Joint management regulation and control method and system for automobile air conditioners

Abstract

The invention relates to the technical field of automobile air conditioner control, in particular to an automobile air conditioner combined management regulation and control method and system.The method comprises the steps that automobile interior and exterior environment data and automobile state information are obtained, and an automobile comprehensive data set is obtained; passenger comfort demand data are obtained; calculating an energy consumption demand and a comfort demand of the air conditioner based on the vehicle comprehensive data set and the passenger comfort demand data, and generating a preliminary optimization control signal; the optimized control signal is adjusted in real time through a self-adaptive algorithm according to the change of the environment inside and outside the vehicle and the sensible temperature feedback of passengers; and continuously collecting passenger feedback data and environment change data, and optimizing a control signal based on a reinforcement learning model to obtain a final dynamic management regulation and control scheme. By means of the air conditioning system, the problems that an existing air conditioning system cannot comprehensively consider changes of the environment inside and outside the automobile and individual requirements of passengers and lacks dynamic regulation and control and self-learning optimization capacity are effectively solved, the comfort of the passengers is improved, and the overall performance of the air conditioning system is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile air-conditioning control, and in particular to an automobile air-conditioning joint management and control method and system. Background Art

[0002] With the rapid development of the automobile industry and consumers' increasing demand for driving comfort, automobile air-conditioning systems play an increasingly important role in vehicle comfort control. Modern automobile air-conditioning systems usually integrate multiple control functions such as temperature, humidity, wind speed, and air quality, aiming to provide a comfortable in-car environment.

[0003] However, most existing automotive air-conditioning systems use fixed control algorithms and cannot be adjusted in real time according to the dynamic changes in the vehicle's internal and external environments and the personalized needs of the occupants. Traditional methods usually rely on preset temperature control rules and ignore the combined effects of other comfort factors such as wind speed and humidity. At the same time, existing air-conditioning systems lack adaptive and learning optimization capabilities and cannot dynamically adjust control strategies based on historical data or real-time feedback, thus failing to achieve the optimal balance between comfort and energy efficiency. Summary of the invention

[0004] The present invention provides a vehicle air-conditioning joint management and control method and system, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for joint management and control of automobile air conditioning, comprising:

[0007] Obtain vehicle internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set;

[0008] Acquiring occupant comfort demand data, wherein the occupant comfort demand data includes a target temperature, a body temperature, and an activity state set by the occupant;

[0009] Based on the vehicle comprehensive data set and the passenger comfort demand data, the energy consumption demand and comfort demand of the air conditioner are calculated, and a preliminary optimization control signal is generated;

[0010] According to the changes in the vehicle's internal and external environments and the passengers' body temperature feedback, the optimized control signal is adjusted in real time through an adaptive algorithm;

[0011] Continuously collect passenger feedback data and environmental change data, optimize control signals based on the reinforcement learning model, and obtain the final dynamic management and control plan.

[0012] Furthermore, the method further comprises: performing offline optimization on the control signal based on historical data.

[0013] Furthermore, the total air conditioning demand is calculated based on the energy consumption demand and comfort demand, and the formula is:

[0014]

[0015] Among them, E total is the total air conditioning demand, E eff is the energy demand, E comfort For comfort needs, E env Influenced by environmental factors, T car is the actual temperature inside the car, T target is the set target temperature, α, β, γ, δ and λ are dynamic weight coefficients, and θ1 and θ2 are parameters for adjusting the nonlinearity of energy consumption and comfort demand response.

[0016] Furthermore, the method for solving each dynamic weight coefficient includes:

[0017]

[0018] β=β0·(1+|T car -T target |)·(1+H car -H target )

[0019]

[0020]

[0021] Among them, α0, β0, δ0 and γ0 are basic coefficients, which are determined based on historical operation data. battery is the vehicle battery capacity, E battery_max is the maximum battery capacity, T env is the external temperature, T env_max is the maximum external temperature, H car is the humidity inside the car, H target is the target humidity, H env is the external humidity, H env_max is the maximum external humidity, is the rate of change of temperature inside the vehicle.

[0022] Furthermore, according to the changes in the vehicle's internal and external environments and the occupant's body temperature feedback, the optimized control signal is adjusted in real time through an adaptive algorithm, including:

[0023] Based on the vehicle comprehensive data set and comfort requirements, a comprehensive comfort requirement model is determined through a target mapping algorithm, and a real-time evaluation index of in-vehicle comfort is generated;

[0024] Dynamically adjust the priority of each control signal based on real-time environmental changes and occupant feedback;

[0025] A predictive adjustment mechanism is adopted to continuously optimize the weight coefficients in the control signal based on feedback data through an adaptive algorithm.

[0026] Furthermore, the comprehensive comfort demand model is determined through the target mapping algorithm, including:

[0027] Standardize environmental data and comfort demand data to remove dimensional differences;

[0028] Based on the standardized data, a multi-dimensional weighted model is constructed, and the comprehensive comfort demand value is calculated by weighted summation to obtain a real-time comfort evaluation index.

[0029] Furthermore, the occupant feedback data and environmental change data are continuously collected, and the control signal is optimized based on the reinforcement learning model to obtain the final dynamic management and control plan, including:

[0030] Continuously collect data on the vehicle's internal and external environments and passenger feedback, and pre-process the data;

[0031] Build a reinforcement learning model, train it based on real-time collected data, and adjust the air conditioning control signal to optimize the balance between comfort and energy efficiency;

[0032] Generate control strategies based on real-time training results to update and optimize the reinforcement learning model.

[0033] Furthermore, the reinforcement learning model includes:

[0034] State space, various environmental variables and occupant needs that affect air conditioning control;

[0035] Action space, including adjustment parameters of air conditioning control signals;

[0036] Reward function, which defines the function that maximizes comfort and minimizes energy consumption;

[0037] The learning strategy adopts Q learning to optimize the air conditioning control signal through an exploration-exploitation mechanism.

[0038] A vehicle air conditioning joint management and control system, the system comprising:

[0039] The vehicle data acquisition module acquires the vehicle's internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set;

[0040] A comfort demand acquisition module, which acquires occupant comfort demand data, wherein the occupant comfort demand data includes a target temperature, a body temperature, and an activity state set by the occupant;

[0041] A preliminary signal generation module, which calculates the energy consumption demand and comfort demand of the air conditioner based on the vehicle comprehensive data set and the passenger comfort demand data, and generates a preliminary optimization control signal;

[0042] An adaptive algorithm optimization module adjusts the optimized control signal in real time through an adaptive algorithm according to changes in the vehicle's internal and external environments and the passenger's body temperature feedback;

[0043] The control scheme generation module continuously collects occupant feedback data and environmental change data, optimizes the control signal based on the reinforcement learning model, and obtains the final dynamic management control scheme.

[0044] Furthermore, the adaptive algorithm optimization module includes:

[0045] An evaluation index generating unit, based on the vehicle comprehensive data set and the comfort demand, determines a comprehensive comfort demand model through a target mapping algorithm, and generates a real-time evaluation index of in-vehicle comfort;

[0046] The priority adjustment unit dynamically adjusts the priority of each control signal according to real-time environmental changes and occupant feedback;

[0047] The mechanism optimization unit adopts a predictive adjustment mechanism and continuously optimizes the weight coefficients in the control signal based on feedback data through an adaptive algorithm.

[0048] The technical solution of the present invention can achieve the following technical effects:

[0049] It effectively solves the problem that the existing air-conditioning system cannot comprehensively consider the changes in the internal and external environment of the vehicle and the personalized needs of the passengers, and lacks dynamic control and self-learning optimization capabilities, improves the comfort of the passengers, and optimizes the overall performance of the air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A schematic diagram of a process for a joint management and control method of an automobile air conditioner;

[0052] Figure 2 A schematic diagram of a flow chart for adjusting an optimized control signal in real time through an adaptive algorithm;

[0053] Figure 3Schematic diagram of the process for determining the comprehensive comfort demand model;

[0054] Figure 4 A flow chart showing the final dynamic management and control solution. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0057] Embodiment 1

[0058] like Figure 1 As shown, the present invention provides a method for joint management and control of automobile air conditioning, the method comprising:

[0059] S1: Obtain vehicle internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set;

[0060] Specifically, the in-vehicle environment data, including in-vehicle temperature, humidity and air quality, etc., are collected through in-vehicle and in-vehicle sensors; at the same time, the in-vehicle environment data, such as outside temperature, humidity, air quality, solar radiation intensity, etc., are obtained. Combined with the vehicle status information, including the vehicle's current running speed, acceleration, battery power or remaining fuel, and the current working mode of the air-conditioning system (such as cooling, heating or ventilation), all data are integrated and pre-processed. After denoising and normalization, these data are unified into a comprehensive vehicle data set as the basic input for subsequent analysis and optimization of control signal generation.

[0061] S2: Acquire occupant comfort demand data, which includes the target temperature, body temperature and activity status set by the occupant;

[0062] Specifically, the occupants' comfort demand data is obtained through the in-vehicle user interface or automatic detection system. Occupants can actively set the target temperature to reflect their desired in-vehicle ambient temperature. At the same time, sensors are used to monitor the occupants' perceived temperature to capture their actual comfort feelings. In addition, the occupants' activity status (such as stationary, moving, or seat occupancy) is obtained through the in-vehicle monitoring system or seat sensors to comprehensively evaluate the occupants' dynamic comfort needs.

[0063] S3: Based on the comprehensive vehicle data set and the passenger comfort demand data, the energy consumption demand and comfort demand of the air conditioner are calculated, and a preliminary optimization control signal is generated;

[0064] Specifically, this step aims to accurately calculate the energy consumption and comfort requirements of the air-conditioning system under current conditions by analyzing the vehicle's comprehensive data set and the passenger comfort demand data, and generate a preliminary optimization control signal to guide air-conditioning regulation. Through a comprehensive analysis of the vehicle's internal and external environmental parameters (such as temperature, humidity, air quality) and the passenger's personalized needs (such as target temperature, body temperature, activity status), the system is evaluated for the amount of cooling, heating or ventilation that needs to be provided. The goal of this process is to ensure the comfort of the passengers while minimizing the energy consumption of the air-conditioning system to achieve a balance between comfort and energy efficiency. The preliminary optimization control signal provides a reference for the temperature setting, wind speed adjustment, humidity control, etc. of the air-conditioning, laying the foundation for subsequent real-time dynamic adjustments.

[0065] S4: Based on the changes in the vehicle's internal and external environments and the passengers' body temperature feedback, the adaptive algorithm adjusts the optimized control signal in real time;

[0066] Specifically, the process uses real-time monitored environmental data (such as temperature, humidity, and air quality) and occupant feedback (such as deviations in perceived temperature) to dynamically update the air-conditioning control parameters (such as cooling / heating intensity, wind speed, and humidity control). This adjustment mechanism is designed to ensure that the air-conditioning system can respond quickly when environmental conditions and occupant needs change, achieving continuous comfort in the vehicle environment while maximizing energy efficiency and reducing resource waste. Through real-time adjustments, it can balance the dynamic relationship between comfort and energy efficiency, providing occupants with a smarter and more efficient air-conditioning management experience.

[0067] S5: Continuously collect passenger feedback data and environmental change data, optimize the control signal based on the reinforcement learning model, and obtain the final dynamic management and control plan.

[0068] Specifically, by continuously collecting occupant feedback data (such as occupants' evaluation of the comfort of the in-vehicle environment) and environmental change data (such as dynamic changes in temperature, humidity, and air quality), the air-conditioning control signal is adaptively optimized using a reinforcement learning model to generate the final dynamic management and control solution. Through the reinforcement learning model, the system can continuously learn and adjust the control strategy based on historical data and real-time feedback to optimize the operating efficiency and comfort effects of the air conditioner. The ultimate goal is to enable the air-conditioning system to have the ability to adapt to different environments and occupant needs in the long term, achieve continuous optimization of comfort and energy efficiency, and provide the best air-conditioning control solution in a complex and dynamic environment.

[0069] The present invention effectively solves the problems of the existing air-conditioning system being unable to comprehensively consider changes in the vehicle's internal and external environments and the passengers' personalized needs, and lacking dynamic regulation and self-learning optimization capabilities, thereby improving passenger comfort and optimizing the overall performance of the air-conditioning system.

[0070] As a preferred embodiment of the above embodiment, the method further includes: optimizing the control signal offline based on historical data.

[0071] Specifically, by collecting historical operating data of the air-conditioning system under different environmental conditions, including environmental parameters inside and outside the vehicle (such as temperature, humidity, and air quality), occupant feedback data (such as comfort evaluation, perceived temperature deviation), and corresponding air-conditioning control signals and energy consumption information, offline analysis and optimization are carried out. Through in-depth analysis of these historical data, a mathematical model or machine learning model that reflects the relationship between the control signal and occupant comfort and energy efficiency performance is established; subsequently, the control strategy in the historical data is optimized using an optimization algorithm (such as genetic algorithm, particle swarm optimization, or neural network tuning, etc.) to find the best control signal generation method under different environmental conditions and occupant needs. The optimized control strategy is embedded in the control logic of the system through model updating, so that the air-conditioning system can directly use the optimization results to generate more accurate control signals in subsequent operation, thereby further improving the system's comfort regulation capability and energy efficiency performance. Through this offline optimization process, the overall performance of the system can be continuously improved with the running time to adapt to more complex environmental requirements and personalized preferences of occupants.

[0072] As a preferred embodiment of the above embodiment, the total air conditioning demand is calculated according to the energy consumption demand and the comfort demand, and the formula is:

[0073]

[0074] Among them, E total is the total air conditioning demand, E eff is the energy demand, E comfort For comfort needs, E env Influenced by environmental factors, T car is the actual temperature inside the car, T target is the set target temperature, α, β, γ, δ and λ are dynamic weight coefficients, and θ1 and θ2 are parameters for adjusting the nonlinearity of energy consumption and comfort demand response.

[0075] Specifically, the formula dynamically calculates the total demand of the air conditioning system by integrating energy demand, comfort demand and environmental factors. eff It reflects the current energy consumption demand of the air conditioner, which is affected by the battery power, fuel remaining and vehicle operating status. Its weight is controlled by the coefficient α. When the system is in a low power or high energy consumption state, α will increase to prioritize energy consumption. Comfort demand Ecomfort It is used to measure the air conditioning control intensity required to meet the comfort of passengers. It is affected by the perceived temperature deviation, humidity demand and wind speed demand. Its priority is dynamically adjusted by the weight coefficient β to meet the personalized needs of passengers. The temperature deviation attenuation factor exp(-γ·||T car -T target |) reflects the deviation between the actual temperature in the car and the target temperature. When the temperature difference is small, the attenuation factor value is high, prompting the air conditioning system to reduce the adjustment intensity. When the temperature difference is large, the attenuation factor value decreases, and the system needs to strengthen cooling or heating. In addition, the environmental factor E env The influence of is controlled by the dynamic coefficient λ, and combined with δ·log(1+λ·E env ) to ensure that the effect of the external environment on air conditioning regulation is moderately balanced and to avoid over-reliance on external data; the nonlinear adjustment parameters θ1 and θ2 in the formula are used to adjust the response intensity of energy consumption demand and comfort demand in the formula, so that the system can flexibly respond to complex conditions. Through the calculation of this formula, the air-conditioning system can dynamically balance energy efficiency and comfort in a real-time changing environment, providing a basis for the subsequent generation of optimized control signals.

[0076] As a preferred embodiment of the above embodiment, the method for solving each dynamic weight coefficient includes:

[0077]

[0078] β=β0·(1+||T car -T target |)·(1+H car -H target )

[0079]

[0080] Among them, α0, β0, δ0 and γ0 are basic coefficients, which are determined based on historical operation data. battery is the vehicle battery capacity, E battery_max is the maximum battery capacity, T env is the external temperature, T env_max is the maximum external temperature, H car is the humidity inside the car, H target is the target humidity, H env is the external humidity, H env_max is the maximum external humidity, is the rate of change of temperature inside the vehicle.

[0081] Specifically, α is used to measure the importance of air conditioning energy efficiency, which is mainly affected by the vehicle battery power E battery and external ambient temperature T envWhen the vehicle battery power is low, α increases, prompting the system to prioritize energy consumption; when the external temperature is high, the value of α will also increase to cope with the additional demand of the external environment for air conditioning energy efficiency; β is used to measure the importance of passenger comfort needs, which is mainly affected by the deviation between the actual temperature in the car and the target temperature |T car -T target |And the deviation between the humidity inside the vehicle and the target humidity H car -H target When the temperature or humidity deviation is large, β increases, prompting the system to give priority to meeting the comfort needs of the occupants; δ is used to measure the impact of external environmental factors on air conditioning control, which is affected by the external temperature T env and external humidity H env The influence of , when the external temperature or humidity is high, δ increases, prompting the system to need more energy to adapt to the extreme external environment; γ is used to measure the importance of the rate of change of the temperature inside the car to the air conditioning control. When the temperature inside the car changes too quickly, γ increases, prompting the system to quickly adjust the cooling or heating intensity to maintain the stability of the temperature inside the car. The basic coefficients α0, β0, δ0 and γ0 are the initial values ​​of the weight adjustment, which are determined by offline analysis and modeling based on historical operation data. By statistically analyzing and fitting historical operation data (such as environmental conditions, occupant feedback, and air conditioning operation efficiency), the initial weights of these basic coefficients in different driving scenarios are obtained to ensure that the system can have a high adaptability at the beginning of operation. Through the above dynamic adjustment formula, each weight coefficient can respond to changes in the internal and external environment of the car, the vehicle status and the fluctuations of occupant needs in real time, providing a reliable basis for the dynamic optimization control of the air conditioning system and ensuring a continuous balance between comfort and energy efficiency.

[0082] As a preferred embodiment of the above, Figure 2 As shown, step S4, according to the changes in the vehicle's internal and external environments and the passenger's body temperature feedback, the optimized control signal is adjusted in real time through an adaptive algorithm, including:

[0083] S41: Based on the comprehensive vehicle data set and comfort requirements, a comprehensive comfort requirement model is determined through a target mapping algorithm, and a real-time evaluation index of in-vehicle comfort is generated;

[0084] S42: dynamically adjusting the priority of each control signal according to real-time environmental changes and occupant feedback;

[0085] S43: A predictive adjustment mechanism is adopted to continuously optimize the weight coefficients of each control signal based on feedback data through an adaptive algorithm.

[0086] Specifically, the comprehensive comfort demand model is determined by combining the in-vehicle and out-of-vehicle environmental data and occupant demand data with the target mapping algorithm, and a real-time comfort evaluation index is generated as the basis for optimizing the control signal. During operation, the changes in the in-vehicle and out-of-vehicle environment (such as temperature fluctuations, humidity changes) and occupant feedback (such as perceived temperature deviation or comfort score) are monitored in real time, and the priority of the air-conditioning control signal (such as temperature adjustment, humidity control, wind speed adjustment) is adjusted according to the monitoring data. When the deviation of a certain parameter is large or the occupant is more sensitive to a certain demand, the priority of the corresponding control signal is dynamically increased to quickly meet the key needs of the occupants. Through the predictive adjustment mechanism, the weight coefficient of the control signal is dynamically optimized using an adaptive algorithm based on real-time feedback data and historical operation data. The mechanism can pre-adjust parameters such as energy efficiency weight, comfort weight and environmental factor weight according to possible future environmental changes and occupant behavior patterns to ensure that the air-conditioning system can respond quickly and provide the best control strategy when environmental conditions or demands change.

[0087] As a preferred embodiment of the above, Figure 3 As shown in the figure, the comprehensive comfort demand model is determined by the target mapping algorithm, including:

[0088] A10: Standardize environmental data and comfort demand data to remove dimensional differences;

[0089] A20: Based on the standardized data, a multi-dimensional weighted model is constructed, and the comprehensive comfort demand value is calculated by weighted summation to obtain a real-time comfort evaluation index.

[0090] Specifically, the environmental data and comfort demand data are first standardized to remove the dimensional differences between different data types. The standardized processing ensures that these data can be compared and analyzed on the same calculation scale, improving the accuracy of the model calculation; then, based on the standardized data, a multi-dimensional weighted model is constructed, in which the weights of different factors (such as temperature, humidity, and air quality) are dynamically adjusted according to their influence on comfort demand, and the comprehensive comfort demand value is calculated by weighted summation. The final real-time comfort evaluation index reflects the overall matching degree of the in-vehicle environment to the occupant's comfort demand, providing a scientific basis for the subsequent optimization of control signals.

[0091] As a preferred embodiment of the above, Figure 4 As shown, step S5 continuously collects passenger feedback data and environmental change data, optimizes the control signal based on the reinforcement learning model, and obtains the final dynamic management and control scheme, including:

[0092] S51: continuously collects vehicle and interior environment data and passenger feedback data, and pre-processes the data;

[0093] S52: Build a reinforcement learning model, based on real-time collected data, train the reinforcement learning model, and adjust the air conditioning control signal to optimize the balance between comfort and energy efficiency;

[0094] S53: Generate a control strategy based on the real-time training results to update and optimize the reinforcement learning model.

[0095] Specifically, environmental data is continuously acquired through sensors inside and outside the vehicle, including temperature, humidity, air quality inside and outside the vehicle, and vehicle operating status, while passenger feedback data, such as perceived temperature deviation and comfort score, is collected. The collected data is preprocessed, including data denoising, normalization, and outlier processing, to ensure the accuracy and consistency of the input data, providing a high-quality data foundation for subsequent model training and optimization. Based on the preprocessed data, a reinforcement learning model is constructed, and the model is trained using real-time collected data. Through continuous trials and feedback to adjust the control signal, the air-conditioning system gradually learns how to balance comfort and energy efficiency in complex environments. A control strategy is generated based on the real-time training results of the reinforcement learning model, including adjusted air-conditioning control parameters (such as cooling / heating intensity, humidity control mode, and wind speed). At the same time, the latest operating data and control effects are fed back to the reinforcement learning model, and the model parameters are updated and optimized to improve the adaptability and decision-making efficiency of the model in future complex environments. Through continuous learning, the reinforcement learning model can gradually improve the accuracy and efficiency of the control plan, and ultimately achieve the optimization goal of dynamic management and control.

[0096] As a preferred embodiment of the above, the reinforcement learning model includes:

[0097] State space, various environmental variables and occupant needs that affect air conditioning control;

[0098] Action space, including adjustment parameters of air conditioning control signals;

[0099] Reward function, which defines the function that maximizes comfort and minimizes energy consumption;

[0100] The learning strategy adopts Q learning to optimize the air conditioning control signal through the exploration-exploitation mechanism.

[0101] Specifically, the reinforcement learning model includes state space, action space, reward function and learning strategy. The state space covers various environmental variables and passenger needs that affect air conditioning control, including in-vehicle and out-vehicle environmental data (such as in-vehicle and out-vehicle temperature, humidity, and air quality), vehicle operating status (such as vehicle speed, battery power or fuel remaining), and passenger personalized needs (such as target temperature, body temperature, and activity status). These data together constitute the current system state and provide a basis for the decision-making of the reinforcement learning model; the action space defines the adjustment parameters of the air conditioning control signal, including temperature adjustment, humidity control, wind speed adjustment, and air circulation mode switching. The model selects the optimal control strategy through the action space to dynamically adjust the air conditioning operation mode; the reward function is used to evaluate each time. The design goal of the model is to maximize the comfort of the passengers and minimize the energy consumption. The reward value is calculated by the two parts of comfort and energy consumption: the comfort part is evaluated based on the deviation between the actual temperature and humidity in the car and the target value. The smaller the deviation, the higher the reward. The energy consumption part is based on the real-time energy consumption of the air conditioner. The lower the energy consumption, the higher the reward. The learning strategy adopts Q learning, which continuously optimizes the air conditioner control signal through the exploration-utilization mechanism. In the initial stage, the model accumulates experience by exploring different control signals and establishes a mapping table of state-action-reward. As the training progresses, the model gradually uses the existing experience to select the optimal action, and combines the exploration of new strategies to ensure the adaptability of the decision in a dynamic environment. Through this design, the reinforcement learning model can dynamically balance the comfort of passengers and the energy efficiency of the air conditioner, and provide a precise intelligent control solution.

[0102] Embodiment 2

[0103] Based on the same inventive concept as the automobile air conditioner joint management and control method in the aforementioned embodiment, the present invention further provides an automobile air conditioner joint management and control system, the system comprising:

[0104] The vehicle data acquisition module acquires the vehicle's internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set;

[0105] A comfort demand acquisition module is used to acquire the occupant's comfort demand data, which includes the target temperature, body temperature and activity status set by the occupant;

[0106] A preliminary signal generation module calculates the energy consumption demand and comfort demand of the air conditioner based on the vehicle comprehensive data set and the passenger comfort demand data, and generates a preliminary optimization control signal;

[0107] Adaptive algorithm optimization module, which adjusts the optimized control signal in real time through adaptive algorithm according to the changes in the vehicle's internal and external environment and the temperature feedback from the passengers;

[0108] The control scheme generation module continuously collects occupant feedback data and environmental change data, optimizes the control signal based on the reinforcement learning model, and obtains the final dynamic management control scheme.

[0109] The above-mentioned management and control system in the present invention can effectively implement the automobile air-conditioning joint management and control method, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.

[0110] As a preferred embodiment of the above, the adaptive algorithm optimization module includes:

[0111] An evaluation index generation unit, based on the vehicle comprehensive data set and comfort requirements, determines the comprehensive comfort requirement model through a target mapping algorithm, and generates a real-time evaluation index for in-vehicle comfort;

[0112] The priority adjustment unit dynamically adjusts the priority of each control signal according to real-time environmental changes and occupant feedback;

[0113] The mechanism optimization unit adopts a predictive adjustment mechanism and continuously optimizes the weight coefficients in the control signal based on feedback data through an adaptive algorithm.

[0114] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0115] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application.

[0116] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. A method for joint management and control of automobile air conditioning, characterized in that: include: Obtain vehicle internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set; Acquiring occupant comfort demand data, wherein the occupant comfort demand data includes a target temperature, a body temperature, and an activity state set by the occupant; Based on the vehicle comprehensive data set and the passenger comfort demand data, the energy consumption demand and comfort demand of the air conditioner are calculated, and a preliminary optimization control signal is generated; According to the changes in the vehicle's internal and external environments and the passengers' body temperature feedback, the optimized control signal is adjusted in real time through an adaptive algorithm; Continuously collect occupant feedback data and environmental change data, optimize the control signal based on the reinforcement learning model, and obtain the final dynamic management and control plan.

2. The automobile air conditioning joint management and control method according to claim 1 is characterized in that: The method further includes: optimizing the control signal offline based on historical data.

3. The automobile air conditioning joint management and control method according to claim 1, characterized in that: The total air conditioning demand is calculated based on energy consumption demand and comfort demand. The formula is: Among them, E total is the total air conditioning demand, E eff is the energy demand, E comfort For comfort needs, E env Influenced by environmental factors, T car is the actual temperature inside the car, T targer is the set target temperature, α, β, γ, δ and λ are dynamic weight coefficients, and θ1 and θ2 are parameters for adjusting the nonlinearity of energy consumption and comfort demand response.

4. The automobile air conditioning joint management and control method according to claim 3 is characterized in that: The solution method of each dynamic weight coefficient includes: Among them, α0, β0, δ0 and γ0 are basic coefficients, which are determined based on historical operation data. battery is the vehicle battery capacity, E battery_max is the maximum battery capacity, T env is the external temperature, T env_max is the maximum external temperature, H car is the humidity inside the car, H target is the target humidity, H env is the external humidity, H env_max is the maximum external humidity, is the rate of change of temperature inside the vehicle.

5. The automobile air conditioning joint management and control method according to claim 1, characterized in that: According to the changes in the vehicle's internal and external environments and the passengers' body temperature feedback, the optimized control signal is adjusted in real time through an adaptive algorithm, including: Based on the vehicle comprehensive data set and comfort requirements, a comprehensive comfort requirement model is determined through a target mapping algorithm, and a real-time evaluation index of in-vehicle comfort is generated; Dynamically adjust the priority of each control signal based on real-time environmental changes and occupant feedback; A predictive adjustment mechanism is adopted to continuously optimize the weight coefficients in the control signal based on feedback data through an adaptive algorithm.

6. The automobile air conditioning joint management and control method according to claim 5, characterized in that: The comprehensive comfort demand model is determined through the target mapping algorithm, including: Standardize environmental data and comfort demand data to remove dimensional differences; Based on the standardized data, a multi-dimensional weighted model is constructed, and the comprehensive comfort demand value is calculated by weighted summation to obtain a real-time comfort evaluation index.

7. The automobile air conditioning joint management and control method according to claim 1, characterized in that: Continuously collect passenger feedback data and environmental change data, optimize control signals based on reinforcement learning models, and obtain the final dynamic management and control plan, including: Continuously collect data on the vehicle's internal and external environments and passenger feedback, and pre-process the data; Build a reinforcement learning model, train it based on real-time collected data, and adjust the air conditioning control signal to optimize the balance between comfort and energy efficiency; Generate control strategies based on real-time training results to update and optimize the reinforcement learning model.

8. The automobile air conditioning joint management and control method according to claim 7, characterized in that: The reinforcement learning model includes: State space, various environmental variables and occupant needs that affect air conditioning control; Action space, including adjustment parameters of air conditioning control signals; Reward function, which defines the function that maximizes comfort and minimizes energy consumption; The learning strategy adopts Q learning to optimize the air conditioning control signal through an exploration-exploitation mechanism.

9. A joint management and control system for automobile air conditioning, characterized in that: The system comprises: The vehicle data acquisition module acquires the vehicle's internal and external environment data and vehicle status information to obtain a comprehensive vehicle data set; A comfort demand acquisition module, which acquires occupant comfort demand data, wherein the occupant comfort demand data includes a target temperature, a body temperature, and an activity state set by the occupant; A preliminary signal generation module, which calculates the energy consumption demand and comfort demand of the air conditioner based on the vehicle comprehensive data set and the passenger comfort demand data, and generates a preliminary optimization control signal; An adaptive algorithm optimization module adjusts the optimized control signal in real time through an adaptive algorithm according to changes in the vehicle's internal and external environments and the passenger's body temperature feedback; The control scheme generation module continuously collects occupant feedback data and environmental change data, optimizes the control signal based on the reinforcement learning model, and obtains the final dynamic management control scheme.

10. The automobile air conditioning joint management and control system according to claim 9, characterized in that: The adaptive algorithm optimization module includes: An evaluation index generating unit, based on the vehicle comprehensive data set and the comfort demand, determines a comprehensive comfort demand model through a target mapping algorithm, and generates a real-time evaluation index of in-vehicle comfort; The priority adjustment unit dynamically adjusts the priority of each control signal according to real-time environmental changes and occupant feedback; The mechanism optimization unit adopts a predictive adjustment mechanism and continuously optimizes the weight coefficients in the control signal based on feedback data through an adaptive algorithm.

Images