Active suspension control method and system based on rolling driving style recognition

Abstract

The invention provides an active suspension control method and system based on rolling driving style recognition, and the method comprises the steps: obtaining brake, accelerator pedal opening, steering wheel angle and vehicle speed information from a CAN bus, so as to construct a working condition information base; pedal opening information and steering wheel angle information are extracted and compared with a preset opening threshold value, and the current driving working condition is recognized; historical vehicle speed information is extracted, rolling cutting based on a time window is carried out on a historical vehicle speed track, and a vehicle speed time sequence is obtained; averaging and standard deviation extraction are carried out on the vehicle speed time sequence to extract statistical characteristics, EMD-DFT is applied to jointly extract time sequence characteristics, and a driving style is identified based on the two characteristics; and the driving working condition and the driving style serve as input to achieve active suspension control. Accurate recognition of the driving style is achieved, meanwhile, rolling recognition based on a time window is introduced, the real-time performance of suspension control is improved, and finally the comfort and operation stability of suspension control are improved in combination with human-vehicle factors.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to an active suspension control method and system based on rolling driving style recognition. Background Art

[0002] High-quality vehicle development is an urgent need at home and abroad, among which the driving comfort and handling stability of vehicles are receiving more and more attention. As an important component connecting the vehicle body and power system, the automobile suspension system directly affects the driver's driving experience comfort and the overall stability of the vehicle during control, and the latter is more related to the safety during driving.

[0003] Suspension control technology is mainly divided into two categories: semi-active suspension control and active suspension control. Semi-active suspension is passive control, which cannot effectively control the stiffness and damping of the suspension when the car starts, turns and brakes, but can automatically adjust the damping parameters according to the changes in vehicle vibration when the car is running; active suspension is active control, which can autonomously adjust the suspension stiffness and damping under various working conditions of the car. At present, regardless of which suspension control technology is used, most studies ignore the personal factors of the driver.

[0004] Patent document CN110901325B (application number: CN201911197599.1) discloses an active suspension control method and system, which relates to the field of vehicle suspension technology. This method observes the unevenness curve of the road ahead, presets the expected value of the vehicle body posture, and continuously compensates for the vehicle body posture during driving, thereby improving the vehicle ride comfort. This method introduces the unevenness curve of the road surface and combines the vehicle-environment information for suspension control, but does not take into account the different definitions and requirements of comfort for different drivers.

[0005] Patent document CN116176197B (application number: CN202111421716.5) discloses a semi-active suspension control method and device, a storage medium, and a vehicle. The method obtains the sprung speed and unsprung speed of the suspension spring, calculates the required damping, and finally uses a control circuit to achieve shock absorber control. This method only requires a small amount of input data to achieve suspension control optimization, and the cost is low. However, it also does not take into account the importance of the driver, and its control effect is limited. Summary of the invention

[0006] In view of the defects in the prior art, an object of the present invention is to provide an active suspension control method and system based on rolling driving style recognition.

[0007] An active suspension control method based on rolling driving style recognition provided by the present invention includes:

[0008] Step S1: Obtain brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and save historical data to build a vehicle operating condition information library;

[0009] Step S2: respectively comparing the current brake and accelerator pedal openings and steering wheel angles with preset corresponding thresholds to distinguish the longitudinal driving condition and the lateral driving condition of the current vehicle;

[0010] Step S3: extracting historical vehicle speed trajectories from the vehicle operating condition information database, and segmenting the historical vehicle speed trajectories based on a sliding time window to obtain a vehicle speed time series;

[0011] Step S4: performing average and variance operations on the vehicle speed time series to obtain statistical features; performing empirical mode decomposition (EMD) and discrete Fourier transform (DFT) joint operations on the vehicle speed time series to obtain time series features; and performing driving style recognition using a classification recognition model based on the statistical and time series features and in comparison with a driving style feature library;

[0012] Step S5: Using the driving condition and driving style as input, applying decision rules to implement active suspension control.

[0013] Preferably, the vehicle longitudinal driving conditions include acceleration, cruising and deceleration;

[0014] The lateral driving conditions include left turn, right turn and straight driving.

[0015] Preferably, step S2 comprises:

[0016] Step S2.1: Set the threshold value based on experience, and set the accelerator pedal opening threshold value to P thr，g , set the brake pedal opening threshold to P thr，b , set the steering wheel angle threshold to A thr，sw ;

[0017] Step S2.2: Extract the latest accelerator pedal opening P from the vehicle operating condition information database g , the latest brake pedal opening P b And the latest steering wheel angle A sw ;

[0018] Step S2.3: Adjust the accelerator pedal opening angle P g With threshold P thr，g Compare the size, brake pedal opening P b With threshold P thr，b Compare the size, P g Greater than P thr，g And P b Less than p thr，b Corresponding to the acceleration driving condition, P g Less than P thr，g And Pb Greater than P thr，b Corresponding to the deceleration driving condition, P g Less than P thr，g And P b Less than P thr，b Corresponding to the cruising driving condition, P g Greater than P thr，g And P b Greater than P thr，b The situation is a dangerous operation, and the situation is defined as a deceleration driving condition, and the safety system is introduced to take over;

[0019] Step S2.4: Turn the steering wheel to angle A sw With threshold A thr，sw Compare the size, A sw Less than -A thr，sw For left-turn driving conditions, A sw Greater than A thr，sw For right turn driving condition, A sw In the range (-A thr，sw , A thr，sw ) corresponds to the straight driving condition.

[0020] Preferably, the step S3 comprises:

[0021] Step S3.1: Set the sliding time window size to L;

[0022] Step S3.2: extract the historical vehicle speed trajectory from the vehicle operating condition information database, and reversely segment the vehicle speed trajectory, that is, retain the latest L vehicle speed data to form a vehicle speed time series, and update it with the vehicle speed information, so that the vehicle speed time series is supplemented with the latest frame of vehicle speed and the oldest frame of vehicle speed is removed, and the length of the vehicle speed time series is always kept the same as the length of the sliding time window L to achieve rolling segmentation.

[0023] Preferably, the empirical mode decomposition (EMD) and discrete Fourier transform (DFT) joint operation in step S4 includes:

[0024] Step S4.1: Perform EMD decomposition on the vehicle speed time series to obtain the intrinsic mode function IMF and residual Res, the formula is:

[0025]

[0026] Where X(t) represents the signal composed of vehicle speed time series, C i (t) is the i-th IMF, n represents the total number of n IMFs obtained after the vehicle speed time series is decomposed;

[0027] Step S4.2: Perform DFT transformation on each IMF to obtain the signal of IMF in the frequency domain. The formula is:

[0028] C i，f (w) = DFT(C i (t))

[0029] Where C i，f (w) is the frequency domain signal of the ith IMF after discrete Fourier transform;

[0030] Step S4.3: Calculate the frequency domain signal C i，f The position w of the maximum amplitude of (w) i，m , at this time C i，f (w i，m ) is the main frequency, find C i，f (w i，m ) value, and compare the main frequencies of n IMFs, extracting their maximum value as the timing feature. The formula is:

[0031] w i,m = argmax(abs(C i，f (w)))

[0032] f i =Freq(C i，f (w i,m ))

[0033]

[0034] In the formula, the function abs(·) obtains the modulus of the signal, and the function argmax(·) obtains the position w of the maximum modulus length. i，m , the function Freq(·) obtains the frequency of the signal, f i is the main frequency of the current signal, f i，m is the maximum main frequency of the vehicle speed time series.

[0035] Preferably, the driving style feature library includes definitions through artificial labels and is obtained by pre-collecting data of different drivers and performing unsupervised learning clustering algorithms.

[0036] Preferably, according to the speed trajectory of the driver during driving, the collected speed trajectory is averaged and variance calculated to obtain the statistical average speed V a and speed standard deviation V s ;

[0037] According to the EMD-IMF joint analysis method, the maximum main frequency f is obtained i，m ;

[0038] The obtained statistical average speed V a , speed standard deviation V s and the maximum main frequency f i，mAs input, K-means++ is used for clustering, and the original vehicle speed trajectories are labeled to build a driving style feature library.

[0039] Preferably, the classification and recognition model includes support vector machine SVM, random forest RF, artificial neural network ANN, and recurrent neural network RNN.

[0040] Preferably, the decision rule described in step S5 is that there are m driving conditions and n driving styles, which can be divided into m×n situations. According to the actual judgment of each situation, the active suspension gear is formulated to achieve suspension control.

[0041] An active suspension control system based on rolling driving style recognition provided by the present invention comprises:

[0042] Module M1: obtains brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and saves historical data to build a vehicle operating condition information library;

[0043] Module M2: compares the current brake and accelerator pedal openings and steering wheel angles with the preset corresponding thresholds to distinguish the longitudinal driving condition and the lateral driving condition of the current vehicle;

[0044] Module M3: extracting historical vehicle speed trajectories from the vehicle operating condition information database, segmenting the historical vehicle speed trajectories based on a sliding time window, and obtaining a vehicle speed time series;

[0045] Module M4: Perform average and variance operations on the vehicle speed time series to obtain statistical features; perform empirical mode decomposition (EMD) and discrete Fourier transform (DFT) on the vehicle speed time series to obtain time series features; and perform driving style recognition using a classification recognition model based on the statistical and time series features and the driving style feature library;

[0046] Module M5: Using driving conditions and driving style as input, it applies decision rules to achieve active suspension control.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention proposes a new method for extracting time series features. This method can obtain different intrinsic mode functions (IMFs) through empirical mode decomposition (EMD), remove low-frequency IMFs, and effectively alleviate clutter interference. In addition, the maximum main frequency in the IMF is extracted through discrete Fourier transform (DFT), and the time series features are extracted from the frequency domain, which can significantly improve the accuracy of subsequent driving style prediction.

[0049] 2. The present invention proposes a rolling identification method of driving style based on a sliding time window. This method continuously updates the vehicle speed time series through a sliding time window, thereby realizing continuous updating of driving style and effectively improving the real-time performance of suspension control.

[0050] 3. The present invention proposes an active suspension control method that combines human-vehicle factors. The method introduces the driver's personal factors and guides the control mode of the active suspension in combination with the current vehicle working conditions, which can significantly enhance the comfort and handling stability of the automobile suspension system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0052] Figure 1 A schematic diagram of an implementation flow of the method described in an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of a process of identifying a rolling driving style according to an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of the decision rule according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0056] The present invention obtains brake and accelerator pedal opening, steering wheel angle, and vehicle speed information from the CAN bus to construct a working condition information library; extracts pedal opening information and steering wheel angle information and compares them with a preset opening threshold to identify the current driving condition; extracts historical vehicle speed information, performs rolling cutting based on a time window on the historical vehicle speed trajectory to obtain a vehicle speed time series; applies averaging and standard deviation to extract statistical features from the vehicle speed time series, applies empirical mode decomposition (EMD)-discrete Fourier transform (DFT) to jointly extract time series features, and identifies driving style based on these two features; uses driving conditions and driving style as input to realize active suspension control. By jointly extracting driver time series features through EMD-DFT, accurate identification of driving style is achieved, and rolling identification based on a time window is introduced to improve the real-time performance of suspension control, and finally combines human-vehicle factors to improve the comfort and handling stability of suspension control.

[0057] Embodiment 1

[0058] According to an active suspension control method based on rolling driving style recognition provided by the present invention, Figure 1 As shown, including:

[0059] Step S1: Obtain brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and save historical data to build a vehicle operating condition information library. Among them, the accelerator and brake pedal opening information and steering wheel angle information only need to save the latest data, and do not need to save their corresponding historical data.

[0060] Step S2: Compare the current brake and accelerator pedal openings and steering wheel angles with the preset corresponding thresholds to distinguish the longitudinal driving condition and the lateral driving condition of the current vehicle. That is, the brake and accelerator pedal opening thresholds are set as P thr，g , P thr，b , respectively, the current accelerator pedal opening P g , Brake pedal opening P b Compared with the brake and accelerator pedal opening thresholds, the longitudinal driving condition of the current vehicle is distinguished, and the steering wheel angle threshold is set to A thr，sw , the steering wheel angle threshold and the steering wheel angle A sw By comparison, the lateral driving condition of the current vehicle is distinguished. The longitudinal driving condition of the vehicle includes acceleration, cruising and deceleration. The lateral driving condition includes left turn, right turn and straight driving. The step S2 includes:

[0061] Step S2.1: Set the threshold value based on experience, and set the accelerator pedal opening threshold value to P thr，g , set the brake pedal opening threshold to P thr，b , set the steering wheel angle threshold to A thr，sw .

[0062] Step S2.2: Extract the latest accelerator pedal opening P from the vehicle operating condition information database g , the latest brake pedal opening P b And the latest steering wheel angle A sw

[0063] Step S2.3: Adjust the accelerator pedal opening angle P g With threshold P thr，g Compare the size, brake pedal opening P b With threshold P thr，b Compare the size, (P g >P thr，g )&(P b <P thr，b ) corresponds to the acceleration driving condition, (P g <P thr，g )&(P b >Pthr，b ) corresponds to the deceleration driving condition, (P g <P thr，g )&(P b >P thr，b ) corresponds to the cruising driving condition. g >P thr，g )&(P b >P thr，b ) situation is a dangerous operation, which is defined as a deceleration driving condition and the safety system is introduced to take over.

[0064] Step S2.4: Turn the steering wheel to angle A sw With threshold A thr，sw Compare the size, (A sw <-A thr，sw ) corresponds to the left-turn driving condition, (A sw >A thr，sw ) corresponds to the right turn driving condition, (-A thr，sw <A sw <A thr，sw ) corresponds to the straight driving condition.

[0065] Step S3: extracting historical vehicle speed trajectories from the vehicle operating condition information database, segmenting the historical vehicle speed trajectories based on a sliding time window, and obtaining a vehicle speed time series. Step S3 includes:

[0066] Step S3.1: Set the sliding time window size to L.

[0067] Step S3.2: extract the historical vehicle speed trajectory from the vehicle operating condition information database, and reversely segment the vehicle speed trajectory, that is, retain the latest L vehicle speed data to form a vehicle speed time series, and update it with the vehicle speed information, so that the vehicle speed time series is supplemented with the latest frame of vehicle speed and the oldest frame of vehicle speed is removed, and the length of the vehicle speed time series is always kept the same as the length of the sliding time window L to achieve rolling segmentation.

[0068] Step S4: Perform average and variance operations on the vehicle speed time series to obtain statistical features; perform EMD-DFT operations on the vehicle speed time series to obtain time series features; and perform driving style recognition using a classification recognition model based on the statistical and time series features and in comparison with the driving style feature library. The specific implementation process of the EMD-DFT operation described in step S4 is as follows:

[0069] Step S4.1: Perform EMD decomposition on the vehicle speed time series described in step S3.2 to obtain the intrinsic mode function (IMF) and residual (Res). The specific formula is:

[0070]

[0071] Where X(t) represents the signal composed of vehicle speed time series, C i (t) The i-th IMF, n represents the n IMFs obtained after the vehicle speed time series is decomposed.

[0072] Step S4.2: Perform DFT transformation on each IMF to obtain the signal of IMF in the frequency domain. The specific formula is:

[0073] C i，f (w) = DFT(C i (t))

[0074] Where C i，f (w) is the frequency domain signal of the ith IMF after discrete Fourier transform.

[0075] Step S4.3: Calculate the frequency domain signal C i，f The position w of the maximum amplitude of (w) i，m , at this time C i，f (w i，m ) is the main frequency, find C i，f (w i，m ) value, and compare the main frequencies of n IMFs, extracting their maximum value as the time series feature. The specific formula is:

[0076] w i,m = argmax(abs(C i,f (w)))

[0077] f i =Freq(C i，f (w i，m ))

[0078]

[0079] In the formula, the function abs(·) obtains the modulus of the signal, and the function argmax(·) obtains the position w of the maximum modulus length. i，m , the function Freq(·) obtains the frequency of the signal, f i is the main frequency of the current signal, f i，m is the maximum dominant frequency of the vehicle speed time series.

[0080] like Figure 2 As shown, the driving style feature library and driving style rolling recognition of the present invention are specifically described as follows:

[0081] The driving style feature library described in step S4 can be defined by artificial labels, or can be obtained by pre-collecting data of different drivers and performing unsupervised learning clustering algorithm, for example, K-means++ algorithm for unsupervised clustering learning. More specifically, the data collected from different drivers mainly include vehicle speed trajectories during driving, and the collected vehicle speed trajectories are averaged and variance calculated to obtain the statistical average speed V a and speed standard deviation V s , and use the above-mentioned EMD-IMF joint analysis method to obtain the maximum main frequency f i，m , these three quantities are used as input features, and K-means++ is applied for clustering. As a preferred implementation of the present invention, the number of clusters is 3, and the original vehicle speed trajectory fragments are labeled to construct a driving style feature library.

[0082] The classification recognition model described in step S4 may adopt machine learning algorithms such as support vector machine (SVM) and random forest (RF), or deep learning algorithms such as artificial neural network (ANN) and recurrent neural network (RNN). More specifically, the driving style feature condition library is used as input, the adopted SVM is pre-trained until the loss function is stable, and the trained SVM is deployed in the vehicle MCU to realize the driving style recognition function.

[0083] Step S5: Using driving conditions and driving styles as input, applying decision rules to achieve active suspension control. The specific meaning of the decision rules in step S5 is that if there are m driving conditions and n driving styles, then m×n situations can be divided. According to the actual judgment of each situation, active suspension gears are formulated, and suspension control can be achieved. For example, Figure 3 The decision rules shown, 27 situations divided into 9 driving conditions and 3 driving styles.

[0084] The present invention aims to realize accurate recognition of driving style by jointly extracting driver timing features through EMD-DFT, and at the same time introduces rolling recognition based on time window to rollingly update driving style, thereby enhancing the real-time performance of active suspension control.

[0085] The present invention realizes active suspension control based on rolling driving style recognition. The present invention can effectively extract the clutter interference during the time series feature, thereby significantly improving the accuracy of driving style prediction; effectively improve the real-time performance of suspension control by rolling update of vehicle speed time series; and guide the control mode of active suspension in combination with human-vehicle factors, significantly enhancing the performance and reliability of the vehicle suspension system. In view of the key role of active suspension control in vehicle comfort, handling stability, etc., the present invention has important practical value.

[0086] Embodiment 2

[0087] The present invention also provides an active suspension control system based on rolling driving style recognition. The active suspension control system based on rolling driving style recognition can be implemented by executing the process steps of the active suspension control method based on rolling driving style recognition, that is, those skilled in the art can understand the active suspension control method based on rolling driving style recognition as a preferred implementation of the active suspension control system based on rolling driving style recognition.

[0088] An active suspension control system based on rolling driving style recognition provided by the present invention comprises:

[0089] Module M1: Obtain brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and save historical data to build a vehicle operating condition information library.

[0090] Module M2: Compare the current brake, accelerator pedal opening, and steering wheel angle with the preset corresponding thresholds to distinguish the longitudinal driving condition and lateral driving condition of the current vehicle. The longitudinal driving condition of the vehicle includes acceleration, cruising, and deceleration. The lateral driving condition includes left turn, right turn, and straight driving. Module M2 includes: Module M2.1: Set the threshold value based on experience, set the accelerator pedal opening threshold value as P thr，g , set the brake pedal opening threshold to P thr，b , set the steering wheel angle threshold to A thr，sw Module M2.2: Extract the latest accelerator pedal opening P from the vehicle operating condition information database g , the latest brake pedal opening P b And the latest steering wheel angle A sw Module M2.3: Set the accelerator pedal opening to P g With threshold P thr，g Compare the size, brake pedal opening P b With threshold P thr，b Compare the size, P g Greater than P thr，g And P b Less than P thr，b Corresponding to the acceleration driving condition, P g Less than P thr，g And P b Greater than P thr，b Corresponding to the deceleration driving condition, P g Less than P thr，g And P b Less than A thr，b Corresponding to the cruising driving condition, P g Greater than A thr，g And P b Greater than P thr，bThe situation is a dangerous operation, and the situation is defined as a deceleration driving condition, and the safety system is introduced to take over. Module M2.4: Turn the steering wheel to an angle A sw With threshold A thr，sw Compare the size, A sw Less than -A thr，sw For left-turn driving conditions, A sw Greater than A thr，sw For right turn driving condition, A sw In the range (-A thr，sw , A thr，sw ) corresponds to the straight driving condition.

[0091] Module M3: Extract historical vehicle speed trajectories from the vehicle operating condition information database, segment the historical vehicle speed trajectories based on the sliding time window, and obtain the vehicle speed time series. Module M3 includes: Module M3.1: Set the sliding time window size to L. Module M3.2: Extract historical vehicle speed trajectories from the vehicle operating condition information database, and segment the vehicle speed trajectories in reverse, that is, retain the latest L vehicle speed data to form a vehicle speed time series, and update it with the vehicle speed information, so that the vehicle speed time series is supplemented with the latest frame of vehicle speed, and the oldest frame of vehicle speed is removed, and the length of the vehicle speed time series is always kept the same as the length of the sliding time window L, so as to achieve rolling segmentation.

[0092] Module M4: Perform average and variance operations on the vehicle speed time series to obtain statistical features. Perform empirical mode decomposition (EMD) and discrete Fourier transform (DFT) on the vehicle speed time series to obtain time series features. According to the statistical and time series features, the classification and recognition model is used to identify the driving style in comparison with the driving style feature library. The empirical mode decomposition (EMD) and discrete Fourier transform (DFT) joint operation in module M4 includes: Module M4.1: Perform EMD decomposition on the vehicle speed time series to obtain the intrinsic mode function (IMF) and the residual (Res), the formula is:

[0093]

[0094] Where X(t) represents the signal composed of vehicle speed time series, C i (t) the ith IMF, n represents the total number of n IMFs obtained after the vehicle speed time series is decomposed. Module M4.2: Perform DFT transformation on each IMF to obtain the signal of the IMF in the frequency domain. The formula is:

[0095] C i，f (w) = DFT(C i (t))

[0096] Where C i，f (w) is the frequency domain signal of the ith IMF after discrete Fourier transform. Module M4.3: Find the frequency domain signal C i，f The position w of the maximum amplitude of (w)i，m , at this time C i，f (w i，m ) is the main frequency, find C i，f (w i，m ) value, and compare the main frequencies of n IMFs, extracting their maximum value as the timing feature. The formula is:

[0097] w i,m = argmax(abs(C i,f (w)))

[0098] f i =Freq(C i,f (w i,m ))

[0099]

[0100] In the formula, the function abs(·) obtains the modulus of the signal, and the function argmax(·) obtains the position w of the maximum modulus length. i，m , the function Freq(·) obtains the frequency of the signal, f i is the main frequency of the current signal, f i，m is the maximum main frequency of the vehicle speed time series.

[0101] The driving style feature library includes artificial label definition and unsupervised learning clustering algorithm obtained by pre-collecting different driver data. According to the speed trajectory of the driver, the collected speed trajectory is averaged and variance is calculated to obtain the statistical average speed V a and speed standard deviation V s According to the EMD-IMF joint analysis method, the maximum main frequency f is obtained i，m The statistical average speed V a , speed standard deviation V s and the maximum main frequency f i，m As input, K-means++ is used for clustering, and the original vehicle speed trajectory is labeled to build a driving style feature library. The classification and recognition models include support vector machine SVM, random forest RF, artificial neural network ANN, and recurrent neural network RNN.

[0102] Module M5: Using driving conditions and driving styles as input, active suspension control is achieved by applying decision rules. The decision rule of module M5 is that if there are m driving conditions and n driving styles, n×n situations can be divided. Based on the actual judgment of each situation, active suspension gears are formulated to achieve suspension control.

[0103] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0104] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. An active suspension control method based on rolling driving style recognition, characterized in that: include: Step S1: Obtain brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and save historical data to build a vehicle operating condition information library; Step S2: respectively comparing the current brake and accelerator pedal openings and steering wheel angles with preset corresponding thresholds to distinguish the longitudinal driving condition and the lateral driving condition of the current vehicle; Step S3: extracting historical vehicle speed trajectories from the vehicle operating condition information database, and segmenting the historical vehicle speed trajectories based on a sliding time window to obtain a vehicle speed time series; Step S4: averaging and variance calculation are performed on the vehicle speed time series to obtain statistical features; Perform empirical mode decomposition (EMD) and discrete Fourier transform (DFT) on the vehicle speed time series to obtain time series features. According to the statistical and time series features, and in comparison with the driving style feature library, a classification recognition model is applied to perform driving style recognition. Step S5: Using the driving condition and driving style as input, applying decision rules to implement active suspension control.

2. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The longitudinal driving conditions of the vehicle include acceleration, cruising and deceleration; The lateral driving conditions include left turn, right turn and straight driving.

3. The active suspension control method based on rolling driving style recognition according to claim 2, characterized in that: Step S2 includes: Step S2.1: Set the threshold value based on experience, and set the accelerator pedal opening threshold value to P thr，g , set the brake pedal opening threshold to P thr，b , set the steering wheel angle threshold to A thr,sw ; Step S2.2: Extract the latest accelerator pedal opening P from the vehicle operating condition information database g , the latest brake pedal opening P b And the latest steering wheel angle A sw ; Step S2.3: Adjust the accelerator pedal opening angle P g With threshold P thr，g Compare the size, brake pedal opening P b With threshold P thr，b Compare the size, P g Greater than P thr，g And P b Less than P thr，b Corresponding to the acceleration driving condition, P g Less than P thr，g And P b Greater than P thr，b Corresponding to the deceleration driving condition, P g Less than P thr，g And P b Less than P thr，b Corresponding to the cruising driving condition, P g Greater than P thr，g And P b Greater than P thr，b The situation is a dangerous operation, and the situation is defined as a deceleration driving condition, and the safety system is introduced to take over; Step S2.4: Turn the steering wheel to angle A sw With threshold A thr，sw Compare the size, A sw Less than -A thr，sw For left-turn driving conditions, A sw Greater than A thr，sw For right turn driving condition, A sw In the range (-A thr，sw , A thr，sw ) corresponds to the straight driving condition.

4. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The step S3 comprises: Step S3.1: Set the sliding time window size to L; Step S3.2: extract the historical vehicle speed trajectory from the vehicle operating condition information database, and reversely segment the vehicle speed trajectory, that is, retain the latest L vehicle speed data to form a vehicle speed time series, and update it with the vehicle speed information, so that the vehicle speed time series is supplemented with the latest frame of vehicle speed and the oldest frame of vehicle speed is removed, and the length of the vehicle speed time series is always kept the same as the length of the sliding time window L to achieve rolling segmentation.

5. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The empirical mode decomposition EMD and discrete Fourier transform DFT joint operation in step S4 includes: Step S4.1: Perform EMD decomposition on the vehicle speed time series to obtain the intrinsic mode function IMF and residual Res, the formula is: Where X(t) represents the signal composed of vehicle speed time series, C n (t) the i-th IMF, n represents the m IMFs obtained after the vehicle speed time series is decomposed; Step S4.2: Perform DFT transformation on each IMF to obtain the signal of IMF in the frequency domain. The formula is: C i，f (w)=DFT(C i (t)) Where C i，f (w) is the frequency domain signal of the ith IMF after discrete Fourier transform; Step S4.3: Calculate the frequency domain signal C i，f The position w where the maximum amplitude of (w) is i，m , at this time C i，f (w i，m ) is the main frequency, find C i，f (w i，m ) value, and compare the main frequencies of n IMFs, extracting their maximum value as the timing feature. The formula is: w i，m =argmax(abs(C i，f (w))) f i =Freq(C i，f (w i，m )) In the formula, the function abs(·) obtains the modulus of the signal, and the function argmax(·) obtains the position w of the maximum modulus length. i,m , the function Freq(·) obtains the frequency of the signal, f i is the main frequency of the current signal, f i，m is the maximum main frequency of the vehicle speed time series.

6. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The driving style feature library includes definitions through artificial labels and is obtained by pre-collecting different driver data and performing unsupervised learning clustering algorithms.

7. The active suspension control method based on rolling driving style recognition according to claim 6, characterized in that: According to the speed trajectory of the driver, the collected speed trajectory is averaged and the variance is calculated to obtain the statistical average speed V a and speed standard deviation V s ; According to the EMD-IMF joint analysis method, the maximum main frequency f is obtained i，m ; The obtained statistical average speed V a , speed standard deviation V s and the maximum main frequency f i，m As input, K-means++ is used for clustering, and the original vehicle speed trajectories are labeled to build a driving style feature library.

8. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The classification and recognition models include support vector machines SVM, random forests RF, artificial neural networks ANN, and recurrent neural networks RNN.

9. The active suspension control method based on rolling driving style recognition according to claim 1, characterized in that: The decision rule described in step S5 is that there are m driving conditions and n driving styles, which can be divided into m×n situations. According to the actual judgment of each situation, the active suspension gear is determined to achieve suspension control.

10. An active suspension control system based on rolling driving style recognition, characterized in that: include: Module M1: obtains brake and accelerator pedal opening, steering wheel angle and vehicle speed information from the CAN bus, and saves historical data to build a vehicle operating condition information library; Module M2: compares the current brake and accelerator pedal openings and steering wheel angles with the preset corresponding thresholds to distinguish the longitudinal driving condition and the lateral driving condition of the current vehicle; Module M3: extracting historical vehicle speed trajectories from the vehicle operating condition information database, segmenting the historical vehicle speed trajectories based on a sliding time window, and obtaining a vehicle speed time series; Module M4: Calculate the average and variance of the vehicle speed time series to obtain statistical characteristics; Perform empirical mode decomposition (EMD) and discrete Fourier transform (DFT) on the vehicle speed time series to obtain time series features. According to the statistical and time series features, and in comparison with the driving style feature library, a classification recognition model is applied to perform driving style recognition. Module M5: Using driving conditions and driving style as input, it applies decision rules to achieve active suspension control.

Images