Vehicle anti-shake control methods, devices, storage media and vehicles

Abstract

This invention discloses a vehicle anti-shake control method, device, storage medium, and vehicle. The method includes: acquiring the rotational speed of a motor in the vehicle and the corresponding rotational speed fluctuation frequency; in response to the rotational speed being within a rotational speed threshold range and the rotational speed fluctuation frequency being within a rotational speed fluctuation frequency threshold range, filtering the motor's rotational speed signal to obtain the fluctuation error of the rotational speed signal; determining the vehicle's anti-shake torque based on the fluctuation error; and performing anti-shake control on the vehicle based on the anti-shake torque. This invention solves the technical problem of vehicle drive system vibration caused by rotational speed fluctuations.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a method, apparatus, storage medium, and vehicle for stabilizing vehicle vibration control. Background Technology

[0002] Currently, vehicle vibration stabilization control typically involves identifying the trend of braking torque changes. If the drive motor was in braking condition at the previous moment and the braking torque trend was decreasing, and the current speed of the drive motor is in the low-speed range, then if the braking torque demand at the current moment is lower than the low torque preset value, the target braking torque at the current moment is reduced according to the dynamic decrease rate. However, the above method only uses the fluctuation trend of speed for open-loop control, which makes it difficult to guarantee the accuracy of vibration stabilization control, thus leading to technical problems such as vibration of the entire vehicle drive system caused by speed fluctuations.

[0003] There is currently no effective solution to the technical problem of vehicle drive system vibration caused by speed fluctuations. Summary of the Invention

[0004] This invention provides a vehicle anti-shake control method, device, storage medium, and vehicle to at least solve the technical problem of vehicle drive system vibration caused by speed fluctuations.

[0005] According to one aspect of the present invention, a vehicle anti-shake control method is provided. The method may include: acquiring the rotational speed of a motor in the vehicle and the corresponding rotational speed fluctuation frequency; in response to the rotational speed being within a rotational speed threshold range and the rotational speed fluctuation frequency being within a rotational speed fluctuation frequency threshold range, filtering the motor rotational speed signal to obtain a fluctuation error in the rotational speed signal; determining the vehicle's anti-shake torque based on the fluctuation error; and performing anti-shake control on the vehicle based on the anti-shake torque.

[0006] Optionally, in response to the speed being within a speed threshold range and the speed fluctuation frequency being within a speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal, including: discretizing the Butterworth filter to obtain a target Butterworth filter; and inputting the speed signal to the target Butterworth filter to obtain the fluctuation error.

[0007] Optionally, after filtering the motor speed signal to obtain the speed signal fluctuation error in response to the speed being within a speed threshold range and the speed fluctuation frequency being within a speed fluctuation frequency threshold range, the vehicle anti-shake control method may further include: storing at least one control parameter in the radial basis function neural network in each sampling period; averaging the control parameters in response to the number of control parameters being equal to the number of preset parameters, and determining the average value as the initial control parameter in the radial basis function neural network.

[0008] Optionally, the anti-shake torque of the vehicle is determined based on the fluctuation error, including: determining the control law in the radial basis function neural network based on the fluctuation error and the initial control parameters; and inputting the control law into the radial basis function neural network to obtain the anti-shake torque.

[0009] Optionally, the control law in the radial basis function neural network is determined based on the fluctuation error and the initial control parameters, including: determining the first parameter of the radial basis function neural network based on the fluctuation error, wherein the first parameter is used to characterize the tuning value of the radial basis function neural network; and determining the control law based on the first parameter, the initial control parameters and the learning rate of the radial basis function neural network.

[0010] Optionally, after performing anti-shake control on the vehicle based on the anti-shake torque, the anti-shake control method for the vehicle may further include: deleting the first control parameter from the control parameters and storing the control parameters in the radial basis function neural network in the current sampling period to obtain updated target control parameters, wherein the first control parameter is used to characterize the control parameter corresponding to the earliest sampling period in the control parameters; in response to the number of target control parameters being equal to the number of preset parameters, averaging the target control parameters and determining the average value as the initial control parameter in the radial basis function neural network.

[0011] According to one aspect of the present invention, a vehicle anti-shake control device is provided. The device may include: an acquisition unit for acquiring the rotational speed of a motor in the vehicle and the corresponding rotational speed fluctuation frequency; a first response unit for filtering the motor rotational speed signal to obtain a rotational speed signal fluctuation error in response to the rotational speed being within a rotational speed threshold range and the rotational speed fluctuation frequency being within a rotational speed fluctuation frequency threshold range; a determination unit for determining the vehicle's anti-shake torque based on the fluctuation error; and a control unit for performing anti-shake control on the vehicle based on the anti-shake torque.

[0012] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the vehicle stabilization control method of the present invention.

[0013] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program, when run by the processor, executes the vehicle stabilization control method of the present invention.

[0014] According to another aspect of the present invention, a vehicle is also provided, which is used to perform the vehicle anti-shake control method of the present invention.

[0015] In this embodiment of the invention, the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency are obtained. The rotational speed of the motor in the vehicle is compared with a rotational speed threshold range, and the rotational speed fluctuation frequency is compared with a rotational speed fluctuation frequency threshold range. If both the rotational speed and the rotational speed fluctuation frequency are within the rotational speed threshold range, the rotational speed signal of the motor is filtered to obtain the fluctuation error of the rotational speed signal. Based on the fluctuation error and the initial control parameters, the control law in the radial basis function neural network is determined. The control law is input into the radial basis function neural network to obtain the anti-shake torque. Based on the obtained anti-shake torque, the vehicle is subjected to anti-shake control, thereby achieving the goal of real-time optimization of proportional-derivative parameters. This solves the technical problem of vehicle drive system vibration caused by rotational speed fluctuation and achieves the technical effect of controlling vehicle drive system vibration caused by rotational speed fluctuation. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a vehicle anti-shake control method according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of an adaptive anti-shake control system based on a Butterworth filter according to an embodiment of the present invention;

[0019] Figure 3 This is a flowchart of a motor speed preprocessing method according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of an RBF neural network adaptive PD control design according to an embodiment of the present invention;

[0021] Figure 5 This is a flowchart of an iterative method for optimal parameters according to an embodiment of the present invention;

[0022] Figure 6 This is a schematic diagram of a vehicle anti-shake control device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of the present invention, a method for stabilizing vehicle vibration control is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a vehicle anti-shake control method according to an embodiment of the present invention, which may include the following steps:

[0028] Step S101: Obtain the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency.

[0029] In the technical solution provided by step S101 of the present invention, the rotational speed of the motor in the vehicle can be the actual motor rotational speed in the Controller Area Network (CAN) communication, and the rotational speed fluctuation frequency corresponding to the rotational speed can be the rotational speed fluctuation frequency corresponding to the actual motor rotational speed in the CAN communication.

[0030] Optionally, the rotational speed of the motor in the vehicle under actual driving conditions can be measured by a speed sensor, and the rotational speed fluctuation frequency corresponding to the rotational speed can be measured by an electronic counting method. This is only an example and is not specifically limited.

[0031] Step S102: In response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal.

[0032] In the technical solution provided by step S102 of the present invention, the above-mentioned speed threshold range can be the accurate motor speed range during the stage when vehicle vibration is likely to occur, the above-mentioned speed fluctuation frequency threshold range can be the motor speed fluctuation frequency range corresponding to the accurate motor speed range during the stage when vehicle vibration is likely to occur, and the above-mentioned filtering process can be performed by using a first-order Butterworth bandpass filter.

[0033] Optionally, after obtaining the motor speed and the corresponding speed fluctuation frequency in the vehicle, the motor speed is compared with a speed threshold range, and the speed fluctuation frequency is compared with a speed fluctuation frequency threshold range. If both the speed and the speed fluctuation frequency are within the speed threshold range, the motor speed signal is filtered to obtain the speed signal fluctuation error. For example, the actual motor speed in CAN communication is compared with the speed threshold range, and the speed fluctuation frequency corresponding to the actual motor speed is compared with the speed fluctuation frequency threshold range. If both the actual motor speed and the speed fluctuation frequency are within the speed fluctuation frequency threshold range, the actual motor speed signal is filtered using a first-order Butterworth bandpass filter to obtain the actual speed signal fluctuation error.

[0034] Step S103: Determine the vehicle's anti-shake torque based on the fluctuation error.

[0035] In the technical solution provided by step S103 of the present invention, the fluctuation error can be the control error output by a first-order Butterworth bandpass filter, and the anti-shake torque of the vehicle can be the torque obtained by a radial basis function neural network.

[0036] Optionally, in response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, the motor speed signal is filtered to obtain the speed signal fluctuation error. Based on the speed signal fluctuation error, the vehicle's anti-shake torque can be determined. For example, based on the control error output by the first-order Butterworth bandpass filter, the vehicle's anti-shake torque can be determined through a proportional-integral controller and a radial basis function neural network. This is only an example and is not specifically limited.

[0037] Step S104: Based on the anti-shake torque, perform anti-shake control on the vehicle.

[0038] In the technical solution provided in step S104 of the present invention, after determining the anti-shake torque of the vehicle based on the fluctuation error, the vehicle is subjected to anti-shake control based on the anti-shake torque. For example, the torque of the vehicle can be adjusted to the anti-shake torque according to the determined anti-shake torque, thereby performing anti-shake control on the vehicle and achieving the technical effect of controlling the vibration of the whole vehicle drive system caused by speed fluctuation.

[0039] Through steps S101 to S104 of this application, the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency are obtained. The rotational speed of the motor in the vehicle is compared with the rotational speed threshold range, and the rotational speed fluctuation frequency is compared with the rotational speed fluctuation frequency threshold range. If the rotational speed is within the rotational speed threshold range and the rotational speed fluctuation frequency is within the rotational speed fluctuation frequency threshold range, the rotational speed signal of the motor is filtered to obtain the fluctuation error of the rotational speed signal. Based on the fluctuation error and the initial control parameters, the control law in the radial basis function neural network is determined. The control law is input into the radial basis function neural network to obtain the anti-shake torque. Based on the obtained anti-shake torque, the vehicle is subjected to anti-shake control, thereby achieving the goal of real-time optimization of proportional derivative (PD) parameters. This solves the technical problem of vehicle drive system vibration caused by rotational speed fluctuation and achieves the technical effect of controlling vehicle drive system vibration caused by rotational speed fluctuation.

[0040] The method described in this embodiment will be further described below.

[0041] As an optional embodiment, step S102, in response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, filters the motor speed signal to obtain the speed signal fluctuation error, including: discretizing the Butterworth filter to obtain a target Butterworth filter; and inputting the speed signal to the target Butterworth filter to obtain the fluctuation error.

[0042] In this embodiment, the Butterworth filter can be a normalized first-order Butterworth bandpass filter, and the target Butterworth filter can be a discretized first-order Butterworth bandpass filter.

[0043] Optionally, after obtaining the motor speed and the corresponding speed fluctuation frequency in the vehicle, the normalized first-order Butterworth bandpass filter is discretized to obtain the target Butterworth filter. The obtained actual speed signal is then input to the target Butterworth filter to obtain the fluctuation error of the actual speed signal.

[0044] Optionally, the normalized first-order Butterworth bandpass filter can be discretized to obtain the target Butterworth filter, which can be achieved by the following equation:

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] The original first-order Butterworth bandpass filter is normalized, and its transfer function is determined as shown in equation (1) above. a0 and b0 can be used to represent the system parameters of the first-order Butterworth bandpass filter system, which can be determined by the system model of the first-order Butterworth bandpass filter system. When a0 = b0 = a n When = 1, the normalized Butterworth transfer function can be obtained. The normalized Butterworth transfer function is shown in equation (2) above. According to the discretization processing rule shown in equation (3) above, the normalized first-order Butterworth transfer function is discretized to obtain the discretized first-order Butterworth transfer function and the input-output relationship, as shown in equations (4) and (5) below, respectively. Among them, z can be used to represent the variables after the first-order Butterworth transfer function is discretized, D and Ez can be used to represent the frequency parameters, which can be determined by the filtering frequency, H(z) can be used to represent the discretized form of the transfer function H(S), y(k) can be used to represent the speed after filtering, r(k) can be used to represent the actual input speed, and k can be used to represent the discretized form of continuous time t.

[0051] As an optional embodiment, in step S102, in response to the rotational speed being within a rotational speed threshold range and the rotational speed fluctuation frequency being within a rotational speed fluctuation frequency threshold range, the rotational speed signal of the motor is filtered to obtain the fluctuation error of the rotational speed signal. The vehicle anti-shake control method may further include: storing at least one control parameter in the radial basis function neural network in each sampling period; in response to the number of control parameters being equal to the number of preset parameters, averaging the control parameters and determining the average value as the initial control parameter in the radial basis function neural network.

[0052] In this embodiment, the aforementioned radial basis function neural network can be a radial basis function (RBF) neural network, the aforementioned control parameters can be the control parameters adjusted by the proportional derivative (PD) control of the neural network in each sampling period, the aforementioned number of preset parameters can be set to 500, and the aforementioned initial control parameters can be the initialization control parameters of the neural network PD control. This is only an example and is not specifically limited.

[0053] Optionally, in response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal. Then, at least one control parameter adjusted by the neural network PD control in each sampling cycle is stored in a register. The number of stored control parameters is calculated and compared with the number of preset parameters. If the number of control parameters is equal to the number of preset parameters, the average value of the control parameters stored in the register is calculated, and the average value of the calculated control parameters is determined as the initial control parameter in the RBF neural network.

[0054] As an optional embodiment, step S103, determining the vehicle's anti-shake torque based on the fluctuation error, includes: determining the control law in the radial basis function neural network based on the fluctuation error and initial control parameters; inputting the control law into the radial basis function neural network to obtain the anti-shake torque.

[0055] In this embodiment, the control law can be determined by the input parameters of the PD controller, the control parameters of the PD controller, and the change in the control parameters of the PD controller. The anti-shake torque can be used to control the vehicle's anti-shake performance. The input parameters of the PD controller can be determined based on the fluctuation error of the actual speed signal. This is only an example and is not specifically limited.

[0056] Optionally, in response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal. Based on the fluctuation error of the actual speed signal, the control parameters of the PD controller, and the change in the control parameters of the PD controller, the control law in the RBF neural network can be determined. The determined control law is input into the RBF neural network to obtain the anti-shake torque of the vehicle.

[0057] Optionally, based on the fluctuation error of the actual speed signal, the control parameters of the PD controller, and the change in the control parameters of the PD controller, the control law in the RBF neural network can be determined by the following formula:

[0058] x1=e(k)-e(k-1) (6)

[0059] x2=e(k)-2e(k-1)+e(k-2) (7)

[0060]

[0061]

[0062]

[0063] u(k)=(k p +Δk p (e(k)-e(k-1))+(k) d +Δk d (e(k)-2e(k-1)+e(k-2) (11)

[0064] Where x1 and x2 can be used to represent the input signals of the PD controller, and E(k) can be used to represent the tuning index of the neural network, k p k can be used to represent the proportional term coefficient of PD control. d It can be used to represent the differential coefficient of PD control, Δk p and Δk d It can be used to represent the change in PD control parameters, γ can be used to represent the learning rate of the neural network, and u(k) can be used to represent the control law of RBF neural network PD control.

[0065] As an optional embodiment, the control law in the radial basis function neural network is determined based on the fluctuation error and the initial control parameters, including: determining the first parameter of the radial basis function neural network based on the fluctuation error; and determining the control law based on the first parameter, the initial control parameters, and the learning rate of the radial basis function neural network.

[0066] In this embodiment, the first parameter can be used to characterize the tuning value of the radial basis function neural network, and the learning rate of the radial basis function neural network can be represented by γ.

[0067] Optionally, the first parameter of the radial basis function neural network can be determined based on the fluctuation error of the actual speed signal. Based on the first parameter, the initial control parameter, and the learning rate γ of the radial basis function neural network, the control law of the RBF neural network PD control can be determined.

[0068] Optionally, the first parameter of the radial basis function neural network can be determined based on the fluctuation error of the actual rotational speed signal using the following formula:

[0069]

[0070] E(k) can be used to represent the tuning index of the neural network.

[0071] Optionally, the control law for PD control of the RBF neural network, based on the first parameter, initial control parameters, and the learning rate γ of the radial basis function neural network, can be determined using the following formula:

[0072]

[0073]

[0074] u(k)=(k p +Ak p (e(k)-e(k-1))+(k) d +Δk d (e(k)-2e(k-1)+e(k-2)) (11)

[0075] Where, Δk p and Δk d It can be used to represent the change in PD control parameters, and u(k) can be used to represent the control law of RBF neural network PD control.

[0076] As an optional embodiment, after performing anti-shake control on the vehicle based on the anti-shake torque in step S104, the anti-shake control method of the vehicle may further include: deleting the first control parameter in the control parameters and storing the control parameters in the radial basis function neural network in the current sampling period to obtain the updated target control parameters; in response to the number of target control parameters being equal to the number of preset parameters, averaging the target control parameters and determining the average value as the initial control parameter in the radial basis function neural network.

[0077] In this embodiment, the first control parameter can be used to characterize the control parameter corresponding to the earliest sampling period in the control parameters, and the number of preset parameters can be set to 500.

[0078] Optionally, after performing anti-shake control on the vehicle based on the anti-shake torque, if the number of control parameters currently stored in the register has reached the preset number of parameters, the control parameter corresponding to the earliest sampling period in the control parameters is deleted, and the control parameters in the RBF neural network in the current sampling period are stored to obtain the updated target control parameters. Then, the number of target control parameters is compared with the preset number of parameters. If the number of target control parameters is equal to the preset number of parameters, the average value of the target control parameters is calculated, and the calculated average value is determined as the initial control parameter in the RBF neural network. If the number of target control parameters is not equal to the preset number of parameters, there is no need to calculate the average value of the target control parameters, nor is there a need to update the initial control parameters in the RBF neural network.

[0079] This embodiment obtains the motor speed and the corresponding speed fluctuation frequency in the vehicle. It compares the motor speed with a speed threshold range and the speed fluctuation frequency with a speed fluctuation frequency threshold range. If both the speed and the speed fluctuation frequency are within the speed threshold range, the motor speed signal is filtered to obtain the speed signal fluctuation error. Based on the fluctuation error and initial control parameters, a control law in the radial basis function neural network is determined. The control law is input into the radial basis function neural network to obtain the anti-shake torque. Based on the obtained anti-shake torque, the vehicle is subjected to anti-shake control, thereby solving the technical problem of vehicle drive system vibration caused by speed fluctuation and achieving the technical effect of controlling vehicle drive system vibration caused by speed fluctuation.

[0080] Example 2

[0081] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0082] Current vehicle vibration stabilization control typically identifies the trend of braking torque changes. If, in the previous moment, the drive motor was in braking mode and the braking torque trend was decreasing, and if the current drive motor speed is in the low-speed range, then if the current braking torque demand is lower than a preset low torque value, the target braking torque is reduced according to a dynamic decrease rate. However, this method relies solely on open-loop control based on speed fluctuations, making it difficult to guarantee the accuracy of vibration stabilization control. This leads to technical problems such as vibration in the entire vehicle drive system caused by speed fluctuations. Therefore, a vehicle vibration stabilization control method is needed to ensure that vibration in the entire vehicle drive system caused by speed fluctuations can be controlled.

[0083] In one related technology, an active anti-shake control method for electric vehicles is disclosed, comprising: acquiring the current speed of the drive motor through a rotary transformer speed sensor installed in the electric drive system, transmitting it to the damping module in the disturbance controller, outputting control torque, and then limiting the torque to finally output a corrected damping torque; the disturbance controller assesses the existing system requirements and the current vehicle status based on the data from various sensors and the motor status, determines whether to enter the active anti-shake damping mode, selects appropriate setting parameters, and provides them to the damping module of the disturbance controller; the torque transmitted from the entire vehicle is transmitted to the filtering module of the filter controller; the filter controller assesses the existing system requirements and the current vehicle status based on the data from various sensors and the motor status, determines whether to enter the active anti-shake filtering mode, selects appropriate setting parameters, provides them to the filtering module of the filter controller, outputs control torque, and then limits the torque through load change condition damping control to finally output a corrected filtering control torque; the difference between the corrected damping control torque and the corrected filtering control torque is used as the final corrected torque, which is added to the torque requirement as the requested torque for electric drive. However, this method only retrieves the corresponding filter parameter values ​​by calibrating the parameters to complete the corresponding control, inputs the difference between the two into the electric drive system, and continuously adjusts it through the speed closed loop to make the motor output speed tend to the target speed. It cannot determine the anti-shake torque through neural network adaptive PD control based on the fluctuation error of the motor speed, and thus it is difficult to guarantee that the vibration of the whole vehicle drive system caused by speed fluctuation can be controlled.

[0084] However, this invention proposes an adaptive anti-shake control method based on a Butterworth filter. By calibrating the accurate motor speed range during periods when vehicle vibration is prone to occur, and the corresponding motor speed fluctuation frequency range, this method serves as the criterion for enabling and disabling the anti-shake algorithm. Based on the fluctuation error of the ideal speed signal, it utilizes neural network adaptive proportional-derivative (PD) control to perform anti-shake torque compensation, achieving real-time optimization of PD parameters. This solves the technical problem of vehicle drive system vibration caused by speed fluctuations and achieves the technical effect of controlling vehicle drive system vibration caused by speed fluctuations.

[0085] Figure 2This is a schematic diagram of an adaptive anti-shake control system based on a Butterworth filter according to an embodiment of the present invention. The system may include: an anti-shake algorithm activation determination module 201, a first-order Butterworth bandpass filter module 202, an RBF neural network PD control module 203, an optimal parameter iteration module 204, and a motor module 205. The anti-shake algorithm activation determination module 201 can communicate with the first-order Butterworth bandpass filter module 202, the first-order Butterworth bandpass filter module 202 can communicate with the RBF neural network PD control module 203, and the RBF neural network PD control module 203 can communicate with the optimal parameter iteration module 204.

[0086] Figure 3 This is a flowchart of a motor speed preprocessing method according to an embodiment of the present invention, such as... Figure 3 As shown, the motor speed preprocessing method may include the following steps:

[0087] Step S301: Obtain the actual motor speed from the CAN communication.

[0088] After obtaining the actual motor speed via CAN communication, proceed to step S302, where the anti-shake algorithm is activated.

[0089] After the anti-shake algorithm is activated, step S303 is entered to determine whether the actual motor speed is greater than 0 and whether the actual motor speed is less than the algorithm exit calibration threshold. If the actual motor speed is greater than 0 and less than the algorithm exit calibration threshold, then steps S304, S305, S306, and S307 are entered to activate the anti-shake algorithm, transmit the actual motor speed, and use a first-order Butterworth bandpass filter to filter the motor speed signal to obtain the fluctuation error of the ideal speed signal. If the actual motor speed is less than 0 or greater than the algorithm exit calibration threshold, then step S308 is entered to disable the anti-shake algorithm.

[0090] Optionally, by analyzing real-vehicle data under driving conditions of rapid acceleration (Tip in) and rapid deceleration (Tip out), the accurate motor speed range during which vehicle vibration is prone to occur, as well as the corresponding motor speed fluctuation frequency range, are calibrated. These serve as the criteria for enabling and disabling the anti-shake algorithm. The speed signal within this range is filtered using a first-order Butterworth bandpass filter. The filtered actual motor speed signal becomes a low-frequency speed fluctuation curve symmetrical about the 0-axis, which can be regarded as the fluctuation error of the ideal speed signal at the control level.

[0091] Alternatively, the design of a first-order Butterworth bandpass filter can be achieved through the following process:

[0092] The first-order Butterworth bandpass filter is normalized, and the form of its transfer function is determined, where the form of the transfer function is as follows:

[0093]

[0094] Here, a0 and b0 can be used to represent the system parameters of a first-order Butterworth bandpass filter system, which can be determined by the system model of the first-order Butterworth bandpass filter system. Generally, it is desirable to keep the passband gain at 0 dB, that is, 20lg|H(w)|=0. Therefore, we set a0=b0, and when a0=b0=a n When = 1, the normalized Butterworth transfer function can be obtained, which is shown in the following equation:

[0095]

[0096] Optionally, in the vehicle control system, the control strategy is a time-based discrete algorithm. Therefore, the first-order Butterworth transfer function is discretized, and the discretization rule can be expressed as follows:

[0097]

[0098] Here, z can be used to represent the variables after discretization of the first-order Butterworth transfer function, and D and Ez can be used to represent the frequency parameters, which can be determined by the filtering frequency.

[0099] Alternatively, the discretized first-order Butterworth transfer function and the input-output relationship can be represented as follows:

[0100]

[0101]

[0102] Where D and E can be used to represent frequency parameters, which can be determined by the filtering frequency; H(z) can be used to represent the discrete form of the transfer function H(S); y(k) can be used to represent the rotational speed after filtering; r(k) can be used to represent the actual input rotational speed; and k can be used to represent the discrete form of the continuous time t.

[0103] Figure 4 This is a schematic diagram of an RBF neural network adaptive PD control design according to an embodiment of the present invention, as shown below. Figure 4 As shown, the control error e(k) can be used to represent the output signal of the first-order bandpass Butterworth filter, and the input of the PD controller can be expressed as follows:

[0104] x1=e(k)-e(k-1) (6)

[0105] x2=e(k)-2e(k-1)+e(k-2) (7)

[0106] x1 and x2 can be used to represent the input signals of the PD controller.

[0107] Alternatively, the tuning index of the neural network can be expressed as follows:

[0108]

[0109] Optionally, the change Δk of the PD control parameters can be obtained through RBF neural network identification. p and Δk d , where Δk p and Δk d It can be calculated using the following formula:

[0110]

[0111]

[0112] Where γ can be used to represent the learning rate of the neural network, from which the control law for the PD control of the RBF neural network can be obtained. This control law can be calculated using the following formula:

[0113] u(k)=(k p +Δk p (e(k)-e(k-1))+(k) d +Δk d (e(k)-2e(k-1)+e(k-2)) (11)

[0114] Figure 5 This is a flowchart of an iterative method for optimal parameters according to an embodiment of the present invention, such as... Figure 5 As shown, the method may include the following steps:

[0115] Step S501, read K p and K d The initial value is used to complete the parameter initialization.

[0116] Reading K p and K d After initializing the parameters, proceed to step S502 to check if the anti-shake algorithm is started. If the anti-shake algorithm is not started, there is no need to perform the optimal parameter iteration process. If the anti-shake algorithm is started, proceed to steps S503, S504, and S505, where the register stores K for each sampling period. p and K dThe register count is incremented by 1, and a check is performed to see if the register count is greater than 500.

[0117] If the register count is not greater than 500, proceed to step S503, where the register stores K for each sampling period. p and K d If the register count is greater than 500, proceed to steps S506 and S507 to calculate the average value of the control parameters in the register and replace K. p and K d The calculation of the next sampling period is initiated, and the anti-shake algorithm is monitored. If the anti-shake algorithm is disabled, the process proceeds to step S508, where the average value of the control parameters in the register is calculated and used to initialize K. p and K d The value of K is used in the calculation to enable the next image stabilization algorithm. If the image stabilization algorithm is not disabled, proceed to step S503, where the register stores K for each sampling period. p and K d .

[0118] Optionally, a register is set in the control system to store the control parameters adjusted by the neural network PD control in each sampling period. The maximum number of registers that can be stored is 500. Whenever the register count reaches 500, the average value of the stored PD control parameters is used as the initial control parameters for the neural network PD control. After the algorithm is turned off, the optimized PD parameters are saved as the initial values ​​for the neural network PD control.

[0119] In this embodiment, the actual motor speed is obtained from the CAN communication. The system checks whether the actual motor speed is greater than 0 and whether it is less than the algorithm exit calibration threshold. If the actual motor speed is greater than 0 and less than the algorithm exit calibration threshold, the anti-shake algorithm is activated. The actual motor speed is transmitted, and a first-order Butterworth bandpass filter is used to filter the motor speed signal to obtain the fluctuation error of the ideal speed signal. This fluctuation error is then input into the RBF neural network to obtain the vehicle's anti-shake torque. This process controls the vehicle's anti-shake performance, thus solving the technical problem of vehicle drive system vibration caused by speed fluctuations and achieving the technical effect of controlling vehicle drive system vibration caused by speed fluctuations.

[0120] Example 3

[0121] According to an embodiment of the present invention, a vehicle anti-shake control device is also provided. It should be noted that this vehicle anti-shake control device can be used to execute a vehicle anti-shake control method as described in Embodiment 1.

[0122] Figure 6This is a schematic diagram of a vehicle anti-shake control device according to an embodiment of the present invention. Figure 6 As shown, the vehicle's anti-shake control device 600 may include: an acquisition unit 601, a first response unit 602, a determination unit 603, and a control unit 604.

[0123] The acquisition unit 501 is used to acquire the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency.

[0124] The first response unit 602 is used to filter the motor speed signal in response to the speed being within the speed threshold range and the speed fluctuation frequency being within the speed fluctuation frequency threshold range, so as to obtain the fluctuation error of the speed signal.

[0125] The determination unit 603 is used to determine the vehicle's anti-shake torque based on the fluctuation error.

[0126] Control unit 604 is used to perform anti-shake control on the vehicle based on anti-shake torque.

[0127] Optionally, the response unit 602 may include: a discretization module for discretizing the Butterworth filter to obtain a target Butterworth filter; and a first input module for inputting the rotational speed signal into the target Butterworth filter to obtain the fluctuation error.

[0128] Optionally, the vehicle's anti-shake control device 600 may further include: a storage unit for storing at least one control parameter in the radial basis function neural network in each sampling period; and a second response unit for averaging the control parameters in response to the number of control parameters being equal to the number of preset parameters, and determining the average value as the initial control parameter in the radial basis function neural network.

[0129] Optionally, the determining unit 603 may include: a determining module for determining the control law in the radial basis function neural network based on the fluctuation error and the initial control parameters; and a second input module for inputting the control law into the radial basis function neural network to obtain the anti-jitter torque.

[0130] Optionally, the determining module may include: a first determining submodule, used to determine the first parameter of the radial basis function neural network based on the fluctuation error, wherein the first parameter is used to characterize the tuning value of the radial basis function neural network; and a second determining submodule, used to determine the control law based on the first parameter, the initial control parameter and the learning rate of the radial basis function neural network.

[0131] Optionally, the vehicle's anti-shake control device 600 may further include: a deletion unit, used to delete a first control parameter from the control parameters and store the control parameters in the radial basis function neural network in the current sampling period to obtain updated target control parameters, wherein the first control parameter is used to characterize the control parameter corresponding to the earliest sampling period in the control parameters; and a third response unit, used to calculate the average value of the target control parameters in response to the number of target control parameters being equal to the number of preset parameters, and to determine the average value as the initial control parameter in the radial basis function neural network.

[0132] In this embodiment, the acquisition unit is used to acquire the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency; the first response unit is used to filter the motor's rotational speed signal to obtain the fluctuation error of the rotational speed signal in response to the rotational speed being within a rotational speed threshold range and the rotational speed fluctuation frequency being within a rotational speed fluctuation frequency threshold range; the determination unit is used to determine the vehicle's anti-shake torque based on the fluctuation error; and the control unit is used to perform anti-shake control on the vehicle based on the anti-shake torque. This solves the technical problem of vehicle drive system vibration caused by rotational speed fluctuation and achieves the technical effect of controlling vehicle drive system vibration caused by rotational speed fluctuation.

[0133] Example 4

[0134] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the vehicle anti-shake control method of Embodiment 1.

[0135] Example 5

[0136] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program is executed by the processor to perform the vehicle anti-shake control method of Embodiment 1.

[0137] Example 6

[0138] According to an embodiment of the present invention, a vehicle is also provided for performing the anti-shake control method of any vehicle in Embodiment 1.

[0139] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0140] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0142] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0145] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for stabilizing vehicle vibration control, characterized in that, include: Obtain the rotational speed of the motor in the vehicle and the corresponding rotational speed fluctuation frequency; In response to the speed being within a speed threshold range and the speed fluctuation frequency being within a speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal; Based on the fluctuation error, the anti-shake torque of the vehicle is determined; Based on the anti-shake torque, the vehicle is subjected to anti-shake control; The method for determining the anti-shake torque of the vehicle based on the fluctuation error includes: determining the control law in the radial basis function neural network based on the fluctuation error and the initial control parameters; inputting the control law into the radial basis function neural network to obtain the anti-shake torque, wherein the initial control parameters are obtained by averaging the control parameters when the number of control parameters in the radial basis function neural network is equal to the number of preset parameters; Determining the control law in the radial basis function neural network based on the fluctuation error and initial control parameters includes: determining a first parameter of the radial basis function neural network based on the fluctuation error, wherein the first parameter is used to characterize the tuning value of the radial basis function neural network; and determining the control law based on the first parameter, the initial control parameters, and the learning rate of the radial basis function neural network.

2. The method according to claim 1, characterized in that, In response to the speed being within a speed threshold range and the speed fluctuation frequency being within a speed fluctuation frequency threshold range, the speed signal of the motor is filtered to obtain the fluctuation error of the speed signal, including: Discretize the Butterworth filter to obtain the target Butterworth filter; The rotational speed signal is input to the target Butterworth filter to obtain the fluctuation error.

3. The method according to claim 1, characterized in that, After filtering the motor speed signal to obtain the fluctuation error of the speed signal in response to the speed being within a speed threshold range and the speed fluctuation frequency being within a speed fluctuation frequency threshold range, the method further includes: Store at least one control parameter in the radial basis function neural network for each sampling period; In response to the fact that the number of control parameters equals the number of preset parameters, the average value of the control parameters is calculated, and the average value is determined as the initial control parameter in the radial basis function neural network.

4. The method according to claim 1, characterized in that, After performing anti-shake control on the vehicle based on the anti-shake torque, the method further includes: The first control parameter in the control parameters is deleted, and the control parameters in the radial basis function neural network in the current sampling period are stored to obtain the updated target control parameters. The first control parameter is used to characterize the control parameter corresponding to the earliest sampling period in the control parameters. In response to the number of target control parameters being equal to the number of preset parameters, the target control parameters are averaged, and the average value is determined as the initial control parameter in the radial basis function neural network.

5. A vehicle anti-shake control device, characterized in that, include: The acquisition unit is used to acquire the rotational speed of the motor in the vehicle and the rotational speed fluctuation frequency corresponding to the rotational speed; The first response unit is configured to filter the motor speed signal in response to the fact that the speed is within the speed threshold range and the speed fluctuation frequency is within the speed fluctuation frequency threshold range, and obtain the fluctuation error of the speed signal. A determining unit is used to determine the anti-shake torque of the vehicle based on the fluctuation error; A control unit is configured to perform anti-shake control on the vehicle based on the anti-shake torque; The determining unit is further configured to determine the control law in the radial basis function neural network based on the fluctuation error and the initial control parameters; input the control law into the radial basis function neural network to obtain the anti-jitter torque, wherein the initial control parameters are obtained by averaging the control parameters when the number of control parameters in the radial basis function neural network is equal to the number of preset parameters; The determining unit is further configured to determine a first parameter of the radial basis function neural network based on the fluctuation error, wherein the first parameter is used to characterize the tuning value of the radial basis function neural network; and to determine the control law based on the first parameter, the initial control parameter and the learning rate of the radial basis function neural network.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the anti-shake control method for the vehicle according to any one of claims 1 to 4.

7. A processor, characterized in that, The processor is used to run a program, wherein the program, when run by the processor, executes the vehicle anti-shake control method according to any one of claims 1 to 4.

8. A vehicle, characterized in that, The vehicle is used to perform the anti-shake control method of the vehicle according to any one of claims 1 to 4.

Images