Partition temperature control method, system and device for vehicle cabin and readable storage medium

Abstract

The invention discloses a partition temperature control method for a vehicle cabin, and the method is characterized in that the method comprises the following steps: S1, obtaining the temperature distribution data in the cabin; s2, fusing the temperature distribution data and preset environment temperature and humidity data to generate a dynamic partition thermodynamic diagram; s3, identifying the posture of the passenger through a convolutional neural network unit, and predicting future temperature and thermal comfort requirements based on the dynamic partition thermodynamic diagram through an LSTM model; s4, after an air conditioner controller receives the predicted thermal comfort degree demand signal, the working state of a semiconductor chilling plate of an independent execution mechanism of each air outlet is controlled and adjusted, and the air supply temperature is adjusted; the air conditioner controller transmits a PWM signal to the PWM air volume controller, the PWM controller adjusts the duty ratio of the PWM air valve after receiving the PWM signal, the micro stepping motor adjusts the opening degree of the air outlet blades of the independent air outlets according to the PWM signal transmitted by the PWM air valve to adjust the air supply volume, and temperature regulation and control required by different individuals are adapted.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent automobile environmental control, and specifically relates to a zoned temperature control method, system, device and readable storage medium for a vehicle cabin. Background Art

[0002] Modern vehicle cabin temperature control systems often rely on a limited number of fixed temperature sensors for environmental monitoring, which have significant limitations in spatial resolution and dynamic response. Traditional solutions use contact sensors installed on the dashboard or ceiling to obtain single-point temperature data, which cannot accurately reflect the differences in thermal sensation of occupants' body surfaces. Research shows that in typical driving scenarios, the temperature difference between the upper body and lower extremities of occupants often exceeds 4°C. However, existing systems, lacking refined thermal field sensing capabilities, often adopt a global mean adjustment strategy, resulting in frequent localized overcooling or overheating. Although some improved systems have introduced the concept of zoned temperature control (such as the solution described in CN114291044A), their control logic based on preset fixed zones cannot adapt to dynamic changes in occupant posture or when seats are vacant. In particular, in scenarios with significant differences in solar radiation intensity, energy allocation cannot be achieved on demand, resulting in over 20% inefficient energy consumption.

[0003] In recent years, infrared thermal imaging technology has begun to be applied to cabin environmental perception, exemplified by the thermal radiation detection solution proposed in Tesla's patent US20210197872A1. While this technology can capture occupant surface temperature distribution, it faces multiple bottlenecks in practical application. Limited by the resolution of on-board infrared cameras (typically 384×288 pixels) and a temperature measurement accuracy of ±1.5°C, the system's ability to discern subtle temperature gradients is limited. Furthermore, existing solutions often rely on single-source heat data for air conditioning control, failing to deeply integrate multi-dimensional parameters such as ambient temperature, humidity, and airflow velocity. This leads to systematic biases in the temperature compensation algorithm. More significantly, traditional air outlet control mechanisms generally employ a linked damper design, which prevents independent air volume and temperature regulation for each outlet unit. Consequently, sudden changes in heat load in a local area force the system to activate full-cabin temperature control, resulting in a double loss of energy efficiency and comfort. These technical shortcomings are particularly pronounced in new energy vehicles, where the additional energy consumption of the air conditioning system can directly reduce driving range by 12%-15%. A breakthrough is urgently needed through high-precision thermal field reconstruction and coordinated control of distributed actuators.

[0004] Therefore, how to design a zoned temperature control method, system, device and readable storage medium for a vehicle cabin to urgently solve the above-mentioned technical problems that need to be solved. Summary of the Invention

[0005] The present invention aims to provide a method, system, device and readable storage medium for zoned temperature control of a vehicle cabin, a method and system for independently controlling each air outlet of a vehicle air conditioner to adjust the temperature, thereby achieving precise and flexible adjustment of the temperature in the cabin, improving the comfort of occupants in the cabin, and improving the energy utilization efficiency of the air conditioning system.

[0006] Technical solution: To achieve the above technical objectives, the present invention adopts the following technical solution: A vehicle cabin zone temperature control method, comprising the following steps: S1. Obtaining cabin temperature distribution data; S2. Fusion of temperature distribution data with preset ambient temperature and humidity data to generate a dynamic partitioned heat map; S3. Use convolutional neural network units to identify occupant posture and use an LSTM model to predict future temperature and thermal comfort needs based on a dynamic partitioned heat map. S4. After receiving the predicted thermal comfort demand signal through the air conditioning controller, the control adjusts the working state of the semiconductor refrigeration film of each air outlet independent actuator and adjusts the air supply temperature; The air conditioning controller transmits a PWM signal to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro stepping motor adjusts the opening of the air outlet blades according to the PWM signal transmitted by the PWM air valve to adjust the air supply volume.

[0007] Preferably, step S1 further includes step S11, wherein the infrared camera starts the short integration mode in the strong light area to avoid pixel saturation; switches to the long integration mode in the shadow area to improve the signal-to-noise ratio, and the infrared camera outputs the digital thermal signal using a two-point correction method to dynamically update the gain coefficient matrix G(x, y) and the offset matrix O(x, y) to perform non-uniformity correction. The calculation formula is: (1), Among them, the above formula (1) T calibrated ( x , y ) is the temperature value after calibration, T raw (x, y) is the original temperature signal to eliminate the error caused by the temperature drift of the infrared camera; The equivalent emissivity of the front windshield composite interlayer is calculated according to the following formula (2): : (2), Among them, the above formula (2) r 1 is the reflectivity of the interface between air and glass, r 2 is the reflectivity of the glass-PVB interface, α is the PVB absorption coefficient, dis the thickness of the laminated glass; According to the equivalent emissivity Compensate the temperature measurement of the window area to reduce the temperature measurement error of the window area inside the cabin.

[0008] Preferably, step S2 further includes step S21, establishing a six-degree-of-freedom heat transfer equation: (3), Calculate the energy flow in the cabin, Among them, the above formula (3) p =1.2kg / m³ is the air density, c p =1005J / (kg·K) is the specific heat capacity at constant pressure, k =0.026W / (m·K) is the thermal conductivity, h =8W / (m²·K) is the convection heat transfer coefficient, The finite volume method is used to discretize the cabin into multiple control volumes, and the particle filter algorithm is used to process the temperature, humidity, air pressure and CO2 concentration data. A Kriging interpolation model is constructed to generate a three-dimensional environmental parameter field, and its variation function is set as: (4), Wherein, c0 in the above formula (4) is the nugget constant, c is the base value, a is the range, h is the sensor spacing, Sharp-change boundaries in the temperature field are detected, and bidirectional region expansion is performed using each edge segment as a seed. Adjacent grids with similar thermal time constants are merged, and the ambient temperature and humidity data are integrated to generate a dynamic partitioned thermal map.

[0009] Preferably, in step S3, step S3 further includes step S311, inputting the dynamic partition heat map, the door switch signal and the historical temperature change rate into the LSTM model, and the LSTM model outputs the predicted temperature field T pred ( x , y , t +30s) (5), predict the temperature distribution in the next 30 seconds, Among them, in the above formula (5) x,y For coordinates x axis, y axis ；t +30s is the time 30 seconds after the current moment. Real-time analysis and recognition of occupant posture through convolutional neural network unit: Infrared thermal image, seat pressure distribution and light intensity parameters are input into the convolutional neural network unit, which calculates the occupant's sitting angle i and limb coverageC =Total number of grids and number of obscured grids, The LSTM model predicts the temperature field based on the output T pred by β e 0.5|Δ T pred ∣+(1 β ) cos i Match and predict thermal comfort needs, in, β =0.6 is the temperature weight, Δ T pred To predict temperature deviation, i For the sitting posture inclination, the temperature controller performs dynamic regulation of the air supply temperature and air volume; Preferably, step S4 further includes step S41, according to the PID temperature control algorithm using the following formula (5): (6), Calculate the required thermal power Q req , dynamically adjust the air supply temperature and air volume of the independent air outlet actuator, Among them, in the above formula (6) Q req is the required thermal power, ΔT is the temperature deviation, kp is the current temperature difference, who The accumulation of historical temperature differences, kd is the temperature difference change trend, ΔTdt is the time integral of the historical temperature difference, is the temperature difference change rate, The dynamic output of the air conditioning controller contains the thermal power Q req The PWM signal of the information is sent to the PWM air volume controller and the semiconductor refrigeration chip, which is conducive to grid-based partition temperature control.

[0010] A temperature control system for a vehicle cabin zone temperature control method, characterized by comprising an infrared camera, a data processing module, an air conditioning controller and a plurality of independent air outlet actuators, The infrared camera is installed in the middle of the vehicle roof and is used to collect real-time surface temperature distribution data in the cabin; The data processing module is in communication with the infrared camera and is used to fuse the temperature distribution data in the cabin with the preset ambient temperature and humidity data to generate a dynamic partitioned thermal map; The air conditioning controller is in communication with the data processing module, and is used to control and drive each independent air outlet actuator to adjust the air supply temperature and air volume of the corresponding area.

[0011] Preferably, the data processing module includes a Kalman filter unit, the Kalman filter unit is communicatively connected to the infrared camera, and the Kalman filter unit is used to fuse the infrared temperature data with the ambient temperature and humidity sensor data; a convolutional neural network unit, the convolutional neural network unit being communicatively connected to the Kalman filter unit, wherein a training data set of the convolutional neural network unit includes data associated with an occupant's sitting posture and body surface temperature distribution; Temperature distribution data, seat pressure distribution, and light intensity parameters are input into the input layer of the convolutional neural network unit to identify the occupant posture; The LSTM model is communicatively connected to the convolutional neural network unit, and the dynamic partition heat map, the door switch signal, and the historical temperature change rate are input into the LSTM model to predict future temperature and thermal comfort needs.

[0012] Preferably, the independent air outlet actuator includes: a micro-stepping motor, the micro-stepping motor is connected to the air outlet blades of the air conditioner in the cabin, and the micro-stepping motor is used to drive the air outlet blades to flip; The semiconductor refrigeration chip is arranged inside the air outlet and is electrically connected to the air conditioning controller. After receiving the dynamic partition signal of the dynamic partition heat map, the air conditioning controller controls the working state of the semiconductor refrigeration chip to adjust the air supply temperature; A PWM air volume controller is electrically connected to the air conditioning controller and the stepper motor driver on the micro-stepping motor. After receiving the dynamic partition signal of the dynamic partition heat map, the air conditioning controller transmits a PWM signal to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro-stepping motor adjusts the opening of the blades according to the PWM signal transmitted by the PWM air valve, thereby adjusting the air supply volume. A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of a zoned temperature control method for a vehicle cabin are implemented.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a method for zoned temperature control of a vehicle cabin.

[0014] Compared with the existing technology, the beneficial effects are: 1) This method and system can independently control each air outlet of the vehicle air conditioner to adjust the temperature, realize accurate and flexible adjustment of the temperature in the cabin, improve the comfort of the people in the cabin, and at the same time improve the energy utilization efficiency of the air conditioning system.

[0015] This system uses infrared cameras to monitor the temperature of the entire cabin with an accuracy of ±0.5°C. Combined with independent air outlet control, it reduces regional temperature differences to within 1°C, significantly improving comfort. It adopts a dual-temperature cooling source system and waste heat recovery technology, improving energy efficiency by 25-30% in summer and reducing measured energy consumption by 15-20%. Relying on 30Hz real-time temperature updates and <100ms control delay, it can quickly respond to sudden environmental changes. It also supports multi-passenger zoned temperature control and status recognition, dynamically adapting to different individual needs and scene changes, and realizing personalized energy-saving adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 Schematic diagram of the flow of the vehicle cabin zone temperature control method of the present invention; Figure 2 Schematic diagram of the generated dynamic partition heat map. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] Reference Figure 1 to Figure 2 A first aspect of the present invention provides a method for controlling temperature of a vehicle cabin by zones, comprising the following steps: S1. Use an infrared camera located in the middle of the vehicle's roof to obtain temperature distribution data within the cabin. S2. The data processing module in the vehicle cabin fuses the temperature distribution data with the preset ambient temperature and humidity data to generate a dynamic partition heat map; S3. Recognize occupant posture using network neural units and predict future temperature and thermal comfort needs based on dynamic partitioned heat maps using an LSTM (Long Short-Term Memory) model. S4. After receiving the predicted thermal comfort demand signal through the air conditioning controller, the control adjusts the working state of the semiconductor refrigeration film of each air outlet independent actuator and adjusts the air supply temperature; After receiving the thermal comfort demand signal through the air conditioning controller, the PWM signal is transmitted to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro stepping motor adjusts the opening of the air outlet blades according to the PWM signal transmitted by the PWM air valve to adjust the air supply volume, so that the temperature of each zone deviates from the target value by ≤1°C.

[0020] Specifically, step S1 also includes step S11, where the infrared camera can adopt an infrared thermal imaging system using a quantum infrared detector array and configure a dual integration time mode to cope with high dynamic range temperature distribution in the cabin.

[0021] The infrared camera uses a short integration mode (10μs) in brightly lit areas (>80,000 Lux) to avoid pixel saturation; it switches to a long integration mode (100ms) in shadowed areas (<100 Lux) to improve the signal-to-noise ratio. The infrared camera outputs a 14-bit digital thermal signal representing the raw temperature matrix in a 10cm×10cm grid. The two-point correction method dynamically updates the gain coefficient matrix G(x,y) and the offset matrix O(x,y) for non-uniformity correction. The calculation formula is: (1), Among them, the above formula (1) T calibrated ( x , y ) is the temperature value after calibration, T raw (x, y) is the original temperature signal to eliminate the error caused by the temperature drift of the infrared camera; This calibration process is automatically performed every 30 seconds to eliminate errors caused by temperature drift of the detector.

[0022] The equivalent emissivity of the front windshield composite interlayer is calculated according to the following formula (2): : (2), Among them, the above formula (2) r 1=0.04 is the reflectivity of the air-glass interface, r 2=0.96 is the reflectivity of the glass-PVB (laminated glass) interface, α =0.8c ¹ is the PVB absorption coefficient, d =0.76mm is the thickness of laminated glass.

[0023] According to the equivalent emissivity The temperature measurement in the window area is compensated to reduce the temperature measurement error in the window area. After this compensation, the temperature measurement error in the window area in the cabin is reduced from ±2.1℃ to ±0.5℃.

[0024] Specifically, step S2 also includes step S21, establishing a six-degree-of-freedom heat transfer equation: (3), Calculate the energy flow in the cabin, Among them, the above formula (3) p =1.2kg / m³ is the air density, c p =1005J / (kg·K) is the specific heat capacity at constant pressure, k =0.026W / (m·K) is the thermal conductivity, h =8W / (m²·K) is the convection heat transfer coefficient.

[0025] The finite volume method is used to discretize the cabin into 12,000 control volumes, each with a size of 5cm×5cm×5cm. The temperature, humidity, air pressure, and CO2 concentration data from 12 distributed sensors are synchronously processed at a frequency of 200Hz using a particle filter algorithm.

[0026] A Kriging interpolation model is constructed to generate a three-dimensional environmental parameter field, and its variation function is set as: (4), Among them, c0=0.2 in the above formula (4) is the nugget constant, c=1.5 is the base value, and a=0.5m is the range.

[0027] The Canny operator is used to detect sharp boundaries in the temperature field (i.e., areas where the temperature changes dramatically, such as the edge of the occupant's body, the junction of direct sunlight and shadow). Then, bidirectional region expansion is performed using each edge segment as a seed, and adjacent grids with similar thermal time constants are merged. The ambient temperature and humidity data are integrated to generate a dynamic partitioned thermal map.

[0028] Specifically, step S3 also includes step S311, where the LSTM (Long Short-Term Memory Network) model predicts the temperature distribution in the next 30 seconds based on the dynamic partition heat map: Specifically, the input parameters of LSTM include the current dynamic partition heat map, the door switch signal and the historical temperature change rate. The LSTM model outputs the predicted temperature field. T pred ( x , y , t +30s)(5), Among them, in the above formula (5) x,y For coordinates xaxis, y axis ；t +30s is the time 30 seconds after the current moment. When the door is detected to be open, it is predicted that the temperature of the driver's leg area will drop by 2.8°C within 15 seconds.

[0029] At the same time, the convolutional neural network unit is used to analyze and identify the occupant's posture in real time: the infrared thermal image, seat pressure distribution and light intensity parameters are input into the convolutional neural network unit, and the convolutional neural network unit calculates the occupant's sitting inclination angle i and limb coverage C =Total number of grids × number of obscured grids.

[0030] Especially, when the sitting angle i >120° and limb (abdomen) coverage C When it is >80%, it is marked as pregnant posture.

[0031] The LSTM model then predicts the temperature field based on the output T pred by β e 0.5|Δ T pred ∣+(1 β ) cos i Match and predict thermal comfort needs, in, β =0.6 is the temperature weight, Δ T pred To predict temperature deviation, i The temperature controller performs dynamic control: for normal adults, it adopts progressive dual-parameter coordinated control. The temperature controller is based on the 30-second temperature deviation Δ predicted by LSTM. T pred , proportionally correct the air supply temperature, the temperature controller adjusts the temperature according to the sitting angle i (Standard 90°) Dynamically adjust air volume; Among them, pregnant women's posture and Target leg temperature rise And the air volume is reduced by 40%; children's posture and This solution reduces the 30-second temperature prediction error from Compress to The satisfaction rate among special groups reached 96%, and the misadjustment caused by sudden posture changes decreased by 67%.

[0032] Specifically, step S4 also includes step S41, the air conditioning controller calculates the required power according to the PID temperature algorithm using the following formula (5):Q req , (6), Calculate the required thermal power Q req , dynamically adjust the air supply temperature and air volume of the independent air outlet actuator; Among them, in the above formula (6) Q req is the required thermal power, ΔT is the temperature deviation, kp is the proportional term coefficient, who is the integral term coefficient, kd is the differential term coefficient, ΔTdt is the time integral of the historical temperature difference, is the temperature difference change rate, The dynamic output of the air conditioning controller contains the thermal power Q req The PWM signal of the information is sent to the PWM air volume controller and the semiconductor refrigeration chip to achieve fast response, eliminate steady-state errors and suppress temperature overshoot, which is conducive to the realization of grid-based zone temperature control.

[0033] A second aspect of the present invention provides a vehicle cabin zone temperature control system based on infrared thermal imaging, comprising an infrared camera, a data processing module, an air conditioning controller, and a plurality of independent air outlet actuators, characterized in that: The infrared camera is installed in the middle of the vehicle roof and is used to collect real-time surface temperature distribution data in the cabin; The data processing module is in communication with the infrared camera and is used to fuse the temperature distribution data in the cabin with the preset ambient temperature and humidity data to generate a dynamic partitioned heat map. The dynamic partitioned heat map is generated based on the division criteria of temperature difference ≥ 2°C and area ≥ 200 cm²; The air conditioning controller is in communication with the data processing module, and is used to control and drive each independent air outlet actuator to adjust the air supply temperature and air volume of the corresponding area.

[0034] It should be noted that, in this embodiment, the detection band of the infrared camera is 8-14 μm, the resolution is not less than 640×480 pixels, and the temperature measurement accuracy is ±0.5°C.

[0035] In a preferred embodiment, the data processing module includes: a Kalman filter unit, the Kalman filter unit is communicatively connected to the infrared camera, and the Kalman filter unit is used to fuse the infrared temperature data with the ambient temperature and humidity sensor data; A convolutional neural network unit, wherein the convolutional neural network unit is in communication with the Kalman filter unit, and the training data set of the convolutional neural network unit includes at least 100,000 sets of data related to the sitting posture and body surface temperature distribution of the occupants, The temperature distribution data, seat pressure distribution and light intensity parameters are input into the input layer of the convolutional neural network unit to identify the occupant posture. The LSTM model is communicatively connected to the convolutional neural network unit, and the dynamic partition heat map, the door switch signal, and the historical temperature change rate are input into the LSTM model to predict future temperature and thermal comfort requirements.

[0036] In a preferred embodiment, the independent air outlet actuator includes: a micro-stepping motor connected to the air outlet blades of the air conditioner in the cabin, and the micro-stepping motor is used to drive the air outlet blades to flip; The semiconductor refrigeration chip is arranged inside the air outlet and is electrically connected to the air conditioning controller. After receiving the dynamic partition signal of the dynamic partition heat map, the air conditioning controller controls the working state of the semiconductor refrigeration chip (such as cooling on, cooling off, cooling intensity, heating on, heating off and heating intensity, supporting linear temperature control from -10°C to 50°C) to adjust the supply air temperature; A PWM air volume controller is electrically connected to the air conditioning controller and the stepper motor driver on the micro-stepping motor. After receiving the dynamic partition signal of the dynamic partition heat map, the air conditioning controller transmits a PWM signal to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro-stepping motor adjusts the opening of the blades (opening θ = 0°-75°) according to the PWM signal transmitted by the PWM air valve, thereby adjusting the air supply volume; A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the zoned temperature control method for the vehicle cabin are implemented.

[0037] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the vehicle cabin zone temperature control method.

[0038] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0039] In particular, according to some embodiments of the present disclosure, the process described above can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0040] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0041] In some embodiments of the present disclosure, a computer-readable signal medium may include a mission data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated mission data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or convey a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0042] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital task data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., adhoc peer-to-peer networks), as well as any currently known or later developed networks.

[0043] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to detecting a query operation on a production collaboration document in the switch production line management application, determines the network connection status of the switch production line management application; in response to determining that the network connection status of the switch production line management application represents an offline state, replaces the web page entry information corresponding to the production collaboration document with target entry file information, and loads target web page resource information to display the web page of the production collaboration document offline in the switch production line management application, wherein the target entry file information is file information of a pre-downloaded entry file corresponding to the web page of the production collaboration document, and the target web page resource information is locally stored resource information corresponding to the web page; in response to determining that the network connection status of the switch production line management application represents an online state and the web page resource information corresponding to the production collaboration document is not stored locally, downloads the web page resource information of the web page from the production line document server, wherein the web page resource information includes the entry file and resource information; displays the web page of the production collaboration document in the switch production line management application according to the web page resource information, and stores the web page resource information in a local database.

[0044] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including product-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0045] 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, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A vehicle cabin zone temperature control method, characterized in that: The following steps are involved: S1. Obtaining cabin temperature distribution data; S2. Fusion of temperature distribution data with preset ambient temperature and humidity data to generate a dynamic partitioned heat map; S3. Use convolutional neural network units to identify occupant posture and use an LSTM model to predict future temperature and thermal comfort needs based on a dynamic partitioned heat map. S4. After receiving the predicted thermal comfort demand signal through the air conditioning controller, the control adjusts the working state of the semiconductor refrigeration film of each air outlet independent actuator and adjusts the air supply temperature; The air conditioning controller transmits a PWM signal to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro stepping motor adjusts the opening of the air outlet blades according to the PWM signal transmitted by the PWM air valve to adjust the air supply volume.

2. The vehicle cabin zone temperature control method according to claim 1, wherein: Step S1 also includes step S11, in which the infrared camera starts the short integration mode in the strong light area to avoid pixel saturation; switches to the long integration mode in the shadow area to improve the signal-to-noise ratio. The infrared camera outputs the digital thermal signal and uses the two-point correction method to dynamically update the gain coefficient matrix G(x, y) and the offset matrix O(x, y) to perform non-uniformity correction. The calculation formula is: （1）， Among them, the above formula (1) T calibrated ( x , y ) is the temperature value after calibration, T raw (x, y) is the original temperature signal to eliminate the error caused by the temperature drift of the infrared camera; The equivalent emissivity of the front windshield composite interlayer is calculated according to the following formula (2): : （2）， Among them, the above formula (2) ρ 1 is the reflectivity of the interface between air and glass, ρ 2 is the reflectivity of the glass-PVB interface, α is the PVB absorption coefficient, d is the thickness of the laminated glass; According to the equivalent emissivity Compensate the temperature measurement of the window area to reduce the temperature measurement error of the window area inside the cabin.

3. The vehicle cabin zone temperature control method according to claim 1, wherein: Step S2 also includes step S21, establishing a six-degree-of-freedom heat transfer equation: （3）， Calculate the energy flow in the cabin, Among them, the above formula (3) p =1.2kg / m³ is the air density, c p =1005J / (kg·K) is the specific heat capacity at constant pressure, k =0.026W / (m·K) is the thermal conductivity, h =8W / (m²·K) is the convection heat transfer coefficient, The finite volume method is used to discretize the cabin into multiple control volumes, and the particle filter algorithm is used to process the temperature, humidity, air pressure and CO2 concentration data. A Kriging interpolation model is constructed to generate a three-dimensional environmental parameter field, and its variation function is set as: （4）， Wherein, c0 in the above formula (4) is the nugget constant, c is the base value, a is the range, h is the sensor spacing, Sharp-change boundaries in the temperature field are detected, and bidirectional region expansion is performed using each edge segment as a seed. Adjacent grids with similar thermal time constants are merged, and the ambient temperature and humidity data are integrated to generate a dynamic partitioned thermal map.

4. The vehicle cabin zone temperature control method according to claim 1, wherein: In step S3, step S3 also includes step S311, inputting the dynamic partition heat map, the door switch signal and the historical temperature change rate into the LSTM model, and the LSTM model outputs the predicted temperature field T pred ( x , y , t +30s) (5), predict the temperature distribution in the next 30 seconds, Among them, in the above formula (5) x,y For coordinates x axis, y axis ；t +30s is the time 30 seconds after the current moment. Real-time analysis and recognition of occupant posture through convolutional neural network unit: Infrared thermal image, seat pressure distribution and light intensity parameters are input into the convolutional neural network unit, which calculates the occupant's sitting angle θ and limb coverage C =Total number of grids and number of obscured grids, The LSTM model predicts the temperature field based on the output T pred by β e 0.5|Δ T pred ∣+(1 β ) cos θ Match and predict thermal comfort needs, in, β =0.6 is the temperature weight, Δ T pred To predict temperature deviation, θ The temperature controller dynamically adjusts the air supply temperature and air volume according to the sitting inclination angle.

5. The vehicle cabin zone temperature control method according to claim 4, characterized in that: Step S4 also includes step S41, according to the PID temperature control algorithm with the following formula (6) （6）， Calculate the required thermal power Q req , dynamically adjust the air supply temperature and air volume of the independent air outlet actuator, Among them, in the above formula (5) Q req is the required thermal power, ΔT is the temperature deviation, kp is the current temperature difference, ki The accumulation of historical temperature differences, kd is the temperature difference change trend, ΔTdt is the time integral of the historical temperature difference, is the temperature difference change rate, The dynamic output of the air conditioning controller contains the thermal power Q req The PWM signal of the information is sent to the PWM air volume controller and the semiconductor refrigeration chip, which is conducive to grid-based partition temperature control.

6. A temperature control system for a vehicle cabin zone temperature control method according to any one of claims 1 to 5, characterized in that: Including infrared camera, data processing module, air conditioning controller and multiple independent air outlet actuators, The infrared camera is installed in the middle of the vehicle roof and is used to collect real-time surface temperature distribution data in the cabin; The data processing module is in communication with the infrared camera and is used to fuse the temperature distribution data in the cabin with the preset ambient temperature and humidity data to generate a dynamic partitioned thermal map; The air conditioning controller is in communication with the data processing module, and is used to control and drive each independent air outlet actuator to adjust the air supply temperature and air volume of the corresponding area.

7. The vehicle cabin zone temperature control system according to claim 1, characterized in that: The data processing module includes: a Kalman filter unit, the Kalman filter unit is communicatively connected to the infrared camera, and the Kalman filter unit is used to fuse infrared temperature data with ambient temperature and humidity sensor data; a convolutional neural network unit, the convolutional neural network unit being communicatively connected to the Kalman filter unit, wherein a training data set of the convolutional neural network unit includes data associated with an occupant's sitting posture and body surface temperature distribution; Temperature distribution data, seat pressure distribution, and light intensity parameters are input into the input layer of the convolutional neural network unit to identify the occupant posture; The LSTM model is communicatively connected to the convolutional neural network unit, and the dynamic partition heat map, the door switch signal, and the historical temperature change rate are input into the LSTM model to predict future temperature and thermal comfort needs.

8. The vehicle cabin zone temperature control system according to claim 1, characterized in that: The independent air outlet actuator includes: a micro-stepping motor, the micro-stepping motor is connected to the air outlet blades of the air conditioner in the cabin, and the micro-stepping motor is used to drive the air outlet blades to flip; The semiconductor refrigeration chip is arranged inside the air outlet and is electrically connected to the air conditioning controller. After receiving the dynamic partition signal of the dynamic partition heat map, the air conditioning controller controls the working state of the semiconductor refrigeration chip to adjust the air supply temperature; A PWM air volume controller is electrically connected to the air conditioning controller and the stepper motor driver on the micro stepper motor. After the air conditioning controller receives the dynamic partition signal of the dynamic partition heat map, it transmits the PWM signal to the PWM air volume controller. After receiving the PWM signal, the PWM controller adjusts the duty cycle of the PWM air valve. The micro stepper motor adjusts the opening of the blade according to the PWM signal transmitted by the PWM air valve, thereby adjusting the air supply volume.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the steps of the vehicle cabin zone temperature control method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the vehicle cabin zone temperature control method according to any one of claims 1 to 5 are implemented.

Images