Air conditioner seat collaborative cooling control method based on neural network

Abstract

The application is suitable for the field of automobile intelligent control technology, and provides an air conditioner seat collaborative cooling control method based on a neural network, a human-environment comfortable temperature original index model is constructed by collecting a large amount of human and environment temperature distribution data in advance, on the basis, real-time human temperature, environment temperature and passenger cabin temperature before the passenger gets on the vehicle are collected and compared with the model, the most reasonable pre-adjustment of the thermal comfort in the vehicle is realized before the passenger gets on the vehicle, and the air conditioner and the seat ventilation and heating collaborative control method is used, so that the two jointly work together to improve the thermal comfort of the passenger and the passenger cabin. Meanwhile, when the passenger feels uncomfortable during the ride, the real-time sensing data is quickly processed, the passenger body temperature and the passenger cabin environment temperature are recorded, the model is inputted for correction, the comfort needs of the passenger body are more personalized, and the comfort of the passenger in the vehicle running process is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent control of automobiles, and particularly relates to a cooling control method for air-conditioned seats based on a neural network. BACKGROUND

[0002] With the development of science and technology, intelligentization, automation and personalization of a cockpit have become an important development direction of the automobile industry, and people's requirements for comfort have also increased day by day. As an important part of the comfort, thermal comfort plays a very key role in improving the cockpit environment and driving experience of people.

[0003] Traditional air-conditioning temperature adjustment methods or seat ventilation and heating adjustment are limited to active operation of people, and independent operation systems of the two make it very inconvenient for people to adjust thermal comfort. People are difficult to timely operate the two to meet their own comfort requirements in the face of complex driving environments, which is not conducive to the development of cockpit intelligentization and convenience and safety during driving. SUMMARY

[0004] The purpose of the embodiment of the application is to provide a cooling control method for air-conditioned seats based on a neural network, which aims to solve the problems proposed in the background.

[0005] The embodiment of the application is implemented as follows: a cooling control method for air-conditioned seats based on a neural network, comprising the following steps:

[0006] Step 1: data model preparation stage, collecting a large amount of human body comfort temperature distribution data and corresponding environment temperature data, and pre-processing, using the pre-processed human body temperature distribution data set and corresponding environment temperature data set, combining a neural network algorithm to construct a human-environment comfort temperature original index model;

[0007] A large amount of human body temperature and corresponding environment temperature data are collected by infrared thermal imagers, temperature sensors and other detection and sensing devices, and effective data preprocessing is performed to obtain high-quality training data. Data preprocessing includes data cleaning, data conversion, data arrangement, processing of unbalanced data, data verification and quality inspection, etc. to ensure the performance and precision of the model, so as to obtain the best human-environment temperature comfort index model that people feel comfortable.

[0008] Step 2: Practice running phase, after deploying the human-environment comfortable temperature index model, the corresponding data is obtained through the infrared thermal imager and the in-vehicle temperature sensor, including the occupant human thermal image, the human surrounding environment temperature map and the in-vehicle occupant cabin temperature data, the input data is used to construct the human-environment temperature data map by using the neural network, and compared with the human-environment comfortable temperature original index model, the data difference between the two is used to preliminarily preset the air conditioner-seat ventilation and heating control strategy method;

[0009] Step 3: In the adaptive learning phase, when the occupant adjusts the air conditioner temperature, air volume, air angle, seat ventilation and heating of any gear due to temperature discomfort, the occupant thermal image and the in-vehicle cabin temperature data are collected in real time, uploaded to the controller to correct the human-environment comfortable temperature index original model by using the neural network, and record the updated human-environment temperature comfortable index model, realize the individualized adaptive learning improvement to the adjustment of the occupant thermal comfort.

[0010] Further technical solutions, in the step 1, when collecting data, three wind measuring points are arranged on the head, trunk and lower limbs, the human body is divided into head and neck, trunk and lower limbs three parts, the average value of the transient temperature of the three parts and the average value of the occupant cabin temperature are obtained as the data set, and the collected human temperature partition data and the corresponding occupant cabin environment temperature data are substituted into the PMV calculation formula, and the calculation formula is as follows:

[0011] PMV=[0.303e -0.036M +0.0275]TL

[0012] TL=M0-W0-3.05[5.73-0.07(M-W)-P a ]-0.0014M(34-t a )

[0013] -0.0173M(5.87-P a )-0.42(M-W-58)

[0014] -3.96×10 -8 f cl [(t cl +273) 4 -(t r +273) 4 ]-f cl h c (t cl -t a )

[0015] Wherein, M is the human energy metabolic rate, TL is the difference between the human heat production and the heat dissipation to the outside world, M0 is the human metabolic rate in the heat neutral heat balance state, W0 is the mechanical work done by the human body in the heat neutral heat balance state, P a is the water vapor partial pressure around the human body, t a is the air temperature around the human body, W is the mechanical work done by the human body, f cl is the area coefficient of the clothing, t cl is the temperature of the outer surface of the clothing, t r is the average radiation temperature, h c is the convective heat transfer coefficient, t a is the air temperature around the human body;

[0016] The obtained three-part average temperature, the passenger compartment average temperature and the corresponding PMV value calculated are respectively input into the neural network for training, and finally the human-environment temperature comfort index model is obtained.

[0017] Further technical solutions, in the step 2, the control object of the air conditioning-seat ventilation heating control strategy method includes the automobile air conditioner and the seat ventilation heating function, and the two are cooperatively controlled according to the set control strategy; the control strategy method is specifically as follows:

[0018] The obtained three-part human-environment comfort temperature index data are input into the cabin controller for comparison, wherein the part with the worst thermal comfort is preferentially adjusted by the air conditioner and the seat ventilation heating is double-adjusted, and the remaining parts are adjusted by the seat ventilation heating for thermal comfort.

[0019] Further technical solutions, in the step 3, when the neural network is used to correct the human-environment comfort temperature index original model, the model can be improved according to the operation behavior of the passenger under different driving environments and driver behaviors, so as to automatically adjust and continuously update the structure and parameters of the neural network model, adapt to complex and changeable driving environments, temperatures and passenger body states, and continuously improve the performance and precision of the model.

[0020] The embodiment of the present application provides a kind of air conditioner seat collaborative cooling control method based on neural network, which is constructed by pre-acquiring a large amount of human and environmental temperature distribution data to build human-environment comfortable temperature original index model, on the basis of which, the real-time human temperature, environmental temperature and passenger cabin temperature of passenger before getting on are collected and compared with model, to realize the most reasonable pre-adjustment of in-vehicle thermal comfort before passenger getting on, and using the method of air conditioner and seat ventilation heating collaborative control, make both jointly work together to improve the thermal comfort of passenger and passenger cabin. When the passenger feels uncomfortable when adjusting, the real-time sensing data is quickly processed, the passenger body temperature and passenger cabin environmental temperature are recorded, and the model is inputted for correction, to achieve more personalized and comfortable needs of passenger body, so that the cabin thermal comfort adjustment can respond to environmental changes and passenger demand more quickly, and the personalized air conditioner seat collaborative heating and cooling system design method based on neural network can optimize energy utilization and operation efficiency, reduce operating cost, realize automation, intelligentization and personalization, and further improve the comfort of passenger in vehicle operation process. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 A schematic diagram of data preparation stage in the air conditioner seat collaborative cooling control method based on neural network provided by the embodiment of the present application is shown.

[0022] Figure 2 A schematic diagram of practical operation stage in the air conditioner seat collaborative cooling control method based on neural network provided by the embodiment of the present application is shown.

[0023] Figure 3 A schematic diagram of adaptive learning stage in the air conditioner seat collaborative cooling control method based on neural network provided by the embodiment of the present application is shown.

[0024] Figure 4 A schematic diagram of passenger cabin, seat and monitoring dummy three-dimensional model is shown.

[0025] Figure 5 Passenger cabin and human body temperature distribution after ventilation cooling simulation is finished.

[0026] Figure 6 PMV change data of head and neck part.

[0027] Figure 7 PMV change curve of trunk part.

[0028] Figure 8 PMV change curve of lower limbs.

[0029] Figure 9 Human-environment comfortable temperature index model obtained after fitting.

[0030] Figure 10 These are the comfort indices corresponding to the three zones. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0032] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0033] like Figures 1-3 As shown, an embodiment of the present invention provides a method for coordinated cooling control of air-conditioned seats based on neural networks, comprising the following steps:

[0034] Step 1: Data model preparation stage. Collect a large amount of human body comfort temperature distribution data and corresponding environmental temperature data, and preprocess them. Use the preprocessed human body temperature distribution dataset and corresponding environmental temperature dataset, combined with neural network algorithm, to construct the original index model of human body-environment comfort temperature.

[0035] A large amount of human body temperature and corresponding ambient temperature data is collected through detection and sensing devices such as infrared thermal imagers and temperature sensors. Effective data preprocessing is then performed to obtain high-quality training data. Data preprocessing includes data cleaning, data transformation, data organization, handling imbalanced data, data validation, and quality checks to ensure model performance and accuracy, thereby obtaining the optimal human-ambient temperature comfort index model for human comfort.

[0036] Step 2: In the practical operation phase, after deploying the human-environmental comfort temperature index model, relevant data are acquired through infrared thermal imagers and in-vehicle temperature sensors, including thermal images of occupants, temperature maps of the surrounding environment, and temperature data of the occupant cabin. The input data is used to construct a human-environmental temperature data map using a neural network, and compared with the original human-environmental comfort temperature index model. The difference between the two data is used to preliminarily preset the ventilation and heating control strategy for air conditioning and seats.

[0037] Step 3: During the adaptive learning phase, when occupants adjust the air conditioning temperature, air volume, air outlet angle, or seat ventilation and heating settings due to temperature discomfort, real-time thermal imaging of occupants and cabin temperature data are collected and uploaded to the controller. The controller then uses a neural network to correct the original human-environmental comfort temperature index model and records the updated human-environmental temperature comfort index model, thereby achieving personalized adaptive learning to improve the adjustment of occupant thermal comfort.

[0038] In the embodiment of the present application, a large amount of human body comfortable temperature distribution data and corresponding environment temperature data are collected and preprocessed in the model data preparation stage. The human body-environment comfortable temperature original index model is constructed by using the preprocessed human body temperature distribution data set and corresponding environment temperature data set in combination with the neural network algorithm. The neural network can specifically adopt the accumulative neural network or the recurrent neural network.

[0039] After the human body-environment comfortable temperature index model is deployed, in the practical operation stage, the corresponding data are acquired by the infrared thermal imager and the in-vehicle temperature sensor, including the occupant human body thermal image, the human surrounding environment temperature image and the in-vehicle occupant cabin temperature data, the input data constitute the human body-environment temperature data image, and the human body-environment comfortable temperature original index model is compared, and the data difference between the two is used to preliminarily preset the air conditioner-seat ventilation and heating control strategy method.

[0040] In the adaptive learning stage, when the occupant adjusts the air conditioner temperature, the air volume, the air outlet angle, the seat ventilation and heating of any gear due to temperature discomfort, the occupant thermal image and the in-vehicle occupant cabin temperature data are collected in real time, uploaded to the controller, and the human body-environment comfortable temperature index original model is corrected by using the neural network, and the updated human body-environment temperature comfortable index model is recorded, so as to realize the adjustment of the individualized adaptive learning improvement on the occupant thermal comfort.

[0041] As a preferred embodiment of the present application, in step 1, the occupant cabin, the seat and the monitoring dummy three-dimensional model are established, the starCCM+ is used to carry out the occupant cabin ventilation and cooling simulation test, and the feasibility verification is carried out taking the summer working condition as an example, the simulation initial temperature is set to 40℃, as shown in Figure 4 three wind measuring points are arranged at the head, the trunk and the lower limbs respectively, the simulation step is set to 1s, the simulation time is 100s, the human body is divided into three parts of head and neck, trunk and lower limbs, and the average values of the transient simulation temperatures of the three parts and the average value of the occupant cabin temperature are obtained as the data set. The occupant cabin and human body temperature distribution after the ventilation and cooling simulation is shown in Figure 5 .

[0042] After the simulation is completed, 100 groups of human body temperature partition data and corresponding occupant cabin environment temperature data are obtained, which are used as data and substituted into the PMV calculation formula. The PMV evaluation index is the expected average thermal sensation, which represents the thermal sensation of the vast majority of people in the current environment, and is used to evaluate the comfort of the human body under different environmental conditions and different activity levels. The PMV takes into account the activity level, clothing thermal resistance, air temperature, relative humidity, average radiation temperature and gas flow rate, and the calculation formula is as follows:

[0043] PMV=[0.303e -0.036M +0.0275]TL

[0044] TL = M0 - W0 - 3.05 [5.73 - 0.07 (M - W) - P a ] - 0.0014M (34 - t a )

[0045] - 0.0173M (5.87 - P a ) - 0.42 (M - W - 58)

[0046] - 3.96 x 10 -8 f cl [(t cl + 273) 4 - (t r + 273) 4 ] - f cl h c (t cl - t a )

[0047] Wherein, M is the human energy metabolism rate, TL is the difference between the human heat production and the heat dissipated to the outside world, M0 is the human metabolism rate in the heat neutral heat balance state, W0 is the mechanical work done by the human body in the heat neutral heat balance state, P a is the human body surrounding water vapor partial pressure, t a is the human body surrounding air temperature, W is the mechanical work done by the human body, f cl is the area coefficient of the clothing, t cl is the clothing outer surface temperature, t r is the average radiation temperature, h c is the convective heat transfer coefficient, t a is the human body surrounding air temperature.

[0048] The obtained average temperatures of the three parts (head and neck, torso, lower limbs), the average temperature of the passenger compartment and the corresponding PMV values calculated are finally input into the neural network for training, and separate neural network fitting models are established, wherein the PMV change data are as shown in Figures 6-8 . Only as a method verification, therefore, this example uses a simple feedforward neural network as an example for fitting, and the finally obtained model is imported into simulink, as shown in Figure 9 .

[0049] Wherein, input part 1 is the average temperature of the head and neck part, 2 is the average temperature of the torso part, 3 is the average temperature of the lower limb part, output part 1 is the PMV of the head and neck part, 2 is the PMV of the torso part, 3 is the PMV of the lower limb part, and the last output box (blue) is the average value of the PMV of the three parts, i.e. the whole body comfort PMV index.

[0050] As a preferred embodiment of the present application, in the step 2, taking the data obtained in a certain simulation process as an example, wherein the average head and neck temperature is 35.1℃, the torso temperature is 37.5℃, and the lower limb temperature is 39.3℃, the three groups of data are input into the established human-environment comfort temperature index model as a test group, and the corresponding three model outputs of comfort indexes can be obtained, as shown in the following table. Figure 10 As shown in the table, when the index is 0, it proves that the human body region is comfortable, and thus the corresponding index of the head and neck region is 3.682, the corresponding index of the torso region is 3.662, and the corresponding index of the lower limb part is 4.931.

[0051] As a preferred embodiment of the present application, in the step 2, the control object of the air conditioning-seat ventilation heating control strategy method includes the automobile air conditioner and the seat ventilation heating function, and the two are cooperatively controlled according to the set control strategy; the control strategy method is specifically as follows:

[0052] The obtained three-part human-environment comfort temperature index data are input into the cabin controller for comparison, wherein the part with the worst thermal comfort is preferentially adjusted by the air conditioner and the seat ventilation heating, and the remaining parts are adjusted by the seat ventilation heating for thermal comfort.

[0053] In the embodiment of the present application, as known from the previous simulation data, the lower limb part has the worst thermal comfort, followed by the head and neck, and the torso has the best thermal comfort, and thus based on this condition, the air conditioner will automatically adjust the horizontal air outlet angle downward to directly blow the lower limb part of the human body, increase the air outlet volume, and open the seat ventilation of the leg support part and increase the gear to improve the air outlet volume, so as to accelerate the thermal comfort adjustment of the lower limb, the head is adjusted by the seat ventilation function of opening the seat headrest ventilation port, and the torso is adjusted by the seat ventilation function of opening the seat backrest ventilation port.

[0054] As a preferred embodiment of the present application, in the step 3, when the neural network is used to correct the human-environment comfort temperature index original model, the model can be improved according to the operation behavior of the occupant according to different driving environments and driver behaviors, so as to automatically adjust and continuously update the structure and parameters of the neural network model, adapt to the complex and changeable driving environment, temperature and occupant body state, and thus the performance and precision of the model can be continuously improved.

[0055] The above only describes the preferred embodiments of the present application, and is not used to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for coordinated cooling control of air-conditioned seats based on neural networks, characterized in that, Includes the following steps: Step 1: Data model preparation stage. Collect a large amount of human body comfort temperature distribution data and corresponding environmental temperature data, and preprocess them. Use the preprocessed human body temperature distribution dataset and corresponding environmental temperature dataset, combined with neural network algorithm, to construct the original index model of human body-environment comfort temperature. Step 2: In the practical operation phase, after deploying the human-environmental comfort temperature index model, relevant data are acquired through infrared thermal imagers and in-vehicle temperature sensors, including thermal images of occupants, temperature maps of the surrounding environment, and temperature data of the occupant cabin. The input data is used to construct a human-environmental temperature data map using a neural network, and compared with the original human-environmental comfort temperature index model. The difference between the two data is used to preliminarily preset the ventilation and heating control strategy for air conditioning and seats. Step 3: During the adaptive learning phase, when occupants adjust the air conditioning temperature, air volume, air outlet angle, or seat ventilation and heating settings due to temperature discomfort, real-time thermal imaging of occupants and cabin temperature data are collected and uploaded to the controller. The original human-environmental comfort temperature index model is corrected using a neural network, and the updated human-environmental temperature comfort index model is recorded to achieve personalized adaptive learning to improve the adjustment of occupant thermal comfort. In step 1, during data collection, three wind measurement points are set up at the head, torso, and lower limbs respectively. The human body is divided into three parts: head and neck, torso, and lower limbs. The average transient temperature of these three parts and the average temperature of the passenger cabin are obtained as the dataset. The collected human body temperature partition data and the corresponding passenger cabin ambient temperature data are substituted into the PMV calculation formula. The three average temperatures, the average temperature of the passenger cabin, and the corresponding calculated PMV values ​​were respectively input into the neural network for training, and finally a human-environment temperature comfort index model was obtained. In step 2, the controlled objects of the air conditioning-seat ventilation and heating control strategy method include the vehicle air conditioning and seat ventilation and heating functions, which are controlled collaboratively according to the set control strategy; the specific control strategy method is as follows: The obtained human-environmental comfort temperature index data from the three parts are input into the cockpit controller for comparison. The part with the worst thermal comfort will be adjusted by prioritizing air conditioning and dual adjustment of seat ventilation and heating, while the rest will be adjusted by seat ventilation and heating for thermal comfort.

2. The air-conditioned seat cooperative cooling control method based on neural network according to claim 1, characterized in that, The formula for calculating PMV is as follows: PMV=[0.303e -0.036M [TL +0.0275] TL=M0-W0-3.05[5.73-0.07(M-W)-P a ]-0.0014M(34-t a ) -0.0173M(5.87-P a )-0.42(M-W-58) -3.96×10 -8 f cl [(t cl +273) 4 -(t r +273) 4 ]-f cl h c (t cl -t a ) Where M is the human body's metabolic rate, TL is the difference between the heat produced by the human body and the heat dissipated by the human body to the outside world, M0 is the human body's metabolic rate under thermoneutral thermal equilibrium, W0 is the mechanical work done by the human body to the outside world under thermoneutral thermal equilibrium, and P... a The partial pressure of water vapor around the human body, t a Let W be the temperature of the air surrounding the human body, W be the mechanical work done by the human body, and f be the temperature of the air surrounding the human body. cl t is the area coefficient of clothing. cl The temperature of the outer surface of the clothing, t r h is the average radiation temperature. c t is the convective heat transfer coefficient. a The temperature of the air surrounding the human body.

3. The air-conditioned seat cooperative cooling control method based on neural networks according to claim 2, characterized in that, In step 1, human body temperature and corresponding ambient temperature data are collected using an infrared thermal imager and a temperature sensor; Data preprocessing includes data cleaning, data transformation, data organization, handling imbalanced data, data validation, and quality checks.

4. The air-conditioned seat cooperative cooling control method based on neural network according to claim 1, characterized in that, In step 3, when the original human-environment comfort temperature index model is corrected using a neural network, the model is improved based on the occupant's operating behavior under different driving environments and driver behaviors. This allows for automatic adjustment and continuous updating of the neural network model's structure and parameters to adapt to different driving environments, temperatures, and occupant physical conditions.

Images