Multifunctional passive door based on Internet of Things and artificial intelligence intelligent control

Abstract

The invention discloses a multifunctional passive door based on Internet of Things and artificial intelligence control, which comprises a temperature sensor, a gas flow sensor, a controller, a communication module and a prompt module, and is characterized in that the temperature sensor is used for monitoring the temperature inside and outside a door body; the gas flow sensor is used for monitoring gas leakage inside and outside the door body; the controller is connected with the temperature sensor and the gas flow sensor and used for receiving monitoring signals of all the sensors and judging whether reminding is triggered or not according to preset conditions. The communication module is connected with the controller and is used for sending a reminding message to a mobile terminal of a user when the controller judges to trigger reminding; and the prompt module is connected with the controller and is used for sending a local prompt signal when the controller judges that the prompt is triggered. Real-time detection of various performances of the door body is achieved, if unqualified products are installed, abnormal conditions can be directly fed back to a user so that the user can carry out next-step processing, and energy conservation, safety and comfort of a building are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving technologies for building doors and windows, and particularly to a multifunctional passive door based on Internet of Things and artificial intelligence intelligent control. Background Art

[0002] With the increasing requirements for building energy conservation, especially the rapid development of green energy-saving buildings such as ultra-low energy consumption, near-zero energy consumption, low-carbon and zero-carbon buildings, the performance requirements for doors are increasing day by day. Traditional doors have many deficiencies in aspects such as heat preservation, airtightness, sound insulation, anti-theft, and fire prevention, and it is difficult to meet the requirements of green building energy conservation. In green buildings, passive doors are a type of door that, through optimized design and material selection, minimizes energy consumption and improves building energy efficiency. It is not only an important part of the building envelope structure but also plays a key role in aspects such as heat preservation, airtightness, sound insulation, and fire prevention.

[0003] Due to the requirements of high energy conservation and comfort in contemporary green energy-saving buildings, when existing passive doors are not installed properly, users cannot visually tell. As a result, after the installation of unqualified products, the building energy conservation fails to meet the standards, the high comfort of the building is lost, the user experience is poor, resources are wasted, and the full promotion of high energy conservation and comfort buildings is hindered. Summary of the Invention

[0004] In view of the above problems, the present invention provides a multifunctional passive door based on Internet of Things and artificial intelligence intelligent control to solve the problem that when existing passive doors are not installed properly, users cannot visually tell, resulting in the building energy conservation failing to meet the standards, the high comfort of the building being lost, and the poor user experience after the installation of unqualified products.

[0005] The present invention is implemented as follows: The present invention provides a multifunctional passive door based on Internet of Things and artificial intelligence intelligent control, including a temperature sensor for monitoring the temperature inside and outside the door body; a gas flow sensor disposed between the door body and the door frame for monitoring the gas leakage amount inside and outside the door body; a controller connected to the temperature sensor and the gas flow sensor for receiving the monitoring signals of each sensor and judging whether to trigger a reminder according to preset conditions; a communication module connected to the controller for sending a reminder message to the user's mobile terminal when the controller judges that a reminder is triggered; and a reminder module connected to the controller for emitting a local reminder signal when the controller judges that a reminder is triggered.

[0006] Further, the controller calculates the heat transfer coefficient according to the data measured by the temperature sensor, and triggers an abnormal heat preservation performance reminder when the heat transfer coefficient exceeds the preset standard range. The calculation formula is: , where q represents the heat flux density, λ represents the thermal conductivity of the material, Indicates the temperature gradient. The heat transfer coefficient is calculated based on the heat flux density, and the calculation formula is , where K is the heat transfer coefficient, A is the area of the door, and ΔT is the temperature difference between both sides of the door body.

[0007] Furthermore, , where T1 is the temperature of the first measurement point, T2 is the temperature of the second measurement point, x1 is the position coordinate of the first measurement point, and x2 is the position coordinate of the second measurement point.

[0008] Furthermore, the controller calculates the airtight performance index of the door body according to the pressure difference inside and outside the door body and the gas leakage amount provided by the gas flow sensor. When the gas leakage amount exceeds the preset airtight standard value, an airtight performance unqualified reminder is triggered. The calculation formula is: , where L represents the airtight performance index, Q represents the gas leakage amount, and Δ P represents the pressure difference between both sides inside and outside the door body.

[0009] Furthermore, it also includes a door magnetic sensor. The door magnetic sensor is installed at the corresponding positions of the door frame and the door body and is connected to the controller. The door magnetic sensor is used to collect the door opening time and the door opening angle change rate of the door body. The controller detects whether it is an abnormal door opening through the data provided by the door magnetic sensor combined with the One-Class SVM algorithm. When the door is abnormally opened or remains open for more than the preset time without closing, an anti-theft warning or a reminder for forgetting to close the door is triggered.

[0010] Furthermore, the method for abnormal door opening detection is as follows: The data of the door opening time and the door opening angle change rate of the collected normal door opening behaviors are used as the training set and input into the One-Class SVM model to construct a decision boundary. For the input of new door opening data into the model, the model calculates the distance from the new door opening data to the decision boundary. If the distance exceeds the set threshold, the model will determine that the behavior is abnormal. The controller triggers a reminder and sends a reminder message to the user's mobile terminal through the communication module and issues a local reminder signal through the reminder module.

[0011] Furthermore, it also includes a smoke sensor and a flame sensor. The smoke sensor and the flame sensor are installed above the door body and are connected to the controller.

[0012] Furthermore, it also includes a linear displacement sensor, which is installed at the hinge of the door body. The controller performs integral calculation on the displacement data collected by the linear displacement sensor to calculate the cumulative sag amount of the door body. The integral operation formula is: , where t is the time, x is the displacement, x(t) is the displacement data, and t0 and t1 are the start time and end time of the integral respectively.

[0013] Furthermore, , where ti is the i-th time point, t i-1 is the (i - 1)-th time point, Δt i = t i - t i-1 is the time interval.

[0014] Furthermore, a maintenance management module is built in the controller to record the opening and closing times and usage time of the door lock, establish an ARIMA model, and predict the possibility of door lock failure.

[0015] The beneficial effects of the present invention are as follows: The multifunctional passive door based on the Internet of Things and artificial intelligence intelligent control of the present invention realizes real-time detection of various performances of the door body. If an unqualified product is installed, the abnormal situation can be directly feedback to the user so that the user can carry out the next step of processing, ensuring building energy conservation, safety and comfort. The multiple intelligent functions improve the user's convenience and safety in use and reduce the safety risk. The intelligent linkage function enhances the coordination with the smart home system, improves the level of home intelligence, and the maintenance reminder also standardizes the user's use. Description of the Drawings

[0016] Figure 1 is a schematic diagram of the installation positions of the door body and various sensors of the present invention.

[0017] Description of the Reference Numerals: 1. Door body; 2. Door lock; 3. Temperature sensor; 4. Gas flow sensor; 5. Smoke sensor; 6. Linear displacement sensor; 7. Door magnetic sensor. Detailed Embodiments

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Many specific details are set forth in the following description in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0019] Such as Figure 1The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control of the present invention is shown, including a temperature sensor 3, a gas flow sensor 4, a controller, a communication module and a reminder module. The temperature sensor 3 is used to monitor the temperature inside and outside the door body 1; the gas flow sensor 4 is arranged between the door body 1 and the door frame and is used to monitor the gas leakage amount inside and outside the door body 1; the controller is connected to the temperature sensor 3 and the gas flow sensor 4 and is used to receive the monitoring signals of each sensor and judge whether to trigger a reminder according to preset conditions; the communication module is connected to the controller and is used to send a reminder message to the user's mobile terminal when the controller judges that a reminder is triggered; the reminder module is connected to the controller and is used to send out a local reminder signal when the controller judges that a reminder is triggered.

[0020] The detection of the heat preservation performance of the door body is realized through the temperature sensor 3, the controller, the communication module and the reminder module. The temperature sensor 3 is used to monitor the temperature inside and outside the door body 1. A plurality of high-precision thermistor temperature sensors 3 are evenly distributed on the inner and outer surfaces and the internal structure of the door body 1, with an interval of no more than 5 cm. The temperature sensor 3 collects temperature data once every 60 seconds, and the measurement accuracy error of the temperature sensor 3 is within ±0.1°C. Combining the data of the temperature sensor 3, an algorithm based on Fourier's law is used to calculate the heat transfer coefficient. Specifically, the controller calculates the heat transfer coefficient according to the data measured by the temperature sensor 3, and triggers an abnormal heat preservation performance reminder when the heat transfer coefficient exceeds the preset standard range. The calculation formula is: , where q represents the heat flux density, λ represents the thermal conductivity of the material, represents the temperature gradient, and the heat transfer coefficient is calculated according to the heat flux density. The calculation formula is , K is the heat transfer coefficient, A is the area of the door, and ΔT is the temperature difference between the two sides of the door body 1. By measuring the temperature at different positions of the door body 1, temperature gradient data is obtained, , T1 is the temperature of the first measurement point, T2 is the temperature of the second measurement point, x1 is the position coordinate of the first measurement point, and x2 is the position coordinate of the second measurement point. When the heat transfer coefficient exceeds the range specified by the energy-saving standard for the corresponding building climate zone, such as the heat transfer coefficient in winter in severe cold areas exceeds 1.0 W / (㎡·K). Specifically, the heat transfer coefficient can refer to the "Technical Standard for Passive Ultra-Low Energy Consumption Buildings" JGJ / T 269-2020. The controller triggers an abnormal heat preservation performance reminder. The controller alarms the local buzzer and the indicator light flashes through the reminder module. At the same time, the controller sends a reminder message to the user's mobile terminal through the communication module, that is, pushes a message to the mobile phone APP, accompanied by the temperature change curve and the heat transfer coefficient data.

[0021] The airtightness detection of the door body is achieved through the gas flow sensor 4, the controller, the communication module and the reminder module. The gas flow sensor 4 is arranged between the door body 1 and the door frame to monitor the gas leakage amount inside and outside the door body 1. Preferably, gas flow sensors 4 are installed at all gaps of the door, such as between the door frame and the door body, at the hinge, etc. The accuracy of the gas flow sensor 4 reaches ±20 sccm (standard cubic centimeters per minute), the detection accuracy error is within ±1%, and the response time does not exceed 1 second to monitor the gas leakage amount in real time. The controller calculates the airtightness performance index of the door body 1 according to the pressure difference inside and outside the door body 1 and the gas leakage amount provided by the gas flow sensor 4. When the gas leakage amount exceeds the preset airtight standard value, an airtightness performance unqualified reminder is triggered. The calculation formula is: , where L represents the airtightness performance index, Q represents the gas leakage amount, and Δ P represents the pressure difference between the inside and outside of the door body 1. When L exceeds the threshold set by the building airtightness grade, such as the leakage amount per hour per meter gap corresponding to the airtightness grade 8 of high-rise residential buildings exceeds 0.5 m³, the alarm threshold of the gas leakage amount can be referred to "Classification and Test Methods for Airtightness, Watertightness and Wind Resistance Performance of Building Exterior Windows and Doors" GB / T 7106-2019. The controller displays the unqualified airtightness performance information on the local display screen through the reminder module, and also pops up a reminder to the mobile phone APP through the communication module and gives the leakage amount value and location identification.

[0022] The present invention can remotely monitor the safety of the door body 1 and give an alarm, which is realized through a door magnetic sensor 7, a controller, a communication module and a prompt module. The door magnetic sensor 7 is installed at the corresponding positions of the door frame and the door body 1 and is connected to the controller. The door magnetic sensor 7 is used to collect the opening time of the door body 1 and the change rate of the opening angle. The door magnetic sensor 7 adopts a Hall effect sensor, and the minimum change in the induced magnetic field strength is not higher than 20 Gauss. Based on the data provided by the door magnetic sensor 7, the controller combines the One-Class SVM algorithm to detect whether the door opening is abnormal. When the door body 1 is abnormally opened or remains open for more than the preset time without being closed, an anti-theft warning or a reminder for forgetting to close the door is triggered. When the door is abnormally opened, such as too fast opening speed or unauthorized opening, the door magnetic sensor 7 sends a signal to the controller. The controller adopts an abnormal behavior detection algorithm based on machine learning to analyze the data of the door magnetic sensor 7. First, the data of normal door opening behaviors are collected and marked, including features such as the opening time and the change rate of the opening angle. The method for detecting abnormal door opening in the present invention is as follows: The data of the opening time and the change rate of the opening angle of the collected normal door opening behaviors are used as a training set and input into the One-Class SVM model to construct a decision boundary. For the input of new door opening data into the model, the model calculates the distance from the new door opening data to the decision boundary. If the distance exceeds the set threshold, the model will determine that the behavior is abnormal, and the controller triggers a reminder and sends a reminder message to the user's mobile terminal through the communication module, and issues a local prompt signal through the prompt module. In specific implementation, when it is determined that the door opening is abnormal, the controller activates the anti-theft warning, pushes an alarm message to the user's mobile phone APP through the 5G network, accompanied by on-site photos (taken by a camera near the door), and at the same time, the indoor smart speaker is linked to emit an alarm sound.

[0023] In addition, the door magnetic sensor 7 is used to continuously monitor the opening and closing state of the door body 1. If the door body 1 remains open for more than the preset time, such as 5 minutes without being closed, the controller determines that the door has been forgotten to be closed, and pushes a message to the mobile phone APP through the communication module to remind the user. The message includes the location information of the door, such as "The living room door is not closed", and at the same time, a soft prompt sound is emitted locally through the prompt module, which has the function of reminding of forgetting to close the door.

[0024] The present invention can also realize remote opening and closing of the door. The controller integrates Bluetooth 5.0, Wi-Fi 6 and Zigbee communication modules. Through the mobile phone APP (supporting systems above iOS 10.0 and Android 5.0), under authorized circumstances, such as after password input, fingerprint recognition or face recognition is passed, a remote door opening or closing instruction is sent. The instruction is transmitted to the controller through the communication module, and the controller controls the motor to drive the door lock 2 to perform corresponding actions, and at the same time feedbacks the operation result to the mobile phone APP to display the door opening or closing state. In this embodiment, the door lock 2 adopts an intelligent lock, and the intelligent lock has functions such as remote opening, mobile phone interconnection, video monitoring, and monitoring of the number of opening and closing times.

[0025] The present invention further includes a smoke sensor 5 and a flame sensor. The smoke sensor 5 and the flame sensor are installed above and around the door body 1 and are connected to the controller. In this embodiment, the smoke sensor 5 adopts a photoelectric smoke sensor, and the flame sensor adopts an infrared flame sensor, but it is not limited thereto, and other types of sensors can also be used. The detection accuracy of the smoke sensor 5 reaches 0.01 mg / m³, and the detection distance of the flame sensor is not less than 5 meters. The smoke sensor 5 utilizes the principle of light scattering. When smoke particles enter the measurement area of the smoke sensor 5, the light will be scattered, and the smoke concentration is determined by detecting the intensity of the scattered light. The flame sensor determines whether there is a flame by detecting the intensity of infrared radiation within a specific wavelength range. When the smoke concentration exceeds 0.015 mg / m³ or a flame is detected, the smoke sensor 5 or the flame sensor quickly transmits the signal to the controller. The controller immediately activates the fire alarm mode, emits a high-decibel alarm sound and strong light flashing locally through the prompt module, and at the same time sends an alarm signal to the fire protection system through the communication module, including the specific location information of the door, such as the community name, building number, room number, etc., for rapid rescue.

[0026] The present invention further includes a linear displacement sensor 6, which is installed at the hinge of the door body 1 and the edge of the door frame. The accuracy of the linear displacement sensor 6 reaches ±0.1 mm. The linear displacement sensor 6 monitors the displacement change of the door body 1 in real time, and calculates the cumulative sag amount of the door body 1 by performing integral operation on the displacement data. The controller calculates the cumulative sag amount of the door body 1 by integrating the displacement data collected by the linear sensor. The integral operation formula is: , where t is time, x is displacement, x(t) is the displacement data, and t0 and t1 are the start time and end time of the integral respectively. , where t i is the i-th time point, t i-1 is the (i - 1)-th time point, and Δt i = t i - t i-1 is the time interval.

[0027] First, the displacement data of the door body 1 is collected in real time by linear displacement sensors 6 installed at the hinge of the door body 1 and the edge of the door frame. These data can be expressed as a time series x(t). Necessary preprocessing is performed on the collected displacement data, such as filtering, denoising, etc. In this embodiment, mean filtering is used to remove noise to improve the accuracy and reliability of the data. Then, an integration operation is performed on the preprocessed displacement data x(t) to calculate the cumulative sag of the door body 1. Through the above integration operation formula, the cumulative sag of the door body 1 from time t0 to t1 is obtained. This value represents the total displacement change of the door body 1 due to factors such as gravity and material aging during this period. Finally, the calculated cumulative sag is output to the local display device through the prompt module or sent to a remote device through the communication module for further processing by the user or the system. For example, when the accumulated displacement exceeds a preset sag threshold, such as 5 mm, the specific alarm threshold for the cumulative sag can refer to the door structure safety design specification (enterprise standard Q / SY 001-2024). The controller issues a sag reminder for the door body 1, the reminder information is displayed on the local display screen, and the mobile phone APP synchronously pushes the reminder to prompt the user to repair in time.

[0028] The controller of the present invention is built-in with a maintenance management module, which records the opening and closing times and usage time of the door lock 2, establishes an ARIMA model, and predicts the possibility of the door lock 2 malfunctioning. The specific working process is as follows: First, the usage data of the door lock 2 is collected, including information such as the opening and closing times and usage time. These data can be analyzed as time series data. The collected data is cleaned and preprocessed to ensure the integrity and accuracy of the data. Then, an ARIMA model is established, and the historical data is used to train the ARIMA model. The model parameters are estimated by maximum likelihood estimation (MLE) or ordinary least squares (OLS). The trained ARIMA model is used to predict the future performance trend of the door lock 2. According to the prediction result, the possibility of the door lock 2 malfunctioning is evaluated. The controller outputs the prediction result to the local display device through the prompt module or sends it to a remote device through the communication module for further processing by the user or the system. For example, when the prediction result shows that the performance of the door lock 2 has dropped to a certain extent, such as when the usage duration of the door lock 2 exceeds six months, the controller generates a maintenance reminder. The maintenance items and recommended time are displayed on the local display screen through the prompt module, and detailed maintenance content, such as "It is recommended to clean and lubricate the door lock this month", is pushed to the mobile phone APP through the communication module.

[0029] The installation and calibration of multiple sensors in the present invention are crucial. When installing the temperature sensor 3, use thermal conductive glue to tightly paste it on the surface and internal structure of the door body 1 to ensure full contact with the material of the door body 1. After installation, use a high-precision temperature calibrator to calibrate the sensor in different temperature environments (such as -20°C, 0°C, 20°C, 40°C), record the measurement errors at each temperature point, and compensate for the errors through software algorithms. When installing the gas flow sensor 4, set a special installation groove at the gap of the door body 1 to ensure that the gas flow sensor 4 fits tightly with the gap and avoid air flow interference. During the calibration process, use a standard gas flow generator to calibrate according to different flow values (such as 0 sccm, 5 sccm, 10 sccm, etc.), and adjust the output parameters of the sensor to make its measurement accuracy reach ±20 sccm. After installing the door magnetic sensor 7 at the corresponding positions of the door frame and the door body 1, simulate magnetic field changes of different intensities through a magnetic field generator to debug the induction sensitivity of the door magnetic sensor 7, ensure that the minimum change in the induction magnetic field intensity is not higher than 20 gauss, and at the same time set anti-interference parameters to avoid false triggering. After installing the smoke sensor 5 and the flame sensor above and around the door body 1, regularly (monthly) use a standard smoke generator and a simulated flame light source to conduct functional tests on them, and clean the dust on the surfaces of the smoke sensor 5 and the flame sensor to ensure the detection accuracy and response speed.

[0030] When programming the controller, set the standard parameters for performance judgment and the intelligent linkage logic algorithm according to relevant building standards, safety codes, and the actual needs of users. In the judgment of thermal insulation performance, set the qualified range of the heat transfer coefficient according to different building climate zones and energy-saving standards. The judgment of airtightness performance is based on the building airtightness grade standard to set the gas leakage threshold. In terms of intelligent linkage, when a fire alarm signal is triggered, set the communication protocol and data format for the intelligent control system to send a closing instruction to the ventilation system through programming. Adopt a modular programming method to independently write and debug each functional module, such as the sensor data acquisition module, communication module, control module, etc. In the test link, build a simulated test environment, including simulating different temperature, humidity, and air pressure environments, simulating various opening and closing states of the door, abnormal external force impacts, fire smoke and flame situations, etc. Use professional test equipment, such as data collectors, signal generators, etc., to strictly test the accuracy of performance judgment, data processing speed, communication stability, intelligent linkage effect, and function test correction ability of the intelligent control system. Record the data and problems during the test process, and promptly optimize the code and adjust the logic for the problems found. For example, when testing the remote door opening function, simulate the instruction transmission in different network environments, test the door opening response time and success rate, and if there are delays or failures, optimize the code of the communication module.

[0031] Select solar panels and batteries with appropriate specifications according to the overall power consumption requirements of the door body 1. First, calculate the power consumption of the door body 1 in different working states, including the power consumption of sensors, the operation power consumption of the intelligent control system, the power consumption of the communication module, the power consumption of the actuator (such as the door lock motor), etc. According to the calculation results, select a lithium battery with a large capacity and good charge-discharge performance, such as a lithium battery with a capacity of ≥5000 mAh and a charge-discharge cycle life of not less than 800 times. When installing the battery, pay attention to the correct connection of the positive and negative poles and do a good job of insulation protection. After the installation of the energy supply system is completed, conduct a comprehensive test. The test contents include the charge-discharge performance test of the battery. Use a battery charge-discharge tester to conduct charge-discharge cycle tests according to different charge-discharge rates (such as 0.5C, 1C, 2C), and record the capacity retention rate, charge-discharge efficiency, and service life of the battery. At the same time, test the stability of the energy supply system after continuous operation for a certain period of time (such as 72 hours), monitor parameters such as the battery power and the system power supply voltage to ensure stable and reliable energy supply. During the test, if problems are found, such as low charging efficiency and serious battery heating, optimize and adjust the circuit design and component selection of the energy supply system.

[0032] Although the present invention discloses preferred specific embodiments for achieving the above object, it is not intended to limit the structural features of the present invention. Any person skilled in the art should know that under the technical spirit of the present invention, any easily conceivable changes or modifications are possible and are all covered by the scope of the patent application of the present invention.

Claims

1. A multifunctional passive door based on Internet of Things and artificial intelligence intelligent control, characterized in that, Including: A temperature sensor for monitoring the temperature inside and outside the door body; A gas flow sensor disposed between the door body and the door frame for monitoring the gas leakage amount inside and outside the door body; A controller connected to the temperature sensor and the gas flow sensor for receiving the monitoring signals of the sensors and judging whether to trigger a reminder according to preset conditions; A communication module connected to the controller for sending a reminder message to the user's mobile terminal when the controller judges that a reminder is triggered; A reminder module connected to the controller for emitting a local reminder signal when the controller judges that a reminder is triggered.

2. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, wherein, The controller calculates the heat transfer coefficient based on the data measured by the temperature sensor, and triggers an abnormal heat preservation performance reminder when the heat transfer coefficient exceeds the preset standard range. The calculation formula is: , where q represents the heat flux density, λ represents the thermal conductivity of the material, represents the temperature gradient, and the heat transfer coefficient is calculated based on the heat flux density. The calculation formula is , K is the heat transfer coefficient, A is the area of the door, and ΔT is the temperature difference between both sides of the door body.

3. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 2, wherein, , where T1 is the temperature of the first measurement point, T2 is the temperature of the second measurement point, x1 is the position coordinate of the first measurement point, and x2 is the position coordinate of the second measurement point.

4. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, wherein The controller calculates the airtight performance index of the door body based on the pressure difference inside and outside the door body and the gas leakage rate provided by the gas flow sensor. When the gas leakage rate exceeds the preset airtight standard value, an airtight performance unqualified reminder is triggered. The calculation formula is: , where L represents the airtight performance index, Q represents the gas leakage rate, and Δ P represents the pressure difference between the two sides inside and outside the door body.

5. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, characterized in that, It further includes a door magnetic sensor which is installed at the corresponding positions of the door frame and the door body and connected to the controller. The door magnetic sensor is used to collect the opening time and the opening angle change rate of the door body. The controller combines the data provided by the door magnetic sensor with the One-Class SVM algorithm to detect whether it is an abnormal door opening. When the door is abnormally opened or remains open for more than a preset time without being closed, an anti-theft warning or a reminder for forgetting to close the door is triggered.

6. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 5, characterized in that, The method for abnormal door opening detection is as follows: The data of the opening time and the opening angle change rate of the normal door opening behavior collected are used as a training set and input into the One-Class SVM model to construct a decision boundary. For the input of new door opening data into the model, the model calculates the distance from the new door opening data to the decision boundary. If the distance exceeds the set threshold, the model will judge this behavior as abnormal. The controller triggers a reminder and sends a reminder message to the user's mobile terminal through the communication module, and emits a local reminder signal through the reminder module.

7. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, characterized in that, It further includes a smoke sensor and a flame sensor which are installed above the door body and connected to the controller.

8. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, characterized in that, It also includes a linear displacement sensor installed at the hinge of the door body. The controller performs integral calculation on the displacement data collected by the linear displacement sensor to calculate the cumulative sag of the door body. The integral operation formula is: , where t is time, x is displacement, x(t) is the displacement data, and t0 and t1 are the start time and end time of the integral respectively.

9. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 8, characterized in that, , where t i is the i-th time point, t i-1 is the (i - 1)-th time point, Δt i = t i - t i-1 is the time interval.

10. The multifunctional passive door based on Internet of Things and artificial intelligence intelligent control according to claim 1, characterized in that, A maintenance management module is built in the controller to record the opening and closing times and the usage time of the door lock, establish an ARIMA model, and predict the possibility of door lock failure.

Images