Thermal self-adaptive temperature control system and method for regulating and controlling thermal conductivity through graphene current

Abstract

The invention relates to the technical field of thermal management and control, in particular to a thermal self-adaptive temperature control system and method for dynamically controlling the thermal conductivity of a graphene film by adjusting the current in the graphene film so as to realize heat flow adjustment. The system is mainly composed of a graphene film module, a temperature sensor module, an ESP32 microcontroller module, a current driving module and a power supply module. The invention also provides an optimization control method based on deep reinforcement learning, and the method is used for improving the adjustment strategy of the thermal self-adaptive temperature control system based on graphene.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal management and control, and in particular to a thermal self-adaptive temperature control system and method for dynamically controlling the thermal conductivity by adjusting the current in a graphene film, thereby realizing the regulation of heat flow. It is applicable to multiple fields such as smart clothing, heat dissipation of electronic devices, and building energy conservation. Background Art

[0002] With the rapid development of science and technology, heat management has become a key issue in multiple fields. For example, the heat dissipation efficiency of electronic devices directly affects their performance, stability, and service life; building energy conservation requires highly efficient thermal control materials to meet the increasingly stringent energy consumption requirements. However, traditional thermal control technologies face limitations such as slow response speed, high energy consumption, and insufficient control accuracy, and cannot meet the requirements of modern applications for efficient, precise, and intelligent thermal control.

[0003] Graphene, as a two-dimensional nanomaterial, has received extensive attention in recent years due to its excellent physical and chemical properties, especially its high thermal conductivity. Research shows that the thermal conductivity of graphene can be dynamically adjusted with the change of current density under certain conditions. Utilizing this property, through precise adjustment of the current in the graphene film, a temperature control technical solution with rapid response, low energy consumption, and strong adaptability can be developed. However, current graphene-based thermal control technologies still have problems such as high design complexity, poor adaptability in practical applications, and insufficient optimization of control strategies.

[0004] Therefore, there is an urgent need for a new type of thermal management system that can efficiently utilize the unique properties of graphene, significantly improve the thermal control accuracy and response speed through an optimized current regulation method, and meet the requirements of various complex application scenarios. The present invention is proposed under this background, aiming to provide a set of efficient, intelligent, and low-energy-consuming thermal self-adaptive temperature control solutions through an innovative method of regulating the thermal conductivity by graphene current. Summary of the Invention

[0005] It should be understood that the above general description and the following detailed description of the present invention are both exemplary and explanatory, and are intended to provide further explanation of the present invention as claimed.

[0006] According to one aspect of the present invention, there is provided a thermal self-adaptive temperature control system for regulating the thermal conductivity by graphene current, including a graphene film module for adjusting the thermal conductivity of the graphene film through current, a temperature sensor module for collecting the ambient temperature and the surface temperature of the graphene film, a current driving module for adjusting the current density flowing through the graphene film according to a control signal; and a microcontroller module for receiving the data of the temperature sensor and generating a current regulation instruction to control the current driving module, thereby realizing the dynamic temperature control of the graphene film.

[0007] According to another aspect of the present invention, there is provided a thermal self - adaptive temperature control method for regulating thermal conductivity by graphene current, including: collecting real - time data of the ambient temperature and the surface temperature of the graphene film through a temperature sensor; calculating the required current density by a microcontroller based on the difference between the target temperature and the current temperature; adjusting the current flowing through the graphene film according to the current density by a current driving module; and adjusting the current output in real - time through a feedback control mechanism to keep the temperature of the graphene film within the target range.

[0008] According to yet another aspect of the present invention, there is provided an optimization control method based on deep reinforcement learning for improving the adjustment strategy of a graphene - based thermal self - adaptive temperature control system, including using the current temperature state, the target temperature, and the ambient temperature as inputs, and training a reinforcement learning model to predict an optimal current adjustment strategy; this strategy dynamically updates the control model through experience replay and real - time feedback mechanisms to optimize the temperature control accuracy and response speed.

[0009] According to still another aspect of the present invention, there is provided a hardware architecture and device for a thermal self - adaptive temperature control system and method for regulating thermal conductivity by graphene current, including a microcontroller module, a graphene film module, a temperature sensor module, and a current driving module for executing the above - mentioned methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a system architecture diagram of a thermal self - adaptive temperature control system and method for regulating thermal conductivity by graphene current, which shows the connection mode of an ESP32 microcontroller, a graphene film, a temperature sensor, and a driving circuit;

[0011] Figure 2 is a circuit diagram, as Figure 1 an embodiment in

[0012] Figure 3 shows the detailed design of the current driving circuit of a thermal self - adaptive temperature control system and method for regulating thermal conductivity by graphene current;

[0013] Figure 4 is a control flow chart, which describes the temperature control logic and feedback algorithm of a thermal self - adaptive temperature control system and method for regulating thermal conductivity by graphene current; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] As Figure 1 shown, the thermal self - adaptive temperature control system of the present invention mainly consists of five major modules: a graphene film module, a temperature sensor module, an ESP32 microcontroller module, a current driving module, and a power supply module.

[0015] At S101, it supports lithium battery and USB power supply, and the appropriate power supply can be selected according to different scenarios. In some mobile devices or outdoor scenarios, lithium battery power supply can conveniently provide power for the system; while in indoor or fixed devices, USB power supply is more convenient. In addition, an integrated power management chip is used to support real-time power monitoring and low-power reminder, enabling users to timely understand the power situation of the system and take corresponding measures. The power management chip can also optimize the power supply to improve the system efficiency. This power supply module can provide stable power support for the system to ensure the long-term operation of each module. It can provide the required electrical energy for the system to ensure the normal operation of the system.

[0016] At S102, the dynamic thermal conductivity can be adjusted by controlling the current flowing through the graphene film with a PWM signal. This module can accurately control the magnitude and direction of the current according to the PWM signal output by the microcontroller, and then adjust the thermal conductivity of the graphene film. To achieve this function, a MOSFET drive circuit that responds to the PWM signal is adopted, which can support a current output range of 0 - 2A. This drive circuit can quickly respond to the PWM signal to achieve precise control of the current. To protect the graphene film from damage caused by excessive current, we have set an integrated current limiting function. When the current exceeds a certain value, the system will automatically cut off the current to protect the film from damage.

[0017] At S103, ESP32 is adopted as the core control unit, which is responsible for receiving sensor data, calculating the current adjustment signal, and outputting the PWM signal. It plays a key role in the entire thermal adaptive temperature control system and can make corresponding control decisions according to the data collected by the sensors. It allows users to view and adjust the target temperature range in real time through Wi-Fi and Bluetooth. After reaching the target temperature, the system will enter the deep sleep state to save energy consumption. This mode can effectively extend the operation time of the system while reducing energy consumption.

[0018] At S104, temperature sensors such as DS18B20 or DHT22 are adopted because their detection accuracy can reach ±0.1°C, which can well sense the temperature changes on the surface of the graphene film and the surrounding environment. Multiple temperature sensors are arranged in the key areas of the graphene film to monitor the temperature distribution, so as to ensure that the film can maintain a uniform temperature in each area. Through multi-point arrangement, the system can timely detect temperature anomalies and make corresponding treatments. It is connected to the ESP32 through the I2C or UART interface to ensure the stable and reliable data transmission, and transmit the data collected by the temperature sensor to the microcontroller in a timely and accurate manner. The main function of the temperature sensor module is to collect the surface temperature of the graphene film and the ambient temperature in real time. These real-time data provide an important basis for the temperature control algorithm of the microcontroller, enabling the system to make adjustments according to the actual situation.

[0019] At S105, the graphene film can adopt a single-layer or multi-layer structure. The single-layer structure has a unique atomic arrangement and can exhibit specific physical properties; the multi-layer structure further optimizes the thermal conductivity of the material through the superposition between layers. The thickness and performance can be selected according to the requirements of specific application scenarios. For example, in scenarios with higher thermal conductivity requirements, a thicker multi-layer graphene film can be selected to increase the thermal conductivity. The film is fixed on a flexible substrate, and this flexible substrate such as polyimide has good flexibility. It can enable the graphene film to be easily applied to bendable devices. On the flexible substrate, the graphene film can deform as the device bends, and at the same time, it can maintain the stability of its performance. Both ends of the film are connected to the drive module through highly conductive electrodes. The highly conductive electrodes can ensure that the current flows through the film stably, thereby realizing the precise control of the thermal conductivity. The design of the electrodes needs to consider the compatibility and conductivity with the graphene film to ensure the efficient operation of the entire system. By adjusting the current density, the thermal conductivity of the graphene film can be adjusted from 300 W / m·K to 1000 W / m·K. This range can meet the requirements of most application scenarios.

[0020] Figure 2 For Figure 1 one of the embodiments, it describes the detailed design of the current drive circuit of the thermal self-adaptive temperature control system and method for regulating the thermal conductivity of graphene by current;

[0021] S201 is the power supply module, which can provide a 5V or 3.3V power supply. The ESP32 requires a 3.3V voltage to operate, while the voltage of the current drive circuit is 5V (which can be adjusted according to the selected type of MOSFET and current requirements). An external battery or adapter can also be used for power supply.

[0022] S202 is the ESP32 control module, which controls the conduction state of the MOSFET through the PWM signal, thereby regulating the current flowing through the graphene film. At the same time, the PWM signal can also adjust the duty cycle to control the intensity of the current and regulate the thermal conductivity of the graphene film.

[0023] S203 is the MOSFET: It regulates the current flowing through the graphene film by controlling the on-off of the current between the source and the drain. The gate of the MOSFET is controlled by the PWM signal of the ESP32. When the PWM signal is at a high level, the MOSFET is turned on, and when the PWM signal is at a low level, the MOSFET is turned off.

[0024] S204 is the graphene film module: It is the core part of thermal regulation, and the current of the graphene film is regulated by the MOSFET. When the current flowing through the graphene film increases, the thermal conductivity of graphene increases; when the current decreases, the thermal conductivity of graphene decreases.

[0025] S205 is the current-limiting resistor, which is used to limit the maximum current flowing through the graphene film to prevent damage to the circuit or the graphene film caused by excessive current. The appropriate resistance value can be selected according to the current specification of the graphene film.

[0026] Figure 3 is the flowchart of the control logic of the present invention. It can also be used as Figure 1 an embodiment in. It describes the temperature control logic and feedback algorithm of the thermal adaptive temperature control system and method for regulating the thermal conductivity by graphene current.

[0027] At step S301, the system startup work is performed, and the ESP32 microcontroller executes the initialization operation. It can be the following steps: call the temperature sensor driver, then initialize all connected DS18B20 temperature sensors, initialize the PWM output pins, set the PWM signal frequency and the initial duty cycle. Then start the current detection module, verify the integrity of the circuit connection, ensure that the power supply voltage and current are within the safe range. Read the user-set target temperature range from the EEPROM or Flash memory. If the user does not configure the target temperature, the system defaults to set the target temperature to 25 °C with a tolerance of ±0.5 °C. Verify the validity of the sensor data. After the self-check is completed, the system can enter the working mode.

[0028] At step S302, the temperature sensor collects the surface temperature of the graphene film and the ambient temperature in a periodic manner. By collecting the ambient temperature, the ambient temperature data is obtained by calling. If the data reading fails, the return value is an invalid value, the system records an error log, and attempts to read again. Then, the surface temperature of the film is read by collecting the temperature of the graphene film. When multiple sensors work simultaneously, the temperature values of all sensors are collected, data processing is performed, and then its weighted average is calculated. The collected data is smoothed and filtered to eliminate noise, thereby ensuring the stability and accuracy of the data. The collected temperature data is stored in the memory of the ESP32 for subsequent error calculation and control logic use.

[0029] At step S303, by judging the validity of the temperature data, the valid data and the invalid data can be diverted for subsequent work.

[0030] At step S304, the invalid data will be used to alert the user in the form of an error alarm, while the valid data will be further processed.

[0031] At step S305, the ESP32 calculates the error value (E) based on the target temperature (T1) and the current temperature (T2). The calculation formula is:

[0032] E = T1 - T2

[0033] After the calculation, a tolerance range judgment is made to determine whether it is within the tolerance range (such as ±0.5 °C). If the absolute value of the error is less than the tolerance range, it is considered that the temperature has reached the target range and no adjustment is required. Error classification: If the error is positive, the system increases the PWM duty cycle to increase the current, increases the thermal conductivity of the graphene film, and raises the current temperature. If the error is negative, the system reduces the PWM duty cycle to decrease the current and reduce the thermal conductivity of the film. At the same time, the system will also adjust the weight of the error value, control the sensitivity of the PWM adjustment according to the magnitude of the temperature difference, and avoid large adjustments that cause system oscillation.

[0034] At step S306, based on the error value, the system dynamically generates a PWM signal with a duty cycle range of 0% - 100%. At the same time, the system introduces a control algorithm to generate a PWM adjustment value according to the magnitude and change of the temperature difference. If the error is large and the change trend is increasing, the PWM duty cycle is quickly increased. If the error is small and the change trend is decreasing, the PWM duty cycle is slowly decreased.

[0035] At step S307, the ESP32 PWM output signal can be adjusted. The PWM adjustment requires calculating the current new PWM duty cycle. The formula for the new PWM duty cycle is

[0036] PWM = PWM1 + Kp × E + K d (E - E1)

[0037] Among them, Kp and Kd are the proportional coefficient and the differential coefficient, which are used to adjust the response speed and stability.

[0038] At step S308, the generated PWM signal is output to the MOSFET drive module. The frequency of the output signal is 1 kHz, and the duty cycle range is 0 - 255. Furthermore, the current flowing through the graphene film is adjusted by the MOSFET.

[0039] At step S309, the system updates the feedback control periodically with time, dynamically adjusts the PWM signal according to the new temperature data to form a closed-loop control. At the same time, the system re-collects the current temperature data and updates the error value. When the system detects that the frequency of temperature change is too high, it will reduce the adjustment amplitude of the PWM to avoid system oscillation caused by over-regulation. Then, parameters such as the current temperature, error value, and PWM duty cycle are recorded in the memory of the ESP32 to form a data trend. If the device supports long-term operation, it can be uploaded to the cloud regularly.

[0040] Figure 4 It is the flowchart of the present invention for optimizing the temperature control strategy through the deep reinforcement learning algorithm. The temperature control strategy optimization module based on deep reinforcement learning can be trained by this method.

[0041] At step S401, the policy network is initialized. A multi-layer perceptron based on the Q-network is constructed. Its input layer receives environmental state information, including the current temperature, target temperature, and environmental temperature. The hidden layer performs feature extraction and non-linear transformation through the ReLU activation function, and the output layer outputs the Q value of the action space, that is, the value corresponding to each PWM signal duty cycle. At the same time, the value network is initialized. It has the same structure as the policy network, with the environmental state information as the input and the state value as the output. The weight matrices are randomly initialized to ensure the randomness of the initial state of the network.

[0042] At step S402, an interaction with the environment is carried out. The current environmental temperature is read through the temperature sensor. The sensor converts the environmental temperature into an electrical signal and transmits it to the system. At the same time, the thermal conductivity regulation is controlled through the graphene film. According to the target temperature and the current temperature, the thermal conductivity of the graphene film is adjusted. When the temperature is too high, the thermal conductivity of the graphene film is increased to accelerate heat transfer; when the temperature is too low, the thermal conductivity is reduced to reduce heat loss.

[0043] At step S403, the transition data is stored in the replay buffer. The current state, reward, and the next state are stored in the replay buffer. At the same time, the current temperature, control current, and the obtained feedback reward are stored.

[0044] At step S404, a certain number of empirical data are randomly sampled to ensure the randomness and representativeness of the sampling. The sampled data are processed in batches, with each batch containing multiple samples, so as to perform parallel computing and optimization during the training process.

[0045] At step S405, according to the Q-learning algorithm, the Q-value of the action in the current state is calculated using the policy network. By iteratively updating the state-action value function, the optimal value is gradually approximated. At the same time, the value network is used to calculate the target value, and the target value is compared with the Q-value of the action in the current state, and the target value is adjusted according to the error.

[0046] At step S406, the mean squared error is used as the loss function to calculate the average of the squared errors between the predicted value and the true value. By minimizing the mean squared error, the Q-value or the policy is optimized.

[0047] At step S407, the backpropagation algorithm is used to calculate the gradient and update the neural network weights. Starting from the output layer, the error is propagated backward to the input layer to adjust the weight matrix. According to the gradient and the learning rate, the parameters are updated to ensure the stability and convergence of the parameters.

[0048] At step S408, new temperature and feedback information are obtained through the sensor and used as the input of the new state. The above training process is repeated to continuously optimize the neural network parameters and improve the performance and control accuracy of the system.

Claims

1. A thermally adaptive temperature control system based on graphene, characterized in that: The system includes the following modules: a graphene film module that adjusts its thermal conductivity through electric current to achieve temperature control; a current driving module that controls the thermal conductivity of the graphene film by adjusting the current flowing through the graphene film; a temperature sensor module that is used to collect the ambient temperature and the surface temperature of the graphene film in real time; and a microcontroller module that is used to receive signals from the temperature sensor and adjust the current driving module according to the temperature data, thereby controlling the temperature of the graphene film.

2. The thermally adaptive temperature control system according to claim 1, characterized in that: The thermal conductivity of the graphene film is adjusted by the current density flowing through the graphene film, and the change of the current density is linearly related to the thermal conductivity of the graphene film.

3. The thermally adaptive temperature control system according to claim 1, characterized in that: The current driving module includes a MOSFET driving circuit, and the MOSFET driving circuit adjusts the current density flowing through the graphene film through a PWM signal.

4. The thermally adaptive temperature control system according to claim 1, characterized in that: The temperature sensor is a digital temperature sensor selected from DS18B20 or DHT22 type.

5. The thermally adaptive temperature control system according to claim 1, characterized in that: The microcontroller is an ESP32 microcontroller, which can read temperature sensor data in real time and adjust the current drive module according to a preset control algorithm.

6. The thermally adaptive temperature control system according to claim 1, characterized in that: The system also includes a deep reinforcement learning module, which optimizes the current regulation strategy through a deep reinforcement learning algorithm to adjust the temperature control strategy according to real-time feedback.

7. The thermally adaptive temperature control system according to claim 1, characterized in that: The system monitors the temperature of the graphene film in real time through a feedback control mechanism and adjusts the current density to maintain temperature control accuracy.

8. The thermally adaptive temperature control system according to claim 1, characterized in that: The system can automatically adjust the target temperature in different application scenarios to meet different temperature control requirements, and is suitable for smart wearable devices, electronic devices, buildings and other fields.

9. The thermally adaptive temperature control system according to claim 1, characterized in that: The system exchanges data with the user's smart device through a wireless communication module, allowing the user to monitor and adjust temperature control parameters in real time.

10. The thermally adaptive temperature control system according to claim 1, characterized in that: By adjusting the thermal conductivity of the graphene film, the system can achieve fast and accurate temperature control at low power consumption, and is suitable for low-power application scenarios such as wearable devices, mobile devices and smart homes.

Images