Self-adaptive control method for ventilation and heating of automobile seat

Abstract

The invention relates to a self-adaptive control method for ventilation and heating of an automobile seat. The self-adaptive control method comprises the following steps: acquiring parameters of an environment where the automobile seat to be detected is located in real time; the environmental parameters comprise seat temperature, seat humidity, airflow velocity, passenger skin temperature and passenger skin conductivity; inputting the parameters of the environment where the to-be-tested automobile seat is located into the trained comfort level index obtaining model, and obtaining the comfort level index of the to-be-tested automobile seat; when the comfort level index is smaller than a preset threshold value, inputting parameters of the environment where the to-be-tested automobile seat is located into a parameter acquisition model, and acquiring related adjustment parameters of the automobile seat; the parameter acquisition model comprises a heating power acquisition sub-model and a ventilation intensity acquisition sub-model. Self-adaptive adjustment of ventilation and heating parameters is achieved, the comfort level of passengers is improved, and meanwhile energy consumption is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of automobiles, and particularly to an adaptive control method for ventilation and heating of automobile seats. Background Art

[0002] With the development of the automobile industry and the improvement of consumers' requirements for driving experience, the design of automobile seats is no longer limited to the basic support function, but is gradually developing towards improving riding comfort and health. Especially in long-distance driving or extreme climate conditions, the ventilation and heating functions of seats are particularly important.

[0003] However, the traditional ventilation and heating of automobile seats mainly rely on manual adjustment or fixed-mode adjustment, and cannot meet the comfort requirements of different passengers in various environmental conditions in real time and accurately.

[0004] Therefore, there is an urgent need for an adaptive control method for ventilation and heating of automobile seats at present. Summary of the Invention

[0005] (I) Technical Problems to be Solved

[0006] In view of the above-mentioned disadvantages and deficiencies of the prior art, the present invention provides an adaptive control method for ventilation and heating of automobile seats, which solves the technical problem that the prior art cannot meet the personalized needs of different passengers in various environmental conditions in real time and accurately.

[0007] (II) Technical Solutions

[0008] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, an embodiment of the present invention provides an adaptive control method for ventilation and heating of automobile seats, including:

[0010] S100. Real-time obtain the environmental parameters of the automobile seat to be measured;

[0011] The environmental parameters include: seat temperature, seat humidity, air flow velocity, passenger skin temperature, and passenger skin conductivity;

[0012] S200. Input the environmental parameters of the automobile seat to be measured into the trained comfort index acquisition model to obtain the comfort index of the automobile seat to be measured;

[0013] S300. When the comfort index is less than a pre-set threshold, input the environmental parameters of the automobile seat to be measured into the parameter acquisition model to obtain the relevant adjustment parameters of the automobile seat;

[0014] The parameter acquisition model includes: a heating power acquisition sub-model and a ventilation intensity acquisition sub-model.

[0015] Optionally, in S200, the comfort index acquisition model includes:

[0016] A data input layer for receiving the environmental parameters of the vehicle seat to be measured;

[0017] A feature engineering layer for preprocessing the environmental parameters of the vehicle seat to be measured to obtain the processed data;

[0018] A deep learning feature extraction layer for using a deep neural network to extract features from the processed data, obtaining high-level features, and obtaining a first comfort index;

[0019] A fuzzy logic inference layer for obtaining a second comfort index according to the high-level features and a pre-constructed fuzzy rule base;

[0020] A fusion adjustment layer for combining the first comfort index and the second comfort index to obtain a comfort index.

[0021] An output layer for outputting the comfort data of the vehicle seat to be measured.

[0022] Optionally, in S200,

[0023] The trained comfort index acquisition model is a model trained by an asynchronous training method according to a historical data set;

[0024] The historical data set includes: historical environmental parameters and the comfort index corresponding to each historical environmental parameter.

[0025] Optionally, in S300, when the comfort index is less than a pre-set threshold, it specifically includes:

[0026] S310. Input the environmental parameters of the vehicle seat to be measured into the heating power acquisition sub-model to obtain the heating power of the vehicle seat;

[0027] S320. Input the environmental parameters of the vehicle seat to be measured into the ventilation intensity acquisition sub-model to obtain the ventilation intensity acquisition sub-model of the vehicle seat.

[0028] Optionally, S310 includes:

[0029] Input the environmental parameters of the vehicle seat to be measured into the following formula to obtain the heating power of the vehicle seat:

[0030]

[0031] where P is the heating power, T skin is the passenger's skin temperature, T seatThe seat temperature, CI is the comfort index, and G skin is the skin conductivity of the passenger, and α, β, and γ are weight coefficients.

[0032] Optionally, the S320 includes:

[0033] Input the environmental parameters of the to-be-tested vehicle seat into the following formula to obtain the ventilation intensity of the vehicle seat:

[0034]

[0035] where I vent is the ventilation intensity, V a is the air flow velocity, H s is the seat humidity, H max is the maximum seat humidity, G skin is the skin conductivity of the passenger, CI target is the pre-set comfort index threshold, CI is the comfort index, and the γ1, γ2, γ3, and γ4 are weight parameters to be optimized, which are obtained by training the ventilation intensity acquisition sub-model using historical environmental parameters and the corresponding ventilation intensity.

[0036] Optionally, the method further includes:

[0037] S400. Real-time monitor the environmental parameters and comfort index of the to-be-tested seat after adjustment. If the comfort index is still lower than the pre-set threshold, repeat step S300 until the comfort index is greater than the pre-set threshold.

[0038] Optionally, the method further includes:

[0039] S500. Add the environmental parameters of the to-be-tested vehicle seat and the comfort index of the to-be-tested vehicle seat to the historical data set, continuously train the comfort index acquisition model, and obtain the optimized comfort index acquisition model as the comfort index acquisition model for the next use.

[0040] In a second aspect, an embodiment of the present invention provides a vehicle seat ventilation and heating structure, including:

[0041] A multi-modal sensor, ventilation holes, heating elements, a control element, and a ventilation fan;

[0042] The heating element, the ventilation fan, and the control element are embedded inside the vehicle seat, the ventilation holes are uniformly distributed on the surface of the vehicle seat and the backrest area, and the multi-modal sensor is installed on the surface of the part of the vehicle seat that is in direct contact with the passenger's skin;

[0043] The control element executes an adaptive control method for vehicle seat ventilation and heating as described in any one of the claims.

[0044] Optionally, the multimodal sensor includes:

[0045] a temperature sensor, a humidity sensor, an air flow sensor, and a skin conductivity sensor;

[0046] The temperature sensor is used to detect the skin temperature of the passenger and the seat temperature, the humidity sensor is used to detect the seat humidity, the air flow sensor is used to detect the air flow speed, and the skin conductivity sensor is used to detect the skin conductivity of the passenger.

[0047] (III) Beneficial Effects

[0048] The beneficial effects of the present invention are as follows: An adaptive control method for ventilation and heating of an automotive seat of the present invention dynamically adjusts the ventilation and heating intensity of the seat by real-time monitoring and analyzing various environmental parameters and the physiological state of the passengers, providing the most suitable comfort for each passenger; at the same time, the present invention combines deep learning with fuzzy logic and self-optimizes by continuously updating the historical data set, realizing the intelligent control of seat ventilation and heating and improving the riding experience of passengers; in addition, the present invention realizes the adaptive adjustment of ventilation and heating parameters through a comfort index model and a parameter acquisition model, reducing energy consumption while improving the comfort of passengers. Description of the Drawings

[0049] Figure 1 It is a schematic flow chart of an adaptive control method for ventilation and heating of an automotive seat according to an embodiment of the present invention. Detailed Embodiments

[0050] In order to better explain the present invention for easy understanding, the present invention will be described in detail below with reference to the drawings and through specific embodiments.

[0051] An adaptive control method for ventilation and heating of an automotive seat proposed in an embodiment of the present invention is to solve the technical problem in the prior art that the comfort requirements of different passengers under various environmental conditions cannot be met in real time and accurately. By real-time monitoring and analyzing various environmental parameters and the physiological state of the passengers, the ventilation and heating intensity of the seat is dynamically adjusted to provide the most suitable comfort for each passenger; at the same time, the present invention combines deep learning with fuzzy logic and self-optimizes by continuously updating the historical data set, realizing the intelligent control of seat ventilation and heating and improving the riding experience of passengers; further, a comfort index model and a parameter acquisition model are set up to realize the adaptive adjustment of ventilation and heating parameters, reducing energy consumption while improving the comfort of passengers.

[0052] To better understand the above technical solution, the exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more clear and thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0053] Embodiment 1

[0054] See Figure 1 , an adaptive control method for ventilation and heating of an automotive seat in this embodiment includes:

[0055] Step S100: Real-time obtain the environmental parameters of the automotive seat to be measured;

[0056] The environmental parameters include: seat temperature, seat humidity, air flow velocity, passenger skin temperature, and passenger skin conductivity;

[0057] Step S200: Input the environmental parameters of the automotive seat to be measured into the trained comfort index acquisition model to obtain the comfort index of the automotive seat to be measured;

[0058] Step S300: When the comfort index is less than the preset threshold, input the environmental parameters of the automotive seat to be measured into the parameter acquisition model to obtain the relevant adjustment parameters of the automotive seat;

[0059] The parameter acquisition model includes: a heating power acquisition sub-model and a ventilation intensity acquisition sub-model.

[0060] In the specific implementation process, environmental parameters are obtained through different sensors; for example, a temperature sensor is used to detect the passenger skin temperature and the seat temperature, a humidity sensor is used to detect the seat humidity, an air flow sensor is used to detect the air flow velocity, and a skin conductivity sensor is used to detect the passenger skin conductivity.

[0061] An adaptive control method for ventilation and heating of an automotive seat in this embodiment improves the comfort of passengers during riding, and at the same time precisely adjusts heating and ventilation, avoiding waste of energy, reflecting the perfect combination of the humanized and environmental protection concepts of modern automobiles.

[0062] Embodiment 2

[0063] An adaptive control method for ventilation and heating of an automotive seat in this embodiment includes:

[0064] Step S100: Real-time obtain the environmental parameters of the automotive seat to be measured;

[0065] The environmental parameters include: seat temperature, seat humidity, air flow velocity, passenger skin temperature, and passenger skin conductivity;

[0066] Step S200: Input the environmental parameters of the automobile seat to be measured into the trained comfort index acquisition model to obtain the comfort index of the automobile seat to be measured;

[0067] Step S300: When the comfort index is less than the pre-set threshold, input the environmental parameters of the automobile seat to be measured into the parameter acquisition model to obtain the relevant adjustment parameters of the automobile seat;

[0068] The parameter acquisition model includes: a heating power acquisition sub-model and a ventilation intensity acquisition sub-model.

[0069] In step S200, the comfort index acquisition model includes:

[0070] A data input layer, which is used to receive the environmental parameters of the automobile seat to be measured;

[0071] A feature engineering layer, which is used to perform data preprocessing on the environmental parameters of the automobile seat to be measured to obtain the processed data;

[0072] A deep learning feature extraction layer, which is used to use a deep neural network to extract features from the processed data to obtain high-level features and obtain a first comfort index;

[0073] A fuzzy logic inference layer, which is used to obtain a second comfort index according to the high-level features and the pre-constructed fuzzy rule base;

[0074] A fusion adjustment layer, which is used to combine the first comfort index and the second comfort index to obtain the comfort index.

[0075] An output layer, which is used to output the comfort data of the automobile seat to be measured.

[0076] In the specific implementation process, the feature engineering layer processes the environmental parameters of the automobile seat to be measured received by the data input layer; for example, the environmental parameters are scaled to the same scale using the Z-score normalization method:

[0077] For each environmental parameter, its Z-score normalized value z i can be calculated by the following method:

[0078]

[0079] where xi is the original feature value, μ is the average value of all sample values of this feature, and σ is the standard deviation of all sample values of this feature.

[0080] Further, in practical applications, before data standardization, it is also necessary to remove error values, missing values, or duplicate values from the environmental parameters. For example, if the temperature data at a certain moment is significantly incorrect, it is corrected or deleted.

[0081] In this embodiment, the deep learning feature extraction layer includes: a fully connected layer, a convolutional layer, a recurrent layer, an attention mechanism, and a regularization layer. The deep learning feature extraction layer uses a deep neural network to extract high-level features from the processed environmental parameters. These features are usually high-level abstract representations of the original data and can capture complex patterns and relationships in the data.

[0082] In the fuzzy logic inference layer, first, based on the high-level features output by the deep learning feature extraction layer and the pre-constructed fuzzy rule base, a fuzzification process is performed. The fuzzy rule base contains a series of fuzzy rules constructed based on expert knowledge and experience, which define the fuzzy relationships between different feature values and the comfort index. The fuzzy logic inference layer uses these rules for reasoning, obtains the membership degree of the fuzzy set through the triangular membership function, and minimizes the membership degree to calculate the fuzzy comfort index. The reasoning process may involve operations on fuzzy sets (such as union, intersection, complement, etc.) and the calculation of fuzzy implication relationships.

[0083] To convert the fuzzy comfort index into an exact numerical value, the fuzzy logic inference layer also includes a defuzzification step. The purpose of defuzzification is to select one or several most representative values as the exact representation of the comfort index according to the membership function of the fuzzy set. Defuzzification methods may include the centroid method, the maximum membership degree method, or the weighted average method, etc.

[0084] For example, in the fuzzy logic inference layer, the pre-constructed fuzzy rule base includes:

[0085] Seat temperature: T seat <20°C, fuzzified as cold; 18°C < T seat <25°C, fuzzified as cool; 25°C < T seat <30°C, fuzzified as warm; T seat >27°C, fuzzified as hot;

[0086] Seat humidity: Hs < 40%, fuzzified as dry; 40% < Hs < 60%, fuzzified as moderate; Hs > 60%, fuzzified as humid;

[0087] Airflow velocity: V a <0.1, fuzzified as calm; 0.1 < V a <0.5, fuzzified as gentle breeze; V a > 0.5, fuzzified as strong wind;

[0088] Passenger skin temperature: Tskin < 33 °C, it is fuzzy as low; 33 < T skin < 36 °C, it is fuzzy as normal; T skin > 36 °C, it is fuzzy as high;

[0089] Passenger skin conductivity: G skin < 5, it is fuzzy as low; 5 < G skin < 8, it is fuzzy as medium, G skin > 8, it is fuzzy as high.

[0090] Rule 1: If the seat temperature is cold and the humidity is dry, the comfort level is very uncomfortable.

[0091] Rule 2: If the seat temperature is cool and the humidity is moderate, the comfort level is relatively comfortable.

[0092] Rule 3: If the air flow speed is gentle breeze and the passenger skin temperature is normal, the comfort level is average.

[0093] Rule 4: If the passenger skin conductivity is high and the seat temperature is hot, the comfort level is not very comfortable.

[0094] In this embodiment, after obtaining the first comfort index output by the deep learning feature extraction layer and the second comfort index output by the fuzzy logic inference layer, the final comfort index is obtained by weighted average.

[0095] In this embodiment, in step S200,

[0096] The trained comfort index acquisition model is a model trained by an asynchronous training method according to the historical data set;

[0097] The historical data set includes: historical environmental parameters and the comfort index corresponding to each historical environmental parameter.

[0098] Specifically, asynchronous training means that in a distributed computing environment, multiple worker nodes train the model in parallel, but each node independently updates the model parameters without waiting for other nodes to complete the current iteration process. By adopting asynchronous training, the idle time caused by synchronous waiting can be significantly reduced, thereby improving the overall training speed.

[0099] In the specific usage process, first, the historical data set is divided into several subsets, and these subsets are assigned to different worker nodes. Each node is responsible for processing the data of one or more subsets and updating the model parameters based on this data; that is, each node independently trains according to the data subset it receives and is not affected by the progress of other nodes.

[0100] After every 10 iterations are completed, each node updates its model parameters to the central server or aggregates and averages these model parameters using a parameter server architecture to obtain a new global model.

[0101] In summary, adopting an asynchronous training method for constructing a comfort index acquisition model for car seats can not only speed up the training process, but also better adapt to various situations that may occur in practical applications, ensuring the accuracy and practicality of the comfort index acquisition model.

[0102] In this embodiment, in step S300, when the comfort index is less than a preset threshold, it specifically includes:

[0103] Step S310: Input the environmental parameters of the car seat to be measured into the heating power acquisition sub-model to obtain the heating power of the car seat;

[0104] Step S320: Input the environmental parameters of the car seat to be measured into the ventilation intensity acquisition sub-model to obtain the ventilation intensity acquisition sub-model of the car seat.

[0105] When the comfort index is greater than or equal to the preset threshold, heating and ventilation are not performed, that is, both the heating power and the ventilation intensity are 0.

[0106] In the specific implementation process, the preset threshold is dynamically adjusted according to the season or climate conditions. For example, if the range of the comfort index is 0 - 100 and the initial basic threshold is set to 70, when the comfort index is lower than 70, the heating and ventilation functions are activated.

[0107] In winter, due to the low environmental temperature and the high demand for the heating function by users, the threshold is adjusted to 65; in spring and autumn, the environmental temperature is relatively suitable and the demand for heating or ventilation by users is low, so the basic threshold is maintained; in summer, due to the high environmental temperature and the high demand for the ventilation function by users, the threshold is appropriately lowered and adjusted to 65.

[0108] Furthermore, when the environmental temperature is lower than 10°C, the threshold is further lowered by 3; when the environmental temperature is higher than 30°C, the threshold is further lowered by 3; when the environmental humidity is higher than 70%, the threshold is lowered by 2; when the environmental humidity is lower than 30%, the threshold is further lowered by 3.

[0109] Furthermore, the threshold set in this embodiment can also be manually adjusted and modified by the user.

[0110] In this embodiment, step S310 specifically includes:

[0111] Input the environmental parameters of the car seat to be measured into the following formula to obtain the heating power of the car seat:

[0112]

[0113] Among them, P is the heating power, and T skin is the passenger's skin temperature, T seat is the seat temperature, CI is the comfort index, and G skin is the passenger's skin conductivity, and α, β, and γ are weight coefficients.

[0114] In a specific implementation process, if the environmental parameters of the automobile seat to be tested are input into the following formula, and if the obtained heating power is negative, no heating is performed, that is, the heating power is set to 0.

[0115] Further, step S320 includes:

[0116] Input the environmental parameters of the automobile seat to be tested into the following formula to obtain the ventilation intensity of the automobile seat:

[0117]

[0118] Among them, I vent is the ventilation intensity, V a is the air flow velocity, H s is the seat humidity, H max is the maximum seat humidity, G skin is the passenger's skin conductivity, CI target is the pre-set comfort index threshold, CI is the comfort index, and the γ1, γ2, γ3, and γ4 are weight parameters to be optimized, which are obtained by training the ventilation intensity acquisition sub-model using historical environmental parameters and the corresponding ventilation intensity.

[0119] The method of this embodiment further includes:

[0120] Step S400: Real-time monitor the environmental parameters and comfort index of the seat to be tested after adjustment. If the comfort index is still lower than the pre-set threshold, repeat step S300 until the comfort index is greater than the pre-set threshold.

[0121] This embodiment is a closed-loop feedback control system, which enables the effect after each adjustment to be evaluated in a timely manner, and further optimizes the heating power and ventilation intensity according to the results until the requirements of the comfort index are met. Through the above operations, not only can it ensure that when the comfort index is lower than the set threshold, it can effectively trigger and execute the corresponding adjustment process, but also can effectively reduce resource waste and achieve an efficient and comfortable user experience.

[0122] Step S500: Add the environmental parameters of the vehicle seat to be measured and the comfort index of the vehicle seat to be measured to the historical data set, continuously train the comfort index acquisition model, and obtain the optimized comfort index acquisition model as the comfort index acquisition model for the next use.

[0123] In this embodiment, by continuously updating the comfort index acquisition model and using it as the comfort index acquisition model for the next use, the accuracy of the comfort index acquisition model can be continuously improved, thus better meeting the actual needs of vehicle seat comfort evaluation.

[0124] An adaptive control method for vehicle seat ventilation and heating in this embodiment can not only significantly improve the riding experience of passengers, but also has the advantages of energy conservation, environmental protection, and intelligent operation.

[0125] Embodiment 2

[0126] A vehicle seat ventilation and heating structure in this embodiment is characterized by including:

[0127] Multimodal sensors, ventilation holes, heating elements, control elements, and ventilation fans;

[0128] The heating elements, ventilation fans, and control elements are embedded inside the vehicle seat. The ventilation holes are evenly distributed on the surface of the vehicle seat and the backrest area. The multimodal sensors are installed on the surface of the parts of the vehicle seat that are in direct contact with the passenger's skin.

[0129] The control element executes any one of the adaptive control methods for vehicle seat ventilation and heating in Embodiment 1 or Embodiment 2.

[0130] In the specific implementation process, the multimodal sensors include:

[0131] Temperature sensors, humidity sensors, airflow sensors, and skin conductivity sensors;

[0132] The temperature sensors are used to detect the passenger's skin temperature and the seat temperature. The humidity sensors are used to detect the seat humidity. The airflow sensors are used to detect the airflow speed. The skin conductivity sensors are used to detect the passenger's skin conductivity.

[0133] Specifically, the temperature sensors adopt high-precision digital temperature sensors. The humidity sensors adopt capacitive humidity sensors, and the humidity sensors are set near the ventilation holes of the seat cushion and the backrest unsealer where moisture is likely to accumulate. The airflow sensors adopt thermistor-type wind speed sensors and are installed near the ventilation holes of the seat. The skin conductivity sensors are Ag / AgCL electrode patch sensors.

[0134] Further, the ventilation holes include main ventilation holes and micro-ventilation holes. The main ventilation holes are circular holes with a diameter of 8-12 mm and are evenly distributed at the front, middle, and both sides of the seat cushion. The micro-ventilation holes are strip-shaped holes with a diameter of 3-5 mm and are integrated into the texture of the backrest mesh.

[0135] A ventilation and heating structure for an automotive seat according to this embodiment can real-time monitor various environmental parameters such as the skin temperature of passengers, the seat temperature, humidity, air flow velocity, and skin conductivity, and automatically adjust the heating and ventilation states of the seat accordingly to ensure the best comfort experience for passengers under various conditions.

[0136] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, the meaning of "a plurality" is two or more unless otherwise specifically defined.

[0137] In the present invention, unless otherwise clearly specified and defined, the terms "mounted", "connected", "coupled", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium; it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0138] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "below" and "beneath" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0139] In the description of this specification, the descriptions of terms such as "one embodiment", "some embodiments", "embodiment", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0140] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. An adaptive control method for ventilation and heating of automobile seats, characterized in that: include: S100, obtaining the environmental parameters of the tested automobile seat in real time; The environmental parameters include: seat temperature, seat humidity, air flow velocity, passenger skin temperature and passenger skin conductivity; S200, inputting the environmental parameters of the automobile seat to be tested into a trained comfort index acquisition model to obtain a comfort index of the automobile seat to be tested; S300, when the comfort index is less than a preset threshold, inputting the environmental parameters of the automobile seat to be tested into a parameter acquisition model to acquire relevant adjustment parameters of the automobile seat; The parameter acquisition model includes: a heating power acquisition sub-model and a ventilation intensity acquisition sub-model.

2. The adaptive control method for vehicle seat ventilation and heating according to claim 1, characterized in that: In S200, the comfort index acquisition model includes: The data input layer is used to receive the environmental parameters of the car seat to be tested; The feature engineering layer is used to pre-process the environmental parameters of the tested car seat and obtain the processed data; A deep learning feature extraction layer is used to extract features from the processed data using a deep neural network, obtain high-level features, and obtain a first comfort index; The fuzzy logic reasoning layer is used to obtain the second comfort index based on high-level features and a pre-built fuzzy rule base; The fusion adjustment layer is used to combine the first comfort index and the second comfort index to obtain a comfort index. The output layer is used to output the comfort data of the car seat to be tested.

3. The adaptive control method for vehicle seat ventilation and heating according to claim 1, characterized in that: In the S200, The trained comfort index acquisition model is a model trained in an asynchronous training manner based on a historical data set; The historical data set includes: historical environmental parameters and a comfort index corresponding to each historical environmental parameter.

4. The adaptive control method for vehicle seat ventilation and heating according to claim 1, characterized in that: In S300, when the comfort index is less than a preset threshold, the following steps are specifically performed: S310, inputting the environmental parameters of the automobile seat to be tested into a heating power acquisition sub-model to obtain the heating power of the automobile seat; S320, inputting the environmental parameters of the automobile seat to be tested into a ventilation intensity acquisition sub-model to obtain the ventilation intensity acquisition sub-model of the automobile seat.

5. The adaptive control method for vehicle seat ventilation and heating according to claim 4, characterized in that: The S310 includes: The environmental parameters of the automobile seat to be tested are input into the following formula to obtain the heating power of the automobile seat: Where P is the heating power, T skin is the passenger skin temperature, T seat is the seat temperature, CI is the comfort index, G skin is the passenger's skin conductivity, and α, β, γ are weight coefficients.

6. The adaptive control method for vehicle seat ventilation and heating according to claim 4, characterized in that: The S320 includes: The environmental parameters of the automobile seat to be tested are input into the following formula to obtain the ventilation intensity of the automobile seat: Among them, I vent is the ventilation intensity, V a is the air flow velocity, H s is the seat humidity, H max is the maximum humidity of the seat, G skin is the passenger skin conductivity, CI target is a comfort index threshold set in advance, CI is a comfort index, γ1, γ2, γ3, and γ4 are weight parameters that need to be optimized, and the ventilation intensity acquisition sub-model is trained and acquired by using historical environmental parameters and corresponding ventilation intensities.

7. The adaptive control method for vehicle seat ventilation and heating according to claim 1, characterized in that: The method further comprises: S400, real-time monitoring of the environmental parameters and comfort index of the seat to be tested after adjustment. If the comfort index is still lower than the threshold value set in advance, repeat step S300 until the comfort index is greater than the threshold value set in advance.

8. The adaptive control method for vehicle seat ventilation and heating according to claim 3, characterized in that: The method further comprises: S500, adding the environmental parameters of the automobile seat to be tested and the comfort index of the automobile seat to be tested to a historical data set, continuously training the comfort index acquisition model, and obtaining an optimized comfort index acquisition model as the comfort index acquisition model to be used next time.

9. A vehicle seat ventilation and heating structure, characterized in that: include: Multimodal sensors, vents, heating elements, control elements, and ventilation fans; The heating element, the ventilation fan and the control element are embedded in the interior of the car seat, the ventilation holes are evenly distributed on the surface and backrest area of ​​the car seat, and the multimodal sensor is installed on the surface of the part of the car seat that directly contacts the passenger's skin; The control element executes an adaptive control method for vehicle seat ventilation and heating as described in any one of claims 1 to 8.

10. The vehicle seat ventilation and heating structure according to claim 9, characterized in that: The multimodal sensor comprises: Temperature sensor, humidity sensor, airflow sensor, skin conductivity sensor; The temperature sensor is used to detect the passenger's skin temperature and the seat temperature, the humidity sensor is used to detect the seat humidity, the airflow sensor is used to detect the airflow velocity, and the skin conductivity sensor is used to detect the passenger's skin conductivity.

Images