Internet of Things automatic control method and system for medical temperature and humidity automatic control box

Abstract

The invention discloses an internet-of-things automatic control method and system for a medical temperature and humidity automatic control box, and relates to the technical field of medical cold chains, and the method comprises the following steps: setting a target temperature and a target humidity, initializing a coefficient of a dynamic weight distribution algorithm, and calibrating a sensor; carrying out preprocessing according to the calibrated sensor, collecting data in the box in real time, and calculating an external disturbance factor; based on the preprocessed data, calculating temperature and humidity deviation and a change rate thereof, generating a control weight through a dynamic weight distribution algorithm in combination with an external disturbance factor, and performing dynamic priority distribution of multi-target control; according to the calculated weight, a priority mode of temperature or humidity adjustment is selected, and an execution mechanism is driven; the execution result and the environment data are uploaded to a cloud end through an Internet of Things module, a user is supported to remotely adjust target parameters, and closed-loop control is formed; and circularly executing the steps until the temperature and the humidity are stabilized in the target range for three continuous periods or the user actively stops, and entering a low-power-consumption mode.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical cold chain, and in particular relates to an Internet of Things automatic control method and system for a medical temperature and humidity automatic control box. Background Art

[0002] In the field of medical transportation, drugs, vaccines, and biological samples have extremely high requirements for the temperature and humidity stability of the storage environment. Traditional medical temperature and humidity control boxes usually use fixed parameter control systems, relying on preset thresholds to trigger heating or cooling operations, which are difficult to cope with complex and changeable actual application scenarios. Existing technologies generally have problems such as single temperature and humidity control strategies and poor dynamic coupling adaptability. They cannot effectively coordinate the priority of multi-variable adjustment, resulting in control lag or overshoot. In addition, traditional systems lack deep integration of Internet of Things technology, making it difficult to achieve remote real-time monitoring and data-driven parameter optimization, and low operation and maintenance efficiency. External disturbance factors such as door opening and closing frequency and ambient temperature and humidity differences are often ignored, further reducing control accuracy and increasing energy consumption. It is impossible to dynamically allocate actuator weights according to real-time deviations, change rates, and external disturbances, which can easily cause resource conflicts or redundant operations. In addition, the lack of a closed-loop optimization mechanism makes historical data underutilized, and parameter drift or performance degradation may occur in long-term operation. These problems not only increase the risk of deterioration of medical supplies during transportation, but also lead to energy waste and increased equipment maintenance costs. Therefore, we propose an Internet of Things automatic control method and system for a medical temperature and humidity automatic control box. Summary of the invention

[0003] In order to solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is an Internet of Things automatic control method for a medical temperature and humidity automatic control box, comprising the following steps: Step S1: Set the target temperature and target humidity, initialize the coefficients of the dynamic weight allocation algorithm, set the control cycle, and calibrate the temperature sensor, humidity sensor and door magnetic sensor; Step S2: Preprocessing is performed based on the calibrated sensor to collect the temperature, humidity, door opening and closing times in the box and the external environment temperature and humidity in real time, and the noise is eliminated through sliding average filtering to calculate the external disturbance factor; Step S3: Based on the preprocessed data, the temperature and humidity deviations and their change rates are calculated, and combined with the external disturbance factors, the control weights of heating, cooling, humidification and dehumidification are generated through a dynamic weight allocation algorithm to perform dynamic priority allocation for multi-objective control; Step S4: selecting a priority mode for temperature or humidity regulation based on the calculated weight, driving the corresponding actuator, and dynamically adjusting the power or working time based on the weight value; Step S5: Upload the execution results and environmental data to the cloud through the Internet of Things module, support users to remotely adjust the target parameters, and optimize the coefficients in step 1 based on historical data to form a closed-loop control; Step S6: The above steps are executed repeatedly until the temperature and humidity are stable within the target range for three consecutive cycles, or the user actively terminates the process, and the system enters a low-power standby mode.

[0004] Furthermore, the step S1 includes the following steps: Step S11: Input through user terminal or default configuration setting and , initialize the coefficients , , , ; Step S12: calibrate the zero drift of the temperature sensor and the humidity sensor, and confirm the online status of the device through the Internet of Things module.

[0005] Furthermore, in step S2, the comprehensive impact of the external environment change on the internal environment of the box is quantified, and the external disturbance factor is defined , the calculation formula is as follows: ; In the formula, The external environment temperature is collected by the temperature and humidity sensor deployed outside the box. is the target temperature value of the automatic control box, The external environment humidity is collected by the temperature and humidity sensor deployed outside the box. is the target humidity value of the automatic control box, The number of times the door was opened and closed in the past five minutes.

[0006] Furthermore, the step S3 includes the following steps: Step S31, calculate the temperature and humidity deviation according to the collected data, and the temperature deviation formula is as follows: ; The humidity deviation formula is as follows: ; In the formula, It is the real-time temperature value measured inside the box, collected by the PT1000 temperature sensor. It is the real-time humidity value measured in the box, collected by the capacitive humidity sensor; Step S32, the formula for calculating the deviation change rate is as follows: Temperature deviation change rate: ; Humidity deviation change rate: ; In the formula, To control the cycle; Step S33: Implement dynamic priority allocation for heating, cooling, humidification and dehumidification control modes, combining real-time deviation, deviation change rate and external disturbance factor , define the dynamic weight allocation algorithm, the formula is as follows: ; In the formula, is the basic weight coefficient, is the nonlinear adjustment coefficient, is the change rate weight coefficient, is the external disturbance weight coefficient, is the temperature and humidity deviation, is the instantaneous change of temperature and humidity deviation, is the rate of change of deviation.

[0007] Furthermore, the step S4 includes the following steps: Step S41, comparing the maximum values ​​of the temperature control weight and the humidity control weight, and preferentially executing the type of adjustment with a higher weight; Step S42: Map the weight value to the specific operating parameters of the actuator, and define the control rule formula as follows: Heating power calculation formula: ; Cooling power limit function to avoid overload operation, the calculation formula is as follows: ; Humidification time calculation formula: (seconds / cycle); Dehumidification fan calculation formula: ; In the formula, is the output power of the heater, expressed in percentage. is the proportionality coefficient, and its value is a fixed constant of 0.1. is the heating control weight, reflecting the priority of the current heating demand. is the output power of the semiconductor refrigeration chip, in percentage. is a minimum function, ensuring that the cooling power does not exceed the rated maximum value (100%). is the cooling control weight, is the humidification time, which indicates the running time of the ultrasonic atomizer in each control cycle. is the humidification control weight, is the dehumidification fan speed, Control weights for dehumidification.

[0008] Furthermore, in step S5, to adapt to different environmental scenarios and reduce energy consumption, the cloud uses the gradient descent method to iteratively update the coefficients based on historical data. , , , and pushed to the device via wireless remote update.

[0009] Further, in step S6, when the temperature and humidity are stable for three consecutive cycles, and The control process is terminated when the system is out of range or the user actively shuts down the system.

[0010] An Internet of Things automatic control system for a medical temperature and humidity automatic control box, comprising a configuration management module, a sensor calibration module, a data acquisition module, a data processing module, a control algorithm module, an actuator control module, an Internet of Things communication module, a cloud interaction module, a circulation control module and a low power consumption management module; The output end of the configuration management module is unidirectionally connected to the input end of the sensor calibration module, the output end of the sensor calibration module is unidirectionally connected to the input end of the data acquisition module, the output end of the data acquisition module is unidirectionally connected to the input end of the data processing module, the output end of the data processing module is unidirectionally connected to the input ends of the control algorithm module and the cycle control module respectively, the output end of the control algorithm module is unidirectionally connected to the input end of the actuator control module, the output end of the actuator control module is unidirectionally connected to the input end of the Internet of Things communication module, the output end of the Internet of Things communication module is unidirectionally connected to the input end of the cloud interaction module, and the output end of the cloud interaction module is unidirectionally connected to the input end of the control algorithm module; the output end of the cycle control module is unidirectionally connected to the input end of the actuator control module and the input end of the low power management module respectively; The configuration management module is used to receive user input or load target temperature, humidity, control period, initialize the coefficients of the dynamic weight allocation algorithm, and set system operation parameters; The sensor calibration module includes a calibration temperature sensor, a capacitive humidity sensor, and a door magnetic sensor, which are used to verify the online status of the device; The data acquisition module is used to collect the temperature, humidity, door opening and closing times inside the box and the external environment temperature and humidity in real time, and transmit the original data to the data processing module; The data processing module is used to pre-process the raw data, including sliding average filtering and denoising, calculating external disturbance factors, temperature and humidity deviations, and deviation change rates; The control algorithm module is used to calculate the control weights of heating, cooling, humidification and dehumidification based on preprocessed data through a dynamic weight allocation algorithm, and dynamically allocate priorities; The actuator control module is used to select the priority of temperature and humidity adjustment according to the weight value, drive the actuators such as heater, refrigerator, humidifier and dehumidification fan, and map the weight value to the specific operation parameter; The IoT communication module is used to upload the temperature, humidity, door opening and closing times and execution results in the box to the cloud, and receive remote user commands issued by the cloud; The cloud interaction module is used to store historical data, optimize the coefficients of the dynamic weight allocation algorithm based on the gradient descent method, and push the optimized parameters to the device end; it supports users to remotely adjust target parameters; The cycle control module is used to control the cycle execution of the process, monitor whether the temperature and humidity are stable within the target range for three consecutive cycles, or whether the user actively terminates it, triggering the low-power standby mode; The low power management module is used to reduce energy consumption and enter standby mode when the system meets the termination conditions.

[0011] The present invention has the following beneficial effects: 1. The present invention adopts a dynamic weight allocation algorithm, combines real-time temperature and humidity deviation, deviation change rate and external disturbance factor, dynamically adjusts the control weights of heating, cooling, humidification and dehumidification, and solves the problems of single control strategy and rigid priority allocation of traditional systems. The algorithm flexibly allocates actuator resources based on multi-variable coupling relationship, which not only avoids control lag or overshoot, but also responds quickly to environmental changes, significantly improves the temperature and humidity control accuracy and stability, ensures that medical supplies are always within the target environment during transportation, and reduces the risk of deterioration.

[0012] 2. The present invention uploads environmental data and execution results in real time to the cloud, supports user remote monitoring and parameter adjustment, and uses historical data to optimize the dynamic weight allocation coefficient through the gradient descent method to form a closed-loop self-learning mechanism. This design not only improves operation and maintenance efficiency, but also continuously optimizes system performance, reduces the risk of parameter drift in long-term operation, reduces energy waste and equipment maintenance costs, and realizes data-driven intelligent control and sustainable energy efficiency management.

[0013] 3. The present invention introduces a quantitative model of external disturbance factors, comprehensively considers the impact of the temperature and humidity differences in the external environment and the frequency of opening and closing the door on the environment inside the box, and incorporates it into the control algorithm decision-making process. By dynamically adjusting the weights of the actuators, the temperature and humidity fluctuations caused by external interference are effectively offset, solving the problem of decreased control accuracy caused by traditional systems ignoring external disturbances, and further ensuring the safety of the storage environment for medical supplies.

[0014] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 It is a schematic flow chart of an Internet of Things automatic control method of a medical temperature and humidity automatic control box of the present invention; Figure 2 The present invention is a schematic flow chart of an Internet of Things automatic control system for a medical temperature and humidity automatic control box. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1-2 As shown, the present invention is an Internet of Things automatic control method for a medical temperature and humidity automatic control box, comprising the following steps: Step S1: Set the target temperature and target humidity, initialize the coefficients of the dynamic weight allocation algorithm, set the control cycle, and calibrate the temperature sensor, humidity sensor and door magnetic sensor; Step S2: Preprocessing is performed based on the calibrated sensor to collect the temperature, humidity, door opening and closing times in the box and the external environment temperature and humidity in real time, and the noise is eliminated through sliding average filtering to calculate the external disturbance factor; Step S3: Based on the preprocessed data, the temperature and humidity deviations and their change rates are calculated, and combined with the external disturbance factors, the control weights of heating, cooling, humidification and dehumidification are generated through a dynamic weight allocation algorithm to perform dynamic priority allocation for multi-objective control; Step S4: selecting a priority mode for temperature or humidity regulation based on the calculated weight, driving the corresponding actuator, and dynamically adjusting the power or working time based on the weight value; Step S5: Upload the execution results and environmental data to the cloud through the Internet of Things module, support users to remotely adjust the target parameters, and optimize the coefficients in step 1 based on historical data to form a closed-loop control; Step S6: The above steps are executed repeatedly until the temperature and humidity are stable within the target range for three consecutive cycles, or the user actively terminates the process, and the system enters a low-power standby mode.

[0019] Step S1 includes the following steps: Step S11: Input through user terminal or default configuration setting and , initialize the coefficients , , , ; Step S12: calibrate the zero drift of the temperature sensor and the humidity sensor, and confirm the online status of the device through the Internet of Things module.

[0020] In step S2, the comprehensive impact of external environmental changes on the internal environment is quantified, and the external disturbance factor is defined. , the calculation formula is as follows: ; In the formula, The external environment temperature is collected by the temperature and humidity sensor deployed outside the box. is the target temperature value of the automatic control box, The external environment humidity is collected by the temperature and humidity sensor deployed outside the box. is the target humidity value of the automatic control box, The number of times the door was opened and closed in the past five minutes.

[0021] Step S3 includes the following steps: Step S31, calculate the temperature and humidity deviation according to the collected data, and the temperature deviation formula is as follows: ; The humidity deviation formula is as follows: ; In the formula, It is the real-time temperature value measured inside the box, collected by the PT1000 temperature sensor. It is the real-time humidity value measured in the box, collected by the capacitive humidity sensor; Step S32, the formula for calculating the deviation change rate is as follows: Temperature deviation change rate: ; Humidity deviation change rate: ; In the formula, To control the cycle; Step S33: Implement dynamic priority allocation for heating, cooling, humidification and dehumidification control modes, combining real-time deviation, deviation change rate and external disturbance factor , define the dynamic weight allocation algorithm, the formula is as follows: ; In the formula, is the basic weight coefficient, is the non-linear adjustment coefficient, is the change rate weight coefficient, is the external disturbance weight coefficient, is the temperature and humidity deviation, is the instantaneous change of the temperature and humidity deviation, is the deviation change rate.

[0022] Step S4 includes the following steps: Step S41, compare the maximum values of the temperature control weight and the humidity control weight, and preferentially execute the adjustment of the type with the higher weight; Step S42, map the weight value to the specific operation parameters of the actuator, and define the control rule formula as follows: Heating power calculation formula: ; Refrigeration power limit function to avoid overloading operation, and the calculation formula is as follows: ; Humidification time calculation formula: (seconds / cycle); Dehumidification fan calculation formula: .

[0023] In the formula, is the output power of the heating element, in percentage, is the proportionality coefficient, with a fixed constant value of 0.1, is the heating control weight, reflecting the priority of the current heating demand, is the output power of the semiconductor refrigeration chip, in percentage, is the minimum value function to ensure that the refrigeration power does not exceed the rated maximum value (100%), is the refrigeration control weight, is the humidification time, indicating the running duration of the ultrasonic atomizer in each control cycle, is the humidification control weight, is the dehumidification fan speed, is the dehumidification control weight.

[0024] In step S5, adapt to different environmental scenarios and reduce energy consumption. The cloud iteratively updates the coefficients using the gradient descent method based on historical data , , , , and pushes it to the device side through wireless remote update.

[0025] In step S6, when the temperature and humidity are stable for three consecutive cycles, and The control process is terminated when the system is out of range or the user actively shuts down the system.

[0026] An Internet of Things automatic control system for a medical temperature and humidity automatic control box, comprising a configuration management module, a sensor calibration module, a data acquisition module, a data processing module, a control algorithm module, an actuator control module, an Internet of Things communication module, a cloud interaction module, a circulation control module and a low power consumption management module; The output end of the configuration management module is unidirectionally connected to the input end of the sensor calibration module, the output end of the sensor calibration module is unidirectionally connected to the input end of the data acquisition module, the output end of the data acquisition module is unidirectionally connected to the input end of the data processing module, the output end of the data processing module is unidirectionally connected to the input ends of the control algorithm module and the loop control module respectively, the output end of the control algorithm module is unidirectionally connected to the input end of the actuator control module, the output end of the actuator control module is unidirectionally connected to the input end of the Internet of Things communication module, the output end of the Internet of Things communication module is unidirectionally connected to the input end of the cloud interaction module, and the output end of the cloud interaction module is unidirectionally connected to the input end of the control algorithm module; the output end of the loop control module is unidirectionally connected to the input end of the actuator control module and the input end of the low power management module respectively.

[0027] The configuration management module is used to receive user input or load target temperature, humidity, control period, initialize the coefficients of the dynamic weight allocation algorithm, and set system operation parameters; The sensor calibration module includes calibration of temperature sensors, capacitive humidity sensors, and door magnetic sensors to verify the online status of the device; The data acquisition module is used to collect the temperature, humidity, door opening and closing times inside the box and the external environment temperature and humidity in real time, and transmit the original data to the data processing module; The data processing module is used to pre-process the raw data, including sliding average filtering and denoising, calculating external disturbance factors, temperature and humidity deviations, and deviation change rates; The control algorithm module is used to calculate the control weights of heating, cooling, humidification and dehumidification based on preprocessed data through a dynamic weight allocation algorithm, and dynamically allocate priorities; The actuator control module is used to select the priority of temperature and humidity adjustment according to the weight value, drive the actuators such as heater, refrigerator, humidifier and dehumidification fan, and map the weight value to the specific operation parameter; The IoT communication module is used to upload the temperature, humidity, door opening and closing times and execution results in the box to the cloud, and receive remote user commands issued by the cloud; The cloud interaction module is used to store historical data, optimize the coefficients of the dynamic weight allocation algorithm based on the gradient descent method, and push the optimized parameters to the device end; it supports users to remotely adjust target parameters; The cycle control module is used to control the cycle execution of the process, monitor whether the temperature and humidity are stable within the target range for three consecutive cycles, or whether the user actively terminates it, triggering the low-power standby mode; The low power management module is used to reduce energy consumption and enter standby mode when the system meets the termination conditions.

[0028] A specific application of this embodiment is: System Hardware Settings Sensor module: PT1000 high-precision temperature sensor (measuring range: -50℃~100℃, accuracy ±0.1℃) and capacitive humidity sensor (measuring range: 0%~100%RH, accuracy ±1.5%RH) are installed inside the box; environmental temperature and humidity sensor (model SHT35) is deployed outside the box; door magnetic sensor is used to monitor the number of times the door is opened and closed; Actuators: semiconductor heating plate (maximum power 50W), semiconductor cooling plate (maximum power 60W), ultrasonic humidifier (humidification rate 0.5L / h), centrifugal dehumidification fan (air volume 200m³ / h); Control core: STM32F407 microcontroller with built-in dynamic weight allocation algorithm program; IoT communication module uses NB-IoT module; Cloud platform: Alibaba Cloud IoT platform, used for data storage and analysis, supports gradient descent method to optimize algorithm parameters; Implementation steps 1. Initialization and parameter setting: Users set the target temperature through the mobile APP (Vaccine storage scenario), target humidity ; Initialize dynamic weight coefficient , , , ; Control cycle ; Calibrate the sensor: immerse the PT1000 temperature sensor in an ice-water mixture (0°C) and boiling water (100°C) for two-point calibration; the capacitive humidity sensor is calibrated using a saturated salt solution at 25°C (75%RH and 33%RH); 2. Data collection and preprocessing: Real-time collection of temperature inside the box ,humidity ; External ambient temperature ,humidity ; Number of times the door was opened and closed in the past 5 minutes ; Sliding average filtering: Take the average of 5 samplings of temperature data to eliminate random noise; Calculate the external disturbance factor: ; 3. Dynamic weight calculation and priority matching: Calculate the temperature and humidity deviation: ; ; Deviation change rate, last cycle : ; ; Dynamic weight distribution (taking humidity control as an example): ; Calculating temperature weights ,because , humidity adjustment is performed first; 4. Actuator control Select the dehumidification mode according to the weight mapping formula: ; Limited by the maximum air volume of the fan, the actual operating air volume is 200m³ / h (full load).

[0029] At the same time, the semiconductor refrigeration sheet is started to assist in cooling, and the power limit is: ; 5. Data upload and closed-loop optimization: Upload the execution results (dehumidification fan runs for 30 seconds, cooling power is 22W) and environmental data to the cloud; The cloud optimizes the coefficients using the gradient descent method based on historical data , Updated to , , and push it to the device; 6. Cycle control and low power management After 3 cycles (90 seconds) of continuous monitoring, the temperature inside the chamber stabilized to , humidity stabilized to , the system enters low-power standby mode and only maintains periodic sampling of the sensor.

[0030] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0031] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An Internet of Things automatic control method for a medical temperature and humidity automatic control box, characterized in that: The following steps are involved: Step S1: Set the target temperature and target humidity, initialize the coefficients of the dynamic weight allocation algorithm, set the control cycle, and calibrate the temperature sensor, humidity sensor and door magnetic sensor; Step S2: Preprocessing is performed based on the calibrated sensor to collect the temperature, humidity, door opening and closing times in the box and the external environment temperature and humidity in real time, and the noise is eliminated through sliding average filtering to calculate the external disturbance factor; Step S3: Based on the preprocessed data, the temperature and humidity deviation and its change rate are calculated, and combined with the external disturbance factor, the control weights of heating, cooling, humidification and dehumidification are generated through the dynamic weight allocation algorithm to perform dynamic priority allocation of multi-objective control; Step S4: selecting a priority mode for temperature or humidity regulation based on the calculated weight, driving the corresponding actuator, and dynamically adjusting the power or working time based on the weight value; Step S5: Upload the execution results and environmental data to the cloud through the Internet of Things module, support users to remotely adjust the target parameters, and optimize the coefficients in step 1 based on historical data to form a closed-loop control; Step S6: The above steps are executed repeatedly until the temperature and humidity are stable within the target range for three consecutive cycles, or the user actively terminates the process, and the system enters a low-power standby mode.

2. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: The step S1 includes the following steps: Step S11: Input through user terminal or default configuration setting and , initialize the coefficients , , , ; is the target temperature value of the automatic control box, is the target humidity value of the automatic control box; Step S12: calibrate the zero drift of the temperature sensor and the humidity sensor, and confirm the online status of the device through the Internet of Things module.

3. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: In step S2, the comprehensive impact of external environmental changes on the internal environment of the box is quantified, and the external disturbance factor is defined , the calculation formula is as follows: ； In the formula, The external environment temperature is collected by the temperature and humidity sensor deployed outside the box. is the target temperature value of the automatic control box, The external environment humidity is collected by the temperature and humidity sensor deployed outside the box. is the target humidity value of the automatic control box, The number of times the door was opened and closed in the past five minutes.

4. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: The step S3 includes the following steps: Step S31, calculate the temperature and humidity deviation according to the collected data, and the temperature deviation formula is as follows: ； The humidity deviation formula is as follows: ； In the formula, It is the real-time temperature value measured inside the box, collected by the PT1000 temperature sensor. It is the real-time humidity value measured in the box, collected by the capacitive humidity sensor; Step S32, the formula for calculating the deviation change rate is as follows: Temperature deviation change rate: ； Humidity deviation change rate: ； In the formula, To control the cycle; Step S33: Implement dynamic priority allocation for heating, cooling, humidification and dehumidification control modes, combining real-time deviation, deviation change rate and external disturbance factor , define the dynamic weight allocation algorithm, the formula is as follows: ； In the formula, is the basic weight coefficient, is the nonlinear adjustment coefficient, is the change rate weight coefficient, is the external disturbance weight coefficient, is the temperature and humidity deviation, is the instantaneous change of temperature and humidity deviation, is the rate of change of deviation.

5. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: The step S4 includes the following steps: Step S41, comparing the maximum values ​​of the temperature control weight and the humidity control weight, and preferentially executing the type of adjustment with a higher weight; Step S42: Map the weight value to the specific operating parameters of the actuator, and define the control rule formula as follows: Heating power calculation formula: ； Cooling power limit function to avoid overload operation, the calculation formula is as follows: ； Humidification time calculation formula: (seconds / cycle); Dehumidification fan calculation formula: ； In the formula, is the output power of the heater, expressed in percentage. is the proportionality coefficient, the value is a fixed constant of 0.1, is the heating control weight, reflecting the priority of the current heating demand. is the output power of the semiconductor refrigeration chip, in percentage. is a minimum function, ensuring that the cooling power does not exceed the rated maximum value (100%). is the cooling control weight, is the humidification time, which indicates the running time of the ultrasonic atomizer in each control cycle. is the humidification control weight, is the dehumidification fan speed, Control weights for dehumidification.

6. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: In step S5, to adapt to different environmental scenarios and reduce energy consumption, the cloud uses the gradient descent method to iteratively update the coefficients based on historical data. , , , and pushed to the device via wireless remote update.

7. The Internet of Things automatic control method of a medical temperature and humidity automatic control box according to claim 1, characterized in that: In step S6, when the temperature and humidity are stable for three consecutive cycles, and The control process is terminated when the system is out of range or the user actively shuts down the system.

8. An Internet of Things automatic control system for a medical temperature and humidity automatic control box, characterized in that: It includes configuration management module, sensor calibration module, data acquisition module, data processing module, control algorithm module, actuator control module, Internet of Things communication module, cloud interaction module, cycle control module and low power consumption management module; The output end of the configuration management module is unidirectionally connected to the input end of the sensor calibration module, the output end of the sensor calibration module is unidirectionally connected to the input end of the data acquisition module, the output end of the data acquisition module is unidirectionally connected to the input end of the data processing module, the output end of the data processing module is unidirectionally connected to the input ends of the control algorithm module and the cycle control module respectively, the output end of the control algorithm module is unidirectionally connected to the input end of the actuator control module, the output end of the actuator control module is unidirectionally connected to the input end of the Internet of Things communication module, the output end of the Internet of Things communication module is unidirectionally connected to the input end of the cloud interaction module, and the output end of the cloud interaction module is unidirectionally connected to the input end of the control algorithm module; the output end of the cycle control module is unidirectionally connected to the input end of the actuator control module and the input end of the low power management module respectively; The configuration management module is used to receive user input or load target temperature, humidity, control period, initialize the coefficients of the dynamic weight allocation algorithm, and set system operation parameters; The sensor calibration module includes a calibration temperature sensor, a capacitive humidity sensor, and a door magnetic sensor, which are used to verify the online status of the device; The data acquisition module is used to collect the temperature, humidity, door opening and closing times inside the box and the external environment temperature and humidity in real time, and transmit the original data to the data processing module; The data processing module is used to pre-process the raw data, including sliding average filtering and denoising, calculating external disturbance factors, temperature and humidity deviations, and deviation change rates; The control algorithm module is used to calculate the control weights of heating, cooling, humidification and dehumidification based on preprocessed data through a dynamic weight allocation algorithm, and dynamically allocate priorities; The actuator control module is used to select the priority of temperature and humidity adjustment according to the weight value, drive the actuators such as heater, refrigerator, humidifier and dehumidification fan, and map the weight value to the specific operation parameter; The IoT communication module is used to upload the temperature, humidity, door opening and closing times and execution results in the box to the cloud, and receive remote user commands issued by the cloud; The cloud interaction module is used to store historical data, optimize the coefficients of the dynamic weight allocation algorithm based on the gradient descent method, and push the optimized parameters to the device end; Support users to adjust target parameters remotely; The cycle control module is used to control the cycle execution of the process, monitor whether the temperature and humidity are stable within the target range for three consecutive cycles, or whether the user actively terminates it, triggering the low-power standby mode; The low power management module is used to reduce energy consumption and enter standby mode when the system meets the termination conditions.

Images