Intelligent dehumidifier based on AI and using method thereof

Abstract

The AI-based intelligent dehumidifier comprises a central server and multiple sets of intelligent dehumidifiers, the multiple sets of intelligent dehumidifiers are matched with attributes of the Internet of Things, the central server is in information transmission with the intelligent dehumidifiers through the Internet of Things, and each intelligent dehumidifier comprises a dehumidifier shell. And the thermal imaging camera is used for high-angle shooting and monitoring of a temperature field distribution diagram of the evaporator and the capillary tube. The AI simulation algorithm which can intelligently predict the frosting state and the frosting time of the intelligent dehumidifier, delay the frosting speed and accelerate the defrosting process is arranged in the intelligent dehumidifier in a matched mode, the air volume of a draught fan and the operation frequency of an inverter compressor can be automatically adjusted according to environment changes and equipment states, and therefore the dehumidification efficiency is optimized; by predicting the frosting condition of the evaporator and taking measures in advance, the defrosting time and frequency can be remarkably reduced, and the dehumidification efficiency is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of dehumidifier technology, specifically to an AI-based intelligent dehumidifier and its usage method. Background Technology

[0002] A dehumidifier is a device used to reduce the humidity of the air, suitable for homes, offices, or other indoor spaces in humid environments. It helps maintain a more comfortable and healthy indoor environment by removing excess moisture from the air. The main types of dehumidifiers include condenser dehumidifiers and absorption dehumidifiers.

[0003] In existing technologies, most dehumidifiers are non-intelligent devices, merely used in conjunction with IoT functionality. The main control chips used in non-intelligent dehumidifiers are relatively outdated. Even dehumidifiers with IoT connectivity lack the ability to analyze data collected over long-term operation due to the outdated control chips. Therefore, they cannot analyze operational data under different conditions, and existing dehumidifiers cannot intelligently adjust based on changes in the ambient temperature and humidity. Consequently, non-intelligent dehumidifiers simply perform pre-programmed actions. This lack of adaptability, high energy consumption, and short lifespan results in poor adaptability. To address this, we propose an AI-based intelligent dehumidifier and its usage method. Summary of the Invention

[0004] The purpose of this invention is to provide an AI-based intelligent dehumidifier and its usage method to solve the problems that need to be addressed in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an AI-based intelligent dehumidifier, comprising a central server and multiple sets of intelligent dehumidifiers, wherein the multiple sets of intelligent dehumidifiers are equipped with Internet of Things (IoT) attributes, and the central server transmits information with the intelligent dehumidifiers through IoT;

[0006] The intelligent dehumidifier includes a dehumidifier housing, inside which a control module is installed. The control module is equipped with an AI simulation algorithm that can predict the frosting state of the intelligent dehumidifier in advance, slow down the frosting speed, and speed up the defrosting process. Inside the dehumidifier housing, a speed-regulating fan and a variable frequency compressor are installed as drive units.

[0007] It also includes an evaporator, a capillary tube, a thermal imaging camera, and a condenser, which are located inside the dehumidifier housing. The evaporator is used to absorb heat from the air and cause the moisture in the air to condense into water droplets.

[0008] The thermal imaging camera is used to take overhead photos of the temperature field distribution of the evaporator and capillary tube.

[0009] The capillary tube is used to control the amount of refrigerant flowing into the evaporator, and the capillary tube is connected to the evaporator.

[0010] The condenser transfers the heat absorbed by the evaporator and the heat generated by the variable frequency compressor to the external environment, thereby cooling and liquefying the high-temperature, high-pressure gaseous refrigerant.

[0011] In existing technologies, most dehumidifiers are non-intelligent devices, merely used in conjunction with IoT (Internet of Things) functions. The main control chips used in non-intelligent dehumidifiers are relatively outdated. Even dehumidifiers with IoT connectivity lack the ability to analyze data collected over long-term operation due to the outdated control chips. Therefore, they cannot analyze operational data under different conditions, and existing dehumidifiers cannot intelligently adjust their operation based on changes in the ambient temperature and humidity. Consequently, under any circumstances, non-intelligent dehumidifiers will only perform predetermined actions according to their programmed settings. In this situation, non-intelligent dehumidifiers cannot adjust their control based on model data, and they are unable to make effective adjustments in special circumstances. This results in defects such as poor adaptability, high energy consumption, and short equipment lifespan. This invention, however, incorporates an AI simulation algorithm within the intelligent dehumidifier that can intelligently predict the dehumidifier's frosting state, frosting time, delay frosting speed, and accelerate the defrosting process. This algorithm automatically adjusts the fan airflow and the operating frequency of the variable frequency compressor based on environmental changes and equipment status, thereby optimizing dehumidification efficiency. By predicting evaporator frosting and taking preventative measures, defrosting time and frequency can be significantly reduced, resulting in a substantial improvement in dehumidification efficiency. Furthermore, the included thermal imaging camera monitors the temperature field distribution of the evaporator and capillary tubes from above, enabling complete... The invention provides monitoring and management capabilities, enabling more precise control of the operating mode, avoiding unnecessary energy consumption, and reducing electricity usage. Through analysis of long-term operational data, the intelligent dehumidifier can predict potential faults such as refrigerant leaks and evaporator fin blockage, and perform maintenance in advance without affecting normal use, thereby extending the equipment's lifespan. Furthermore, the predictive maintenance function allows users to identify and resolve problems before they become serious, reducing high repair costs and downtime caused by sudden failures, and lowering overall maintenance costs. The intelligent dehumidifier also features network connectivity, allowing it to receive climate information from a server and input it as parameters into the AI ​​simulation algorithm, making the fitted curve more consistent with actual environmental changes and enhancing the system's adaptability and response speed.

[0012] As a further description of the above technical solution:

[0013] The thermal imaging camera is installed on the top of the inner wall of the dehumidifier housing, and the monitoring angle of the thermal imaging camera is 90°.

[0014] As a further description of the above technical solution:

[0015] The control module is internally equipped with an MCU based on ARM or RISC-V architecture as the control unit.

[0016] As a further description of the above technical solution:

[0017] It also includes a temperature sensor, which is used to monitor the temperature change inside the dehumidifier housing. Both the thermal imaging camera and the temperature sensor are connected to the control module via a communication line. The temperature sensor is used to collect the temperature inside the dehumidifier housing and combine it with the thermal imaging camera to calibrate the temperature field deviation value captured by the thermal imaging camera in real time.

[0018] As a further description of the above technical solution:

[0019] It also includes a current monitoring module, which is electrically connected to the control module and is used to monitor the compressor's operating current.

[0020] As a further description of the above technical solution:

[0021] The method of using the AI-based smart dehumidifier includes the following steps:

[0022] Step 1: Use the smart dehumidifier to collect temperature distribution maps and temperature data from the thermal imaging camera and summarize the data.

[0023] Step 2: Fit a curve by combining the edge AI model algorithm with the temperature distribution map and temperature acquisition point data;

[0024] Step 3: Obtain the start time of evaporator frosting by fitting the curve. Increase the air volume of the speed-regulating fan and reduce the frequency of the variable frequency compressor to prolong the rate of decline of the curve at the time of frosting.

[0025] Step 4: Based on the start time of evaporator defrosting in the fitted curve, stop the variable frequency compressor in advance and increase the air volume of the speed-regulating fan.

[0026] As a further description of the above technical solution:

[0027] The edge AI model algorithm obtains the fitted curve by the following steps;

[0028] Step A1: Normalize and filter the data collected by the thermal imaging camera and temperature sensor;

[0029] Step A2: Predict the frosting status of the evaporator using a nonlinear regression model;

[0030] Step A3: Use the autoregressive integral moving average model time series analysis method to model the long-term running data;

[0031] Step A4: Use an automatic encoder to identify abnormal operating patterns of the smart dehumidifier and provide potential early warnings for the smart dehumidifier;

[0032] Step A5: Use the least squares method to fit a curve reflecting the temperature change over time based on the data points collected by the thermal imaging camera and temperature sensor.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention is equipped with an AI simulation algorithm inside the intelligent dehumidifier that can intelligently predict the frosting status, frosting time, delay the frosting speed, and speed up the defrosting process. It can automatically adjust the fan air volume and the operating frequency of the variable frequency compressor according to environmental changes and equipment status, thereby optimizing dehumidification efficiency. By predicting the evaporator frosting situation and taking measures in advance, the defrosting time and frequency can be significantly reduced, resulting in a significant improvement in dehumidification efficiency.

[0035] 2. The thermal imaging camera monitors the temperature field distribution of the evaporator and capillary tube by taking a top-down view, which can achieve complete monitoring and management. In addition, the present invention can more accurately control the working mode, avoid unnecessary energy consumption, and reduce power consumption.

[0036] 3. By analyzing long-term operating data of the equipment, the intelligent dehumidifier can predict potential faults such as refrigerant leakage and evaporator fin blockage, and perform maintenance in advance without affecting normal use, thereby extending the service life of the equipment. Moreover, the predictive maintenance function allows users to discover and solve problems before they become serious, reducing high repair costs and downtime caused by sudden failures, and lowering the overall maintenance cost.

[0037] 4. Furthermore, the smart dehumidifier has network connectivity, which allows it to receive climate information from the server and input it as parameters into the AI ​​simulation algorithm, making the fitted curve more consistent with actual environmental changes and enhancing the system's adaptability and response speed. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the central server and intelligent dehumidifier structure of the present invention;

[0039] Figure 2 This is a schematic diagram of the first internal structure of the intelligent dehumidifier of the present invention;

[0040] Figure 3 This is a schematic diagram of the second internal structure of the intelligent dehumidifier of the present invention;

[0041] Figure 4 This is a schematic diagram of the temperature change fitting curve of the evaporator of the present invention.

[0042] In the diagram: 1. Central server, 2. Intelligent dehumidifier, 3. Dehumidifier housing, 4. Control module, 5. Variable speed fan, 6. Evaporator, 7. Capillary tube, 8. Thermal imaging camera, 9. Condenser, 10. Variable frequency compressor, 11. Temperature sensor. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1:

[0045] Please see Figure 1-3 The present invention provides a technical solution: an AI-based smart dehumidifier, including a central server 1 and multiple sets of smart dehumidifiers 2, wherein the multiple sets of smart dehumidifiers 2 are equipped with Internet of Things (IoT) attributes, the central server 1 transmits information with the smart dehumidifiers 2 through IoT, and the central server 1 and the smart dehumidifiers 2 transmit data through communication methods such as Wi-Fi, 4G or 5G.

[0046] The intelligent dehumidifier 2 includes a dehumidifier housing 3, and a control module 4 is installed inside the dehumidifier housing 3. The control module 4 is equipped with an AI simulation algorithm that can predict the frosting state of the intelligent dehumidifier 2 in advance, slow down the frosting speed, and speed up the defrosting process. The dehumidifier housing 3 is equipped with a speed-regulating fan 5 and a variable frequency compressor 10 as drive units.

[0047] It also includes an evaporator 6, a capillary tube 7, a thermal imaging camera 8, and a condenser 9. The evaporator 6, capillary tube 7, thermal imaging camera 8, and condenser 9 are disposed inside the dehumidifier housing 3. The evaporator 6 is used to absorb heat from the air and cause the moisture in the air to condense into water droplets.

[0048] The thermal imaging camera 8 is used to take overhead photos of the temperature field distribution of the evaporator 6 and capillary tube 7.

[0049] The capillary tube 7 is used to control the amount of refrigerant flowing into the evaporator. The capillary tube 7 is connected to the evaporator 6 and reduces the pressure and temperature of the refrigerant to facilitate effective heat absorption in the evaporator 6.

[0050] The condenser 9 transfers the heat absorbed by the evaporator 6 and the heat generated by the variable frequency compressor 10 to the external environment, thereby cooling and liquefying the high-temperature and high-pressure gaseous refrigerant.

[0051] The intelligent dehumidifier is equipped with an AI simulation algorithm that can intelligently predict the dehumidifier's frosting status, frosting time, delay frosting speed, and accelerate the defrosting process. This algorithm can automatically adjust the fan airflow and the operating frequency of the variable frequency compressor based on environmental changes and equipment status, thereby optimizing dehumidification efficiency. By predicting evaporator frosting and taking measures in advance, it can significantly reduce defrosting time and frequency, resulting in a substantial improvement in dehumidification efficiency. The included thermal imaging camera monitors the temperature field distribution of the evaporator and capillary tubes from above, enabling complete monitoring and management. Furthermore, this invention can more precisely control the operating mode, avoiding unnecessary energy consumption and reducing power consumption. The intelligent dehumidifier also has network connectivity, allowing it to receive climate information from a server and input it as parameters into the AI ​​simulation algorithm, making the fitted curve more consistent with actual environmental changes and enhancing the system's adaptability and response speed.

[0052] Example 2:

[0053] The thermal imaging camera 8 is located on the top of the inner wall of the dehumidifier housing 3. The monitoring angle of the thermal imaging camera 8 is 90°. It also includes a temperature sensor 11. Both the thermal imaging camera 8 and the temperature sensor 11 are connected to the control module 4 through a communication line. The temperature sensor 11 is used to collect the internal temperature of the dehumidifier housing 3 and combine it with the thermal imaging camera 8 to calibrate the temperature deviation value of the temperature field captured by the thermal imaging camera 8 in real time.

[0054] The temperature sensor 11 is used to monitor the temperature changes inside the dehumidifier housing 3, providing data support to help the control system adjust operating parameters according to actual working conditions, such as adjusting the air volume of the variable speed fan 5 or the frequency of the variable frequency compressor 10. The thermal imaging camera 8 set on the top of the inner wall of the dehumidifier housing 3 has a monitoring angle of 90°, which can capture the temperature field distribution map of the evaporator 6 and capillary tube 7 from above. At the same time, combined with the original temperature sensor 11, the temperature deviation value of the temperature field captured by the thermal imaging camera 8 can be calibrated in real time. Moreover, the thermal imaging camera 8 is connected to the control module 4 of the intelligent dehumidifier 2 by a communication line, which has real-time performance, stability and strong anti-interference ability.

[0055] The control module 4 internally houses an ARM or RISC-V based MCU as a control unit, specifically an STM32 or ESP32 model. It also includes a current monitoring module electrically connected to the control module 4, which monitors the compressor's operating current.

[0056] By collecting operational status and fault monitoring data and fitting curves using edge AI model algorithms, intelligent dehumidifiers can predict the occurrence of faults, improving work efficiency. Moreover, intelligent dehumidifiers with predictive capabilities can predict the working status of internal components and impending faults as early as possible through long-term analysis of collected data and curve fitting using AI model algorithms. For example, they can predict refrigerant leaks, evaporator fin blockage, poor ventilation, refrigeration system pipe contamination, and inverter compressor stall. Intelligent prediction can alert the intelligent dehumidifier to potential faults early, allowing for early handling of faults without affecting production or use, thus reducing maintenance costs.

[0057] Example 3:

[0058] Please see Figure 1-3 The present invention provides a technical solution: the method of using the AI-based intelligent dehumidifier includes the following steps:

[0059] Step 1: Use the smart dehumidifier 2 to collect temperature distribution maps and temperature data from the thermal imaging camera and then summarize the data.

[0060] Step 2: Fit a curve by combining the edge AI model algorithm with the temperature distribution map and temperature acquisition point data;

[0061] Step 3: By fitting the curve, we obtain time t1 as the start time of frost formation on the evaporator 6. By increasing the air volume of the speed-regulating fan 5 and reducing the frequency of the variable frequency compressor 10, we can slow down the frost formation speed and extend the rate of descent of the curve at time t1 as much as possible. Therefore, the frost formation time of the dehumidifier will be extended, the dehumidification working time of the dehumidifier will be extended, and the efficiency will be improved.

[0062] Step 4: From the fitted curve, time t2 is the start time of defrosting for evaporator 6. The inverter compressor 10 is stopped earlier, and the airflow of the variable-speed fan 5 is increased to accelerate the defrosting time. Unlike traditional defrosting methods that rely on setting a defrosting time, the intelligent dehumidifier can sense the end time of defrosting through curve changes and can start the inverter compressor 10 earlier, ensuring it operates at its maximum allowable value. This setting shortens the overall defrosting process of the intelligent dehumidifier 2, improves its efficiency, reduces wasted energy due to defrosting, and saves electricity.

[0063] The edge AI model algorithm obtains the fitted curve by the following steps;

[0064] Step A1: Normalize and filter the data collected by the thermal imaging camera 8 and temperature sensor 11 to improve the accuracy of subsequent analysis.

[0065] Step A2: Use a nonlinear regression model to predict the frosting state of evaporator 6; for example, train a model using historical data to predict the temperature change trend at a future moment, and then adjust the air volume of the speed-regulating fan and the frequency of the variable frequency compressor.

[0066] Step A3: Use the autoregressive integral moving average model time series analysis method to model long-term operating data in order to predict future changes in operating conditions or failure risks;

[0067] Step A4: Use an automatic encoder to identify abnormal operating modes of the intelligent dehumidifier 2 and provide potential early warnings for the intelligent dehumidifier 2, thereby providing early warnings of potential problems;

[0068] Step A5: Use the least squares method to fit a curve reflecting the temperature change over time based on the data points collected by the thermal imaging camera 8 and the temperature sensor 11.

[0069] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An AI-based intelligent dehumidifier, comprising a central server (1) and multiple intelligent dehumidifiers (2), characterized in that: Multiple sets of the aforementioned smart dehumidifiers (2) are equipped with Internet of Things (IoT) attributes, and the central server (1) transmits information with the smart dehumidifiers (2) through IoT; The intelligent dehumidifier (2) includes a dehumidifier housing (3), and a control module (4) is provided inside the dehumidifier housing (3). The control module (4) is equipped with an AI simulation algorithm that predicts the frosting state of the intelligent dehumidifier (2) in advance, slows down the frosting speed, and speeds up the defrosting process. The dehumidifier housing (3) is provided with a speed-regulating fan (5) and a variable frequency compressor (10) as driving units. It also includes an evaporator (6), a capillary tube (7), a thermal imaging camera (8), and a condenser (9). The evaporator (6), capillary tube (7), thermal imaging camera (8), and condenser (9) are located inside the dehumidifier housing (3). The evaporator (6) is used to absorb heat from the air and cause the moisture in the air to condense into water droplets. The thermal imaging camera (8) is used to take overhead photos of the temperature field distribution of the evaporator (6) and capillary (7); The capillary tube (7) is used to control the amount of refrigerant flowing into the evaporator, and the capillary tube (7) is connected to the evaporator (6); The condenser (9) transfers the heat absorbed by the evaporator (6) and the heat generated by the variable frequency compressor (10) to the external environment, thereby cooling and liquefying the high-temperature and high-pressure gaseous refrigerant.

2. The AI-based intelligent dehumidifier according to claim 1, characterized in that: The thermal imaging camera (8) is located on the top of the inner wall of the dehumidifier housing (3), and the monitoring angle of the thermal imaging camera (8) is 90°.

3. The AI-based intelligent dehumidifier according to claim 2, characterized in that: The control module (4) is internally equipped with an MCU based on ARM or RISC-V architecture as a control unit.

4. The AI-based intelligent dehumidifier according to claim 1, characterized in that: It also includes a temperature sensor (11), which is used to monitor the temperature change inside the dehumidifier housing (3). The thermal imaging camera (8) and the temperature sensor (11) are both connected to the control module (4) via a communication line. The temperature sensor (11) is used to collect the temperature inside the dehumidifier housing (3) and combine it with the thermal imaging camera (8) to calibrate the temperature deviation value of the temperature field captured by the thermal imaging camera (8) in real time.

5. The AI-based intelligent dehumidifier according to claim 1, characterized in that: It also includes a current monitoring module, which is electrically connected to the control module (4) and is used to monitor the compressor's operating current.

6. A method of using an AI-based intelligent dehumidifier, applicable to an AI-based intelligent dehumidifier as described in any one of claims 1-5, characterized in that: The method of using the AI-based smart dehumidifier includes the following steps: Step 1: Use the intelligent dehumidifier (2) to collect temperature distribution maps and temperature collection point data from the thermal imaging camera and summarize them; Step 2: Fit a curve by combining the edge AI model algorithm with the temperature distribution map and temperature acquisition point data; Step 3: Obtain the start time of frost formation on the evaporator (6) by fitting the curve. Increase the air volume of the speed-regulating fan (5) and reduce the frequency of the variable frequency compressor (10) to prolong the rate of decline of the curve at the time of frost formation. Step 4: Based on the start time of defrosting of the evaporator (6) in the curve obtained from the fitting, stop the variable frequency compressor (10) in advance and increase the air volume of the speed-regulating fan (5).

7. The method of using an AI-based intelligent dehumidifier according to claim 6, characterized in that: The edge AI model algorithm obtains the fitted curve by the following steps; Step A1: Normalize and filter the data collected by the thermal imaging camera (8) and the temperature sensor (11); Step A2: Predict the frosting state of the evaporator (6) using a nonlinear regression model; Step A3: Use the autoregressive integral moving average model time series analysis method to model the long-term running data; Step A4: Use an automatic encoder to identify abnormal operating modes of the intelligent dehumidifier (2) and provide potential early warnings for the intelligent dehumidifier (2); Step A5: Use the least squares method to fit the data points collected by the thermal imaging camera (8) and the temperature sensor (11) to obtain a curve that reflects the temperature change over time.

Images