Heating personalized control method based on deep learning

Abstract

The application relates to the field of heating technology and discloses a heating individualized control method based on deep learning, which comprises the following steps: S1, detecting the temperature range area of an indoor space by an infrared temperature sensor; a user sets the indoor maintained temperature; the temperature range area of the infrared temperature sensor is 2-3 DEG C lower / higher than the set temperature; the temperature range area 2-3 DEG C lower / higher than the set temperature is set as a first temperature zone; the temperature range area 2-3 DEG C lower / higher than the first temperature zone is set as a second temperature zone; and the set temperature, the first temperature zone and the second temperature zone are marked. The heating individualized control method based on deep learning can make the control of heating more intelligent and convenient, can ensure the individualized control of the indoor heating temperature, can reduce the influence of the day and night temperature difference in the indoor space and has other advantages.

Description

Technical Field

[0001] The present invention relates to the field of heating technology, and specifically to a personalized heating control method based on deep learning. Background Art

[0002] The appropriate temperature inside buildings can be achieved through the design of buildings and their cold-proof heating devices. According to the "Residential Design Code" (GB50096-2011) jointly issued by the Ministry of Housing and Urban-Rural Development and the General Administration of Quality Supervision, Inspection and Quarantine, residential buildings in extremely cold and cold areas should be equipped with heating facilities.

[0003] There are many different heating methods available, including but not limited to:

[0004] Floor heating: Due to traditional living habits, Japan and South Korea in Asia have adopted floor heating as their preferred method of residential heating. This technology has been introduced to my country for less than a decade, first arriving in Yanbian, Jilin Province, from South Korea and quickly spreading to the three northeastern provinces. With the advancement of technology, there are now two types of heating: electric heating and water heating.

[0005] Electric heating: The principle is to heat the floor to 18-28℃ through heating cables buried under the floor, and evenly radiate heat into the room to achieve the heating effect;

[0006] Water heating: The principle is to use equipment to heat the water in the water pipes buried under the floor to a suitable temperature so that it can be evenly radiated into the room.

[0007] However, the existing heating method is relatively inconvenient in the control process. People in the room will only think of controlling the heating in the house after they feel the temperature change. This causes the temperature in the house to be different during the day and at night. When the indoor space is connected to the balcony through a large sliding door, the difference between day and night will be more significant, causing people in the house to feel uncomfortable and often catch colds during the season change. Summary of the Invention

[0008] (1) Technical problems solved

[0009] In response to the shortcomings of the existing technology, the present invention provides a personalized heating control method based on deep learning, which has the advantages of ensuring personalized control of indoor heating temperature and reducing the impact of day and night temperature differences in the house. It solves the problem that the existing heating method is inconvenient during the control process. People in the room will only think of controlling the indoor heating after they feel the temperature change, which causes the temperature in the house to be different during the day and at night. When the indoor room is connected to the balcony through a large sliding door, the difference between day and night will be more significant, causing people in the house to feel uncomfortable and frequent colds during the season change.

[0010] (2) Technical solution

[0011] In order to achieve the above-mentioned purpose of being able to control the indoor heating temperature in a personalized manner and reduce the impact of the temperature difference between day and night in the house, the present invention provides the following technical solution: a personalized heating control method based on deep learning, comprising the following steps:

[0012] S1. Use an infrared temperature sensor to detect the indoor temperature range. The user sets the indoor maintenance temperature. The temperature range of the infrared temperature sensor is 2-3°C lower or higher than the set temperature. The temperature range of 2-3°C lower or higher than the set temperature is set as the first temperature zone. The temperature range of the infrared temperature sensor is 2-3°C lower or higher than the first temperature zone is set as the second temperature zone. The positions of the set temperature, the first temperature zone, and the second temperature zone are marked.

[0013] S2. Record the temperature during the day and night based on the first and second temperature zones identified by the infrared temperature sensor, and mark the time periods where the temperature changes by more than 3-5°C. At the same time, perform zoning control on the floor heating, and the user marks the key temperature maintenance zones, and the floor heating is diffused according to the key maintenance zones;

[0014] S3. When the user is using the device, the user is marked as setting the temperature, and the time is calibrated through the Internet. The user is marked according to the time period and the indoor temperature, and the time during the use period, the first half hour of the use period, and the last half hour of the use period are recorded;

[0015] S4. After the user sets a certain temperature, the floor heating starts heating. The heating system takes the key maintenance area as the standard temperature and monitors the temperature. When the second temperature area reaches 3-4°C below the standard temperature, the heating temperature of the second temperature area is increased and the temperature of the key maintenance area is reduced by 1-3°C.

[0016] S5. Use the dry temperature of the second temperature zone to diffuse to the surrounding areas to maintain the temperature variation in the key maintenance zone within a certain range. During the day, according to the working hours recorded by the user, stop the floor heating outside the key maintenance zone while the user is working, and reduce the temperature of the key maintenance zone to 3-5°C above the set temperature. At the same time, record the temperature of the first and second temperature zones. When the temperature difference between the second temperature zone and the set temperature is within 5°C, stop heating the key maintenance zone. When the temperature difference exceeds 5°C, resume heating.

[0017] S6. When heating is not needed during the user's work hours, the floor heating is turned off, and the time when the user turns it off and on is recorded. The indoor temperature is continuously detected when the user is not at home. At the same time, the time required to rise to the set temperature usually set by the user is controlled during the heating time before the user returns home. The temperature of the key maintenance area is controlled to rise. When the heating time lasts for 1 / 2-3, the area outside the key maintenance area starts to be heated.

[0018] The deep learning-based personalized heating control method provided by the present invention can make the heating control more intelligent and convenient, and has the advantages of ensuring personalized control of the indoor heating temperature and reducing the impact of the day and night temperature difference in the house. It solves the problem that the existing heating method is relatively inconvenient during the control process. Only after the indoor people feel the temperature change will they think of controlling the indoor heating. This causes the temperature in the house to be different during the day and at night. When the indoor room is connected to the balcony through a large sliding door, the difference between day and night will be more significant, causing the people in the house to feel uncomfortable and frequent colds during the season change.

[0019] In a possible embodiment, in S1, when the set temperature is 28°C, the temperature of the first temperature zone is 28.5-30°C and 27.5-25°C, and the temperature of the second temperature zone is 24.5-22°C and 30.5-33°C.

[0020] In a possible implementation, in S2, when the user sets the key maintenance zone, the area outside the indoor key maintenance zone is divided into two parts and bound to the first temperature zone and the second temperature zone.

[0021] In a possible implementation, in S3, the areas with diurnal temperature changes are bound to the time, and the binding is performed separately according to the outdoor temperature.

[0022] In a possible implementation, in S4, when the heating temperature in the key maintenance area is lowered, the set temperature of the key maintenance area is ensured to remain unchanged.

[0023] In a possible implementation, in S5, heating is selectively performed in the first temperature zone according to the outdoor temperature.

[0024] In a possible implementation, in S6, the heating time is the time required to heat the current temperature to the set temperature.

[0025] Compared with the existing technology, the present invention provides a personalized heating control method based on deep learning, which has the following beneficial effects:

[0026] 1. The present invention uses different control methods in different time periods to ensure that the temperature in the house will not change significantly during the heating process, thereby ensuring that the indoor temperature can be better positioned, and can automatically control according to the user's usage habits to avoid the trouble of adjusting and controlling only when the user feels the temperature changes during use, and avoids excessive energy consumption caused by improper adjustment, further avoids harm to the human body, and can also avoid the problem of rapid temperature loss at night. DETAILED DESCRIPTION

[0027] Example 1:

[0028] The personalized heating control method based on deep learning includes the following steps:

[0029] S1. Use an infrared temperature sensor to detect the indoor temperature range. The user sets the indoor maintenance temperature. The temperature range of the infrared temperature sensor is 2°C lower or higher than the set temperature. The temperature range of 2°C lower or higher than the set temperature is set as the first temperature zone. The temperature range of the infrared temperature sensor is 2°C lower or higher than the first temperature zone is set as the second temperature zone. The positions of the set temperature, the first temperature zone, and the second temperature zone are marked.

[0030] S2. Record the temperature during the day and night based on the first and second temperature zones identified by the infrared temperature sensor, and mark the time periods where the temperature changes by more than 3°C. At the same time, perform zoning control on the floor heating, and the user marks the key temperature maintenance zones, and the floor heating is diffused according to the key maintenance zones.

[0031] S3. When the user is using the device, the user is marked as setting the temperature, and the time is calibrated through the Internet. The user is marked according to the time period and the indoor temperature, and the time during the use period, the first half hour of the use period, and the last half hour of the use period are recorded;

[0032] S4. After the user sets a certain temperature, the floor heating starts heating. The heating system uses the key maintenance area as the standard temperature and monitors the temperature. When the second temperature area reaches 3°C below the standard temperature, the heating temperature of the second temperature area is increased and the temperature of the key maintenance area is reduced by 1°C.

[0033] S5. Use the dry temperature of the second temperature zone to diffuse to the surrounding areas to maintain the temperature variation in the key maintenance zone within a certain range. During the day, according to the working hours recorded by the user, stop the floor heating outside the key maintenance zone while the user is working, and lower the temperature of the key maintenance zone to 3°C above the set temperature. At the same time, record the temperature of the first and second temperature zones. When the temperature difference between the second temperature zone and the set temperature is within 5°C, stop heating the key maintenance zone. When the temperature difference exceeds 5°C, resume heating.

[0034] S6. When heating is not needed during the user's work hours, the floor heating is turned off, and the time when the user turns it off and on is recorded. The indoor temperature is continuously detected when the user is not at home. At the same time, the time required to rise to the set temperature usually set by the user is controlled during the heating time before the user returns home. The temperature of the key maintenance area is controlled to rise. When the heating time lasts for 1 / 2, the area outside the key maintenance area starts to be heated.

[0035] Example 2:

[0036] The personalized heating control method based on deep learning includes the following steps:

[0037] S1. Use an infrared temperature sensor to detect the indoor temperature range. The user sets the indoor maintenance temperature. The temperature range of the infrared temperature sensor is 3°C lower or higher than the set temperature. The temperature range of 3°C lower or higher than the set temperature is set as the first temperature zone. The temperature range of the infrared temperature sensor is 3°C lower or higher than the first temperature zone is set as the second temperature zone. The positions of the set temperature, the first temperature zone, and the second temperature zone are marked.

[0038] S2. Record the temperature during the day and night based on the first and second temperature zones identified by the infrared temperature sensor, and mark the time periods where the temperature changes by more than 5°C. At the same time, perform zoning control on the floor heating. The user marks the key temperature maintenance zones, and the floor heating is diffused according to the key maintenance zones.

[0039] S3. When the user is using the device, the user is marked as setting the temperature, and the time is calibrated through the Internet. The user is marked according to the time period and the indoor temperature, and the time during the use period, the first half hour of the use period, and the last half hour of the use period are recorded;

[0040] S4. After the user sets a certain temperature, the floor heating starts heating. The heating system uses the key maintenance area as the standard temperature and monitors the temperature. When the second temperature area reaches 4°C below the standard temperature, the heating temperature of the second temperature area is increased and the temperature of the key maintenance area is reduced by 3°C.

[0041] S5. Use the dry temperature of the second temperature zone to diffuse to the surrounding areas to maintain the temperature variation in the key maintenance zone within a certain range. During the day, according to the working hours recorded by the user, stop the floor heating outside the key maintenance zone while the user is working, and lower the temperature of the key maintenance zone to 5°C above the set temperature. At the same time, record the temperature of the first and second temperature zones. When the temperature difference between the second temperature zone and the set temperature is within 5°C, stop heating the key maintenance zone. When the temperature difference exceeds 5°C, resume heating.

[0042] S6. When heating is not needed during the user's work hours, the floor heating is turned off, and the time when the user turns it off and on is recorded. The indoor temperature is continuously detected when the user is not at home. At the same time, the time required to rise to the set temperature usually set by the user is controlled during the heating time before the user returns home. The temperature of the key maintenance area is controlled to rise. When the heating time lasts for 1 / 3, the area outside the key maintenance area starts to be heated.

[0043] Example 3:

[0044] The personalized heating control method based on deep learning includes the following steps:

[0045] S1. Use an infrared temperature sensor to detect the indoor temperature range. The user sets the indoor maintenance temperature. The temperature range of the infrared temperature sensor is 2.5°C lower or higher than the set temperature. The temperature range of 2.5°C lower or higher than the set temperature is set as the first temperature zone. The temperature range of the infrared temperature sensor is 2.5°C lower or higher than the first temperature zone is set as the second temperature zone. The positions of the set temperature, the first temperature zone, and the second temperature zone are marked.

[0046] S2. Record the temperature of the first and second temperature zones identified by the infrared temperature sensor during the day and night, and mark the time periods where the temperature changes by more than 4°C. At the same time, perform zoning control on the floor heating. The user marks the key temperature maintenance zones, and the floor heating is diffused according to the key maintenance zones.

[0047] S3. When the user is using the device, the user is marked as setting the temperature, and the time is calibrated through the Internet. The user is marked according to the time period and the indoor temperature, and the time during the use period, the first half hour of the use period, and the last half hour of the use period are recorded;

[0048] S4. After the user sets a certain temperature, the floor heating starts heating. The heating system uses the key maintenance area as the standard temperature and monitors the temperature. When the second temperature area reaches 3.5°C below the standard temperature, the heating temperature of the second temperature area is increased and the temperature of the key maintenance area is reduced by 2°C.

[0049] S5. Use the dry temperature of the second temperature zone to diffuse to the surrounding areas to maintain the temperature variation in the key maintenance zone within a certain range. During the day, according to the working hours recorded by the user, stop the floor heating outside the key maintenance zone while the user is working, and lower the temperature of the key maintenance zone to 4°C above the set temperature. At the same time, record the temperature of the first and second temperature zones. When the temperature difference between the second temperature zone and the set temperature is within 5°C, stop heating the key maintenance zone. When the temperature difference exceeds 5°C, resume heating.

[0050] S6. When heating is not needed during the user's work hours, the floor heating is turned off, and the time when the user turns it off and on is recorded. The indoor temperature is continuously detected when the user is not at home. At the same time, the time required to rise to the set temperature usually set by the user is controlled during the heating time before the user returns home. The temperature of the key maintenance area is controlled to rise. When the heating time lasts for 1 / 2.5, the area outside the key maintenance area starts to be heated.

[0051] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A personalized heating control method based on deep learning includes the following steps: S1. Use an infrared temperature sensor to detect the indoor temperature range. The user sets the indoor maintenance temperature. The temperature range of the infrared temperature sensor is 2-3°C lower or higher than the set temperature. The temperature range of 2-3°C lower or higher than the set temperature is set as the first temperature zone. The temperature range of the infrared temperature sensor is 2-3°C lower or higher than the first temperature zone is set as the second temperature zone. The positions of the set temperature, the first temperature zone, and the second temperature zone are marked. S2. Record the temperature during the day and night based on the first and second temperature zones identified by the infrared temperature sensor, and mark the time periods where the temperature changes by more than 3-5°C. At the same time, perform zoning control on the floor heating, and the user marks the key temperature maintenance zones, and the floor heating is diffused according to the key maintenance zones; S3. When the user is using the device, the temperature set by the user is marked, and the time is calibrated through the Internet. The time period of the user's main use and the indoor temperature are marked, and the time of use, the first half hour of the use period, and the last half hour of the use period are recorded; S4. After the user sets a certain temperature, the floor heating starts heating. The heating is carried out in the order of the standard temperature of the key maintenance area. At the same time, the temperature is monitored. When the second temperature area reaches 3-4°C below the standard temperature, the heating temperature of the second temperature area is increased, and the temperature of the key maintenance area is reduced by 1-3°C. S5. Use the dry temperature of the second temperature zone to diffuse to the surrounding areas to maintain the temperature variation in the key maintenance zone within a certain range. During the day, according to the working hours recorded by the user, stop the floor heating outside the key maintenance zone while the user is working, and reduce the temperature of the key maintenance zone to 3-5°C above the set temperature. At the same time, record the temperature of the first and second temperature zones. When the temperature difference between the second temperature zone and the set temperature is within 5°C, stop heating the key maintenance zone. When the temperature difference exceeds 5°C, resume heating. S6. When heating is not needed during the user's work hours, the floor heating is turned off, and the time when the user turns it off and on is recorded. The indoor temperature is continuously detected when the user is not at home. At the same time, the time required to rise to the set temperature usually set by the user is controlled during the heating time before the user returns home. The temperature of the key maintenance area is controlled to rise. When the heating time lasts for 1 / 2-3 hours, the area outside the key maintenance area begins to heat up.

2. The deep learning-based personalized heating control method according to claim 1, characterized in that: In S1, when the set temperature is 28°C, the temperatures in the first temperature zone are 28.5-30°C and 27.5-25°C, and the temperatures in the second temperature zone are 24.5-22°C and 30.5-33°C.

3. The deep learning-based personalized heating control method according to claim 2, characterized in that: In the above S2, when the user sets the key maintenance zone, the area outside the indoor key maintenance zone is divided into two parts and bound to the first temperature zone and the second temperature zone.

4. The deep learning-based personalized heating control method according to claim 1, characterized in that: In S3, the areas with diurnal temperature changes are bound to the time, and are bound respectively according to the outdoor temperature.

5. The deep learning-based personalized heating control method according to claim 1, characterized in that: In the above-mentioned S4, when the heating temperature in the key maintenance area is lowered, the set temperature of the key maintenance area is ensured to remain unchanged.

6. The deep learning-based personalized heating control method according to claim 1, characterized in that: In S5, heating is selectively performed in the first temperature zone according to the outdoor temperature.

7. The deep learning-based personalized heating control method according to claim 1, characterized in that: In S6, the heating time is the time required to heat the current temperature to the set temperature.