Air conditioning unit remote monitoring and energy efficiency analysis system based on Internet of Things

Abstract

The invention discloses an air conditioning unit remote monitoring and energy efficiency analysis system based on the Internet of Things, and relates to the technical field of the Internet of Things, and the system comprises an equipment virtual module which is used for setting a monitoring sensor and constructing a virtual equipment model; the unit monitoring module is used for monitoring equipment to obtain environment data and operation state data; the unit model module is used for generating a visual unit twinborn digital model of the air conditioning unit; the user model module is used for constructing a user-oriented user twinborn digital model; the energy efficiency analysis module is used for obtaining first energy efficiency data according to the unit twinning digital model and obtaining second energy efficiency data according to the user twinning digital model; and the comprehensive analysis module is used for obtaining target energy efficiency data according to the first energy efficiency data and the second energy efficiency data. The method has the effect of improving the efficiency and comprehensiveness of monitoring and energy efficiency analysis of the air conditioning unit.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to an IoT-based remote monitoring and energy efficiency analysis system for air conditioning units. Background Technology

[0002] Air conditioning is an indispensable tool in modern life, but people rarely pay attention to the operation and energy efficiency of the air conditioning unit. However, the air conditioning unit is the most important component when the air conditioner is running.

[0003] Currently, monitoring of air conditioning units typically relies on manual methods. When malfunctions occur, manual inspection, testing, and monitoring of the unit are essential, consuming significant manpower and resulting in low efficiency. Furthermore, energy efficiency monitoring is crucial for air conditioning performance; low-efficiency units lead to poor performance and substantial electricity waste. Traditional energy efficiency monitoring only tracks power consumption, rarely considering cooling or heating performance, leading to inaccurate data for energy efficiency analysis. Therefore, efficiently and comprehensively monitoring and analyzing the energy efficiency of air conditioning units remotely is a pressing issue. Summary of the Invention

[0004] The purpose of this invention is to provide a remote monitoring and energy efficiency analysis system for air conditioning units based on the Internet of Things, in order to solve the problems mentioned in the background art.

[0005] This application provides an Internet of Things-based remote monitoring and energy efficiency analysis system for air conditioning units, the system comprising: Virtual Equipment Module: Used to acquire the external shape parameters of the equipment within the air conditioning unit, set monitoring sensors according to the equipment model parameters, and construct a virtual equipment model based on the equipment external shape parameters; Unit monitoring module: used to call the monitoring sensors to perform environmental monitoring and operational status monitoring of the equipment in the air conditioning unit, and obtain environmental data and operational status data; Unit Model Module: Used to input the environmental data and the operating status data into the virtual equipment model to generate a visualized unit twin digital model of the air conditioning unit; User Model Module: Used to acquire user screen data, user text feedback and actual indoor and outdoor temperature data of users when the air conditioning unit is running, and to construct a user twin digital model based on the user screen data, user text feedback and actual indoor and outdoor temperature data; Energy efficiency analysis module: used to perform unit-oriented energy efficiency analysis based on the unit's digital twin model to obtain first energy efficiency data, and to perform user-oriented energy efficiency analysis based on the user's digital twin model to obtain second energy efficiency data; Comprehensive analysis module: used to comprehensively evaluate the energy efficiency parameters of the air conditioning unit based on the first energy efficiency data and the second energy efficiency data, and obtain the target energy efficiency data.

[0006] Preferably, the steps of obtaining the external shape parameters of the equipment within the air conditioning unit, setting monitoring sensors according to the equipment model parameters, and constructing a virtual equipment model based on the external shape parameters are as follows: Obtain the external shape parameters of the equipment inside the air conditioning unit, and obtain the spatial clearance data inside the air conditioning unit based on the external shape data of the equipment; Based on the spatial gap data, gap size data and gap distribution data are obtained. Based on the gap size data and gap distribution data, monitoring sensors are set in the spatial gap. A virtual internal space for the air conditioning unit is constructed, and a virtual device model is generated in the virtual internal space based on the device's external shape parameters.

[0007] Preferably, the step of calling the monitoring sensors to perform environmental monitoring and operational status monitoring of the equipment within the air conditioning unit, and obtaining environmental data and operational status data, specifically includes: The monitoring sensors are invoked to continuously monitor the environment and operating status of the equipment in the air conditioning unit, and initial environmental data and initial operating status data are obtained. The initial environmental data is classified to obtain temperature and humidity data and air composition data. The temperature and humidity data and air composition data are cleaned and initialized to obtain target temperature and humidity data and target air composition data. The environmental data is obtained by combining the target temperature and humidity data and the target air composition data. Based on the operating status data, the operating status data is decomposed to obtain energy consumption data and equipment status data; Energy consumption data is analyzed to identify energy loss and actual energy usage. Equipment status data is analyzed to identify the current energy utilization rate of the equipment. Based on the actual energy usage and the utilization rate, operating status data is obtained.

[0008] Preferably, the step of substituting the environmental data and the operating status data into the virtual device model to generate a visualized digital twin model of the air conditioning unit specifically includes: Based on the virtual device model, a virtual monitoring space is constructed for the virtual device model, and the environmental data and the operating status data are substituted into the virtual monitoring space; Based on the target temperature and humidity data, a visual temperature and humidity distribution map is generated, and the visual temperature and humidity distribution map is added to the virtual monitoring space; Based on the target air composition data, beneficial and harmful air components in the air are extracted, and the beneficial effects of the beneficial air components and the harmful effects of the harmful air components are identified. The beneficial and harmful effects are then substituted into the virtual monitoring space. Based on the operational status data, an operational status label is generated for each virtual device model, and the operational status label is affixed to the virtual device model. The operational status label includes energy flow parameters, operational heat generation parameters, operational efficiency parameters, and device health parameters.

[0009] Preferably, the step of constructing a user-oriented user twin digital model based on the user's screen data, the user's text feedback, and the actual indoor and outdoor temperature data specifically includes: Based on the user screen data, identify the distribution data and movement data of people in the building interior, and generate the first parameter of the user model based on the distribution data and movement data. Based on the user's text feedback, text content recognition is performed on the user's text feedback to obtain the user's usage preference parameters and usage suggestion parameters regarding air conditioner usage. Based on the usage preference parameters and usage suggestion parameters, a second parameter of the user model is generated. Based on the actual indoor and outdoor temperature data, indoor temperature distribution data and indoor and outdoor temperature difference data are obtained. Based on the indoor temperature distribution data and the indoor and outdoor temperature difference data, the third parameter of the user model is generated. Based on the first parameter, second parameter, and third parameter of the user model, a user-oriented twin digital model is constructed.

[0010] Preferably, the step of generating the first parameter of the user model based on the personnel distribution data and the personnel action data specifically includes: Based on the personnel distribution data, the gathering and dispersal of indoor personnel are identified to obtain areas where personnel gather and areas where personnel are scattered. Based on the personnel movement data, the movement recognition is performed on the personnel gathering area and the personnel scattering area to obtain the personnel's dressing and undressing movements and micro-movement warming movements, and the movement speed and movement frequency are recorded. Based on the speed and frequency of the person's actions of putting on and taking off clothes and the micro-motion heating action, determine the person's satisfaction with the temperature of their area; Using the satisfaction value as the parameter base point, and using the personnel distribution data, the personnel's dressing and undressing actions, and the speed and frequency of the micro-warming actions as parameter connection points, the parameter base point and the parameter connection points are connected to generate the first parameter of the user model.

[0011] Preferably, the step of performing text content recognition on the user's text feedback to obtain the user's usage preference parameters and usage suggestion parameters regarding air conditioner usage is as follows: The user's text feedback is subjected to text content recognition, and comfort keywords and pain keywords are extracted from the text; Extract the first text position of the comfort keyword in the text feedback, and perform contextual semantic recognition based on the first text position to obtain the user's usage preference parameters for air conditioning usage. Extract the second text position of the painful keywords in the text feedback, and perform contextual semantic recognition based on the second text position to obtain the user's usage suggestion parameters for air conditioner usage.

[0012] Preferably, the steps of performing unit-oriented energy efficiency analysis based on the unit's digital twin model to obtain first energy efficiency data, and performing user-oriented energy efficiency analysis based on the user's digital twin model to obtain second energy efficiency data, are as follows: Based on the unit's digital twin model, the unit's digital twin model is simulated and run, and data is monitored in the simulation environment to obtain unit simulation test data; Based on the unit's simulated test data, simulated consumption data and simulated heating / cooling values ​​of the unit's digital twin model are obtained. Based on the simulated consumption data and the simulated heating / cooling values, first energy efficiency data is obtained. Based on the user twin digital model, the simulated heating / cooling values ​​are substituted into the user twin digital model, the user twin digital model is simulated and run, and data is monitored in the simulation environment to obtain user simulation test data. Based on the user simulation test data, simulated user behavior and simulated user evaluation of the user twin digital model are obtained. Based on the simulated user behavior and simulated user evaluation, the energy efficiency value of the simulated heating / cooling value is evaluated to obtain the second energy efficiency data.

[0013] In summary, this application includes at least one of the following beneficial technical effects: By acquiring the external parameters of the equipment within the air conditioning unit, monitoring sensors are deployed on each device, and a virtual device model is constructed based on these parameters. Data monitoring of the equipment is then performed to obtain environmental and operational status data. This data is then input into the virtual device model to generate a visualized digital twin model of the unit. Next, user screen data, user text feedback, and actual indoor and outdoor temperature data are acquired during air conditioning unit operation to construct a user digital twin model. Simulation tests and energy efficiency analyses are then performed on both the unit and user digital twin models to obtain first-level energy efficiency data. Finally, simulation tests and energy efficiency analyses are performed on the user digital twin model to obtain second-level energy efficiency data. Combining the first and second energy efficiency data, the energy efficiency parameters of the air conditioning unit are comprehensively evaluated to obtain the target energy efficiency data. This approach improves the efficiency and comprehensiveness of air conditioning unit monitoring and energy efficiency analysis. Attached Figure Description

[0014] Figure 1 This is a block diagram of a remote monitoring and energy efficiency analysis system for air conditioning units based on the Internet of Things, provided in an embodiment of this application.

[0015] Explanation of reference numerals in the attached diagram: 1. Virtual Equipment Module; 2. Unit Monitoring Module; 3. Unit Model Module; 4. User Model Module; 5. Energy Efficiency Analysis Module; 6. Comprehensive Analysis Module. Detailed Implementation

[0016] The following is in conjunction with the appendix Figure 1 This application will be described in further detail, but the embodiments of the present invention are not limited thereto.

[0017] This application discloses an IoT-based remote monitoring and energy efficiency analysis system for air conditioning units.

[0018] In this embodiment, an IoT-based remote monitoring and energy efficiency analysis system for air conditioning units includes: Virtual Equipment Module 1: Used to acquire the external parameters of the equipment in the air conditioning unit, set monitoring sensors according to the equipment model parameters, and construct a virtual equipment model based on the external parameters of the equipment; Unit monitoring module 2: Used to call monitoring sensors to monitor the environment and operating status of the equipment in the air conditioning unit, and obtain environmental data and operating status data; Unit Model Module 3: Used to input environmental data and operating status data into the virtual equipment model to generate a visualized unit twin digital model of the air conditioning unit; User Model Module 4: Used to acquire user screen data, user text feedback and actual indoor and outdoor temperature data when the air conditioning unit is running, and to construct a user twin digital model based on the user screen data, user text feedback and actual indoor and outdoor temperature data. Energy efficiency analysis module 5: It is used to perform unit-oriented energy efficiency analysis based on the unit's twin digital model to obtain the first energy efficiency data, and to perform user-oriented energy efficiency analysis based on the user's twin digital model to obtain the second energy efficiency data. Comprehensive Analysis Module 6: Used to comprehensively evaluate the energy efficiency parameters of the air conditioning unit based on the first energy efficiency data and the second energy efficiency data, and obtain the target energy efficiency data.

[0019] The steps for obtaining the external parameters of the equipment within the air conditioning unit, setting monitoring sensors based on the equipment model parameters, and constructing a virtual equipment model based on the external parameters are as follows: Obtain the external shape parameters of the equipment inside the air conditioning unit, and based on the equipment external shape data, obtain the space clearance data inside the air conditioning unit; Based on the spatial gap data, the gap size data and gap distribution data are obtained. Based on the gap size data and gap distribution data, monitoring sensors are set in the spatial gap. Construct a virtual internal space for the air conditioning unit, and generate a virtual equipment model within the virtual internal space based on the equipment's external parameters.

[0020] In practice, taking a central air conditioning unit on the top floor of an office building as an example, when obtaining the external parameters of the equipment within the unit, the specific dimensions of the refrigeration compressor, condenser, evaporator, and fan are first measured. For example, the compressor is 80 cm long, 50 cm wide, and 60 cm high; the condenser is 120 cm long, 80 cm wide, and 40 cm high. Based on these external dimensions, the internal spatial clearances of the unit are analyzed. It is found that there is a 15 cm wide gap between the compressor and the condenser, and a 20 cm wide gap between the evaporator and the fan. Next, based on the gap size and distribution data, a temperature and humidity sensor is installed in the 15 cm wide gap, and an air composition detector is installed in the 20 cm wide gap. Then, a virtual internal space for the air conditioning unit is constructed, which is 3 meters long, 2 meters wide, and 2 meters high. Based on the equipment's external parameters, a virtual equipment model that matches the physical object is generated in the virtual internal space. For example, the 3D model of the compressor is placed in the upper left corner of the virtual space, the condenser model is placed on the right side, the evaporator model is placed in the lower left corner, and the fan model is placed in the lower right corner, ensuring that the model positions completely correspond to the actual layout.

[0021] The steps for using monitoring sensors to perform environmental and operational status monitoring of equipment within the air conditioning unit, and to obtain environmental and operational status data, are as follows: The monitoring sensors are invoked to continuously monitor the environment and operating status of the equipment in the air conditioning unit, and initial environmental data and initial operating status data are obtained. The initial environmental data is classified to obtain temperature and humidity data and air composition data. The temperature and humidity data and air composition data are cleaned and initialized to obtain target temperature and humidity data and target air composition data. The environmental data is obtained by combining the target temperature and humidity data and target air composition data. Based on the operational status data, the operational status data is decomposed to obtain energy consumption data and equipment status data; Energy consumption data is analyzed to identify energy loss and actual energy usage. Equipment status data is analyzed to identify the current energy utilization rate of the equipment. Based on the actual energy usage and utilization rate, the operating status data is obtained.

[0022] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, the deployed monitoring sensors continuously monitor the equipment within the unit. The temperature and humidity sensors collect data every 5 minutes, obtaining initial environmental data, such as a temperature of 25 degrees Celsius and humidity of 60%. The air composition detector collects data every 10 minutes, detecting a carbon dioxide concentration of 400 ppm and a formaldehyde concentration of 0.08 mg / m³. The initial environmental data is categorized: the temperature of 25 degrees Celsius and humidity of 60% are classified as temperature and humidity data, while the carbon dioxide and formaldehyde concentrations are classified as air composition data. The temperature and humidity data are cleaned, removing outliers caused by brief sensor malfunctions (such as a sudden temperature rise to 50 degrees Celsius), and the data is initialized to a standard format, resulting in target temperature and humidity data: a temperature of 24.8 degrees Celsius and humidity of 59.5%. The air composition data is initialized, resulting in target air composition data: a carbon dioxide concentration of 398 ppm and a formaldehyde concentration of 0.075 mg / m³. Combining these two types of data, a complete environmental data report is generated. Simultaneously, based on the operational status data, energy consumption data and equipment status data were extracted: energy consumption data showed that the unit consumed 15 kWh per hour, while equipment status data showed that the compressor's current speed was 2000 rpm and the fan's speed was 1500 rpm. Identifying the energy consumption data revealed an energy loss of 1 kWh per hour and an actual energy usage of 14 kWh per hour; identifying the equipment status data calculated the current energy utilization rate to be 85%. Based on the actual energy usage and utilization rate, an operational status data report was generated.

[0023] The steps for generating a visualized digital twin model of the air conditioning unit by inputting environmental data and operational status data into the virtual device model are as follows: Based on the virtual device model, a virtual monitoring space is constructed for the virtual device model, and environmental data and operating status data are substituted into the virtual monitoring space; Based on the target temperature and humidity data, a visual temperature and humidity distribution map is generated and added to the virtual monitoring space. Based on the target air composition data, the beneficial and harmful air components in the air are extracted, and the beneficial effects of the beneficial air components and the harmful effects of the harmful air components are identified. The beneficial and harmful effects are then substituted into the virtual monitoring space. Based on the operational status data, an operational status label is generated for each virtual device model. The operational status label is then affixed to the virtual device model. The operational status label includes energy flow parameters, operational heat generation parameters, operational efficiency parameters, and device health parameters.

[0024] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, environmental data and operational status data are substituted into the constructed virtual equipment model. First, a virtual monitoring space is created for the virtual equipment model. This space is 3 meters long, 2 meters wide, and 2 meters high, and the temperature of 24.8 degrees Celsius and humidity of 59.5% from the environmental data are substituted into the corresponding locations within the space. Based on the target temperature and humidity data, a visual temperature and humidity distribution map is generated: the upper left corner (compressor area) of the virtual space displays a temperature of 26 degrees Celsius and humidity of 58%, the right side (condenser area) displays a temperature of 24 degrees Celsius and humidity of 60%, and the lower left corner (evaporator area) displays a temperature of 25 degrees Celsius and humidity of 59%. This distribution map is added to the virtual monitoring space. Based on the target air composition data, beneficial air components (such as oxygen concentration of 21%) and harmful air components (such as formaldehyde concentration of 0.075 mg / m³) are extracted from the air. The beneficial effect of oxygen on human health is identified as maintaining normal breathing, and the harmful effect of formaldehyde on health is identified as potentially causing discomfort. These impacts are labeled at corresponding locations in the virtual monitoring space. Based on the operational status data, operational status labels are generated for each virtual device model: the compressor label shows an energy flow rate of 5 kWh per hour, an operating heat generation parameter of 40 degrees Celsius (surface temperature), an operating efficiency parameter of 90%, and a good health parameter; the condenser label shows an energy flow rate of 4 kWh per hour, an operating heat generation parameter of 35 degrees Celsius (surface temperature), an operating efficiency parameter of 85%, and a normal health parameter. These labels are then affixed to the corresponding virtual models.

[0025] The steps for constructing a user-oriented user twin digital model based on user screen data, user text feedback, and actual indoor and outdoor temperature data are as follows: Based on user screen data, identify the distribution data and movement data of people in the building interior, and generate the first parameter of the user model based on the distribution data and movement data. Based on user text feedback, text content recognition is performed on the user text feedback to obtain user preference parameters and usage suggestion parameters for air conditioner usage. Based on the user preference parameters and usage suggestion parameters, the second parameter of the user model is generated. Based on actual indoor and outdoor temperature data, indoor temperature distribution data and indoor and outdoor temperature difference data are obtained. Based on indoor temperature distribution data and indoor and outdoor temperature difference data, the third parameter of the user model is generated. Based on the first parameter, second parameter, and third parameter of the user model, a user-oriented twin digital model is constructed.

[0026] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, the system acquires user screen data, user text feedback, and actual indoor and outdoor temperature data during the operation of the air conditioning unit. User screen data comes from surveillance cameras in the office, identifying the distribution of people indoors as follows: 10 people gathered in the conference room, and 15 people scattered in the open office area. Personnel movement data shows that some people in the conference room frequently put on and took off their coats, while some people in the open office area rubbed their hands to warm them. Based on the personnel distribution and movement data, the first parameter of the user model is generated: the personnel concentration in the conference room is 10 people per square meter, and the movement frequency is 3 times per minute; the personnel dispersion in the open office area is 0.5 people per square meter, and the movement frequency is 1 time per minute. User text feedback comes from the company's internal feedback system. One feedback message reads: "The conference room is too cold; I hope the temperature can be increased. The temperature in the open office area is suitable, but it's a bit dry." Content recognition is performed on the text to extract the comfort keyword "suitable temperature" and the discomfort keywords "too cold" and "dry." Based on the contextual semantic recognition of the phrase "suitable temperature" within the text, the following usage preference parameters were obtained: the open office area temperature should be set to 24 degrees Celsius. Based on the location of phrases like "too cold" and "dry," the following usage suggestion parameters were obtained: the meeting room temperature should be adjusted to 26 degrees Celsius, and humidity should be increased. Actual indoor and outdoor temperature data showed an indoor temperature distribution of 23 degrees Celsius in the meeting room and 24 degrees Celsius in the open office area, with a temperature difference of 10 degrees Celsius. Based on the indoor temperature distribution and temperature difference data, the third parameter of the user model was generated: a temperature difference compensation value of +2 degrees Celsius for the meeting room and +1 degree Celsius for the open office area. Combining the first, second, and third parameters of the user model, a user twin digital model was constructed, which includes personnel distribution, action frequency, temperature preferences, and temperature difference compensation data.

[0027] The steps for generating the first parameter of the user model based on personnel distribution data and personnel action data are as follows: Based on the personnel distribution data, the gathering and dispersal of indoor personnel are identified to obtain areas where personnel gather and areas where personnel are scattered. Based on the personnel movement data, the movement recognition was performed in the areas where people gathered and the areas where people were scattered to obtain the people's actions of putting on and taking off clothes and their micro-movements to keep warm, and the speed and frequency of the movements were recorded. The satisfaction level of a person with the temperature in their area is determined by the speed and frequency of their actions of putting on and taking off clothes and making small movements to warm themselves. Using the satisfaction value as the parameter base point, and the speed and frequency of personnel distribution data, personnel's dressing and undressing actions, and micro-warming actions as parameter connection points, the parameter base point and parameter connection points are connected to generate the first parameter of the user model.

[0028] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, the gathering and dispersal of people indoors is identified based on personnel distribution data. A meeting room with an area of ​​30 square meters, with 10 people gathered, is identified as a gathering area with a density of 0.33 people per square meter; an open office area with an area of ​​100 square meters, with 15 people scattered around, is identified as a scattered area with a density of 0.15 people per square meter. Based on personnel movement data, action recognition is performed in these two areas: In the gathering area (meeting room), the action of putting on and taking off clothes is identified as 3 times per minute, with an average speed of 2 seconds per movement; the micro-warming action is rubbing hands, with a frequency of 5 times per minute and an average speed of 1 second per movement. In the scattered area (open office area), the action of putting on and taking off clothes is identified as 1 time per minute, with an average speed of 3 seconds per movement; the micro-warming action is stomping feet, with a frequency of 2 times per minute and an average speed of 2 seconds per movement. Based on the speed and frequency of dressing / undressing actions and micro-warming actions, the temperature satisfaction level of individuals in their respective areas was determined: 60 points for meeting rooms (frequent actions indicate discomfort), and 85 points for open office areas (fewer actions indicate relative comfort). Using this satisfaction level as the baseline parameter, and connecting the baseline parameter with data on personnel distribution (clustering density 0.33 people per square meter, dispersion density 0.15 people per square meter), dressing / undressing speed (2 seconds and 3 seconds respectively), and micro-warming action frequency (5 times per minute and 2 times per minute respectively), the user model's first parameter was generated. This parameter forms a network structure reflecting the correlation between personnel distribution, actions, and temperature satisfaction.

[0029] The steps for performing text content recognition on user feedback to obtain user preference parameters and suggested usage parameters regarding air conditioner usage are as follows: Perform text content recognition on user text feedback to extract comfort and pain keywords from the text; Extract the first text position of the comfort keyword in the text feedback, and perform contextual semantic recognition based on the first text position to obtain the user's usage preference parameters for air conditioning usage. Extract the second text position of painful keywords in the text feedback, and perform contextual semantic recognition based on the second text position to obtain usage suggestion parameters for the user's air conditioner usage.

[0030] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, text content recognition was performed on user feedback. The feedback text was: "The meeting room is too cold, my hands and feet are freezing; the open office area has a suitable temperature, but it's a bit dry in the afternoon, I hope it can be humidified." First, the comfort keyword "suitable temperature" and the pain keywords "too cold," "dry," and "freezing" were extracted from the text. The comfort keyword "suitable temperature" is located in the middle of the text. Based on its contextual semantic recognition, the open office area is mentioned earlier, and the dryness in the afternoon is mentioned later, so the user preference parameter is obtained: the open office area temperature is maintained at 24 degrees Celsius, and the user is satisfied with the current temperature. The pain keyword "too cold" is located at the beginning of the text, with the context pointing to the meeting room; "dry" is located at the end of the text, with the context pointing to the open office area in the afternoon; "freezing" further describes the feeling in the meeting room. Based on the second position of "too cold," semantic recognition was performed to obtain the suggested usage parameter: the meeting room temperature needs to be raised to 26 degrees Celsius, and air circulation should be increased. Based on the second position of "dry," another suggested usage parameter is obtained: the open office area needs to be humidified to 65% humidity in the afternoon. Meanwhile, the "cold" setting further emphasizes the problem of insufficient temperature in the conference room, suggesting the addition of a perceived temperature compensation feature. These parameters, when integrated, form a list of specific user needs regarding air conditioning usage.

[0031] The steps for performing unit-oriented energy efficiency analysis based on the unit's digital twin model to obtain the first energy efficiency data, and performing user-oriented energy efficiency analysis based on the user's digital twin model to obtain the second energy efficiency data, are as follows: Based on the unit's digital twin model, the unit's digital twin model is simulated and operated, and data is monitored in the simulation environment to obtain the unit's simulation test data; Based on the unit's simulated test data, the simulated consumption data and simulated heating / cooling values ​​of the unit's digital twin model are obtained. Based on the simulated consumption data and simulated heating / cooling values, the first energy efficiency data is obtained. Based on the user's digital twin model, simulated heating / cooling values ​​are substituted into the user's digital twin model to simulate its operation. Data monitoring is then performed in the simulation environment to obtain user simulation test data. Based on user simulation test data, simulated user behavior and simulated user evaluations are obtained from the user twin digital model. Based on the simulated user behavior and simulated user evaluations, the energy efficiency value of the simulated heating / cooling value is evaluated to obtain the second energy efficiency data.

[0032] In practice, taking the central air conditioning unit on the top floor of the same office building as an example, energy efficiency analysis of the unit is performed based on the unit's digital twin model. First, the unit's digital twin model is simulated: in the virtual environment, the external temperature is set to 35 degrees Celsius, the initial indoor temperature is 28 degrees Celsius, and the air conditioning unit runs for 1 hour. Data monitoring is performed in the simulation environment, obtaining the following simulated test data: the virtual compressor consumes 5 kWh, the virtual condenser consumes 4 kWh, the virtual evaporator produces 12 kW of cooling capacity, and the virtual fan consumes 1 kWh. Based on the simulated test data, the simulated power consumption data of the unit's digital twin model is obtained as a total power consumption of 10 kWh and a simulated cooling capacity of 12 kW. Based on the simulated power consumption data and the simulated cooling capacity, the first energy efficiency data is calculated: the energy efficiency ratio is 1.2 (cooling capacity of 12 kW divided by power consumption of 10 kWh). Next, the simulated cooling capacity of 12 kW was substituted into the user twin digital model, and the model was simulated: the required temperature for the meeting room was set at 26 degrees Celsius, and the required temperature for the open office area at 24 degrees Celsius, for one hour. User behavior data was monitored in the simulated environment: the frequency of users putting on and taking off clothes in the meeting room decreased to once per minute, and the frequency of users micro-adjusting heating in the open office area decreased to 0 times per minute. Simultaneously, simulated user evaluation data was collected: the satisfaction level in the meeting room increased to 80 points, and the satisfaction level in the open office area increased to 90 points. Based on the simulated user behavior and evaluations, the energy efficiency value of the simulated cooling capacity of 12 kW was evaluated: the average user satisfaction increased by 15 points, corresponding to an energy efficiency gain coefficient of 1.1. This yielded the second energy efficiency data: the user-oriented energy efficiency value was 1.32 (the first energy efficiency data of 1.2 multiplied by the gain coefficient of 1.1).

[0033] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An IoT-based remote monitoring and energy efficiency analysis system for air conditioning units, characterized in that, include: Virtual Equipment Module: Used to acquire the external shape parameters of the equipment within the air conditioning unit, set monitoring sensors according to the equipment model parameters, and construct a virtual equipment model based on the equipment external shape parameters; Unit monitoring module: used to call the monitoring sensors to perform environmental monitoring and operational status monitoring of the equipment in the air conditioning unit, and obtain environmental data and operational status data; Unit Model Module: Used to input the environmental data and the operating status data into the virtual equipment model to generate a visualized unit twin digital model of the air conditioning unit; User Model Module: Used to acquire user screen data, user text feedback and actual indoor and outdoor temperature data of users when the air conditioning unit is running, and to construct a user twin digital model based on the user screen data, user text feedback and actual indoor and outdoor temperature data; Energy efficiency analysis module: used to perform unit-oriented energy efficiency analysis based on the unit's digital twin model to obtain first energy efficiency data, and to perform user-oriented energy efficiency analysis based on the user's digital twin model to obtain second energy efficiency data; Comprehensive analysis module: used to comprehensively evaluate the energy efficiency parameters of the air conditioning unit based on the first energy efficiency data and the second energy efficiency data, and obtain the target energy efficiency data.

2. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 1, characterized in that, The steps of obtaining the external shape parameters of the equipment within the air conditioning unit, setting monitoring sensors according to the equipment model parameters, and constructing a virtual equipment model based on the external shape parameters are as follows: Obtain the external shape parameters of the equipment inside the air conditioning unit, and obtain the spatial clearance data inside the air conditioning unit based on the external shape data of the equipment; Based on the spatial gap data, gap size data and gap distribution data are obtained. Based on the gap size data and gap distribution data, monitoring sensors are set in the spatial gap. A virtual internal space for the air conditioning unit is constructed, and a virtual device model is generated in the virtual internal space based on the device's external shape parameters.

3. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 2, characterized in that, The steps for using the monitoring sensors to perform environmental and operational status monitoring of the equipment within the air conditioning unit, and to obtain environmental and operational status data, are as follows: The monitoring sensors are invoked to continuously monitor the environment and operating status of the equipment in the air conditioning unit, and initial environmental data and initial operating status data are obtained. The initial environmental data is classified to obtain temperature and humidity data and air composition data. The temperature and humidity data and air composition data are cleaned and initialized to obtain target temperature and humidity data and target air composition data. The environmental data is obtained by combining the target temperature and humidity data and the target air composition data. Based on the operating status data, the operating status data is decomposed to obtain energy consumption data and equipment status data; Energy consumption data is analyzed to identify energy loss and actual energy usage. Equipment status data is analyzed to identify the current energy utilization rate of the equipment. Based on the actual energy usage and the utilization rate, operating status data is obtained.

4. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 3, characterized in that, The steps of substituting the environmental data and the operating status data into the virtual device model to generate a visualized digital twin model of the air conditioning unit are as follows: Based on the virtual device model, a virtual monitoring space is constructed for the virtual device model, and the environmental data and the operating status data are substituted into the virtual monitoring space; Based on the target temperature and humidity data, a visual temperature and humidity distribution map is generated, and the visual temperature and humidity distribution map is added to the virtual monitoring space; Based on the target air composition data, beneficial and harmful air components in the air are extracted, and the beneficial effects of the beneficial air components and the harmful effects of the harmful air components are identified. The beneficial and harmful effects are then substituted into the virtual monitoring space. Based on the operational status data, an operational status label is generated for each virtual device model, and the operational status label is affixed to the virtual device model. The operational status label includes energy flow parameters, operational heat generation parameters, operational efficiency parameters, and device health parameters.

5. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 4, characterized in that, The steps for constructing a user-oriented user twin digital model based on the user's screen data, the user's text feedback, and the actual indoor and outdoor temperature data are as follows: Based on the user screen data, identify the distribution data and movement data of people in the building interior, and generate the first parameter of the user model based on the distribution data and movement data. Based on the user's text feedback, text content recognition is performed on the user's text feedback to obtain the user's usage preference parameters and usage suggestion parameters regarding air conditioner usage. Based on the usage preference parameters and usage suggestion parameters, a second parameter of the user model is generated. Based on the actual indoor and outdoor temperature data, indoor temperature distribution data and indoor and outdoor temperature difference data are obtained. Based on the indoor temperature distribution data and the indoor and outdoor temperature difference data, the third parameter of the user model is generated. Based on the first parameter, second parameter, and third parameter of the user model, a user-oriented twin digital model is constructed.

6. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 5, characterized in that, The step of generating the first parameter of the user model based on the personnel distribution data and the personnel action data is as follows: Based on the personnel distribution data, the gathering and dispersal of indoor personnel are identified to obtain areas where personnel gather and areas where personnel are scattered. Based on the personnel movement data, the movement recognition is performed on the personnel gathering area and the personnel scattering area to obtain the personnel's dressing and undressing movements and micro-movement warming movements, and the movement speed and movement frequency are recorded. Based on the speed and frequency of the person's actions of putting on and taking off clothes and the micro-motion heating action, determine the person's satisfaction with the temperature of their area; Using the satisfaction value as the parameter base point, and using the personnel distribution data, the personnel's dressing and undressing actions, and the speed and frequency of the micro-warming actions as parameter connection points, the parameter base point and the parameter connection points are connected to generate the first parameter of the user model.

7. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 6, characterized in that, The steps for performing text content recognition on the user's text feedback to obtain the user's usage preference parameters and usage suggestion parameters regarding air conditioner usage are as follows: The user's text feedback is subjected to text content recognition, and comfort keywords and pain keywords are extracted from the text; Extract the first text position of the comfort keyword in the text feedback, and perform contextual semantic recognition based on the first text position to obtain the user's usage preference parameters for air conditioning usage. Extract the second text position of the painful keywords in the text feedback, and perform contextual semantic recognition based on the second text position to obtain the user's usage suggestion parameters for air conditioner usage.

8. The IoT-based remote monitoring and energy efficiency analysis system for air conditioning units according to claim 7, characterized in that, The steps of performing unit-oriented energy efficiency analysis based on the unit's digital twin model to obtain first energy efficiency data, and performing user-oriented energy efficiency analysis based on the user's digital twin model to obtain second energy efficiency data, are as follows: Based on the unit's digital twin model, the unit's digital twin model is simulated and run, and data is monitored in the simulation environment to obtain unit simulation test data; Based on the unit's simulated test data, simulated consumption data and simulated heating / cooling values ​​of the unit's digital twin model are obtained. Based on the simulated consumption data and the simulated heating / cooling values, first energy efficiency data is obtained. Based on the user twin digital model, the simulated heating / cooling values ​​are substituted into the user twin digital model, the user twin digital model is simulated and run, and data is monitored in the simulation environment to obtain user simulation test data. Based on the user simulation test data, simulated user behavior and simulated user evaluation of the user twin digital model are obtained. Based on the simulated user behavior and simulated user evaluation, the energy efficiency value of the simulated heating / cooling value is evaluated to obtain the second energy efficiency data.

Images