Multi-motor control method and device for seat, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a multi-motor control method and device for a seat, electronic equipment and a storage medium. The method comprises the following steps: constructing a dynamic characteristic equation of a multi-motor system of a seat based on current running data of a vehicle and body shape information of a passenger on the seat; the multi-motor system comprises a plurality of motors; for each motor, determining a plurality of candidate set point sequences of the motor based on the dynamic characteristic equation of the motor; determining the comprehensive fitness of the plurality of candidate set point sequences of the motor, and determining a target set point sequence in the plurality of candidate set point sequences according to the comprehensive fitness; the target set point sequence comprises a target rotating speed and a target position of the motor; and controlling the multi-motor system according to the target rotating speeds and the target positions of the plurality of motors. The method is used for cooperatively controlling a multi-motor system of the seat in a self-adaptive manner according to an actual application scene, so that the adjustment of the seat conforms to the actual application scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and in particular to a multi-motor control method and device for a seat, an electronic device, and a storage medium. BACKGROUND

[0002] With the development of technology, the seat of a vehicle is becoming more and more intelligent. In order to improve the comfort of driving and riding, the adjustment of the seat is required to meet the needs of users in the use scenario.

[0003] In the related art, each motor in the seat operates according to a set mode. For example, when a passenger triggers adjustment of a backrest, each motor operates according to the operation point timing corresponding to the adjustment mode of the backrest. The flexibility is poor, and the adjustment of the seat cannot meet the needs of the use scenario. SUMMARY

[0004] Embodiments of the present application provide a multi-motor control method and device for a seat, an electronic device, and a storage medium, to adaptively control a multi-motor system of the seat according to an actual application scenario, so that the adjustment of the seat meets the actual application scenario.

[0005] In a first aspect, embodiments of the present application provide a multi-motor control method for a seat, comprising:

[0006] Based on current running data of the vehicle and body information of a passenger on the seat, a dynamic characteristic equation of a multi-motor system of the seat is constructed. The multi-motor system includes multiple motors.

[0007] For each motor, based on the dynamic characteristic equation of the motor, multiple candidate set point sequences of the motor are determined.

[0008] The comprehensive fitness of the multiple candidate set point sequences of the motor is determined, and a target set point sequence is determined in the multiple candidate set point sequences according to the comprehensive fitness. The target set point sequence includes a target speed and a target position of the motor.

[0009] The multi-motor system is controlled according to the target speed and the target position of each motor.

[0010] In a second aspect, embodiments of the present application provide a multi-motor control device for a seat, comprising:

[0011] A dynamic characteristic equation construction module is configured to construct a dynamic characteristic equation of a multi-motor system of a seat based on current running data of a vehicle and body information of a passenger on the seat. The multi-motor system includes multiple motors.

[0012] A first determination module is configured to determine, for each motor, multiple candidate set point sequences of the motor based on the dynamic characteristic equation of the motor.

[0013] The second determining module is configured to determine comprehensive fitness of the multiple candidate set point sequences of the motor, and determine a target set point sequence from the multiple candidate set point sequences according to the comprehensive fitness; the target set point sequence comprises a target rotating speed and a target position of the motor;

[0014] The control module is configured to control the multi-motor system according to the target rotating speed and the target position of each motor.

[0015] In a third aspect, an electronic device is provided, comprising a memory and a processor; the memory stores computer-executable instructions; and the processor executes the computer-executable instructions stored in the memory, so that the processor executes the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0016] In a fourth aspect, a computer-readable storage medium is provided, which stores computer-executable instructions; and the computer-executable instructions are executed by a processor to implement the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0017] In a fifth aspect, a computer program product is provided, which comprises a computer program; and the computer program is executed by a processor to implement the method according to the first aspect and / or various possible implementation manners of the first aspect.

[0018] The method and device for controlling multiple motors of a seat, the electronic device and the storage medium provided by the embodiments of the present application adaptively construct a dynamic characteristic equation of a multi-motor system in a seat according to current running data of a vehicle and body shape information of an occupant on the seat, systematically describe the dynamic behavior of the multi-motor system, so that the control of the multiple motors is collaborative and consistent with the current actual application scenario, determine multiple candidate set point sequences of the motor according to the dynamic characteristic equation, so that the candidate set point sequences have stability, dynamic performance and physical consistency, determine a target set point sequence that has the best comprehensive performance under multiple indexes from the multiple candidate set point sequences according to comprehensive fitness, control the multi-motor system through the target set point sequence of each motor, and improve the control precision and response efficiency of the multi-motor system; adaptively control the multi-motor system of the seat according to the current driving scenario and the body shape of the occupant, so that the adjustment of the seat conforms to the actual application scenario, and the support of the seat to the occupant can offset the influence of the current running state of the vehicle on the body posture of the occupant, and improve the riding comfort. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0020] Figure 1A flowchart illustrating the multi-motor control method for the seat provided in this application;

[0021] Figure 2 A schematic diagram illustrating the determination of the target setpoint sequence using a target optimization model, as provided in this application;

[0022] Figure 3 A schematic diagram of the structure of the multi-motor control system for the seat provided in this application;

[0023] Figure 4 A schematic diagram of the multi-motor control device for the seat provided in this application;

[0024] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0025] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0028] Figure 1 Flowchart of the multi-motor control method for the seat provided in this application Figure 1 Multi-motor control methods for seats can be applied to intelligent vehicle seats; such as Figure 2 As shown, the multi-motor control method for the seat includes:

[0029] S101. Based on the vehicle's current operating data and the body shape information of the occupants in the seats, construct the dynamic characteristic equations of the multi-motor system of the seats; the multi-motor system includes multiple motors.

[0030] Among them, the vehicle's current operating data can reflect the vehicle's driving status; for example, the operating data includes, but is not limited to: vehicle speed, acceleration, yaw rate and roll rate; the occupant's body shape information can reflect the occupant's use of the seat.

[0031] The multi-motor system includes multiple motors; for example, the multiple motors include, but are not limited to: height adjustment motor, backrest tilt motor, seat cushion tilt motor, lumbar support motor, side wing adjustment motor, and leg support motor; it should be noted that the height adjustment motor, backrest tilt motor, seat cushion tilt motor, lumbar support motor, side wing adjustment motor, and leg support motor can each be one or more.

[0032] During vehicle operation, driving conditions affect the body posture of occupants in the seat, with varying degrees of impact depending on body type. Controlling the seat's multi-motor system can mitigate or counteract these effects. For example, during vehicle acceleration, the occupant leans back, and the backrest tilt motor and lumbar support motor are adjusted to increase back and lumbar support. During braking, the occupant leans forward and their thighs slide, requiring adjustments to the backrest tilt motor, lumbar support motor, and leg support motor. When the vehicle turns, the body deviates from the seat centerline, requiring adjustments to the seat cushion tilt motor and side wing adjustment motor to provide lateral support and suppress lateral sliding. When the vehicle travels on bumpy roads with longitudinal acceleration, the height motor is adjusted to counteract the vertical impact on the occupant.

[0033] It should be noted that the above is an example of adjusting the motor under one driving state of the vehicle. It is only used to illustrate the relationship between driving state, occupant body posture and seat motor control. In practical applications, there are complex driving states such as vehicle acceleration and steering, and vehicle steering on bumpy roads. The impact of complex driving states on the occupant's body posture in the seat can also be mitigated or offset by adjusting the multi-motor system.

[0034] Optionally, for each seat in the vehicle, an image of the occupant is acquired using an in-vehicle camera, and the occupant's image is detected using a first body shape detection model to obtain the occupant's body shape information. The first body shape detection model is obtained by training an initial detection model based on occupant image samples and corresponding body shape labels.

[0035] Optionally, for each seat in the vehicle, an image of the occupant on the seat is acquired through an in-vehicle camera, and the pressure exerted by the occupant on the seat is acquired through a pressure sensor on the seat cushion. The occupant's image and pressure are then detected by a second body shape detection model to obtain the occupant's body shape information. The second body shape detection model is obtained by training the initial detection model based on occupant image samples, pressure samples, and corresponding body shape labels.

[0036] Among them, the body size information of the occupants can be: small, medium or large.

[0037] Specifically, the vehicle's current operating data is obtained from the on-board terminal, or through the vehicle's sensors, such as the vehicle's acceleration obtained through the accelerometer, the vehicle speed obtained through the wheel speed sensor, and the yaw rate and roll rate obtained through the gyroscope in the inertial measurement unit.

[0038] Specifically, based on the vehicle's current operating data, the body shape information of the occupants in the seats, and the inherent parameters of the motor system, the inertia matrix and system matrix of the multi-motor system are determined, and the dynamic characteristic equation of the multi-motor system is constructed based on the inertia matrix and system matrix.

[0039] In one optional approach, the operating data includes: vehicle speed, acceleration, yaw rate, and roll rate. Based on the current operating data of the vehicle and the body shape information of the occupants in the seat, a dynamic characteristic equation for the multi-motor system of the seat is constructed, including: inputting the current vehicle speed, acceleration, yaw rate, and roll rate, as well as the body shape information of the occupants in the seat, into a dynamic prediction model to obtain the current inertia coefficients and mechanical inertia coefficients of the multiple motors of the seat; constructing the inertia matrix of the multiple motors based on the current inertia coefficients and mechanical inertia coefficients; determining the system matrix of the multiple motors based on the inherent parameters and operating parameters of the multiple motors; and constructing the dynamic characteristic equation of the multiple motors based on the inertia matrix and the system matrix.

[0040] Specifically, based on the vehicle's current speed, acceleration, yaw rate, roll rate, and the occupants' body shape information, an operating data set is formed. The dynamic characteristics of the operating data set are extracted through a dynamic prediction model, and the dynamic characteristics are processed to obtain the current inertia coefficient and mechanical inertia coefficient of each motor in the multi-motor system.

[0041] The dynamic prediction model is trained on an initial dynamic prediction model based on the operating data set samples and the corresponding current inertia coefficient and mechanical inertia coefficient labels. The operating data set samples include: vehicle speed samples, acceleration samples, yaw rate samples, roll rate samples, and body shape information samples. The operating data set samples are actually collected. The current inertia coefficient and mechanical inertia coefficient labels include the current inertia coefficient and mechanical inertia coefficient labels of each motor in the multi-motor system, which are determined based on the ideal operating state of the multi-motor system under the operating data set samples.

[0042] Specifically, the process of training the initial dynamic prediction model is as follows: input the running data set samples into the initial dynamic prediction model, extract the training dynamic features of the running data set samples through the initial dynamic prediction model, process the training dynamic features to obtain the predicted current inertia coefficient and predicted mechanical inertia coefficient of each motor in the multi-motor system; calculate the loss value based on the predicted current inertia coefficient and predicted mechanical inertia coefficient of each motor, and the current inertia coefficient label and mechanical inertia coefficient label of each motor under the running data set samples, and use the loss value to adjust the parameters of the initial dynamic prediction model.

[0043] The initial dynamic prediction model is iteratively trained in the manner described above until the model converges or the number of training iterations reaches the preset number, thus obtaining the dynamic prediction model.

[0044] Specifically, the current inertia coefficient includes the d-axis current inertia coefficient (e.g., d-axis inductance) and the q-axis current inertia coefficient (e.g., q-axis inductance); for each motor in a multi-motor system, the motor's inertia matrix is ​​constructed based on the motor's d-axis current inertia coefficient, q-axis current inertia coefficient, and mechanical inertia coefficient (e.g., moment of inertia);

[0045] For example, the inertia matrix of the motor is represented as: ;

[0046] in, It is the d-axis current inertia coefficient of the motor. It is the q-axis current inertia coefficient of the motor. It is the mechanical inertia coefficient of the motor.

[0047] For each motor, the inherent parameters of the motor include: inductance, resistance, number of pole pairs, and permanent magnet flux linkage; the electromagnetic equations and mechanical equations of the motor are constructed based on the inherent parameters and operating parameters of the motor, and the system matrix is ​​determined based on the electromagnetic equations and mechanical equations of the motor.

[0048] For example, the electromagnetic equation of the motor is:

[0049] ;

[0050] The mechanical equation of the electric motor is:

[0051] ;

[0052] in, It is the d-axis current. It is the q-axis current. It is the d-axis inductance. It is a q-axis inductor. It is the stator resistance. It is the motor speed. It is the q-axis voltage. It is the d-axis voltage. It is an extreme logarithm. It is a permanent magnet flux chain; It is the moment of inertia. It is the damping coefficient. It is the load torque; among them, d-axis inductance, q-axis inductance, stator resistance, permanent magnet flux linkage, number of pole pairs, moment of inertia and damping coefficient are the inherent parameters of the motor, while d-axis current, q-axis current, d-axis voltage, q-axis voltage and load torque are the current operating parameters of the motor.

[0053] Converting the electromagnetic and mechanical equations into state-variable form yields the system matrix, which is represented as:

[0054] ,in, ;

[0055] The state vector X of the dynamic characteristic equation of the motor is expressed as: .

[0056] The dynamic characteristic equation is expressed as: ;in, , and It is determined based on the elements in the system matrix A.

[0057] in, It is the d-axis inductance. It is a q-axis inductor. It is the stator resistance. It is the motor speed. It is an extreme logarithm. It is a permanent magnet flux chain; It is the moment of inertia. It is the damping coefficient.

[0058] It should be noted that the system matrix A of the motor describes the state variables: , and The relationship between them and pass coupling, and Through electromagnetic torque coupling The change in current affects the dynamic response of the motor. Therefore, the dynamic characteristic equation is essentially an equation between the motor's current and speed.

[0059] In the above embodiments, dynamic characteristic equations are constructed based on the vehicle's current speed, acceleration, yaw rate, roll rate, and the body shape information of the occupants in the seats, as well as the operating parameters of the multi-motor system. This makes the dynamic characteristic equations relevant to the current actual operating scenario, which is an adaptive way of constructing dynamic characteristic equations. This can systematically describe the dynamic behavior of the multi-motor system, comprehensively analyze the response of the multi-motor system in the current scenario, and subsequently achieve adaptive control and optimize dynamic response performance based on the dynamic characteristic equations.

[0060] S102. For each motor, based on the motor's dynamic characteristic equation, determine multiple candidate setpoint sequences for the motor.

[0061] Specifically, for each motor, the dynamic characteristic equation of the motor is solved to obtain the characteristic mode mode of the motor. The characteristic mode mode includes: stability boundary and state coupling relationship; under the constraints of stability boundary and state coupling relationship, multiple candidate setpoint sequences of the motor are generated.

[0062] Specifically, the dynamic characteristic equation of the motor is solved to obtain eigenvalues. These eigenvalues ​​are then arranged in descending order of their real parts to obtain eigenvectors. For each eigenvalue, the time constant, damped oscillation frequency, and damping ratio are calculated based on its real and imaginary parts. The maximum rate of change of rotational speed is calculated based on the time constant and damped oscillation frequency. The stability boundary includes the maximum rate of change of rotational speed. State coupling relationships are calculated based on the eigenvectors; these relationships include ideal current proportionality and ideal electromechanical proportionality.

[0063] Maximum speed change rate Ideal electromechanical ratio and ideal electromechanical ratio Under the constraints, multiple candidate setpoint sequences are generated. The candidate setpoint sequence includes the candidate speed and candidate position of the motor at k time points, represented as: The value of k can be set according to requirements, and this application embodiment does not limit it.

[0064] It should be noted that using the stability boundary as a constraint ensures that the generated candidate setpoint sequence is stable and will not lead to system instability; the information contained in the eigenvalues, such as the time constant and damping ratio, reflects the dynamic response performance of the motor, thus the candidate setpoint sequence has good dynamic performance; the eigenvectors reflect the coupling relationship between state variables, making the candidate setpoint sequence conform to the inherent physical characteristics of the motor.

[0065] S103. Determine the overall fitness of multiple candidate setpoint sequences of the motor, and determine the target setpoint sequence from the multiple candidate setpoint sequences based on the overall fitness; the target setpoint sequence includes the target speed and target position of the motor.

[0066] Among them, the overall fitness of the candidate setpoint sequence can reflect the performance of the candidate setpoint sequence under multiple indicators; the higher the overall fitness value, the better the performance of the candidate setpoint sequence.

[0067] Optionally, for each candidate setpoint sequence of the motor, the fitness of the candidate setpoint sequence under multiple indicators is obtained by weighted summation of the fitness of the candidate setpoint sequence under multiple indicators.

[0068] These indicators include, but are not limited to: seat pressure distribution, energy consumption, smoothness, consistency, and temperature; and comprehensive fitness, which is a comprehensive score reflecting the seat pressure distribution, energy consumption, temperature, smoothness, and consistency performance.

[0069] Optionally, for multiple candidate setpoint sequences of the motor, the multiple candidate setpoint sequences are input into the target optimization model, and the comprehensive fitness of the multiple candidate setpoint sequences is determined by the target optimization model.

[0070] Among the comprehensive fitness of multiple candidate setpoint sequences for the motor, the highest comprehensive fitness is determined, and the setpoint sequence corresponding to the highest comprehensive fitness is taken as the target setpoint sequence for the motor. The target setpoint sequence includes the target speed and target position of the motor at k time points, expressed as: .

[0071] S104. Control the multi-motor system according to the target speed and target position of each motor.

[0072] Specifically, for each motor, control commands are generated based on the target speed and target position of each motor at k time points, and the motor is controlled to run according to the target speed and target position at k time points through the control commands.

[0073] The multi-motor control method for seats provided in this application adaptively constructs dynamic characteristic equations for the multi-motor system in the seat based on the current vehicle operating data and the body shape information of the occupants in the seat. This systematically describes the dynamic behavior of the multi-motor system, enabling coordinated control of multiple motors and conforming to the current actual application scenario. Multiple candidate setpoint sequences for the motors are determined based on the dynamic characteristic equations, ensuring stability, dynamic performance, and physical consistency. Based on comprehensive fitness, the optimal target setpoint sequence with the best overall performance under multiple indicators is determined from the multiple candidate setpoint sequences. By controlling the multi-motor system through the target setpoint sequences of each motor, the control accuracy and response efficiency of the multi-motor system are improved. Furthermore, by adaptively controlling the multi-motor system of the seat according to the current driving scenario and the occupant's body shape, the seat adjustment conforms to the actual application scenario, ensuring that the seat's support for the occupants can offset the influence of the vehicle's current operating state on the occupant's body posture, thus improving riding comfort.

[0074] In some embodiments, for each candidate setpoint sequence of the motor, the seat pressure distribution fitness, energy efficiency thermal management fitness, and smoothness consistency fitness of the candidate setpoint sequence are determined; the seat pressure distribution fitness, energy efficiency thermal management fitness, and smoothness consistency fitness are weighted and summed to obtain the comprehensive fitness of the candidate setpoint sequence.

[0075] Among them, energy efficiency thermal management adaptability includes energy efficiency adaptability and temperature adaptability, and smoothness and consistency adaptability includes smoothness adaptability and consistency adaptability.

[0076] Specifically, for each candidate setpoint sequence, the seat pressure distribution fitness, energy consumption fitness, temperature fitness, smoothness fitness, and consistency fitness of the candidate setpoint sequence are determined based on the candidate rotation speed and candidate position at multiple times in the candidate setpoint sequence. The seat pressure distribution fitness, energy consumption fitness, temperature fitness, smoothness fitness, and consistency fitness are weighted and summed to obtain the comprehensive fitness.

[0077] For example, the overall fitness is calculated according to formula (1).

[0078] Formula (1): .

[0079] in, It is overall adaptability. It is the seat pressure distribution adaptability. It is the weight of the seat pressure distribution adaptability. It is energy adaptability. It is the weight of energy consumption adaptability. It is smoothness fitness. It is the weight of smoothness fitness. It is consistency fitness. It is the weight of consistency fitness. It is temperature adaptability. It is the weight of temperature adaptability. , , , and The specific value can be set according to actual needs.

[0080] In the above embodiments, the overall fitness is determined based on the seat pressure distribution fitness, energy efficiency thermal management fitness, and smoothness consistency fitness of the candidate setpoint sequence, so that the overall fitness can reflect the comprehensive performance of the candidate setpoint sequence in multiple aspects, thereby improving the quality of the target candidate setpoint sequence determined based on the overall fitness.

[0081] In some embodiments, determining the seat pressure distribution fitness, energy efficiency thermal management fitness, and smoothness consistency fitness of the candidate setpoint sequence includes: determining the estimated current and estimated voltage based on the candidate rotational speed and candidate position included in the candidate setpoint sequence; determining the seat pressure distribution fitness based on the estimated current; determining the energy efficiency thermal management fitness based on the estimated voltage and current; and determining the smoothness consistency fitness based on the candidate rotational speed and candidate position.

[0082] Specifically, the candidate setpoint sequence is represented as follows: Based on the candidate rotational speed and candidate position at each moment in the candidate setpoint sequence, determine the estimated current and estimated voltage required to achieve the candidate rotational speed and candidate position; for example, in At any time, according to and , determine implementation and Estimated current required Predicted voltage .

[0083] Specifically, candidate acceleration is calculated based on candidate rotational speed; the required electromagnetic torque is calculated based on candidate acceleration and candidate rotational speed; the reference current in the rotating coordinate system is calculated based on the electromagnetic torque; the reference current in the rotating coordinate system is mapped through candidate positions, i.e., the estimated current is obtained through coordinate transformation and inverse Park transformation; the reference voltage in the rotating coordinate system is calculated based on candidate rotational speed and reference current; the reference voltage in the rotating coordinate system is mapped through candidate positions, i.e., the estimated voltage is obtained through coordinate transformation and inverse Park transformation.

[0084] Based on the estimated current corresponding to the candidate rotation speed and candidate position at each moment, the seat pressure distribution sub-fitness corresponding to the candidate rotation speed and candidate position at each moment is determined. The seat pressure distribution sub-fitness corresponding to multiple moments is summed to obtain the seat pressure distribution fitness, as shown in formula (2).

[0085] Formula (2): ;in, It is the seat pressure distribution adaptability. It is the motor torque constant. It is a conversion factor used to convert torque into a pressure distribution value; express The estimated current at that moment .

[0086] It should be noted that the current directly reflects the load on the motor during operation. If the seat pressure is high, the motor needs a larger current to overcome the pressure. Therefore, the seat pressure distribution can be indirectly determined by the current.

[0087] Based on the estimated voltage and estimated current corresponding to the candidate rotation speed and candidate position at each time moment, the fitness of the energy efficiency thermal management sub-sub ...

[0088] In some embodiments, the energy efficiency thermal management adaptability includes: energy consumption adaptability and temperature adaptability; determining the energy efficiency thermal management adaptability based on the estimated voltage and estimated current includes: determining the energy consumption adaptability based on the estimated voltage and the resistance of the motor; and determining the temperature adaptability based on the estimated current and resistance.

[0089] Specifically, based on the resistance of the motor and the estimated voltage corresponding to the candidate speed and candidate position at each moment, the fitness of the energy consumption at each moment is determined, and the fitness of the energy consumption at multiple moments is summed to obtain the fitness of energy consumption; as shown in formula (3).

[0090] Formula (3): ;

[0091] in, It is energy adaptability. It is the resistance of the motor. express The estimated voltage at that moment .

[0092] Specifically, when current passes through the conductor (motor winding) of the motor, electrical energy is converted into heat energy due to the resistance of the conductor. Based on the resistance of the motor and the estimated current corresponding to the candidate speed and candidate position at each moment, the temperature sub-fitness at each moment is determined. The temperature sub-fitness at multiple moments is summed to obtain the temperature fitness, as shown in formula (4).

[0093] Formula (4): ;

[0094] in, It is temperature adaptability. It is the resistance of the motor. express The estimated current at that moment .

[0095] In the above embodiments, the energy efficiency thermal management adaptability includes energy consumption adaptability and temperature adaptability. Subsequently, considering energy consumption and temperature, the optimal target setpoint sequence is determined, thereby improving the overall performance of the target setpoint sequence.

[0096] In some embodiments, the smoothness-consistency fitness includes: smoothness fitness and consistency fitness; determining the smoothness-consistency fitness based on the candidate rotational speeds and candidate positions included in the candidate setpoint sequence includes: determining the smoothness fitness based on the difference values ​​between multiple candidate rotational speeds and multiple candidate positions included in the candidate setpoint sequence; determining the synchronization error based on the multiple candidate positions included in the candidate setpoint sequence, and determining the consistency fitness based on the synchronization error.

[0097] Specifically, the difference between any two adjacent candidate positions among multiple candidate positions is determined, the difference between any two adjacent candidate rotation speeds among multiple candidate rotation speeds is determined, and the smoothness fitness is determined based on the difference between any two adjacent candidate positions and the difference between any two adjacent candidate rotation speeds, as shown in formula (5).

[0098] Formula (5): ;

[0099] in, It is smoothness fitness. yes The candidate rotational speed corresponding to the given time. yes The candidate rotational speed corresponding to the given time. Time and Adjacent moments; yes Candidate positions corresponding to each time point yes Candidate positions corresponding to each time point.

[0100] Specifically, the position of the uniform axis is determined based on multiple candidate positions, the difference between each candidate position and the position of the uniform axis is calculated, the synchronization error of each candidate position is obtained, and the synchronization error of each candidate position is summed to obtain the consistency fitness, as shown in formula (6).

[0101] Formula (6): ;

[0102] in, It is consistency fitness. It is the position of the uniform-speed principal axis; yes Candidate positions corresponding to each time point.

[0103] In the above embodiments, the smoothness and consistency fitness includes smoothness fitness and consistency fitness. Subsequently, considering the smoothness and consistency of the candidate setpoint sequences, the optimal target setpoint sequence is determined, thereby improving the overall performance of the target setpoint sequence.

[0104] In some embodiments, after determining multiple candidate setpoint sequences for the motor, the method further includes: inputting multiple candidate setpoint sequences, seat pressure distribution weights, energy efficiency thermal management weights, and smoothing consistency weights into the target optimization model to obtain the target setpoint sequence.

[0105] Among them, the energy efficiency thermal management weights include energy consumption weights and temperature weights, and the smoothness and consistency weights include smoothness weights and consistency weights.

[0106] Specifically, multiple candidate setpoint sequences, seat pressure distribution weights, energy consumption weights, temperature weights, smoothness weights, and consistency weights are input into the target optimization model, and the comprehensive fitness of each of the multiple candidate setpoint sequences is obtained through the target optimization model. The seat pressure distribution weights, energy consumption weights, temperature weights, smoothness weights, and consistency weights can be set according to actual needs, and this application embodiment does not limit them.

[0107] It should be noted that the objective optimization model is as follows: Figure 3 As shown, it includes an embedding layer, a fusion layer, and a decoder.

[0108] Seat pressure distribution weight Energy consumption weight Temperature weighting Smoothness weights Consistency weight Construct the weight vector: This weight vector can represent the importance of seat pressure distribution, energy consumption, temperature, smoothness, and consistency, for example, The values ​​[0.1, 0.7, 0.1, 0.05, 0.05] indicate that energy consumption is of high importance during the optimization process; for example, The value [0.2, 0.2, 0.2, 0.2, 0.2] indicates that balanced optimization is performed during the optimization process.

[0109] The weight vector and multiple candidate setpoint sequences are input into the embedding layer of the target optimization model to obtain the weight features corresponding to the weight vector and the setpoint sequence features corresponding to the multiple candidate setpoint sequences. The weight features are fused with the multiple setpoint sequence features through the fusion layer to obtain multiple fused features. The multiple fused features are input into the decoder to obtain the target setpoint sequence.

[0110] The training process of the objective optimization model includes:

[0111] Weight vector samples are obtained by sampling on a 5-dimensional standard unit simplex; a multi-objective optimizer for the motor is constructed, and the Pareto optimal solution is obtained by solving the weight vector samples and multiple setpoint sequence samples through the multi-objective optimizer; training data is constructed: (weight vector samples; multiple setpoint sequence samples; Pareto optimal solution); multiple training data are obtained through the above method.

[0112] One training iteration includes: inputting weight vector samples and multiple setpoint sequence samples into the initial optimization model to obtain the predicted optimal solution; calculating the mean squared error loss value based on the predicted optimal solution and the Pareto optimal solution; and adjusting the parameters of the initial optimization model based on the mean squared error loss value.

[0113] In the above embodiments, the target optimization model can quickly obtain an accurate sequence of target setpoints, improving the adjustment efficiency of the multi-motor system. Furthermore, during application, the target optimization model can be continuously updated based on the actual operating parameters of the multi-motor system. For example, the target optimization model can be updated and trained in the cloud, and the target optimization model deployed on the vehicle's seats can be remotely upgraded via wireless network, enabling continuous and accurate control of the multi-motor system.

[0114] In some embodiments, the motor is a DC motor; controlling the multi-motor system according to the target speed and target position of each of the multiple motors includes: processing the target speed and target position of each of the multiple DC motors to obtain the pulse width modulation waveform of each of the multiple DC motors; and controlling the multiple DC motors using the pulse width modulation waveform of each of the multiple DC motors.

[0115] Specifically, when the DC motor is a brushless motor, the target speed and target position are converted into SVPWM (Space Vector Pulse Width Modulation) waveforms using a motor vector control model, and the brushless motor is controlled through the SVPWM waveforms; when the DC motor is a brushed motor, the target speed and target position are directly converted into PWM (Pulse Width Modulation) waveforms, and the brushed motor is controlled through the PWM waveforms.

[0116] After controlling the multi-motor system according to the target speed and target position of each of the multiple motors, the sampling resistor retrieval information is obtained to obtain the actual speed and actual position of the multiple motors. Then, the multi-motor control method of the seat provided in the embodiment of this application is used to control the multiple motors in the next round.

[0117] In a specific example, the seat's multi-motor system, such as Figure 3 As shown, the multi-motor system includes an optimization algorithm module, a brushless motor control module, and a brushed motor control module.

[0118] The optimization algorithm module is used to construct the dynamic characteristic equation of the multi-motor system of the seat based on the current operating data of the vehicle and the body shape information of the occupants in the seat, and determine the candidate setpoint sequence according to the dynamic characteristic equation. The optimal target setpoint sequence is determined among multiple candidate setpoint sequences. This can be done by calculating the comprehensive fitness of multiple candidate setpoint sequences, or by using the trained target optimization model to determine the optimal target setpoint sequence among multiple candidate setpoint sequences.

[0119] When the DC motor is a brushless motor, the target setpoint sequence is the target speed and target position of multiple brushless motors; when the DC motor is a brushed motor, the target setpoint sequence is the target speed and target position of multiple brushed motors.

[0120] The brushless motor control module receives the target speed of multiple brushless motors through a PI regulator. During the control process, it performs overall control of multiple brushless motors based on the deviation between the actual speed and the target speed. It determines the d-axis and q-axis current components based on the speed, and transmits the control signal to the inverter module after coordinate transformation and Park inverse transformation to achieve control.

[0121] The brushed motor control module uses a pre-drive plus H-bridge approach to receive the target speeds of multiple brushed motors, convert them into PWM waveforms, and control the opening and closing of the H-bridge based on the frequency and duty cycle of the PWM waveforms.

[0122] refer to Figure 4For brushless motor control: The PID (Proportional-Derivative-Integral) controller receives the target signal and the actual signals of the multi-motor system. The target signal is obtained from the target setpoint sequence output by the optimization algorithm module, such as the d-axis target current (Idref) and the q-axis target current (Iqref). The actual signals are the actual d-axis current and q-axis current. The PID controller outputs control voltages Vd and Vq, which are converted by the Park inverse transform module to obtain the voltage in the stationary coordinate system. and The SVPWM (Space Vector Pulse Width Modulation) module adjusts according to voltage. and The output PWM signal is used to drive the PWM inverter, which in turn drives the power switches (MD1, MD2, etc.) to output three-phase voltage to the brushless motor.

[0123] The Clark transform module receives the phase current and converts it into a current in a stationary coordinate system. The Park transform module receives the current in the stationary coordinate system output by the Clark transform module and converts it into a rotating coordinate system signal to obtain the actual d-axis current and q-axis current, which are then fed back to the optimization algorithm module and the PID controller.

[0124] For brushed motor control: The target setpoint sequence output by the optimization algorithm module is converted into a PMW signal by the PMW module. The PMW signal controls the switching of the H-bridge (MD1, MD2, etc.) and outputs three-phase voltage to the brushed motor.

[0125] The AD (Analog-to-Digital) sampling module collects the ripple current, converts it into a digital signal, and feeds it back to the optimization algorithm module.

[0126] The multi-motor control method for seats provided in this application adaptively constructs dynamic characteristic equations for the multi-motor system in the seat based on the current vehicle operating data and the body shape information of the occupants in the seat. This systematically describes the dynamic behavior of the multi-motor system, enabling coordinated control of multiple motors and conforming to the current actual application scenario. Multiple candidate setpoint sequences for the motors are determined based on the dynamic characteristic equations, ensuring stability, dynamic performance, and physical consistency. Based on comprehensive fitness, the optimal target setpoint sequence with the best overall performance under multiple indicators is determined from the multiple candidate setpoint sequences. By controlling the multi-motor system through the target setpoint sequences of each motor, the control accuracy and response efficiency of the multi-motor system are improved. Furthermore, by adaptively controlling the multi-motor system of the seat according to the current driving scenario and the occupant's body shape, the seat adjustment conforms to the actual application scenario, ensuring that the seat's support for the occupants can offset the influence of the vehicle's current operating state on the occupant's body posture, thus improving riding comfort.

[0127] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0128] Figure 4 A schematic diagram of the multi-motor control device for the seat provided in this application is shown below. Figure 5 As shown, the multi-motor control device 40 for the seat provided in this embodiment includes:

[0129] The dynamic characteristic equation construction module 401 is used to construct the dynamic characteristic equation of the multi-motor system of the seat based on the current operating data of the vehicle and the body shape information of the occupants in the seat; the multi-motor system includes multiple motors.

[0130] The first determining module 402 is used to determine a sequence of multiple candidate setpoints for each motor based on the motor's dynamic characteristic equation.

[0131] The second determining module 403 is used to determine the comprehensive fitness of multiple candidate setpoint sequences of the motor, and to determine the target setpoint sequence from the multiple candidate setpoint sequences based on the comprehensive fitness; the target setpoint sequence includes the target speed and target position of the motor.

[0132] The control module 404 is used to control the multi-motor system according to the target speed and target position of each of the multiple motors.

[0133] In some embodiments, the operating data includes: vehicle speed, acceleration, yaw rate and roll rate;

[0134] The dynamic characteristic equation construction module 401 is used to input the vehicle's current speed, acceleration, yaw rate, and roll rate, as well as the body shape information of the occupants in the seat, into the dynamic prediction model to obtain the current inertia coefficients and mechanical inertia coefficients of multiple motors of the seat; construct the inertia matrix of multiple motors based on the current inertia coefficients and mechanical inertia coefficients of multiple motors; determine the system matrix of multiple motors based on the inherent parameters and operating parameters of multiple motors; and construct the dynamic characteristic equations of multiple motors based on the inertia matrix and system matrix of multiple motors.

[0135] In some embodiments, the second determining module 403 is used to determine the seat pressure distribution fitness, energy efficiency thermal management fitness, and smooth consistency fitness of each candidate setpoint sequence of the motor; and to perform a weighted summation of the seat pressure distribution fitness, energy efficiency thermal management fitness, and smooth consistency fitness to obtain the comprehensive fitness of the candidate setpoint sequence.

[0136] In some embodiments, the second determining module 403 is configured to determine the estimated current and estimated voltage based on the candidate rotational speed and candidate position included in the candidate setpoint sequence; determine the seat pressure distribution fitness based on the estimated current; determine the energy efficiency thermal management fitness based on the estimated voltage and estimated current; and determine the smoothness consistency fitness based on the candidate rotational speed and candidate position included in the candidate setpoint sequence.

[0137] In some embodiments, the energy efficiency thermal management adaptability includes: energy consumption adaptability and temperature adaptability; the second determining module 403 is used to determine the energy efficiency thermal management adaptability based on the estimated voltage and the estimated current, including: determining the energy consumption adaptability based on the estimated voltage and the resistance of the motor; and determining the temperature adaptability based on the estimated current and the resistance.

[0138] In some embodiments, the smoothness and consistency fitness includes: smoothness fitness and consistency fitness; the second determining module 403 is used to determine the smoothness fitness based on the difference values ​​between multiple candidate rotation speeds and multiple candidate positions included in the candidate setpoint sequence; determine the synchronization error based on the multiple candidate positions included in the candidate setpoint sequence; and determine the consistency fitness based on the synchronization error.

[0139] In some embodiments, the multi-motor control device for the seat further includes: a third determining module, used to input multiple candidate setpoint sequences, seat pressure distribution weights, energy efficiency thermal management weights and smoothing consistency weights into the target optimization model to obtain the target setpoint sequence.

[0140] In some embodiments, the motor is a DC motor; the control module 404 is used to process the target speed and target position of each of the multiple DC motors to obtain the pulse width modulation waveform of each of the multiple DC motors; and to control the multiple DC motors through the pulse width modulation waveform of each of the multiple DC motors.

[0141] The multi-motor control device for the seat provided in this embodiment can execute the multi-motor control method for the seat provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0142] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. ​As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0143] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0144] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0145] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0146] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0147] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0148] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0149] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0150] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0151] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0152] The division of units is merely a logical functional division; 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 coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0153] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] In addition, 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.

[0155] If a function 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, or the part that contributes to the prior art, or a 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, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0157] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A multi-motor control method for a seat, characterized in that, include: Based on the vehicle's current operating data and the body shape information of the occupants in the seats, the dynamic characteristic equations of the multi-motor system of the seats are constructed. The multi-motor system includes multiple motors; For each motor, based on the dynamic characteristic equation of the motor, a sequence of multiple candidate setpoints for the motor is determined; Determine the overall fitness of the plurality of candidate setpoint sequences of the motor, and determine the target setpoint sequence from the plurality of candidate setpoint sequences based on the overall fitness; The target setpoint sequence includes the target speed and target position of the motor; The multi-motor system is controlled according to the target speed and target position of each of the multiple motors.

2. The method according to claim 1, characterized in that, The operational data includes: vehicle speed, acceleration, yaw rate, and roll rate; The dynamic characteristic equations of the seat's multi-motor system are constructed based on the vehicle's current operating data and the body shape information of the occupants in the seat, including: The vehicle's current speed, acceleration, yaw rate, and roll rate, as well as the body shape information of the occupants in the seats, are input into the dynamic prediction model to obtain the current inertia coefficient and mechanical inertia coefficient of multiple motors in the seats. Based on the current inertia coefficient and the mechanical inertia coefficient of the multiple motors, an inertia matrix of the multiple motors is constructed; The system matrix of multiple motors is determined based on their inherent parameters and operating parameters. The dynamic characteristic equations of multiple motors are constructed based on the inertia matrix and the system matrix of the multiple motors.

3. The method according to claim 1, characterized in that, The determination of the overall fitness of the plurality of candidate setpoint sequences of the motor includes: For each candidate setpoint sequence of the motor, determine the seat pressure distribution adaptability, energy efficiency thermal management adaptability, and smoothness consistency adaptability of the candidate setpoint sequence; The weighted sum of the seat pressure distribution fitness, the energy efficiency thermal management fitness, and the smoothness consistency fitness is used to obtain the comprehensive fitness of the candidate setpoint sequence.

4. The method according to claim 3, characterized in that, The determination of the seat pressure distribution fitness, energy efficiency thermal management fitness, and smoothness consistency fitness of the candidate setpoint sequence includes: Based on the candidate rotational speed and candidate position included in the candidate setpoint sequence, the estimated current and estimated voltage are determined; The seat pressure distribution suitability is determined based on the estimated current. The energy efficiency thermal management suitability is determined based on the estimated voltage and the estimated current. Based on the candidate rotational speeds and candidate positions included in the candidate setpoint sequence, a smooth and consistent fitness is determined.

5. The method according to claim 4, characterized in that, The energy efficiency thermal management adaptability includes: energy consumption adaptability and temperature adaptability; The step of determining the energy efficiency thermal management suitability based on the estimated voltage and the estimated current includes: Based on the estimated voltage and the resistance of the motor, the energy consumption adaptability is determined; The temperature adaptability is determined based on the estimated current and the resistance.

6. The method according to claim 4, characterized in that, The smoothness-consistency fitness includes: smoothness fitness and consistency fitness; The step of determining the smooth consistency fitness based on the candidate rotation speed and candidate position included in the candidate setpoint sequence includes: Based on the difference values ​​between multiple candidate rotational speeds and multiple candidate positions included in the candidate setpoint sequence, the smoothness fitness is determined; The synchronization error is determined based on the multiple candidate positions included in the candidate setpoint sequence, and the consistency fitness is determined based on the synchronization error.

7. The method according to claim 1, characterized in that, After determining the sequence of multiple candidate setpoints for the motor, the method further includes: The multiple candidate setpoint sequences, seat pressure distribution weights, energy efficiency thermal management weights, and smoothing consistency weights are input into the target optimization model to obtain the target setpoint sequence.

8. The method according to any one of claims 1 to 7, characterized in that, The motor is a DC motor; the control of the multi-motor system based on the target speed and target position of each of the multiple motors includes: The target speed and target position of each of the plurality of DC motors are processed to obtain the pulse width modulation waveform of each of the plurality of DC motors; The multiple DC motors are controlled by their respective pulse width modulation waveforms.

9. A multi-motor control device for a seat, characterized in that, include: The dynamic characteristic equation construction module is used to construct the dynamic characteristic equation of the seat's multi-motor system based on the vehicle's current operating data and the body shape information of the occupants in the seat. The multi-motor system includes multiple motors; The first determining module is used to determine a sequence of multiple candidate setpoints for each motor based on the dynamic characteristic equation of the motor. The second determining module is used to determine the comprehensive fitness of the plurality of candidate setpoint sequences of the motor, and to determine the target setpoint sequence from the plurality of candidate setpoint sequences based on the comprehensive fitness. The target setpoint sequence includes the target speed and target position of the motor; The control module is used to control the multi-motor system according to the target speed and target position of each of the multiple motors.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 8.

12. A computer program product, characterized in that, Includes computer execution instructions, which, when executed by a processor, implement the method as described in any one of claims 1 to 8.

Images