Intelligent closed-loop control method for comfort of whole vehicle

Abstract

The invention relates to the technical field of vehicle comfort, and belongs to a vehicle comfort intelligent closed-loop control method which comprises the following steps: S1, a vehicle sensor collects vehicle environment data and outputs a signal, and vehicle thermal load parameters in a current environment state are calculated; s2, user information is counted, user thermal system data features are extracted, and a user behavior analysis result is calculated and output; s3, based on the whole vehicle thermal load parameters obtained in the step S1, the user behavior analysis result in the step S2 is used for conducting correction compensation on the thermal load parameters, and a comfort control target is defined and output according to the user and the feature state; s4, the thermal system is regulated and controlled according to the comfort control target output in the S3, and comfort adjustment is preliminarily completed; and S5, after preliminary adjustment, monitoring whether the user actively adjusts the set parameters in real time in the process, and feeding back to the upper level to recalculate the control target, synchronously evaluate and score the control target, redefine and record the user habits, and perform data iteration and parameter optimization.

Description

Technical Field

[0001] This invention relates to the field of vehicle comfort technology, specifically a method for intelligent closed-loop control of vehicle comfort. Background Technology

[0002] With the development of intelligent vehicle technology, the importance of automotive thermal management systems in improving driving comfort and energy efficiency is becoming increasingly prominent. Traditional automotive thermal management systems mainly rely on fixed temperature settings and simple sensor feedback to adjust the in-vehicle temperature and airflow manually or through preset modes. However, such systems cannot fully consider the personalized comfort needs of different users, nor can they adapt to complex external environmental changes in real time, such as seasons, diurnal temperature differences, humidity, and different driving scenarios.

[0003] There are some defects and shortcomings in the existing technology: Lack of personalized adaptability: Traditional thermal management systems typically use uniform temperature and airflow settings, which cannot be personalized according to individual user differences (such as age, gender, physical condition, etc.), making it difficult to meet the comfort needs of different users.

[0004] Poor environmental adaptability: The existing system has limited ability to respond to changes in the vehicle's external environment and cannot dynamically adjust the in-vehicle temperature and airflow in real time according to complex environmental factors such as season, day-night temperature difference, and humidity, resulting in insufficient comfort.

[0005] Low energy efficiency: Due to the lack of intelligent heat flow control and air distribution strategies, traditional systems waste energy and cannot effectively improve thermal management efficiency.

[0006] Lack of self-learning ability: Existing systems cannot learn and optimize users' comfort preferences through self-learning dynamic factors, making it difficult to achieve long-term comfort adaptation.

[0007] Simple control strategy: Traditional thermal management systems mainly rely on simple sensor feedback and preset modes, lacking the support of advanced control theory and cloud computing technology, making it difficult to achieve complex multi-dimensional parameter fusion and intelligent control. Summary of the Invention

[0008] To address the aforementioned technical problems, this invention provides a method for intelligent closed-loop control of vehicle comfort.

[0009] To achieve the above objectives, the present invention provides the following technical solution: This invention provides a vehicle comfort intelligent closed-loop control method, comprising the following steps: S1. The vehicle sensors collect vehicle environmental data and output signals to calculate the vehicle thermal load parameters under the current environmental conditions. S2. Collect user information and extract user thermal system data features, calculate and output user behavior analysis results; S3. Based on the vehicle thermal load parameters obtained in S1, the thermal load parameters are corrected and compensated using the user behavior analysis results in S2. Comfort control targets are defined and output for users and characteristic states. S4. Adjust the thermal system according to the comfort control target output by S3 to initially complete the comfort adjustment; S5. After the initial adjustment, monitor in real time whether the user actively adjusts the set parameters and provide real-time feedback to the next level to recalculate the control target. Simultaneously evaluate and score the control target, redefine user habits and record them, and perform data iteration and parameter optimization.

[0010] Preferably, in step S1, the vehicle thermal load parameters are calculated using a comfort control algorithm.

[0011] Preferably, in step S2, the user's thermal system data characteristics include the specific user's preferences for temperature, humidity, and airflow.

[0012] Preferably, in step S2, the user behavior analysis results are obtained through a big data-based behavioral habit processing algorithm, as follows: Based on a large amount of vehicle and user data, data features are extracted, and the cooling or heating energy requirements for different features are evaluated to complete data quantification. By using machine learning, the system continuously corrects the cooling or heating energy requirements of different characteristics under different environments, iterates and optimizes parameters, and achieves accurate judgment of behavioral habits.

[0013] Preferably, in step S3, the heat load parameter correction compensation amount is obtained based on the PWV evaluation model combined with existing big data models, as follows: The human body heat load is derived from the human body heat balance equation. The evaluation index of the PWV evaluation model is derived based on the human body's heat load. Based on the evaluation index of the PWV evaluation model, dynamic parameter compensation and optimization are performed to realize a control algorithm that matches the user and meets the thermal comfort needs of each user.

[0014] This invention also provides a vehicle comfort intelligent closed-loop control system for implementing the above-mentioned vehicle comfort intelligent closed-loop control method: It includes a big data information statistics module, a basic comfort module, a human thermal comfort big model, and a system execution module. The big data information statistics module and the basic comfort module are respectively connected to the front end of the human thermal comfort big model, and the system execution module is connected to the back end of the human thermal comfort big model. The big data information statistics module mainly uses cloud servers to collect user information, analyze user behavior, and extract user thermal system data features. The basic comfort module is used for environmental perception, collecting environmental data, and calculating the vehicle's thermal load under the current environmental conditions. The large-scale human thermal comfort model is used to generate specific comfort control targets, monitor user active operation records in real time, evaluate comfort control targets, and perform data iteration and optimization. The system execution module outputs control targets based on the human thermal comfort model, regulates the thermal system, and adjusts the overall vehicle comfort.

[0015] Compared with the prior art, the present invention provides a vehicle comfort intelligent closed-loop control method, which has the following beneficial effects: 1. This invention uses a self-learning control algorithm based on user feedback to score the control target based on the customer's active operation, analyze the user's temperature preference, and continuously optimize the control target in a closed loop based on the user's active adjustment actions to meet the customized comfort needs of individual users.

[0016] 2. During the monitoring process, this invention monitors whether the user actively adjusts the air conditioning settings. Based on the user's actual operation feedback, the human comfort model recalculates the target and scores the control target to confirm the user's habit type. Using the scoring principle, the user's preference for parameters such as temperature / airflow is evaluated based on the actual control results achieved. Based on the above scores, the user's control target is optimized and adjusted to achieve a better comfort adjustment effect.

[0017] The features and advantages of the present invention will be described in detail through embodiments and in conjunction with the accompanying drawings. Attached Figure Description

[0018] Figure 1 This is a flowchart of a vehicle comfort intelligent closed-loop control method according to the present invention; Figure 2 is a logic block diagram of the intelligent closed-loop control system for vehicle comfort of the present invention; Figure 3 is an interactive logic block diagram of the user big data and intelligent algorithm of the present invention; Figure 4 is a control flowchart of the intelligent comfort control algorithm of the present invention. Detailed Implementation

[0019] 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. However, it should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0020] See Figures 1-4 A method for intelligent closed-loop control of vehicle comfort includes the following steps: S1. The vehicle sensors collect vehicle environmental data and output signals to calculate the vehicle thermal load parameters under the current environmental conditions. S2. Collect user information and extract user thermal system data features, calculate and output user behavior analysis results; S3. Based on the vehicle thermal load parameters obtained in S1, the thermal load parameters are corrected and compensated using the user behavior analysis results in S2. Comfort control targets are defined and output for users and characteristic states. S4. Adjust the thermal system according to the comfort control target output by S3 to initially complete the comfort adjustment; S5. After the initial adjustment, monitor in real time whether the user actively adjusts the set parameters and provide real-time feedback to the next level to recalculate the control target. Simultaneously evaluate and score the control target, redefine user habits and record them, and perform data iteration and parameter optimization.

[0021] Preferably, in step S1, the vehicle thermal load parameters are calculated using a comfort control algorithm.

[0022] Preferably, in step S2, the user thermal system data characteristics include the specific user's preferences for temperature, humidity, and airflow.

[0023] Preferably, in step S2, the user behavior analysis results are obtained through a big data-based behavioral habit processing algorithm, as follows: Based on a large amount of vehicle and user data, data features are extracted, and the cooling or heating energy requirements for different features are evaluated to complete data quantification. By using machine learning, the system continuously corrects the cooling or heating energy requirements of different characteristics under different environments, iterates and optimizes parameters, and achieves accurate judgment of behavioral habits.

[0024] Preferably, in step S3, the heat load parameter correction compensation amount is obtained based on the PWV evaluation model combined with an existing big data model, as follows: The human body heat load is derived from the human body heat balance equation. The evaluation index of the PWV evaluation model is derived based on the human body's heat load. Based on the evaluation index of the PWV evaluation model, dynamic parameter compensation and optimization are performed to realize a control algorithm that matches the user and meets the thermal comfort needs of each user.

[0025] To further clarify: The thermal comfort PWV evaluation model is an evaluation index used to assess users' comfort of the environment. The calculation formula is: The PMV index is derived by introducing the human body heat load TL, which reflects the degree of deviation from the human body's thermal balance. It is assumed that the average skin temperature of the human body and the latent heat dissipation caused by sweating are the values ​​under the condition that the human body maintains comfort. The human body heat load TL is the heat storage rate S in the human body heat balance equation.

[0026] The human body's heat balance equation is MW=C+R+E+S; where M is the human body's energy metabolism rate, W is the mechanical work done by the human body, C is the heat dissipated from the human body's surface to the surrounding environment through convection, R is the heat dissipated from the human body's surface to the surrounding environment through radiation, E is the heat carried away by sweat evaporation and exhaled water vapor, and S is the human body's heat storage rate.

[0027] Indicator scale: The PMV index adopts a 7-level scale, namely hot (+3), warm (+2), slightly warm (+1), moderate (0), slightly cool (-1), cool (-2), and cold (-3).

[0028] Based on the evaluation results of PWV, the control algorithm performs dynamic parameter compensation and optimization to achieve a personalized control algorithm that meets the thermal comfort needs of each user.

[0029] This invention also provides a vehicle comfort intelligent closed-loop control system for implementing the above-mentioned vehicle comfort intelligent closed-loop control method: It includes a big data information statistics module, a basic comfort module, a human thermal comfort big model, and a system execution module. The big data information statistics module and the basic comfort module are respectively connected to the front end of the human thermal comfort big model, and the system execution module is connected to the back end of the human thermal comfort big model. The big data information statistics module mainly uses cloud servers to collect user information, analyze user behavior, and extract user thermal system data features. The basic comfort module is used for environmental perception, collecting environmental data, and calculating the vehicle's thermal load under the current environmental conditions. The large-scale human thermal comfort model is used to generate specific comfort control targets, monitor user active operation records in real time, evaluate comfort control targets, and perform data iteration and optimization. The system execution module outputs control targets based on the human thermal comfort model, regulates the thermal system, and adjusts the overall vehicle comfort.

[0030] Furthermore, the system modules and methods of this invention are implemented in the following specific ways: 1) Basic comfort module: Based on traditional comfort control algorithms, the vehicle's heat load under the current environmental conditions is calculated by inputting signals from sensors such as ambient temperature, in-vehicle temperature, and solar radiation intensity. Then, the cooling / heating capacity of the thermal system is confirmed based on the heat load parameters, and the target air outlet temperature of the system is calculated. 2) Big Data Information Statistics Module: Based on the thermal system-related database uploaded by the cloud server for the whole vehicle, including but not limited to user ID, gender and body type characteristics, the target in-vehicle temperature, clothing, etc., after a large amount of database and feature extraction, the module calculates the user's behavioral habits in different scenarios and proposes the user's preferences for temperature, humidity and airflow.

[0031] 3) Large-scale thermal comfort model: Based on the calculation results of the basic comfort module, the calculation results of the basic comfort module are corrected and compensated using user behavior analysis results. For example, different compensations are made for parameters such as male / female, age differences, and clothing differences. At the same time, the system monitors and records user active operations. For example, when a user actively adjusts the air volume or sets the temperature, the system analyzes the user's behavioral purpose and actively adjusts the target value to meet the user's needs. Through the above continuous self-learning optimization of the control target, the target results are scored to evaluate the user's preference for hot and cold, and the results are recorded in the large-scale thermal comfort model.

[0032] 4) System Execution Module: This module is responsible for executing the control results output from the upper layer, ensuring that the control objectives of the upper layer are effectively executed and achieved; Specifically, the processing algorithm based on big data processing behavior habits in this invention is as follows: The data, including vehicle and user data downloaded from the cloud server, requires over 50,000 sets of data. Extracted data includes, but is not limited to, wind speed settings, light intensity, gender, age, clothing, metabolism, temperature, and humidity. The system assesses the cooling or heating energy requirements of different characteristics. For example, a person wearing long-sleeved clothing in summer needs 100W of cooling capacity, while a person wearing short-sleeved clothing needs 80W. This is quantified using analogies, as shown in the parameter compensation tables in Tables 1 and 2. Through machine learning, the system continuously adjusts the cooling or heating requirements of different characteristics in different environments, iterating and optimizing parameters to achieve accurate behavioral habit determination.

[0033] Table 1. Energy Compensation Based on Age Table 2. Based on male and female energy compensation values Referring to Figure 3, the closed-loop control process for comfort performance is as follows: The system collects parameters from the vehicle's sensors and calculates the basic energy demand using basic module algorithms. It then uses cloud server data to statistically analyze the behavioral habits and energy demand compensation values ​​of different users. The calculation of the basic energy demand and the behavioral target energy demand results in the final comfort energy demand. The control execution system achieves the control target and monitors whether the user actively adjusts the set parameters during the process. The system then feeds this feedback back to the human comfort model to recalculate the target and scores the control target to determine the user's type of habit, such as preferring a comfortable target temperature (3 points) or a slightly warmer target temperature (5 points).

[0034] Based on the feedback from the actual control target value, the customer's preferred temperature control range is evaluated, such as on a scale of 1 to 5, as shown in Table 3: Table 3 Scoring Sheet To further explain: The system execution module's main function is to implement cooling / heating functions, and it can adjust the outlet air temperature / air outlet mode / air outlet air volume, etc. Its main components are: 1. Cooling / Heating Unit Compressor: The "heart" of the air conditioner, responsible for compressing the refrigerant (such as Freon, R32, etc.), increasing its pressure and temperature, and driving the refrigerant to circulate within the system.

[0035] Types: reciprocating, scroll, centrifugal, etc. (household air conditioners are mostly scroll type, while large central air conditioners commonly use centrifugal type).

[0036] Condenser: The refrigerant releases heat and condenses into a liquid here (when cooling, the heat exchanger of the outdoor unit of a household air conditioner is the condenser; when heating, it switches to the evaporator through a four-way valve).

[0037] Types: Air-cooled (heat exchanged between the fan and the air, such as the outdoor unit of a household unit), water-cooled (heat exchanged between cooling water and water, such as the cooling tower equipment of a large central air conditioning system).

[0038] Evaporator: The refrigerant evaporates and absorbs heat here, lowering the ambient air temperature (when cooling, the indoor unit's heat exchanger is the evaporator; when heating, it switches to the condenser).

[0039] Function: It exchanges heat directly with the air to achieve cooling or heating.

[0040] Throttling device (expansion valve / capillary tube): controls the refrigerant flow rate, throttles and reduces the pressure of the high-pressure liquid, and allows it to quickly evaporate and absorb heat after entering the evaporator.

[0041] Types: Capillary tube (commonly used in household fixed-frequency air conditioners), electronic expansion valve (commonly used in variable-frequency air conditioners, which can precisely adjust the flow rate).

[0042] II. Air Handling System (Adjusting Air Parameters) Responsible for delivering treated air into the room and exhausting indoor air, mainly including: 1. Air handling equipment Fan: Drives airflow and delivers treated air into the room (such as the cross-flow fan of the indoor unit and the centrifugal fan of the central air conditioning).

[0043] Heat exchanger (evaporator / condenser): It comes into direct contact with the air and achieves cooling, heating or dehumidification of the air through the phase change of the refrigerant (during refrigeration, the evaporator cools down and condenses the moisture in the air to achieve dehumidification).

[0044] Humidifier / Dehumidifier: Humidifiers: Increase air humidity in dry environments (such as ultrasonic humidifiers and electrode humidifiers).

[0045] Dehumidifiers reduce air humidity in high-humidity environments (through evaporator condensation or rotary adsorption).

[0046] Filters: Filter dust, particulate matter, odors, etc. in the air to improve air cleanliness (such as pre-filters and HEPA filters).

[0047] III. Control System (Core of Operation and Regulation) Automating the operation of the air conditioning system through sensors and controllers to ensure stable environmental parameters includes: 1. Sensor Temperature sensor: detects indoor, outdoor or heat exchanger temperature (such as NTC thermistor).

[0048] Humidity sensor: detects indoor air humidity (such as capacitive humidity sensor).

[0049] Pressure sensor: detects refrigerant pressure (used to protect the compressor from overpressure or underpressure failures).

[0050] Wind speed sensor: monitors the air volume delivered by the fan (equipped in some high-end systems).

[0051] 2. Controller Main control board: Receives sensor signals and controls the start-up, shutdown, and operation status of equipment such as compressors, fans, and valves according to set parameters (such as target temperature).

[0052] Control panel: The user interface used to set temperature, fan speed, mode (cooling / heating / air supply / dehumidification), etc. (such as the remote control of a household air conditioner or the wired controller of a central air conditioner).

[0053] Auxiliary controllers include: frequency converters (to adjust compressor speed), four-way valves (to switch between cooling and heating modes), and electronic expansion valve controllers.

[0054] The algorithms for big data processing are as follows: The algorithm uses cross-feature analysis to identify the relationship between user characteristics and comfort temperature settings. Then, it uses aggregated feature analysis to statistically analyze this information and confirm the preferences for comfort temperature settings for different ages and genders. This data, after processing a large number of user data, is used to compensate for the vehicle's thermal load. Essentially, the basic algorithm incorporates the calculation of large data processing results.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions or improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent closed-loop control of vehicle comfort, characterized in that: Includes the following steps: S1. The vehicle sensors collect vehicle environmental data and output signals to calculate the vehicle thermal load parameters under the current environmental conditions. S2. Collect user information and extract user thermal system data features, calculate and output user behavior analysis results; S3. Based on the vehicle thermal load parameters obtained in S1, the thermal load parameters are corrected and compensated using the user behavior analysis results in S2. Comfort control targets are defined and output for users and characteristic states. S4. Adjust the thermal system according to the comfort control target output by S3 to initially complete the comfort adjustment; S5. After the initial adjustment, monitor in real time whether the user actively adjusts the set parameters and provide real-time feedback to the next level to recalculate the control target. Simultaneously evaluate and score the control target, redefine user habits and record them, and perform data iteration and parameter optimization.

2. The intelligent closed-loop control method for vehicle comfort as described in claim 1, characterized in that: In step S1, the vehicle thermal load parameters are calculated using a comfort control algorithm.

3. The intelligent closed-loop control method for vehicle comfort as described in claim 1, characterized in that: In step S2, the user thermal system data features include the specific user's preferences for temperature, humidity, and airflow.

4. The intelligent closed-loop control method for vehicle comfort as described in claim 1, characterized in that: In step S2, the user behavior analysis results are obtained through a big data-based behavioral habit processing algorithm, as follows: Based on a large amount of vehicle and user data, data features are extracted, and the cooling or heating energy requirements for different features are evaluated to complete data quantification. By using machine learning, the system continuously corrects the cooling or heating energy requirements of different characteristics under different environments, iterates and optimizes parameters, and achieves accurate judgment of behavioral habits.

5. The intelligent closed-loop control method for vehicle comfort as described in claim 1, characterized in that: In step S3, the heat load parameter correction compensation amount is obtained based on the PWV evaluation model combined with existing big data models, as follows: The human body heat load is derived from the human body heat balance equation. The evaluation index of the PWV evaluation model is derived based on the human body's heat load. Based on the evaluation index of the PWV evaluation model, dynamic parameter compensation and optimization are performed to realize a control algorithm that matches the user and meets the thermal comfort needs of each user.

6. A vehicle comfort intelligent closed-loop control system, used to implement the vehicle comfort intelligent closed-loop control method according to any one of claims 1 to 5, characterized in that: It includes a big data information statistics module, a basic comfort module, a human thermal comfort big model, and a system execution module. The big data information statistics module and the basic comfort module are respectively connected to the front end of the human thermal comfort big model, and the system execution module is connected to the back end of the human thermal comfort big model. The big data information statistics module mainly uses cloud servers to collect user information, analyze user behavior, and extract user thermal system data features. The basic comfort module is used for environmental perception, collecting environmental data, and calculating the vehicle's thermal load under the current environmental conditions. The large-scale human thermal comfort model is used to generate specific comfort control targets, monitor user active operation records in real time, evaluate comfort control targets, and perform data iteration and optimization. The system execution module outputs control targets based on the human thermal comfort model, regulates the thermal system, and adjusts the overall vehicle comfort.

Images