Driving control method and device of hybrid electric vehicle and hybrid electric vehicle

Abstract

The invention provides a driving control method and device of a hybrid electric vehicle and the hybrid electric vehicle. The method comprises the steps that vehicle driving intelligent control is started based on user verification information and a vehicle SOC value; window following prediction is conducted on the vehicle speed start-stop information through a continuous prediction window, and the driving speed following degree of vehicle running is determined based on a window following prediction result and the vehicle speed start-stop information; abnormal driving characteristic recording is carried out based on the driving torque data and the vehicle speed starting and stopping information, and abnormal driving characteristics of the hybrid electric vehicle are obtained; according to the method, the vehicle driving comfort is scored based on the driving speed following degree and the abnormal driving characteristics, flexible driving control is conducted on the hybrid electric vehicle according to the driving speed following degree, flexible driving control can be conducted on the vehicle according to the driving speed following degree in the vehicle running process, and the driving comfort of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of hybrid vehicle drive, and more specifically, to a drive control method, device, and hybrid vehicle for a hybrid vehicle. Background Art

[0002] Hybrid technology is a revolutionary upgrade and combination of pure fuel and pure electric power systems. Although the power of traditional internal combustion engines has been quite mature after years of development, there are still certain limitations in terms of fuel efficiency and environmental friendliness. Pure electric vehicles still have certain deficiencies in terms of endurance and usage convenience due to battery technology limitations. Hybrid technology can combine electric motors and internal combustion engines to make up for the deficiencies of pure fuel or pure electric systems.

[0003] When a hybrid vehicle is in a relatively harsh driving environment, the driver and passengers are subject to frequent vehicle speed start-stop processes. The rapid change of vehicle acceleration can cause the driver and passengers to feel carsick, resulting in typical carsickness manifestations such as dizziness, nausea, cold sweats, and even vomiting, which reduces the comfort of vehicle occupants. Therefore, how to improve the comfort of hybrid vehicles during riding through vehicle drive control has become an urgent problem to be solved. Summary of the Invention

[0004] The present application provides a drive control method, device, and hybrid vehicle for a hybrid vehicle, which can perform flexible drive control on the vehicle according to the drive speed following degree during vehicle driving, thereby improving the comfort of vehicle occupants.

[0005] In a first aspect, the present application provides a drive control method for a hybrid vehicle. This method can be executed by a network device, or alternatively, by a chip configured in the network device. The present application does not limit this.

[0006] Specifically, the method includes:

[0007] Obtain the user verification information and vehicle SOC value of the hybrid vehicle, and start vehicle drive intelligent control based on the user verification information and the vehicle SOC value;

[0008] Obtain the vehicle speed start-stop information of the hybrid vehicle, perform window following prediction on the vehicle speed start-stop information using a continuous prediction window, and determine the drive speed following degree of vehicle driving based on the window following prediction result and the vehicle speed start-stop information;

[0009] Obtain the drive torque data of the drive shaft of the hybrid vehicle, record abnormal drive characteristics based on the drive torque data and the vehicle speed start-stop information, and obtain the abnormal drive characteristics of the hybrid vehicle;

[0010] Based on the driving speed following degree and the abnormal driving characteristics, a vehicle driving comfort score is calculated. When the vehicle driving comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters the flexible driving mode, and the hybrid vehicle is flexibly driven according to the driving speed following degree.

[0011] Combined with the first aspect, in some implementation manners of the first aspect, starting the vehicle driving intelligent control based on the user verification information and the vehicle SOC value specifically includes: when the user verification information is successfully verified and the SOC value of the vehicle is higher than the preset power threshold, starting the vehicle driving intelligent control.

[0012] Combined with the first aspect, in some implementation manners of the first aspect, when the vehicle driving comfort score is higher than the comfort score threshold, it is determined that the hybrid vehicle enters the power driving mode. In the power driving mode, when the hybrid vehicle battery SOC > 30%, the working mode of preferentially driving by the vehicle motor is adopted; when the hybrid vehicle battery SOC < 30%, the working mode of preferentially driving by the vehicle engine is adopted.

[0013] Combined with the first aspect, in some implementation manners of the first aspect, determining the driving speed following degree of vehicle driving based on the window following prediction result and the vehicle speed start-stop information specifically includes:

[0014] Obtain the acceleration prediction values at the endpoints of different windows in the window following prediction result;

[0015] Based on the acceleration prediction values at the endpoints of different windows, perform time series fitting to obtain acceleration prediction information, and perform following degree detection based on the acceleration prediction information and the acceleration information of the vehicle speed start-stop information to obtain the driving speed following degree of vehicle driving.

[0016] Combined with the first aspect, in some implementation manners of the first aspect, recording the abnormal driving characteristics based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle specifically includes:

[0017] Obtain the driving torque data, and perform acceleration prediction from the driving torque data to obtain predicted start-stop information;

[0018] Based on the predicted start-stop information and the vehicle speed start-stop information, perform driving correlation detection to obtain a dynamic driving correlation index;

[0019] Obtain the feature recording period, respectively obtain the periodic signals of the predicted start-stop information and the vehicle speed start-stop information through the feature recording period, and construct a driving feature matrix according to the periodic signals of the predicted start-stop information and the vehicle speed start-stop information;

[0020] Extract abnormal features from the drive feature matrix according to the dynamic drive correlation index to obtain the abnormal drive features of the hybrid vehicle.

[0021] Combined with the first aspect, in some implementation manners of the first aspect, during the process of performing window following prediction on the vehicle speed start-stop information by using a continuous prediction window, window following prediction is performed through an autoregressive moving average model.

[0022] In a second aspect, the present application provides a drive control device for a hybrid vehicle, which includes a drive control unit, and the drive control unit includes:

[0023] A verification module, configured to obtain user verification information of the hybrid vehicle and the vehicle SOC value, and start intelligent vehicle drive control based on the user verification information and the vehicle SOC value;

[0024] An automotive data detection module, configured to obtain the vehicle speed start-stop information of the hybrid vehicle, perform window following prediction on the vehicle speed start-stop information by using a continuous prediction window, and determine the drive speed following degree of vehicle travel based on the window following prediction result and the vehicle speed start-stop information;

[0025] The automotive data detection module is further configured to obtain the drive torque data of the drive shaft of the hybrid vehicle, record abnormal drive features based on the drive torque data and the vehicle speed start-stop information, and obtain the abnormal drive features of the hybrid vehicle;

[0026] A drive mode decision module, configured to perform a vehicle drive comfort score based on the drive speed following degree and the abnormal drive features. When the vehicle drive comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters a flexible drive mode, and flexible drive control is performed on the hybrid vehicle according to the drive speed following degree.

[0027] In a third aspect, the present application provides a hybrid vehicle, and the hybrid vehicle includes the drive control device for a hybrid vehicle as described above to execute the drive control method for a hybrid vehicle as described above.

[0028] In a fourth aspect, the present application provides a computer terminal device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the drive control method for a hybrid vehicle as described above.

[0029] Fourthly, the present application provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the operations performed by the above-mentioned driving control method for a hybrid vehicle.

[0030] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0031] In a driving control method, device and hybrid vehicle provided by the present application, first, user verification information and the vehicle SOC value of the hybrid vehicle are obtained, and vehicle driving intelligent control is started based on the user verification information and the vehicle SOC value; the vehicle speed start-stop information of the hybrid vehicle is obtained, and window following prediction is performed on the vehicle speed start-stop information using a continuous prediction window, and the driving speed follow degree of vehicle driving is determined based on the window following prediction result and the vehicle speed start-stop information; the driving torque data of the drive shaft of the hybrid vehicle is obtained, and abnormal driving characteristics are recorded based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle; a vehicle driving comfort score is calculated based on the driving speed follow degree and the abnormal driving characteristics. When the vehicle driving comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters the flexible driving mode, and flexible driving control is performed on the hybrid vehicle according to the driving speed follow degree, which can perform flexible driving control on the vehicle according to the driving speed follow degree during vehicle driving and improve the comfort of vehicle drivers and passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is an exemplary flowchart of a driving control method for a hybrid vehicle according to some embodiments of the present application;

[0033] Figure 2 is a schematic structural diagram of a drive control unit according to some embodiments of the present application;

[0034] Figure 3 is a schematic structural diagram of a computer terminal device for implementing a driving control method for a hybrid vehicle according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] This application starts the intelligent control of vehicle driving by obtaining the user verification information and vehicle SOC value of a hybrid vehicle; obtains the vehicle speed start-stop information of the hybrid vehicle, uses a continuous prediction window to perform window following prediction on the vehicle speed start-stop information, and determines the driving speed following degree of vehicle driving based on the window following prediction result and the vehicle speed start-stop information; obtains the driving torque data of the drive shaft of the hybrid vehicle, records abnormal driving characteristics based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle; performs a vehicle driving comfort score based on the driving speed following degree and the abnormal driving characteristics. When the vehicle driving comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters the flexible driving mode, and flexible driving control is performed on the hybrid vehicle according to the driving speed following degree, which can perform flexible driving control on the vehicle according to the driving speed following degree during vehicle driving and improve the comfort of vehicle drivers and passengers.

[0036] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the specification drawings and specific embodiments. Refer to Figure 1 , which is an exemplary flowchart of a driving control method for a hybrid vehicle shown according to some embodiments of the present application. The driving control method 100 for the hybrid vehicle mainly includes the following steps:

[0037] In step S101, obtain the user verification information and vehicle SOC value of the hybrid vehicle, and start the intelligent control of vehicle driving based on the user verification information and the vehicle SOC value.

[0038] It should be noted that the user verification information in this application can be implemented through methods such as car key authentication, vehicle networking App authorization, face recognition / fingerprint, and driver behavior recognition. This application does not limit this. The user verification information is used to start the intelligent control of vehicle driving. For example, the hybrid vehicle can be controlled to start the intelligent control of vehicle driving through the driver's seat verification switch or driver gesture recognition.

[0039] Preferably, in some embodiments, starting the intelligent control of vehicle driving based on the user verification information and the vehicle SOC value specifically includes: when the user verification information is successfully verified and the SOC value of the vehicle is higher than the preset power threshold, start the intelligent control of vehicle driving.

[0040] In step S102, obtain the vehicle speed start-stop information of the hybrid vehicle, use a continuous prediction window to perform window following prediction on the vehicle speed start-stop information, and determine the driving speed following degree of vehicle driving based on the window following prediction result and the vehicle speed start-stop information.

[0041] Optionally, in some embodiments, obtaining the vehicle speed start-stop information of the hybrid vehicle specifically includes: obtaining the speed information of the hybrid vehicle through the vehicle sensor system, and extracting the acceleration sequence of the vehicle based on the speed information of the hybrid vehicle as the vehicle speed start-stop information of the hybrid vehicle. Specifically, when implemented, the acceleration sequence of the hybrid vehicle can be obtained by performing forward difference on the speed information of the hybrid vehicle.

[0042] Optionally, in some embodiments, during the process of performing window following prediction on the vehicle speed start-stop information using a continuous prediction window, window following prediction is performed through an autoregressive moving average model.

[0043] The following gives a preferred embodiment of performing window following prediction in the present application: First, preset the prediction window length to 5s. At this time, the vehicle speed start-stop information (acceleration sequence values) of the vehicle in the past 5s can be recorded respectively to obtain a historical acceleration sequence. In some other embodiments, the prediction window length can also be preset to other time lengths; furthermore, a time series graph of this acceleration sequence can be plotted, and the abscissa of the time series graph corresponds to different moments. Furthermore, the time series graph of the acceleration sequence set can be exponentially transformed to eliminate the trend of variance changing with time in the time series graph.

[0044] Secondly, according to the time series graph of the acceleration sequence, plot the autocorrelation coefficient graph of the acceleration value, where the horizontal axis of the autocorrelation coefficient graph is the number of lags, and the vertical axis is the value of the autocorrelation coefficient. Plot the partial autocorrelation coefficient graph of the acceleration value, where the horizontal axis of the partial autocorrelation coefficient graph is the number of lags, and the vertical axis is the value of the partial autocorrelation coefficient.

[0045] According to the characteristics of the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, the order of the model and the value range of the coefficients can be initially determined. For example, the autocorrelation coefficient graph can be plotted to observe whether the autocorrelation coefficient shows a truncated feature after a certain order. If the autocorrelation coefficient drops sharply and remains near 0 after a certain order, the order of the autoregressive model can be initially determined; plot the partial autocorrelation coefficient graph to observe whether the partial autocorrelation coefficient shows a truncated feature after a certain order. If the partial autocorrelation coefficient drops sharply and remains near 0 after a certain order, the order of the moving average model can be initially determined.

[0046] In specific implementation, the last significant autocorrelation coefficient can be found according to the autocorrelation coefficient graph first, which is the order of the autoregressive model. For example, if the last significant autocorrelation coefficient in the autocorrelation coefficient graph is at the 3rd order, the order of the autoregressive model is 3. Then, according to the partial autocorrelation coefficient graph, the last significant partial autocorrelation coefficient can be found, which is the order of the moving average model. For example, if the last significant partial autocorrelation coefficient in the partial autocorrelation coefficient graph is at the 2nd order, the order of the moving average model is 2. Finally, according to the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, the order (p,q) of the autoregressive moving average model is determined. For example, if both the autocorrelation coefficient graph and the partial autocorrelation coefficient graph decay to zero after the 3rd order, the order of the autoregressive moving average model is (3,3). Then, according to the order of the autoregressive moving average model, appropriate parameters are selected to establish the autoregressive moving average model of the acceleration sequence. By substituting the acceleration sequence into the autoregressive moving average model, the subsequent acceleration values can be predicted. Among them, the acceleration value at the end of the next prediction window length is used as the window acceleration prediction value.

[0047] The autoregressive moving average model is the change function of the acceleration value in the past prediction window length. By substituting the acceleration sequence into the autoregressive moving average model, the subsequent acceleration values can be predicted. Among them, in some embodiments, the acceleration value at the end of the next prediction window length is used as the acceleration prediction value. Then, by sliding the prediction window, the acceleration prediction values at different window endpoints are obtained, and the acceleration prediction values at different window endpoints are combined into the window following prediction result according to the time sequence.

[0048] Optionally, in some embodiments, determining the driving speed following degree of vehicle driving based on the window following prediction result and the vehicle speed start-stop information specifically includes:

[0049] Obtain the acceleration prediction values at different window endpoints in the window following prediction result;

[0050] Perform time series fitting based on the acceleration prediction values at different window endpoints to obtain acceleration prediction information, and perform following degree detection based on the acceleration prediction information and the acceleration information of the vehicle speed start-stop information to obtain the driving speed following degree of vehicle driving.

[0051] Optionally, in some embodiments, in the process of performing time series fitting based on the acceleration prediction values at different window endpoints to obtain acceleration prediction information, the Lagrange interpolation method can be used to perform polynomial interpolation on the acceleration prediction values at different window endpoints to obtain the acceleration fitting curve as the acceleration prediction information.

[0052] Preferably, in some embodiments, the following steps are specifically included to obtain the driving speed following degree based on the acceleration information of the acceleration prediction information and the vehicle speed start-stop information:

[0053] Obtain the acceleration prediction information and the vehicle speed start-stop information, and perform following detection according to a preset following threshold to obtain a plurality of following conflict intervals;

[0054] For any one of the following conflict intervals, obtain the difference component between the acceleration prediction information and the vehicle speed start-stop information in the following conflict interval as the following conflict weight of this following conflict interval, and perform weighted fusion on each following conflict interval according to the following conflict weights of each following conflict interval to determine the driving speed following degree.

[0055] Specifically, the integral of the deviation signal between the acceleration prediction information and the vehicle speed start-stop information within this following conflict interval can be used as the following conflict weight of this following conflict interval, and weighted fusion is performed on the interval lengths of each following conflict interval based on the following conflict weight to obtain a driving following conflict amount, and then the ratio between the standard driving following conflict amount and the driving following conflict amount is used as the driving speed following degree.

[0056] Specifically, the following detection period can be preset to 10 minutes, the following threshold is preset as a constant according to the average vehicle speed within the following detection period, and the larger the average vehicle speed of the vehicle is, the larger the calibration value of the following threshold is. In an ideal driving road environment, the integral of the deviation signal between the acceleration prediction information obtained by performing driving speed following detection using a hybrid vehicle and the initial acceleration information within the following detection period can be used as the standard driving following conflict amount.

[0057] It should be noted that the "sensory-motor conflict hypothesis" proposed by Charles Oman, a scholar at the Massachusetts Institute of Technology in 1990, states that motion sickness (car sickness) mainly stems from the conflict between the brain's anticipation of body movement and the actual sensory input. That is, when the human body moves, the brain subtracts the actual sensory input from the expected neural activity pattern, and what remains is the "sensory-motor conflict signal". The sensory-motor conflict signal causes dizziness when observing the external environment. A strong proof is that during daily self-controlled movements (such as walking and cycling), the brain actively sends movement instructions to various parts of the body and predicts the resulting visual, vestibular, and balance sensations based on past experience or neural patterns. The prediction and the actual sensation match highly, so the human body usually does not feel discomfort when walking or cycling. However, when controlling the drive of a hybrid vehicle, the body does not actively send movement instructions, but the body senses the changing acceleration signal. Therefore, when the driving environment is harsh (such as congestion and bumpiness) and the vehicle needs to start and stop frequently, it is more likely to cause motion sickness symptoms in the driver and passengers.

[0058] This application adopts the method of window following prediction, and makes a following prediction for the next moment based on the acceleration change in the past short time period, which to a certain extent conforms to the regular change expected by the human brain during vehicle driving. Then, the driving speed following degree is determined through the deviation between the predicted acceleration and the actual acceleration, so as to be able to quantify the deviation (sensory-motor conflict signal) between the actual sensation of the passengers in the vehicle and the brain's expectation to a limited extent. Based on the driving speed following degree, the hybrid vehicle is controlled for flexible driving control, which can reduce the dizziness sensation of the passengers in the vehicle and improve the comfort of riding a hybrid vehicle.

[0059] In step S103, the drive torque data of the drive shaft of the hybrid vehicle is obtained, and based on the drive torque data and the vehicle speed start-stop information, abnormal drive characteristics are recorded to obtain the abnormal drive characteristics of the hybrid vehicle.

[0060] Optionally, in some embodiments, the drive torque can be collected at equal intervals by the torque sensor on the upper drive shaft of the hybrid vehicle to obtain the hybrid drive torque data. Specifically, when implementing, a strain gauge or magnetostrictive sensor can be used to collect the drive torque at equal intervals. This application does not make any limitations in this regard.

[0061] It should be noted that the abnormal driving feature is the eigenvalue of the distribution matrix for reflecting the abnormal driving conditions where the torque output of the vehicle does not match the speed state. For example, when the vehicle speed remains unchanged but there is a sudden large torque, or the motor is still driving forward under deceleration, it may indicate the presence of large potholes or steep slopes on the road surface. Abnormal driving will also cause discomfort for the driver and passengers. Especially in urban congested or bumpy road conditions, the abnormal driving control of the vehicle is likely to cause large acceleration changes, thus increasing the possibility of passengers getting dizzy. By scoring the driving comfort of the vehicle according to the abnormal driving conditions of the vehicle, the accuracy of the driving comfort score result of the vehicle can be improved.

[0062] Optionally, in some embodiments, recording the abnormal driving feature based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving feature of the hybrid vehicle specifically includes:

[0063] Obtain the driving torque data, and perform acceleration prediction from the driving torque data to obtain predicted start-stop information;

[0064] Perform driving correlation detection based on the predicted start-stop information and the vehicle speed start-stop information to obtain a dynamic driving correlation index;

[0065] Obtain a feature recording period, respectively obtain the periodic signals of the predicted start-stop information and the vehicle speed start-stop information through the feature recording period, and construct a driving feature matrix according to the periodic signals of the predicted start-stop information and the vehicle speed start-stop information;

[0066] Extract abnormal features from the driving feature matrix according to the dynamic driving correlation index to obtain the abnormal driving feature of the hybrid vehicle.

[0067] Optionally, in some embodiments, in the process of performing acceleration prediction from the driving torque data to obtain predicted start-stop information, the standard driving torque data and acceleration data obtained through testing in an ideal driving environment can be used as training samples to train a support vector regression model. By inputting the standard driving torque data into the support vector regression model for acceleration prediction, comparing the predicted acceleration data output by the support vector regression model with the actual acceleration sample data, and adjusting the model parameters in the support vector regression model according to the comparison result until the deviation between the predicted acceleration data output by the support vector regression model and the actual acceleration sample data is less than a preset deviation threshold, it is determined that the support vector regression model training is completed. Then, input the driving torque data into the trained support vector regression model, and the support vector regression model divides the driving torque data into each torque sliding window and performs acceleration prediction respectively to obtain the acceleration prediction values at different time series to form the predicted start-stop information.

[0068] It should be noted that the dynamic drive correlation index reflects the degree of correlation between the trend change of the torque of the drive shaft of the vehicle and the trend change of the vehicle acceleration in the vehicle start-stop information. Extracting abnormal drive characteristics of the hybrid vehicle based on the dynamic drive correlation index can dynamically increase the feature storage amount of abnormal drive characteristics and improve the accuracy of vehicle drive comfort score learning when the degree of correlation between the trend change of the torque of the drive shaft of the vehicle and the trend change of the vehicle acceleration in the vehicle start-stop information is low. Optionally, in some embodiments, performing drive correlation detection based on the predicted start-stop information and the vehicle speed start-stop information to obtain the dynamic drive correlation index specifically includes:

[0069] Obtain the predicted start-stop information and the vehicle speed start-stop information, and respectively extract a plurality of vehicle drive trends corresponding to the predicted start-stop information and the vehicle speed start-stop information;

[0070] Perform trend correlation feature extraction based on the plurality of vehicle drive trends corresponding to the predicted start-stop information and the vehicle speed start-stop information, and determine the dynamic drive correlation index based on the mean value of the trend correlation features.

[0071] In specific implementation, the predicted start-stop information and the vehicle speed start-stop information can be divided into a plurality of trend extraction windows, and then the empirical mode decomposition is used to decompose the predicted start-stop information and the vehicle speed start-stop information in the plurality of trend extraction windows into corresponding intrinsic mode functions as vehicle drive trends. The Pearson correlation coefficient is extracted according to the vehicle drive trends corresponding to the predicted start-stop information and the vehicle speed start-stop information in the same time series window, and the mean value of the Pearson correlation coefficients corresponding to each vehicle drive trend is used as the dynamic drive correlation index.

[0072] Optionally, in some embodiments, the Pearson correlation coefficient between the predicted start-stop information and the vehicle speed start-stop information can also be used as the dynamic drive correlation index.

[0073] Optionally, in some embodiments, respectively obtain the periodic signals of the predicted start-stop information and the vehicle speed start-stop information through the feature recording period, and constructing a drive feature matrix according to the periodic signals of the predicted start-stop information and the vehicle speed start-stop information specifically includes: windowing the acceleration predicted value and the actual acceleration value in the predicted start-stop information and the vehicle speed start-stop information respectively through the feature recording period, and using the difference between the acceleration predicted value and the actual acceleration value in each feature recording period window as a matrix row vector respectively to obtain the drive feature matrix.

[0074] Preferably, in some embodiments, performing abnormal feature extraction on the drive feature matrix according to the dynamic drive correlation index to obtain the abnormal drive characteristics of the hybrid vehicle specifically includes:

[0075] Perform threshold mapping according to the dynamic drive correlation index to determine the abnormal drive feature length;

[0076] Perform singular value decomposition on the drive feature matrix to obtain multiple abnormal drive feature values. Select the abnormal drive feature values based on the abnormal drive feature length to form a feature vector as the abnormal drive feature.

[0077] It should be noted that the abnormal drive feature length represents the vector length of the feature vector formed by selecting the abnormal drive feature values. That is, after performing singular value decomposition on the drive feature matrix to obtain the eigenvalue of the matrix as the abnormal drive feature value, the first n abnormal drive feature values are selected to form a feature vector as the abnormal drive feature, where n is the abnormal drive feature length. The process of obtaining the abnormal drive feature length by performing threshold mapping according to the dynamic drive correlation index can map the threshold interval where the dynamic drive correlation index is located according to a preset mapping table to obtain the corresponding abnormal drive feature length.

[0078] In step S104, perform a vehicle drive comfort score based on the drive speed followability and the abnormal drive feature. When the vehicle drive comfort score is lower than the comfort score threshold, determine that the hybrid vehicle enters the flexible drive mode, and perform flexible drive control on the hybrid vehicle according to the drive speed followability.

[0079] It should be noted that the vehicle drive comfort score in this application is used to determine the driver and passenger comfort of the vehicle in the current driving state. The vehicle drive comfort is determined by feature learning based on the drive speed followability and the abnormal drive feature during the vehicle driving process. Optionally, in some embodiments, the process of performing a vehicle drive comfort score based on the drive speed followability and the abnormal drive feature can be implemented using a single-hidden layer neural network.

[0080] In specific implementation, during the process of evaluating the vehicle driving comfort based on the driving speed following degree and the abnormal driving characteristics, a single-hidden-layer neural network can be used to perform dual-channel clustering modeling on the driving control characteristics. Among them, the driving speed following degree and the abnormal driving characteristics are respectively input into the single-hidden-layer neural network through a data channel. The hidden layer of the single-hidden-layer neural network contains multiple activation function nodes, which are used to perform clustering training on the input feature data and respectively output the classification results of the two channels. The first clustering channel is used to characterize the speed following stability, and the second clustering channel is used to characterize the driving abnormal perturbation level. The two clustering results respectively correspond to the first score and the second score. The single-hidden-layer neural network is trained using a pre-constructed training sample set and the corresponding artificial comfort score labels. When the fitting degree between the clustering result of the training sample set and the artificial score is lower than a preset threshold, the activation parameters of the activation function in the hidden layer are dynamically adjusted until the correlation between the clustering output and the artificial score meets the preset standard threshold. Finally, based on the score weights corresponding to the first score and the second score, weighted fusion is performed to output the driving comfort score result of the target vehicle under the current control strategy, where the score weights corresponding to the first score and the second score are calibrated as constants based on experience.

[0081] Optionally, in some embodiments, the comfort score threshold is determined based on the vehicle driving comfort score corresponding to the ideal driving environment. In specific implementation, the vehicle start-stop control can be performed in the ideal driving environment, and the driving speed following degree and the abnormal driving characteristics can be obtained to evaluate the vehicle driving comfort, and the obtained score result is used as the comfort score threshold. This application will not elaborate on this.

[0082] Preferably, in some embodiments, when the vehicle driving comfort score is higher than the comfort score threshold, it is determined that the hybrid vehicle enters the power driving mode. In the power driving mode, when the battery SOC of the hybrid vehicle > 30%, the working mode of preferentially driving by the vehicle motor is adopted. When the battery SOC of the hybrid vehicle < 30%, the working mode of preferentially driving by the vehicle engine is adopted.

[0083] It should be noted that the driving speed tracking ability represents the tracking ability between the actual speed of the vehicle and the predicted / desired speed. The greater the tracking ability, the more stable the current vehicle running state and the more accurate the response of the power system. Therefore, the driving speed tracking ability can be used as the key regulation basis for flexible driving control to achieve smoother acceleration response, improve passenger comfort, and reduce the risk of motion sickness. Among them, in some embodiments, the specific steps of performing flexible driving control on the hybrid vehicle according to the driving speed tracking ability include: by obtaining the angular velocity and opening information of the accelerator pedal, judging the acceleration intention of the current driving behavior, and dynamically scaling and correcting the output torque command of the motor in combination with a preset intention classification strategy, so that the motor of the hybrid vehicle outputs a relatively smooth torque response, thereby optimizing the driving acceleration change curve, improving passenger riding comfort, and reducing the probability of passenger motion sickness.

[0084] Preferably, in some embodiments, the specific steps of performing flexible driving control on the hybrid vehicle according to the driving speed tracking ability include: using the real-time driving speed tracking ability as a feedback signal, and using the deviation signal between the real-time driving speed tracking ability and the desired driving speed tracking ability as an input signal, and dynamically scaling and correcting the output torque command of the motor according to the input signal. Specifically, when implementing, the deviation signal between the real-time driving speed tracking ability and the desired driving speed tracking ability can be used as a proportional adjustment signal to scale and correct the output torque change command of the motor. At the same time, the output torque change of the motor can also be controlled in a fuzzy manner according to the deviation signal between the real-time driving speed tracking ability and the desired driving speed tracking ability. Specifically, when the deviation signal between the real-time driving speed tracking ability and the desired driving speed tracking ability is large, the controller outputs a smaller torque change, so that the vehicle speed changes slowly, avoiding excessive acceleration or sudden stop. When the deviation gradually decreases, the controller outputs a larger torque change to quickly adjust the vehicle speed and respond quickly. Therefore, when the deviation signal between the real-time driving speed tracking ability and the desired driving speed tracking ability is large, by reducing the output torque change of the motor, the purpose of reducing the acceleration change during frequent start and stop is achieved, thereby improving the comfort of the driver and passengers in the vehicle.

[0085] In addition, on the other hand of the present application, in some embodiments, the present application provides a driving control device for a hybrid vehicle, which includes a driving control unit. Refer to Figure 2 , which is a schematic diagram of the exemplary hardware and / or software structure of the driving control unit according to some embodiments of the present application. The driving control unit 200 includes: a verification module 201, a vehicle data detection module 202, and a driving mode decision module 203, which are described as follows:

[0086] The verification module 201 is configured to obtain user verification information and the vehicle SOC value of a hybrid vehicle, and start intelligent vehicle drive control based on the user verification information and the vehicle SOC value;

[0087] The vehicle data detection module 202 is configured to obtain the vehicle speed start-stop information of the hybrid vehicle, perform window following prediction on the vehicle speed start-stop information by using a continuous prediction window, and determine the drive speed following degree of vehicle travel based on the window following prediction result and the vehicle speed start-stop information;

[0088] The vehicle data detection module 202 is further configured to obtain the drive torque data of the drive shaft of the hybrid vehicle, record abnormal drive characteristics based on the drive torque data and the vehicle speed start-stop information, and obtain the abnormal drive characteristics of the hybrid vehicle;

[0089] The drive mode decision module 203 is configured to perform a vehicle drive comfort score based on the drive speed following degree and the abnormal drive characteristics. When the vehicle drive comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters a flexible drive mode, and flexible drive control is performed on the hybrid vehicle according to the drive speed following degree.

[0090] The above has introduced in detail an example of a drive control method, device, and hybrid vehicle provided by an embodiment of the present application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function.

[0091] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in the manner of hardware or computer software driving hardware depends on the specific application and design constraint conditions of the technical solution. Therefore, those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0092] In addition, the present application further provides a computer terminal device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned drive control method for a hybrid vehicle.

[0093] In some embodiments, referring to Figure 3 This figure is a schematic structural diagram of a computer terminal device for implementing a drive control method for a hybrid vehicle according to some embodiments of the present application. The above-mentioned drive control method for a hybrid vehicle in the above embodiments can be passed throughFigure 3 It is implemented by the computer terminal device shown. The computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303, and a memory 304.

[0094] The processor 303 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of a drive control method for a hybrid vehicle in this application.

[0095] The communication bus 301 may include a path for transmitting information between the above components.

[0096] The memory 304 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 304 can exist independently and be connected to the processor 303 through the communication bus 301. The memory 304 can also be integrated with the processor 303.

[0097] Among them, the memory 304 is used to store the program code for executing the solution of this application and is controlled by the processor 303 for execution. The processor 303 is used to execute the program code stored in the memory 304. The program code may include one or more software modules. The determination of the driving speed following degree in the above embodiments can be implemented by one or more software modules in the program code in the processor 303 and the memory 304.

[0098] A communication interface 302, using any device such as a transceiver, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0099] Optionally, the above computer terminal device 300 may further include a power supply 305 for supplying power to various components or circuits in the real-time computer terminal device.

[0100] In a specific implementation, as an embodiment, the computer terminal device may include multiple processors, and each of these processors may be a single-CPU processor or a multi-CPU processor. Here, the processor may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0101] The above computer terminal device may be a general-purpose computer terminal device or a special-purpose computer terminal device. In a specific implementation, the computer terminal device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer terminal device.

[0102] In addition, in other aspects of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned drive control method for a hybrid electric vehicle.

[0103] In summary, in a driving control method, device, and hybrid vehicle disclosed in an embodiment of the present application, first, user verification information and the vehicle's SOC value of the hybrid vehicle are obtained, and vehicle driving intelligent control is started based on the user verification information and the vehicle's SOC value; the vehicle speed start-stop information of the hybrid vehicle is obtained, the window following prediction is performed on the vehicle speed start-stop information by using a continuous prediction window, and the driving speed following degree of the vehicle during driving is determined based on the window following prediction result and the vehicle speed start-stop information; the driving torque data of the drive shaft of the hybrid vehicle is obtained, and abnormal driving characteristics are recorded based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle; the vehicle driving comfort score is calculated based on the driving speed following degree and the abnormal driving characteristics. When the vehicle driving comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters the flexible driving mode, and the hybrid vehicle is flexibly driven based on the driving speed following degree. It is possible to flexibly drive the vehicle according to the driving speed following degree during the vehicle driving process, improving the comfort of the vehicle driver and passengers.

[0104] The above are only embodiments of the present application, and specific technical solutions or common knowledge such as characteristics well known in the art are not described in detail here. It should be noted that for those skilled in the art, without departing from the technical solution of the present application, several modifications and improvements can still be made, which should also be regarded as the protection scope of the present application, and these will not affect the implementation effect of the present application and the practicality of the patent.

[0105] The protection scope required by the present application should be based on the content of its claims, and the specific implementation manners described in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A driving control method for a hybrid vehicle, characterized in that: include: Acquiring user authentication information and a vehicle SOC value of the hybrid vehicle, and starting vehicle driving intelligent control based on the user authentication information and the vehicle SOC value; Acquiring vehicle speed start-stop information of the hybrid vehicle, performing window following prediction on the vehicle speed start-stop information using a continuous prediction window, and determining a driving speed following degree of the vehicle based on the window following prediction result and the vehicle speed start-stop information; Acquiring driving torque data of a transmission shaft of the hybrid vehicle, recording abnormal driving characteristics based on the driving torque data and the vehicle speed start-stop information, and obtaining abnormal driving characteristics of the hybrid vehicle; A vehicle driving comfort score is scored based on the driving speed following degree and the abnormal driving characteristics. When the vehicle driving comfort score is lower than a comfort score threshold, it is determined that the hybrid vehicle enters a flexible driving mode, and flexible driving control is performed on the hybrid vehicle according to the driving speed following degree.

2. The method according to claim 1, characterized in that Starting the vehicle driving intelligent control based on the user verification information and the vehicle SOC value specifically includes: when the user verification information is successfully verified and the SOC value of the vehicle is higher than a preset power threshold, starting the vehicle driving intelligent control.

3. The method according to claim 1, characterized in that When the vehicle driving comfort score is higher than the comfort score threshold, it is determined that the hybrid vehicle enters the power drive mode. In the power drive mode, when the hybrid vehicle battery SOC>30%, the vehicle motor priority drive working mode is adopted; when the hybrid vehicle battery SOC<30%, the vehicle engine priority drive working mode is adopted.

4. The method according to claim 1, characterized in that Determining the driving speed following degree of the vehicle based on the window following prediction result and the vehicle speed start-stop information specifically includes: Obtaining acceleration prediction values ​​of different window endpoints in the window following prediction result; Based on the acceleration prediction values ​​at different window endpoints, time series fitting is performed to obtain acceleration prediction information, and based on the acceleration prediction information and the acceleration information of the vehicle speed start and stop information, a followability detection is performed to obtain the driving speed followability of the vehicle.

5. The method according to claim 1, characterized in that Recording abnormal driving characteristics based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle specifically includes: Acquiring the driving torque data, performing acceleration prediction based on the driving torque data, and obtaining predicted start-stop information; Performing a driving association detection based on the predicted start-stop information and the vehicle speed start-stop information to obtain a dynamic driving association index; Acquire a characteristic recording cycle, respectively acquire periodic signals of the predicted start-stop information and the vehicle speed start-stop information through the characteristic recording cycle, and construct a driving characteristic matrix according to the periodic signals of the predicted start-stop information and the vehicle speed start-stop information; Abnormal features are extracted from the driving feature matrix according to the dynamic driving association index to obtain abnormal driving features of the hybrid vehicle.

6. The method according to claim 1, characterized in that In the process of using a continuous prediction window to perform window following prediction on the vehicle speed start and stop information, a moving average autoregressive model is used to perform window following prediction.

7. A driving control device for a hybrid vehicle, comprising a driving control unit, characterized in that: The drive control unit comprises: A verification module, used to obtain user verification information and a vehicle SOC value of the hybrid vehicle, and start vehicle driving intelligent control based on the user verification information and the vehicle SOC value; A vehicle data detection module, used for acquiring vehicle speed start-stop information of the hybrid vehicle, performing window following prediction on the vehicle speed start-stop information using a continuous prediction window, and determining a driving speed following degree of the vehicle based on the window following prediction result and the vehicle speed start-stop information; The vehicle data detection module is further used to obtain the driving torque data of the transmission shaft of the hybrid vehicle, and to record the abnormal driving characteristics based on the driving torque data and the vehicle speed start-stop information to obtain the abnormal driving characteristics of the hybrid vehicle; The driving mode decision module is used to score the vehicle driving comfort based on the driving speed following degree and the abnormal driving characteristics, and when the vehicle driving comfort score is lower than the comfort score threshold, it is determined that the hybrid vehicle enters the flexible driving mode, and the hybrid vehicle is flexibly driven according to the driving speed following degree.

8. A hybrid vehicle, characterized in that: The hybrid vehicle includes a hybrid vehicle driving control device as claimed in claim 7.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute a hybrid vehicle driving control method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the driving control method of a hybrid vehicle as claimed in any one of claims 1 to 7.

Images