and the vehicle speed curves before and after the filtering are relatively identical.
In some embodiments, after preprocessing the historical driving data of the vehicle, firstly, the preprocessed driving data needs to be divided into a plurality of short condition segments.
Specifically, the preprocessed running data may be divided into a plurality of short condition segments with a time period of 150 s.
Then, a plurality of characteristic parameters are extracted from the historical travel data of the vehicle, and a plurality of characteristic parameter combinations are selected from the plurality of characteristic parameters.
The characteristic parameter is a parameter for describing a characteristic of the operating condition, and specifically, the plurality of characteristic parameters may include at least one of: the system comprises a running distance, an average speed, an average running speed, a highest vehicle speed, a speed standard deviation, an acceleration absolute value average value, an acceleration absolute value standard deviation, an acceleration time ratio, a deceleration time ratio, an idle speed time ratio and a uniform speed time ratio. The average speed is the average speed in a certain working condition segment, and the average running speed is the average speed of speeds greater than 0 in the working condition segment.
In some embodiments, since all the characteristic parameters are not independent from each other but have a certain correlation, a plurality of characteristic parameter combinations can be selected to be used for characterizing the operating condition information. The characteristic parameters can be processed by adopting a principal component analysis method, the characteristic parameters with the accumulated contribution rate higher than a preset threshold value are selected as reserved characteristic parameters, and the reserved characteristic parameters are combined to obtain various characteristic parameter combinations.
In this embodiment, taking the above 11 characteristic parameters as an example, 2047 combinations are total, the number is large, and there are many combinations with less influence in the 2047 combinations. The 11 characteristic parameters can be processed by adopting a principal component analysis method, a plurality of characteristic parameters with the accumulated contribution rate higher than a preset threshold value are selected, and the reserved characteristic parameters are combined to obtain a plurality of characteristic parameter combinations.
For example, 6 characteristic parameters are retained by principal component analysis, including: average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination. Then, these 6 characteristic parameters are combined.
Specifically, at least one of the following 7 candidate feature parameter combinations consisting of 6 feature parameters may be selected: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average value of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average, idle speed time ratio, uniform speed time ratio and running distance combination.
And step S120, for each candidate characteristic parameter combination, performing cluster analysis on the historical driving data of the vehicle based on the candidate characteristic parameter combination to obtain a data set of preset multiple working condition types of the candidate characteristic parameter combination. And respectively selecting all or part of data from the data sets of each working condition type in the candidate characteristic parameter combination as training samples, and training and testing a pre-constructed neural network based on the training samples to obtain a test result corresponding to the candidate characteristic parameter combination.
In some embodiments, based on the candidate feature parameter combination, cluster analysis is performed on all short condition segments to obtain a data set of a preset condition type of the candidate feature parameter combination.
Specifically, a K-means clustering algorithm may be used to perform cluster analysis on all short condition segments. The core idea of the K-means clustering algorithm is that the minimum Euclidean distance between each sample datum and a clustering center is calculated by selecting the clustering number K and an initial clustering center, the sample datum is distributed to the nearest clustering center according to the distance, a new clustering center is selected in a continuous iteration mode, and each data category is adjusted.
In this embodiment, each candidate feature parameter combination may be clustered into at least one of four operating condition types, namely, a congestion operating condition, an urban operating condition, a suburban operating condition, and a high-speed operating condition, by using a K-means clustering algorithm. Of course, the working conditions can be clustered into other types according to actual use scenes, and the working condition types can be set according to actual use conditions.
Specifically, each candidate characteristic parameter combination can be clustered into four data sets of congestion conditions, urban conditions, suburban conditions and high-speed conditions respectively. And respectively selecting all or random partial fragments from each candidate characteristic parameter combination as training samples, and using part of data in the training samples for training and the other part of data for testing.
In some embodiments, the pre-constructed neural network may select a probabilistic neural network as the neural network for condition recognition. The user can select other neural networks according to application scenes.
The probabilistic neural network is a feedforward neural network and consists of an input layer, a hidden layer and an output layer. The first layer is an input layer, which is used for receiving values of training samples and transferring a data layer to a hidden layer. The second layer is a hidden layer, the matching relation between the input feature vector and each mode in the training set is calculated, and the number of neurons in the hidden layer is equal to the sum of the number of training samples in each category. The third layer is an output layer, the sum of the mode layer node outputs corresponding to the test samples of the same category is obtained, normalization processing is carried out to obtain the probabilities of the test samples corresponding to different categories, and the categories of the test samples are judged according to the probabilities.
And after the neural network identified by the working condition is determined to be the probabilistic neural network, selecting a proper training sample to train the probabilistic neural network.
And respectively selecting all or part of data in the data set of each working condition type in each candidate characteristic parameter combination as training samples, inputting the training samples into a pre-constructed probabilistic neural network, and then training the probabilistic neural network corresponding to each candidate characteristic parameter combination. After the training is finished, the candidate vehicle working condition recognition model corresponding to each candidate characteristic parameter combination can be tested.
For example, 300 segments from each type of condition of each candidate characteristic parameter combination may be selected as training samples, 280 segments may be selected as a training set, and the other 20 segments may be selected as a test set.
In some embodiments, the test results may be the recognition accuracy and/or the time taken for recognition. Different test results can be selected as the basis for judging the characteristic parameter combination and the performance of the probabilistic neural network according to different requirements.
And S130, determining a preset characteristic parameter combination and a corresponding trained vehicle working condition recognition model based on the test results of the various candidate characteristic parameter combinations in the neural network.
And determining a preset characteristic parameter combination and a vehicle working condition recognition model based on the recognition accuracy and/or the recognition time of the multiple candidate characteristic parameter combinations in the neural network.
Specifically, the preset feature parameter combination may be a preset feature parameter combination that is the highest recognition accuracy of multiple candidate feature parameter combinations in the neural network. The shortest time for identifying the multiple candidate characteristic parameter combinations in the neural network can be used as the preset characteristic parameter combination. The recognition accuracy and the recognition time can be simultaneously used as the judgment standard, the recognition accuracy and the recognition time are combined according to the preset weight, and the optimal combination is selected as the preset characteristic parameter combination.
And after the preset characteristic parameter combination is determined, selecting a neural network trained by adopting the preset characteristic parameter combination, namely the vehicle working condition recognition model.
Illustratively, the preset characteristic parameter is a combination of an average speed, an average absolute value of acceleration, a uniform speed-time ratio and an idle speed-time ratio.
After the preset characteristic parameter combination and the vehicle working condition recognition model are determined, the driving working condition can be recognized based on the vehicle driving data collected in real time. The future driving trend can be predicted by extracting the vehicle speed change rule of a past period of time in real time.
The method comprises the steps of firstly selecting various candidate characteristic parameter combinations from historical driving data of a vehicle, carrying out cluster analysis on the historical driving data according to each candidate characteristic parameter combination to obtain a data set corresponding to the candidate characteristic parameter combinations, training and testing a pre-constructed neural network by adopting all or part of the data set, and finally selecting a preset characteristic parameter combination and a vehicle working condition recognition model for testing the data collected in real time, so that the driving working condition of the vehicle can be recognized more accurately. The preset characteristic parameter combinations screened out can more accurately contain road condition information of the vehicle in the driving process, and more characteristic parameter combinations are not required to be input into the vehicle working condition recognition model, so that the processing time of the vehicle working condition recognition model can be shortened, and the recognition accuracy of the working conditions can be improved.
After the preset characteristic parameter combination and the vehicle working condition recognition model are determined, the driving working condition of the vehicle can be recognized in real time.
Referring to fig. 3, it shows a flowchart of implementing the method for identifying the vehicle driving condition according to the embodiment of the present invention, which is detailed as follows:
and S310, acquiring running data of a preset characteristic parameter combination of the vehicle in the running process.
The vehicle may be a scooter, a truck, a bus, a taxi, a commercial vehicle, or a passenger vehicle, and the like, which is not limited herein.
The acquisition equipment can be a driving recorder, a vehicle data acquisition system and other equipment which can acquire relevant driving data of the vehicle in the driving process in real time.
And acquiring running data of the preset characteristic parameter combination in the running process of the vehicle according to the preset characteristic parameter combination determined in the determination method of the preset characteristic parameter combination and the vehicle working condition recognition model.
Illustratively, the preset characteristic parameter is a combination of an average speed, an average absolute value of acceleration, a uniform speed-time ratio and an idle speed-time ratio. The running data of the average speed, the average value of the absolute values of the acceleration, the uniform speed time ratio and the idle speed time ratio of the vehicle in the running process can be collected.
And step S320, inputting the running data combined by the preset characteristic parameters into the trained vehicle working condition recognition model to obtain the running working condition of the vehicle.
The vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination. The preset feature parameter combination is obtained by screening multiple candidate feature parameter combinations based on the test result of each candidate feature parameter combination. And the test result of each candidate characteristic parameter combination is a test result tested by using a corresponding candidate vehicle working condition recognition model, and each candidate vehicle working condition recognition model is obtained by training a training sample based on the candidate characteristic parameter combination.
And inputting the collected driving data of the preset characteristic parameter combination into a vehicle working condition recognition model, and taking the obtained result as the working condition type of a period of time in the future.
In some embodiments, in order to improve the recognition accuracy of the vehicle condition recognition model, the condition recognition type may be continuously updated through multiple recognition results, so as to further improve the recognition accuracy of the vehicle condition recognition model.
According to the invention, an optimal preset characteristic parameter combination capable of accurately representing the working condition is screened from multiple candidate characteristic parameter combinations, and a neural network obtained by training the optimal preset characteristic parameter combination is determined as a vehicle working condition recognition model. The driving data of the preset characteristic parameter combination is only input into the vehicle working condition recognition model, so that the processing time of the vehicle working condition recognition model can be shortened, the recognition accuracy of the working conditions can be improved, and the driving working conditions of the vehicle can be recognized more accurately. When the vehicle working condition is identified, the driving working condition of the vehicle can be obtained only by inputting the driving data of the preset characteristic parameter combination of the vehicle in the driving process into the vehicle working condition identification model.
The following describes the method for identifying the driving condition of the vehicle according to a specific embodiment of the present invention in detail:
and S410, acquiring vehicle historical driving data of drivers with different sexes, ages and driving ages on sections of commercial areas, residential areas, suburbs, urban and rural areas, expressways, main roads, expressways and the like.
And S420, performing GPS signal missing processing and moving average filtering processing on the collected historical vehicle driving data. The processed data is divided into a plurality of short working condition segments with the time period of 150 s.
S430, selecting 11 characteristic parameters of the running distance, the average speed, the average running speed, the highest vehicle speed, the speed standard deviation, the average value of the absolute value of the acceleration, the standard deviation of the absolute value of the acceleration, the acceleration time ratio, the deceleration time ratio, the idling time ratio and the uniform speed time ratio for describing the working condition.
And S440, processing the 11 characteristic parameters based on a principal component analysis method, selecting 6 characteristic parameters with the accumulated contribution rate higher than a preset threshold value, and reserving the 6 characteristic parameters, wherein the 6 characteristic parameters are the combination of average speed, maximum vehicle speed, average value of absolute values of acceleration, idle time ratio, constant speed time ratio and running distance. And 7 candidate characteristic parameter combinations consisting of the 6 characteristic parameters can be selected to continue processing the historical driving data of the vehicle. Wherein, the 7 candidate feature parameter combinations are respectively: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average value of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average, idle speed time ratio, uniform speed time ratio and running distance combination.
And S450, based on the 7 candidate characteristic parameter combinations, dividing the candidate characteristic parameter combinations into four working condition types through K-means clustering, wherein the four working condition types are a congestion working condition, an urban working condition, a suburb working condition and a high-speed working condition. 300 segments are randomly selected from each working condition of the 7 candidate characteristic parameter combinations respectively to serve as training samples, and each candidate characteristic parameter combination has 1200 segment samples.
S460, 280 segments are selected from 300 segments in each working condition in each candidate characteristic parameter combination to serve as training sets, and the other 20 segments are used as test sets. And respectively inputting the training sample of each candidate characteristic parameter combination into a pre-constructed probabilistic neural network, and training and testing the probabilistic neural network.
S470, comparing and analyzing the identification accuracy and the identification time of the 7 candidate characteristic parameter combinations in the probabilistic neural network to obtain the optimal characteristic parameter combination, namely, the preset characteristic parameter combination is the average speed, the average acceleration absolute value, the idle speed time ratio and the uniform speed time ratio. And the probabilistic neural network corresponding to the preset characteristic parameter combination is a vehicle working condition recognition model.
The average speed, the average acceleration absolute value, the idle speed time ratio and the uniform speed time ratio are used as preset characteristic parameter combinations, the four working conditions are 80 segments in total, and as shown in the test result of fig. 4, the test result input into the vehicle working condition identification model PNN is 100% identification. It should be noted that the vertical axis in fig. 4 represents 4 different operating mode types.
And S480, identifying the running data of the average speed, the average acceleration absolute value, the idling time ratio and the uniform speed time ratio of the vehicle, which are acquired in real time, by using the vehicle working condition identification model.
Specifically, as shown in fig. 5, Δ T is an identification period selected as 150s, and Δ P is a prediction time selected as 3s. In the identification 1, the working condition information of the average speed, the average acceleration absolute value, the idle speed time ratio and the uniform speed time ratio of the past delta T is identified through a trained vehicle working condition identification model, and the identification result is used as the working condition type of the future 3 seconds. For example, the data of the preset characteristic parameter combination of 1 s-150 s is input into the vehicle working condition recognition model for recognition, and the recognition result is taken as the type of 151 s-153 s. Then, the data of the preset feature parameter combinations in the range of 4s to 153s are input into the vehicle condition recognition model for recognition, the recognition result is regarded as the type of 154s to 156s, and the prediction information shown in fig. 6 is obtained through the following cycle recognition. The ordinate in fig. 6 is 4 operating mode types.
Four preset characteristic parameters of average speed, average acceleration absolute value, idle speed time ratio and uniform speed time ratio are used as input and input into a vehicle working condition recognition model which is trained by combining the 4 characteristic parameters, and driving data collected in real time are recognized and predicted, so that the method has high recognition precision and short running time.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not limit the implementation process of the embodiments of the present invention in any way.
Based on the method for identifying the vehicle running condition provided by the embodiment, correspondingly, the invention also provides a specific implementation mode of the device for identifying the vehicle running condition, which is applied to the method for identifying the vehicle running condition. Please see the examples below.
As shown in fig. 7, there is provided an apparatus 700 for recognizing a driving condition of a vehicle, the apparatus including:
the data acquisition module 710 is used for acquiring the driving data of a preset characteristic parameter combination in the driving process of the vehicle;
the working condition recognition module 720 is configured to input the driving data of the preset feature parameter combination into the trained vehicle working condition recognition model to obtain the driving working condition of the vehicle;
the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on a training sample of a preset characteristic parameter combination; presetting a feature parameter combination, and screening the feature parameter combination from multiple candidate feature parameter combinations based on the test result of each candidate feature parameter combination; and the test result of each candidate characteristic parameter combination is a test result tested by using a corresponding candidate vehicle working condition recognition model, and each candidate vehicle working condition recognition model is obtained by training a training sample based on the candidate characteristic parameter combination.
In one possible implementation manner, each candidate characteristic parameter combination comprises a plurality of characteristic parameters, and the plurality of characteristic parameters are obtained by performing characteristic extraction on historical driving data of the vehicle; the combination of the multiple candidate characteristic parameters is obtained by screening the multiple characteristic parameters based on a principal component analysis method and combining several characteristic parameters reserved after screening.
In a possible implementation manner, the training sample of each candidate characteristic parameter combination is a data set which is based on the candidate characteristic parameter combination and used for carrying out cluster analysis on historical driving data of the vehicle to obtain multiple preset working condition types of the candidate characteristic parameter combination; respectively selecting all or part of data from the data sets of each working condition type in the candidate characteristic parameter combination as training samples; wherein the type of operating condition comprises at least one of: congestion conditions, urban conditions, suburban conditions and high-speed conditions.
In a possible implementation manner, the historical driving data of the vehicle needs to be preprocessed before feature extraction, and the preprocessed driving data is divided into a plurality of short condition segments.
In one possible implementation mode, the preprocessing is to perform GPS signal missing processing on historical driving data of the vehicle and perform moving average filtering processing on the processed data; wherein the historical driving data of the vehicle comprises driving data of a plurality of different road sections and a plurality of different drivers.
In one possible implementation, the plurality of characteristic parameters includes at least one of: the system comprises a running distance, an average speed, an average running speed, a highest vehicle speed, a speed standard deviation, an acceleration absolute value average value, an acceleration absolute value standard deviation, an acceleration time ratio, a deceleration time ratio, an idle time ratio and a uniform speed time ratio; wherein, the average speed is the average value of speeds in a certain segment, and the average running speed is the average value of speeds in the segment, the speeds of which are more than 0;
the plurality of candidate feature parameter combinations include at least one of the following 7 candidate feature parameter combinations: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average value of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination.
In one possible implementation, the test result includes a recognition accuracy and/or a time taken for recognition;
the preset characteristic parameter combination is a combination of average speed, an average value of absolute values of acceleration, a uniform speed time ratio and an idle speed time ratio.
Fig. 8 is a schematic diagram of an electronic device of a vehicle according to an embodiment of the present invention. As shown in fig. 8, the electronic apparatus 8 of this embodiment includes: a processor 80, a memory 81 and a computer program 82 stored in said memory 81 and executable on said processor 80. The processor 80, when executing the computer program 82, implements the steps in the above-described embodiments of the method for identifying the driving condition of the vehicle, such as the steps 310 to 320 shown in fig. 3. Alternatively, the processor 80, when executing the computer program 82, implements the functions of the modules in the above-described device embodiments, such as the functions of the modules 710 to 720 shown in fig. 7.
Illustratively, the computer program 82 may be partitioned into one or more modules that are stored in the memory 81 and executed by the processor 80 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing certain functions that are used to describe the execution of the computer program 82 in the electronic device 8. For example, the computer program 82 may be divided into modules 710 to 720 shown in fig. 7.
The electronic device 8 may include, but is not limited to, a processor 80, a memory 81. Those skilled in the art will appreciate that fig. 8 is merely an example of an electronic device 8, and does not constitute a limitation of the electronic device 8, and may include more or fewer components than shown, or some of the components may be combined, or different components, e.g., the electronic device may also include input-output devices, network access devices, buses, etc.
The Processor 80 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 81 may be an internal storage unit of the electronic device 8, such as a hard disk or a memory of the electronic device 8. The memory 81 may also be an external storage device of the electronic device 8, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the electronic device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the electronic device 8. The memory 81 is used for storing the computer program and other programs and data required by the electronic device. The memory 81 may also be used to temporarily store data that has been output or is to be output.
The embodiment of the present application further provides a vehicle, and as shown in fig. 9, the vehicle 9 includes the foregoing electronic device 8.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. For the specific working processes of the units and modules in the system, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other ways. For example, the above-described apparatus/electronic device embodiments are merely illustrative, and for example, the division of the modules or units is only one type of logical function division, and other division manners may exist in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the method for identifying the driving condition of the vehicle may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
The above-mentioned embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method for identifying a driving condition of a vehicle is characterized by comprising the following steps:
acquiring running data of a preset characteristic parameter combination of a vehicle in a running process; the preset characteristic parameter combination is a combination of an average speed, an average value of absolute values of acceleration, a uniform speed time ratio and an idle speed time ratio;
inputting the driving data combined by the preset characteristic parameters into a trained vehicle working condition recognition model to obtain the driving working condition of the vehicle;
the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on the training sample of the preset characteristic parameter combination; the preset characteristic parameter combination is obtained by screening a plurality of candidate characteristic parameter combinations based on the test result of each candidate characteristic parameter combination; the test result of each candidate characteristic parameter combination is a test result tested by using a candidate vehicle working condition identification model corresponding to the candidate characteristic parameter combination, and each candidate vehicle working condition identification model is obtained by training a training sample based on the candidate characteristic parameter combination;
the plurality of candidate feature parameter combinations comprise at least one of the following 7 candidate feature parameter combinations: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average value of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average value of the absolute values of the acceleration, the constant speed time ratio and the running distance are combined; average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination.
2. The identification method according to claim 1, wherein each candidate feature parameter combination includes a plurality of feature parameters obtained based on feature extraction of historical travel data of the vehicle; the plurality of candidate characteristic parameter combinations are obtained by screening the plurality of characteristic parameters based on a principal component analysis method and combining several characteristic parameters reserved after screening.
3. The identification method according to claim 2, wherein the training sample of each candidate characteristic parameter combination is a data set which is obtained by performing cluster analysis on historical driving data of the vehicle based on the candidate characteristic parameter combination to obtain multiple preset working condition types of the candidate characteristic parameter combination; respectively selecting all or part of data from the data sets of each working condition type in the candidate characteristic parameter combination as training samples; wherein the type of operating condition comprises at least one of: congestion working conditions, urban working conditions, suburban working conditions and high-speed working conditions.
4. The identification method according to claim 2, characterized in that the historical travel data of the vehicle is further preprocessed before feature extraction, and the preprocessed travel data is divided into a plurality of short condition segments.
5. The identification method according to claim 4, wherein the preprocessing is to perform GPS signal missing processing on the historical travel data of the vehicle and perform moving average filtering processing on the processed data; wherein the historical travel data of the vehicle includes travel data for a plurality of different road segments and a plurality of different drivers.
6. An identification method as claimed in any one of claims 2 to 5, characterized in that said plurality of characteristic parameters comprises at least one of the following: the system comprises a running distance, an average speed, an average running speed, a highest vehicle speed, a speed standard deviation, an acceleration absolute value average value, an acceleration absolute value standard deviation, an acceleration time ratio, a deceleration time ratio, an idle time ratio and a uniform speed time ratio; the average speed is the average speed in a certain segment, and the average running speed is the average speed of speeds greater than 0 in the segment.
7. An identification method as claimed in any one of claims 1 to 5, characterized in that the test results comprise the identification accuracy and/or the time taken for identification.
8. An apparatus for identifying a driving condition of a vehicle, comprising:
the data acquisition module is used for acquiring running data of a preset characteristic parameter combination in the running process of the vehicle; the preset characteristic parameter combination is a combination of an average speed, an average value of absolute values of acceleration, a uniform speed time ratio and an idle speed time ratio;
the working condition recognition module is used for inputting the driving data of the preset characteristic parameter combination into a trained vehicle working condition recognition model so as to obtain the driving working condition of the vehicle;
the vehicle working condition recognition model is obtained by training a pre-constructed neural network based on the training sample of the preset characteristic parameter combination; the preset characteristic parameter combination is obtained by screening a plurality of candidate characteristic parameter combinations based on the test result of each candidate characteristic parameter combination; the test result of each candidate characteristic parameter combination is a test result tested by using a candidate vehicle working condition recognition model corresponding to the test result, and each candidate vehicle working condition recognition model is obtained by training a training sample based on the candidate characteristic parameter combination;
the plurality of candidate feature parameter combinations comprise at least one of the following 7 candidate feature parameter combinations: average speed and absolute value average combination of acceleration; average speed and idle time ratio combinations; the average speed, the average of the absolute value of the acceleration and the idle time ratio are combined; the average speed, the uniform speed time ratio and the idle speed time ratio are combined; the average speed, the average value of the absolute value of the acceleration, the constant speed time ratio and the idle speed time ratio are combined; the average speed, the highest vehicle speed, the average absolute value of the acceleration, the constant speed time ratio and the driving distance are combined; average speed, maximum vehicle speed, acceleration absolute value average value, idle speed time ratio, uniform speed time ratio and running distance combination.
9. A vehicle comprising electronic equipment including a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method for identifying a driving condition of a vehicle according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method for identifying a driving situation of a vehicle according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194619.1A CN115271001B (en) | 2022-09-29 | 2022-09-29 | Vehicle driving condition identification method and device, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194619.1A CN115271001B (en) | 2022-09-29 | 2022-09-29 | Vehicle driving condition identification method and device, vehicle and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115271001A CN115271001A (en) | 2022-11-01 |
| CN115271001B true CN115271001B (en) | 2023-02-07 |
Family
ID=83757061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211194619.1A Active CN115271001B (en) | 2022-09-29 | 2022-09-29 | Vehicle driving condition identification method and device, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115271001B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008505A (en) * | 2019-11-18 | 2020-04-14 | 西华大学 | Urban ramp driving condition construction method and application |
| CN111999657A (en) * | 2020-10-29 | 2020-11-27 | 北京航空航天大学 | Method for evaluating driving mileage of lithium ion battery of electric vehicle in residual life |
| CN114771542A (en) * | 2022-06-17 | 2022-07-22 | 中汽研汽车检验中心（天津）有限公司 | Vehicle driving condition determining method, device and storage medium |
-
2022
- 2022-09-29 CN CN202211194619.1A patent/CN115271001B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008505A (en) * | 2019-11-18 | 2020-04-14 | 西华大学 | Urban ramp driving condition construction method and application |
| CN111999657A (en) * | 2020-10-29 | 2020-11-27 | 北京航空航天大学 | Method for evaluating driving mileage of lithium ion battery of electric vehicle in residual life |
| CN114771542A (en) * | 2022-06-17 | 2022-07-22 | 中汽研汽车检验中心（天津）有限公司 | Vehicle driving condition determining method, device and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 基于工况与驾驶风格识别的混合动力汽车能量管理策略研究;詹森;《中国博士学位论文全文数据库工程科技Ⅱ辑》;20170315;C035-17 * |
| 基于神经网络的行驶工况智能识别方法研究;罗婷;《拖拉机与农用运输车》;20210430;10-15页 * |
| 汽车行驶工况识别模型搭建的方法研究;余卓平;《汽车行驶工况识别模型搭建的方法研究》;20200225;39-42页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115271001A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112396093B (en) | Driving scene classification method, device and equipment and readable storage medium | |
| CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
| CN108229567B (en) | Driver identity recognition method and device | |
| CN111723854B (en) | Expressway traffic jam detection method, equipment and readable storage medium | |
| CN111144446B (en) | Driver identity recognition method and system based on space-time grid | |
| CN113297795A (en) | Method for constructing running condition of pure electric vehicle | |
| CN103345842A (en) | Road vehicle classification system and method | |
| CN110807552A (en) | Urban electric bus running condition construction method based on improved K-means | |
| CN111881243A (en) | Taxi track hotspot area analysis method and system | |
| CN117542195A (en) | Traffic running state identification method, device, equipment and medium | |
| CN115271001B (en) | Vehicle driving condition identification method and device, vehicle and storage medium | |
| CN117400948A (en) | Automobile energy consumption prediction method and device, electronic equipment and storage medium | |
| CN115204755B (en) | Service area access rate measuring method and device, electronic equipment and readable storage medium | |
| Van Hinsbergh et al. | Vehicle point of interest detection using in-car data | |
| CN115083162B (en) | Road condition prediction method, device, equipment and storage medium | |
| CN113538735B (en) | Vehicle use identification method and device | |
| CN115691139A (en) | Big data road conditions prediction system of new energy automobile | |
| CN115718886A (en) | Construction method and device for pure electric vehicle running condition | |
| CN112200052B (en) | Track deviation recognition and vehicle running analysis method, device, equipment and medium | |
| CN110544378B (en) | Method for judging traffic jam condition of mobile phone user | |
| CN114485826A (en) | Method and device for determining mileage and oil consumption data of vehicle | |
| CN112927497A (en) | Floating car identification method, related method and device | |
| Wen et al. | Analysis of vehicle driving styles at freeway merging areas using trajectory data | |
| CN117894192B (en) | Road section vehicle average passenger carrying number estimation method based on mobile phone signaling data | |
| CN117985026A (en) | Driving style analysis method and device and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |