A method for dynamically adjusting the shape and position of a car seat surface

Abstract

The application discloses a kind of dynamic adjustment method of car seat chair surface shape and position, it is first by human-chair coupling model and human body shape data acquisition current user corresponding optimal seat posture, based on the seat parameter value adjustment of optimal seat posture chair surface shape and position of car seat;On this basis, every interval setting length, then obtain the car seat pressure characteristic data of current user within preset time length, and based on the fine adjustment of current seat posture of car seat pressure characteristic data;By bayesian optimization algorithm, the objective function of car seat pressure characteristic data optimization construction is obtained, and the optimal car seat parameter value of objective function output is obtained, and based on optimal car seat parameter value adjustment car seat, it is realized to the individualization adjustment of car seat based on the body characteristics of passenger, and on this basis, active adjustment of car seat chair surface shape and position in the process of user driving is realized.

Description

Technical Field

[0001] This invention relates to the field of automotive seat adjustment, and more particularly to a method for dynamically adjusting the shape and position of an automotive seat surface. Background Technology

[0002] Traditional car seats are usually statically designed and cannot be personalized according to the user's body characteristics (body shape), which may cause discomfort and health problems after sitting for a long time.

[0003] In addition, commercial vehicle seats are often used by truck drivers and bus drivers who need to drive long distances. When driving long distances, a person's body is in a static position for a long time, which leads to stagnation of blood circulation and causes problems such as muscle fatigue and stiffness. From a medical point of view, this is caused by ischemia, which leads to insufficient blood supply to a certain part of the body. In response, a person will naturally change their body position. Even slight movement will change blood circulation and cause congestion in the affected area. However, when driving a vehicle, a person cannot actively respond.

[0004] To address this technical problem, this invention first enables personalized adjustments to car seats based on the user's physical characteristics, and then actively adjusts the seat profile during passenger use by fully considering human biomechanical factors, thereby improving the long-distance comfort of commercial vehicle drivers. Summary of the Invention

[0005] To achieve personalized adjustments to car seats based on user body characteristics, and to intelligently and proactively adjust the seat surface shape and position during user use, this invention proposes a dynamic adjustment method for the seat surface shape and position of a car seat, comprising:

[0006] S1: Based on the biomechanical analysis model, a human-chair coupling model is established using the design parameters of the chair and human body parameter data;

[0007] S2: Obtain the car seat pressure characteristic data within the current user's preset time period, and obtain the human body shape data corresponding to the current user based on the car seat pressure characteristic data. Obtain the optimal seat posture corresponding to the current user based on the human-chair coupling model and human body shape data. Adjust the seat surface shape and position of the car seat based on the seat parameter values ​​of the optimal seat posture.

[0008] S3: At set intervals, acquire the car seat pressure characteristic data within the current user's preset time period, and fine-tune the current seat posture based on the car seat pressure characteristic data. The current seat posture is the optimal seat posture or the optimal fine-tuned seat posture corresponding to the last fine-tuning, specifically including:

[0009] S31: Construct an objective function using the musculoskeletal torque and muscle activation values ​​under normal conditions and the car seat parameter values ​​to be adjusted. Optimize the objective function using the car seat pressure feature data through a Bayesian optimization algorithm to obtain the optimal car seat parameter values ​​output by the objective function, which is the optimal fine-tuning of the seat posture.

[0010] S32: Adjust the shape and position of the car seat surface based on optimal fine-tuning of seat posture.

[0011] Furthermore, step S2 specifically includes:

[0012] Obtain car seat pressure characteristic data within the current user's preset time period;

[0013] By mapping human body shape to car seat pressure feature data, and establishing a relationship model between car seat pressure feature data and human body shape, the human body shape data corresponding to the current user can be predicted through the relationship model.

[0014] Multiple sets of human body size data are acquired, with each set corresponding to a user. Based on the human-chair coupling model, simulation calculations and biomechanical analyses are performed on each set of human body size data in sequence to read the skeletal torque and muscle activation values ​​of the corresponding user's musculoskeletal system. The optimal chair posture corresponding to each set of human body size data is then constructed based on the skeletal torque and muscle activation values.

[0015] The system matches the current user's body shape data with the body size data set. When a body size data set matches the current user's body shape data, the system obtains the optimal seat posture corresponding to that body size data set.

[0016] Adjust the shape and position of the car seat surface based on the car seat parameter values ​​corresponding to the optimal seat posture.

[0017] Furthermore, the vehicle seat pressure characteristic data includes:

[0018] Maximum pressure, Average pressure, contact area A, pressure gradient G, and static pressure distribution SPD%; wherein, the pressure gradient G includes circular pressure gradient and linear pressure gradient;

[0019] The formula for calculating the static pressure distribution is: ;

[0020] In the formula, n is the total number of pressure points with non-zero values. Let be the pressure value corresponding to the i-th pressure point.

[0021] Furthermore, in step S31, the formula expression for the objective function is: ;

[0022] In the formula, X represents the car seat parameter value corresponding to the optimal fine-tuning of the seat posture in the last fine-tuning; This indicates the car seat parameter value to be adjusted, which corresponds to the current seat posture. , is the covariance function, representing the difference in changes in skeletal torque and muscle activation values ​​after changes in the car seat pressure characteristic data between the last fine-tuning and the current adjustment; This is a mean function, representing the musculoskeletal torque and muscle activation values ​​of a user in a normal state; It is a Gaussian process regression model; This represents the optimal pressure difference, which includes the optimal car seat parameter values ​​for the current adjustment.

[0023] Furthermore, in step S31, the objective function is optimized using the car seat pressure feature data through a Bayesian optimization algorithm, specifically including:

[0024] S311: Select the initial pressure point from the pressure points of the car seat pressure characteristic data. And at that point, an experiment was conducted to obtain the value of the objective function;

[0025] S312: Using experimental data corresponding to the characteristic data of car seat pressure, construct a Gaussian process regression model to obtain the posterior distribution of the objective function. ;in , where n represents the total number of pressure points with non-zero values. This represents the output value of the objective function. D represents the sample set of existing experimental data, and D represents the dataset, which is used to store experimental data that have been tested.

[0026] S313: In parameter space In the process, a sampling strategy is used to select the next experimental point. And an experiment was conducted at that point to obtain the value of the objective function. ;in Space for storing car seat parameter values, ;

[0027] S314: New experimental points Add to existing experimental data. In this process, the posterior distribution of the objective function is updated using a Gaussian process regression model;

[0028] S315: Repeat steps S313 and S314 until the predetermined number of experiments is reached or the Gaussian process regression model converges.

[0029] Furthermore, the skeletal torque includes: cumulative muscle force, normal muscle force, and muscle shear force; in step S2, the formula for constructing the optimal seat posture is: ;

[0030] In the formula, CMA represents cumulative muscle force, CNF represents muscle force under normal conditions, CSF represents muscle shear force, and LDDFF represents muscle activation value, i.e., the optimal human biomechanical state.

[0031] Furthermore, in step S2, the model for the mapping between car seat pressure characteristic data and human body shape is defined by the following formula: ;

[0032] In the formula, MLP represents a multilayer perceptron neural network, P represents car seat pressure feature data, and h,w represents predicted human body shape data, where h represents the current user's height and w represents the current user's weight.

[0033] Furthermore, the human body size data set includes: height and weight; in step S2, the formula for obtaining the optimal seat posture is: ;

[0034] In the formula, h represents the current user's height, w represents the current user's weight, h1 represents the height in the human body size data set, and w1 represents the weight in the human body size data set.

[0035] Furthermore, in step S1, the design parameters of the seat include: the design position of the seat, H point, heel point, footrest point, seat cushion departure point, backrest departure point, steering wheel and eyeball position;

[0036] The human body parameter data includes height, shoulder height, shoulder width, and weight corresponding to various body types.

[0037] Furthermore, the automotive seat parameter values ​​include: the seat's fore-and-aft position, height position, backrest position, the inflation / deflation volume of the seat lumbar airbag, backrest airbag, and seat cushion airbag, and the seat surface pressure of each airbag at the corresponding inflation / deflation volume.

[0038] Compared with the prior art, the present invention has at least the following beneficial effects:

[0039] (1) The present invention first obtains the optimal seat posture corresponding to the current user through the human-chair coupling model and human body shape data, and adjusts the seat surface shape and position of the car seat based on the seat parameter value of the optimal seat posture; on this basis, at each set time interval, the car seat pressure feature data within the current user's preset time period is obtained, and the current seat posture is fine-tuned based on the car seat pressure feature data: the objective function constructed by the car seat pressure feature data is optimized using the Bayesian optimization algorithm to obtain the optimal car seat parameter value output by the objective function, which is the optimal fine-tuned seat posture, and the seat surface shape and position of the car seat are adjusted based on the optimal fine-tuned seat posture. It realizes the personalized adjustment of the car seat based on the passenger's body characteristics, and on this basis, it realizes the active adjustment of the car seat surface shape and position using the Bayesian optimization algorithm at each set time interval during the user's driving or use, thereby changing the human blood circulation and improving the user's fatigue.

[0040] (2) The present invention optimizes the objective function using the pressure feature data of car seats through the Bayesian optimization algorithm. During the optimization process, the optimization is completed when the predetermined number of experiments is reached or the Gaussian process regression model converges, which greatly improves the accuracy of the car seat parameter values ​​corresponding to the optimal fine-tuning of the seat posture.

[0041] (3) This invention performs simulation calculations and biomechanical analysis on each set of human body size data to read the skeletal torque and muscle activation values ​​of the corresponding user's skeletal muscle system, thereby constructing the optimal seat posture corresponding to each set of human body size data. By obtaining the current user's car seat pressure characteristic data, a relationship model between the car seat pressure characteristic data and the human body shape is established. The relationship model is used to predict the current user's corresponding human body shape data. When there is a human body size data set that matches the current user's corresponding human body shape data, the optimal seat posture corresponding to that human body size data set is obtained. The car seat is adjusted based on the car seat parameter values ​​of the optimal seat posture. It applies human body size data to the construction of the optimal seat posture, fully considers the factors of human biomechanics, and obtains the optimal seat posture corresponding to the current user through matching. It realizes personalized adjustment of the car seat based on the user's human body shape data and human biomechanical factors, which greatly improves the user's riding comfort.

[0042] (4) By pre-constructing the optimal seat posture corresponding to each group of human body size data, the present invention adjusts the seat in a matching manner when the user sits, which greatly improves the adjustment speed of the seat. Attached Figure Description

[0043] Figure 1 A flowchart illustrating a method for dynamically adjusting the shape and position of a car seat surface;

[0044] Figure 2 A 3D diagram of the human-chair coupling model. Implementation

[0045] The following are specific embodiments of the present invention, which are described in conjunction with the accompanying drawings. However, the present invention is not limited to these embodiments. Example

[0046] To achieve personalized adjustments to car seats based on user body characteristics, and to intelligently and proactively adjust the seat surface shape and position during user use, such as... Figure 1 As shown, this invention proposes a method for dynamically adjusting the shape and position of an automobile seat surface, comprising:

[0047] S1: Based on a biomechanical analysis model, a system is established using the design parameters of the seat and human body parameter data, such as... Figure 2 The human-chair coupling model shown;

[0048] In step S1, the design parameters of the seat include: the design position of the seat, H point, heel point, footrest point, seat cushion departure point, backrest departure point, steering wheel and eyeball position;

[0049] The human body parameter data includes height, shoulder height, shoulder width, and weight corresponding to various body types.

[0050] S2: Obtain the car seat pressure characteristic data within the current user's preset time period, and obtain the human body shape data corresponding to the current user based on the car seat pressure characteristic data. Obtain the optimal seat posture corresponding to the current user based on the human-chair coupling model and human body shape data. Adjust the seat surface shape and position of the car seat based on the seat parameter values ​​of the optimal seat posture.

[0051] The S2 step specifically includes:

[0052] After a user uses the car seat, the system acquires the car seat pressure characteristic data for the current user over a preset time period. Specifically, this includes acquiring the car seat pressure data for the current user over a preset time period, wherein the car seat pressure data includes the pressure values ​​corresponding to each pressure point on the car seat; and the maximum pressure in the car seat pressure characteristic data. With average pressure The pressure values ​​are obtained by measuring the pressure at various pressure points on the car seat.

[0053] The pressure characteristic data of the car seat is obtained by deploying a flexible fabric pressure sensor on the foam surface of the car seat.

[0054] The automotive seat pressure characteristic data includes:

[0055] Maximum pressure average pressure The contact area A, pressure gradient G, and static pressure distribution SPD% are defined as follows: The pressure gradient G includes circular pressure gradients and linear pressure gradients; the linear pressure gradient mainly describes the pressure distribution characteristics between the ischial tuberosities.

[0056] The formula for calculating the static pressure distribution is: ;

[0057] In the formula, n is the total number of pressure points with non-zero values. Let be the pressure value corresponding to the i-th pressure point.

[0058] It can be used to calculate pressure distribution under static and dynamic environments; the smaller the value, the more uniform the pressure distribution. In this embodiment, the formula for calculating the linear pressure gradient is: ;

[0059] In the formula, ;

[0060] in, This indicates the pressure gradient on the lateral side of the right ischium. This indicates the pressure gradient on the lateral side of the left ischium. This indicates the pressure gradient on the medial side of the right ischium. This indicates the pressure gradient on the medial side of the left ischium; This represents the pressure gradient on the outside. The pressure gradient on the inner side represents the rate of pressure change in the ischial tuberosity region; the smaller the value, the more uniform the pressure distribution.

[0061] By mapping human body shape to car seat pressure feature data, and establishing a relationship model between car seat pressure feature data and human body shape, the human body shape data corresponding to the current user can be predicted through the relationship model.

[0062] In step S2, the model for the mapping between car seat pressure characteristic data and human body shape is defined by the following formula: ;

[0063] In the formula, MLP represents a multilayer perceptron neural network, P represents car seat pressure feature data, and h and w represent predicted human body shape data, where h represents the current user's height and w represents the current user's weight.

[0064] It should be noted that in this embodiment, the mapping of human body shape is specifically implemented using a Multi-layer Perceptron (MLP) neural network. An MLP typically consists of multiple fully connected layers, each containing a set of neurons and corresponding weights. During training, the model automatically learns how to predict output data based on input data, optimizing prediction accuracy by adjusting the weights between neurons. In this embodiment, the MLP calculates the output value based on the input car seat pressure feature data. The output value of each neuron is obtained by weighted summation of the output values ​​of the neurons in the previous layer, followed by a non-linear mapping using an activation function. Finally, the model's output value represents the predicted user (passenger) height and weight.

[0065] Multiple sets of human body size data are acquired, with each set corresponding to a user. Based on the human-chair coupling model, simulation calculations and biomechanical analyses are performed on each set of human body size data to read the skeletal torque and muscle activation values ​​of the corresponding user's musculoskeletal system (the data obtained from the human body size data here are the skeletal torque and muscle activation values ​​in the non-fatigue state, i.e., the normal state). The optimal chair posture corresponding to each set of human body size data is constructed based on the skeletal torque and muscle activation values.

[0066] It should be noted that the multiple sets of human body size data obtained in this embodiment basically cover the human body sizes of all adults. In addition, after a person is seated and stabilized in a car seat, the skeletal torque and muscle activation values ​​are generally within the normal range for the first 20 minutes.

[0067] The human body size data set includes: height, weight, etc.;

[0068] The skeletal torque includes: cumulative muscle force, normal muscle force, and muscle shear force; in step S2, the formula for constructing the optimal seat posture is: ;

[0069] In the formula, CMA represents cumulative muscle force, CNF represents muscle force under normal conditions, CSF represents muscle shear force, and LDDFF represents muscle activation value, i.e., the optimal human biomechanical state.

[0070] The system matches the current user's body shape data with the body size data set. When a body size data set matches the current user's body shape data, the system obtains the optimal seat posture corresponding to that body size data set.

[0071] It should be noted that, in this embodiment, after constructing the optimal seat posture corresponding to each set of human body size data, during application, when a user (or passenger) sits in the car seat, the predicted human body shape data corresponding to the current user is directly matched with the human body size data set. If there is no human body size data set that matches the current user's human body shape data, simulation calculations and biomechanical analysis are performed on the user's human body shape data to read the skeletal torque and muscle activation values ​​in the user's corresponding musculoskeletal system, and the optimal seat posture corresponding to the user is constructed based on the skeletal torque and muscle activation values. The car seat is then adjusted according to the optimal seat posture.

[0072] In step S2, the formula for obtaining the optimal seat posture is: ;

[0073] In the formula, h represents the current user's height, w represents the current user's weight, h1 represents the height in the human body size data set, and w1 represents the weight in the human body size data set.

[0074] Adjust the shape and position of the car seat surface based on the car seat parameter values ​​corresponding to the optimal seat posture.

[0075] The automotive seat parameter values ​​include: the seat's fore-and-aft position, height position, backrest position, the inflation / deflation volume of the seat lumbar airbag, backrest airbag, and seat cushion airbag, and the seat surface pressure of each airbag at the corresponding inflation / deflation volume.

[0076] This invention uses simulation calculations and biomechanical analysis on each set of human body size data to read the skeletal torque and muscle activation values ​​of the corresponding user's musculoskeletal system, thereby constructing the optimal seat posture corresponding to each set of human body size data. It establishes a mapping model between car seat pressure characteristic data and human body shape by acquiring the current user's car seat pressure characteristic data. This model predicts the current user's corresponding human body shape data, and when a human body size data set matches the current user's corresponding human body shape data, it obtains the optimal seat posture corresponding to that human body size data set. Based on the optimal seat posture's parameter values, the car seat is adjusted. By applying human body size data to the construction of the optimal seat posture, fully considering human biomechanical factors, and obtaining the optimal seat posture for the current user through matching, this invention achieves personalized adjustments to the car seat based on the user's human body shape data and human biomechanical factors, greatly improving the user's riding comfort.

[0077] S3: At each set interval (in this embodiment, it can be set to 20 minutes; after the commercial vehicle enters long-distance driving mode, it is adjusted every 20 minutes to represent biomechanical monitoring of fatigue, thereby continuously improving driver fatigue), the car seat pressure characteristic data within the current user's preset time period is obtained, and the current seat posture is fine-tuned based on the car seat pressure characteristic data. The current seat posture is the optimal seat posture or the optimal fine-tuned seat posture corresponding to the last fine-tuning, specifically including:

[0078] S31: Construct an objective function using the musculoskeletal torque and muscle activation values ​​under normal conditions, as well as the car seat parameter values ​​to be adjusted. Optimize the objective function using the car seat pressure feature data through a Bayesian optimization algorithm (i.e., use a Bayesian optimization algorithm to find the car seat parameter values ​​that maximize the objective function), and obtain the optimal car seat parameter values ​​output by the objective function, which is the optimal fine-tuning of the seat posture.

[0079] In step S31, the formula expression for the objective function is: ;

[0080] In the formula, X represents the car seat parameter value corresponding to the optimal fine-tuning of the seat posture in the last fine-tuning; This indicates the car seat parameter value to be adjusted, which corresponds to the current seat posture. , is the covariance function, representing the difference in changes in skeletal torque and muscle activation values ​​after changes in the car seat pressure characteristic data between the last fine-tuning and the current adjustment; This is a mean function, representing the musculoskeletal torque and muscle activation values ​​of a user in a normal state; For Gaussian process regression model ( The main function of the model is to model the objective function under limited experimental data and predict the optimal parameter settings based on this model. This represents the optimal pressure difference, which includes the optimal car seat parameter values ​​for the current adjustment.

[0081] In step S31, the objective function is optimized using the car seat pressure feature data through a Bayesian optimization algorithm, specifically including:

[0082] S311: Select the initial pressure point from the pressure points of the car seat pressure characteristic data. And the value of the objective function was obtained by conducting an experiment at that point. ;

[0083] S312: Experimental data corresponding to automobile seat pressure characteristic data Construct a Gaussian process regression model to obtain the posterior distribution of the objective function. ;in , where n represents the total number of pressure points with non-zero values, and f represents the output value of the objective function. D represents the sample set of existing experimental data, and D represents the dataset, which is used to store experimental data that have been tested.

[0084] S313: In parameter space In the process, sampling strategies (such as UCB, EI, etc.) are used to select the next experimental point. And an experiment was conducted at that point to obtain the value of the objective function. ;in, Space for storing car seat parameter values ;

[0085] S314: New experimental points Add to existing experimental data. In this process, the posterior distribution of the objective function is updated using a Gaussian process regression model;

[0086] S315: Repeat steps S313 and S314 until the predetermined number of experiments is reached or the Gaussian process regression model converges.

[0087] S32: Adjust the shape and position of the car seat surface based on optimal fine-tuning of seat posture.

[0088] This invention first obtains the optimal seat posture for the current user through a human-chair coupling model and human body shape data. Based on the seat parameter values ​​of the optimal seat posture, the shape and position of the car seat are adjusted. Furthermore, at set intervals, the car seat pressure characteristic data within the current user's preset time period is obtained, and the current seat posture is fine-tuned based on this data. A Bayesian optimization algorithm is used to optimize the constructed objective function using the car seat pressure characteristic data, yielding the optimal car seat parameter values ​​output by the objective function, i.e., the optimal fine-tuned seat posture. Based on this optimal fine-tuned seat posture, the shape and position of the car seat are adjusted. This personalized adjustment of the car seat based on the passenger's body characteristics is achieved. Furthermore, it enables proactive adjustment of the car seat shape and position using a Bayesian optimization algorithm at set intervals during the user's driving or use, thereby altering blood circulation and reducing user fatigue.

[0089] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0090] Furthermore, in this invention, descriptions involving terms such as "first," "second," and "a" are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0091] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0092] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

Claims

1. A method for dynamically adjusting the shape and position of a car seat surface, characterized in that, include: S1: Based on the biomechanical analysis model, a human-chair coupling model is established using the design parameters of the chair and human body parameter data; S2: Obtain the car seat pressure characteristic data within the current user's preset time period, and obtain the human body shape data corresponding to the current user based on the car seat pressure characteristic data. Obtain the optimal seat posture corresponding to the current user based on the human-chair coupling model and human body shape data. Adjust the seat surface shape and position of the car seat based on the seat parameter values ​​of the optimal seat posture. S3: At set intervals, acquire the car seat pressure characteristic data within the current user's preset time period, and fine-tune the current seat posture based on the car seat pressure characteristic data. The current seat posture is the optimal seat posture or the optimal fine-tuned seat posture corresponding to the last fine-tuning, specifically including: S31: Construct an objective function using the musculoskeletal torque and muscle activation values ​​under normal conditions and the car seat parameter values ​​to be adjusted. Optimize the objective function using the car seat pressure feature data through a Bayesian optimization algorithm to obtain the optimal car seat parameter values ​​output by the objective function, which is the optimal fine-tuning of the seat posture. In step S31, the formula expression for the objective function is: ； In the formula, This represents the car seat parameter value corresponding to the last fine-tuning of the optimal seat posture; This indicates the car seat parameter value to be adjusted, which corresponds to the current seat posture. , is the covariance function, representing the difference in changes in skeletal torque and muscle activation values ​​after changes in the car seat pressure characteristic data between the last fine-tuning and the current adjustment; This is a mean function, representing the musculoskeletal torque and muscle activation values ​​of a user in a normal state; It is a Gaussian process regression model; This represents the optimal pressure difference, which includes the optimal car seat parameter values ​​for the current adjustment. S32: Adjust the shape and position of the car seat surface based on optimal fine-tuning of seat posture.

2. The method for dynamically adjusting the shape and position of a car seat surface according to claim 1, characterized in that, The S2 step specifically includes: Obtain car seat pressure characteristic data within the current user's preset time period; By mapping human body shape to car seat pressure feature data, and establishing a relationship model between car seat pressure feature data and human body shape, the human body shape data corresponding to the current user can be predicted through the relationship model. Multiple sets of human body size data are acquired, with each set corresponding to a user. Based on the human-chair coupling model, simulation calculations and biomechanical analyses are performed on each set of human body size data in sequence to read the skeletal torque and muscle activation values ​​of the corresponding user's musculoskeletal system. The optimal chair posture corresponding to each set of human body size data is then constructed based on the skeletal torque and muscle activation values. The system matches the current user's body shape data with the body size data set. When a body size data set matches the current user's body shape data, the system obtains the optimal seat posture corresponding to that body size data set. Adjust the shape and position of the car seat surface based on the car seat parameter values ​​corresponding to the optimal seat posture.

3. The method for dynamically adjusting the shape and position of a car seat surface according to claim 2, characterized in that, The automotive seat pressure characteristic data includes: Maximum pressure average pressure The contact area A, pressure gradient G, and static pressure distribution SPD% are given. The pressure gradient G includes a circular pressure gradient and a linear pressure gradient. The static pressure distribution The calculation formula is: ； In the formula, The total number of pressure points with non-zero values. For the first The pressure value corresponding to each pressure point.

4. The method for dynamically adjusting the shape and position of a car seat surface according to claim 3, characterized in that, In step S31, the objective function is optimized using the car seat pressure feature data through a Bayesian optimization algorithm, specifically including: S311: Select the initial pressure point from the pressure points of the car seat pressure characteristic data. And the value of the objective function was obtained by conducting an experiment at that point. ; S312: Experimental data corresponding to automobile seat pressure characteristic data Construct a Gaussian process regression model to obtain the posterior distribution of the objective function. ;in, , This represents the total number of pressure points with non-zero values. This represents the output value of the objective function. This represents the sample set of existing experimental data. This refers to a dataset used to store experimental data that has already been used in experiments; S313: In parameter space In the process, a sampling strategy is used to select the next experimental point. And an experiment was conducted at that point to obtain the value of the objective function. ;in, Space for storing car seat parameter values, ; S314: New experimental points Add to existing experimental data. In this process, the posterior distribution of the objective function is updated using a Gaussian process regression model; S315: Repeat steps S313 and S314 until the predetermined number of experiments is reached or the Gaussian process regression model converges.

5. The method for dynamically adjusting the shape and position of a car seat surface according to claim 3, characterized in that, The skeletal torque includes: cumulative muscle force, normal muscle force, and muscle shear force; in step S2, the formula for constructing the optimal seat posture is: ； In the formula, Indicates accumulated muscle strength. This indicates that the muscle is under normal stress. Indicates muscle shear force. This represents the muscle activation level, which is the optimal biomechanical state of the human body.

6. The method for dynamically adjusting the shape and position of a car seat surface according to claim 5, characterized in that, In step S2, the model for the mapping between car seat pressure characteristic data and human body shape is defined by the following formula: ； In the formula, This represents a multilayer perceptron neural network. This represents data on the pressure characteristics of car seats. This represents the predicted human body shape data, where, This indicates the current user's height. This indicates the current user's weight.

7. The method for dynamically adjusting the shape and position of an automobile seat surface according to claim 6, characterized in that, The human body size data set includes: height and weight; in step S2, the formula for obtaining the optimal seat posture is: ； In the formula, This indicates the current user's height. This indicates the current user's weight. This represents the height in the human body size data set. This represents the weight in the human body size data set.

8. The method for dynamically adjusting the shape and position of a car seat surface according to claim 1, characterized in that, In step S1, the design parameters of the seat include: the design position of the seat, H point, heel point, footrest point, seat cushion departure point, backrest departure point, steering wheel and eyeball position; The human body parameter data includes height, shoulder height, shoulder width, and weight corresponding to various body types.

9. A method for dynamically adjusting the shape and position of an automobile seat surface according to claim 7, characterized in that, The automotive seat parameter values ​​include: the seat's fore-and-aft position, height position, backrest position, the inflation / deflation volume of the seat lumbar airbag, backrest airbag, and seat cushion airbag, and the seat surface pressure of each airbag at the corresponding inflation / deflation volume.

Images